Merge tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma

Pull Automatic NUMA Balancing bare-bones from Mel Gorman:
 "There are three implementations for NUMA balancing, this tree
  (balancenuma), numacore which has been developed in tip/master and
  autonuma which is in aa.git.

  In almost all respects balancenuma is the dumbest of the three because
  its main impact is on the VM side with no attempt to be smart about
  scheduling.  In the interest of getting the ball rolling, it would be
  desirable to see this much merged for 3.8 with the view to building
  scheduler smarts on top and adapting the VM where required for 3.9.

  The most recent set of comparisons available from different people are

    mel:    https://lkml.org/lkml/2012/12/9/108
    mingo:  https://lkml.org/lkml/2012/12/7/331
    tglx:   https://lkml.org/lkml/2012/12/10/437
    srikar: https://lkml.org/lkml/2012/12/10/397

  The results are a mixed bag.  In my own tests, balancenuma does
  reasonably well.  It's dumb as rocks and does not regress against
  mainline.  On the other hand, Ingo's tests shows that balancenuma is
  incapable of converging for this workloads driven by perf which is bad
  but is potentially explained by the lack of scheduler smarts.  Thomas'
  results show balancenuma improves on mainline but falls far short of
  numacore or autonuma.  Srikar's results indicate we all suffer on a
  large machine with imbalanced node sizes.

  My own testing showed that recent numacore results have improved
  dramatically, particularly in the last week but not universally.
  We've butted heads heavily on system CPU usage and high levels of
  migration even when it shows that overall performance is better.
  There are also cases where it regresses.  Of interest is that for
  specjbb in some configurations it will regress for lower numbers of
  warehouses and show gains for higher numbers which is not reported by
  the tool by default and sometimes missed in treports.  Recently I
  reported for numacore that the JVM was crashing with
  NullPointerExceptions but currently it's unclear what the source of
  this problem is.  Initially I thought it was in how numacore batch
  handles PTEs but I'm no longer think this is the case.  It's possible
  numacore is just able to trigger it due to higher rates of migration.

  These reports were quite late in the cycle so I/we would like to start
  with this tree as it contains much of the code we can agree on and has
  not changed significantly over the last 2-3 weeks."

* tag 'balancenuma-v11' of git://git.kernel.org/pub/scm/linux/kernel/git/mel/linux-balancenuma: (50 commits)
  mm/rmap, migration: Make rmap_walk_anon() and try_to_unmap_anon() more scalable
  mm/rmap: Convert the struct anon_vma::mutex to an rwsem
  mm: migrate: Account a transhuge page properly when rate limiting
  mm: numa: Account for failed allocations and isolations as migration failures
  mm: numa: Add THP migration for the NUMA working set scanning fault case build fix
  mm: numa: Add THP migration for the NUMA working set scanning fault case.
  mm: sched: numa: Delay PTE scanning until a task is scheduled on a new node
  mm: sched: numa: Control enabling and disabling of NUMA balancing if !SCHED_DEBUG
  mm: sched: numa: Control enabling and disabling of NUMA balancing
  mm: sched: Adapt the scanning rate if a NUMA hinting fault does not migrate
  mm: numa: Use a two-stage filter to restrict pages being migrated for unlikely task<->node relationships
  mm: numa: migrate: Set last_nid on newly allocated page
  mm: numa: split_huge_page: Transfer last_nid on tail page
  mm: numa: Introduce last_nid to the page frame
  sched: numa: Slowly increase the scanning period as NUMA faults are handled
  mm: numa: Rate limit setting of pte_numa if node is saturated
  mm: numa: Rate limit the amount of memory that is migrated between nodes
  mm: numa: Structures for Migrate On Fault per NUMA migration rate limiting
  mm: numa: Migrate pages handled during a pmd_numa hinting fault
  mm: numa: Migrate on reference policy
  ...

