Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "191 patches.

  Subsystems affected by this patch series: kthread, ia64, scripts,
  ntfs, squashfs, ocfs2, kernel/watchdog, and mm (gup, pagealloc, slab,
  slub, kmemleak, dax, debug, pagecache, gup, swap, memcg, pagemap,
  mprotect, bootmem, dma, tracing, vmalloc, kasan, initialization,
  pagealloc, and memory-failure)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (191 commits)
  mm,hwpoison: make get_hwpoison_page() call get_any_page()
  mm,hwpoison: send SIGBUS with error virutal address
  mm/page_alloc: split pcp->high across all online CPUs for cpuless nodes
  mm/page_alloc: allow high-order pages to be stored on the per-cpu lists
  mm: replace CONFIG_FLAT_NODE_MEM_MAP with CONFIG_FLATMEM
  mm: replace CONFIG_NEED_MULTIPLE_NODES with CONFIG_NUMA
  docs: remove description of DISCONTIGMEM
  arch, mm: remove stale mentions of DISCONIGMEM
  mm: remove CONFIG_DISCONTIGMEM
  m68k: remove support for DISCONTIGMEM
  arc: remove support for DISCONTIGMEM
  arc: update comment about HIGHMEM implementation
  alpha: remove DISCONTIGMEM and NUMA
  mm/page_alloc: move free_the_page
  mm/page_alloc: fix counting of managed_pages
  mm/page_alloc: improve memmap_pages dbg msg
  mm: drop SECTION_SHIFT in code comments
  mm/page_alloc: introduce vm.percpu_pagelist_high_fraction
  mm/page_alloc: limit the number of pages on PCP lists when reclaim is active
  mm/page_alloc: scale the number of pages that are batch freed
  ...

29 files changed, 320 insertions, 164 deletions

diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index fff9367a6348..1d7edad9914f 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -154,6 +154,8 @@ struct bdi_writeback {
 	struct cgroup_subsys_state *blkcg_css; /* and blkcg */
 	struct list_head memcg_node;	/* anchored at memcg->cgwb_list */
 	struct list_head blkcg_node;	/* anchored at blkcg->cgwb_list */
+	struct list_head b_attached;	/* attached inodes, protected by list_lock */
+	struct list_head offline_node;	/* anchored at offline_cgwbs */
 
 	union {
 		struct work_struct release_work;
@@ -239,8 +241,9 @@ static inline void wb_get(struct bdi_writeback *wb)
 /**
  * wb_put - decrement a wb's refcount
  * @wb: bdi_writeback to put
+ * @nr: number of references to put
  */
-static inline void wb_put(struct bdi_writeback *wb)
+static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr)
 {
 	if (WARN_ON_ONCE(!wb->bdi)) {
 		/*
@@ -251,7 +254,16 @@ static inline void wb_put(struct bdi_writeback *wb)
 	}
 
 	if (wb != &wb->bdi->wb)
-		percpu_ref_put(&wb->refcnt);
+		percpu_ref_put_many(&wb->refcnt, nr);
+}
+
+/**
+ * wb_put - decrement a wb's refcount
+ * @wb: bdi_writeback to put
+ */
+static inline void wb_put(struct bdi_writeback *wb)
+{
+	wb_put_many(wb, 1);
 }
 
 /**
@@ -280,6 +292,10 @@ static inline void wb_put(struct bdi_writeback *wb)
 {
 }
 
