Merge branch 'akpm' (incoming from Andrew)

Merge first patch-bomb from Andrew Morton:

 - a couple of misc things

 - inotify/fsnotify work from Jan

 - ocfs2 updates (partial)

 - about half of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (117 commits)
  mm/migrate: remove unused function, fail_migrate_page()
  mm/migrate: remove putback_lru_pages, fix comment on putback_movable_pages
  mm/migrate: correct failure handling if !hugepage_migration_support()
  mm/migrate: add comment about permanent failure path
  mm, page_alloc: warn for non-blockable __GFP_NOFAIL allocation failure
  mm: compaction: reset scanner positions immediately when they meet
  mm: compaction: do not mark unmovable pageblocks as skipped in async compaction
  mm: compaction: detect when scanners meet in isolate_freepages
  mm: compaction: reset cached scanner pfn's before reading them
  mm: compaction: encapsulate defer reset logic
  mm: compaction: trace compaction begin and end
  memcg, oom: lock mem_cgroup_print_oom_info
  sched: add tracepoints related to NUMA task migration
  mm: numa: do not automatically migrate KSM pages
  mm: numa: trace tasks that fail migration due to rate limiting
  mm: numa: limit scope of lock for NUMA migrate rate limiting
  mm: numa: make NUMA-migrate related functions static
  lib/show_mem.c: show num_poisoned_pages when oom
  mm/hwpoison: add '#' to hwpoison_inject
  mm/memblock: use WARN_ONCE when MAX_NUMNODES passed as input parameter
  ...

20 files changed, 543 insertions, 243 deletions

diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index f1f07d31a3af..2fae55def608 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -5,6 +5,7 @@
 #define _LINUX_BOOTMEM_H
 
 #include <linux/mmzone.h>
+#include <linux/mm_types.h>
 #include <asm/dma.h>
 
 /*
@@ -52,7 +53,6 @@ extern void free_bootmem_node(pg_data_t *pgdat,
 			      unsigned long size);
 extern void free_bootmem(unsigned long physaddr, unsigned long size);
 extern void free_bootmem_late(unsigned long physaddr, unsigned long size);
-extern void __free_pages_bootmem(struct page *page, unsigned int order);
 
 /*
  * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE,
@@ -142,6 +142,157 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 #define alloc_bootmem_low_pages_node(pgdat, x) \
 	__alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0)
 
+
+#if defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM)
+
+/* FIXME: use MEMBLOCK_ALLOC_* variants here */
+#define BOOTMEM_ALLOC_ACCESSIBLE	0
+#define BOOTMEM_ALLOC_ANYWHERE		(~(phys_addr_t)0)
+
+/* FIXME: Move to memblock.h at a point where we remove nobootmem.c */
+void *memblock_virt_alloc_try_nid_nopanic(phys_addr_t size,
+		phys_addr_t align, phys_addr_t min_addr,
+		phys_addr_t max_addr, int nid);
+void *memblock_virt_alloc_try_nid(phys_addr_t size, phys_addr_t align,
+		phys_addr_t min_addr, phys_addr_t max_addr, int nid);
+void __memblock_free_early(phys_addr_t base, phys_addr_t size);
+void __memblock_free_late(phys_addr_t base, phys_addr_t size);
+
+static inline void * __init memblock_virt_alloc(
+					phys_addr_t size,  phys_addr_t align)
+{
+	return memblock_virt_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT,
+					    BOOTMEM_ALLOC_ACCESSIBLE,
+					    NUMA_NO_NODE);
+}
+
+static inline void * __init memblock_virt_alloc_nopanic(
+					phys_addr_t size, phys_addr_t align)
+{
+	return memblock_virt_alloc_try_nid_nopanic(size, align,
+						    BOOTMEM_LOW_LIMIT,
+						    BOOTMEM_ALLOC_ACCESSIBLE,
+						    NUMA_NO_NODE);
+}
+
+static inline void * __init memblock_virt_alloc_from_nopanic(
+		phys_addr_t size, phys_addr_t align, phys_addr_t min_addr)
+{
+	return memblock_virt_alloc_try_nid_nopanic(size, align, min_addr,
+						    BOOTMEM_ALLOC_ACCESSIBLE,
+						    NUMA_NO_NODE);
+}
+
+static inline void * __init memblock_virt_alloc_node(
+						phys_addr_t size, int nid)
+{
+	return memblock_virt_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT,
+					    BOOTMEM_ALLOC_ACCESSIBLE, nid);
+}
+
+static inline void * __init memblock_virt_alloc_node_nopanic(
+						phys_addr_t size, int nid)
+{
+	return memblock_virt_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT,
+						    BOOTMEM_ALLOC_ACCESSIBLE,
+						    nid);
+}
+
+static inline void __init memblock_free_early(
+					phys_addr_t base, phys_addr_t size)
+{
+	__memblock_free_early(base, size);
+}
+
+static inline void __init memblock_free_early_nid(
+				phys_addr_t base, phys_addr_t size, int nid)
+{
+	__memblock_free_early(base, size);
+}
+
+static inline void __init memblock_free_late(
+					phys_addr_t base, phys_addr_t size)
+{
+	__memblock_free_late(base, size);
+}
+
+#else
+
+#define BOOTMEM_ALLOC_ACCESSIBLE	0
+
+
+/* Fall back to all the existing bootmem APIs */
+static inline void * __init memblock_virt_alloc(
+					phys_addr_t size,  phys_addr_t align)
+{
+	if (!align)
+		align = SMP_CACHE_BYTES;
+	return __alloc_bootmem(size, align, BOOTMEM_LOW_LIMIT);
+}
+
+static inline void * __init memblock_virt_alloc_nopanic(
+					phys_addr_t size, phys_addr_t align)
+{
+	if (!align)
+		align = SMP_CACHE_BYTES;
+	return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT);
+}
+
+static inline void * __init memblock_virt_alloc_from_nopanic(
+		phys_addr_t size, phys_addr_t align, phys_addr_t min_addr)
+{
+	return __alloc_bootmem_nopanic(size, align, min_addr);
+}
+
+static inline void * __init memblock_virt_alloc_node(
+						phys_addr_t size, int nid)
+{
+	return __alloc_bootmem_node(NODE_DATA(nid), size, SMP_CACHE_BYTES,
+				     BOOTMEM_LOW_LIMIT);
+}
+
+static inline void * __init memblock_virt_alloc_node_nopanic(
+						phys_addr_t size, int nid)
+{
+	return __alloc_bootmem_node_nopanic(NODE_DATA(nid), size,
+					     SMP_CACHE_BYTES,
+					     BOOTMEM_LOW_LIMIT);
+}
+
+static inline void * __init memblock_virt_alloc_try_nid(phys_addr_t size,
+	phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid)
+{
+	return __alloc_bootmem_node_high(NODE_DATA(nid), size, align,
+					  min_addr);
+}
+
+static inline void * __init memblock_virt_alloc_try_nid_nopanic(
+			phys_addr_t size, phys_addr_t align,
+			phys_addr_t min_addr, phys_addr_t max_addr, int nid)
+{
+	return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align,
+				min_addr, max_addr);
+}
+
+static inline void __init memblock_free_early(
+					phys_addr_t base, phys_addr_t size)
+{
+	free_bootmem(base, size);
+}
+
+static inline void __init memblock_free_early_nid(
+				phys_addr_t base, phys_addr_t size, int nid)
+{
+	free_bootmem_node(NODE_DATA(nid), base, size);
+}
+
+static inline void __init memblock_free_late(
+					phys_addr_t base, phys_addr_t size)
+{
+	free_bootmem_late(base, size);
+}
+#endif /* defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) */
+
 #ifdef CONFIG_HAVE_ARCH_ALLOC_REMAP
 extern void *alloc_remap(int nid, unsigned long size);
 #else
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 091d72e70d8a..7e1c76e3cd68 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -62,6 +62,22 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 	return zone->compact_considered < defer_limit;
 }
 