14 files changed, 396 insertions, 21 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 284e80831d2..701beab27aa 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -219,6 +219,10 @@ static inline int pmd_same(pmd_t pmd_a, pmd_t pmd_b)
 #define move_pte(pte, prot, old_addr, new_addr)	(pte)
 #endif
 
+#ifndef pte_accessible
+# define pte_accessible(pte)		((void)(pte),1)
+#endif
+
 #ifndef flush_tlb_fix_spurious_fault
 #define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
 #endif
@@ -580,6 +584,112 @@ static inline int pmd_trans_unstable(pmd_t *pmd)
 #endif
 }
 
+#ifdef CONFIG_NUMA_BALANCING
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+/*
+ * _PAGE_NUMA works identical to _PAGE_PROTNONE (it's actually the
+ * same bit too). It's set only when _PAGE_PRESET is not set and it's
+ * never set if _PAGE_PRESENT is set.
+ *
+ * pte/pmd_present() returns true if pte/pmd_numa returns true. Page
+ * fault triggers on those regions if pte/pmd_numa returns true
+ * (because _PAGE_PRESENT is not set).
+ */
+#ifndef pte_numa
+static inline int pte_numa(pte_t pte)
+{
+	return (pte_flags(pte) &
+		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+#ifndef pmd_numa
+static inline int pmd_numa(pmd_t pmd)
+{
+	return (pmd_flags(pmd) &
+		(_PAGE_NUMA|_PAGE_PRESENT)) == _PAGE_NUMA;
+}
+#endif
+
+/*
+ * pte/pmd_mknuma sets the _PAGE_ACCESSED bitflag automatically
+ * because they're called by the NUMA hinting minor page fault. If we
+ * wouldn't set the _PAGE_ACCESSED bitflag here, the TLB miss handler
+ * would be forced to set it later while filling the TLB after we
+ * return to userland. That would trigger a second write to memory
+ * that we optimize away by setting _PAGE_ACCESSED here.
+ */
+#ifndef pte_mknonnuma
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+	pte = pte_clear_flags(pte, _PAGE_NUMA);
+	return pte_set_flags(pte, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pmd_mknonnuma
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+	pmd = pmd_clear_flags(pmd, _PAGE_NUMA);
+	return pmd_set_flags(pmd, _PAGE_PRESENT|_PAGE_ACCESSED);
+}
+#endif
+
+#ifndef pte_mknuma
+static inline pte_t pte_mknuma(pte_t pte)
+{
+	pte = pte_set_flags(pte, _PAGE_NUMA);
+	return pte_clear_flags(pte, _PAGE_PRESENT);
+}
+#endif
+
+#ifndef pmd_mknuma
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+	pmd = pmd_set_flags(pmd, _PAGE_NUMA);
+	return pmd_clear_flags(pmd, _PAGE_PRESENT);
+}
+#endif
+#else
+extern int pte_numa(pte_t pte);
+extern int pmd_numa(pmd_t pmd);
+extern pte_t pte_mknonnuma(pte_t pte);
+extern pmd_t pmd_mknonnuma(pmd_t pmd);
+extern pte_t pte_mknuma(pte_t pte);
+extern pmd_t pmd_mknuma(pmd_t pmd);
+#endif /* CONFIG_ARCH_USES_NUMA_PROT_NONE */
+#else
+static inline int pmd_numa(pmd_t pmd)
+{
+	return 0;
+}
+
+static inline int pte_numa(pte_t pte)
+{
+	return 0;
+}
+
+static inline pte_t pte_mknonnuma(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mknonnuma(pmd_t pmd)
+{
+	return pmd;
+}
+
+static inline pte_t pte_mknuma(pte_t pte)
+{
+	return pte;
+}
+
+static inline pmd_t pmd_mknuma(pmd_t pmd)
+{
+	return pmd;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
 #endif /* CONFIG_MMU */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 092dc5305a3..1d76f8ca90f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -31,7 +31,8 @@ extern int move_huge_pmd(struct vm_area_struct *vma,
 			 unsigned long new_addr, unsigned long old_end,
 			 pmd_t *old_pmd, pmd_t *new_pmd);
 extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-			unsigned long addr, pgprot_t newprot);
+			unsigned long addr, pgprot_t newprot,
+			int prot_numa);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_FLAG,
@@ -111,7 +112,7 @@ extern void __split_huge_page_pmd(struct vm_area_struct *vma,
 #define wait_split_huge_page(__anon_vma, __pmd)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		anon_vma_lock(__anon_vma);				\
+		anon_vma_lock_write(__anon_vma);			\
 		anon_vma_unlock(__anon_vma);				\
 		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
 		       pmd_trans_huge(*____pmd));			\
@@ -171,6 +172,10 @@ static inline struct page *compound_trans_head(struct page *page)
 	}
 	return page;
 }
+
+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);
+
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
 #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
@@ -209,6 +214,13 @@ static inline int pmd_trans_huge_lock(pmd_t *pmd,
 {
 	return 0;
 }
+
+static inline int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
+					unsigned long addr, pmd_t pmd, pmd_t *pmdp)
+{
+	return 0;
+}
+
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 3e7fa1acf09..0c80d3f57a5 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -87,7 +87,7 @@ struct page *follow_huge_pud(struct mm_struct *mm, unsigned long address,
 				pud_t *pud, int write);
 int pmd_huge(pmd_t pmd);
 int pud_huge(pud_t pmd);
-void hugetlb_change_protection(struct vm_area_struct *vma,
+unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot);
 
