Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few hotfixes

 - various misc updates

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (108 commits)
  mm, memory_hotplug: move movable_node to the hotplug proper
  mm, memory_hotplug: drop CONFIG_MOVABLE_NODE
  mm, memory_hotplug: drop artificial restriction on online/offline
  mm: memcontrol: account slab stats per lruvec
  mm: memcontrol: per-lruvec stats infrastructure
  mm: memcontrol: use generic mod_memcg_page_state for kmem pages
  mm: memcontrol: use the node-native slab memory counters
  mm: vmstat: move slab statistics from zone to node counters
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_dstmem_prepare()
  mm/zswap.c: improve a size determination in zswap_frontswap_init()
  mm/zswap.c: delete an error message for a failed memory allocation in zswap_pool_create()
  mm/swapfile.c: sort swap entries before free
  mm/oom_kill: count global and memory cgroup oom kills
  mm: per-cgroup memory reclaim stats
  mm: kmemleak: treat vm_struct as alternative reference to vmalloc'ed objects
  mm: kmemleak: factor object reference updating out of scan_block()
  mm: kmemleak: slightly reduce the size of some structures on 64-bit architectures
  mm, mempolicy: don't check cpuset seqlock where it doesn't matter
  mm, cpuset: always use seqlock when changing task's nodemask
  mm, mempolicy: simplify rebinding mempolicies when updating cpusets
  ...

26 files changed, 566 insertions, 185 deletions

diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 99b490b4d05a..540354f94f83 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -31,10 +31,12 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 	return pte_modify(pte, newprot);
 }
 
+#ifndef huge_pte_clear
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
-				  pte_t *ptep)
+		    pte_t *ptep, unsigned long sz)
 {
 	pte_clear(mm, addr, ptep);
 }
+#endif
 
 #endif /* _ASM_GENERIC_HUGETLB_H */
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 962164d36506..e223d91b6439 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -358,6 +358,7 @@ extern void *alloc_large_system_hash(const char *tablename,
 #define HASH_EARLY	0x00000001	/* Allocating during early boot? */
 #define HASH_SMALL	0x00000002	/* sub-page allocation allowed, min
 					 * shift passed via *_hash_shift */
+#define HASH_ZERO	0x00000004	/* Zero allocated hash table */
 
 /* Only NUMA needs hash distribution. 64bit NUMA architectures have
  * sufficient vmalloc space.
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index d614c5ea1b5e..de179993e039 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -15,11 +15,3 @@
  * with any version that can compile the kernel
  */
 #define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
-
-/*
- * GCC does not warn about unused static inline functions for
- * -Wunused-function.  This turns out to avoid the need for complex #ifdef
- * directives.  Suppress the warning in clang as well.
- */
-#undef inline
-#define inline inline __attribute__((unused)) notrace
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 7deaae3dc87d..cd4bbe8242bd 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -66,18 +66,22 @@
 
 /*
  * Force always-inline if the user requests it so via the .config,
- * or if gcc is too old:
+ * or if gcc is too old.
+ * GCC does not warn about unused static inline functions for
+ * -Wunused-function.  This turns out to avoid the need for complex #ifdef
+ * directives.  Suppress the warning in clang as well by using "unused"
+ * function attribute, which is redundant but not harmful for gcc.
  */
 #if !defined(CONFIG_ARCH_SUPPORTS_OPTIMIZED_INLINING) ||		\
     !defined(CONFIG_OPTIMIZE_INLINING) || (__GNUC__ < 4)
-#define inline		inline		__attribute__((always_inline)) notrace
-#define __inline__	__inline__	__attribute__((always_inline)) notrace
-#define __inline	__inline	__attribute__((always_inline)) notrace
+#define inline inline		__attribute__((always_inline,unused)) notrace
+#define __inline__ __inline__	__attribute__((always_inline,unused)) notrace
+#define __inline __inline	__attribute__((always_inline,unused)) notrace
 #else
 /* A lot of inline functions can cause havoc with function tracing */
-#define inline		inline		notrace
-#define __inline__	__inline__	notrace
-#define __inline	__inline	notrace
+#define inline inline		__attribute__((unused)) notrace
+#define __inline__ __inline__	__attribute__((unused)) notrace
+#define __inline __inline	__attribute__((unused)) notrace
 #endif
 
 #define __always_inline	inline __attribute__((always_inline))
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f1fc9baa3509..bfef1e5734f8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -16,13 +16,10 @@
 #include <linux/sched.h>
 #include <linux/capability.h>
 #include <linux/cryptohash.h>
+#include <linux/set_memory.h>
 
 #include <net/sch_generic.h>
 
-#ifdef CONFIG_ARCH_HAS_SET_MEMORY
-#include <asm/set_memory.h>
-#endif
-
 #include <uapi/linux/filter.h>
 #include <uapi/linux/bpf.h>
 
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index a89d37e8b387..4c6656f1fee7 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -432,14 +432,13 @@ static inline void arch_alloc_page(struct page *page, int order) { }
 #endif
 
 struct page *
-__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
-		       struct zonelist *zonelist, nodemask_t *nodemask);
+__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid,
+							nodemask_t *nodemask);
 
 static inline struct page *
-__alloc_pages(gfp_t gfp_mask, unsigned int order,
-		struct zonelist *zonelist)
+__alloc_pages(gfp_t gfp_mask, unsigned int order, int preferred_nid)
 {
-	return __alloc_pages_nodemask(gfp_mask, order, zonelist, NULL);
+	return __alloc_pages_nodemask(gfp_mask, order, preferred_nid, NULL);
 }
 
 /*
@@ -452,7 +451,7 @@ __alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
 	VM_WARN_ON(!node_online(nid));
 
-	return __alloc_pages(gfp_mask, order, node_zonelist(nid, gfp_mask));
+	return __alloc_pages(gfp_mask, order, nid);
 }
 
 /*
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index a3762d49ba39..d3b3e8fcc717 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -113,6 +113,7 @@ extern unsigned long thp_get_unmapped_area(struct file *filp,
 extern void prep_transhuge_page(struct page *page);
 extern void free_transhuge_page(struct page *page);
 
+bool can_split_huge_page(struct page *page, int *pextra_pins);
 int split_huge_page_to_list(struct page *page, struct list_head *list);
 static inline int split_huge_page(struct page *page)
 {
@@ -231,6 +232,12 @@ static inline void prep_transhuge_page(struct page *page) {}
 
 #define thp_get_unmapped_area	NULL
 
+static inline bool
+can_split_huge_page(struct page *page, int *pextra_pins)
+{
+	BUILD_BUG();
+	return false;
+}
 static inline int
 split_huge_page_to_list(struct page *page, struct list_head *list)
 {
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b857fc8cc2ec..46bfb702e7d6 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -14,6 +14,30 @@ struct ctl_table;
 struct user_struct;
 struct mmu_gather;
 
+#ifndef is_hugepd
+/*
+ * Some architectures requires a hugepage directory format that is
+ * required to support multiple hugepage sizes. For example
+ * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
+ * introduced the same on powerpc. This allows for a more flexible hugepage
+ * pagetable layout.
+ */
+typedef struct { unsigned long pd; } hugepd_t;
+#define is_hugepd(hugepd) (0)
+#define __hugepd(x) ((hugepd_t) { (x) })
+static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+			      unsigned pdshift, unsigned long end,
+			      int write, struct page **pages, int *nr)
+{
+	return 0;
+}
+#else
+extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
+		       unsigned pdshift, unsigned long end,
+		       int write, struct page **pages, int *nr);
+#endif
+
+
 #ifdef CONFIG_HUGETLB_PAGE
 
 #include <linux/mempolicy.h>
@@ -113,19 +137,27 @@ extern struct list_head huge_boot_pages;
 
 pte_t *huge_pte_alloc(struct mm_struct *mm,
 			unsigned long addr, unsigned long sz);
-pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr);
+pte_t *huge_pte_offset(struct mm_struct *mm,
+		       unsigned long addr, unsigned long sz);
 int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep);
 struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address,
 			      int write);
+struct page *follow_huge_pd(struct vm_area_struct *vma,
+			    unsigned long address, hugepd_t hpd,
+			    int flags, int pdshift);
 struct page *follow_huge_pmd(struct mm_struct *mm, unsigned long address,
 				pmd_t *pmd, int flags);
 struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int flags);
+struct page *follow_huge_pgd(struct mm_struct *mm, unsigned long address,
+			     pgd_t *pgd, int flags);
+
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pud);
 unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
+bool is_hugetlb_entry_migration(pte_t pte);
 #else /* !CONFIG_HUGETLB_PAGE */
 
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
@@ -147,8 +179,10 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 static inline void hugetlb_show_meminfo(void)
 {
 }
+#define follow_huge_pd(vma, addr, hpd, flags, pdshift) NULL
 #define follow_huge_pmd(mm, addr, pmd, flags)	NULL
 #define follow_huge_pud(mm, addr, pud, flags)	NULL
+#define follow_huge_pgd(mm, addr, pgd, flags)	NULL
 #define prepare_hugepage_range(file, addr, len)	(-EINVAL)
 #define pmd_huge(x)	0
 #define pud_huge(x)	0
@@ -157,7 +191,7 @@ static inline void hugetlb_show_meminfo(void)
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
 #define hugetlb_mcopy_atomic_pte(dst_mm, dst_pte, dst_vma, dst_addr, \
 				src_addr, pagep)	({ BUG(); 0; })
-#define huge_pte_offset(mm, address)	0
+#define huge_pte_offset(mm, address, sz)	0
 static inline int dequeue_hwpoisoned_huge_page(struct page *page)
 {
 	return 0;
@@ -217,29 +251,6 @@ static inline int pud_write(pud_t pud)
 }
 #endif
 
-#ifndef is_hugepd
-/*
- * Some architectures requires a hugepage directory format that is
- * required to support multiple hugepage sizes. For example
- * a4fe3ce76 "powerpc/mm: Allow more flexible layouts for hugepage pagetables"
- * introduced the same on powerpc. This allows for a more flexible hugepage
- * pagetable layout.
- */
-typedef struct { unsigned long pd; } hugepd_t;
-#define is_hugepd(hugepd) (0)
-#define __hugepd(x) ((hugepd_t) { (x) })
-static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-			      unsigned pdshift, unsigned long end,
-			      int write, struct page **pages, int *nr)
-{
-	return 0;
-}
-#else
-extern int gup_huge_pd(hugepd_t hugepd, unsigned long addr,
-		       unsigned pdshift, unsigned long end,
-		       int write, struct page **pages, int *nr);
-#endif
-
 #define HUGETLB_ANON_FILE "anon_hugepage"
 
 enum {
@@ -466,7 +477,11 @@ extern int dissolve_free_huge_pages(unsigned long start_pfn,
 static inline bool hugepage_migration_supported(struct hstate *h)
 {
 #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
-	return huge_page_shift(h) == PMD_SHIFT;
+	if ((huge_page_shift(h) == PMD_SHIFT) ||
+		(huge_page_shift(h) == PGDIR_SHIFT))
+		return true;
+	else
+		return false;
 #else
 	return false;
 #endif
@@ -501,6 +516,14 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 {
 	atomic_long_sub(l, &mm->hugetlb_usage);
 }
+
+#ifndef set_huge_swap_pte_at
+static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep, pte_t pte, unsigned long sz)
+{
+	set_huge_pte_at(mm, addr, ptep, pte);
+}
+#endif
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 #define alloc_huge_page(v, a, r) NULL
@@ -518,6 +541,11 @@ struct hstate {};
 #define vma_mmu_pagesize(v) PAGE_SIZE
 #define huge_page_order(h) 0
 #define huge_page_shift(h) PAGE_SHIFT
+static inline bool hstate_is_gigantic(struct hstate *h)
+{
+	return false;
+}
+
 static inline unsigned int pages_per_huge_page(struct hstate *h)
 {
 	return 1;
@@ -545,6 +573,11 @@ static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m)
 static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 {
 }
+
+static inline void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
+					pte_t *ptep, pte_t pte, unsigned long sz)
+{
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 1c2a32829620..590343f6c1b1 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -22,6 +22,7 @@
 #define __KMEMLEAK_H
 
 #include <linux/slab.h>
+#include <linux/vmalloc.h>
 
 #ifdef CONFIG_DEBUG_KMEMLEAK
 
@@ -30,6 +31,8 @@ extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			   gfp_t gfp) __ref;
 extern void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
 				  gfp_t gfp) __ref;
+extern void kmemleak_vmalloc(const struct vm_struct *area, size_t size,
+			     gfp_t gfp) __ref;
 extern void kmemleak_free(const void *ptr) __ref;
 extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;
@@ -81,6 +84,10 @@ static inline void kmemleak_alloc_percpu(const void __percpu *ptr, size_t size,
 					 gfp_t gfp)
 {
 }
+static inline void kmemleak_vmalloc(const struct vm_struct *area, size_t size,
+				    gfp_t gfp)
+{
+}
 static inline void kmemleak_free(const void *ptr)
 {
 }
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 8098695e5d8d..77d427974f57 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -57,10 +57,6 @@ struct memblock {
 
 extern struct memblock memblock;
 extern int memblock_debug;
-#ifdef CONFIG_MOVABLE_NODE
-/* If movable_node boot option specified */
-extern bool movable_node_enabled;
-#endif /* CONFIG_MOVABLE_NODE */
 
 #ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
 #define __init_memblock __meminit
@@ -169,27 +165,11 @@ void __next_reserved_mem_region(u64 *idx, phys_addr_t *out_start,
 	     i != (u64)ULLONG_MAX;					\
 	     __next_reserved_mem_region(&i, p_start, p_end))
 
-#ifdef CONFIG_MOVABLE_NODE
 static inline bool memblock_is_hotpluggable(struct memblock_region *m)
 {
 	return m->flags & MEMBLOCK_HOTPLUG;
 }
 
-static inline bool __init_memblock movable_node_is_enabled(void)
-{
-	return movable_node_enabled;
-}
-#else
-static inline bool memblock_is_hotpluggable(struct memblock_region *m)
-{
-	return false;
-}
-static inline bool movable_node_is_enabled(void)
-{
-	return false;
-}
-#endif
-
 static inline bool memblock_is_mirror(struct memblock_region *m)
 {
 	return m->flags & MEMBLOCK_MIRROR;
@@ -296,7 +276,6 @@ phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
 
 phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
 
-#ifdef CONFIG_MOVABLE_NODE
 /*
  * Set the allocation direction to bottom-up or top-down.
  */
@@ -314,10 +293,6 @@ static inline bool memblock_bottom_up(void)
 {
 	return memblock.bottom_up;
 }
-#else
-static inline void __init memblock_set_bottom_up(bool enable) {}
-static inline bool memblock_bottom_up(void) { return false; }
-#endif
 
 /* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
 #define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 899949bbb2f9..3914e3dd6168 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -26,7 +26,8 @@
 #include <linux/page_counter.h>
 #include <linux/vmpressure.h>
 #include <linux/eventfd.h>
-#include <linux/mmzone.h>
+#include <linux/mm.h>
+#include <linux/vmstat.h>
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
 
@@ -44,8 +45,6 @@ enum memcg_stat_item {
 	MEMCG_SOCK,
 	/* XXX: why are these zone and not node counters? */
 	MEMCG_KERNEL_STACK_KB,
-	MEMCG_SLAB_RECLAIMABLE,
-	MEMCG_SLAB_UNRECLAIMABLE,
 	MEMCG_NR_STAT,
 };
 
@@ -100,11 +99,16 @@ struct mem_cgroup_reclaim_iter {
 	unsigned int generation;
 };
 
+struct lruvec_stat {
+	long count[NR_VM_NODE_STAT_ITEMS];
+};
+
 /*
  * per-zone information in memory controller.
  */
 struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
+	struct lruvec_stat __percpu *lruvec_stat;
 	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
 
 	struct mem_cgroup_reclaim_iter	iter[DEF_PRIORITY + 1];
@@ -357,6 +361,17 @@ static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 }
 struct mem_cgroup *mem_cgroup_from_id(unsigned short id);
 
+static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
+{
+	struct mem_cgroup_per_node *mz;
+
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	return mz->memcg;
+}
+
 /**
  * parent_mem_cgroup - find the accounting parent of a memcg
  * @memcg: memcg whose parent to find
@@ -487,23 +502,18 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 	return val;
 }
 
-static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx, int val)
+static inline void __mod_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx, int val)
 {
 	if (!mem_cgroup_disabled())
-		this_cpu_add(memcg->stat->count[idx], val);
+		__this_cpu_add(memcg->stat->count[idx], val);
 }
 
-static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
-{
-	mod_memcg_state(memcg, idx, 1);
-}
-
-static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+static inline void mod_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx, int val)
 {
-	mod_memcg_state(memcg, idx, -1);
+	if (!mem_cgroup_disabled())
+		this_cpu_add(memcg->stat->count[idx], val);
 }
 
 /**
@@ -523,6 +533,13 @@ static inline void dec_memcg_state(struct mem_cgroup *memcg,
  *
  * Kernel pages are an exception to this, since they'll never move.
  */
+static inline void __mod_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx, int val)
+{
+	if (page->mem_cgroup)
+		__mod_memcg_state(page->mem_cgroup, idx, val);
+}
+
 static inline void mod_memcg_page_state(struct page *page,
 					enum memcg_stat_item idx, int val)
 {
@@ -530,24 +547,99 @@ static inline void mod_memcg_page_state(struct page *page,
 		mod_memcg_state(page->mem_cgroup, idx, val);
 }
 
-static inline void inc_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
+					      enum node_stat_item idx)
 {
-	mod_memcg_page_state(page, idx, 1);
+	struct mem_cgroup_per_node *pn;
+	long val = 0;
+	int cpu;
+
+	if (mem_cgroup_disabled())
+		return node_page_state(lruvec_pgdat(lruvec), idx);
+
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	for_each_possible_cpu(cpu)
+		val += per_cpu(pn->lruvec_stat->count[idx], cpu);
+
+	if (val < 0)
+		val = 0;
+
+	return val;
 }
 
-static inline void dec_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline void __mod_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx, int val)
 {
-	mod_memcg_page_state(page, idx, -1);
+	struct mem_cgroup_per_node *pn;
+
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+	if (mem_cgroup_disabled())
+		return;
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	__mod_memcg_state(pn->memcg, idx, val);
+	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+}
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	struct mem_cgroup_per_node *pn;
+
+	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+	if (mem_cgroup_disabled())
+		return;
+	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
+	mod_memcg_state(pn->memcg, idx, val);
+	this_cpu_add(pn->lruvec_stat->count[idx], val);
+}
+
+static inline void __mod_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx, int val)
+{
+	struct mem_cgroup_per_node *pn;
+
+	__mod_node_page_state(page_pgdat(page), idx, val);
+	if (mem_cgroup_disabled() || !page->mem_cgroup)
+		return;
+	__mod_memcg_state(page->mem_cgroup, idx, val);
+	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
+	__this_cpu_add(pn->lruvec_stat->count[idx], val);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	struct mem_cgroup_per_node *pn;
+
+	mod_node_page_state(page_pgdat(page), idx, val);
+	if (mem_cgroup_disabled() || !page->mem_cgroup)
+		return;
+	mod_memcg_state(page->mem_cgroup, idx, val);
+	pn = page->mem_cgroup->nodeinfo[page_to_nid(page)];
+	this_cpu_add(pn->lruvec_stat->count[idx], val);
 }
 
 unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
-static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
-					     enum vm_event_item idx)
+static inline void count_memcg_events(struct mem_cgroup *memcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
+{
+	if (!mem_cgroup_disabled())
+		this_cpu_add(memcg->stat->events[idx], count);
+}
+
+static inline void count_memcg_page_event(struct page *page,
+					  enum memcg_stat_item idx)
+{
+	if (page->mem_cgroup)
+		count_memcg_events(page->mem_cgroup, idx, 1);
+}
+
+static inline void count_memcg_event_mm(struct mm_struct *mm,
+					enum vm_event_item idx)
 {
 	struct mem_cgroup *memcg;
 
@@ -556,8 +648,11 @@ static inline void mem_cgroup_count_vm_event(struct mm_struct *mm,
 
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
-	if (likely(memcg))
+	if (likely(memcg)) {
 		this_cpu_inc(memcg->stat->events[idx]);
+		if (idx == OOM_KILL)
+			cgroup_file_notify(&memcg->events_file);
+	}
 	rcu_read_unlock();
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -675,6 +770,11 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id)
 	return NULL;
 }
 
+static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
+{
+	return NULL;
+}
+
 static inline bool mem_cgroup_online(struct mem_cgroup *memcg)
 {
 	return true;
@@ -745,19 +845,21 @@ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg,
 	return 0;
 }
 
-static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx,
-				   int nr)
+static inline void __mod_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx,
+				     int nr)
 {
 }
 
-static inline void inc_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+static inline void mod_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx,
+				   int nr)
 {
 }
 
-static inline void dec_memcg_state(struct mem_cgroup *memcg,
-				   enum memcg_stat_item idx)
+static inline void __mod_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx,
+					  int nr)
 {
 }
 
@@ -767,14 +869,34 @@ static inline void mod_memcg_page_state(struct page *page,
 {
 }
 
-static inline void inc_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
+					      enum node_stat_item idx)
 {
+	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void dec_memcg_page_state(struct page *page,
-					enum memcg_stat_item idx)
+static inline void __mod_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx, int val)
+{
+	__mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void mod_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx, int val)
+{
+	mod_node_page_state(lruvec_pgdat(lruvec), idx, val);
+}
+
+static inline void __mod_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx, int val)
 {
+	__mod_node_page_state(page_pgdat(page), idx, val);
+}
+
+static inline void mod_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx, int val)
+{
+	mod_node_page_state(page_pgdat(page), idx, val);
 }
 
 static inline
@@ -789,12 +911,119 @@ static inline void mem_cgroup_split_huge_fixup(struct page *head)
 {
 }
 
+static inline void count_memcg_events(struct mem_cgroup *memcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
+{
+}
+
+static inline void count_memcg_page_event(struct page *page,
+					  enum memcg_stat_item idx)
+{
+}
+
 static inline
-void mem_cgroup_count_vm_event(struct mm_struct *mm, enum vm_event_item idx)
+void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
 #endif /* CONFIG_MEMCG */
 
+static inline void __inc_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx)
+{
+	__mod_memcg_state(memcg, idx, 1);
+}
+
+static inline void __dec_memcg_state(struct mem_cgroup *memcg,
+				     enum memcg_stat_item idx)
+{
+	__mod_memcg_state(memcg, idx, -1);
+}
+
+static inline void __inc_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx)
+{
+	__mod_memcg_page_state(page, idx, 1);
+}
+
+static inline void __dec_memcg_page_state(struct page *page,
+					  enum memcg_stat_item idx)
+{
+	__mod_memcg_page_state(page, idx, -1);
+}
+
+static inline void __inc_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx)
+{
+	__mod_lruvec_state(lruvec, idx, 1);
+}
+
+static inline void __dec_lruvec_state(struct lruvec *lruvec,
+				      enum node_stat_item idx)
+{
+	__mod_lruvec_state(lruvec, idx, -1);
+}
+
+static inline void __inc_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx)
+{
+	__mod_lruvec_page_state(page, idx, 1);
+}
+
+static inline void __dec_lruvec_page_state(struct page *page,
+					   enum node_stat_item idx)
+{
+	__mod_lruvec_page_state(page, idx, -1);
+}
+
+static inline void inc_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx)
+{
+	mod_memcg_state(memcg, idx, 1);
+}
+
+static inline void dec_memcg_state(struct mem_cgroup *memcg,
+				   enum memcg_stat_item idx)
+{
+	mod_memcg_state(memcg, idx, -1);
+}
+
+static inline void inc_memcg_page_state(struct page *page,
+					enum memcg_stat_item idx)
+{
+	mod_memcg_page_state(page, idx, 1);
+}
+
+static inline void dec_memcg_page_state(struct page *page,
+					enum memcg_stat_item idx)
+{
+	mod_memcg_page_state(page, idx, -1);
+}
+
+static inline void inc_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx)
+{
+	mod_lruvec_state(lruvec, idx, 1);
+}
+
+static inline void dec_lruvec_state(struct lruvec *lruvec,
+				    enum node_stat_item idx)
+{
+	mod_lruvec_state(lruvec, idx, -1);
+}
+
+static inline void inc_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx)
+{
+	mod_lruvec_page_state(page, idx, 1);
+}
+
+static inline void dec_lruvec_page_state(struct page *page,
+					 enum node_stat_item idx)
+{
+	mod_lruvec_page_state(page, idx, -1);
+}
+
 #ifdef CONFIG_CGROUP_WRITEBACK
 
 struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg);
@@ -886,19 +1115,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
-/**
- * memcg_kmem_update_page_stat - update kmem page state statistics
- * @page: the page
- * @idx: page state item to account
- * @val: number of pages (positive or negative)
- */
-static inline void memcg_kmem_update_page_stat(struct page *page,
-				enum memcg_stat_item idx, int val)
-{
-	if (memcg_kmem_enabled() && page->mem_cgroup)
-		this_cpu_add(page->mem_cgroup->stat->count[idx], val);
-}
-
 #else
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
@@ -921,10 +1137,6 @@ static inline void memcg_put_cache_ids(void)
 {
 }
 
-static inline void memcg_kmem_update_page_stat(struct page *page,
-				enum memcg_stat_item idx, int val)
-{
-}
 #endif /* CONFIG_MEMCG && !CONFIG_SLOB */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 134a2f69c21a..c8a5056a5ae0 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -14,6 +14,20 @@ struct memory_block;
 struct resource;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+/*
+ * Return page for the valid pfn only if the page is online. All pfn
+ * walkers which rely on the fully initialized page->flags and others
+ * should use this rather than pfn_valid && pfn_to_page
+ */
+#define pfn_to_online_page(pfn)				\
+({							\
+	struct page *___page = NULL;			\
+	unsigned long ___nr = pfn_to_section_nr(pfn);	\
+							\
+	if (___nr < NR_MEM_SECTIONS && online_section_nr(___nr))\
+		___page = pfn_to_page(pfn);		\
+	___page;					\
+})
 
 /*
  * Types for free bootmem stored in page->lru.next. These have to be in
@@ -101,6 +115,12 @@ extern void __online_page_free(struct page *page);
 extern int try_online_node(int nid);
 
 extern bool memhp_auto_online;
+/* If movable_node boot option specified */
+extern bool movable_node_enabled;
+static inline bool movable_node_is_enabled(void)
+{
+	return movable_node_enabled;
+}
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 extern bool is_pageblock_removable_nolock(struct page *page);
@@ -109,9 +129,9 @@ extern int __remove_pages(struct zone *zone, unsigned long start_pfn,
 	unsigned long nr_pages);
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
-/* reasonably generic interface to expand the physical pages in a zone  */
-extern int __add_pages(int nid, struct zone *zone, unsigned long start_pfn,
-	unsigned long nr_pages);
+/* reasonably generic interface to expand the physical pages */
+extern int __add_pages(int nid, unsigned long start_pfn,
+	unsigned long nr_pages, bool want_memblock);
 
 #ifdef CONFIG_NUMA
 extern int memory_add_physaddr_to_nid(u64 start);
@@ -203,6 +223,14 @@ extern void set_zone_contiguous(struct zone *zone);
 extern void clear_zone_contiguous(struct zone *zone);
 
 #else /* ! CONFIG_MEMORY_HOTPLUG */
+#define pfn_to_online_page(pfn)			\
+({						\
+	struct page *___page = NULL;		\
+	if (pfn_valid(pfn))			\
+		___page = pfn_to_page(pfn);	\
+	___page;				\
+ })
+
 /*
  * Stub functions for when hotplug is off
  */
@@ -244,6 +272,10 @@ static inline void put_online_mems(void) {}
 static inline void mem_hotplug_begin(void) {}
 static inline void mem_hotplug_done(void) {}
 
+static inline bool movable_node_is_enabled(void)
+{
+	return false;
+}
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
@@ -274,18 +306,19 @@ extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn,
 		void *arg, int (*func)(struct memory_block *, void *));
 extern int add_memory(int nid, u64 start, u64 size);
 extern int add_memory_resource(int nid, struct resource *resource, bool online);
-extern int zone_for_memory(int nid, u64 start, u64 size, int zone_default,
-		bool for_device);
-extern int arch_add_memory(int nid, u64 start, u64 size, bool for_device);
+extern int arch_add_memory(int nid, u64 start, u64 size, bool want_memblock);
+extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long nr_pages);
 extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
 extern bool is_memblock_offlined(struct memory_block *mem);
 extern void remove_memory(int nid, u64 start, u64 size);
-extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn);
+extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn);
 extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms,
 		unsigned long map_offset);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
-extern bool zone_can_shift(unsigned long pfn, unsigned long nr_pages,
-			  enum zone_type target, int *zone_shift);
-
+extern bool allow_online_pfn_range(int nid, unsigned long pfn, unsigned long nr_pages,
+		int online_type);
+extern struct zone *default_zone_for_pfn(int nid, unsigned long pfn,
+		unsigned long nr_pages);
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 5f4d8281832b..3a58b4be1b0c 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -142,11 +142,10 @@ bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
-extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new,
-				enum mpol_rebind_step step);
+extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new);
 extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
 
-extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
+extern int huge_node(struct vm_area_struct *vma,
 				unsigned long addr, gfp_t gfp_flags,
 				struct mempolicy **mpol, nodemask_t **nodemask);
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
@@ -260,8 +259,7 @@ static inline void numa_default_policy(void)
 }
 
 static inline void mpol_rebind_task(struct task_struct *tsk,
-				const nodemask_t *new,
-				enum mpol_rebind_step step)
+				const nodemask_t *new)
 {
 }
 
@@ -269,13 +267,13 @@ static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
 {
 }
 
-static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
+static inline int huge_node(struct vm_area_struct *vma,
 				unsigned long addr, gfp_t gfp_flags,
 				struct mempolicy **mpol, nodemask_t **nodemask)
 {
 	*mpol = NULL;
 	*nodemask = NULL;
-	return node_zonelist(0, gfp_flags);
+	return 0;
 }
 
 static inline bool init_nodemask_of_mempolicy(nodemask_t *m)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index ef6a13b7bd3e..7e8f100cb56d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -125,8 +125,6 @@ enum zone_stat_item {
 	NR_ZONE_UNEVICTABLE,
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
-	NR_SLAB_RECLAIMABLE,
-	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
 	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
@@ -152,6 +150,8 @@ enum node_stat_item {
 	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
 	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
 	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_SLAB_RECLAIMABLE,
+	NR_SLAB_UNRECLAIMABLE,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
 	WORKINGSET_REFAULT,
@@ -533,6 +533,22 @@ static inline bool zone_is_empty(struct zone *zone)
 }
 
 /*
+ * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
+ * intersection with the given zone
+ */
+static inline bool zone_intersects(struct zone *zone,
+		unsigned long start_pfn, unsigned long nr_pages)
+{
+	if (zone_is_empty(zone))
+		return false;
+	if (start_pfn >= zone_end_pfn(zone) ||
+	    start_pfn + nr_pages <= zone->zone_start_pfn)
+		return false;
+
+	return true;
+}
+
+/*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
  * queues ("queue_length >> 12") during an aging round.
@@ -772,7 +788,7 @@ enum memmap_context {
 	MEMMAP_EARLY,
 	MEMMAP_HOTPLUG,
 };
-extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
+extern void init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
 				     unsigned long size);
 
 extern void lruvec_init(struct lruvec *lruvec);
@@ -1144,9 +1160,10 @@ extern unsigned long usemap_size(void);
  */
 #define	SECTION_MARKED_PRESENT	(1UL<<0)
 #define SECTION_HAS_MEM_MAP	(1UL<<1)
-#define SECTION_MAP_LAST_BIT	(1UL<<2)
+#define SECTION_IS_ONLINE	(1UL<<2)
+#define SECTION_MAP_LAST_BIT	(1UL<<3)
 #define SECTION_MAP_MASK	(~(SECTION_MAP_LAST_BIT-1))
-#define SECTION_NID_SHIFT	2
+#define SECTION_NID_SHIFT	3
 
 static inline struct page *__section_mem_map_addr(struct mem_section *section)
 {
@@ -1175,11 +1192,30 @@ static inline int valid_section_nr(unsigned long nr)
 	return valid_section(__nr_to_section(nr));
 }
 
+static inline int online_section(struct mem_section *section)
+{
+	return (section && (section->section_mem_map & SECTION_IS_ONLINE));
+}
+
+static inline int online_section_nr(unsigned long nr)
+{
+	return online_section(__nr_to_section(nr));
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
+#ifdef CONFIG_MEMORY_HOTREMOVE
+void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn);
+#endif
+#endif
+
 static inline struct mem_section *__pfn_to_section(unsigned long pfn)
 {
 	return __nr_to_section(pfn_to_section_nr(pfn));
 }
 
+extern int __highest_present_section_nr;
+
 #ifndef CONFIG_HAVE_ARCH_PFN_VALID
 static inline int pfn_valid(unsigned long pfn)
 {
@@ -1251,10 +1287,15 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
 #ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
 /*
  * pfn_valid() is meant to be able to tell if a given PFN has valid memmap
- * associated with it or not. In FLATMEM, it is expected that holes always
- * have valid memmap as long as there is valid PFNs either side of the hole.
- * In SPARSEMEM, it is assumed that a valid section has a memmap for the
- * entire section.
+ * associated with it or not. This means that a struct page exists for this
+ * pfn. The caller cannot assume the page is fully initialized in general.
+ * Hotplugable pages might not have been onlined yet. pfn_to_online_page()
+ * will ensure the struct page is fully online and initialized. Special pages
+ * (e.g. ZONE_DEVICE) are never onlined and should be treated accordingly.
+ *
+ * In FLATMEM, it is expected that holes always have valid memmap as long as
+ * there is valid PFNs either side of the hole. In SPARSEMEM, it is assumed
+ * that a valid section has a memmap for the entire section.
  *
  * However, an ARM, and maybe other embedded architectures in the future
  * free memmap backing holes to save memory on the assumption the memmap is
diff --git a/include/linux/node.h b/include/linux/node.h
index 2115ad5d6f19..d1751beb462c 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -30,9 +30,38 @@ struct memory_block;
 extern struct node *node_devices[];
 typedef  void (*node_registration_func_t)(struct node *);
 
+#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_NUMA)
+extern int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages);
+#else
+static inline int link_mem_sections(int nid, unsigned long start_pfn, unsigned long nr_pages)
+{
+	return 0;
+}
+#endif
+
 extern void unregister_node(struct node *node);
 #ifdef CONFIG_NUMA
-extern int register_one_node(int nid);
+/* Core of the node registration - only memory hotplug should use this */
+extern int __register_one_node(int nid);
+
+/* Registers an online node */
+static inline int register_one_node(int nid)
+{
+	int error = 0;
+
+	if (node_online(nid)) {
+		struct pglist_data *pgdat = NODE_DATA(nid);
+
+		error = __register_one_node(nid);
+		if (error)
+			return error;
+		/* link memory sections under this node */
+		error = link_mem_sections(nid, pgdat->node_start_pfn, pgdat->node_spanned_pages);
+	}
+
+	return error;
+}
+
 extern void unregister_one_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
@@ -46,6 +75,10 @@ extern void register_hugetlbfs_with_node(node_registration_func_t doregister,
 					 node_registration_func_t unregister);
 #endif
 #else
+static inline int __register_one_node(int nid)
+{
+	return 0;
+}
 static inline int register_one_node(int nid)
 {
 	return 0;
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index f746e44d4046..cf0b91c3ec12 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -387,11 +387,7 @@ enum node_states {
 #else
 	N_HIGH_MEMORY = N_NORMAL_MEMORY,
 #endif
-#ifdef CONFIG_MOVABLE_NODE
 	N_MEMORY,		/* The node has memory(regular, high, movable) */
-#else
-	N_MEMORY = N_HIGH_MEMORY,
-#endif
 	N_CPU,		/* The node has one or more cpus */
 	NR_NODE_STATES
 };
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 6b5818d6de32..d33e3280c8ad 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -326,11 +326,14 @@ PAGEFLAG_FALSE(HighMem)
 #ifdef CONFIG_SWAP
 static __always_inline int PageSwapCache(struct page *page)
 {
+#ifdef CONFIG_THP_SWAP
+	page = compound_head(page);
+#endif
 	return PageSwapBacked(page) && test_bit(PG_swapcache, &page->flags);
 
 }
-SETPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
-CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_COMPOUND)
+SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
+CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
 #else
 PAGEFLAG_FALSE(SwapCache)
 #endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c4ca7433d9d..5e8759b1b428 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -904,7 +904,7 @@ struct task_struct {
 #ifdef CONFIG_NUMA
 	/* Protected by alloc_lock: */
 	struct mempolicy		*mempolicy;
-	short				il_next;
+	short				il_prev;
 	short				pref_node_fork;
 #endif
 #ifdef CONFIG_NUMA_BALANCING
diff --git a/include/linux/set_memory.h b/include/linux/set_memory.h
new file mode 100644
index 000000000000..e5140648f638
--- /dev/null
+++ b/include/linux/set_memory.h
@@ -0,0 +1,20 @@
+/*
+ * Copyright 2017, Michael Ellerman, IBM Corporation.
+ *
+ * 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;
+ */
+#ifndef _LINUX_SET_MEMORY_H_
+#define _LINUX_SET_MEMORY_H_
+
+#ifdef CONFIG_ARCH_HAS_SET_MEMORY
+#include <asm/set_memory.h>
+#else
+static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }
+static inline int set_memory_x(unsigned long addr,  int numpages) { return 0; }
+static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
+#endif
+
+#endif /* _LINUX_SET_MEMORY_H_ */
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 93315d6b21a8..cc0faf3a90be 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -41,12 +41,31 @@ struct kmem_cache_cpu {
 	void **freelist;	/* Pointer to next available object */
 	unsigned long tid;	/* Globally unique transaction id */
 	struct page *page;	/* The slab from which we are allocating */
+#ifdef CONFIG_SLUB_CPU_PARTIAL
 	struct page *partial;	/* Partially allocated frozen slabs */
+#endif
 #ifdef CONFIG_SLUB_STATS
 	unsigned stat[NR_SLUB_STAT_ITEMS];
 #endif
 };
 
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+#define slub_percpu_partial(c)		((c)->partial)
+
+#define slub_set_percpu_partial(c, p)		\
+({						\
+	slub_percpu_partial(c) = (p)->next;	\
+})
+
+#define slub_percpu_partial_read_once(c)     READ_ONCE(slub_percpu_partial(c))
+#else
+#define slub_percpu_partial(c)			NULL
+
+#define slub_set_percpu_partial(c, p)
+
+#define slub_percpu_partial_read_once(c)	NULL
+#endif // CONFIG_SLUB_CPU_PARTIAL
+
 /*
  * Word size structure that can be atomically updated or read and that
  * contains both the order and the number of objects that a slab of the
@@ -67,7 +86,9 @@ struct kmem_cache {
 	int size;		/* The size of an object including meta data */
 	int object_size;	/* The size of an object without meta data */
 	int offset;		/* Free pointer offset. */
+#ifdef CONFIG_SLUB_CPU_PARTIAL
 	int cpu_partial;	/* Number of per cpu partial objects to keep around */
+#endif
 	struct kmem_cache_order_objects oo;
 
 	/* Allocation and freeing of slabs */
@@ -79,9 +100,9 @@ struct kmem_cache {
 	int inuse;		/* Offset to metadata */
 	int align;		/* Alignment */
 	int reserved;		/* Reserved bytes at the end of slabs */
+	int red_left_pad;	/* Left redzone padding size */
 	const char *name;	/* Name (only for display!) */
 	struct list_head list;	/* List of slab caches */
-	int red_left_pad;	/* Left redzone padding size */
 #ifdef CONFIG_SYSFS
 	struct kobject kobj;	/* For sysfs */
 	struct work_struct kobj_remove_work;
@@ -112,6 +133,17 @@ struct kmem_cache {
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
+#ifdef CONFIG_SLUB_CPU_PARTIAL
+#define slub_cpu_partial(s)		((s)->cpu_partial)
+#define slub_set_cpu_partial(s, n)		\
+({						\
+	slub_cpu_partial(s) = (n);		\
+})
+#else
+#define slub_cpu_partial(s)		(0)
+#define slub_set_cpu_partial(s, n)
+#endif // CONFIG_SLUB_CPU_PARTIAL
+
 #ifdef CONFIG_SYSFS
 #define SLAB_SUPPORTS_SYSFS
 void sysfs_slab_release(struct kmem_cache *);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index ba5882419a7d..5ab1c98c7d27 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -353,7 +353,7 @@ extern struct address_space *swapper_spaces[];
 		>> SWAP_ADDRESS_SPACE_SHIFT])
 extern unsigned long total_swapcache_pages(void);
 extern void show_swap_cache_info(void);
-extern int add_to_swap(struct page *, struct list_head *list);
+extern int add_to_swap(struct page *page);
 extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t);
 extern int __add_to_swap_cache(struct page *page, swp_entry_t entry);
 extern void __delete_from_swap_cache(struct page *);
@@ -386,15 +386,15 @@ static inline long get_nr_swap_pages(void)
 }
 
 extern void si_swapinfo(struct sysinfo *);
-extern swp_entry_t get_swap_page(void);
+extern swp_entry_t get_swap_page(struct page *page);
+extern void put_swap_page(struct page *page, swp_entry_t entry);
 extern swp_entry_t get_swap_page_of_type(int);
-extern int get_swap_pages(int n, swp_entry_t swp_entries[]);
+extern int get_swap_pages(int n, bool cluster, swp_entry_t swp_entries[]);
 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);
 extern int swapcache_prepare(swp_entry_t);
 extern void swap_free(swp_entry_t);
-extern void swapcache_free(swp_entry_t);
 extern void swapcache_free_entries(swp_entry_t *entries, int n);
 extern int free_swap_and_cache(swp_entry_t);
 extern int swap_type_of(dev_t, sector_t, struct block_device **);
@@ -453,7 +453,7 @@ static inline void swap_free(swp_entry_t swp)
 {
 }
 
-static inline void swapcache_free(swp_entry_t swp)
+static inline void put_swap_page(struct page *page, swp_entry_t swp)
 {
 }
 
@@ -473,7 +473,7 @@ static inline struct page *lookup_swap_cache(swp_entry_t swp)
 	return NULL;
 }
 
-static inline int add_to_swap(struct page *page, struct list_head *list)
+static inline int add_to_swap(struct page *page)
 {
 	return 0;
 }
@@ -515,7 +515,7 @@ static inline int try_to_free_swap(struct page *page)
 	return 0;
 }
 
-static inline swp_entry_t get_swap_page(void)
+static inline swp_entry_t get_swap_page(struct page *page)
 {
 	swp_entry_t entry;
 	entry.val = 0;
@@ -548,7 +548,7 @@ static inline int mem_cgroup_swappiness(struct mem_cgroup *mem)
 #ifdef CONFIG_MEMCG_SWAP
 extern void mem_cgroup_swapout(struct page *page, swp_entry_t entry);
 extern int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry);
-extern void mem_cgroup_uncharge_swap(swp_entry_t entry);
+extern void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages);
 extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg);
 extern bool mem_cgroup_swap_full(struct page *page);
 #else
@@ -562,7 +562,8 @@ static inline int mem_cgroup_try_charge_swap(struct page *page,
 	return 0;
 }
 
-static inline void mem_cgroup_uncharge_swap(swp_entry_t entry)
+static inline void mem_cgroup_uncharge_swap(swp_entry_t entry,
+					    unsigned int nr_pages)
 {
 }
 
diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
index 145306bdc92f..b2b8ec7bda3f 100644
--- a/include/linux/swap_cgroup.h
+++ b/include/linux/swap_cgroup.h
@@ -7,7 +7,8 @@
 
 extern unsigned short swap_cgroup_cmpxchg(swp_entry_t ent,
 					unsigned short old, unsigned short new);
-extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
+extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
+					 unsigned int nr_ents);
 extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
 extern int swap_cgroup_swapon(int type, unsigned long max_pages);
 extern void swap_cgroup_swapoff(int type);
@@ -15,7 +16,8 @@ extern void swap_cgroup_swapoff(int type);
 #else
 
 static inline
-unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id,
+				  unsigned int nr_ents)
 {
 	return 0;
 }
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index be3ab2d13adf..37e8d31a4632 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -41,6 +41,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		PAGEOUTRUN, PGROTATED,
 		DROP_PAGECACHE, DROP_SLAB,
+		OOM_KILL,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
 		NUMA_HUGE_PTE_UPDATES,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 613771909b6e..b3d85f30d424 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -3,7 +3,6 @@
 
 #include <linux/types.h>
 #include <linux/percpu.h>
-#include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/vm_event_item.h>
 #include <linux/atomic.h>
diff --git a/include/uapi/linux/magic.h b/include/uapi/linux/magic.h
index a0908f1d2760..e439565df838 100644
--- a/include/uapi/linux/magic.h
+++ b/include/uapi/linux/magic.h
@@ -42,6 +42,7 @@
 #define MSDOS_SUPER_MAGIC	0x4d44		/* MD */
 #define NCP_SUPER_MAGIC		0x564c		/* Guess, what 0x564c is :-) */
 #define NFS_SUPER_MAGIC		0x6969
+#define OCFS2_SUPER_MAGIC	0x7461636f
 #define OPENPROM_SUPER_MAGIC	0x9fa1
 #define QNX4_SUPER_MAGIC	0x002f		/* qnx4 fs detection */
 #define QNX6_SUPER_MAGIC	0x68191122	/* qnx6 fs detection */
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 9cd8b21dddbe..2a4d89508fec 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -24,13 +24,6 @@ enum {
 	MPOL_MAX,	/* always last member of enum */
 };
 
-enum mpol_rebind_step {
-	MPOL_REBIND_ONCE,	/* do rebind work at once(not by two step) */
-	MPOL_REBIND_STEP1,	/* first step(set all the newly nodes) */
-	MPOL_REBIND_STEP2,	/* second step(clean all the disallowed nodes)*/
-	MPOL_REBIND_NSTEP,
-};
-
 /* Flags for set_mempolicy */
 #define MPOL_F_STATIC_NODES	(1 << 15)
 #define MPOL_F_RELATIVE_NODES	(1 << 14)
@@ -65,7 +58,6 @@ enum mpol_rebind_step {
  */
 #define MPOL_F_SHARED  (1 << 0)	/* identify shared policies */
 #define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
-#define MPOL_F_REBINDING (1 << 2)	/* identify policies in rebinding */
 #define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
 #define MPOL_F_MORON	(1 << 4) /* Migrate On protnone Reference On Node */