+/*
+ * Update defer tracking counters after successful compaction of given order,
+ * which means an allocation either succeeded (alloc_success == true) or is
+ * expected to succeed.
+ */
+static inline void compaction_defer_reset(struct zone *zone, int order,
+		bool alloc_success)
+{
+	if (alloc_success) {
+		zone->compact_considered = 0;
+		zone->compact_defer_shift = 0;
+	}
+	if (order >= zone->compact_order_failed)
+		zone->compact_order_failed = order + 1;
+}
+
 /* Returns true if restarting compaction after many failures */
 static inline bool compaction_restarting(struct zone *zone, int order)
 {
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index fc0e34ce038f..fe8cb610deac 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -85,6 +85,8 @@ extern void debug_dma_sync_sg_for_device(struct device *dev,
 
 extern void debug_dma_dump_mappings(struct device *dev);
 
+extern void debug_dma_assert_idle(struct page *page);
+
 #else /* CONFIG_DMA_API_DEBUG */
 
 static inline void dma_debug_add_bus(struct bus_type *bus)
@@ -183,6 +185,10 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 {
 }
 
+static inline void debug_dma_assert_idle(struct page *page)
+{
+}
+
 #endif /* CONFIG_DMA_API_DEBUG */
 
 #endif /* __DMA_DEBUG_H */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 4b2ee8d12f5e..7d8d5e608594 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -15,7 +15,6 @@
 #include <linux/path.h> /* struct path */
 #include <linux/spinlock.h>
 #include <linux/types.h>
-
 #include <linux/atomic.h>
 
 /*
@@ -79,6 +78,7 @@ struct fsnotify_group;
 struct fsnotify_event;
 struct fsnotify_mark;
 struct fsnotify_event_private_data;
+struct fsnotify_fname;
 
 /*
  * Each group much define these ops.  The fsnotify infrastructure will call
@@ -94,17 +94,27 @@ struct fsnotify_event_private_data;
  * 		userspace messages that marks have been removed.
  */
 struct fsnotify_ops {
-	bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode,
-				  struct fsnotify_mark *inode_mark,
-				  struct fsnotify_mark *vfsmount_mark,
-				  __u32 mask, void *data, int data_type);
 	int (*handle_event)(struct fsnotify_group *group,
+			    struct inode *inode,
 			    struct fsnotify_mark *inode_mark,
 			    struct fsnotify_mark *vfsmount_mark,
-			    struct fsnotify_event *event);
+			    u32 mask, void *data, int data_type,
+			    const unsigned char *file_name);
 	void (*free_group_priv)(struct fsnotify_group *group);
 	void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group);
-	void (*free_event_priv)(struct fsnotify_event_private_data *priv);
+	void (*free_event)(struct fsnotify_event *event);
+};
+
+/*
+ * all of the information about the original object we want to now send to
+ * a group.  If you want to carry more info from the accessing task to the
+ * listener this structure is where you need to be adding fields.
+ */
+struct fsnotify_event {
+	struct list_head list;
+	/* inode may ONLY be dereferenced during handle_event(). */
+	struct inode *inode;	/* either the inode the event happened to or its parent */
+	u32 mask;		/* the type of access, bitwise OR for FS_* event types */
 };
 