 #else /* !CONFIG_HUGETLB_PAGE */
@@ -132,7 +132,11 @@ static inline void copy_huge_page(struct page *dst, struct page *src)
 {
 }
 
-#define hugetlb_change_protection(vma, address, end, newprot)
+static inline unsigned long hugetlb_change_protection(struct vm_area_struct *vma,
+		unsigned long address, unsigned long end, pgprot_t newprot)
+{
+	return 0;
+}
 
 static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index dbd212723b7..9adc270de7e 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -188,6 +188,8 @@ static inline int vma_migratable(struct vm_area_struct *vma)
 	return 1;
 }
 
+extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
+
 #else
 
 struct mempolicy {};
@@ -307,5 +309,11 @@ static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
 	return 0;
 }
 
+static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
+				 unsigned long address)
+{
+	return -1; /* no node preference */
+}
+
 #endif /* CONFIG_NUMA */
 #endif
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 0b5865c61ef..1e9f627967a 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -23,6 +23,15 @@ typedef struct page *new_page_t(struct page *, unsigned long private, int **);
 #define MIGRATEPAGE_BALLOON_SUCCESS	1 /* special ret code for balloon page
 					   * sucessful migration case.
 					   */
+enum migrate_reason {
+	MR_COMPACTION,
+	MR_MEMORY_FAILURE,
+	MR_MEMORY_HOTPLUG,
+	MR_SYSCALL,		/* also applies to cpusets */
+	MR_MEMPOLICY_MBIND,
+	MR_NUMA_MISPLACED,
+	MR_CMA
+};
 
 #ifdef CONFIG_MIGRATION
 
@@ -32,7 +41,7 @@ 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, bool offlining,
-			enum migrate_mode mode);
+			enum migrate_mode mode, int reason);
 extern int migrate_huge_page(struct page *, new_page_t x,
 			unsigned long private, bool offlining,
 			enum migrate_mode mode);
@@ -54,7 +63,7 @@ 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, bool offlining,
-		enum migrate_mode mode) { return -ENOSYS; }
+		enum migrate_mode mode, int reason) { return -ENOSYS; }
 static inline int migrate_huge_page(struct page *page, new_page_t x,
 		unsigned long private, bool offlining,
 		enum migrate_mode mode) { return -ENOSYS; }
@@ -83,4 +92,37 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #define fail_migrate_page NULL
 
