Merge branch 'akpm' (patches from Andrew)

Merge more updates from Andrew Morton:
 "The rest of MM"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (101 commits)
  mm, compaction: simplify contended compaction handling
  mm, compaction: introduce direct compaction priority
  mm, thp: remove __GFP_NORETRY from khugepaged and madvised allocations
  mm, page_alloc: make THP-specific decisions more generic
  mm, page_alloc: restructure direct compaction handling in slowpath
  mm, page_alloc: don't retry initial attempt in slowpath
  mm, page_alloc: set alloc_flags only once in slowpath
  lib/stackdepot.c: use __GFP_NOWARN for stack allocations
  mm, kasan: switch SLUB to stackdepot, enable memory quarantine for SLUB
  mm, kasan: account for object redzone in SLUB's nearest_obj()
  mm: fix use-after-free if memory allocation failed in vma_adjust()
  zsmalloc: Delete an unnecessary check before the function call "iput"
  mm/memblock.c: fix index adjustment error in __next_mem_range_rev()
  mem-hotplug: alloc new page from a nearest neighbor node when mem-offline
  mm: optimize copy_page_to/from_iter_iovec
  mm: add cond_resched() to generic_swapfile_activate()
  Revert "mm, mempool: only set __GFP_NOMEMALLOC if there are free elements"
  mm, compaction: don't isolate PageWriteback pages in MIGRATE_SYNC_LIGHT mode
  mm: hwpoison: remove incorrect comments
  make __section_nr() more efficient
  ...

26 files changed, 418 insertions, 226 deletions

diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index c82794f20110..491a91717788 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -197,7 +197,7 @@ static inline int wb_congested(struct bdi_writeback *wb, int cong_bits)
 }
 
 long congestion_wait(int sync, long timeout);
-long wait_iff_congested(struct zone *zone, int sync, long timeout);
+long wait_iff_congested(struct pglist_data *pgdat, int sync, long timeout);
 int pdflush_proc_obsolete(struct ctl_table *table, int write,
 		void __user *buffer, size_t *lenp, loff_t *ppos);
 
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 1a02dab16646..d4e106b5dc27 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -1,6 +1,18 @@
 #ifndef _LINUX_COMPACTION_H
 #define _LINUX_COMPACTION_H
 
+/*
+ * Determines how hard direct compaction should try to succeed.
+ * Lower value means higher priority, analogically to reclaim priority.
+ */
+enum compact_priority {
+	COMPACT_PRIO_SYNC_LIGHT,
+	MIN_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
+	DEF_COMPACT_PRIORITY = COMPACT_PRIO_SYNC_LIGHT,
+	COMPACT_PRIO_ASYNC,
+	INIT_COMPACT_PRIORITY = COMPACT_PRIO_ASYNC
+};
+
 /* Return values for compact_zone() and try_to_compact_pages() */
 /* When adding new states, please adjust include/trace/events/compaction.h */
 enum compact_result {
@@ -43,14 +55,6 @@ enum compact_result {
 	COMPACT_PARTIAL,
 };
 
-/* Used to signal whether compaction detected need_sched() or lock contention */
-/* No contention detected */
-#define COMPACT_CONTENDED_NONE	0
-/* Either need_sched() was true or fatal signal pending */
-#define COMPACT_CONTENDED_SCHED	1
-/* Zone lock or lru_lock was contended in async compaction */
-#define COMPACT_CONTENDED_LOCK	2
-
 struct alloc_context; /* in mm/internal.h */
 
 #ifdef CONFIG_COMPACTION
@@ -64,9 +68,8 @@ extern int sysctl_compact_unevictable_allowed;
 
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
-			unsigned int order,
-		unsigned int alloc_flags, const struct alloc_context *ac,
-		enum migrate_mode mode, int *contended);
+		unsigned int order, unsigned int alloc_flags,
+		const struct alloc_context *ac, enum compact_priority prio);
 extern void compact_pgdat(pg_data_t *pgdat, int order);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern enum compact_result compaction_suitable(struct zone *zone, int order,
@@ -151,14 +154,6 @@ extern void kcompactd_stop(int nid);
 extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx);
 
 #else
-static inline enum compact_result try_to_compact_pages(gfp_t gfp_mask,
-			unsigned int order, int alloc_flags,
-			const struct alloc_context *ac,
-			enum migrate_mode mode, int *contended)
-{
-	return COMPACT_CONTINUE;
-}
-
 static inline void compact_pgdat(pg_data_t *pgdat, int order)
 {
 }
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index c29e9d347bc6..f8041f9de31e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -237,9 +237,11 @@ struct vm_area_struct;
  *   are expected to be movable via page reclaim or page migration. Typically,
  *   pages on the LRU would also be allocated with GFP_HIGHUSER_MOVABLE.
  *
- * GFP_TRANSHUGE is used for THP allocations. They are compound allocations
- *   that will fail quickly if memory is not available and will not wake
- *   kswapd on failure.
+ * GFP_TRANSHUGE and GFP_TRANSHUGE_LIGHT are used for THP allocations. They are
+ *   compound allocations that will generally fail quickly if memory is not
+ *   available and will not wake kswapd/kcompactd on failure. The _LIGHT
+ *   version does not attempt reclaim/compaction at all and is by default used
+ *   in page fault path, while the non-light is used by khugepaged.
  */
 #define GFP_ATOMIC	(__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM)
 #define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
@@ -254,9 +256,9 @@ struct vm_area_struct;
 #define GFP_DMA32	__GFP_DMA32
 #define GFP_HIGHUSER	(GFP_USER | __GFP_HIGHMEM)
 #define GFP_HIGHUSER_MOVABLE	(GFP_HIGHUSER | __GFP_MOVABLE)
-#define GFP_TRANSHUGE	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN) & \
-			 ~__GFP_RECLAIM)
+#define GFP_TRANSHUGE_LIGHT	((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
+			 __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM)
+#define GFP_TRANSHUGE	(GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM)
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 92ce91c03cd0..6f14de45b5ce 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -11,7 +11,7 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
-extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+extern bool madvise_free_huge_pmd(struct mmu_gather *tlb,
 			struct vm_area_struct *vma,
 			pmd_t *pmd, unsigned long addr, unsigned long next);
 extern int zap_huge_pmd(struct mmu_gather *tlb,
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index ac4b3c46a84d..c9cf374445d8 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -77,6 +77,7 @@ void kasan_free_shadow(const struct vm_struct *vm);
 
 size_t ksize(const void *);
 static inline void kasan_unpoison_slab(const void *ptr) { ksize(ptr); }
+size_t kasan_metadata_size(struct kmem_cache *cache);
 