 /*
@@ -148,7 +158,11 @@ struct fsnotify_group {
 					 * a group */
 	struct list_head marks_list;	/* all inode marks for this group */
 
-	struct fasync_struct    *fsn_fa;    /* async notification */
+	struct fasync_struct *fsn_fa;    /* async notification */
+
+	struct fsnotify_event overflow_event;	/* Event we queue when the
+						 * notification list is too
+						 * full */
 
 	/* groups can define private fields here or use the void *private */
 	union {
@@ -177,76 +191,10 @@ struct fsnotify_group {
 	};
 };
 
-/*
- * A single event can be queued in multiple group->notification_lists.
- *
- * each group->notification_list will point to an event_holder which in turns points
- * to the actual event that needs to be sent to userspace.
- *
- * Seemed cheaper to create a refcnt'd event and a small holder for every group
- * than create a different event for every group
- *
- */
-struct fsnotify_event_holder {
-	struct fsnotify_event *event;
-	struct list_head event_list;
-};
-
-/*
- * Inotify needs to tack data onto an event.  This struct lets us later find the
- * correct private data of the correct group.
- */
-struct fsnotify_event_private_data {
-	struct fsnotify_group *group;
-	struct list_head event_list;
-};
-
-/*
- * all of the information about the original object we want to now send to
- * a group.  If you want to carry more info from the accessing task to the
- * listener this structure is where you need to be adding fields.
- */
-struct fsnotify_event {
-	/*
-	 * If we create an event we are also likely going to need a holder
-	 * to link to a group.  So embed one holder in the event.  Means only
-	 * one allocation for the common case where we only have one group
-	 */
-	struct fsnotify_event_holder holder;
-	spinlock_t lock;	/* protection for the associated event_holder and private_list */
-	/* to_tell may ONLY be dereferenced during handle_event(). */
-	struct inode *to_tell;	/* either the inode the event happened to or its parent */
-	/*
-	 * depending on the event type we should have either a path or inode
-	 * We hold a reference on path, but NOT on inode.  Since we have the ref on
-	 * the path, it may be dereferenced at any point during this object's
-	 * lifetime.  That reference is dropped when this object's refcnt hits
-	 * 0.  If this event contains an inode instead of a path, the inode may
-	 * ONLY be used during handle_event().
-	 */
-	union {
-		struct path path;
-		struct inode *inode;
-	};
 /* when calling fsnotify tell it if the data is a path or inode */
 #define FSNOTIFY_EVENT_NONE	0
 #define FSNOTIFY_EVENT_PATH	1
 #define FSNOTIFY_EVENT_INODE	2
-	int data_type;		/* which of the above union we have */
-	atomic_t refcnt;	/* how many groups still are using/need to send this event */
-	__u32 mask;		/* the type of access, bitwise OR for FS_* event types */
-
-	u32 sync_cookie;	/* used to corrolate events, namely inotify mv events */
-	const unsigned char *file_name;
-	size_t name_len;
-	struct pid *tgid;
-
-#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-	__u32 response;	/* userspace answer to question */
-#endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
-
-	struct list_head private_data_list;	/* groups can store private data here */
-};
 
 /*
  * Inode specific fields in an fsnotify_mark
@@ -370,17 +318,12 @@ extern void fsnotify_put_group(struct fsnotify_group *group);
 extern void fsnotify_destroy_group(struct fsnotify_group *group);
 /* fasync handler function */
 extern int fsnotify_fasync(int fd, struct file *file, int on);
-/* take a reference to an event */
-extern void fsnotify_get_event(struct fsnotify_event *event);
-extern void fsnotify_put_event(struct fsnotify_event *event);
-/* find private data previously attached to an event and unlink it */
-extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struct fsnotify_group *group,
-									   struct fsnotify_event *event);
-
+/* Free event from memory */
+extern void fsnotify_destroy_event(struct fsnotify_group *group,
+				   struct fsnotify_event *event);
 /* attach the event to the group notification queue */
 extern struct fsnotify_event *fsnotify_add_notify_event(struct fsnotify_group *group,
 							struct fsnotify_event *event,
-							struct fsnotify_event_private_data *priv,
 							struct fsnotify_event *(*merge)(struct list_head *,
 											struct fsnotify_event *));
 /* true if the group notification queue is empty */
@@ -430,15 +373,8 @@ extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_unmount_inodes(struct list_head *list);
 
 /* put here because inotify does some weird stuff when destroying watches */
-extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
-						    void *data, int data_is,
-						    const unsigned char *name,
-						    u32 cookie, gfp_t gfp);
-
-/* fanotify likes to change events after they are on lists... */
-extern struct fsnotify_event *fsnotify_clone_event(struct fsnotify_event *old_event);
-extern int fsnotify_replace_event(struct fsnotify_event_holder *old_holder,
-				  struct fsnotify_event *new_event);
+extern void fsnotify_init_event(struct fsnotify_event *event,
+				struct inode *to_tell, u32 mask);
 