+static inline void wb_put_many(struct bdi_writeback *wb, unsigned long nr)
+{
+}
+
 static inline bool wb_dying(struct bdi_writeback *wb)
 {
 	return false;
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 4a62b3980642..47e13582d9fc 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -54,7 +54,7 @@ enum cpuhp_state {
 	CPUHP_MM_MEMCQ_DEAD,
 	CPUHP_PERCPU_CNT_DEAD,
 	CPUHP_RADIX_DEAD,
-	CPUHP_PAGE_ALLOC_DEAD,
+	CPUHP_PAGE_ALLOC,
 	CPUHP_NET_DEV_DEAD,
 	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_IOVA_DEAD,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c3c88fdb9b2a..fad6663cd1b0 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3417,18 +3417,14 @@ extern int simple_rename(struct user_namespace *, struct inode *,
 extern void simple_recursive_removal(struct dentry *,
                               void (*callback)(struct dentry *));
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
-extern int noop_set_page_dirty(struct page *page);
 extern void noop_invalidatepage(struct page *page, unsigned int offset,
 		unsigned int length);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
-extern int simple_readpage(struct file *file, struct page *page);
 extern int simple_write_begin(struct file *file, struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned flags,
 			struct page **pagep, void **fsdata);
-extern int simple_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct page *page, void *fsdata);
+extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
 extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index e6102dfa4faa..55b2ec1f965a 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -506,8 +506,8 @@ static inline int gfp_zonelist(gfp_t flags)
  * There are two zonelists per node, one for all zones with memory and
  * one containing just zones from the node the zonelist belongs to.
  *
- * For the normal case of non-DISCONTIGMEM systems the NODE_DATA() gets
- * optimized to &contig_page_data at compile-time.
+ * For the case of non-NUMA systems the NODE_DATA() gets optimized to
+ * &contig_page_data at compile-time.
  */
 static inline struct zonelist *node_zonelist(int nid, gfp_t flags)
 {
@@ -548,6 +548,15 @@ alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_arr
 	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array);
 }
 
+static inline unsigned long
+alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array)
+{
+	if (nid == NUMA_NO_NODE)
+		nid = numa_mem_id();
+
+	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
+}
+
 /*
  * Allocate pages, preferring the node given as nid. The node must be valid and
  * online. For more general interface, see alloc_pages_node().
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index c87d0cb0de6d..479c1da3e221 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -159,7 +159,6 @@ ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
 		const struct iomap_ops *ops);
 int iomap_readpage(struct page *page, const struct iomap_ops *ops);
 void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
-int iomap_set_page_dirty(struct page *page);
 int iomap_is_partially_uptodate(struct page *page, unsigned long from,
 		unsigned long count);
 int iomap_releasepage(struct page *page, gfp_t gfp_mask);
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index a1c7ce5f3e4f..5310e217bd74 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -18,7 +18,6 @@ struct task_struct;
 
 /* kasan_data struct is used in KUnit tests for KASAN expected failures */
 struct kunit_kasan_expectation {
-	bool report_expected;
 	bool report_found;
 };
 
@@ -42,9 +41,9 @@ struct kunit_kasan_expectation {
 #endif
 
 extern unsigned char kasan_early_shadow_page[PAGE_SIZE];
-extern pte_t kasan_early_shadow_pte[PTRS_PER_PTE + PTE_HWTABLE_PTRS];
-extern pmd_t kasan_early_shadow_pmd[PTRS_PER_PMD];
-extern pud_t kasan_early_shadow_pud[PTRS_PER_PUD];
+extern pte_t kasan_early_shadow_pte[MAX_PTRS_PER_PTE + PTE_HWTABLE_PTRS];
+extern pmd_t kasan_early_shadow_pmd[MAX_PTRS_PER_PMD];
+extern pud_t kasan_early_shadow_pud[MAX_PTRS_PER_PUD];
 extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
 
 int kasan_populate_early_shadow(const void *shadow_start,
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 15d8bad3d2f2..bf950621febf 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -357,6 +357,8 @@ int sscanf(const char *, const char *, ...);
 extern __scanf(2, 0)
 int vsscanf(const char *, const char *, va_list);
 
+extern int no_hash_pointers_enable(char *str);
+
 extern int get_option(char **str, int *pint);
 extern char *get_options(const char *str, int nints, int *ints);
 extern unsigned long long memparse(const char *ptr, char **retptr);
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index d9133d6db308..346b0f269161 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -18,7 +18,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data),
  * @threadfn: the function to run in the thread
  * @data: data pointer for @threadfn()
  * @namefmt: printf-style format string for the thread name
- * @arg...: arguments for @namefmt.
+ * @arg: arguments for @namefmt.
  *
  * This macro will create a kthread on the current node, leaving it in
  * the stopped state.  This is just a helper for kthread_create_on_node();
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 5984fff3f175..552309342c38 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -50,7 +50,7 @@ struct memblock_region {
 	phys_addr_t base;
 	phys_addr_t size;
 	enum memblock_flags flags;
-#ifdef CONFIG_NEED_MULTIPLE_NODES
+#ifdef CONFIG_NUMA
 	int nid;
 #endif
 };
@@ -347,7 +347,7 @@ int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
 int memblock_set_node(phys_addr_t base, phys_addr_t size,
 		      struct memblock_type *type, int nid);
 
-#ifdef CONFIG_NEED_MULTIPLE_NODES
+#ifdef CONFIG_NUMA
 static inline void memblock_set_region_node(struct memblock_region *r, int nid)
 {
 	r->nid = nid;
@@ -366,7 +366,7 @@ static inline int memblock_get_region_node(const struct memblock_region *r)
 {
 	return 0;
 }
-#endif /* CONFIG_NEED_MULTIPLE_NODES */
+#endif /* CONFIG_NUMA */
 
 /* Flags for memblock allocation APIs */
 #define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index c193be760709..6d66037be646 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -192,7 +192,7 @@ enum memcg_kmem_state {
 struct memcg_padding {
 	char x[0];
 } ____cacheline_internodealigned_in_smp;
-#define MEMCG_PADDING(name)      struct memcg_padding name;
+#define MEMCG_PADDING(name)      struct memcg_padding name
 #else
 #define MEMCG_PADDING(name)
 #endif
@@ -349,8 +349,7 @@ struct mem_cgroup {
 	struct deferred_split deferred_split_queue;
 #endif
 
-	struct mem_cgroup_per_node *nodeinfo[0];
-	/* WARNING: nodeinfo must be the last member here */
+	struct mem_cgroup_per_node *nodeinfo[];
 };
 
 /*
@@ -743,35 +742,18 @@ out:
 /**
  * mem_cgroup_page_lruvec - return lruvec for isolating/putting an LRU page
  * @page: the page
- * @pgdat: pgdat of the page
  *
  * This function relies on page->mem_cgroup being stable.
  */
-static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
-						struct pglist_data *pgdat)
+static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page)
 {
+	pg_data_t *pgdat = page_pgdat(page);
 	struct mem_cgroup *memcg = page_memcg(page);
 
 	VM_WARN_ON_ONCE_PAGE(!memcg && !mem_cgroup_disabled(), page);
 	return mem_cgroup_lruvec(memcg, pgdat);
 }
 
-static inline bool lruvec_holds_page_lru_lock(struct page *page,
-					      struct lruvec *lruvec)
-{
-	pg_data_t *pgdat = page_pgdat(page);
-	const struct mem_cgroup *memcg;
-	struct mem_cgroup_per_node *mz;
-
-	if (mem_cgroup_disabled())
-		return lruvec == &pgdat->__lruvec;
-
-	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	memcg = page_memcg(page) ? : root_mem_cgroup;
-
-	return lruvec->pgdat == pgdat && mz->memcg == memcg;
-}
-
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
@@ -1221,18 +1203,11 @@ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg,
 	return &pgdat->__lruvec;
 }
 
-static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
-						    struct pglist_data *pgdat)
-{
-	return &pgdat->__lruvec;
-}
-
-static inline bool lruvec_holds_page_lru_lock(struct page *page,
-					      struct lruvec *lruvec)
+static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page)
 {
 	pg_data_t *pgdat = page_pgdat(page);
 
-	return lruvec == &pgdat->__lruvec;
+	return &pgdat->__lruvec;
 }
 
 static inline void lruvec_memcg_debug(struct lruvec *lruvec, struct page *page)
@@ -1255,6 +1230,12 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return NULL;
 }
 
+static inline
+struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
+{
+	return NULL;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1516,12 +1497,19 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
 	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
 }
 
+/* Test requires a stable page->memcg binding, see page_memcg() */
+static inline bool page_matches_lruvec(struct page *page, struct lruvec *lruvec)
+{
+	return lruvec_pgdat(lruvec) == page_pgdat(page) &&
+	       lruvec_memcg(lruvec) == page_memcg(page);
+}
+
 /* Don't lock again iff page's lruvec locked */
 static inline struct lruvec *relock_page_lruvec_irq(struct page *page,
 		struct lruvec *locked_lruvec)
 {
 	if (locked_lruvec) {
-		if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+		if (page_matches_lruvec(page, locked_lruvec))
 			return locked_lruvec;
 
 		unlock_page_lruvec_irq(locked_lruvec);
@@ -1535,7 +1523,7 @@ static inline struct lruvec *relock_page_lruvec_irqsave(struct page *page,
 		struct lruvec *locked_lruvec, unsigned long *flags)
 {
 	if (locked_lruvec) {
-		if (lruvec_holds_page_lru_lock(page, locked_lruvec))
+		if (page_matches_lruvec(page, locked_lruvec))
 			return locked_lruvec;
 
 		unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 01ecf9e3603c..6d0f827ca4eb 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -46,7 +46,7 @@ extern int sysctl_page_lock_unfairness;
 
 void init_mm_internals(void);
 
-#ifndef CONFIG_NEED_MULTIPLE_NODES	/* Don't use mapnrs, do it properly */
+#ifndef CONFIG_NUMA		/* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
 
 static inline void set_max_mapnr(unsigned long limit)
@@ -234,7 +234,11 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 int __add_to_page_cache_locked(struct page *page, struct address_space *mapping,
 		pgoff_t index, gfp_t gfp, void **shadowp);
 
+#if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
+#else
+#define nth_page(page,n) ((page) + (n))
+#endif
 
 /* to align the pointer to the (next) page boundary */
 #define PAGE_ALIGN(addr) ALIGN(addr, PAGE_SIZE)
@@ -1341,7 +1345,7 @@ static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
 	if (!is_cow_mapping(vma->vm_flags))
 		return false;
 
-	if (!atomic_read(&vma->vm_mm->has_pinned))
+	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
 		return false;
 
 	return page_maybe_dma_pinned(page);
@@ -1850,12 +1854,8 @@ extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
 extern void do_invalidatepage(struct page *page, unsigned int offset,
 			      unsigned int length);
 
-void __set_page_dirty(struct page *, struct address_space *, int warn);
-int __set_page_dirty_nobuffers(struct page *page);
-int __set_page_dirty_no_writeback(struct page *page);
 int redirty_page_for_writepage(struct writeback_control *wbc,
 				struct page *page);
-void account_page_dirtied(struct page *page, struct address_space *mapping);
 void account_page_cleaned(struct page *page, struct address_space *mapping,
 			  struct bdi_writeback *wb);
 int set_page_dirty(struct page *page);
@@ -2420,7 +2420,7 @@ static inline unsigned long free_initmem_default(int poison)
 	extern char __init_begin[], __init_end[];
 
 	return free_reserved_area(&__init_begin, &__init_end,
-				  poison, "unused kernel");
+				  poison, "unused kernel image (initmem)");
 }
 
 static inline unsigned long get_num_physpages(void)
@@ -2460,7 +2460,7 @@ extern void get_pfn_range_for_nid(unsigned int nid,
 			unsigned long *start_pfn, unsigned long *end_pfn);
 extern unsigned long find_min_pfn_with_active_regions(void);
 
-#ifndef CONFIG_NEED_MULTIPLE_NODES
+#ifndef CONFIG_NUMA
 static inline int early_pfn_to_nid(unsigned long pfn)
 {
 	return 0;
@@ -2474,7 +2474,6 @@ extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void memmap_init_range(unsigned long, int, unsigned long,
 		unsigned long, unsigned long, enum meminit_context,
 		struct vmem_altmap *, int migratetype);
-extern void memmap_init_zone(struct zone *zone);
 extern void setup_per_zone_wmarks(void);
 extern int __meminit init_per_zone_wmark_min(void);
 extern void mem_init(void);
@@ -2681,17 +2680,45 @@ extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long add
 extern struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
 					     struct vm_area_struct **pprev);
 
-/* Look up the first VMA which intersects the interval start_addr..end_addr-1,
-   NULL if none.  Assume start_addr < end_addr. */
-static inline struct vm_area_struct * find_vma_intersection(struct mm_struct * mm, unsigned long start_addr, unsigned long end_addr)
+/**
+ * find_vma_intersection() - Look up the first VMA which intersects the interval
+ * @mm: The process address space.
+ * @start_addr: The inclusive start user address.
+ * @end_addr: The exclusive end user address.
+ *
+ * Returns: The first VMA within the provided range, %NULL otherwise.  Assumes
+ * start_addr < end_addr.
+ */
+static inline
+struct vm_area_struct *find_vma_intersection(struct mm_struct *mm,
+					     unsigned long start_addr,
+					     unsigned long end_addr)
 {
-	struct vm_area_struct * vma = find_vma(mm,start_addr);
+	struct vm_area_struct *vma = find_vma(mm, start_addr);
 
 	if (vma && end_addr <= vma->vm_start)
 		vma = NULL;
 	return vma;
 }
 
+/**
+ * vma_lookup() - Find a VMA at a specific address
+ * @mm: The process address space.
+ * @addr: The user address.
+ *
+ * Return: The vm_area_struct at the given address, %NULL otherwise.
+ */
+static inline
+struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma = find_vma(mm, addr);
+
+	if (vma && addr < vma->vm_start)
+		vma = NULL;
+
+	return vma;
+}
+
 static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
 {
 	unsigned long vm_start = vma->vm_start;
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8f0fb62e8975..b66d0225414e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -435,16 +435,6 @@ struct mm_struct {
 		 */
 		atomic_t mm_count;
 
-		/**
-		 * @has_pinned: Whether this mm has pinned any pages.  This can
-		 * be either replaced in the future by @pinned_vm when it
-		 * becomes stable, or grow into a counter on its own. We're
-		 * aggresive on this bit now - even if the pinned pages were
-		 * unpinned later on, we'll still keep this bit set for the
-		 * lifecycle of this mm just for simplicity.
-		 */
-		atomic_t has_pinned;
-
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* PTE page table pages */
 #endif
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 629cefc4ecba..ebb09a964272 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -31,6 +31,8 @@
 /*
  * The historical set of flags that all mmap implementations implicitly
  * support when a ->mmap_validate() op is not provided in file_operations.
+ *
+ * MAP_EXECUTABLE is completely ignored throughout the kernel.
  */
 #define LEGACY_MAP_MASK (MAP_SHARED \
 		| MAP_PRIVATE \
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 5d0767cb424a..1935d4c72d10 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -9,8 +9,7 @@ struct page;
 struct vm_area_struct;
 struct mm_struct;
 
-extern void dump_page(struct page *page, const char *reason);
-extern void __dump_page(struct page *page, const char *reason);
+void dump_page(struct page *page, const char *reason);
 void dump_vma(const struct vm_area_struct *vma);
 void dump_mm(const struct mm_struct *mm);
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 0d53eba1c383..265a32e1ff74 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -20,6 +20,7 @@
 #include <linux/atomic.h>
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
+#include <linux/local_lock.h>
 #include <asm/page.h>
 
 /* Free memory management - zoned buddy allocator.  */
@@ -134,10 +135,10 @@ enum numa_stat_item {
 	NUMA_INTERLEAVE_HIT,	/* interleaver preferred this zone */
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
-	NR_VM_NUMA_STAT_ITEMS
+	NR_VM_NUMA_EVENT_ITEMS
 };
 #else
-#define NR_VM_NUMA_STAT_ITEMS 0
+#define NR_VM_NUMA_EVENT_ITEMS 0
 #endif
 
 enum zone_stat_item {
@@ -332,29 +333,55 @@ enum zone_watermarks {
 	NR_WMARK
 };
 
+/*
+ * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER plus one additional
+ * for pageblock size for THP if configured.
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define NR_PCP_THP 1
+#else
+#define NR_PCP_THP 0
+#endif
+#define NR_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1 + NR_PCP_THP))
+
+/*
+ * Shift to encode migratetype and order in the same integer, with order
+ * in the least significant bits.
+ */
+#define NR_PCP_ORDER_WIDTH 8
+#define NR_PCP_ORDER_MASK ((1<<NR_PCP_ORDER_WIDTH) - 1)
+
 #define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost)
 #define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost)
 #define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
 #define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
 
+/* Fields and list protected by pagesets local_lock in page_alloc.c */
 struct per_cpu_pages {
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */
 	int batch;		/* chunk size for buddy add/remove */
+	short free_factor;	/* batch scaling factor during free */
+#ifdef CONFIG_NUMA
+	short expire;		/* When 0, remote pagesets are drained */
+#endif
 
 	/* Lists of pages, one per migrate type stored on the pcp-lists */
-	struct list_head lists[MIGRATE_PCPTYPES];
+	struct list_head lists[NR_PCP_LISTS];
 };
 
-struct per_cpu_pageset {
-	struct per_cpu_pages pcp;
-#ifdef CONFIG_NUMA
-	s8 expire;
-	u16 vm_numa_stat_diff[NR_VM_NUMA_STAT_ITEMS];
-#endif
+struct per_cpu_zonestat {
 #ifdef CONFIG_SMP
-	s8 stat_threshold;
 	s8 vm_stat_diff[NR_VM_ZONE_STAT_ITEMS];
+	s8 stat_threshold;
+#endif
+#ifdef CONFIG_NUMA
+	/*
+	 * Low priority inaccurate counters that are only folded
+	 * on demand. Use a large type to avoid the overhead of
+	 * folding during refresh_cpu_vm_stats.
+	 */
+	unsigned long vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
 #endif
 };
 
@@ -484,7 +511,8 @@ struct zone {
 	int node;
 #endif
 	struct pglist_data	*zone_pgdat;
-	struct per_cpu_pageset __percpu *pageset;
+	struct per_cpu_pages	__percpu *per_cpu_pageset;
+	struct per_cpu_zonestat	__percpu *per_cpu_zonestats;
 	/*
 	 * the high and batch values are copied to individual pagesets for
 	 * faster access
@@ -619,7 +647,7 @@ struct zone {
 	ZONE_PADDING(_pad3_)
 	/* Zone statistics */
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
-	atomic_long_t		vm_numa_stat[NR_VM_NUMA_STAT_ITEMS];
+	atomic_long_t		vm_numa_event[NR_VM_NUMA_EVENT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
 enum pgdat_flags {
@@ -637,6 +665,7 @@ enum zone_flags {
 	ZONE_BOOSTED_WATERMARK,		/* zone recently boosted watermarks.
 					 * Cleared when kswapd is woken.
 					 */
+	ZONE_RECLAIM_ACTIVE,		/* kswapd may be scanning the zone. */
 };
 
 static inline unsigned long zone_managed_pages(struct zone *zone)
@@ -738,10 +767,12 @@ struct zonelist {
 	struct zoneref _zonerefs[MAX_ZONES_PER_ZONELIST + 1];
 };
 
-#ifndef CONFIG_DISCONTIGMEM
-/* The array of struct pages - for discontigmem use pgdat->lmem_map */
+/*
+ * The array of struct pages for flatmem.
+ * It must be declared for SPARSEMEM as well because there are configurations
+ * that rely on that.
+ */
 extern struct page *mem_map;
-#endif
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 struct deferred_split {
@@ -775,7 +806,7 @@ typedef struct pglist_data {
 	struct zonelist node_zonelists[MAX_ZONELISTS];
 
 	int nr_zones; /* number of populated zones in this node */
-#ifdef CONFIG_FLAT_NODE_MEM_MAP	/* means !SPARSEMEM */
+#ifdef CONFIG_FLATMEM	/* means !SPARSEMEM */
 	struct page *node_mem_map;
 #ifdef CONFIG_PAGE_EXTENSION
 	struct page_ext *node_page_ext;
@@ -865,7 +896,7 @@ typedef struct pglist_data {
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
 #define node_spanned_pages(nid)	(NODE_DATA(nid)->node_spanned_pages)
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
+#ifdef CONFIG_FLATMEM
 #define pgdat_page_nr(pgdat, pagenr)	((pgdat)->node_mem_map + (pagenr))
 #else
 #define pgdat_page_nr(pgdat, pagenr)	pfn_to_page((pgdat)->node_start_pfn + (pagenr))
@@ -982,22 +1013,11 @@ static inline void zone_set_nid(struct zone *zone, int nid) {}
 
 extern int movable_zone;
 
-#ifdef CONFIG_HIGHMEM
-static inline int zone_movable_is_highmem(void)
-{
-#ifdef CONFIG_NEED_MULTIPLE_NODES
-	return movable_zone == ZONE_HIGHMEM;
-#else
-	return (ZONE_MOVABLE - 1) == ZONE_HIGHMEM;
-#endif
-}
-#endif
-
 static inline int is_highmem_idx(enum zone_type idx)
 {
 #ifdef CONFIG_HIGHMEM
 	return (idx == ZONE_HIGHMEM ||
-		(idx == ZONE_MOVABLE && zone_movable_is_highmem()));
+		(idx == ZONE_MOVABLE && movable_zone == ZONE_HIGHMEM));
 #else
 	return 0;
 #endif
@@ -1029,7 +1049,7 @@ int watermark_scale_factor_sysctl_handler(struct ctl_table *, int, void *,
 extern int sysctl_lowmem_reserve_ratio[MAX_NR_ZONES];
 int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *, int, void *,
 		size_t *, loff_t *);
-int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int,
+int percpu_pagelist_high_fraction_sysctl_handler(struct ctl_table *, int,
 		void *, size_t *, loff_t *);
 int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
 		void *, size_t *, loff_t *);
@@ -1037,21 +1057,21 @@ int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
 		void *, size_t *, loff_t *);
 int numa_zonelist_order_handler(struct ctl_table *, int,
 		void *, size_t *, loff_t *);
-extern int percpu_pagelist_fraction;
+extern int percpu_pagelist_high_fraction;
 extern char numa_zonelist_order[];
 #define NUMA_ZONELIST_ORDER_LEN	16
 
-#ifndef CONFIG_NEED_MULTIPLE_NODES
+#ifndef CONFIG_NUMA
 
 extern struct pglist_data contig_page_data;
 #define NODE_DATA(nid)		(&contig_page_data)
 #define NODE_MEM_MAP(nid)	mem_map
 
-#else /* CONFIG_NEED_MULTIPLE_NODES */
+#else /* CONFIG_NUMA */
 
 #include <asm/mmzone.h>
 
-#endif /* !CONFIG_NEED_MULTIPLE_NODES */
+#endif /* !CONFIG_NUMA */
 
 extern struct pglist_data *first_online_pgdat(void);
 extern struct pglist_data *next_online_pgdat(struct pglist_data *pgdat);
@@ -1200,8 +1220,6 @@ static inline struct zoneref *first_zone