 #else /* CONFIG_KASAN */
 
@@ -121,6 +122,7 @@ static inline int kasan_module_alloc(void *addr, size_t size) { return 0; }
 static inline void kasan_free_shadow(const struct vm_struct *vm) {}
 
 static inline void kasan_unpoison_slab(const void *ptr) { }
+static inline size_t kasan_metadata_size(struct kmem_cache *cache) { return 0; }
 
 #endif /* CONFIG_KASAN */
 
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index a19bcf9e762e..410decacff8f 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -177,7 +177,7 @@ extern int kdb_get_kbd_char(void);
 static inline
 int kdb_process_cpu(const struct task_struct *p)
 {
-	unsigned int cpu = task_thread_info(p)->cpu;
+	unsigned int cpu = task_cpu(p);
 	if (cpu > num_possible_cpus())
 		cpu = 0;
 	return cpu;
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 6c14b6179727..2925da23505d 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -332,6 +332,7 @@ phys_addr_t memblock_mem_size(unsigned long limit_pfn);
 phys_addr_t memblock_start_of_DRAM(void);
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+void memblock_mem_limit_remove_map(phys_addr_t limit);
 bool memblock_is_memory(phys_addr_t addr);
 int memblock_is_map_memory(phys_addr_t addr);
 int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 71aff733a497..5d8ca6e02e39 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -52,7 +52,7 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_SWAP,		/* # of pages, swapped out */
 	MEM_CGROUP_STAT_NSTATS,
 	/* default hierarchy stats */
-	MEMCG_KERNEL_STACK = MEM_CGROUP_STAT_NSTATS,
+	MEMCG_KERNEL_STACK_KB = MEM_CGROUP_STAT_NSTATS,
 	MEMCG_SLAB_RECLAIMABLE,
 	MEMCG_SLAB_UNRECLAIMABLE,
 	MEMCG_SOCK,
@@ -60,7 +60,7 @@ enum mem_cgroup_stat_index {
 };
 
 struct mem_cgroup_reclaim_cookie {
-	struct zone *zone;
+	pg_data_t *pgdat;
 	int priority;
 	unsigned int generation;
 };
@@ -118,7 +118,7 @@ struct mem_cgroup_reclaim_iter {
 /*
  * per-zone information in memory controller.
  */
-struct mem_cgroup_per_zone {
+struct mem_cgroup_per_node {
 	struct lruvec		lruvec;
 	unsigned long		lru_size[NR_LRU_LISTS];
 
@@ -132,10 +132,6 @@ struct mem_cgroup_per_zone {
 						/* use container_of	   */
 };
 
-struct mem_cgroup_per_node {
-	struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES];
-};
-
 struct mem_cgroup_threshold {
 	struct eventfd_ctx *eventfd;
 	unsigned long threshold;
@@ -314,8 +310,46 @@ void mem_cgroup_uncharge_list(struct list_head *page_list);
 
 void mem_cgroup_migrate(struct page *oldpage, struct page *newpage);
 
-struct lruvec *mem_cgroup_zone_lruvec(struct zone *, struct mem_cgroup *);
-struct lruvec *mem_cgroup_page_lruvec(struct page *, struct zone *);
+static struct mem_cgroup_per_node *
+mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid)
+{
+	return memcg->nodeinfo[nid];
+}
+
+/**
+ * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone
+ * @node: node of the wanted lruvec
+ * @memcg: memcg of the wanted lruvec
+ *
+ * Returns the lru list vector holding pages for a given @node or a given
+ * @memcg and @zone. This can be the node lruvec, if the memory controller
+ * is disabled.
+ */
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_node *mz;
+	struct lruvec *lruvec;
+
+	if (mem_cgroup_disabled()) {
+		lruvec = node_lruvec(pgdat);
+		goto out;
+	}
+
+	mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id);
+	lruvec = &mz->lruvec;
+out:
+	/*
+	 * Since a node can be onlined after the mem_cgroup was created,
+	 * we have to be prepared to initialize lruvec->pgdat here;
+	 * and if offlined then reonlined, we need to reinitialize it.
+	 */
+	if (unlikely(lruvec->pgdat != pgdat))
+		lruvec->pgdat = pgdat;
+	return lruvec;
+}
+
+struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *);
 
 bool task_in_mem_cgroup(struct task_struct *task, struct mem_cgroup *memcg);
 struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
@@ -404,9 +438,9 @@ unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg,
 static inline
 unsigned long mem_cgroup_get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 {
-	struct mem_cgroup_per_zone *mz;
+	struct mem_cgroup_per_node *mz;
 
-	mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec);
+	mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
 	return mz->lru_size[lru];
 }
 
@@ -477,7 +511,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 	mem_cgroup_update_page_stat(page, idx, -1);
 }
 
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 						gfp_t gfp_mask,
 						unsigned long *total_scanned);
 
@@ -568,16 +602,16 @@ static inline void mem_cgroup_migrate(struct page *old, struct page *new)
 {
 }
 
-static inline struct lruvec *mem_cgroup_zone_lruvec(struct zone *zone,
-						    struct mem_cgroup *memcg)
+static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat,
+				struct mem_cgroup *memcg)
 {
-	return &zone->lruvec;
+	return node_lruvec(pgdat);
 }
 
 static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page,
-						    struct zone *zone)
+						    struct pglist_data *pgdat)
 {
-	return &zone->lruvec;
+	return &pgdat->lruvec;
 }
 
 static inline bool mm_match_cgroup(struct mm_struct *mm,
@@ -681,7 +715,7 @@ static inline void mem_cgroup_dec_page_stat(struct page *page,
 }
 
 static inline
-unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
+unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 					    gfp_t gfp_mask,
 					    unsigned long *total_scanned)
 {
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index bcaa634139a9..93416196ba64 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -26,7 +26,7 @@ struct vmem_altmap {
 unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
 void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 
-#if defined(CONFIG_SPARSEMEM_VMEMMAP) && defined(CONFIG_ZONE_DEVICE)
+#ifdef CONFIG_ZONE_DEVICE
 struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start);
 #else
 static inline struct vmem_altmap *to_vmem_altmap(unsigned long memmap_start)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 192c1bbe5fcd..08ed53eeedd5 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -933,6 +933,11 @@ static inline struct zone *page_zone(const struct page *page)
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
 }
 