 #else
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 91672e2deec3..db512014e061 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -157,6 +157,26 @@ static inline int hpage_nr_pages(struct page *page)
 		return HPAGE_PMD_NR;
 	return 1;
 }
+/*
+ * compound_trans_head() should be used instead of compound_head(),
+ * whenever the "page" passed as parameter could be the tail of a
+ * transparent hugepage that could be undergoing a
+ * __split_huge_page_refcount(). The page structure layout often
+ * changes across releases and it makes extensive use of unions. So if
+ * the page structure layout will change in a way that
+ * page->first_page gets clobbered by __split_huge_page_refcount, the
+ * implementation making use of smp_rmb() will be required.
+ *
+ * Currently we define compound_trans_head as compound_head, because
+ * page->private is in the same union with page->first_page, and
+ * page->private isn't clobbered. However this also means we're
+ * currently leaving dirt into the page->private field of anonymous
+ * pages resulting from a THP split, instead of setting page->private
+ * to zero like for every other page that has PG_private not set. But
+ * anonymous pages don't use page->private so this is not a problem.
+ */
+#if 0
+/* This will be needed if page->private will be clobbered in split_huge_page */
 static inline struct page *compound_trans_head(struct page *page)
 {
 	if (PageTail(page)) {
@@ -174,6 +194,9 @@ static inline struct page *compound_trans_head(struct page *page)
 	}
 	return page;
 }
+#else
+#define compound_trans_head(page) compound_head(page)
+#endif
 
 extern int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 				unsigned long addr, pmd_t pmd, pmd_t *pmdp);
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index bd7e98752222..d01cc972a1d9 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -31,7 +31,6 @@ struct hugepage_subpool *hugepage_new_subpool(long nr_blocks);
 void hugepage_put_subpool(struct hugepage_subpool *spool);
 
 int PageHuge(struct page *page);
-int PageHeadHuge(struct page *page_head);
 
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -104,11 +103,6 @@ static inline int PageHuge(struct page *page)
 	return 0;
 }
 
-static inline int PageHeadHuge(struct page *page_head)
-{
-	return 0;
-}
-
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 }
@@ -360,6 +354,7 @@ static inline pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 
 static inline struct hstate *page_hstate(struct page *page)
 {
+	VM_BUG_ON(!PageHuge(page));
 	return size_to_hstate(PAGE_SIZE << compound_order(page));
 }
 
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index f0e52383a001..1516a8ff8f92 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -41,6 +41,7 @@ extern struct fs_struct init_fs;
 
 #define INIT_SIGNALS(sig) {						\
 	.nr_threads	= 1,						\
+	.thread_head	= LIST_HEAD_INIT(init_task.thread_node),	\
 	.wait_chldexit	= __WAIT_QUEUE_HEAD_INITIALIZER(sig.wait_chldexit),\
 	.shared_pending	= { 						\
 		.list = LIST_HEAD_INIT(sig.shared_pending.list),	\
@@ -222,6 +223,7 @@ extern struct task_group root_task_group;
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
 	.thread_group	= LIST_HEAD_INIT(tsk.thread_group),		\
+	.thread_node	= LIST_HEAD_INIT(init_signals.thread_head),	\
 	INIT_IDS							\
 	INIT_PERF_EVENTS(tsk)						\
 	INIT_TRACE_IRQFLAGS						\
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 45c9b6a17bcb..3be6bb18562d 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -73,11 +73,7 @@ static inline void set_page_stable_node(struct page *page,
 struct page *ksm_might_need_to_copy(struct page *page,
 			struct vm_area_struct *vma, unsigned long address);
 
-int page_referenced_ksm(struct page *page,
-			struct mem_cgroup *memcg, unsigned long *vm_flags);
-int try_to_unmap_ksm(struct page *page, enum ttu_flags flags);
-int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page *,
-		  struct vm_area_struct *, unsigned long, void *), void *arg);
+int rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc);
 void ksm_migrate_page(struct page *newpage, struct page *oldpage);
 
 #else  /* !CONFIG_KSM */
@@ -115,13 +111,8 @@ static inline int page_referenced_ksm(struct page *page,
 	return 0;
 }
 
-static inline int try_to_unmap_ksm(struct page *page, enum ttu_flags flags)
-{
-	return 0;
-}
-
-static inline int rmap_walk_ksm(struct page *page, int (*rmap_one)(struct page*,
-		struct vm_area_struct *, unsigned long, void *), void *arg)
+static inline int rmap_walk_ksm(struct page *page,
+			struct rmap_walk_control *rwc)
 {
 	return 0;
 }
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 77c60e52939d..cd0274bebd4c 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -19,9 +19,13 @@
 
 #define INIT_MEMBLOCK_REGIONS	128
 
+/* Definition of memblock flags. */
+#define MEMBLOCK_HOTPLUG	0x1	/* hotpluggable region */
+
 struct memblock_region {
 	phys_addr_t base;
 	phys_addr_t size;
+	unsigned long flags;
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 	int nid;
 #endif
@@ -43,12 +47,17 @@ 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 */
 
 #define memblock_dbg(fmt, ...) \
 	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
 
-phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end,
-				phys_addr_t size, phys_addr_t align, int nid);
+phys_addr_t memblock_find_in_range_node(phys_addr_t size, phys_addr_t align,
+					    phys_addr_t start, phys_addr_t end,
+					    int nid);
 phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
 				   phys_addr_t size, phys_addr_t align);
 phys_addr_t get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
@@ -59,6 +68,28 @@ int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_free(phys_addr_t base, phys_addr_t size);
 int memblock_reserve(phys_addr_t base, phys_addr_t size);
 void memblock_trim_memory(phys_addr_t align);
+int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
+int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
+#ifdef CONFIG_MOVABLE_NODE
+static inline bool memblock_is_hotpluggable(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_HOTPLUG;
+}
+
+static inline bool 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
 
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
 int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
@@ -87,7 +118,7 @@ void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start,
 /**
  * for_each_free_mem_range - iterate through free memblock areas
  * @i: u64 used as loop variable
- * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @nid: node selector, %NUMA_NO_NODE for all nodes
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
@@ -107,7 +138,7 @@ void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
 /**
  * for_each_free_mem_range_reverse - rev-iterate through free memblock areas
  * @i: u64 used as loop variable
- * @nid: node selector, %MAX_NUMNODES for all nodes
+ * @nid: node selector, %NUMA_NO_NODE for all nodes
  * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
  * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
@@ -121,8 +152,21 @@ void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
 	     i != (u64)ULLONG_MAX;					\
 	     __next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid))
 