 #endif /* CONFIG_MIGRATION */
+
+#ifdef CONFIG_NUMA_BALANCING
+extern int migrate_misplaced_page(struct page *page, int node);
+extern int migrate_misplaced_page(struct page *page, int node);
+extern bool migrate_ratelimited(int node);
+#else
+static inline int migrate_misplaced_page(struct page *page, int node)
+{
+	return -EAGAIN; /* can't migrate now */
+}
+static inline bool migrate_ratelimited(int node)
+{
+	return false;
+}
+#endif /* CONFIG_NUMA_BALANCING */
+
+#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
+extern int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, pmd_t entry,
+			unsigned long address,
+			struct page *page, int node);
+#else
+static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm,
+			struct vm_area_struct *vma,
+			pmd_t *pmd, pmd_t entry,
+			unsigned long address,
+			struct page *page, int node)
+{
+	return -EAGAIN;
+}
+#endif /* CONFIG_NUMA_BALANCING && CONFIG_TRANSPARENT_HUGEPAGE*/
+
 #endif /* _LINUX_MIGRATE_H */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4af4f0b1be4..7f4f906190b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -693,6 +693,36 @@ static inline int page_to_nid(const struct page *page)
 }
 #endif
 
+#ifdef CONFIG_NUMA_BALANCING
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+	return xchg(&page->_last_nid, nid);
+}
+
+static inline int page_last_nid(struct page *page)
+{
+	return page->_last_nid;
+}
+static inline void reset_page_last_nid(struct page *page)
+{
+	page->_last_nid = -1;
+}
+#else
+static inline int page_xchg_last_nid(struct page *page, int nid)
+{
+	return page_to_nid(page);
+}
+
+static inline int page_last_nid(struct page *page)
+{
+	return page_to_nid(page);
+}
+
+static inline void reset_page_last_nid(struct page *page)
+{
+}
+#endif
+
 static inline struct zone *page_zone(const struct page *page)
 {
 	return &NODE_DATA(page_to_nid(page))->node_zones[page_zonenum(page)];
@@ -1078,6 +1108,9 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 extern unsigned long do_mremap(unsigned long addr,
 			       unsigned long old_len, unsigned long new_len,
 			       unsigned long flags, unsigned long new_addr);
+extern unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
+			      unsigned long end, pgprot_t newprot,
+			      int dirty_accountable, int prot_numa);
 extern int mprotect_fixup(struct vm_area_struct *vma,
 			  struct vm_area_struct **pprev, unsigned long start,
 			  unsigned long end, unsigned long newflags);
@@ -1579,6 +1612,11 @@ static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
 }
 #endif
 
+#ifdef CONFIG_ARCH_USES_NUMA_PROT_NONE
+unsigned long change_prot_numa(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end);
+#endif
+
 struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
@@ -1600,6 +1638,7 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_MLOCK	0x40	/* mark page as mlocked */
 #define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
 #define FOLL_HWPOISON	0x100	/* check page is hwpoisoned */
+#define FOLL_NUMA	0x200	/* force NUMA hinting page fault */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7ade2731b5d..7d9ebb7cc98 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -175,6 +175,10 @@ struct page {
 	 */
 	void *shadow;
 #endif
+
+#ifdef CONFIG_NUMA_BALANCING
+	int _last_nid;
+#endif
 }
 /*
  * The struct page can be forced to be double word aligned so that atomic ops
@@ -411,9 +415,36 @@ struct mm_struct {
 #ifdef CONFIG_CPUMASK_OFFSTACK
 	struct cpumask cpumask_allocation;
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	/*
+	 * numa_next_scan is the next time when the PTEs will me marked
+	 * pte_numa to gather statistics and migrate pages to new nodes
+	 * if necessary
+	 */
+	unsigned long numa_next_scan;
+
+	/* numa_next_reset is when the PTE scanner period will be reset */
+	unsigned long numa_next_reset;
+
+	/* Restart point for scanning and setting pte_numa */
+	unsigned long numa_scan_offset;
+
+	/* numa_scan_seq prevents two threads setting pte_numa */
+	int numa_scan_seq;
+
+	/*
+	 * The first node a task was scheduled on. If a task runs on
+	 * a different node than Make PTE Scan Go Now.
+	 */
+	int first_nid;
+#endif
 	struct uprobes_state uprobes_state;
 };
 