+static inline pg_data_t *page_pgdat(const struct page *page)
+{
+	return NODE_DATA(page_to_nid(page));
+}
+
 #ifdef SECTION_IN_PAGE_FLAGS
 static inline void set_page_section(struct page *page, unsigned long section)
 {
@@ -973,11 +978,21 @@ static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return page->mem_cgroup;
 }
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return READ_ONCE(page->mem_cgroup);
+}
 #else
 static inline struct mem_cgroup *page_memcg(struct page *page)
 {
 	return NULL;
 }
+static inline struct mem_cgroup *page_memcg_rcu(struct page *page)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held());
+	return NULL;
+}
 #endif
 
 /*
@@ -2284,6 +2299,8 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr)
 }
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
+extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
+
 #ifdef CONFIG_SYSCTL
 extern int sysctl_drop_caches;
 int drop_caches_sysctl_handler(struct ctl_table *, int,
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 5bd29ba4f174..71613e8a720f 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -23,25 +23,30 @@ static inline int page_is_file_cache(struct page *page)
 }
 
 static __always_inline void __update_lru_size(struct lruvec *lruvec,
-				enum lru_list lru, int nr_pages)
+				enum lru_list lru, enum zone_type zid,
+				int nr_pages)
 {
-	__mod_zone_page_state(lruvec_zone(lruvec), NR_LRU_BASE + lru, nr_pages);
+	struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+	__mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
+	__mod_zone_page_state(&pgdat->node_zones[zid],
+				NR_ZONE_LRU_BASE + lru, nr_pages);
 }
 
 static __always_inline void update_lru_size(struct lruvec *lruvec,
-				enum lru_list lru, int nr_pages)
+				enum lru_list lru, enum zone_type zid,
+				int nr_pages)
 {
+	__update_lru_size(lruvec, lru, zid, nr_pages);
 #ifdef CONFIG_MEMCG
 	mem_cgroup_update_lru_size(lruvec, lru, nr_pages);
-#else
-	__update_lru_size(lruvec, lru, nr_pages);
 #endif
 }
 
 static __always_inline void add_page_to_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
-	update_lru_size(lruvec, lru, hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), hpage_nr_pages(page));
 	list_add(&page->lru, &lruvec->lists[lru]);
 }
 
@@ -49,7 +54,7 @@ static __always_inline void del_page_from_lru_list(struct page *page,
 				struct lruvec *lruvec, enum lru_list lru)
 {
 	list_del(&page->lru);
-	update_lru_size(lruvec, lru, -hpage_nr_pages(page));
+	update_lru_size(lruvec, lru, page_zonenum(page), -hpage_nr_pages(page));
 }
 
 /**
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 79472b22d23f..903200f4ec41 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -118,7 +118,7 @@ struct page {
 	 */
 	union {
 		struct list_head lru;	/* Pageout list, eg. active_list
-					 * protected by zone->lru_lock !
+					 * protected by zone_lru_lock !
 					 * Can be used as a generic list
 					 * by the page owner.
 					 */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 19425e988bdc..f2e4e90621ec 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -93,7 +93,7 @@ struct free_area {
 struct pglist_data;
 
 /*
- * zone->lock and zone->lru_lock are two of the hottest locks in the kernel.
+ * zone->lock and the zone lru_lock are two of the hottest locks in the kernel.
  * So add a wild amount of padding here to ensure that they fall into separate
  * cachelines.  There are very few zone structures in the machine, so space
  * consumption is not a concern here.
@@ -110,36 +110,20 @@ struct zone_padding {
 enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
-	NR_ALLOC_BATCH,
-	NR_LRU_BASE,
-	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
-	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
-	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
-	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
-	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
+	NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
+	NR_ZONE_ACTIVE_ANON,
+	NR_ZONE_INACTIVE_FILE,
+	NR_ZONE_ACTIVE_FILE,
+	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_ANON_PAGES,	/* Mapped anonymous pages */
-	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
-			   only modified from process context */
-	NR_FILE_PAGES,
-	NR_FILE_DIRTY,
-	NR_WRITEBACK,
 	NR_SLAB_RECLAIMABLE,
 	NR_SLAB_UNRECLAIMABLE,
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_KERNEL_STACK,
+	NR_KERNEL_STACK_KB,	/* measured in KiB */
 	/* Second 128 byte cacheline */
-	NR_UNSTABLE_NFS,	/* NFS unstable pages */
 	NR_BOUNCE,
-	NR_VMSCAN_WRITE,
-	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
-	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
-	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
-	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
-	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
-	NR_DIRTIED,		/* page dirtyings since bootup */
-	NR_WRITTEN,		/* page writings since bootup */
-	NR_PAGES_SCANNED,	/* pages scanned since last reclaim */
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
@@ -151,14 +135,40 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
+	NR_FREE_CMA_PAGES,
+	NR_VM_ZONE_STAT_ITEMS };
+
+enum node_stat_item {
+	NR_LRU_BASE,
+	NR_INACTIVE_ANON = NR_LRU_BASE, /* must match order of LRU_[IN]ACTIVE */
+	NR_ACTIVE_ANON,		/*  "     "     "   "       "         */
+	NR_INACTIVE_FILE,	/*  "     "     "   "       "         */
+	NR_ACTIVE_FILE,		/*  "     "     "   "       "         */
+	NR_UNEVICTABLE,		/*  "     "     "   "       "         */
+	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
+	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
+	NR_PAGES_SCANNED,	/* pages scanned since last reclaim */
 	WORKINGSET_REFAULT,
 	WORKINGSET_ACTIVATE,
 	WORKINGSET_NODERECLAIM,
-	NR_ANON_THPS,
+	NR_ANON_MAPPED,	/* Mapped anonymous pages */
+	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
+			   only modified from process context */
+	NR_FILE_PAGES,
+	NR_FILE_DIRTY,
+	NR_WRITEBACK,
+	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
+	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_SHMEM_THPS,
 	NR_SHMEM_PMDMAPPED,
-	NR_FREE_CMA_PAGES,
-	NR_VM_ZONE_STAT_ITEMS };
+	NR_ANON_THPS,
+	NR_UNSTABLE_NFS,	/* NFS unstable pages */
+	NR_VMSCAN_WRITE,
+	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
+	NR_DIRTIED,		/* page dirtyings since bootup */
+	NR_WRITTEN,		/* page writings since bootup */
+	NR_VM_NODE_STAT_ITEMS
+};
 
