Merge branch 'akpm' (patches from Andrew)

Merge second patch-bomb from Andrew Morton:

 - most of the rest of MM

 - procfs

 - lib/ updates

 - printk updates

 - bitops infrastructure tweaks

 - checkpatch updates

 - nilfs2 update

 - signals

 - various other misc bits: coredump, seqfile, kexec, pidns, zlib, ipc,
   dma-debug, dma-mapping, ...

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (102 commits)
  ipc,msg: drop dst nil validation in copy_msg
  include/linux/zutil.h: fix usage example of zlib_adler32()
  panic: release stale console lock to always get the logbuf printed out
  dma-debug: check nents in dma_sync_sg*
  dma-mapping: tidy up dma_parms default handling
  pidns: fix set/getpriority and ioprio_set/get in PRIO_USER mode
  kexec: use file name as the output message prefix
  fs, seqfile: always allow oom killer
  seq_file: reuse string_escape_str()
  fs/seq_file: use seq_* helpers in seq_hex_dump()
  coredump: change zap_threads() and zap_process() to use for_each_thread()
  coredump: ensure all coredumping tasks have SIGNAL_GROUP_COREDUMP
  signal: remove jffs2_garbage_collect_thread()->allow_signal(SIGCONT)
  signal: introduce kernel_signal_stop() to fix jffs2_garbage_collect_thread()
  signal: turn dequeue_signal_lock() into kernel_dequeue_signal()
  signals: kill block_all_signals() and unblock_all_signals()
  nilfs2: fix gcc uninitialized-variable warnings in powerpc build
  nilfs2: fix gcc unused-but-set-variable warnings
  MAINTAINERS: nilfs2: add header file for tracing
  nilfs2: add tracepoints for analyzing reading and writing metadata files
  ...

24 files changed, 598 insertions, 341 deletions

diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 8b5ce7c5d9bb..f56cdcecc1c9 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -822,7 +822,6 @@ struct drm_device {
 
 	struct drm_sg_mem *sg;	/**< Scatter gather memory */
 	unsigned int num_crtcs;                  /**< Number of CRTCs on this device */
-	sigset_t sigmask;
 
 	struct {
 		int context;
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index e63553386ae7..2b8ed123ad36 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -164,6 +164,8 @@ static inline __u8 ror8(__u8 word, unsigned int shift)
  * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit
  * @value: value to sign extend
  * @index: 0 based bit index (0<=index<32) to sign bit
+ *
+ * This is safe to use for 16- and 8-bit types as well.
  */
 static inline __s32 sign_extend32(__u32 value, int index)
 {
@@ -171,6 +173,17 @@ static inline __s32 sign_extend32(__u32 value, int index)
 	return (__s32)(value << shift) >> shift;
 }
 
+/**
+ * sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit
+ * @value: value to sign extend
+ * @index: 0 based bit index (0<=index<64) to sign bit
+ */
+static inline __s64 sign_extend64(__u64 value, int index)
+{
+	__u8 shift = 63 - index;
+	return (__s64)(value << shift) >> shift;
+}
+
 static inline unsigned fls_long(unsigned long l)
 {
 	if (sizeof(l) == 4)
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 0e3110a0b771..22ab246feed3 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -205,7 +205,10 @@
 
 #if GCC_VERSION >= 40600
 /*
- * Tell the optimizer that something else uses this function or variable.
+ * When used with Link Time Optimization, gcc can optimize away C functions or
+ * variables which are referenced only from assembly code.  __visible tells the
+ * optimizer that something else uses this function or variable, thus preventing
+ * this.
  */
 #define __visible	__attribute__((externally_visible))
 #endif
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 5a1311942358..85a868ccb493 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -104,6 +104,9 @@ extern void cpuset_print_current_mems_allowed(void);
  */
 static inline unsigned int read_mems_allowed_begin(void)
 {
+	if (!cpusets_enabled())
+		return 0;
+
 	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
@@ -115,6 +118,9 @@ static inline unsigned int read_mems_allowed_begin(void)
  */
 static inline bool read_mems_allowed_retry(unsigned int seq)
 {
+	if (!cpusets_enabled())
+		return false;
+
 	return read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index ac07ff090919..2e551e2d2d03 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -1,6 +1,7 @@
 #ifndef _LINUX_DMA_MAPPING_H
 #define _LINUX_DMA_MAPPING_H
 
+#include <linux/sizes.h>
 #include <linux/string.h>
 #include <linux/device.h>
 #include <linux/err.h>
@@ -145,7 +146,9 @@ static inline void arch_teardown_dma_ops(struct device *dev) { }
 
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
-	return dev->dma_parms ? dev->dma_parms->max_segment_size : 65536;
+	if (dev->dma_parms && dev->dma_parms->max_segment_size)
+		return dev->dma_parms->max_segment_size;
+	return SZ_64K;
 }
 
 static inline unsigned int dma_set_max_seg_size(struct device *dev,
@@ -154,14 +157,15 @@ static inline unsigned int dma_set_max_seg_size(struct device *dev,
 	if (dev->dma_parms) {
 		dev->dma_parms->max_segment_size = size;
 		return 0;
-	} else
-		return -EIO;
+	}
+	return -EIO;
 }
 
 static inline unsigned long dma_get_seg_boundary(struct device *dev)
 {
-	return dev->dma_parms ?
-		dev->dma_parms->segment_boundary_mask : 0xffffffff;
+	if (dev->dma_parms && dev->dma_parms->segment_boundary_mask)
+		return dev->dma_parms->segment_boundary_mask;
+	return DMA_BIT_MASK(32);
 }
 
 static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
@@ -169,8 +173,8 @@ static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
 	if (dev->dma_parms) {
 		dev->dma_parms->segment_boundary_mask = mask;
 		return 0;
-	} else
-		return -EIO;
+	}
+	return -EIO;
 }
 
 #ifndef dma_max_pfn
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f92cbd2f4450..6523109e136d 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -14,7 +14,7 @@ struct vm_area_struct;
 #define ___GFP_HIGHMEM		0x02u
 #define ___GFP_DMA32		0x04u
 #define ___GFP_MOVABLE		0x08u
-#define ___GFP_WAIT		0x10u
+#define ___GFP_RECLAIMABLE	0x10u
 #define ___GFP_HIGH		0x20u
 #define ___GFP_IO		0x40u
 #define ___GFP_FS		0x80u
@@ -29,18 +29,17 @@ struct vm_area_struct;
 #define ___GFP_NOMEMALLOC	0x10000u
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
-#define ___GFP_RECLAIMABLE	0x80000u
+#define ___GFP_ATOMIC		0x80000u
 #define ___GFP_NOACCOUNT	0x100000u
 #define ___GFP_NOTRACK		0x200000u
-#define ___GFP_NO_KSWAPD	0x400000u
+#define ___GFP_DIRECT_RECLAIM	0x400000u
 #define ___GFP_OTHER_NODE	0x800000u
 #define ___GFP_WRITE		0x1000000u
+#define ___GFP_KSWAPD_RECLAIM	0x2000000u
 /* If the above are modified, __GFP_BITS_SHIFT may need updating */
 
