Merge branch 'akpm' (Andrew's patch-bomb)

Merge first batch of patches from Andrew Morton:
 "A few misc things and all the MM queue"

* emailed from Andrew Morton <akpm@linux-foundation.org>: (92 commits)
  memcg: avoid THP split in task migration
  thp: add HPAGE_PMD_* definitions for !CONFIG_TRANSPARENT_HUGEPAGE
  memcg: clean up existing move charge code
  mm/memcontrol.c: remove unnecessary 'break' in mem_cgroup_read()
  mm/memcontrol.c: remove redundant BUG_ON() in mem_cgroup_usage_unregister_event()
  mm/memcontrol.c: s/stealed/stolen/
  memcg: fix performance of mem_cgroup_begin_update_page_stat()
  memcg: remove PCG_FILE_MAPPED
  memcg: use new logic for page stat accounting
  memcg: remove PCG_MOVE_LOCK flag from page_cgroup
  memcg: simplify move_account() check
  memcg: remove EXPORT_SYMBOL(mem_cgroup_update_page_stat)
  memcg: kill dead prev_priority stubs
  memcg: remove PCG_CACHE page_cgroup flag
  memcg: let css_get_next() rely upon rcu_read_lock()
  cgroup: revert ss_id_lock to spinlock
  idr: make idr_get_next() good for rcu_read_lock()
  memcg: remove unnecessary thp check in page stat accounting
  memcg: remove redundant returns
  memcg: enum lru_list lru
  ...

18 files changed, 226 insertions, 137 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 76bff2bff15..a03c098b0cc 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -425,6 +425,8 @@ extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
 				unsigned long size);
 #endif
 
+#ifdef CONFIG_MMU
+
 #ifndef CONFIG_TRANSPARENT_HUGEPAGE
 static inline int pmd_trans_huge(pmd_t pmd)
 {
@@ -441,7 +443,66 @@ static inline int pmd_write(pmd_t pmd)
 	return 0;
 }
 #endif /* __HAVE_ARCH_PMD_WRITE */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/*
+ * This function is meant to be used by sites walking pagetables with
+ * the mmap_sem hold in read mode to protect against MADV_DONTNEED and
+ * transhuge page faults. MADV_DONTNEED can convert a transhuge pmd
+ * into a null pmd and the transhuge page fault can convert a null pmd
+ * into an hugepmd or into a regular pmd (if the hugepage allocation
+ * fails). While holding the mmap_sem in read mode the pmd becomes
+ * stable and stops changing under us only if it's not null and not a
+ * transhuge pmd. When those races occurs and this function makes a
+ * difference vs the standard pmd_none_or_clear_bad, the result is
+ * undefined so behaving like if the pmd was none is safe (because it
+ * can return none anyway). The compiler level barrier() is critically
+ * important to compute the two checks atomically on the same pmdval.
+ */
+static inline int pmd_none_or_trans_huge_or_clear_bad(pmd_t *pmd)
+{
+	/* depend on compiler for an atomic pmd read */
+	pmd_t pmdval = *pmd;
+	/*
+	 * The barrier will stabilize the pmdval in a register or on
+	 * the stack so that it will stop changing under the code.
+	 */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	barrier();
+#endif
+	if (pmd_none(pmdval))
+		return 1;
+	if (unlikely(pmd_bad(pmdval))) {
+		if (!pmd_trans_huge(pmdval))
+			pmd_clear_bad(pmd);
+		return 1;
+	}
+	return 0;
+}
+
+/*
+ * This is a noop if Transparent Hugepage Support is not built into
+ * the kernel. Otherwise it is equivalent to
+ * pmd_none_or_trans_huge_or_clear_bad(), and shall only be called in
+ * places that already verified the pmd is not none and they want to
+ * walk ptes while holding the mmap sem in read mode (write mode don't
+ * need this). If THP is not enabled, the pmd can't go away under the
+ * code even if MADV_DONTNEED runs, but if THP is enabled we need to
+ * run a pmd_trans_unstable before walking the ptes after
+ * split_huge_page_pmd returns (because it may have run when the pmd
+ * become null, but then a page fault can map in a THP and not a
+ * regular page).
+ */
+static inline int pmd_trans_unstable(pmd_t *pmd)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	return pmd_none_or_trans_huge_or_clear_bad(pmd);
+#else
+	return 0;
 #endif
+}
+
+#endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 501adb1b2f4..5a85b3415c1 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -498,7 +498,7 @@ struct cgroup_subsys {
 	struct list_head sibling;
 	/* used when use_id == true */
 	struct idr idr;
-	rwlock_t id_lock;
+	spinlock_t id_lock;
 