 /*
  * We do arithmetic on the LRU lists in various places in the code,
@@ -215,7 +225,7 @@ struct lruvec {
 	/* Evictions & activations on the inactive file list */
 	atomic_long_t			inactive_age;
 #ifdef CONFIG_MEMCG
-	struct zone			*zone;
+	struct pglist_data *pgdat;
 #endif
 };
 
@@ -267,6 +277,11 @@ struct per_cpu_pageset {
 #endif
 };
 
+struct per_cpu_nodestat {
+	s8 stat_threshold;
+	s8 vm_node_stat_diff[NR_VM_NODE_STAT_ITEMS];
+};
+
 #endif /* !__GENERATING_BOUNDS.H */
 
 enum zone_type {
@@ -348,22 +363,9 @@ struct zone {
 #ifdef CONFIG_NUMA
 	int node;
 #endif
-
-	/*
-	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
-	 * this zone's LRU.  Maintained by the pageout code.
-	 */
-	unsigned int inactive_ratio;
-
 	struct pglist_data	*zone_pgdat;
 	struct per_cpu_pageset __percpu *pageset;
 
-	/*
-	 * This is a per-zone reserve of pages that are not available
-	 * to userspace allocations.
-	 */
-	unsigned long		totalreserve_pages;
-
 #ifndef CONFIG_SPARSEMEM
 	/*
 	 * Flags for a pageblock_nr_pages block. See pageblock-flags.h.
@@ -372,14 +374,6 @@ struct zone {
 	unsigned long		*pageblock_flags;
 #endif /* CONFIG_SPARSEMEM */
 
-#ifdef CONFIG_NUMA
-	/*
-	 * zone reclaim becomes active if more unmapped pages exist.
-	 */
-	unsigned long		min_unmapped_pages;
-	unsigned long		min_slab_pages;
-#endif /* CONFIG_NUMA */
-
 	/* zone_start_pfn == zone_start_paddr >> PAGE_SHIFT */
 	unsigned long		zone_start_pfn;
 
@@ -472,24 +466,21 @@ struct zone {
 	unsigned long		wait_table_hash_nr_entries;
 	unsigned long		wait_table_bits;
 
+	/* Write-intensive fields used from the page allocator */
 	ZONE_PADDING(_pad1_)
+
 	/* free areas of different sizes */
 	struct free_area	free_area[MAX_ORDER];
 
 	/* zone flags, see below */
 	unsigned long		flags;
 
-	/* Write-intensive fields used from the page allocator */
+	/* Primarily protects free_area */
 	spinlock_t		lock;
 
+	/* Write-intensive fields used by compaction and vmstats. */
 	ZONE_PADDING(_pad2_)
 
-	/* Write-intensive fields used by page reclaim */
-
-	/* Fields commonly accessed by the page reclaim scanner */
-	spinlock_t		lru_lock;
-	struct lruvec		lruvec;
-
 	/*
 	 * When free pages are below this point, additional steps are taken
 	 * when reading the number of free pages to avoid per-cpu counter
@@ -527,19 +518,18 @@ struct zone {
 	atomic_long_t		vm_stat[NR_VM_ZONE_STAT_ITEMS];
 } ____cacheline_internodealigned_in_smp;
 
-enum zone_flags {
-	ZONE_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
-	ZONE_CONGESTED,			/* zone has many dirty pages backed by
+enum pgdat_flags {
+	PGDAT_CONGESTED,		/* pgdat has many dirty pages backed by
 					 * a congested BDI
 					 */
-	ZONE_DIRTY,			/* reclaim scanning has recently found
+	PGDAT_DIRTY,			/* reclaim scanning has recently found
 					 * many dirty file pages at the tail
 					 * of the LRU.
 					 */
-	ZONE_WRITEBACK,			/* reclaim scanning has recently found
+	PGDAT_WRITEBACK,		/* reclaim scanning has recently found
 					 * many pages under writeback
 					 */
-	ZONE_FAIR_DEPLETED,		/* fair zone policy batch depleted */
+	PGDAT_RECLAIM_LOCKED,		/* prevents concurrent reclaim */
 };
 
 static inline unsigned long zone_end_pfn(const struct zone *zone)
@@ -663,8 +653,9 @@ typedef struct pglist_data {
 	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;	/* Protected by
 					   mem_hotplug_begin/end() */
-	int kswapd_max_order;
-	enum zone_type classzone_idx;
+	int kswapd_order;
+	enum zone_type kswapd_classzone_idx;
+
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
 	enum zone_type kcompactd_classzone_idx;
@@ -681,6 +672,23 @@ typedef struct pglist_data {
 	/* Number of pages migrated during the rate limiting time interval */
 	unsigned long numabalancing_migrate_nr_pages;
 #endif
+	/*
+	 * This is a per-node reserve of pages that are not available
+	 * to userspace allocations.
+	 */
+	unsigned long		totalreserve_pages;
+
+#ifdef CONFIG_NUMA
+	/*
+	 * zone reclaim becomes active if more unmapped pages exist.
+	 */
+	unsigned long		min_unmapped_pages;
+	unsigned long		min_slab_pages;
+#endif /* CONFIG_NUMA */
+
+	/* Write-intensive fields used by page reclaim */
+	ZONE_PADDING(_pad1_)
+	spinlock_t		lru_lock;
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
 	/*
@@ -695,6 +703,23 @@ typedef struct pglist_data {
 	struct list_head split_queue;
 	unsigned long split_queue_len;
 #endif
+
+	/* Fields commonly accessed by the page reclaim scanner */
+	struct lruvec		lruvec;
+
+	/*
+	 * The target ratio of ACTIVE_ANON to INACTIVE_ANON pages on
+	 * this node's LRU.  Maintained by the pageout code.
+	 */
+	unsigned int inactive_ratio;
+
+	unsigned long		flags;
+
+	ZONE_PADDING(_pad2_)
+
+	/* Per-node vmstats */
+	struct per_cpu_nodestat __percpu *per_cpu_nodestats;
+	atomic_long_t		vm_stat[NR_VM_NODE_STAT_ITEMS];
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
@@ -708,6 +733,15 @@ typedef struct pglist_data {
 