 /*
- * GFP bitmasks..
- *
- * Zone modifiers (see linux/mmzone.h - low three bits)
+ * Physical address zone modifiers (see linux/mmzone.h - low four bits)
  *
  * Do not put any conditional on these. If necessary modify the definitions
  * without the underscores and use them consistently. The definitions here may
@@ -50,116 +49,229 @@ struct vm_area_struct;
 #define __GFP_HIGHMEM	((__force gfp_t)___GFP_HIGHMEM)
 #define __GFP_DMA32	((__force gfp_t)___GFP_DMA32)
 #define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* Page is movable */
+#define __GFP_MOVABLE	((__force gfp_t)___GFP_MOVABLE)  /* ZONE_MOVABLE allowed */
 #define GFP_ZONEMASK	(__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE)
+
+/*
+ * Page mobility and placement hints
+ *
+ * These flags provide hints about how mobile the page is. Pages with similar
+ * mobility are placed within the same pageblocks to minimise problems due
+ * to external fragmentation.
+ *
+ * __GFP_MOVABLE (also a zone modifier) indicates that the page can be
+ *   moved by page migration during memory compaction or can be reclaimed.
+ *
+ * __GFP_RECLAIMABLE is used for slab allocations that specify
+ *   SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers.
+ *
+ * __GFP_WRITE indicates the caller intends to dirty the page. Where possible,
+ *   these pages will be spread between local zones to avoid all the dirty
+ *   pages being in one zone (fair zone allocation policy).
+ *
+ * __GFP_HARDWALL enforces the cpuset memory allocation policy.
+ *
+ * __GFP_THISNODE forces the allocation to be satisified from the requested
+ *   node with no fallbacks or placement policy enforcements.
+ */
+#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
+#define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
+#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL)
+#define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)
+
 /*
- * Action modifiers - doesn't change the zoning
+ * Watermark modifiers -- controls access to emergency reserves
+ *
+ * __GFP_HIGH indicates that the caller is high-priority and that granting
+ *   the request is necessary before the system can make forward progress.
+ *   For example, creating an IO context to clean pages.
+ *
+ * __GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is
+ *   high priority. Users are typically interrupt handlers. This may be
+ *   used in conjunction with __GFP_HIGH
+ *
+ * __GFP_MEMALLOC allows access to all memory. This should only be used when
+ *   the caller guarantees the allocation will allow more memory to be freed
+ *   very shortly e.g. process exiting or swapping. Users either should
+ *   be the MM or co-ordinating closely with the VM (e.g. swap over NFS).
+ *
+ * __GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves.
+ *   This takes precedence over the __GFP_MEMALLOC flag if both are set.
+ *
+ * __GFP_NOACCOUNT ignores the accounting for kmemcg limit enforcement.
+ */
+#define __GFP_ATOMIC	((__force gfp_t)___GFP_ATOMIC)
+#define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)
+#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)
+#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC)
+#define __GFP_NOACCOUNT	((__force gfp_t)___GFP_NOACCOUNT)
+
+/*
+ * Reclaim modifiers
+ *
+ * __GFP_IO can start physical IO.
+ *
+ * __GFP_FS can call down to the low-level FS. Clearing the flag avoids the
+ *   allocator recursing into the filesystem which might already be holding
+ *   locks.
+ *
+ * __GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim.
+ *   This flag can be cleared to avoid unnecessary delays when a fallback
+ *   option is available.
+ *
+ * __GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when
+ *   the low watermark is reached and have it reclaim pages until the high
+ *   watermark is reached. A caller may wish to clear this flag when fallback
+ *   options are available and the reclaim is likely to disrupt the system. The
+ *   canonical example is THP allocation where a fallback is cheap but
+ *   reclaim/compaction may cause indirect stalls.
+ *
+ * __GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
  * __GFP_REPEAT: Try hard to allocate the memory, but the allocation attempt
- * _might_ fail.  This depends upon the particular VM implementation.
+ *   _might_ fail.  This depends upon the particular VM implementation.
  *
  * __GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller
- * cannot handle allocation failures. New users should be evaluated carefully
- * (and the flag should be used only when there is no reasonable failure policy)
- * but it is definitely preferable to use the flag rather than opencode endless
- * loop around allocator.
+ *   cannot handle allocation failures. New users should be evaluated carefully
+ *   (and the flag should be used only when there is no reasonable failure
+ *   policy) but it is definitely preferable to use the flag rather than
+ *   opencode endless loop around allocator.
  *
  * __GFP_NORETRY: The VM implementation must not retry indefinitely and will
- * return NULL when direct reclaim and memory compaction have failed to allow
- * the allocation to succeed.  The OOM killer is not called with the current
- * implementation.
- *
- * __GFP_MOVABLE: Flag that this page will be movable by the page migration
- * mechanism or reclaimed
+ *   return NULL when direct reclaim and memory compaction have failed to allow
+ *   the allocation to succeed.  The OOM killer is not called with the current
+ *   implementation.
  */
-#define __GFP_WAIT	((__force gfp_t)___GFP_WAIT)	/* Can wait and reschedule? */
-#define __GFP_HIGH	((__force gfp_t)___GFP_HIGH)	/* Should access emergency pools? */
-#define __GFP_IO	((__force gfp_t)___GFP_IO)	/* Can start physical IO? */
-#define __GFP_FS	((__force gfp_t)___GFP_FS)	/* Can call down to low-level FS? */
-#define __GFP_COLD	((__force gfp_t)___GFP_COLD)	/* Cache-cold page required */
-#define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)	/* Suppress page allocation failure warning */
-#define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)	/* See above */
-#define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)	/* See above */
-#define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY) /* See above */
-#define __GFP_MEMALLOC	((__force gfp_t)___GFP_MEMALLOC)/* Allow access to emergency reserves */
-#define __GFP_COMP	((__force gfp_t)___GFP_COMP)	/* Add compound page metadata */
-#define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)	/* Return zeroed page on success */
-#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) /* Don't use emergency reserves.
-							 * This takes precedence over the
-							 * __GFP_MEMALLOC flag if both are
-							 * set
-							 */
-#define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL) /* Enforce hardwall cpuset memory allocs */
-#define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)/* No fallback, no policies */
-#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
-#define __GFP_NOACCOUNT	((__force gfp_t)___GFP_NOACCOUNT) /* Don't account to kmemcg */
-#define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)  /* Don't track with kmemcheck */
-
-#define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
-#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
-#define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
+#define __GFP_IO	((__force gfp_t)___GFP_IO)
+#define __GFP_FS	((__force gfp_t)___GFP_FS)
+#define __GFP_DIRECT_RECLAIM	((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */
+#define __GFP_KSWAPD_RECLAIM	((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */
+#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM))
+#define __GFP_REPEAT	((__force gfp_t)___GFP_REPEAT)
+#define __GFP_NOFAIL	((__force gfp_t)___GFP_NOFAIL)
+#define __GFP_NORETRY	((__force gfp_t)___GFP_NORETRY)
 