+static inline void memblock_set_region_flags(struct memblock_region *r,
+					     unsigned long flags)
+{
+	r->flags |= flags;
+}
+
+static inline void memblock_clear_region_flags(struct memblock_region *r,
+					       unsigned long flags)
+{
+	r->flags &= ~flags;
+}
+
 #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
-int memblock_set_node(phys_addr_t base, phys_addr_t size, int nid);
+int memblock_set_node(phys_addr_t base, phys_addr_t size,
+		      struct memblock_type *type, int nid);
 
 static inline void memblock_set_region_node(struct memblock_region *r, int nid)
 {
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 9fe426b30a41..5f1ea756aace 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -211,20 +211,8 @@ static inline void mpol_get(struct mempolicy *pol)
 {
 }
 
-static inline struct mempolicy *mpol_dup(struct mempolicy *old)
-{
-	return NULL;
-}
-
 struct shared_policy {};
 
-static inline int mpol_set_shared_policy(struct shared_policy *info,
-					struct vm_area_struct *vma,
-					struct mempolicy *new)
-{
-	return -EINVAL;
-}
-
 static inline void mpol_shared_policy_init(struct shared_policy *sp,
 						struct mempolicy *mpol)
 {
@@ -234,12 +222,6 @@ static inline void mpol_free_shared_policy(struct shared_policy *p)
 {
 }
 
-static inline struct mempolicy *
-mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
-{
-	return NULL;
-}
-
 #define vma_policy(vma) NULL
 
 static inline int
@@ -266,10 +248,6 @@ static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
 {
 }
 
-static inline void mpol_fix_fork_child_flag(struct task_struct *p)
-{
-}
-
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
 				unsigned long addr, gfp_t gfp_flags,
 				struct mempolicy **mpol, nodemask_t **nodemask)
@@ -284,12 +262,6 @@ static inline bool init_nodemask_of_mempolicy(nodemask_t *m)
 	return false;
 }
 
-static inline bool mempolicy_nodemask_intersects(struct task_struct *tsk,
-			const nodemask_t *mask)
-{
-	return false;
-}
-
 static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from,
 				   const nodemask_t *to, int flags)
 {
@@ -307,10 +279,6 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
 }
 #endif
 
-static inline void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
-{
-}
-
 static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
 				 unsigned long address)
 {
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index f015c059e159..84a31ad0b791 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -35,16 +35,12 @@ enum migrate_reason {
 
 #ifdef CONFIG_MIGRATION
 
-extern void putback_lru_pages(struct list_head *l);
 extern void putback_movable_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *, enum migrate_mode);
 extern int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, enum migrate_mode mode, int reason);
 
-extern int fail_migrate_page(struct address_space *,
-			struct page *, struct page *);
-
 extern int migrate_prep(void);
 extern int migrate_prep_local(void);
 extern int migrate_vmas(struct mm_struct *mm,
@@ -59,7 +55,6 @@ extern int migrate_page_move_mapping(struct address_space *mapping,
 		int extra_count);
 #else
 
-static inline void putback_lru_pages(struct list_head *l) {}
 static inline void putback_movable_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
 		unsigned long private, enum migrate_mode mode, int reason)
@@ -86,7 +81,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 /* Possible settings for the migrate_page() method in address_operations */
 #define migrate_page NULL
-#define fail_migrate_page NULL
 
 #endif /* CONFIG_MIGRATION */
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 35527173cf50..a512dd836931 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -57,6 +57,15 @@ extern int sysctl_legacy_va_layout;
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
+extern int sysctl_overcommit_memory;
+extern int sysctl_overcommit_ratio;
+extern unsigned long sysctl_overcommit_kbytes;
+
+extern int overcommit_ratio_handler(struct ctl_table *, int, void __user *,
+				    size_t *, loff_t *);
+extern int overcommit_kbytes_handler(struct ctl_table *, int, void __user *,
+				    size_t *, loff_t *);
+
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
 
 /* to align the pointer to the (next) page boundary */
@@ -414,15 +423,44 @@ static inline int page_count(struct page *page)
 	return atomic_read(&compound_head(page)->_count);
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+extern int PageHeadHuge(struct page *page_head);
+#else /* CONFIG_HUGETLB_PAGE */
+static inline int PageHeadHuge(struct page *page_head)
+{
+	return 0;
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
+static inline bool __compound_tail_refcounted(struct page *page)
+{
+	return !PageSlab(page) && !PageHeadHuge(page);
+}
+
+/*
+ * This takes a head page as parameter and tells if the
+ * tail page reference counting can be skipped.
+ *
+ * For this to be safe, PageSlab and PageHeadHuge must remain true on
+ * any given page where they return true here, until all tail pins
+ * have been released.
+ */
+static inline bool compound_tail_refcounted(struct page *page)
+{
+	VM_BUG_ON(!PageHead(page));
+	return __compound_tail_refcounted(page);
+}
+
 static inline void get_huge_page_tail(struct page *page)
 {
 	/*
-	 * __split_huge_page_refcount() cannot run
-	 * from under us.
+	 * __split_huge_page_refcount() cannot run from under us.
 	 */
+	VM_BUG_ON(!PageTail(page));
 	VM_BUG_ON(page_mapcount(page) < 0);
 	VM_BUG_ON(atomic_read(&page->_count) != 0);
-	atomic_inc(&page->_mapcount);
+	if (compound_tail_refcounted(page->first_page))
+		atomic_inc(&page->_mapcount);
 }
 
 extern bool __get_page_tail(struct page *page);
@@ -846,11 +884,14 @@ static __always_inline void *lowmem_page_address(const struct page *page)
 #endif
 