+/* first nid will either be a valid NID or one of these values */
+#define NUMA_PTE_SCAN_INIT	-1
+#define NUMA_PTE_SCAN_ACTIVE	-2
+
 static inline void mm_init_cpumask(struct mm_struct *mm)
 {
 #ifdef CONFIG_CPUMASK_OFFSTACK
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index cd55dad56aa..4bec5be82ca 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -735,6 +735,19 @@ typedef struct pglist_data {
 	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
 	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.
+	 */
+	spinlock_t numabalancing_migrate_lock;
+
+	/* Rate limiting time interval */
+	unsigned long numabalancing_migrate_next_window;
+
+	/* Number of pages migrated during the rate limiting time interval */
+	unsigned long numabalancing_migrate_nr_pages;
+#endif
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bfe1f478064..c20635c527a 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -7,7 +7,7 @@
 #include <linux/list.h>
 #include <linux/slab.h>
 #include <linux/mm.h>
-#include <linux/mutex.h>
+#include <linux/rwsem.h>
 #include <linux/memcontrol.h>
 
 /*
@@ -25,8 +25,8 @@
  * pointing to this anon_vma once its vma list is empty.
  */
 struct anon_vma {
-	struct anon_vma *root;	/* Root of this anon_vma tree */
-	struct mutex mutex;	/* Serialize access to vma list */
+	struct anon_vma *root;		/* Root of this anon_vma tree */
+	struct rw_semaphore rwsem;	/* W: modification, R: walking the list */
 	/*
 	 * The refcount is taken on an anon_vma when there is no
 	 * guarantee that the vma of page tables will exist for
@@ -64,7 +64,7 @@ struct anon_vma_chain {
 	struct vm_area_struct *vma;
 	struct anon_vma *anon_vma;
 	struct list_head same_vma;   /* locked by mmap_sem & page_table_lock */
-	struct rb_node rb;			/* locked by anon_vma->mutex */
+	struct rb_node rb;			/* locked by anon_vma->rwsem */
 	unsigned long rb_subtree_last;
 #ifdef CONFIG_DEBUG_VM_RB
 	unsigned long cached_vma_start, cached_vma_last;
@@ -108,26 +108,37 @@ static inline void vma_lock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		mutex_lock(&anon_vma->root->mutex);
+		down_write(&anon_vma->root->rwsem);
 }
 
 static inline void vma_unlock_anon_vma(struct vm_area_struct *vma)
 {
 	struct anon_vma *anon_vma = vma->anon_vma;
 	if (anon_vma)
-		mutex_unlock(&anon_vma->root->mutex);
+		up_write(&anon_vma->root->rwsem);
 }
 
-static inline void anon_vma_lock(struct anon_vma *anon_vma)
+static inline void anon_vma_lock_write(struct anon_vma *anon_vma)
 {
-	mutex_lock(&anon_vma->root->mutex);
+	down_write(&anon_vma->root->rwsem);
 }
 
 static inline void anon_vma_unlock(struct anon_vma *anon_vma)
 {
-	mutex_unlock(&anon_vma->root->mutex);
+	up_write(&anon_vma->root->rwsem);
 }
 
+static inline void anon_vma_lock_read(struct anon_vma *anon_vma)
+{
+	down_read(&anon_vma->root->rwsem);
+}
+
+static inline void anon_vma_unlock_read(struct anon_vma *anon_vma)
+{
+	up_read(&anon_vma->root->rwsem);
+}
+
+
 /*
  * anon_vma helper functions.
  */
@@ -220,8 +231,8 @@ int try_to_munlock(struct page *);
 /*
  * Called by memory-failure.c to kill processes.
  */
-struct anon_vma *page_lock_anon_vma(struct page *page);
-void page_unlock_anon_vma(struct anon_vma *anon_vma);
+struct anon_vma *page_lock_anon_vma_read(struct page *page);
+void page_unlock_anon_vma_read(struct anon_vma *anon_vma);
 int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
 