 	/* should be defined only by modular subsystems */
 	struct module *module;
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index bb2bbdbe546..51a90b7f2d6 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -23,6 +23,7 @@ extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
 			bool sync);
+extern int compact_pgdat(pg_data_t *pgdat, int order);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 
 /* Do not skip compaction more than 64 times */
@@ -33,20 +34,26 @@ extern unsigned long compaction_suitable(struct zone *zone, int order);
  * allocation success. 1 << compact_defer_limit compactions are skipped up
  * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT
  */
-static inline void defer_compaction(struct zone *zone)
+static inline void defer_compaction(struct zone *zone, int order)
 {
 	zone->compact_considered = 0;
 	zone->compact_defer_shift++;
 
+	if (order < zone->compact_order_failed)
+		zone->compact_order_failed = order;
+
 	if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT)
 		zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT;
 }
 
 /* Returns true if compaction should be skipped this time */
-static inline bool compaction_deferred(struct zone *zone)
+static inline bool compaction_deferred(struct zone *zone, int order)
 {
 	unsigned long defer_limit = 1UL << zone->compact_defer_shift;
 
+	if (order < zone->compact_order_failed)
+		return false;
+
 	/* Avoid possible overflow */
 	if (++zone->compact_considered > defer_limit)
 		zone->compact_considered = defer_limit;
@@ -62,16 +69,21 @@ static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	return COMPACT_CONTINUE;
 }
 
+static inline int compact_pgdat(pg_data_t *pgdat, int order)
+{
+	return COMPACT_CONTINUE;
+}
+
 static inline unsigned long compaction_suitable(struct zone *zone, int order)
 {
 	return COMPACT_SKIPPED;
 }
 
-static inline void defer_compaction(struct zone *zone)
+static inline void defer_compaction(struct zone *zone, int order)
 {
 }
 
-static inline bool compaction_deferred(struct zone *zone)
+static inline bool compaction_deferred(struct zone *zone, int order)
 {
 	return 1;
 }
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index e9eaec52265..7a7e5fd2a27 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -89,42 +89,33 @@ extern void rebuild_sched_domains(void);
 extern void cpuset_print_task_mems_allowed(struct task_struct *p);
 
 /*
- * reading current mems_allowed and mempolicy in the fastpath must protected
- * by get_mems_allowed()
+ * get_mems_allowed is required when making decisions involving mems_allowed
+ * such as during page allocation. mems_allowed can be updated in parallel
+ * and depending on the new value an operation can fail potentially causing
+ * process failure. A retry loop with get_mems_allowed and put_mems_allowed
+ * prevents these artificial failures.
  */
-static inline void get_mems_allowed(void)
+static inline unsigned int get_mems_allowed(void)
 {
-	current->mems_allowed_change_disable++;
-
-	/*
-	 * ensure that reading mems_allowed and mempolicy happens after the
-	 * update of ->mems_allowed_change_disable.
-	 *
-	 * the write-side task finds ->mems_allowed_change_disable is not 0,
-	 * and knows the read-side task is reading mems_allowed or mempolicy,
-	 * so it will clear old bits lazily.
-	 */
-	smp_mb();
+	return read_seqcount_begin(&current->mems_allowed_seq);
 }
 
-static inline void put_mems_allowed(void)
+/*
+ * If this returns false, the operation that took place after get_mems_allowed
+ * may have failed. It is up to the caller to retry the operation if
+ * appropriate.
+ */
+static inline bool put_mems_allowed(unsigned int seq)
 {
-	/*
-	 * ensure that reading mems_allowed and mempolicy before reducing
-	 * mems_allowed_change_disable.
-	 *
-	 * the write-side task will know that the read-side task is still
-	 * reading mems_allowed or mempolicy, don't clears old bits in the
-	 * nodemask.
-	 */
-	smp_mb();
-	--ACCESS_ONCE(current->mems_allowed_change_disable);
+	return !read_seqcount_retry(&current->mems_allowed_seq, seq);
 }
 
 static inline void set_mems_allowed(nodemask_t nodemask)
 {
 	task_lock(current);
+	write_seqcount_begin(&current->mems_allowed_seq);
 	current->mems_allowed = nodemask;
+	write_seqcount_end(&current->mems_allowed_seq);
 	task_unlock(current);
 }
 