 #if defined(WANT_PAGE_VIRTUAL)
-#define page_address(page) ((page)->virtual)
-#define set_page_address(page, address)			\
-	do {						\
-		(page)->virtual = (address);		\
-	} while(0)
+static inline void *page_address(const struct page *page)
+{
+	return page->virtual;
+}
+static inline void set_page_address(struct page *page, void *address)
+{
+	page->virtual = address;
+}
 #define page_address_init()  do { } while(0)
 #endif
 
@@ -984,7 +1025,6 @@ extern void pagefault_out_of_memory(void);
  * various contexts.
  */
 #define SHOW_MEM_FILTER_NODES		(0x0001u)	/* disallowed nodes */
-#define SHOW_MEM_FILTER_PAGE_COUNT	(0x0002u)	/* page type count */
 
 extern void show_free_areas(unsigned int flags);
 extern bool skip_free_areas_node(unsigned int flags, int nid);
@@ -1318,6 +1358,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 
 #if USE_SPLIT_PTE_PTLOCKS
 #if ALLOC_SPLIT_PTLOCKS
+void __init ptlock_cache_init(void);
 extern bool ptlock_alloc(struct page *page);
 extern void ptlock_free(struct page *page);
 
@@ -1326,6 +1367,10 @@ static inline spinlock_t *ptlock_ptr(struct page *page)
 	return page->ptl;
 }
 #else /* ALLOC_SPLIT_PTLOCKS */
+static inline void ptlock_cache_init(void)
+{
+}
+
 static inline bool ptlock_alloc(struct page *page)
 {
 	return true;
@@ -1378,10 +1423,17 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
 	return &mm->page_table_lock;
 }
+static inline void ptlock_cache_init(void) {}
 static inline bool ptlock_init(struct page *page) { return true; }
 static inline void pte_lock_deinit(struct page *page) {}
 #endif /* USE_SPLIT_PTE_PTLOCKS */
 
+static inline void pgtable_init(void)
+{
+	ptlock_cache_init();
+	pgtable_cache_init();
+}
+
 static inline bool pgtable_page_ctor(struct page *page)
 {
 	inc_zone_page_state(page, NR_PAGETABLE);
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 7f7f8dae4b1d..16373c8f5f57 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -9,6 +9,7 @@
 
 extern int sysctl_overcommit_memory;
 extern int sysctl_overcommit_ratio;
+extern unsigned long sysctl_overcommit_kbytes;
 extern struct percpu_counter vm_committed_as;
 
 #ifdef CONFIG_SMP
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index bd791e452ad7..5f2052c83154 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -490,6 +490,12 @@ struct zone {
 	unsigned long		managed_pages;
 
 	/*
+	 * Number of MIGRATE_RESEVE page block. To maintain for just
+	 * optimization. Protected by zone->lock.
+	 */
+	int			nr_migrate_reserve_block;
+
+	/*
 	 * rarely used fields:
 	 */
 	const char		*name;
@@ -758,10 +764,7 @@ typedef struct pglist_data {
 	int kswapd_max_order;
 	enum zone_type classzone_idx;
 #ifdef CONFIG_NUMA_BALANCING
-	/*
-	 * Lock serializing the per destination node AutoNUMA memory
-	 * migration rate limiting data.
-	 */
+	/* Lock serializing the migrate rate limiting window */
 	spinlock_t numabalancing_migrate_lock;
 
 	/* Rate limiting time interval */
diff --git a/include/linux/posix_acl.h b/include/linux/posix_acl.h
index 7931efe71175..fb616942e4c7 100644
--- a/include/linux/posix_acl.h
+++ b/include/linux/posix_acl.h
@@ -94,78 +94,12 @@ extern int posix_acl_chmod(struct posix_acl **, gfp_t, umode_t);
 extern struct posix_acl *get_posix_acl(struct inode *, int);
 extern int set_posix_acl(struct inode *, int, struct posix_acl *);
 
-#ifdef CONFIG_FS_POSIX_ACL
-static inline struct posix_acl **acl_by_type(struct inode *inode, int type)
-{
-	switch (type) {
-	case ACL_TYPE_ACCESS:
-		return &inode->i_acl;
-	case ACL_TYPE_DEFAULT:
-		return &inode->i_default_acl;
-	default:
-		BUG();
-	}
-}
-
-static inline struct posix_acl *get_cached_acl(struct inode *inode, int type)
-{
-	struct posix_acl **p = acl_by_type(inode, type);
-	struct posix_acl *acl = ACCESS_ONCE(*p);
-	if (acl) {
-		spin_lock(&inode->i_lock);
-		acl = *p;
-		if (acl != ACL_NOT_CACHED)
-			acl = posix_acl_dup(acl);
-		spin_unlock(&inode->i_lock);
-	}
-	return acl;
-}
-
-static inline struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type)
-{
-	return rcu_dereference(*acl_by_type(inode, type));
-}
-
-static inline void set_cached_acl(struct inode *inode,
-				  int type,
-				  struct posix_acl *acl)
-{
-	struct posix_acl **p = acl_by_type(inode, type);
-	struct posix_acl *old;
-	spin_lock(&inode->i_lock);
-	old = *p;
-	rcu_assign_pointer(*p, posix_acl_dup(acl));
-	spin_unlock(&inode->i_lock);
-	if (old != ACL_NOT_CACHED)
-		posix_acl_release(old);
-}
-
-static inline void forget_cached_acl(struct inode *inode, int type)
-{
-	struct posix_acl **p = acl_by_type(inode, type);
-	struct posix_acl *old;
-	spin_lock(&inode->i_lock);
-	old = *p;
-	*p = ACL_NOT_CACHED;
-	spin_unlock(&inode->i_lock);
-	if (old != ACL_NOT_CACHED)
-		posix_acl_release(old);
-}
-
-static inline void forget_all_cached_acls(struct inode *inode)
-{
-	struct posix_acl *old_access, *old_default;
-	spin_lock(&inode->i_lock);
-	old_access = inode->i_acl;
-	old_default = inode->i_default_acl;
-	inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED;
-	spin_unlock(&inode->i_lock);
-	if (old_access != ACL_NOT_CACHED)
-		posix_acl_release(old_access);
-	if (old_default != ACL_NOT_CACHED)
-		posix_acl_release(old_default);
-}
-#endif
+struct posix_acl **acl_by_type(struct inode *inode, int type);
+struct posix_acl *get_cached_acl(struct inode *inode, int type);
+struct posix_acl *get_cached_acl_rcu(struct inode *inode, int type);
+void set_cached_acl(struct inode *inode, int type, struct posix_acl *acl);
+void forget_cached_acl(struct inode *inode, int type);
+void forget_all_cached_acls(struct inode *inode);
 