 /*
- * This may seem redundant, but it's a way of annotating false positives vs.
- * allocations that simply cannot be supported (e.g. page tables).
+ * Action modifiers
+ *
+ * __GFP_COLD indicates that the caller does not expect to be used in the near
+ *   future. Where possible, a cache-cold page will be returned.
+ *
+ * __GFP_NOWARN suppresses allocation failure reports.
+ *
+ * __GFP_COMP address compound page metadata.
+ *
+ * __GFP_ZERO returns a zeroed page on success.
+ *
+ * __GFP_NOTRACK avoids tracking with kmemcheck.
+ *
+ * __GFP_NOTRACK_FALSE_POSITIVE is an alias of __GFP_NOTRACK. It's a means of
+ *   distinguishing in the source between false positives and allocations that
+ *   cannot be supported (e.g. page tables).
+ *
+ * __GFP_OTHER_NODE is for allocations that are on a remote node but that
+ *   should not be accounted for as a remote allocation in vmstat. A
+ *   typical user would be khugepaged collapsing a huge page on a remote
+ *   node.
  */
+#define __GFP_COLD	((__force gfp_t)___GFP_COLD)
+#define __GFP_NOWARN	((__force gfp_t)___GFP_NOWARN)
+#define __GFP_COMP	((__force gfp_t)___GFP_COMP)
+#define __GFP_ZERO	((__force gfp_t)___GFP_ZERO)
+#define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
+#define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE)
 
-#define __GFP_BITS_SHIFT 25	/* Room for N __GFP_FOO bits */
+/* Room for N __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 26
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
-/* This equals 0, but use constants in case they ever change */
-#define GFP_NOWAIT	(GFP_ATOMIC & ~__GFP_HIGH)
-/* GFP_ATOMIC means both !wait (__GFP_WAIT not set) and use emergency pool */
-#define GFP_ATOMIC	(__GFP_HIGH)
-#define GFP_NOIO	(__GFP_WAIT)
-#define GFP_NOFS	(__GFP_WAIT | __GFP_IO)
-#define GFP_KERNEL	(__GFP_WAIT | __GFP_IO | __GFP_FS)
-#define GFP_TEMPORARY	(__GFP_WAIT | __GFP_IO | __GFP_FS | \
+/*
+ * Useful GFP flag combinations that are commonly used. It is recommended
+ * that subsystems start with one of these combinations and then set/clear
+ * __GFP_FOO flags as necessary.
+ *
+ * GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower
+ *   watermark is applied to allow access to "atomic reserves"
+ *
+ * GFP_KERNEL is typical for kernel-internal allocations. The caller requires
+ *   ZONE_NORMAL or a lower zone for direct access but can direct reclaim.
+ *
+ * GFP_NOWAIT is for kernel allocations that should not stall for direct
+ *   reclaim, start physical IO or use any filesystem callback.
+ *
+ * GFP_NOIO will use direct reclaim to discard clean pages or slab pages
+ *   that do not require the starting of any physical IO.
+ *
+ * GFP_NOFS will use direct reclaim but will not use any filesystem interfaces.
+ *
+ * GFP_USER is for userspace allocations that also need to be directly
+ *   accessibly by the kernel or hardware. It is typically used by hardware
+ *   for buffers that are mapped to userspace (e.g. graphics) that hardware
+ *   still must DMA to. cpuset limits are enforced for these allocations.
+ *
+ * GFP_DMA exists for historical reasons and should be avoided where possible.
+ *   The flags indicates that the caller requires that the lowest zone be
+ *   used (ZONE_DMA or 16M on x86-64). Ideally, this would be removed but
+ *   it would require careful auditing as some users really require it and
+ *   others use the flag to avoid lowmem reserves in ZONE_DMA and treat the
+ *   lowest zone as a type of emergency reserve.
+ *
+ * GFP_DMA32 is similar to GFP_DMA except that the caller requires a 32-bit
+ *   address.
+ *
+ * GFP_HIGHUSER is for userspace allocations that may be mapped to userspace,
+ *   do not need to be directly accessible by the kernel but that cannot
+ *   move once in use. An example may be a hardware allocation that maps
+ *   data directly into userspace but has no addressing limitations.
+ *
+ * GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not
+ *   need direct access to but can use kmap() when access is required. They
+ *   are expected to be movable via page reclaim or page migration. Typically,
+ *   pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE.
+ *
+ * GFP_TRANSHUGE is used for THP allocations. They are compound allocations
+ *   that will fail quickly if memory is not available and will not wake
+ *   kswapd on failure.
+ */
+#define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
+#define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+#define GFP_NOIO	(__GFP_RECLAIM)
+#define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
+#define GFP_TEMPORARY	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | \
 			 __GFP_RECLAIMABLE)
-#define GFP_USER	(__GFP_WAIT | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
+#define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
+#define GFP_DMA		__GFP_DMA
+#define GFP_DMA32	__GFP_DMA32
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
 #define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
-#define GFP_IOFS	(__GFP_IO | __GFP_FS)
-#define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
-			 __GFP_NO_KSWAPD)
+#define GFP_TRANSHUGE	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
+			 ~__GFP_KSWAPD_RECLAIM)
 
-/* This mask makes up all the page movable related flags */
+/* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
+#define GFP_MOVABLE_SHIFT 3
 
-/* Control page allocator reclaim behavior */
-#define GFP_RECLAIM_MASK (__GFP_WAIT|__GFP_HIGH|__GFP_IO|__GFP_FS|\
-			__GFP_NOWARN|__GFP_REPEAT|__GFP_NOFAIL|\
-			__GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC)
-
-/* Control slab gfp mask during early boot */
-#define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_WAIT|__GFP_IO|__GFP_FS))
-
-/* Control allocation constraints */
-#define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE)
-
-/* Do not use these with a slab allocator */
-#define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK)
-
-/* Flag - indicates that the buffer will be suitable for DMA.  Ignored on some
-   platforms, used as appropriate on others */
-
-#define GFP_DMA		__GFP_DMA
-
-/* 4GB DMA on some platforms */
-#define GFP_DMA32	__GFP_DMA32
-
-/* Convert GFP flags to their corresponding migrate type */
 static inline int gfpflags_to_migratetype(const gfp_t gfp_flags)
 {
-	WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
+	VM_WARN_ON((gfp_flags & GFP_MOVABLE_MASK) == GFP_MOVABLE_MASK);
+	BUILD_BUG_ON((1UL << GFP_MOVABLE_SHIFT) != ___GFP_MOVABLE);
+	BUILD_BUG_ON((___GFP_MOVABLE >> GFP_MOVABLE_SHIFT) != MIGRATE_MOVABLE);
 
 	if (unlikely(page_group_by_mobility_disabled))
 		return MIGRATE_UNMOVABLE;
 
 	/* Group based on mobility */
-	return (((gfp_flags & __GFP_MOVABLE) != 0) << 1) |
-		((gfp_flags & __GFP_RECLAIMABLE) != 0);
+	return (gfp_flags & GFP_MOVABLE_MASK) >> GFP_MOVABLE_SHIFT;
+}
+#undef GFP_MOVABLE_MASK
+#undef GFP_MOVABLE_SHIFT
+
+static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
+{
+	return gfp_flags & __GFP_DIRECT_RECLAIM;
 }
 