@@ -234,12 +225,14 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 {
 }
 
-static inline void get_mems_allowed(void)
+static inline unsigned int get_mems_allowed(void)
 {
+	return 0;
 }
 
-static inline void put_mems_allowed(void)
+static inline bool put_mems_allowed(unsigned int seq)
 {
+	return true;
 }
 
 #endif /* !CONFIG_CPUSETS */
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 1b921299abc..c8af7a2efb5 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -51,6 +51,9 @@ extern pmd_t *page_check_address_pmd(struct page *page,
 				     unsigned long address,
 				     enum page_check_address_pmd_flag flag);
 
+#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define HPAGE_PMD_SHIFT HPAGE_SHIFT
 #define HPAGE_PMD_MASK HPAGE_MASK
@@ -102,8 +105,6 @@ extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
 	} while (0)
-#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
-#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 #if HPAGE_PMD_ORDER > MAX_ORDER
 #error "hugepages can't be allocated by the buddy allocator"
 #endif
@@ -113,6 +114,18 @@ extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
 				    unsigned long start,
 				    unsigned long end,
 				    long adjust_next);
+extern int __pmd_trans_huge_lock(pmd_t *pmd,
+				 struct vm_area_struct *vma);
+/* mmap_sem must be held on entry */
+static inline int pmd_trans_huge_lock(pmd_t *pmd,
+				      struct vm_area_struct *vma)
+{
+	VM_BUG_ON(!rwsem_is_locked(&vma->vm_mm->mmap_sem));
+	if (pmd_trans_huge(*pmd))
+		return __pmd_trans_huge_lock(pmd, vma);
+	else
+		return 0;
+}
 static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 unsigned long start,
 					 unsigned long end,
@@ -146,9 +159,9 @@ static inline struct page *compound_trans_head(struct page *page)
 	return page;
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
-#define HPAGE_PMD_SHIFT ({ BUG(); 0; })
-#define HPAGE_PMD_MASK ({ BUG(); 0; })
-#define HPAGE_PMD_SIZE ({ BUG(); 0; })
+#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
+#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
+#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
 
 #define hpage_nr_pages(x) 1
 
@@ -176,6 +189,11 @@ static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 long adjust_next)
 {
 }
+static inline int pmd_trans_huge_lock(pmd_t *pmd,
+				      struct vm_area_struct *vma)
+{
+	return 0;
+}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d9d6c868b86..000837e126e 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -14,6 +14,15 @@ struct user_struct;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+struct hugepage_subpool {
+	spinlock_t lock;
+	long count;
+	long max_hpages, used_hpages;
+};
+
+struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
+void hugepage_put_subpool(struct hugepage_subpool *spool);
+
 int PageHuge(struct page *page);
 
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
@@ -128,35 +137,14 @@ enum {
 };
 
 #ifdef CONFIG_HUGETLBFS
-struct hugetlbfs_config {
-	uid_t   uid;
-	gid_t   gid;
-	umode_t mode;
-	long	nr_blocks;
-	long	nr_inodes;
-	struct hstate *hstate;
-};
-
 struct hugetlbfs_sb_info {
-	long	max_blocks;   /* blocks allowed */
-	long	free_blocks;  /* blocks free */
 	long	max_inodes;   /* inodes allowed */
 	long	free_inodes;  /* inodes free */
 	spinlock_t	stat_lock;
 	struct hstate *hstate;
+	struct hugepage_subpool *spool;
 };
 
-
-struct hugetlbfs_inode_info {
-	struct shared_policy policy;
-	struct inode vfs_inode;
-};
-
-static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
-{
-	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
-}
-
 static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 {
 	return sb->s_fs_info;
@@ -164,10 +152,9 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
+struct file *hugetlb_file_setup(const char *name, unsigned long addr,
+				size_t size, vm_flags_t acct,
 				struct user_struct **user, int creat_flags);
-int hugetlb_get_quota(struct address_space *mapping, long delta);
-void hugetlb_put_quota(struct address_space *mapping, long delta);
 
 static inline int is_file_hugepages(struct file *file)
 {
@@ -179,15 +166,11 @@ static inline int is_file_hugepages(struct file *file)
 	return 0;
 }
 