 static inline void cache_no_acl(struct inode *inode)
 {
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 6dacb93a6d94..1da693d51255 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -184,13 +184,13 @@ static inline void page_dup_rmap(struct page *page)
 int page_referenced(struct page *, int is_locked,
 			struct mem_cgroup *memcg, unsigned long *vm_flags);
 int page_referenced_one(struct page *, struct vm_area_struct *,
-	unsigned long address, unsigned int *mapcount, unsigned long *vm_flags);
+	unsigned long address, void *arg);
 
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
 int try_to_unmap(struct page *, enum ttu_flags flags);
 int try_to_unmap_one(struct page *, struct vm_area_struct *,
-			unsigned long address, enum ttu_flags flags);
+			unsigned long address, void *arg);
 
 /*
  * Called from mm/filemap_xip.c to unmap empty zero page
@@ -236,10 +236,27 @@ void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
 /*
- * Called by migrate.c to remove migration ptes, but might be used more later.
+ * rmap_walk_control: To control rmap traversing for specific needs
+ *
+ * arg: passed to rmap_one() and invalid_vma()
+ * rmap_one: executed on each vma where page is mapped
+ * done: for checking traversing termination condition
+ * file_nonlinear: for handling file nonlinear mapping
+ * anon_lock: for getting anon_lock by optimized way rather than default
+ * invalid_vma: for skipping uninterested vma
  */
-int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
-		struct vm_area_struct *, unsigned long, void *), void *arg);
+struct rmap_walk_control {
+	void *arg;
+	int (*rmap_one)(struct page *page, struct vm_area_struct *vma,
+					unsigned long addr, void *arg);
+	int (*done)(struct page *page);
+	int (*file_nonlinear)(struct page *, struct address_space *,
+					struct vm_area_struct *vma);
+	struct anon_vma *(*anon_lock)(struct page *page);
+	bool (*invalid_vma)(struct vm_area_struct *vma, void *arg);
+};
+
+int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
 
 #else	/* !CONFIG_MMU */
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index ffccdad050b5..485234d2fd42 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -549,6 +549,7 @@ struct signal_struct {
 	atomic_t		sigcnt;
 	atomic_t		live;
 	int			nr_threads;
+	struct list_head	thread_head;
 
 	wait_queue_head_t	wait_chldexit;	/* for wait4() */
 
@@ -1271,6 +1272,7 @@ struct task_struct {
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
+	struct list_head thread_node;
 
 	struct completion *vfork_done;		/* for vfork() */
 	int __user *set_child_tid;		/* CLONE_CHILD_SETTID */
@@ -2341,6 +2343,16 @@ extern bool current_is_single_threaded(void);
 #define while_each_thread(g, t) \
 	while ((t = next_thread(t)) != g)
 
+#define __for_each_thread(signal, t)	\
+	list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node)
+
+#define for_each_thread(p, t)		\
+	__for_each_thread((p)->signal, t)
+
+/* Careful: this is a double loop, 'break' won't work as expected. */
+#define for_each_process_thread(p, t)	\
+	for_each_process(p) for_each_thread(p, t)
+
 static inline int get_nr_threads(struct task_struct *tsk)
 {
 	return tsk->signal->nr_threads;
diff --git a/include/trace/events/compaction.h b/include/trace/events/compaction.h
index fde1b3e94c7d..06f544ef2f6f 100644
--- a/include/trace/events/compaction.h
+++ b/include/trace/events/compaction.h
@@ -67,6 +67,48 @@ TRACE_EVENT(mm_compaction_migratepages,
 		__entry->nr_failed)
 );
 
+TRACE_EVENT(mm_compaction_begin,
+	TP_PROTO(unsigned long zone_start, unsigned long migrate_start,
+		unsigned long free_start, unsigned long zone_end),
+
+	TP_ARGS(zone_start, migrate_start, free_start, zone_end),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, zone_start)
+		__field(unsigned long, migrate_start)
+		__field(unsigned long, free_start)
+		__field(unsigned long, zone_end)
+	),
+
+	TP_fast_assign(
+		__entry->zone_start = zone_start;
+		__entry->migrate_start = migrate_start;
+		__entry->free_start = free_start;
+		__entry->zone_end = zone_end;
+	),
+
+	TP_printk("zone_start=%lu migrate_start=%lu free_start=%lu zone_end=%lu",
+		__entry->zone_start,
+		__entry->migrate_start,
+		__entry->free_start,
+		__entry->zone_end)
+);
+
+TRACE_EVENT(mm_compaction_end,
+	TP_PROTO(int status),
+
+	TP_ARGS(status),
+
+	TP_STRUCT__entry(
+		__field(int, status)
+	),
+
+	TP_fast_assign(
+		__entry->status = status;
+	),
+
+	TP_printk("status=%d", __entry->status)
+);
 