 #define node_start_pfn(nid)	(NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid) pgdat_end_pfn(NODE_DATA(nid))
+static inline spinlock_t *zone_lru_lock(struct zone *zone)
+{
+	return &zone->zone_pgdat->lru_lock;
+}
+
+static inline struct lruvec *node_lruvec(struct pglist_data *pgdat)
+{
+	return &pgdat->lruvec;
+}
 
 static inline unsigned long pgdat_end_pfn(pg_data_t *pgdat)
 {
@@ -760,12 +794,12 @@ extern int init_currently_empty_zone(struct zone *zone, unsigned long start_pfn,
 
 extern void lruvec_init(struct lruvec *lruvec);
 
-static inline struct zone *lruvec_zone(struct lruvec *lruvec)
+static inline struct pglist_data *lruvec_pgdat(struct lruvec *lruvec)
 {
 #ifdef CONFIG_MEMCG
-	return lruvec->zone;
+	return lruvec->pgdat;
 #else
-	return container_of(lruvec, struct zone, lruvec);
+	return container_of(lruvec, struct pglist_data, lruvec);
 #endif
 }
 
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 606137b3b778..5bc0457ee3a8 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -73,9 +73,9 @@ static inline bool oom_task_origin(const struct task_struct *p)
 extern void mark_oom_victim(struct task_struct *tsk);
 
 #ifdef CONFIG_MMU
-extern void try_oom_reaper(struct task_struct *tsk);
+extern void wake_oom_reaper(struct task_struct *tsk);
 #else
-static inline void try_oom_reaper(struct task_struct *tsk)
+static inline void wake_oom_reaper(struct task_struct *tsk)
 {
 }
 #endif
@@ -107,27 +107,7 @@ extern void oom_killer_enable(void);
 
 extern struct task_struct *find_lock_task_mm(struct task_struct *p);
 
-static inline bool task_will_free_mem(struct task_struct *task)
-{
-	struct signal_struct *sig = task->signal;
-
-	/*
-	 * A coredumping process may sleep for an extended period in exit_mm(),
-	 * so the oom killer cannot assume that the process will promptly exit
-	 * and release memory.
-	 */
-	if (sig->flags & SIGNAL_GROUP_COREDUMP)
-		return false;
-
-	if (!(task->flags & PF_EXITING))
-		return false;
-
-	/* Make sure that the whole thread group is going down */
-	if (!thread_group_empty(task) && !(sig->flags & SIGNAL_GROUP_EXIT))
-		return false;
-
-	return true;
-}
+bool task_will_free_mem(struct task_struct *task);
 
 /* sysctls */
 extern int sysctl_oom_dump_tasks;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d99218a1e043..553af2923824 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -523,6 +523,7 @@ static inline int get_dumpable(struct mm_struct *mm)
 #define MMF_HAS_UPROBES		19	/* has uprobes */
 #define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
 #define MMF_OOM_REAPED		21	/* mm has been already reaped */
+#define MMF_OOM_NOT_REAPABLE	22	/* mm couldn't be reaped */
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
@@ -1949,6 +1950,32 @@ static inline int tsk_nr_cpus_allowed(struct task_struct *p)
 #define TNF_FAULT_LOCAL	0x08
 #define TNF_MIGRATE_FAIL 0x10
 
+static inline bool in_vfork(struct task_struct *tsk)
+{
+	bool ret;
+
+	/*
+	 * need RCU to access ->real_parent if CLONE_VM was used along with
+	 * CLONE_PARENT.
+	 *
+	 * We check real_parent->mm == tsk->mm because CLONE_VFORK does not
+	 * imply CLONE_VM
+	 *
+	 * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus
+	 * ->real_parent is not necessarily the task doing vfork(), so in
+	 * theory we can't rely on task_lock() if we want to dereference it.
+	 *
+	 * And in this case we can't trust the real_parent->mm == tsk->mm
+	 * check, it can be false negative. But we do not care, if init or
+	 * another oom-unkillable task does this it should blame itself.
+	 */
+	rcu_read_lock();
+	ret = tsk->vfork_done && tsk->real_parent->mm == tsk->mm;
+	rcu_read_unlock();
+
+	return ret;
+}
+
 #ifdef CONFIG_NUMA_BALANCING
 extern void task_numa_fault(int last_node, int node, int pages, int flags);
 extern pid_t task_numa_group_id(struct task_struct *p);
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 339ba027ade9..4ad2c5a26399 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -88,7 +88,8 @@ struct kmem_cache {
 };
 
 static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
-				void *x) {
+				void *x)
+{
 	void *object = x - (x - page->s_mem) % cache->size;
 	void *last_object = page->s_mem + (cache->num - 1) * cache->size;
 
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 5624c1f3eb0a..75f56c2ef2d4 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -104,6 +104,10 @@ struct kmem_cache {
 	unsigned int *random_seq;
 #endif
 
+#ifdef CONFIG_KASAN
+	struct kasan_cache kasan_info;
+#endif
+
 	struct kmem_cache_node *node[MAX_NUMNODES];
 };
 
@@ -119,15 +123,17 @@ static inline void sysfs_slab_remove(struct kmem_cache *s)
 void object_err(struct kmem_cache *s, struct page *page,
 		u8 *object, char *reason);
 
+void *fixup_red_left(struct kmem_cache *s, void *p);
+
 static inline void *nearest_obj(struct kmem_cache *cache, struct page *page,
 				void *x) {
 	void *object = x - (x - page_address(page)) % cache->size;
 	void *last_object = page_address(page) +
 		(page->objects - 1) * cache->size;
-	if (unlikely(object > last_object))
-		return last_object;
-	else
-		return object;
+	void *result = (unlikely(object > last_object)) ? last_object : object;
+
+	result = fixup_red_left(cache, result);
+	return result;
 }
 
 #endif /* _LINUX_SLUB_DEF_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 0af2bb2028fd..b17cc4830fa6 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -157,15 +157,6 @@ enum {
 #define SWAP_CLUSTER_MAX 32UL
 #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX
 
-/*
- * Ratio between zone->managed_pages and the "gap" that above the per-zone
- * "high_wmark". While balancing nodes, We allow kswapd to shrink zones that
- * do not meet the (high_wmark + gap) watermark, even which already met the
- * high_wmark, in order to provide better per-zone lru behavior. We are ok to
- * spend not more than 1% of the memory for this zone balancing "gap".
- */
-#define KSWAPD_ZONE_BALANCE_GAP_RATIO 100
-
 #define SWAP_MAP_MAX	0x3e	/* Max duplication count, in first swap_map */
 #define SWAP_MAP_BAD	0x3f	/* Note pageblock is bad, in first swap_map */
 #define SWAP_HAS_CACHE	0x40	/* Flag page is cached, in first swap_map */
@@ -317,6 +308,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page,
 