 /*
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2c2f3072bee..b089c92c609 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1527,6 +1527,14 @@ struct task_struct {
 	short il_next;
 	short pref_node_fork;
 #endif
+#ifdef CONFIG_NUMA_BALANCING
+	int numa_scan_seq;
+	int numa_migrate_seq;
+	unsigned int numa_scan_period;
+	u64 node_stamp;			/* migration stamp  */
+	struct callback_head numa_work;
+#endif /* CONFIG_NUMA_BALANCING */
+
 	struct rcu_head rcu;
 
 	/*
@@ -1601,6 +1609,18 @@ struct task_struct {
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
 #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed)
 
+#ifdef CONFIG_NUMA_BALANCING
+extern void task_numa_fault(int node, int pages, bool migrated);
+extern void set_numabalancing_state(bool enabled);
+#else
+static inline void task_numa_fault(int node, int pages, bool migrated)
+{
+}
+static inline void set_numabalancing_state(bool enabled)
+{
+}
+#endif
+
 /*
  * Priority of a process goes from 0..MAX_PRIO-1, valid RT
  * priority is 0..MAX_RT_PRIO-1, and SCHED_NORMAL/SCHED_BATCH
@@ -2030,6 +2050,13 @@ enum sched_tunable_scaling {
 };
 extern enum sched_tunable_scaling sysctl_sched_tunable_scaling;
 
+extern unsigned int sysctl_numa_balancing_scan_delay;
+extern unsigned int sysctl_numa_balancing_scan_period_min;
+extern unsigned int sysctl_numa_balancing_scan_period_max;
+extern unsigned int sysctl_numa_balancing_scan_period_reset;
+extern unsigned int sysctl_numa_balancing_scan_size;
+extern unsigned int sysctl_numa_balancing_settle_count;
+
 #ifdef CONFIG_SCHED_DEBUG
 extern unsigned int sysctl_sched_migration_cost;
 extern unsigned int sysctl_sched_nr_migrate;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index fe786f07d2b..fce0a2799d4 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -38,8 +38,18 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		KSWAPD_LOW_WMARK_HIT_QUICKLY, KSWAPD_HIGH_WMARK_HIT_QUICKLY,
 		KSWAPD_SKIP_CONGESTION_WAIT,
 		PAGEOUTRUN, ALLOCSTALL, PGROTATED,
+#ifdef CONFIG_NUMA_BALANCING
+		NUMA_PTE_UPDATES,
+		NUMA_HINT_FAULTS,
+		NUMA_HINT_FAULTS_LOCAL,
+		NUMA_PAGE_MIGRATE,
+#endif
+#ifdef CONFIG_MIGRATION
+		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
+#endif
 #ifdef CONFIG_COMPACTION
-		COMPACTBLOCKS, COMPACTPAGES, COMPACTPAGEFAILED,
+		COMPACTMIGRATE_SCANNED, COMPACTFREE_SCANNED,
+		COMPACTISOLATED,
 		COMPACTSTALL, COMPACTFAIL, COMPACTSUCCESS,
 #endif
 #ifdef CONFIG_HUGETLB_PAGE
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index 92a86b2cce3..a13291f7da8 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -80,6 +80,14 @@ static inline void vm_events_fold_cpu(int cpu)
 