-static inline void set_file_hugepages(struct file *file)
-{
-	file->f_op = &hugetlbfs_file_operations;
-}
 #else /* !CONFIG_HUGETLBFS */
 
 #define is_file_hugepages(file)			0
-#define set_file_hugepages(file)		BUG()
-static inline struct file *hugetlb_file_setup(const char *name, size_t size,
+static inline struct file *
+hugetlb_file_setup(const char *name, unsigned long addr, size_t size,
 		vm_flags_t acctflag, struct user_struct **user, int creat_flags)
 {
 	return ERR_PTR(-ENOSYS);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f994d51f70f..e4baff5f7ff 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -29,6 +29,13 @@ extern struct fs_struct init_fs;
 #define INIT_GROUP_RWSEM(sig)
 #endif
 
+#ifdef CONFIG_CPUSETS
+#define INIT_CPUSET_SEQ							\
+	.mems_allowed_seq = SEQCNT_ZERO,
+#else
+#define INIT_CPUSET_SEQ
+#endif
+
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
@@ -192,6 +199,7 @@ extern struct cred init_cred;
 	INIT_FTRACE_GRAPH						\
 	INIT_TRACE_RECURSION						\
 	INIT_TASK_RCU_PREEMPT(tsk)					\
+	INIT_CPUSET_SEQ							\
 }
 
 
diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index bd92a89f4b0..26a65711676 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -30,6 +30,7 @@
 #define KPF_NOPAGE		20
 
 #define KPF_KSM			21
+#define KPF_THP			22
 
 /* kernel hacking assistances
  * WARNING: subject to change, never rely on them!
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index b80de520670..f94efd2f6c2 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -77,7 +77,8 @@ 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);
 
-extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask);
+extern void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order);
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *memcg);
 
 extern struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page);
@@ -140,6 +141,34 @@ static inline bool mem_cgroup_disabled(void)
 	return false;
 }
 
+void __mem_cgroup_begin_update_page_stat(struct page *page, bool *locked,
+					 unsigned long *flags);
+
+extern atomic_t memcg_moving;
+
+static inline void mem_cgroup_begin_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+	if (mem_cgroup_disabled())
+		return;
+	rcu_read_lock();
+	*locked = false;
+	if (atomic_read(&memcg_moving))
+		__mem_cgroup_begin_update_page_stat(page, locked, flags);
+}
+
+void __mem_cgroup_end_update_page_stat(struct page *page,
+				unsigned long *flags);
+static inline void mem_cgroup_end_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+	if (mem_cgroup_disabled())
+		return;
+	if (*locked)
+		__mem_cgroup_end_update_page_stat(page, flags);
+	rcu_read_unlock();
+}
+
 void mem_cgroup_update_page_stat(struct page *page,
 				 enum mem_cgroup_page_stat_item idx,
 				 int val);
@@ -298,21 +327,6 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
 {
 }
 
-static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *memcg)
-{
-	return 0;
-}
-
-static inline void mem_cgroup_note_reclaim_priority(struct mem_cgroup *memcg,
-						int priority)
-{
-}
-
-static inline void mem_cgroup_record_reclaim_priority(struct mem_cgroup *memcg,
-						int priority)
-{
-}
-
 static inline bool mem_cgroup_disabled(void)
 {
 	return true;
@@ -355,6 +369,16 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
+static inline void mem_cgroup_begin_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+}
+
+static inline void mem_cgroup_end_update_page_stat(struct page *page,
+					bool *locked, unsigned long *flags)
+{
+}
+
 static inline void mem_cgroup_inc_page_stat(struct page *page,
 					    enum mem_cgroup_page_stat_item idx)
 {
@@ -391,7 +415,7 @@ static inline void mem_cgroup_replace_page_cache(struct page *oldpage,
 				struct page *newpage)
 {
 }
-#endif /* CONFIG_CGROUP_MEM_CONT */
+#endif /* CONFIG_CGROUP_MEM_RES_CTLR */
 
 #if !defined(CONFIG_CGROUP_MEM_RES_CTLR) || !defined(CONFIG_DEBUG_VM)
 static inline bool
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 05ed2828a55..855c337b20c 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -8,7 +8,6 @@
 typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 
 #ifdef CONFIG_MIGRATION
-#define PAGE_MIGRATION 1
 
 extern void putback_lru_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
@@ -32,7 +31,6 @@ extern void migrate_page_copy(struct page *newpage, struct page *page);
 extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 				  struct page *newpage, struct page *page);
 #else
-#define PAGE_MIGRATION 0
 
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b5bb54d6d66..ee67e326b6f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1040,6 +1040,9 @@ static inline int stack_guard_page_end(struct vm_area_struct *vma,
 		!vma_growsup(vma->vm_next, addr);
 }
 
+extern pid_t
+vm_is_stack(struct task_struct *task, struct vm_area_struct *vma, int in_group);
+
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
 		unsigned long new_addr, unsigned long len);
@@ -1058,19 +1061,20 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write,
 /*
  * per-process(per-mm_struct) statistics.
  */
-static inline void set_mm_counter(struct mm_struct *mm, int member, long value)
-{
-	atomic_long_set(&mm->rss_stat.count[member], value);
-}
-
-#if defined(SPLIT_RSS_COUNTING)
-unsigned long get_mm_counter(struct mm_struct *mm, int member);
-#else
 static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 {
-	return atomic_long_read(&mm->rss_stat.count[member]);
-}
+	long val = atomic_long_read(&mm->rss_stat.count[member]);
+
+#ifdef SPLIT_RSS_COUNTING
+	/*
+	 * counter is updated in asynchronous manner and may go to minus.
+	 * But it's never be expected number for users.
+	 */
+	if (val < 0)
+		val = 0;
 #endif
+	return (unsigned long)val;
+}
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
 {
@@ -1127,9 +1131,9 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 }
 
 #if defined(SPLIT_RSS_COUNTING)
-void sync_mm_rss(struct task_struct *task, struct mm_struct *mm);
+void sync_mm_rss(struct mm_struct *mm);
 #else
-static inline void sync_mm_rss(struct task_struct *task, struct mm_struct *mm)
+static inline void sync_mm_rss(struct mm_struct *mm)
 {
 }
 #endif
@@ -1291,8 +1295,6 @@ extern void get_pfn_range_for_nid(unsigned int nid,
 extern unsigned long find_min_pfn_with_active_regions(void);
 extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
-int add_from_early_node_map(struct range *range, int az,
-				   int nr_range, int nid);
 extern void sparse_memory_present_with_active_regions(int nid);
 
 #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 650ba2fb330..dff71150966 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -365,6 +365,7 @@ struct zone {
 	 */
 	unsigned int		compact_considered;
 	unsigned int		compact_defer_shift;
+	int			compact_order_failed;
 #endif
 
 	ZONE_PADDING(_pad1_)
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 552fba9c7d5..3d7647536b0 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -49,7 +49,7 @@ extern int try_set_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 extern void clear_zonelist_oom(struct zonelist *zonelist, gfp_t gfp_flags);
 
 extern void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
-		int order, nodemask_t *mask);
+		int order, nodemask_t *mask, bool force_kill);
 extern int register_oom_notifier(struct notifier_block *nb);
 extern int unregister_oom_notifier(struct notifier_block *nb);
 
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index e90a673be67..6b25758e028 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -414,11 +414,26 @@ static inline int PageTransHuge(struct page *page)
 	return PageHead(page);
 }
 
+/*
+ * PageTransCompound returns true for both transparent huge pages
+ * and hugetlbfs pages, so it should only be called when it's known
+ * that hugetlbfs pages aren't involved.
+ */
 static inline int PageTransCompound(struct page *page)
 {
 	return PageCompound(page);
 }
 
+/*
+ * PageTransTail returns true for both transparent huge pages
+ * and hugetlbfs pages, so it should only be called when it's known
+ * that hugetlbfs pages aren't involved.
+ */
+static inline int PageTransTail(struct page *page)
+{
+	return PageTail(page);
+}
+
 #else
 
 static inline int PageTransHuge(struct page *page)
@@ -430,6 +445,11 @@ static inline int PageTransCompound(struct page *page)
 {
 	return 0;
 }
+
+static inline int PageTransTail(struct page *page)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index a2d11771c84..a88cdba2780 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -4,12 +4,8 @@
 enum {
 	/* flags for mem_cgroup */
 	PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
-	PCG_CACHE, /* charged as cache */
 	PCG_USED, /* this object is in use. */
 	PCG_MIGRATION, /* under page migration */
-	/* flags for mem_cgroup and file and I/O status */
-	PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */
-	PCG_FILE_MAPPED, /* page is accounted as "mapped" */
 	__NR_PCG_FLAGS,
 };
 
@@ -64,19 +60,10 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
 static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)	\
 	{ return test_and_clear_bit(PCG_##lname, &pc->flags);  }
 
-/* Cache flag is set only once (at allocation) */
-TESTPCGFLAG(Cache, CACHE)
-CLEARPCGFLAG(Cache, CACHE)
-SETPCGFLAG(Cache, CACHE)
-
 TESTPCGFLAG(Used, USED)
 CLEARPCGFLAG(Used, USED)
 SETPCGFLAG(Used, USED)
 
-SETPCGFLAG(FileMapped, FILE_MAPPED)
-CLEARPCGFLAG(FileMapped, FILE_MAPPED)
-TESTPCGFLAG(FileMapped, FILE_MAPPED)
-
 SETPCGFLAG(Migration, MIGRATION)
 CLEARPCGFLAG(Migration, MIGRATION)
 TESTPCGFLAG(Migration, MIGRATION)
@@ -85,7 +72,7 @@ static inline void lock_page_cgroup(struct page_cgroup *pc)
 {
 	/*
 	 * Don't take this lock in IRQ context.
-	 * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION
+	 * This lock is for pc->mem_cgroup, USED, MIGRATION
 	 */
 	bit_spin_lock(PCG_LOCK, &pc->flags);
 }
@@ -95,24 +82,6 @@ static inline void unlock_page_cgroup(struct page_cgroup *pc)
 	bit_spin_unlock(PCG_LOCK, &pc->flags);
 }
 
-static inline void move_lock_page_cgroup(struct page_cgroup *pc,
-	unsigned long *flags)
-{
-	/*
-	 * We know updates to pc->flags of page cache's stats are from both of
-	 * usual context or IRQ context. Disable IRQ to avoid deadlock.
-	 */
-	local_irq_save(*flags);
-	bit_spin_lock(PCG_MOVE_LOCK, &pc->flags);
-}
-
-static inline void move_unlock_page_cgroup(struct page_cgroup *pc,
-	unsigned long *flags)
-{
-	bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags);
-	local_irq_restore(*flags);
-}
-
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct page_cgroup;
 
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 1cdd62a2788..fd07c4542ce 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -122,7 +122,6 @@ void unlink_anon_vmas(struct vm_area_struct *);
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
 void anon_vma_moveto_tail(struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
-void __anon_vma_link(struct vm_area_struct *);
 
 static inline void anon_vma_merge(struct vm_area_struct *vma,
 				  struct vm_area_struct *next)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e074e1e54f8..0c147a4260a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1514,7 +1514,7 @@ struct task_struct {
 #endif
 #ifdef CONFIG_CPUSETS
 	nodemask_t mems_allowed;	/* Protected by alloc_lock */
-	int mems_allowed_change_disable;
+	seqcount_t mems_allowed_seq;	/* Seqence no to catch updates */
 	int cpuset_mem_spread_rotor;
 	int cpuset_slab_spread_rotor;
 #endif
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3e60228e729..b86b5c20617 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -223,6 +223,7 @@ extern void lru_add_page_tail(struct zone* zone,
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
+extern void lru_add_drain_cpu(int cpu);
 extern int lru_add_drain_all(void);
 extern void rotate_reclaimable_page(struct page *page);
 extern void deactivate_page(struct page *page);
@@ -329,7 +330,6 @@ extern long total_swap_pages;
 extern void si_swapinfo(struct sysinfo *);
 extern swp_entry_t get_swap_page(void);
 extern swp_entry_t get_swap_page_of_type(int);
-extern int valid_swaphandles(swp_entry_t, unsigned long *);
 extern int add_swap_count_continuation(swp_entry_t, gfp_t);
 extern void swap_shmem_alloc(swp_entry_t);
 extern int swap_duplicate(swp_entry_t);