 #ifdef CONFIG_HIGHMEM
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 7edd30515298..24154c26d469 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -32,7 +32,7 @@ static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
 
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return NULL;
-	return (struct hugetlb_cgroup *)page[2].lru.next;
+	return (struct hugetlb_cgroup *)page[2].private;
 }
 
 static inline
@@ -42,7 +42,7 @@ int set_hugetlb_cgroup(struct page *page, struct hugetlb_cgroup *h_cg)
 
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return -1;
-	page[2].lru.next = (void *)h_cg;
+	page[2].private	= (unsigned long)h_cg;
 	return 0;
 }
 
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 5582410727cb..2c13f747ac2e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -413,6 +413,8 @@ extern __printf(2, 3)
 char *kasprintf(gfp_t gfp, const char *fmt, ...);
 extern __printf(2, 0)
 char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
+extern __printf(2, 0)
+const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args);
 
 extern __scanf(2, 3)
 int sscanf(const char *, const char *, ...);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 906c46a05707..00bad7793788 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -430,46 +430,6 @@ static inline void compound_unlock_irqrestore(struct page *page,
 #endif
 }
 
-static inline struct page *compound_head_by_tail(struct page *tail)
-{
-	struct page *head = tail->first_page;
-
-	/*
-	 * page->first_page may be a dangling pointer to an old
-	 * compound page, so recheck that it is still a tail
-	 * page before returning.
-	 */
-	smp_rmb();
-	if (likely(PageTail(tail)))
-		return head;
-	return tail;
-}
-
-/*
- * Since either compound page could be dismantled asynchronously in THP
- * or we access asynchronously arbitrary positioned struct page, there
- * would be tail flag race. To handle this race, we should call
- * smp_rmb() before checking tail flag. compound_head_by_tail() did it.
- */
-static inline struct page *compound_head(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return compound_head_by_tail(page);
-	return page;
-}
-
-/*
- * If we access compound page synchronously such as access to
- * allocated page, there is no need to handle tail flag race, so we can
- * check tail flag directly without any synchronization primitive.
- */
-static inline struct page *compound_head_fast(struct page *page)
-{
-	if (unlikely(PageTail(page)))
-		return page->first_page;
-	return page;
-}
-
 /*
  * The atomic page->_mapcount, starts from -1: so that transitions
  * both from it and to it can be tracked, using atomic_inc_and_test
@@ -518,7 +478,7 @@ static inline void get_huge_page_tail(struct page *page)
 	VM_BUG_ON_PAGE(!PageTail(page), page);
 	VM_BUG_ON_PAGE(page_mapcount(page) < 0, page);
 	VM_BUG_ON_PAGE(atomic_read(&page->_count) != 0, page);
-	if (compound_tail_refcounted(page->first_page))
+	if (compound_tail_refcounted(compound_head(page)))
 		atomic_inc(&page->_mapcount);
 }
 
@@ -541,13 +501,7 @@ static inline struct page *virt_to_head_page(const void *x)
 {
 	struct page *page = virt_to_page(x);
 
-	/*
-	 * We don't need to worry about synchronization of tail flag
-	 * when we call virt_to_head_page() since it is only called for
-	 * already allocated page and this page won't be freed until
-	 * this virt_to_head_page() is finished. So use _fast variant.
-	 */
-	return compound_head_fast(page);
+	return compound_head(page);
 }
 
 /*
@@ -568,28 +522,42 @@ int split_free_page(struct page *page);
 /*
  * Compound pages have a destructor function.  Provide a
  * prototype for that function and accessor functions.
- * These are _only_ valid on the head of a PG_compound page.
+ * These are _only_ valid on the head of a compound page.
  */
+typedef void compound_page_dtor(struct page *);
+
+/* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */
+enum compound_dtor_id {
+	NULL_COMPOUND_DTOR,
+	COMPOUND_PAGE_DTOR,
+#ifdef CONFIG_HUGETLB_PAGE
+	HUGETLB_PAGE_DTOR,
+#endif
+	NR_COMPOUND_DTORS,
+};
+extern compound_page_dtor * const compound_page_dtors[];
 
 static inline void set_compound_page_dtor(struct page *page,
-						compound_page_dtor *dtor)
+		enum compound_dtor_id compound_dtor)
 {
-	page[1].compound_dtor = dtor;
+	VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page);
+	page[1].compound_dtor = compound_dtor;
 }
 
 static inline compound_page_dtor *get_compound_page_dtor(struct page *page)
 {
-	return page[1].compound_dtor;
+	VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page);
+	return compound_page_dtors[page[1].compound_dtor];
 }
 
-static inline int compound_order(struct page *page)
+static inline unsigned int compound_order(struct page *page)
 {
 	if (!PageHead(page))
 		return 0;
 	return page[1].compound_order;
 }
 
-static inline void set_compound_order(struct page *page, unsigned long order)
+static inline void set_compound_order(struct page *page, unsigned int order)
 {
 	page[1].compound_order = order;
 }
@@ -1572,8 +1540,7 @@ static inline bool ptlock_init(struct page *page)
 	 * with 0. Make sure nobody took it in use in between.
 	 *
 	 * It can happen if arch try to use slab for page table allocation:
-	 * slab code uses page->slab_cache and page->first_page (for tail
-	 * pages), which share storage with page->ptl.
+	 * slab code uses page->slab_cache, which share storage with page->ptl.
 	 */
 	VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page);
 	if (!ptlock_alloc(page))
@@ -1843,7 +1810,8 @@ extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
 
 extern __printf(3, 4)
-void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...);
+void warn_alloc_failed(gfp_t gfp_mask, unsigned int order,
+		const char *fmt, ...);
 
 extern void setup_per_cpu_pageset(void);
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 0a85da25a822..f8d1492a114f 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -28,8 +28,6 @@ struct mem_cgroup;
 		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 #define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
 
-typedef void compound_page_dtor(struct page *);
-
 /*
  * Each physical page in the system has a struct page associated with
  * it to keep track of whatever it is we are using the page for at the
@@ -113,7 +111,13 @@ struct page {
 		};
 	};
 
-	/* Third double word block */
+	/*
+	 * Third double word block
+	 *
+	 * WARNING: bit 0 of the first word encode PageTail(). That means
+	 * the rest users of the storage space MUST NOT use the bit to
+	 * avoid collision and false-positive PageTail().
+	 */
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
 					 * protected by zone->lru_lock !
@@ -131,18 +135,37 @@ struct page {
 #endif
 		};
 
-		struct slab *slab_page; /* slab fields */
 		struct rcu_head rcu_head;	/* Used by SLAB
 						 * when destroying via RCU
 						 */
-		/* First tail page of compound page */
+		/* Tail pages of compound page */
 		struct {
-			compound_page_dtor *compound_dtor;
-			unsigned long compound_order;
+			unsigned long compound_head; /* If bit zero is set */
+
+			/* First tail page only */
+#ifdef CONFIG_64BIT
+			/*
+			 * On 64 bit system we have enough space in struct page
+			 * to encode compound_dtor and compound_order with
+			 * unsigned int. It can help compiler generate better or
+			 * smaller code on some archtectures.
+			 */
+			unsigned int compound_dtor;
+			unsigned int compound_order;
+#else
+			unsigned short int compound_dtor;
+			unsigned short int compound_order;
+#endif
 		};
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && USE_SPLIT_PMD_PTLOCKS
-		pgtable_t pmd_huge_pte; /* protected by page->ptl */
+		struct {
+			unsigned long __pad;	/* do not overlay pmd_huge_pte
+						 * with compound_head to avoid
+						 * possible bit 0 collision.
+						 */
+			pgtable_t pmd_huge_pte; /* protected by page->ptl */
+		};
 #endif
 	};
 