 #endif /* CONFIG_VM_EVENT_COUNTERS */
 
+#ifdef CONFIG_NUMA_BALANCING
+#define count_vm_numa_event(x)     count_vm_event(x)
+#define count_vm_numa_events(x, y) count_vm_events(x, y)
+#else
+#define count_vm_numa_event(x) do {} while (0)
+#define count_vm_numa_events(x, y) do {} while (0)
+#endif /* CONFIG_NUMA_BALANCING */
+
 #define __count_zone_vm_events(item, zone, delta) \
 		__count_vm_events(item##_NORMAL - ZONE_NORMAL + \
 		zone_idx(zone), delta)
diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h
new file mode 100644
index 00000000000..ec2a6ccfd7e
--- /dev/null
+++ b/include/trace/events/migrate.h
@@ -0,0 +1,51 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM migrate
+
+#if !defined(_TRACE_MIGRATE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MIGRATE_H
+
+#define MIGRATE_MODE						\
+	{MIGRATE_ASYNC,		"MIGRATE_ASYNC"},		\
+	{MIGRATE_SYNC_LIGHT,	"MIGRATE_SYNC_LIGHT"},		\
+	{MIGRATE_SYNC,		"MIGRATE_SYNC"}		
+
+#define MIGRATE_REASON						\
+	{MR_COMPACTION,		"compaction"},			\
+	{MR_MEMORY_FAILURE,	"memory_failure"},		\
+	{MR_MEMORY_HOTPLUG,	"memory_hotplug"},		\
+	{MR_SYSCALL,		"syscall_or_cpuset"},		\
+	{MR_MEMPOLICY_MBIND,	"mempolicy_mbind"},		\
+	{MR_CMA,		"cma"}
+
+TRACE_EVENT(mm_migrate_pages,
+
+	TP_PROTO(unsigned long succeeded, unsigned long failed,
+		 enum migrate_mode mode, int reason),
+
+	TP_ARGS(succeeded, failed, mode, reason),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,		succeeded)
+		__field(	unsigned long,		failed)
+		__field(	enum migrate_mode,	mode)
+		__field(	int,			reason)
+	),
+
+	TP_fast_assign(
+		__entry->succeeded	= succeeded;
+		__entry->failed		= failed;
+		__entry->mode		= mode;
+		__entry->reason		= reason;
+	),
+
+	TP_printk("nr_succeeded=%lu nr_failed=%lu mode=%s reason=%s",
+		__entry->succeeded,
+		__entry->failed,
+		__print_symbolic(__entry->mode, MIGRATE_MODE),
+		__print_symbolic(__entry->reason, MIGRATE_REASON))
+);
+
+#endif /* _TRACE_MIGRATE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 23e62e0537e..0d11c3dcd3a 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -20,6 +20,7 @@ enum {
 	MPOL_PREFERRED,
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
+	MPOL_LOCAL,
 	MPOL_MAX,	/* always last member of enum */
 };
 
@@ -47,9 +48,15 @@ enum mpol_rebind_step {
 
 /* Flags for mbind */
 #define MPOL_MF_STRICT	(1<<0)	/* Verify existing pages in the mapping */
-#define MPOL_MF_MOVE	(1<<1)	/* Move pages owned by this process to conform to mapping */
-#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to mapping */
-#define MPOL_MF_INTERNAL (1<<3)	/* Internal flags start here */
+#define MPOL_MF_MOVE	 (1<<1)	/* Move pages owned by this process to conform
+				   to policy */
+#define MPOL_MF_MOVE_ALL (1<<2)	/* Move every page to conform to policy */
+#define MPOL_MF_LAZY	 (1<<3)	/* Modifies '_MOVE:  lazy migrate on fault */
+#define MPOL_MF_INTERNAL (1<<4)	/* Internal flags start here */
+
+#define MPOL_MF_VALID	(MPOL_MF_STRICT   | 	\
+			 MPOL_MF_MOVE     | 	\
+			 MPOL_MF_MOVE_ALL)
 
 /*
  * Internal flags that share the struct mempolicy flags word with
@@ -59,6 +66,8 @@ enum mpol_rebind_step {
 #define MPOL_F_SHARED  (1 << 0)	/* identify shared policies */
 #define MPOL_F_LOCAL   (1 << 1)	/* preferred local allocation */
 #define MPOL_F_REBINDING (1 << 2)	/* identify policies in rebinding */
+#define MPOL_F_MOF	(1 << 3) /* this policy wants migrate on fault */
+#define MPOL_F_MORON	(1 << 4) /* Migrate On pte_numa Reference On Node */
 
 
 #endif /* _UAPI_LINUX_MEMPOLICY_H */