 /* linux/mm/vmscan.c */
 extern unsigned long zone_reclaimable_pages(struct zone *zone);
+extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);
 extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 					gfp_t gfp_mask, nodemask_t *mask);
 extern int __isolate_lru_page(struct page *page, isolate_mode_t mode);
@@ -324,9 +316,9 @@ extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 						  unsigned long nr_pages,
 						  gfp_t gfp_mask,
 						  bool may_swap);
-extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
-						struct zone *zone,
+						pg_data_t *pgdat,
 						unsigned long *nr_scanned);
 extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
@@ -334,13 +326,14 @@ extern int remove_mapping(struct address_space *mapping, struct page *page);
 extern unsigned long vm_total_pages;
 
 #ifdef CONFIG_NUMA
-extern int zone_reclaim_mode;
+extern int node_reclaim_mode;
 extern int sysctl_min_unmapped_ratio;
 extern int sysctl_min_slab_ratio;
-extern int zone_reclaim(struct zone *, gfp_t, unsigned int);
+extern int node_reclaim(struct pglist_data *, gfp_t, unsigned int);
 #else
-#define zone_reclaim_mode 0
-static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
+#define node_reclaim_mode 0
+static inline int node_reclaim(struct pglist_data *pgdat, gfp_t mask,
+				unsigned int order)
 {
 	return 0;
 }
diff --git a/include/linux/topology.h b/include/linux/topology.h
index afce69296ac0..cb0775e1ee4b 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -54,7 +54,7 @@ int arch_update_cpu_topology(void);
 /*
  * If the distance between nodes in a system is larger than RECLAIM_DISTANCE
  * (in whatever arch specific measurement units returned by node_distance())
- * and zone_reclaim_mode is enabled then the VM will only call zone_reclaim()
+ * and node_reclaim_mode is enabled then the VM will only call node_reclaim()
  * on nodes within this distance.
  */
 #define RECLAIM_DISTANCE 30
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 42604173f122..4d6ec58a8d45 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -23,21 +23,23 @@
 
 enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		FOR_ALL_ZONES(PGALLOC),
+		FOR_ALL_ZONES(ALLOCSTALL),
+		FOR_ALL_ZONES(PGSCAN_SKIP),
 		PGFREE, PGACTIVATE, PGDEACTIVATE,
 		PGFAULT, PGMAJFAULT,
 		PGLAZYFREED,
-		FOR_ALL_ZONES(PGREFILL),
-		FOR_ALL_ZONES(PGSTEAL_KSWAPD),
-		FOR_ALL_ZONES(PGSTEAL_DIRECT),
-		FOR_ALL_ZONES(PGSCAN_KSWAPD),
-		FOR_ALL_ZONES(PGSCAN_DIRECT),
+		PGREFILL,
+		PGSTEAL_KSWAPD,
+		PGSTEAL_DIRECT,
+		PGSCAN_KSWAPD,
+		PGSCAN_DIRECT,
 		PGSCAN_DIRECT_THROTTLE,
 #ifdef CONFIG_NUMA
 		PGSCAN_ZONE_RECLAIM_FAILED,
 #endif
 		PGINODESTEAL, SLABS_SCANNED, KSWAPD_INODESTEAL,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
-		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+		PAGEOUTRUN, PGROTATED,
 		DROP_PAGECACHE, DROP_SLAB,
 #ifdef CONFIG_NUMA_BALANCING
 		NUMA_PTE_UPDATES,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index d2da8e053210..613771909b6e 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -101,25 +101,42 @@ static inline void vm_events_fold_cpu(int cpu)
 #define count_vm_vmacache_event(x) do {} while (0)
 #endif
 
-#define __count_zone_vm_events(item, zone, delta) \
-		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
-		zone_idx(zone), delta)
+#define __count_zid_vm_events(item, zid, delta) \
+	__count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta)
 
 /*
- * Zone based page accounting with per cpu differentials.
+ * Zone and node-based page accounting with per cpu differentials.
  */
-extern atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS];
+extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS];
 
 static inline void zone_page_state_add(long x, struct zone *zone,
 				 enum zone_stat_item item)
 {
 	atomic_long_add(x, &zone->vm_stat[item]);
-	atomic_long_add(x, &vm_stat[item]);
+	atomic_long_add(x, &vm_zone_stat[item]);
+}
+
+static inline void node_page_state_add(long x, struct pglist_data *pgdat,
+				 enum node_stat_item item)
+{
+	atomic_long_add(x, &pgdat->vm_stat[item]);
+	atomic_long_add(x, &vm_node_stat[item]);
 }
 
 static inline unsigned long global_page_state(enum zone_stat_item item)
 {
-	long x = atomic_long_read(&vm_stat[item]);
+	long x = atomic_long_read(&vm_zone_stat[item]);
+#ifdef CONFIG_SMP
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
+
+static inline unsigned long global_node_page_state(enum node_stat_item item)
+{
+	long x = atomic_long_read(&vm_node_stat[item]);
 #ifdef CONFIG_SMP
 	if (x < 0)
 		x = 0;
@@ -160,32 +177,61 @@ static inline unsigned long zone_page_state_snapshot(struct zone *zone,
 	return x;
 }
 
-#ifdef CONFIG_NUMA
+static inline unsigned long node_page_state_snapshot(pg_data_t *pgdat,
+					enum node_stat_item item)
+{
+	long x = atomic_long_read(&pgdat->vm_stat[item]);
 
-extern unsigned long node_page_state(int node, enum zone_stat_item item);
+#ifdef CONFIG_SMP
+	int cpu;
+	for_each_online_cpu(cpu)
+		x += per_cpu_ptr(pgdat->per_cpu_nodestats, cpu)->vm_node_stat_diff[item];
 
-#else
+	if (x < 0)
+		x = 0;
+#endif
+	return x;
+}
 
-#define node_page_state(node, item) global_page_state(item)
 
+#ifdef CONFIG_NUMA
+extern unsigned long sum_zone_node_page_state(int node,
+						enum zone_stat_item item);
+extern unsigned long node_page_state(struct pglist_data *pgdat,
+						enum node_stat_item item);
+#else
+#define sum_zone_node_page_state(node, item) global_page_state(item)
+#define node_page_state(node, item) global_node_page_state(item)
 #endif /* CONFIG_NUMA */
 
 #define add_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, __d)
 #define sub_zone_page_state(__z, __i, __d) mod_zone_page_state(__z, __i, -(__d))
+#define add_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, __d)
+#define sub_node_page_state(__p, __i, __d) mod_node_page_state(__p, __i, -(__d))
 
 #ifdef CONFIG_SMP
 void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long);
 void __inc_zone_page_state(struct page *, enum zone_stat_item);
 void __dec_zone_page_state(struct page *, enum zone_stat_item);
 
+void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long);
+void __inc_node_page_state(struct page *, enum node_stat_item);
+void __dec_node_page_state(struct page *, enum node_stat_item);
+
 void mod_zone_page_state(struct zone *, enum zone_stat_item, long);
 void inc_zone_page_state(struct page *, enum zone_stat_item);
 void dec_zone_page_state(struct page *, enum zone_stat_item);
 
-extern void inc_zone_state(struct zone *, enum zone_stat_item);
+void mod_node_page_state(struct pglist_data *, enum node_stat_item, long);
+void inc_node_page_state(struct page *, enum node_stat_item);
+void dec_node_page_state(struct page *, enum node_stat_item);
+
+extern void inc_node_state(struct pglist_data *, enum node_stat_item);
 extern void __inc_zone_state(struct zone *, enum zone_stat_item);
+extern void __inc_node_state(struct pglist_data *, enum node_stat_item);
 extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
+extern void __dec_node_state(struct pglist_data *, enum node_stat_item);
 
 void quiet_vmstat(void);
 void cpu_vm_stats_fold(int cpu);
@@ -213,16 +259,34 @@ static inline void __mod_zone_page_state(struct zone *zone,
 	zone_page_state_add(delta, zone, item);
 }
 
+static inline void __mod_node_page_state(struct pglist_data *pgdat,
+			enum node_stat_item item, int delta)
+{
+	node_page_state_add(delta, pgdat, item);
+}
+
 static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	atomic_long_inc(&zone->vm_stat[item]);
-	atomic_long_inc(&vm_stat[item]);
+	atomic_long_inc(&vm_zone_stat[item]);
+}
+
+static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	atomic_long_inc(&pgdat->vm_stat[item]);
+	atomic_long_inc(&vm_node_stat[item]);
 }
 
 static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	atomic_long_dec(&zone->vm_stat[item]);
-	atomic_long_dec(&vm_stat[item]);
+	atomic_long_dec(&vm_zone_stat[item]);
+}
+
+static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item)
+{
+	atomic_long_dec(&pgdat->vm_stat[item]);
+	atomic_long_dec(&vm_node_stat[item]);
 }
 
 static inline void __inc_zone_page_state(struct page *page,
@@ -231,12 +295,26 @@ static inline void __inc_zone_page_state(struct page *page,
 	__inc_zone_state(page_zone(page), item);
 }
 
+static inline void __inc_node_page_state(struct page *page,
+			enum node_stat_item item)
+{
+	__inc_node_state(page_pgdat(page), item);
+}
+
+
 static inline void __dec_zone_page_state(struct page *page,
 			enum zone_stat_item item)
 {
 	__dec_zone_state(page_zone(page), item);
 }
 
+static inline void __dec_node_page_state(struct page *page,
+			enum node_stat_item item)
+{
+	__dec_node_state(page_pgdat(page), item);
+}
+
+
 /*
  * We only use atomic operations to update counters. So there is no need to
  * disable interrupts.
@@ -245,7 +323,12 @@ static inline void __dec_zone_page_state(struct page *page,
 #define dec_zone_page_state __dec_zone_page_state
 #define mod_zone_page_state __mod_zone_page_state
 
+#define inc_node_page_state __inc_node_page_state
+#define dec_node_page_state __dec_node_page_state
+#define mod_node_page_state __mod_node_page_state
+
 #define inc_zone_state __inc_zone_state
+#define inc_node_state __inc_node_state
 #define dec_zone_state __dec_zone_state
 
 #define set_pgdat_percpu_threshold(pgdat, callback) { }
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 717e6149e753..fc1e16c25a29 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -320,7 +320,7 @@ void laptop_mode_timer_fn(unsigned long data);
 static inline void laptop_sync_completion(void) { }
 #endif
 void throttle_vm_writeout(gfp_t gfp_mask);
-bool zone_dirty_ok(struct zone *zone);
+bool node_dirty_ok(struct pglist_data *pgdat);
 int wb_domain_init(struct wb_domain *dom, gfp_t gfp);
 #ifdef CONFIG_CGROUP_WRITEBACK
 void wb_domain_exit(struct wb_domain *dom);
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index 36e2d6fb1360..c2ba402ab256 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -226,26 +226,26 @@ TRACE_EVENT(mm_compaction_try_to_compact_pages,
 	TP_PROTO(
 		int order,
 		gfp_t gfp_mask,
-		enum migrate_mode mode),
+		int prio),
 
-	TP_ARGS(order, gfp_mask, mode),
+	TP_ARGS(order, gfp_mask, prio),
 
 	TP_STRUCT__entry(
 		__field(int, order)
 		__field(gfp_t, gfp_mask)
-		__field(enum migrate_mode, mode)
+		__field(int, prio)
 	),
 
 	TP_fast_assign(
 		__entry->order = order;
 		__entry->gfp_mask = gfp_mask;
-		__entry->mode = mode;
+		__entry->prio = prio;
 	),
 
-	TP_printk("order=%d gfp_mask=0x%x mode=%d",
+	TP_printk("order=%d gfp_mask=0x%x priority=%d",
 		__entry->order,
 		__entry->gfp_mask,
-		(int)__entry->mode)
+		__entry->prio)
 );
 
 DECLARE_EVENT_CLASS(mm_compaction_suitable_template,
diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h
index 43cedbf0c759..5a81ab48a2fb 100644
--- a/include/trace/events/mmflags.h
+++ b/include/trace/events/mmflags.h
@@ -11,6 +11,7 @@
 
 #define __def_gfpflag_names						\
 	{(unsigned long)GFP_TRANSHUGE,		"GFP_TRANSHUGE"},	\
+	{(unsigned long)GFP_TRANSHUGE_LIGHT,	"GFP_TRANSHUGE_LIGHT"}, \
 	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"},\
 	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
 	{(unsigned long)GFP_USER,		"GFP_USER"},		\
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
index 0101ef37f1ee..c88fd0934e7e 100644
--- a/include/trace/events/vmscan.h
+++ b/include/trace/events/vmscan.h
@@ -55,21 +55,23 @@ TRACE_EVENT(mm_vmscan_kswapd_sleep,
 
 TRACE_EVENT(mm_vmscan_kswapd_wake,
 
-	TP_PROTO(int nid, int order),
+	TP_PROTO(int nid, int zid, int order),
 
-	TP_ARGS(nid, order),
+	TP_ARGS(nid, zid, order),
 
 	TP_STRUCT__entry(
 		__field(	int,	nid	)
+		__field(	int,	zid	)
 		__field(	int,	order	)
 	),
 
 	TP_fast_assign(
 		__entry->nid	= nid;
+		__entry->zid    = zid;
 		__entry->order	= order;
 	),
 
-	TP_printk("nid=%d order=%d", __entry->nid, __entry->order)
+	TP_printk("nid=%d zid=%d order=%d", __entry->nid, __entry->zid, __entry->order)
 );
 
 TRACE_EVENT(mm_vmscan_wakeup_kswapd,
@@ -98,47 +100,50 @@ TRACE_EVENT(mm_vmscan_wakeup_kswapd,
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags),
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx),
 
 	TP_STRUCT__entry(
 		__field(	int,	order		)
 		__field(	int,	may_writepage	)
 		__field(	gfp_t,	gfp_flags	)
+		__field(	int,	classzone_idx	)
 	),
 
 	TP_fast_assign(
 		__entry->order		= order;
 		__entry->may_writepage	= may_writepage;
 		__entry->gfp_flags	= gfp_flags;
+		__entry->classzone_idx	= classzone_idx;
 	),
 
-	TP_printk("order=%d may_writepage=%d gfp_flags=%s",
+	TP_printk("order=%d may_writepage=%d gfp_flags=%s classzone_idx=%d",
 		__entry->order,
 		__entry->may_writepage,
-		show_gfp_flags(__entry->gfp_flags))
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->classzone_idx)
 );
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags)
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags)
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
 DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
 
-	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags, int classzone_idx),
 
-	TP_ARGS(order, may_writepage, gfp_flags)
+	TP_ARGS(order, may_writepage, gfp_flags, classzone_idx)
 );
 
 DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
@@ -266,16 +271,18 @@ TRACE_EVENT(mm_shrink_slab_end,
 
 DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file),
 
 	TP_STRUCT__entry(
+		__field(int, classzone_idx)
 		__field(int, order)
 		__field(unsigned long, nr_requested)
 		__field(unsigned long, nr_scanned)
@@ -285,6 +292,7 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 	),
 
 	TP_fast_assign(
+		__entry->classzone_idx = classzone_idx;
 		__entry->order = order;
 		__entry->nr_requested = nr_requested;
 		__entry->nr_scanned = nr_scanned;
@@ -293,8 +301,9 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 		__entry->file = file;
 	),
 
-	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
+	TP_printk("isolate_mode=%d classzone=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu file=%d",
 		__entry->isolate_mode,
+		__entry->classzone_idx,
 		__entry->order,
 		__entry->nr_requested,
 		__entry->nr_scanned,
@@ -304,27 +313,29 @@ DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
 
 DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
 DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
 
-	TP_PROTO(int order,
+	TP_PROTO(int classzone_idx,
+		int order,
 		unsigned long nr_requested,
 		unsigned long nr_scanned,
 		unsigned long nr_taken,
 		isolate_mode_t isolate_mode,
 		int file),
 
-	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
+	TP_ARGS(classzone_idx, order, nr_requested, nr_scanned, nr_taken, isolate_mode, file)
 
 );
 
@@ -352,15 +363,14 @@ TRACE_EVENT(mm_vmscan_writepage,
 
 TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 
-	TP_PROTO(struct zone *zone,
+	TP_PROTO(int nid,
 		unsigned long nr_scanned, unsigned long nr_reclaimed,
 		int priority, int file),
 
-	TP_ARGS(zone, nr_scanned, nr_reclaimed, priority, file),
+	TP_ARGS(nid, nr_scanned, nr_reclaimed, priority, file),
 
 	TP_STRUCT__entry(
 		__field(int, nid)
-		__field(int, zid)
 		__field(unsigned long, nr_scanned)
 		__field(unsigned long, nr_reclaimed)
 		__field(int, priority)
@@ -368,16 +378,15 @@ TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
 	),
 
 	TP_fast_assign(
-		__entry->nid = zone_to_nid(zone);
-		__entry->zid = zone_idx(zone);
+		__entry->nid = nid;
 		__entry->nr_scanned = nr_scanned;
 		__entry->nr_reclaimed = nr_reclaimed;
 		__entry->priority = priority;
 		__entry->reclaim_flags = trace_shrink_flags(file);
 	),
 
-	TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
-		__entry->nid, __entry->zid,
+	TP_printk("nid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
+		__entry->nid,
 		__entry->nr_scanned, __entry->nr_reclaimed,
 		__entry->priority,
 		show_reclaim_flags(__entry->reclaim_flags))
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 531f5811ff6b..2ccd9ccbf9ef 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -412,11 +412,11 @@ TRACE_EVENT(global_dirty_state,
 	),
 
 	TP_fast_assign(
-		__entry->nr_dirty	= global_page_state(NR_FILE_DIRTY);
-		__entry->nr_writeback	= global_page_state(NR_WRITEBACK);
-		__entry->nr_unstable	= global_page_state(NR_UNSTABLE_NFS);
-		__entry->nr_dirtied	= global_page_state(NR_DIRTIED);
-		__entry->nr_written	= global_page_state(NR_WRITTEN);
+		__entry->nr_dirty	= global_node_page_state(NR_FILE_DIRTY);
+		__entry->nr_writeback	= global_node_page_state(NR_WRITEBACK);
+		__entry->nr_unstable	= global_node_page_state(NR_UNSTABLE_NFS);
+		__entry->nr_dirtied	= global_node_page_state(NR_DIRTIED);
+		__entry->nr_written	= global_node_page_state(NR_WRITTEN);
 		__entry->background_thresh = background_thresh;
 		__entry->dirty_thresh	= dirty_thresh;
 		__entry->dirty_limit	= global_wb_domain.dirty_limit;