@@ -163,7 +186,6 @@ struct page {
 #endif
 #endif
 		struct kmem_cache *slab_cache;	/* SL[AU]B: Pointer to slab */
-		struct page *first_page;	/* Compound tail pages */
 	};
 
 #ifdef CONFIG_MEMCG
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2d7e660cdefe..e23a9e704536 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -37,10 +37,10 @@
 
 enum {
 	MIGRATE_UNMOVABLE,
-	MIGRATE_RECLAIMABLE,
 	MIGRATE_MOVABLE,
+	MIGRATE_RECLAIMABLE,
 	MIGRATE_PCPTYPES,	/* the number of types on the pcp lists */
-	MIGRATE_RESERVE = MIGRATE_PCPTYPES,
+	MIGRATE_HIGHATOMIC = MIGRATE_PCPTYPES,
 #ifdef CONFIG_CMA
 	/*
 	 * MIGRATE_CMA migration type is designed to mimic the way
@@ -334,13 +334,16 @@ struct zone {
 	/* zone watermarks, access with *_wmark_pages(zone) macros */
 	unsigned long watermark[NR_WMARK];
 
+	unsigned long nr_reserved_highatomic;
+
 	/*
-	 * We don't know if the memory that we're going to allocate will be freeable
-	 * or/and it will be released eventually, so to avoid totally wasting several
-	 * GB of ram we must reserve some of the lower zone memory (otherwise we risk
-	 * to run OOM on the lower zones despite there's tons of freeable ram
-	 * on the higher zones). This array is recalculated at runtime if the
-	 * sysctl_lowmem_reserve_ratio sysctl changes.
+	 * We don't know if the memory that we're going to allocate will be
+	 * freeable or/and it will be released eventually, so to avoid totally
+	 * wasting several GB of ram we must reserve some of the lower zone
+	 * memory (otherwise we risk to run OOM on the lower zones despite
+	 * there being tons of freeable ram on the higher zones).  This array is
+	 * recalculated at runtime if the sysctl_lowmem_reserve_ratio sysctl
+	 * changes.
 	 */
 	long lowmem_reserve[MAX_NR_ZONES];
 
@@ -429,12 +432,6 @@ struct zone {
 
 	const char		*name;
 
-	/*
-	 * Number of MIGRATE_RESERVE page block. To maintain for just
-	 * optimization. Protected by zone->lock.
-	 */
-	int			nr_migrate_reserve_block;
-
 #ifdef CONFIG_MEMORY_ISOLATION
 	/*
 	 * Number of isolated pageblock. It is used to solve incorrect
@@ -589,75 +586,8 @@ static inline bool zone_is_empty(struct zone *zone)
  * [1]	: No fallback (__GFP_THISNODE)
  */
 #define MAX_ZONELISTS 2
-
-
-/*
- * We cache key information from each zonelist for smaller cache
- * footprint when scanning for free pages in get_page_from_freelist().
- *
- * 1) The BITMAP fullzones tracks which zones in a zonelist have come
- *    up short of free memory since the last time (last_fullzone_zap)
- *    we zero'd fullzones.
- * 2) The array z_to_n[] maps each zone in the zonelist to its node
- *    id, so that we can efficiently evaluate whether that node is
- *    set in the current tasks mems_allowed.
- *
- * Both fullzones and z_to_n[] are one-to-one with the zonelist,
- * indexed by a zones offset in the zonelist zones[] array.
- *
- * The get_page_from_freelist() routine does two scans.  During the
- * first scan, we skip zones whose corresponding bit in 'fullzones'
- * is set or whose corresponding node in current->mems_allowed (which
- * comes from cpusets) is not set.  During the second scan, we bypass
- * this zonelist_cache, to ensure we look methodically at each zone.
- *
- * Once per second, we zero out (zap) fullzones, forcing us to
- * reconsider nodes that might have regained more free memory.
- * The field last_full_zap is the time we last zapped fullzones.
- *
- * This mechanism reduces the amount of time we waste repeatedly
- * reexaming zones for free memory when they just came up low on
- * memory momentarilly ago.
- *
- * The zonelist_cache struct members logically belong in struct
- * zonelist.  However, the mempolicy zonelists constructed for
- * MPOL_BIND are intentionally variable length (and usually much
- * shorter).  A general purpose mechanism for handling structs with
- * multiple variable length members is more mechanism than we want
- * here.  We resort to some special case hackery instead.
- *
- * The MPOL_BIND zonelists don't need this zonelist_cache (in good
- * part because they are shorter), so we put the fixed length stuff
- * at the front of the zonelist struct, ending in a variable length
- * zones[], as is needed by MPOL_BIND.
- *
- * Then we put the optional zonelist cache on the end of the zonelist
- * struct.  This optional stuff is found by a 'zlcache_ptr' pointer in
- * the fixed length portion at the front of the struct.  This pointer
- * both enables us to find the zonelist cache, and in the case of
- * MPOL_BIND zonelists, (which will just set the zlcache_ptr to NULL)
- * to know that the zonelist cache is not there.
- *
- * The end result is that struct zonelists come in two flavors:
- *  1) The full, fixed length version, shown below, and
- *  2) The custom zonelists for MPOL_BIND.
- * The custom MPOL_BIND zonelists have a NULL zlcache_ptr and no zlcache.
- *
- * Even though there may be multiple CPU cores on a node modifying
- * fullzones or last_full_zap in the same zonelist_cache at the same
- * time, we don't lock it.  This is just hint data - if it is wrong now
- * and then, the allocator will still function, perhaps a bit slower.
- */
-
-
-struct zonelist_cache {
-	unsigned short z_to_n[MAX_ZONES_PER_ZONELIST];		/* zone->nid */
-	DECLARE_BITMAP(fullzones, MAX_ZONES_PER_ZONELIST);	/* zone full? */
-	unsigned long last_full_zap;		/* when last zap'd (jiffies) */
-};
 #else
 #define MAX_ZONELISTS 1
-struct zonelist_cache;
 #endif
 
 /*
@@ -675,9 +605,6 @@ struct zoneref {
  * allocation, the other zones are fallback zones, in decreasing
  * priority.
  *
- * If zlcache_ptr is not NULL, then it is just the address of zlcache,
- * as explained above.  If zlcache_ptr is NULL, there is no zlcache.
- * *
  * To speed the reading of the zonelist, the zonerefs contain the zone index
  * of the entry being read. Helper functions to access information given
  * a struct zoneref are
@@ -687,11 +614,7 @@ struct zoneref {
  * zonelist_node_idx()	- Return the index of the node for an entry
  */
 struct zonelist {
-	struct zonelist_cache *zlcache_ptr;		     // NULL or &zlcache
 	struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
-#ifdef CONFIG_NUMA
-	struct zonelist_cache zlcache;			     // optional ...
-#endif
 };
 
 #ifndef CONFIG_DISCONTIGMEM
@@ -817,7 +740,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
 bool zone_watermark_ok(struct zone *z, unsigned int order,
 		unsigned long mark, int classzone_idx, int alloc_flags);
 bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int classzone_idx, int alloc_flags);
+		unsigned long mark, int classzone_idx);
 enum memmap_context {
 	MEMMAP_EARLY,
 	MEMMAP_HOTPLUG,
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index c12f2147c350..52666d90ca94 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -386,6 +386,7 @@ extern int param_get_ullong(char *buffer, const struct kernel_param *kp);
 extern const struct kernel_param_ops param_ops_charp;
 extern int param_set_charp(const char *val, const struct kernel_param *kp);
 extern int param_get_charp(char *buffer, const struct kernel_param *kp);
+extern void param_free_charp(void *arg);
 #define param_check_charp(name, p) __param_check(name, p, char *)
 
 /* We used to allow int as well as bool.  We're taking that away! */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a525e5067484..bb53c7b86315 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -86,12 +86,7 @@ enum pageflags {
 	PG_private,		/* If pagecache, has fs-private data */
 	PG_private_2,		/* If pagecache, has fs aux data */
 	PG_writeback,		/* Page is under writeback */
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
 	PG_head,		/* A head page */
-	PG_tail,		/* A tail page */
-#else
-	PG_compound,		/* A compound page */
-#endif
 	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
@@ -398,85 +393,46 @@ static inline void set_page_writeback_keepwrite(struct page *page)
 	test_set_page_writeback_keepwrite(page);
 }
 
-#ifdef CONFIG_PAGEFLAGS_EXTENDED
-/*
- * System with lots of page flags available. This allows separate
- * flags for PageHead() and PageTail() checks of compound pages so that bit
- * tests can be used in performance sensitive paths. PageCompound is
- * generally not used in hot code paths except arch/powerpc/mm/init_64.c
- * and arch/powerpc/kvm/book3s_64_vio_hv.c which use it to detect huge pages
- * and avoid handling those in real mode.
- */
 __PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
-__PAGEFLAG(Tail, tail)
 
-static inline int PageCompound(struct page *page)
-{
-	return page->flags & ((1L << PG_head) | (1L << PG_tail));
-
-}
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline void ClearPageCompound(struct page *page)
+static inline int PageTail(struct page *page)
 {
-	BUG_ON(!PageHead(page));
-	ClearPageHead(page);
+	return READ_ONCE(page->compound_head) & 1;
 }
-#endif
-
-#define PG_head_mask ((1L << PG_head))
 
-#else
-/*
- * Reduce page flag use as much as possible by overlapping
- * compound page flags with the flags used for page cache pages. Possible
- * because PageCompound is always set for compound pages and not for
- * pages on the LRU and/or pagecache.
- */
-TESTPAGEFLAG(Compound, compound)
-__SETPAGEFLAG(Head, compound)  __CLEARPAGEFLAG(Head, compound)
-
-/*
- * PG_reclaim is used in combination with PG_compound to mark the
- * head and tail of a compound page. This saves one page flag
- * but makes it impossible to use compound pages for the page cache.
- * The PG_reclaim bit would have to be used for reclaim or readahead
- * if compound pages enter the page cache.
- *
- * PG_compound & PG_reclaim	=> Tail page
- * PG_compound & ~PG_reclaim	=> Head page
- */
-#define PG_head_mask ((1L << PG_compound))
-#define PG_head_tail_mask ((1L << PG_compound) | (1L << PG_reclaim))
-
-static inline int PageHead(struct page *page)
+static inline void set_compound_head(struct page *page, struct page *head)
 {
-	return ((page->flags & PG_head_tail_mask) == PG_head_mask);
+	WRITE_ONCE(page->compound_head, (unsigned long)head + 1);
 }
 
-static inline int PageTail(struct page *page)
+static inline void clear_compound_head(struct page *page)
 {
-	return ((page->flags & PG_head_tail_mask) == PG_head_tail_mask);
+	WRITE_ONCE(page->compound_head, 0);
 }
 
-static inline void __SetPageTail(struct page *page)
+static inline struct page *compound_head(struct page *page)
 {
-	page->flags |= PG_head_tail_mask;
+	unsigned long head = READ_ONCE(page->compound_head);
+
+	if (unlikely(head & 1))
+		return (struct page *) (head - 1);
+	return page;
 }
 
-static inline void __ClearPageTail(struct page *page)
+static inline int PageCompound(struct page *page)
 {
-	page->flags &= ~PG_head_tail_mask;
-}
+	return PageHead(page) || PageTail(page);
 
+}
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 static inline void ClearPageCompound(struct page *page)
 {
-	BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound));
-	clear_bit(PG_compound, &page->flags);
+	BUG_ON(!PageHead(page));
+	ClearPageHead(page);
 }
 #endif
 
-#endif /* !PAGEFLAGS_EXTENDED */
+#define PG_head_mask ((1L << PG_head))
 
 #ifdef CONFIG_HUGETLB_PAGE
 int PageHuge(struct page *page);
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 2baeee12f48e..e942558b3585 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -44,7 +44,7 @@ enum pageblock_bits {
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
 /* Huge page sizes are variable */
-extern int pageblock_order;
+extern unsigned int pageblock_order;
 
 #else /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index a6c78e00ea96..26eabf5ec718 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -69,6 +69,13 @@ static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
 	return (__force gfp_t)mapping->flags & __GFP_BITS_MASK;
 }
 
+/* Restricts the given gfp_mask to what the mapping allows. */
+static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
+		gfp_t gfp_mask)
+{
+	return mapping_gfp_mask(mapping) & gfp_mask;
+}
+
 /*
  * This is non-atomic.  Only to be used before the mapping is activated.
  * Probably needs a barrier...
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 830c4992088d..a5aa7ae671f4 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -101,13 +101,21 @@ static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent
 	})
 
 /**
- * rbtree_postorder_for_each_entry_safe - iterate over rb_root in post order of
- * given type safe against removal of rb_node entry
+ * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of
+ * given type allowing the backing memory of @pos to be invalidated
  *
  * @pos:	the 'type *' to use as a loop cursor.
  * @n:		another 'type *' to use as temporary storage
  * @root:	'rb_root *' of the rbtree.
  * @field:	the name of the rb_node field within 'type'.
+ *
+ * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as
+ * list_for_each_entry_safe() and allows the iteration to continue independent
+ * of changes to @pos by the body of the loop.
+ *
+ * Note, however, that it cannot handle other modifications that re-order the
+ * rbtree it is iterating over. This includes calling rb_erase() on @pos, as
+ * rb_erase() may rebalance the tree, causing us to miss some nodes.
  */
 #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \
 	for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index eeb5066a44fb..4069febaa34a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1570,9 +1570,7 @@ struct task_struct {
 
 	unsigned long sas_ss_sp;
 	size_t sas_ss_size;
-	int (*notifier)(void *priv);
-	void *notifier_data;
-	sigset_t *notifier_mask;
+
 	struct callback_head *task_works;
 
 	struct audit_context *audit_context;
@@ -2464,21 +2462,29 @@ extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
 extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
 
-static inline int dequeue_signal_lock(struct task_struct *tsk, sigset_t *mask, siginfo_t *info)
+static inline int kernel_dequeue_signal(siginfo_t *info)
 {
-	unsigned long flags;
+	struct task_struct *tsk = current;
+	siginfo_t __info;
 	int ret;
 
-	spin_lock_irqsave(&tsk->sighand->siglock, flags);
-	ret = dequeue_signal(tsk, mask, info);
-	spin_unlock_irqrestore(&tsk->sighand->siglock, flags);
+	spin_lock_irq(&tsk->sighand->siglock);
+	ret = dequeue_signal(tsk, &tsk->blocked, info ?: &__info);
+	spin_unlock_irq(&tsk->sighand->siglock);
 
 	return ret;
 }
 
-extern void block_all_signals(int (*notifier)(void *priv), void *priv,
-			      sigset_t *mask);
-extern void unblock_all_signals(void);
+static inline void kernel_signal_stop(void)
+{
+	spin_lock_irq(&current->sighand->siglock);
+	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
+		__set_current_state(TASK_STOPPED);
+	spin_unlock_irq(&current->sighand->siglock);
+
+	schedule();
+}
+
 extern void release_task(struct task_struct * p);
 extern int send_sig_info(int, struct siginfo *, struct task_struct *);
 extern int force_sigsegv(int, struct task_struct *);
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 24f4dfd94c51..4355129fff91 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1224,7 +1224,7 @@ static inline int skb_cloned(const struct sk_buff *skb)
 
 static inline int skb_unclone(struct sk_buff *skb, gfp_t pri)
 {
-	might_sleep_if(pri & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(pri));
 
 	if (skb_cloned(skb))
 		return pskb_expand_head(skb, 0, 0, pri);
@@ -1308,7 +1308,7 @@ static inline int skb_shared(const struct sk_buff *skb)
  */
 static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
 {
-	might_sleep_if(pri & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(pri));
 	if (skb_shared(skb)) {
 		struct sk_buff *nskb = skb_clone(skb, pri);
 
@@ -1344,7 +1344,7 @@ static inline struct sk_buff *skb_share_check(struct sk_buff *skb, gfp_t pri)
 static inline struct sk_buff *skb_unshare(struct sk_buff *skb,
 					  gfp_t pri)
 {
-	might_sleep_if(pri & __GFP_WAIT);
+	might_sleep_if(gfpflags_allow_blocking(pri));
 	if (skb_cloned(skb)) {
 		struct sk_buff *nskb = skb_copy(skb, pri);
 
diff --git a/include/linux/zpool.h b/include/linux/zpool.h
index 42f8ec992452..2e97b7707dff 100644
--- a/include/linux/zpool.h
+++ b/include/linux/zpool.h
@@ -38,10 +38,10 @@ enum zpool_mapmode {
 
 bool zpool_has_pool(char *type);
 
-struct zpool *zpool_create_pool(char *type, char *name,
+struct zpool *zpool_create_pool(const char *type, const char *name,
 			gfp_t gfp, const struct zpool_ops *ops);
 
-char *zpool_get_type(struct zpool *pool);
+const char *zpool_get_type(struct zpool *pool);
 
 void zpool_destroy_pool(struct zpool *pool);
 
@@ -83,7 +83,9 @@ struct zpool_driver {
 	atomic_t refcount;
 	struct list_head list;
 
-	void *(*create)(char *name, gfp_t gfp, const struct zpool_ops *ops,
+	void *(*create)(const char *name,
+			gfp_t gfp,
+			const struct zpool_ops *ops,
 			struct zpool *zpool);
 	void (*destroy)(void *pool);
 
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 6398dfae53f1..34eb16098a33 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -41,7 +41,7 @@ struct zs_pool_stats {
 
 struct zs_pool;
 
-struct zs_pool *zs_create_pool(char *name, gfp_t flags);
+struct zs_pool *zs_create_pool(const char *name, gfp_t flags);
 void zs_destroy_pool(struct zs_pool *pool);
 
 unsigned long zs_malloc(struct zs_pool *pool, size_t size);
diff --git a/include/linux/zutil.h b/include/linux/zutil.h
index 6adfa9a6ffe9..663689521759 100644
--- a/include/linux/zutil.h
+++ b/include/linux/zutil.h
@@ -68,10 +68,10 @@ typedef uLong (*check_func) (uLong check, const Byte *buf,
    An Adler-32 checksum is almost as reliable as a CRC32 but can be computed
    much faster. Usage example:
 
-     uLong adler = adler32(0L, NULL, 0);
+     uLong adler = zlib_adler32(0L, NULL, 0);
 
      while (read_buffer(buffer, length) != EOF) {
-       adler = adler32(adler, buffer, length);
+       adler = zlib_adler32(adler, buffer, length);
      }
      if (adler != original_adler) error();
 */
diff --git a/include/net/sock.h b/include/net/sock.h
index f570e75e3da9..bbf7c2cf15b4 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2041,7 +2041,7 @@ struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp,
  */
 static inline struct page_frag *sk_page_frag(struct sock *sk)
 {
-	if (sk->sk_allocation & __GFP_WAIT)
+	if (gfpflags_allow_blocking(sk->sk_allocation))
 		return &current->task_frag;
 
 	return &sk->sk_frag;
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index d6fd8e5b14b7..dde6bf092c8a 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -20,7 +20,7 @@
 	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
 	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
 	{(unsigned long)__GFP_HIGH,		"GFP_HIGH"},		\
-	{(unsigned long)__GFP_WAIT,		"GFP_WAIT"},		\
+	{(unsigned long)__GFP_ATOMIC,		"GFP_ATOMIC"},		\
 	{(unsigned long)__GFP_IO,		"GFP_IO"},		\
 	{(unsigned long)__GFP_COLD,		"GFP_COLD"},		\
 	{(unsigned long)__GFP_NOWARN,		"GFP_NOWARN"},		\
@@ -36,7 +36,8 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
-	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\
+	{(unsigned long)__GFP_DIRECT_RECLAIM,	"GFP_DIRECT_RECLAIM"},	\
+	{(unsigned long)__GFP_KSWAPD_RECLAIM,	"GFP_KSWAPD_RECLAIM"},	\
 	{(unsigned long)__GFP_OTHER_NODE,	"GFP_OTHER_NODE"}	\
 	) : "GFP_NOWAIT"
 
diff --git a/include/trace/events/nilfs2.h b/include/trace/events/nilfs2.h
new file mode 100644
index 000000000000..c7805818fcc6
--- /dev/null
+++ b/include/trace/events/nilfs2.h
@@ -0,0 +1,224 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM nilfs2
+
+#if !defined(_TRACE_NILFS2_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NILFS2_H
+
+#include <linux/tracepoint.h>
+
+struct nilfs_sc_info;
+
+#define show_collection_stage(type)					\
+	__print_symbolic(type,						\
+	{ NILFS_ST_INIT, "ST_INIT" },					\
+	{ NILFS_ST_GC, "ST_GC" },					\
+	{ NILFS_ST_FILE, "ST_FILE" },					\
+	{ NILFS_ST_IFILE, "ST_IFILE" },					\
+	{ NILFS_ST_CPFILE, "ST_CPFILE" },				\
+	{ NILFS_ST_SUFILE, "ST_SUFILE" },				\
+	{ NILFS_ST_DAT, "ST_DAT" },					\
+	{ NILFS_ST_SR, "ST_SR" },					\
+	{ NILFS_ST_DSYNC, "ST_DSYNC" },					\
+	{ NILFS_ST_DONE, "ST_DONE"})
+
+TRACE_EVENT(nilfs2_collection_stage_transition,
+
+	    TP_PROTO(struct nilfs_sc_info *sci),
+
+	    TP_ARGS(sci),
+
+	    TP_STRUCT__entry(
+		    __field(void *, sci)
+		    __field(int, stage)
+	    ),
+
+	    TP_fast_assign(
+			__entry->sci = sci;
+			__entry->stage = sci->sc_stage.scnt;
+		    ),
+
+	    TP_printk("sci = %p stage = %s",
+		      __entry->sci,
+		      show_collection_stage(__entry->stage))
+);
+
+#ifndef TRACE_HEADER_MULTI_READ
+enum nilfs2_transaction_transition_state {
+	TRACE_NILFS2_TRANSACTION_BEGIN,
+	TRACE_NILFS2_TRANSACTION_COMMIT,
+	TRACE_NILFS2_TRANSACTION_ABORT,
+	TRACE_NILFS2_TRANSACTION_TRYLOCK,
+	TRACE_NILFS2_TRANSACTION_LOCK,
+	TRACE_NILFS2_TRANSACTION_UNLOCK,
+};
+#endif
+
+#define show_transaction_state(type)					\
+	__print_symbolic(type,						\
+			 { TRACE_NILFS2_TRANSACTION_BEGIN, "BEGIN" },	\
+			 { TRACE_NILFS2_TRANSACTION_COMMIT, "COMMIT" },	\
+			 { TRACE_NILFS2_TRANSACTION_ABORT, "ABORT" },	\
+			 { TRACE_NILFS2_TRANSACTION_TRYLOCK, "TRYLOCK" }, \
+			 { TRACE_NILFS2_TRANSACTION_LOCK, "LOCK" },	\
+			 { TRACE_NILFS2_TRANSACTION_UNLOCK, "UNLOCK" })
+
+TRACE_EVENT(nilfs2_transaction_transition,
+	    TP_PROTO(struct super_block *sb,
+		     struct nilfs_transaction_info *ti,
+		     int count,
+		     unsigned int flags,
+		     enum nilfs2_transaction_transition_state state),
+
+	    TP_ARGS(sb, ti, count, flags, state),
+
+	    TP_STRUCT__entry(
+		    __field(void *, sb)
+		    __field(void *, ti)
+		    __field(int, count)
+		    __field(unsigned int, flags)
+		    __field(int, state)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->sb = sb;
+		    __entry->ti = ti;
+		    __entry->count = count;
+		    __entry->flags = flags;
+		    __entry->state = state;
+		    ),
+
+	    TP_printk("sb = %p ti = %p count = %d flags = %x state = %s",
+		      __entry->sb,
+		      __entry->ti,
+		      __entry->count,
+		      __entry->flags,
+		      show_transaction_state(__entry->state))
+);
+
+TRACE_EVENT(nilfs2_segment_usage_check,
+	    TP_PROTO(struct inode *sufile,
+		     __u64 segnum,
+		     unsigned long cnt),
+
+	    TP_ARGS(sufile, segnum, cnt),
+
+	    TP_STRUCT__entry(
+		    __field(struct inode *, sufile)
+		    __field(__u64, segnum)
+		    __field(unsigned long, cnt)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->sufile = sufile;
+		    __entry->segnum = segnum;
+		    __entry->cnt = cnt;
+		    ),
+
+	    TP_printk("sufile = %p segnum = %llu cnt = %lu",
+		      __entry->sufile,
+		      __entry->segnum,
+		      __entry->cnt)
+);
+
+TRACE_EVENT(nilfs2_segment_usage_allocated,
+	    TP_PROTO(struct inode *sufile,
+		     __u64 segnum),
+
+	    TP_ARGS(sufile, segnum),
+
+	    TP_STRUCT__entry(
+		    __field(struct inode *, sufile)
+		    __field(__u64, segnum)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->sufile = sufile;
+		    __entry->segnum = segnum;
+		    ),
+
+	    TP_printk("sufile = %p segnum = %llu",
+		      __entry->sufile,
+		      __entry->segnum)
+);
+
+TRACE_EVENT(nilfs2_segment_usage_freed,
+	    TP_PROTO(struct inode *sufile,
+		     __u64 segnum),
+
+	    TP_ARGS(sufile, segnum),
+
+	    TP_STRUCT__entry(
+		    __field(struct inode *, sufile)
+		    __field(__u64, segnum)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->sufile = sufile;
+		    __entry->segnum = segnum;
+		    ),
+
+	    TP_printk("sufile = %p segnum = %llu",
+		      __entry->sufile,
+		      __entry->segnum)
+);
+
+TRACE_EVENT(nilfs2_mdt_insert_new_block,
+	    TP_PROTO(struct inode *inode,
+		     unsigned long ino,
+		     unsigned long block),
+
+	    TP_ARGS(inode, ino, block),
+
+	    TP_STRUCT__entry(
+		    __field(struct inode *, inode)
+		    __field(unsigned long, ino)
+		    __field(unsigned long, block)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->inode = inode;
+		    __entry->ino = ino;
+		    __entry->block = block;
+		    ),
+
+	    TP_printk("inode = %p ino = %lu block = %lu",
+		      __entry->inode,
+		      __entry->ino,
+		      __entry->block)
+);
+
+TRACE_EVENT(nilfs2_mdt_submit_block,
+	    TP_PROTO(struct inode *inode,
+		     unsigned long ino,
+		     unsigned long blkoff,
+		     int mode),
+
+	    TP_ARGS(inode, ino, blkoff, mode),
+
+	    TP_STRUCT__entry(
+		    __field(struct inode *, inode)
+		    __field(unsigned long, ino)
+		    __field(unsigned long, blkoff)
+		    __field(int, mode)
+	    ),
+
+	    TP_fast_assign(
+		    __entry->inode = inode;
+		    __entry->ino = ino;
+		    __entry->blkoff = blkoff;
+		    __entry->mode = mode;
+		    ),
+
+	    TP_printk("inode = %p ino = %lu blkoff = %lu mode = %x",
+		      __entry->inode,
+		      __entry->ino,
+		      __entry->blkoff,
+		      __entry->mode)
+);
+
+#endif /* _TRACE_NILFS2_H */
+
+/* This part must be outside protection */
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE nilfs2
+#include <trace/define_trace.h>