 #endif /* _TRACE_COMPACTION_H */
 
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
index ec2a6ccfd7e5..3075ffbb9a83 100644
--- a/include/trace/events/migrate.h
+++ b/include/trace/events/migrate.h
@@ -45,6 +45,32 @@ TRACE_EVENT(mm_migrate_pages,
 		__print_symbolic(__entry->reason, MIGRATE_REASON))
 );
 
+TRACE_EVENT(mm_numa_migrate_ratelimit,
+
+	TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages),
+
+	TP_ARGS(p, dst_nid, nr_pages),
+
+	TP_STRUCT__entry(
+		__array(	char,		comm,	TASK_COMM_LEN)
+		__field(	pid_t,		pid)
+		__field(	int,		dst_nid)
+		__field(	unsigned long,	nr_pages)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+		__entry->pid		= p->pid;
+		__entry->dst_nid	= dst_nid;
+		__entry->nr_pages	= nr_pages;
+	),
+
+	TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu",
+		__entry->comm,
+		__entry->pid,
+		__entry->dst_nid,
+		__entry->nr_pages)
+);
 #endif /* _TRACE_MIGRATE_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 04c308413a5d..67e1bbf83695 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -443,6 +443,93 @@ TRACE_EVENT(sched_process_hang,
 );
 #endif /* CONFIG_DETECT_HUNG_TASK */
 
+DECLARE_EVENT_CLASS(sched_move_task_template,
+
+	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+	TP_ARGS(tsk, src_cpu, dst_cpu),
+
+	TP_STRUCT__entry(
+		__field( pid_t,	pid			)
+		__field( pid_t,	tgid			)
+		__field( pid_t,	ngid			)
+		__field( int,	src_cpu			)
+		__field( int,	src_nid			)
+		__field( int,	dst_cpu			)
+		__field( int,	dst_nid			)
+	),
+
+	TP_fast_assign(
+		__entry->pid		= task_pid_nr(tsk);
+		__entry->tgid		= task_tgid_nr(tsk);
+		__entry->ngid		= task_numa_group_id(tsk);
+		__entry->src_cpu	= src_cpu;
+		__entry->src_nid	= cpu_to_node(src_cpu);
+		__entry->dst_cpu	= dst_cpu;
+		__entry->dst_nid	= cpu_to_node(dst_cpu);
+	),
+
+	TP_printk("pid=%d tgid=%d ngid=%d src_cpu=%d src_nid=%d dst_cpu=%d dst_nid=%d",
+			__entry->pid, __entry->tgid, __entry->ngid,
+			__entry->src_cpu, __entry->src_nid,
+			__entry->dst_cpu, __entry->dst_nid)
+);
+
+/*
+ * Tracks migration of tasks from one runqueue to another. Can be used to
+ * detect if automatic NUMA balancing is bouncing between nodes
+ */
+DEFINE_EVENT(sched_move_task_template, sched_move_numa,
+	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+	TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+DEFINE_EVENT(sched_move_task_template, sched_stick_numa,
+	TP_PROTO(struct task_struct *tsk, int src_cpu, int dst_cpu),
+
+	TP_ARGS(tsk, src_cpu, dst_cpu)
+);
+
+TRACE_EVENT(sched_swap_numa,
+
+	TP_PROTO(struct task_struct *src_tsk, int src_cpu,
+		 struct task_struct *dst_tsk, int dst_cpu),
+
+	TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu),
+
+	TP_STRUCT__entry(
+		__field( pid_t,	src_pid			)
+		__field( pid_t,	src_tgid		)
+		__field( pid_t,	src_ngid		)
+		__field( int,	src_cpu			)
+		__field( int,	src_nid			)
+		__field( pid_t,	dst_pid			)
+		__field( pid_t,	dst_tgid		)
+		__field( pid_t,	dst_ngid		)
+		__field( int,	dst_cpu			)
+		__field( int,	dst_nid			)
+	),
+
+	TP_fast_assign(
+		__entry->src_pid	= task_pid_nr(src_tsk);
+		__entry->src_tgid	= task_tgid_nr(src_tsk);
+		__entry->src_ngid	= task_numa_group_id(src_tsk);
+		__entry->src_cpu	= src_cpu;
+		__entry->src_nid	= cpu_to_node(src_cpu);
+		__entry->dst_pid	= task_pid_nr(dst_tsk);
+		__entry->dst_tgid	= task_tgid_nr(dst_tsk);
+		__entry->dst_ngid	= task_numa_group_id(dst_tsk);
+		__entry->dst_cpu	= dst_cpu;
+		__entry->dst_nid	= cpu_to_node(dst_cpu);
+	),
+
+	TP_printk("src_pid=%d src_tgid=%d src_ngid=%d src_cpu=%d src_nid=%d dst_pid=%d dst_tgid=%d dst_ngid=%d dst_cpu=%d dst_nid=%d",
+			__entry->src_pid, __entry->src_tgid, __entry->src_ngid,
+			__entry->src_cpu, __entry->src_nid,
+			__entry->dst_pid, __entry->dst_tgid, __entry->dst_ngid,
+			__entry->dst_cpu, __entry->dst_nid)
+);
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */