Merge branch 'akpm' (Andrew's patch-bomb)

Merge patches from Andrew Morton:
 "A few misc things and very nearly all of the MM tree.  A tremendous
  amount of stuff (again), including a significant rbtree library
  rework."

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (160 commits)
  sparc64: Support transparent huge pages.
  mm: thp: Use more portable PMD clearing sequenece in zap_huge_pmd().
  mm: Add and use update_mmu_cache_pmd() in transparent huge page code.
  sparc64: Document PGD and PMD layout.
  sparc64: Eliminate PTE table memory wastage.
  sparc64: Halve the size of PTE tables
  sparc64: Only support 4MB huge pages and 8KB base pages.
  memory-hotplug: suppress "Trying to free nonexistent resource <XXXXXXXXXXXXXXXX-YYYYYYYYYYYYYYYY>" warning
  mm: memcg: clean up mm_match_cgroup() signature
  mm: document PageHuge somewhat
  mm: use %pK for /proc/vmallocinfo
  mm, thp: fix mlock statistics
  mm, thp: fix mapped pages avoiding unevictable list on mlock
  memory-hotplug: update memory block's state and notify userspace
  memory-hotplug: preparation to notify memory block's state at memory hot remove
  mm: avoid section mismatch warning for memblock_type_name
  make GFP_NOTRACK definition unconditional
  cma: decrease cc.nr_migratepages after reclaiming pagelist
  CMA: migrate mlocked pages
  kpageflags: fix wrong KPF_THP on non-huge compound pages
  ...

30 files changed, 730 insertions, 429 deletions

diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index ff4947b7a97..b36ce40bd1c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -87,7 +87,7 @@ static inline pmd_t pmdp_get_and_clear(struct mm_struct *mm,
 				       pmd_t *pmdp)
 {
 	pmd_t pmd = *pmdp;
-	pmd_clear(mm, address, pmdp);
+	pmd_clear(pmdp);
 	return pmd;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -162,6 +162,19 @@ extern void pmdp_splitting_flush(struct vm_area_struct *vma,
 				 unsigned long address, pmd_t *pmdp);
 #endif
 
+#ifndef __HAVE_ARCH_PGTABLE_DEPOSIT
+extern void pgtable_trans_huge_deposit(struct mm_struct *mm, pgtable_t pgtable);
+#endif
+
+#ifndef __HAVE_ARCH_PGTABLE_WITHDRAW
+extern pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm);
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_INVALIDATE
+extern void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
+			    pmd_t *pmdp);
+#endif
+
 #ifndef __HAVE_ARCH_PTE_SAME
 static inline int pte_same(pte_t pte_a, pte_t pte_b)
 {
@@ -381,48 +394,59 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 
 #ifndef __HAVE_PFNMAP_TRACKING
 /*
- * Interface that can be used by architecture code to keep track of
- * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
- *
- * track_pfn_vma_new is called when a _new_ pfn mapping is being established
- * for physical range indicated by pfn and size.
+ * Interfaces that can be used by architecture code to keep track of
+ * memory type of pfn mappings specified by the remap_pfn_range,
+ * vm_insert_pfn.
+ */
+
+/*
+ * track_pfn_remap is called when a _new_ pfn mapping is being established
+ * by remap_pfn_range() for physical range indicated by pfn and size.
  */
-static inline int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
-					unsigned long pfn, unsigned long size)
+static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
+				  unsigned long pfn, unsigned long addr,
+				  unsigned long size)
 {
 	return 0;
 }
 
 /*
- * Interface that can be used by architecture code to keep track of
- * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
- *
- * track_pfn_vma_copy is called when vma that is covering the pfnmap gets
+ * track_pfn_insert is called when a _new_ single pfn is established
+ * by vm_insert_pfn().
+ */
+static inline int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
+				   unsigned long pfn)
+{
+	return 0;
+}
+
+/*
+ * track_pfn_copy is called when vma that is covering the pfnmap gets
  * copied through copy_page_range().
  */
-static inline int track_pfn_vma_copy(struct vm_area_struct *vma)
+static inline int track_pfn_copy(struct vm_area_struct *vma)
 {
 	return 0;
 }
 
 /*
- * Interface that can be used by architecture code to keep track of
- * memory type of pfn mappings (remap_pfn_range, vm_insert_pfn)
- *
  * untrack_pfn_vma is called while unmapping a pfnmap for a region.
  * untrack can be called for a specific region indicated by pfn and size or
- * can be for the entire vma (in which case size can be zero).
+ * can be for the entire vma (in which case pfn, size are zero).
  */
-static inline void untrack_pfn_vma(struct vm_area_struct *vma,
-					unsigned long pfn, unsigned long size)
+static inline void untrack_pfn(struct vm_area_struct *vma,
+			       unsigned long pfn, unsigned long size)
 {
 }
 #else
-extern int track_pfn_vma_new(struct vm_area_struct *vma, pgprot_t *prot,
-				unsigned long pfn, unsigned long size);
-extern int track_pfn_vma_copy(struct vm_area_struct *vma);
-extern void untrack_pfn_vma(struct vm_area_struct *vma, unsigned long pfn,
-				unsigned long size);
+extern int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
+			   unsigned long pfn, unsigned long addr,
+			   unsigned long size);
+extern int track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
+			    unsigned long pfn);
+extern int track_pfn_copy(struct vm_area_struct *vma);
+extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
+			unsigned long size);
 #endif
 
 #ifdef CONFIG_MMU
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index 70cfcb2d63c..5b08a8540ec 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -86,6 +86,31 @@ static inline int atomic_dec_unless_positive(atomic_t *p)
 }
 #endif
 
+/*
+ * atomic_dec_if_positive - decrement by 1 if old value positive
+ * @v: pointer of type atomic_t
+ *
+ * The function returns the old value of *v minus 1, even if
+ * the atomic variable, v, was not decremented.
+ */
+#ifndef atomic_dec_if_positive
+static inline int atomic_dec_if_positive(atomic_t *v)
+{
+	int c, old, dec;
+	c = atomic_read(v);
+	for (;;) {
+		dec = c - 1;
+		if (unlikely(dec < 0))
+			break;
+		old = atomic_cmpxchg((v), c, dec);
+		if (likely(old == c))
+			break;
+		c = old;
+	}
+	return dec;
+}
+#endif
+
 #ifndef CONFIG_ARCH_HAS_ATOMIC_OR
 static inline void atomic_or(int i, atomic_t *v)
 {
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index ef658147e4e..6ecb6dc2f30 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -22,8 +22,9 @@ extern int sysctl_extfrag_handler(struct ctl_table *table, int write,
 extern int fragmentation_index(struct zone *zone, unsigned int order);
 extern unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *mask,
-			bool sync, bool *contended);
+			bool sync, bool *contended, struct page **page);
 extern int compact_pgdat(pg_data_t *pgdat, int order);
+extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern unsigned long compaction_suitable(struct zone *zone, int order);
 
 /* Do not skip compaction more than 64 times */
@@ -61,10 +62,20 @@ static inline bool compaction_deferred(struct zone *zone, int order)
 	return zone->compact_considered < defer_limit;
 }
 
+/* Returns true if restarting compaction after many failures */
+static inline bool compaction_restarting(struct zone *zone, int order)
+{
+	if (order < zone->compact_order_failed)
+		return false;
+
+	return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT &&
+		zone->compact_considered >= 1UL << zone->compact_defer_shift;
+}
+
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
 			int order, gfp_t gfp_mask, nodemask_t *nodemask,
-			bool sync, bool *contended)
+			bool sync, bool *contended, struct page **page)
 {
 	return COMPACT_CONTINUE;
 }
@@ -74,6 +85,10 @@ static inline int compact_pgdat(pg_data_t *pgdat, int order)
 	return COMPACT_CONTINUE;
 }
 
+static inline void reset_isolation_suitable(pg_data_t *pgdat)
+{
+}
+
 static inline unsigned long compaction_suitable(struct zone *zone, int order)
 {
 	return COMPACT_SKIPPED;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index ca6d8c806f4..c617ed024df 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -401,7 +401,7 @@ struct inodes_stat_t {
 #include <linux/cache.h>
 #include <linux/list.h>
 #include <linux/radix-tree.h>
-#include <linux/prio_tree.h>
+#include <linux/rbtree.h>
 #include <linux/init.h>
 #include <linux/pid.h>
 #include <linux/bug.h>
@@ -669,7 +669,7 @@ struct address_space {
 	struct radix_tree_root	page_tree;	/* radix tree of all pages */
 	spinlock_t		tree_lock;	/* and lock protecting it */
 	unsigned int		i_mmap_writable;/* count VM_SHARED mappings */
-	struct prio_tree_root	i_mmap;		/* tree of private and shared mappings */
+	struct rb_root		i_mmap;		/* tree of private and shared mappings */
 	struct list_head	i_mmap_nonlinear;/*list VM_NONLINEAR mappings */
 	struct mutex		i_mmap_mutex;	/* protect tree, count, list */
 	/* Protected by tree_lock together with the radix tree */
@@ -741,7 +741,7 @@ int mapping_tagged(struct address_space *mapping, int tag);
  */
 static inline int mapping_mapped(struct address_space *mapping)
 {
-	return	!prio_tree_empty(&mapping->i_mmap) ||
+	return	!RB_EMPTY_ROOT(&mapping->i_mmap) ||
 		!list_empty(&mapping->i_mmap_nonlinear);
 }
 
@@ -2552,6 +2552,8 @@ extern int sb_min_blocksize(struct super_block *, int);
 
 extern int generic_file_mmap(struct file *, struct vm_area_struct *);
 extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
+extern int generic_file_remap_pages(struct vm_area_struct *, unsigned long addr,
+		unsigned long size, pgoff_t pgoff);
 extern int file_read_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size);
 int generic_write_checks(struct file *file, loff_t *pos, size_t *count, int isblk);
 extern ssize_t generic_file_aio_read(struct kiocb *, const struct iovec *, unsigned long, loff_t);
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 4883f393f50..02c1c9710be 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -30,12 +30,7 @@ struct vm_area_struct;
 #define ___GFP_HARDWALL		0x20000u
 #define ___GFP_THISNODE		0x40000u
 #define ___GFP_RECLAIMABLE	0x80000u
-#ifdef CONFIG_KMEMCHECK
 #define ___GFP_NOTRACK		0x200000u
-#else
-#define ___GFP_NOTRACK		0
-#endif
-#define ___GFP_NO_KSWAPD	0x400000u
 #define ___GFP_OTHER_NODE	0x800000u
 #define ___GFP_WRITE		0x1000000u
 
@@ -90,7 +85,6 @@ struct vm_area_struct;
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) /* Page is reclaimable */
 #define __GFP_NOTRACK	((__force gfp_t)___GFP_NOTRACK)  /* Don't track with kmemcheck */
 
-#define __GFP_NO_KSWAPD	((__force gfp_t)___GFP_NO_KSWAPD)
 #define __GFP_OTHER_NODE ((__force gfp_t)___GFP_OTHER_NODE) /* On behalf of other node */
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)	/* Allocator intends to dirty page */
 
@@ -120,8 +114,7 @@ struct vm_area_struct;
 				 __GFP_MOVABLE)
 #define GFP_IOFS	(__GFP_IO | __GFP_FS)
 #define GFP_TRANSHUGE	(GFP_HIGHUSER_MOVABLE | __GFP_COMP | \
-			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN | \
-			 __GFP_NO_KSWAPD)
+			 __GFP_NOMEMALLOC | __GFP_NORETRY | __GFP_NOWARN)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 4c59b113118..b31cb7da034 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -11,8 +11,7 @@ extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 extern int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			       unsigned long address, pmd_t *pmd,
 			       pmd_t orig_pmd);
-extern pgtable_t get_pmd_huge_pte(struct mm_struct *mm);
-extern struct page *follow_trans_huge_pmd(struct mm_struct *mm,
+extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 					  unsigned long addr,
 					  pmd_t *pmd,
 					  unsigned int flags);
diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h
new file mode 100644
index 00000000000..724556aa3c9
--- /dev/null
+++ b/include/linux/interval_tree.h
@@ -0,0 +1,27 @@
+#ifndef _LINUX_INTERVAL_TREE_H
+#define _LINUX_INTERVAL_TREE_H
+
+#include <linux/rbtree.h>
+
+struct interval_tree_node {
+	struct rb_node rb;
+	unsigned long start;	/* Start of interval */
+	unsigned long last;	/* Last location _in_ interval */
+	unsigned long __subtree_last;
+};
+
+extern void
+interval_tree_insert(struct interval_tree_node *node, struct rb_root *root);
+
+extern void
+interval_tree_remove(struct interval_tree_node *node, struct rb_root *root);
+
+extern struct interval_tree_node *
+interval_tree_iter_first(struct rb_root *root,
+			 unsigned long start, unsigned long last);
+
+extern struct interval_tree_node *
+interval_tree_iter_next(struct interval_tree_node *node,
+			unsigned long start, unsigned long last);
+
+#endif	/* _LINUX_INTERVAL_TREE_H */
diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h
new file mode 100644
index 00000000000..58370e1862a
--- /dev/null
+++ b/include/linux/interval_tree_generic.h
@@ -0,0 +1,191 @@
+/*
+  Interval Trees
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  include/linux/interval_tree_generic.h
+*/
+
+#include <linux/rbtree_augmented.h>
+
+/*
+ * Template for implementing interval trees
+ *
+ * ITSTRUCT:   struct type of the interval tree nodes
+ * ITRB:       name of struct rb_node field within ITSTRUCT
+ * ITTYPE:     type of the interval endpoints
+ * ITSUBTREE:  name of ITTYPE field within ITSTRUCT holding last-in-subtree
+ * ITSTART(n): start endpoint of ITSTRUCT node n
+ * ITLAST(n):  last endpoint of ITSTRUCT node n
+ * ITSTATIC:   'static' or empty
+ * ITPREFIX:   prefix to use for the inline tree definitions
+ *
+ * Note - before using this, please consider if non-generic version
+ * (interval_tree.h) would work for you...
+ */
+
+#define INTERVAL_TREE_DEFINE(ITSTRUCT, ITRB, ITTYPE, ITSUBTREE,		      \
+			     ITSTART, ITLAST, ITSTATIC, ITPREFIX)	      \
+									      \
+/* Callbacks for augmented rbtree insert and remove */			      \
+									      \
+static inline ITTYPE ITPREFIX ## _compute_subtree_last(ITSTRUCT *node)	      \
+{									      \
+	ITTYPE max = ITLAST(node), subtree_last;			      \
+	if (node->ITRB.rb_left) {					      \
+		subtree_last = rb_entry(node->ITRB.rb_left,		      \
+					ITSTRUCT, ITRB)->ITSUBTREE;	      \
+		if (max < subtree_last)					      \
+			max = subtree_last;				      \
+	}								      \
+	if (node->ITRB.rb_right) {					      \
+		subtree_last = rb_entry(node->ITRB.rb_right,		      \
+					ITSTRUCT, ITRB)->ITSUBTREE;	      \
+		if (max < subtree_last)					      \
+			max = subtree_last;				      \
+	}								      \
+	return max;							      \
+}									      \
+									      \
+RB_DECLARE_CALLBACKS(static, ITPREFIX ## _augment, ITSTRUCT, ITRB,	      \
+		     ITTYPE, ITSUBTREE, ITPREFIX ## _compute_subtree_last)    \
+									      \
+/* Insert / remove interval nodes from the tree */			      \
+									      \
+ITSTATIC void ITPREFIX ## _insert(ITSTRUCT *node, struct rb_root *root)	      \
+{									      \
+	struct rb_node **link = &root->rb_node, *rb_parent = NULL;	      \
+	ITTYPE start = ITSTART(node), last = ITLAST(node);		      \
+	ITSTRUCT *parent;						      \
+									      \
+	while (*link) {							      \
+		rb_parent = *link;					      \
+		parent = rb_entry(rb_parent, ITSTRUCT, ITRB);		      \
+		if (parent->ITSUBTREE < last)				      \
+			parent->ITSUBTREE = last;			      \
+		if (start < ITSTART(parent))				      \
+			link = &parent->ITRB.rb_left;			      \
+		else							      \
+			link = &parent->ITRB.rb_right;			      \
+	}								      \
+									      \
+	node->ITSUBTREE = last;						      \
+	rb_link_node(&node->ITRB, rb_parent, link);			      \
+	rb_insert_augmented(&node->ITRB, root, &ITPREFIX ## _augment);	      \
+}									      \
+									      \
+ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, struct rb_root *root)	      \
+{									      \
+	rb_erase_augmented(&node->ITRB, root, &ITPREFIX ## _augment);	      \
+}									      \
+									      \
+/*									      \
+ * Iterate over intervals intersecting [start;last]			      \
+ *									      \
+ * Note that a node's interval intersects [start;last] iff:		      \
+ *   Cond1: ITSTART(node) <= last					      \
+ * and									      \
+ *   Cond2: start <= ITLAST(node)					      \
+ */									      \
+									      \
+static ITSTRUCT *							      \
+ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last)	      \
+{									      \
+	while (true) {							      \
+		/*							      \
+		 * Loop invariant: start <= node->ITSUBTREE		      \
+		 * (Cond2 is satisfied by one of the subtree nodes)	      \
+		 */							      \
+		if (node->ITRB.rb_left) {				      \
+			ITSTRUCT *left = rb_entry(node->ITRB.rb_left,	      \
+						  ITSTRUCT, ITRB);	      \
+			if (start <= left->ITSUBTREE) {			      \
+				/*					      \
+				 * Some nodes in left subtree satisfy Cond2.  \
+				 * Iterate to find the leftmost such node N.  \
+				 * If it also satisfies Cond1, that's the     \
+				 * match we are looking for. Otherwise, there \
+				 * is no matching interval as nodes to the    \
+				 * right of N can't satisfy Cond1 either.     \
+				 */					      \
+				node = left;				      \
+				continue;				      \
+			}						      \
+		}							      \
+		if (ITSTART(node) <= last) {		/* Cond1 */	      \
+			if (start <= ITLAST(node))	/* Cond2 */	      \
+				return node;	/* node is leftmost match */  \
+			if (node->ITRB.rb_right) {			      \
+				node = rb_entry(node->ITRB.rb_right,	      \
+						ITSTRUCT, ITRB);	      \
+				if (start <= node->ITSUBTREE)		      \
+					continue;			      \
+			}						      \
+		}							      \
+		return NULL;	/* No match */				      \
+	}								      \
+}									      \
+									      \
+ITSTATIC ITSTRUCT *							      \
+ITPREFIX ## _iter_first(struct rb_root *root, ITTYPE start, ITTYPE last)      \
+{									      \
+	ITSTRUCT *node;							      \
+									      \
+	if (!root->rb_node)						      \
+		return NULL;						      \
+	node = rb_entry(root->rb_node, ITSTRUCT, ITRB);			      \
+	if (node->ITSUBTREE < start)					      \
+		return NULL;						      \
+	return ITPREFIX ## _subtree_search(node, start, last);		      \
+}									      \
+									      \
+ITSTATIC ITSTRUCT *							      \
+ITPREFIX ## _iter_next(ITSTRUCT *node, ITTYPE start, ITTYPE last)	      \
+{									      \
+	struct rb_node *rb = node->ITRB.rb_right, *prev;		      \
+									      \
+	while (true) {							      \
+		/*							      \
+		 * Loop invariants:					      \
+		 *   Cond1: ITSTART(node) <= last			      \
+		 *   rb == node->ITRB.rb_right				      \
+		 *							      \
+		 * First, search right subtree if suitable		      \
+		 */							      \
+		if (rb) {						      \
+			ITSTRUCT *right = rb_entry(rb, ITSTRUCT, ITRB);	      \
+			if (start <= right->ITSUBTREE)			      \
+				return ITPREFIX ## _subtree_search(right,     \
+								start, last); \
+		}							      \
+									      \
+		/* Move up the tree until we come from a node's left child */ \
+		do {							      \
+			rb = rb_parent(&node->ITRB);			      \
+			if (!rb)					      \
+				return NULL;				      \
+			prev = &node->ITRB;				      \
+			node = rb_entry(rb, ITSTRUCT, ITRB);		      \
+			rb = node->ITRB.rb_right;			      \
+		} while (prev == rb);					      \
+									      \
+		/* Check if the node intersects [start;last] */		      \
+		if (last < ITSTART(node))		/* !Cond1 */	      \
+			return NULL;					      \
+		else if (start <= ITLAST(node))		/* Cond2 */	      \
+			return node;					      \
+	}								      \
+}
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index 19dc455b4f3..569d67d4243 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -70,8 +70,7 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
  * @p_end: ptr to ulong for end pfn of the range, can be %NULL
  * @p_nid: ptr to int for nid of the range, can be %NULL
  *
- * Walks over configured memory ranges.  Available after early_node_map is
- * populated.
+ * Walks over configured memory ranges.
  */
 #define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid)		\
 	for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 8d9489fdab2..fd0e6d53836 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -84,14 +84,14 @@ extern struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg);
 extern struct mem_cgroup *mem_cgroup_from_cont(struct cgroup *cont);
 
 static inline
-int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
+bool mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *memcg)
 {
-	struct mem_cgroup *memcg;
-	int match;
+	struct mem_cgroup *task_memcg;
+	bool match;
 
 	rcu_read_lock();
-	memcg = mem_cgroup_from_task(rcu_dereference((mm)->owner));
-	match = __mem_cgroup_same_or_subtree(cgroup, memcg);
+	task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	match = __mem_cgroup_same_or_subtree(memcg, task_memcg);
 	rcu_read_unlock();
 	return match;
 }
@@ -258,10 +258,10 @@ static inline struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm
 	return NULL;
 }
 
-static inline int mm_match_cgroup(struct mm_struct *mm,
+static inline bool mm_match_cgroup(struct mm_struct *mm,
 		struct mem_cgroup *memcg)
 {
-	return 1;
+	return true;
 }
 
 static inline int task_in_mem_cgroup(struct task_struct *task,
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 910550f3b70..95573ec4ee6 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -10,6 +10,7 @@ struct page;
 struct zone;
 struct pglist_data;
 struct mem_section;
+struct memory_block;
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 
@@ -233,6 +234,8 @@ static inline int is_mem_section_removable(unsigned long pfn,
 extern int mem_online_node(int nid);
 extern int add_memory(int nid, u64 start, u64 size);
 extern int arch_add_memory(int nid, u64 start, u64 size);
+extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages);
+extern int offline_memory_block(struct memory_block *mem);
 extern int remove_memory(u64 start, u64 size);
 extern int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 								int nr_pages);
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 95b738c7abf..cec56932560 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -188,7 +188,7 @@ struct sp_node {
 
 struct shared_policy {
 	struct rb_root root;
-	spinlock_t lock;
+	struct mutex mutex;
 };
 
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
@@ -239,7 +239,7 @@ extern int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol,
 /* Check if a vma is migratable */
 static inline int vma_migratable(struct vm_area_struct *vma)
 {
-	if (vma->vm_flags & (VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED))
+	if (vma->vm_flags & (VM_IO | VM_HUGETLB | VM_PFNMAP))
 		return 0;
 	/*
 	 * Migration allocates pages in the highest zone. If we cannot
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 311be906b57..fa068040273 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -10,7 +10,6 @@
 #include <linux/list.h>
 #include <linux/mmzone.h>
 #include <linux/rbtree.h>
-#include <linux/prio_tree.h>
 #include <linux/atomic.h>
 #include <linux/debug_locks.h>
 #include <linux/mm_types.h>
@@ -21,6 +20,7 @@
 
 struct mempolicy;
 struct anon_vma;
+struct anon_vma_chain;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
@@ -70,6 +70,8 @@ extern unsigned int kobjsize(const void *objp);
 /*
  * vm_flags in vm_area_struct, see mm_types.h.
  */
+#define VM_NONE		0x00000000
+
 #define VM_READ		0x00000001	/* currently active flags */
 #define VM_WRITE	0x00000002
 #define VM_EXEC		0x00000004
@@ -82,16 +84,9 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_MAYSHARE	0x00000080
 
 #define VM_GROWSDOWN	0x00000100	/* general info on the segment */
-#if defined(CONFIG_STACK_GROWSUP) || defined(CONFIG_IA64)
-#define VM_GROWSUP	0x00000200
-#else
-#define VM_GROWSUP	0x00000000
-#define VM_NOHUGEPAGE	0x00000200	/* MADV_NOHUGEPAGE marked this vma */
-#endif
 #define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
 #define VM_DENYWRITE	0x00000800	/* ETXTBSY on write attempts.. */
 
-#define VM_EXECUTABLE	0x00001000
 #define VM_LOCKED	0x00002000
 #define VM_IO           0x00004000	/* Memory mapped I/O or similar */
 
@@ -101,25 +96,34 @@ extern unsigned int kobjsize(const void *objp);
 
 #define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
 #define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
-#define VM_RESERVED	0x00080000	/* Count as reserved_vm like IO */
 #define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
 #define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
 #define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
 #define VM_NONLINEAR	0x00800000	/* Is non-linear (remap_file_pages) */
-#ifndef CONFIG_TRANSPARENT_HUGEPAGE
-#define VM_MAPPED_COPY	0x01000000	/* T if mapped copy of data (nommu mmap) */
-#else
-#define VM_HUGEPAGE	0x01000000	/* MADV_HUGEPAGE marked this vma */
-#endif
-#define VM_INSERTPAGE	0x02000000	/* The vma has had "vm_insert_page()" done on it */
-#define VM_NODUMP	0x04000000	/* Do not include in the core dump */
+#define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
+#define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
 
-#define VM_CAN_NONLINEAR 0x08000000	/* Has ->fault & does nonlinear pages */
 #define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
-#define VM_SAO		0x20000000	/* Strong Access Ordering (powerpc) */
-#define VM_PFN_AT_MMAP	0x40000000	/* PFNMAP vma that is fully mapped at mmap time */
+#define VM_HUGEPAGE	0x20000000	/* MADV_HUGEPAGE marked this vma */
+#define VM_NOHUGEPAGE	0x40000000	/* MADV_NOHUGEPAGE marked this vma */
 #define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
 
+#if defined(CONFIG_X86)
+# define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
+#elif defined(CONFIG_PPC)
+# define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
+#elif defined(CONFIG_PARISC)
+# define VM_GROWSUP	VM_ARCH_1
+#elif defined(CONFIG_IA64)
+# define VM_GROWSUP	VM_ARCH_1
+#elif !defined(CONFIG_MMU)
+# define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
+#endif
+
+#ifndef VM_GROWSUP
+# define VM_GROWSUP	VM_NONE
+#endif
+
 /* Bits set in the VMA until the stack is in its final location */
 #define VM_STACK_INCOMPLETE_SETUP	(VM_RAND_READ | VM_SEQ_READ)
 
@@ -143,7 +147,7 @@ extern unsigned int kobjsize(const void *objp);
  * Special vmas that are non-mergable, non-mlock()able.
  * Note: mm/huge_memory.c VM_NO_THP depends on this definition.
  */
-#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP)
+#define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP)
 
 /*
  * mapping from the currently active vm_flags protection bits (the
@@ -157,24 +161,7 @@ extern pgprot_t protection_map[16];
 #define FAULT_FLAG_ALLOW_RETRY	0x08	/* Retry fault if blocking */
 #define FAULT_FLAG_RETRY_NOWAIT	0x10	/* Don't drop mmap_sem and wait when retrying */
 #define FAULT_FLAG_KILLABLE	0x20	/* The fault task is in SIGKILL killable region */
-
-/*
- * This interface is used by x86 PAT code to identify a pfn mapping that is
- * linear over entire vma. This is to optimize PAT code that deals with
- * marking the physical region with a particular prot. This is not for generic
- * mm use. Note also that this check will not work if the pfn mapping is
- * linear for a vma starting at physical address 0. In which case PAT code
- * falls back to slow path of reserving physical range page by page.
- */
-static inline int is_linear_pfn_mapping(struct vm_area_struct *vma)
-{
-	return !!(vma->vm_flags & VM_PFN_AT_MMAP);
-}
-
-static inline int is_pfn_mapping(struct vm_area_struct *vma)
-{
-	return !!(vma->vm_flags & VM_PFNMAP);
-}
+#define FAULT_FLAG_TRIED	0x40	/* second try */
 
 /*
  * vm_fault is filled by the the pagefault handler and passed to the vma's
@@ -182,8 +169,7 @@ static inline int is_pfn_mapping(struct vm_area_struct *vma)
  * of VM_FAULT_xxx flags that give details about how the fault was handled.
  *
  * pgoff should be used in favour of virtual_address, if possible. If pgoff
- * is used, one may set VM_CAN_NONLINEAR in the vma->vm_flags to get nonlinear
- * mapping support.
+ * is used, one may implement ->remap_pages to get nonlinear mapping support.
  */
 struct vm_fault {
 	unsigned int flags;		/* FAULT_FLAG_xxx flags */
@@ -241,6 +227,9 @@ struct vm_operations_struct {
 	int (*migrate)(struct vm_area_struct *vma, const nodemask_t *from,
 		const nodemask_t *to, unsigned long flags);
 #endif
+	/* called by sys_remap_file_pages() to populate non-linear mapping */
+	int (*remap_pages)(struct vm_area_struct *vma, unsigned long addr,
+			   unsigned long size, pgoff_t pgoff);
 };
 
 struct mmu_gather;
@@ -249,6 +238,18 @@ struct inode;
 #define page_private(page)		((page)->private)
 #define set_page_private(page, v)	((page)->private = (v))
 
+/* It's valid only if the page is free path or free_list */
+static inline void set_freepage_migratetype(struct page *page, int migratetype)
+{
+	page->index = migratetype;
+}
+
+/* It's valid only if the page is free path or free_list */
+static inline int get_freepage_migratetype(struct page *page)
+{
+	return page->index;
+}
+
 /*
  * FIXME: take this include out, include page-flags.h in
  * files which need it (119 of them)
@@ -454,6 +455,7 @@ void put_pages_list(struct list_head *pages);
 
 void split_page(struct page *page, unsigned int order);
 int split_free_page(struct page *page);
+int capture_free_page(struct page *page, int alloc_order, int migratetype);
 
 /*
  * Compound pages have a destructor function.  Provide a
@@ -1071,7 +1073,8 @@ vm_is_stack(struct task_struct *task, struct vm_area_struct *vma, int in_group);
 
 extern unsigned long move_page_tables(struct vm_area_struct *vma,
 		unsigned long old_addr, struct vm_area_struct *new_vma,
-		unsigned long new_addr, unsigned long len);
+		unsigned long new_addr, unsigned long len,
+		bool need_rmap_locks);
 extern unsigned long do_mremap(unsigned long addr,
 			       unsigned long old_len, unsigned long new_len,
 			       unsigned long flags, unsigned long new_addr);
@@ -1366,24 +1369,45 @@ extern void zone_pcp_reset(struct zone *zone);
 extern atomic_long_t mmap_pages_allocated;
 extern int nommu_shrink_inode_mappings(struct inode *, size_t, size_t);
 
-/* prio_tree.c */
-void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
-void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
-void vma_prio_tree_remove(struct vm_area_struct *, struct prio_tree_root *);
-struct vm_area_struct *vma_prio_tree_next(struct vm_area_struct *vma,
-	struct prio_tree_iter *iter);
-
-#define vma_prio_tree_foreach(vma, iter, root, begin, end)	\
-	for (prio_tree_iter_init(iter, root, begin, end), vma = NULL;	\
-		(vma = vma_prio_tree_next(vma, iter)); )
+/* interval_tree.c */
+void vma_interval_tree_insert(struct vm_area_struct *node,
+			      struct rb_root *root);
+void vma_interval_tree_insert_after(struct vm_area_struct *node,
+				    struct vm_area_struct *prev,
+				    struct rb_root *root);
+void vma_interval_tree_remove(struct vm_area_struct *node,
+			      struct rb_root *root);
+struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root *root,
+				unsigned long start, unsigned long last);
+struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
+				unsigned long start, unsigned long last);
+
+#define vma_interval_tree_foreach(vma, root, start, last)		\
+	for (vma = vma_interval_tree_iter_first(root, start, last);	\
+	     vma; vma = vma_interval_tree_iter_next(vma, start, last))
 
 static inline void vma_nonlinear_insert(struct vm_area_struct *vma,
 					struct list_head *list)
 {
-	vma->shared.vm_set.parent = NULL;
-	list_add_tail(&vma->shared.vm_set.list, list);
+	list_add_tail(&vma->shared.nonlinear, list);
 }
 
+void anon_vma_interval_tree_insert(struct anon_vma_chain *node,
+				   struct rb_root *root);
+void anon_vma_interval_tree_remove(struct anon_vma_chain *node,
+				   struct rb_root *root);
+struct anon_vma_chain *anon_vma_interval_tree_iter_first(
+	struct rb_root *root, unsigned long start, unsigned long last);
+struct anon_vma_chain *anon_vma_interval_tree_iter_next(
+	struct anon_vma_chain *node, unsigned long start, unsigned long last);
+#ifdef CONFIG_DEBUG_VM_RB
+void anon_vma_interval_tree_verify(struct anon_vma_chain *node);
+#endif
+
+#define anon_vma_interval_tree_foreach(avc, root, start, last)		 \
+	for (avc = anon_vma_interval_tree_iter_first(root, start, last); \
+	     avc; avc = anon_vma_interval_tree_iter_next(avc, start, last))
+
 /* mmap.c */
 extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
 extern int vma_adjust(struct vm_area_struct *vma, unsigned long start,
@@ -1400,15 +1424,13 @@ extern void __vma_link_rb(struct mm_struct *, struct vm_area_struct *,
 	struct rb_node **, struct rb_node *);
 extern void unlink_file_vma(struct vm_area_struct *);
 extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
-	unsigned long addr, unsigned long len, pgoff_t pgoff);
+	unsigned long addr, unsigned long len, pgoff_t pgoff,
+	bool *need_rmap_locks);
 extern void exit_mmap(struct mm_struct *);
 
 extern int mm_take_all_locks(struct mm_struct *mm);
 extern void mm_drop_all_locks(struct mm_struct *mm);
 
-/* From fs/proc/base.c. callers must _not_ hold the mm's exe_file_lock */
-extern void added_exe_file_vma(struct mm_struct *mm);
-extern void removed_exe_file_vma(struct mm_struct *mm);
 extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file);
 extern struct file *get_mm_exe_file(struct mm_struct *mm);
 
@@ -1662,5 +1684,9 @@ static inline unsigned int debug_guardpage_minorder(void) { return 0; }
 static inline bool page_is_guard(struct page *page) { return false; }
 #endif /* CONFIG_DEBUG_PAGEALLOC */
 
+extern void reset_zone_present_pages(void);
+extern void fixup_zone_present_pages(int nid, unsigned long start_pfn,
+				unsigned long end_pfn);
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bf7867200b9..31f8a3af7d9 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -6,7 +6,6 @@
 #include <linux/threads.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
-#include <linux/prio_tree.h>
 #include <linux/rbtree.h>
 #include <linux/rwsem.h>
 #include <linux/completion.h>
@@ -240,18 +239,15 @@ struct vm_area_struct {
 
 	/*
 	 * For areas with an address space and backing store,
-	 * linkage into the address_space->i_mmap prio tree, or
-	 * linkage to the list of like vmas hanging off its node, or
+	 * linkage into the address_space->i_mmap interval tree, or
 	 * linkage of vma in the address_space->i_mmap_nonlinear list.
 	 */
 	union {
 		struct {
-			struct list_head list;
-			void *parent;	/* aligns with prio_tree_node parent */
-			struct vm_area_struct *head;
-		} vm_set;
-
-		struct raw_prio_tree_node prio_tree_node;
+			struct rb_node rb;
+			unsigned long rb_subtree_last;
+		} linear;
+		struct list_head nonlinear;
 	} shared;
 
 	/*
@@ -349,7 +345,6 @@ struct mm_struct {
 	unsigned long shared_vm;	/* Shared pages (files) */
 	unsigned long exec_vm;		/* VM_EXEC & ~VM_WRITE */
 	unsigned long stack_vm;		/* VM_GROWSUP/DOWN */
-	unsigned long reserved_vm;	/* VM_RESERVED|VM_IO pages */
 	unsigned long def_flags;
 	unsigned long nr_ptes;		/* Page table pages */
 	unsigned long start_code, end_code, start_data, end_data;
@@ -394,7 +389,6 @@ struct mm_struct {
 
 	/* store ref to file /proc/<pid>/exe symlink points to */
 	struct file *exe_file;
-	unsigned long num_exe_file_vmas;
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
diff --git a/include/linux/mman.h b/include/linux/mman.h
index 8b74e9b1d0a..77cec2f45cb 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -86,7 +86,6 @@ calc_vm_flag_bits(unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_DENYWRITE,  VM_DENYWRITE ) |
-	       _calc_vm_trans(flags, MAP_EXECUTABLE, VM_EXECUTABLE) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    );
 }
 #endif /* __KERNEL__ */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 1d1b1e13f79..bc823c4c028 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -4,6 +4,7 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/mm_types.h>
+#include <linux/srcu.h>
 
 struct mmu_notifier;
 struct mmu_notifier_ops;
@@ -245,50 +246,6 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 		__mmu_notifier_mm_destroy(mm);
 }
 
-/*
- * These two macros will sometime replace ptep_clear_flush.
- * ptep_clear_flush is implemented as macro itself, so this also is
- * implemented as a macro until ptep_clear_flush will converted to an
- * inline function, to diminish the risk of compilation failure. The
- * invalidate_page method over time can be moved outside the PT lock
- * and these two macros can be later removed.
- */
-#define ptep_clear_flush_notify(__vma, __address, __ptep)		\
-({									\
-	pte_t __pte;							\
-	struct vm_area_struct *___vma = __vma;				\
-	unsigned long ___address = __address;				\
-	__pte = ptep_clear_flush(___vma, ___address, __ptep);		\
-	mmu_notifier_invalidate_page(___vma->vm_mm, ___address);	\
-	__pte;								\
-})
-
-#define pmdp_clear_flush_notify(__vma, __address, __pmdp)		\
-({									\
-	pmd_t __pmd;							\
-	struct vm_area_struct *___vma = __vma;				\
-	unsigned long ___address = __address;				\
-	VM_BUG_ON(__address & ~HPAGE_PMD_MASK);				\
-	mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address,	\
-					    (__address)+HPAGE_PMD_SIZE);\
-	__pmd = pmdp_clear_flush(___vma, ___address, __pmdp);		\
-	mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address,	\
-					  (__address)+HPAGE_PMD_SIZE);	\
-	__pmd;								\
-})
-
-#define pmdp_splitting_flush_notify(__vma, __address, __pmdp)		\
-({									\
-	struct vm_area_struct *___vma = __vma;				\
-	unsigned long ___address = __address;				\
-	VM_BUG_ON(__address & ~HPAGE_PMD_MASK);				\
-	mmu_notifier_invalidate_range_start(___vma->vm_mm, ___address,	\
-					    (__address)+HPAGE_PMD_SIZE);\
-	pmdp_splitting_flush(___vma, ___address, __pmdp);		\
-	mmu_notifier_invalidate_range_end(___vma->vm_mm, ___address,	\
-					  (__address)+HPAGE_PMD_SIZE);	\
-})
-
 #define ptep_clear_flush_young_notify(__vma, __address, __ptep)		\
 ({									\
 	int __young;							\
@@ -311,14 +268,24 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	__young;							\
 })
 
+/*
+ * set_pte_at_notify() sets the pte _after_ running the notifier.
+ * This is safe to start by updating the secondary MMUs, because the primary MMU
+ * pte invalidate must have already happened with a ptep_clear_flush() before
+ * set_pte_at_notify() has been invoked.  Updating the secondary MMUs first is
+ * required when we change both the protection of the mapping from read-only to
+ * read-write and the pfn (like during copy on write page faults). Otherwise the
+ * old page would remain mapped readonly in the secondary MMUs after the new
+ * page is already writable by some CPU through the primary MMU.
+ */
 #define set_pte_at_notify(__mm, __address, __ptep, __pte)		\
 ({									\
 	struct mm_struct *___mm = __mm;					\
 	unsigned long ___address = __address;				\
 	pte_t ___pte = __pte;						\
 									\
-	set_pte_at(___mm, ___address, __ptep, ___pte);			\
 	mmu_notifier_change_pte(___mm, ___address, ___pte);		\
+	set_pte_at(___mm, ___address, __ptep, ___pte);			\
 })
 
 #else /* CONFIG_MMU_NOTIFIER */
@@ -369,9 +336,6 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 
 #define ptep_clear_flush_young_notify ptep_clear_flush_young
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
-#define ptep_clear_flush_notify ptep_clear_flush
-#define pmdp_clear_flush_notify pmdp_clear_flush
-#define pmdp_splitting_flush_notify pmdp_splitting_flush
 #define set_pte_at_notify set_pte_at
 
 #endif /* CONFIG_MMU_NOTIFIER */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 2daa54f55db..50aaca81f63 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -142,6 +142,7 @@ enum zone_stat_item {
 	NUMA_OTHER,		/* allocation from other node */
 #endif
 	NR_ANON_TRANSPARENT_HUGEPAGES,
+	NR_FREE_CMA_PAGES,
 	NR_VM_ZONE_STAT_ITEMS };
 
 /*
@@ -217,6 +218,8 @@ struct lruvec {
 #define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x2)
 /* Isolate for asynchronous migration */
 #define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x4)
+/* Isolate unevictable pages */
+#define ISOLATE_UNEVICTABLE	((__force isolate_mode_t)0x8)
 
 /* LRU Isolation modes. */
 typedef unsigned __bitwise__ isolate_mode_t;
@@ -369,8 +372,12 @@ struct zone {
 	spinlock_t		lock;
 	int                     all_unreclaimable; /* All pages pinned */
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
-	/* pfn where the last incremental compaction isolated free pages */
+	/* Set to true when the PG_migrate_skip bits should be cleared */
+	bool			compact_blockskip_flush;
+
+	/* pfns where compaction scanners should start */
 	unsigned long		compact_cached_free_pfn;
+	unsigned long		compact_cached_migrate_pfn;
 #endif
 #ifdef CONFIG_MEMORY_HOTPLUG
 	/* see spanned/present_pages for more description */
@@ -704,6 +711,7 @@ typedef struct pglist_data {
 	unsigned long node_spanned_pages; /* total size of physical page
 					     range, including holes */
 	int node_id;
+	nodemask_t reclaim_nodes;	/* Nodes allowed to reclaim from */
 	wait_queue_head_t kswapd_wait;
 	wait_queue_head_t pfmemalloc_wait;
 	struct task_struct *kswapd;	/* Protected by lock_memory_hotplug() */
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 49a3031fda5..d36a8221f58 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -2,17 +2,6 @@
 #define __INCLUDE_LINUX_OOM_H
 
 /*
- * /proc/<pid>/oom_adj is deprecated, see
- * Documentation/feature-removal-schedule.txt.
- *
- * /proc/<pid>/oom_adj set to -17 protects from the oom-killer
- */
-#define OOM_DISABLE (-17)
-/* inclusive */
-#define OOM_ADJUST_MIN (-16)
-#define OOM_ADJUST_MAX 15
-
-/*
  * /proc/<pid>/oom_score_adj set to OOM_SCORE_ADJ_MIN disables oom killing for
  * pid.
  */
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 105077aa768..76a9539cfd3 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -6,6 +6,10 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count);
 void set_pageblock_migratetype(struct page *page, int migratetype);
 int move_freepages_block(struct zone *zone, struct page *page,
 				int migratetype);
+int move_freepages(struct zone *zone,
+			  struct page *start_page, struct page *end_page,
+			  int migratetype);
+
 /*
  * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE.
  * If specified range includes migrate types other than MOVABLE or CMA,
@@ -37,6 +41,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);
  */
 int set_migratetype_isolate(struct page *page);
 void unset_migratetype_isolate(struct page *page, unsigned migratetype);
-
+struct page *alloc_migrate_target(struct page *page, unsigned long private,
+				int **resultp);
 
 #endif
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 19ef95d293a..eed27f4f4c3 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -30,6 +30,9 @@ enum pageblock_bits {
 	PB_migrate,
 	PB_migrate_end = PB_migrate + 3 - 1,
 			/* 3 bits required for migrate types */
+#ifdef CONFIG_COMPACTION
+	PB_migrate_skip,/* If set the block is skipped by compaction */
+#endif /* CONFIG_COMPACTION */
 	NR_PAGEBLOCK_BITS
 };
 
@@ -65,10 +68,22 @@ unsigned long get_pageblock_flags_group(struct page *page,
 void set_pageblock_flags_group(struct page *page, unsigned long flags,
 					int start_bitidx, int end_bitidx);
 
+#ifdef CONFIG_COMPACTION
+#define get_pageblock_skip(page) \
+			get_pageblock_flags_group(page, PB_migrate_skip,     \
+							PB_migrate_skip + 1)
+#define clear_pageblock_skip(page) \
+			set_pageblock_flags_group(page, 0, PB_migrate_skip,  \
+							PB_migrate_skip + 1)
+#define set_pageblock_skip(page) \
+			set_pageblock_flags_group(page, 1, PB_migrate_skip,  \
+							PB_migrate_skip + 1)
+#endif /* CONFIG_COMPACTION */
+
 #define get_pageblock_flags(page) \
-			get_pageblock_flags_group(page, 0, NR_PAGEBLOCK_BITS-1)
+			get_pageblock_flags_group(page, 0, PB_migrate_end)
 #define set_pageblock_flags(page, flags) \
 			set_pageblock_flags_group(page, flags,	\
-						  0, NR_PAGEBLOCK_BITS-1)
+						  0, PB_migrate_end)
 
 #endif	/* PAGEBLOCK_FLAGS_H */
diff --git a/include/linux/prio_tree.h b/include/linux/prio_tree.h
deleted file mode 100644
index db04abb557e..00000000000
--- a/include/linux/prio_tree.h
+++ /dev/null
@@ -1,120 +0,0 @@
-#ifndef _LINUX_PRIO_TREE_H
-#define _LINUX_PRIO_TREE_H
-
-/*
- * K&R 2nd ed. A8.3 somewhat obliquely hints that initial sequences of struct
- * fields with identical types should end up at the same location. We'll use
- * this until we can scrap struct raw_prio_tree_node.
- *
- * Note: all this could be done more elegantly by using unnamed union/struct
- * fields. However, gcc 2.95.3 and apparently also gcc 3.0.4 don't support this
- * language extension.
- */
-
-struct raw_prio_tree_node {
-	struct prio_tree_node	*left;
-	struct prio_tree_node	*right;
-	struct prio_tree_node	*parent;
-};
-
-struct prio_tree_node {
-	struct prio_tree_node	*left;
-	struct prio_tree_node	*right;
-	struct prio_tree_node	*parent;
-	unsigned long		start;
-	unsigned long		last;	/* last location _in_ interval */
-};
-
-struct prio_tree_root {
-	struct prio_tree_node	*prio_tree_node;
-	unsigned short 		index_bits;
-	unsigned short		raw;
-		/*
-		 * 0: nodes are of type struct prio_tree_node
-		 * 1: nodes are of type raw_prio_tree_node
-		 */
-};
-
-struct prio_tree_iter {
-	struct prio_tree_node	*cur;
-	unsigned long		mask;
-	unsigned long		value;
-	int			size_level;
-
-	struct prio_tree_root	*root;
-	pgoff_t			r_index;
-	pgoff_t			h_index;
-};
-
-static inline void prio_tree_iter_init(struct prio_tree_iter *iter,
-		struct prio_tree_root *root, pgoff_t r_index, pgoff_t h_index)
-{
-	iter->root = root;
-	iter->r_index = r_index;
-	iter->h_index = h_index;
-	iter->cur = NULL;
-}
-
-#define __INIT_PRIO_TREE_ROOT(ptr, _raw)	\
-do {					\
-	(ptr)->prio_tree_node = NULL;	\
-	(ptr)->index_bits = 1;		\
-	(ptr)->raw = (_raw);		\
-} while (0)
-
-#define INIT_PRIO_TREE_ROOT(ptr)	__INIT_PRIO_TREE_ROOT(ptr, 0)
-#define INIT_RAW_PRIO_TREE_ROOT(ptr)	__INIT_PRIO_TREE_ROOT(ptr, 1)
-
-#define INIT_PRIO_TREE_NODE(ptr)				\
-do {								\
-	(ptr)->left = (ptr)->right = (ptr)->parent = (ptr);	\
-} while (0)
-
-#define INIT_PRIO_TREE_ITER(ptr)	\
-do {					\
-	(ptr)->cur = NULL;		\
-	(ptr)->mask = 0UL;		\
-	(ptr)->value = 0UL;		\
-	(ptr)->size_level = 0;		\
-} while (0)
-
-#define prio_tree_entry(ptr, type, member) \
-       ((type *)((char *)(ptr)-(unsigned long)(&((type *)0)->member)))
-
-static inline int prio_tree_empty(const struct prio_tree_root *root)
-{
-	return root->prio_tree_node == NULL;
-}
-
-static inline int prio_tree_root(const struct prio_tree_node *node)
-{
-	return node->parent == node;
-}
-
-static inline int prio_tree_left_empty(const struct prio_tree_node *node)
-{
-	return node->left == node;
-}
-
-static inline int prio_tree_right_empty(const struct prio_tree_node *node)
-{
-	return node->right == node;
-}
-
-
-struct prio_tree_node *prio_tree_replace(struct prio_tree_root *root,
-                struct prio_tree_node *old, struct prio_tree_node *node);
-struct prio_tree_node *prio_tree_insert(struct prio_tree_root *root,
-                struct prio_tree_node *node);
-void prio_tree_remove(struct prio_tree_root *root, struct prio_tree_node *node);
-struct prio_tree_node *prio_tree_next(struct prio_tree_iter *iter);
-
-#define raw_prio_tree_replace(root, old, node) \
-	prio_tree_replace(root, (struct prio_tree_node *) (old), \
-	    (struct prio_tree_node *) (node))
-#define raw_prio_tree_insert(root, node) \
-	prio_tree_insert(root, (struct prio_tree_node *) (node))
-#define raw_prio_tree_remove(root, node) \
-	prio_tree_remove(root, (struct prio_tree_node *) (node))
-
-#endif /* _LINUX_PRIO_TREE_H */
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index 033b507b33b..0022c1bb1e2 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -23,72 +23,7 @@
   I know it's not the cleaner way,  but in C (not in C++) to get
   performances and genericity...
 
-  Some example of insert and search follows here. The search is a plain
-  normal search over an ordered tree. The insert instead must be implemented
-  in two steps: First, the code must insert the element in order as a red leaf
-  in the tree, and then the support library function rb_insert_color() must
-  be called. Such function will do the not trivial work to rebalance the
-  rbtree, if necessary.
-
------------------------------------------------------------------------
-static inline struct page * rb_search_page_cache(struct inode * inode,
-						 unsigned long offset)
-{
-	struct rb_node * n = inode->i_rb_page_cache.rb_node;
-	struct page * page;
-
-	while (n)
-	{
-		page = rb_entry(n, struct page, rb_page_cache);
-
-		if (offset < page->offset)
-			n = n->rb_left;
-		else if (offset > page->offset)
-			n = n->rb_right;
-		else
-			return page;
-	}
-	return NULL;
-}
-
-static inline struct page * __rb_insert_page_cache(struct inode * inode,
-						   unsigned long offset,
-						   struct rb_node * node)
-{
-	struct rb_node ** p = &inode->i_rb_page_cache.rb_node;
-	struct rb_node * parent = NULL;
-	struct page * page;
-
-	while (*p)
-	{
-		parent = *p;
-		page = rb_entry(parent, struct page, rb_page_cache);
-
-		if (offset < page->offset)
-			p = &(*p)->rb_left;
-		else if (offset > page->offset)
-			p = &(*p)->rb_right;
-		else
-			return page;
-	}
-
-	rb_link_node(node, parent, p);
-
-	return NULL;
-}
-
-static inline struct page * rb_insert_page_cache(struct inode * inode,
-						 unsigned long offset,
-						 struct rb_node * node)
-{
-	struct page * ret;
-	if ((ret = __rb_insert_page_cache(inode, offset, node)))
-		goto out;
-	rb_insert_color(node, &inode->i_rb_page_cache);
- out:
-	return ret;
-}
------------------------------------------------------------------------
+  See Documentation/rbtree.txt for documentation and samples.
 */
 
 #ifndef	_LINUX_RBTREE_H
@@ -97,63 +32,35 @@ static inline struct page * rb_insert_page_cache(struct inode * inode,
 #include <linux/kernel.h>
 #include <linux/stddef.h>
 
-struct rb_node
-{
-	unsigned long  rb_parent_color;
-#define	RB_RED		0
-#define	RB_BLACK	1
+struct rb_node {
+	unsigned long  __rb_parent_color;
 	struct rb_node *rb_right;
 	struct rb_node *rb_left;
 } __attribute__((aligned(sizeof(long))));
     /* The alignment might seem pointless, but allegedly CRIS needs it */
 
-struct rb_root
-{
+struct rb_root {
 	struct rb_node *rb_node;
 };
 
 
-#define rb_parent(r)   ((struct rb_node *)((r)->rb_parent_color & ~3))
-#define rb_color(r)   ((r)->rb_parent_color & 1)
-#define rb_is_red(r)   (!rb_color(r))
-#define rb_is_black(r) rb_color(r)
-#define rb_set_red(r)  do { (r)->rb_parent_color &= ~1; } while (0)
-#define rb_set_black(r)  do { (r)->rb_parent_color |= 1; } while (0)
-
-static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
-{
-	rb->rb_parent_color = (rb->rb_parent_color & 3) | (unsigned long)p;
-}
-static inline void rb_set_color(struct rb_node *rb, int color)
-{
-	rb->rb_parent_color = (rb->rb_parent_color & ~1) | color;
-}
+#define rb_parent(r)   ((struct rb_node *)((r)->__rb_parent_color & ~3))
 
 #define RB_ROOT	(struct rb_root) { NULL, }
 #define	rb_entry(ptr, type, member) container_of(ptr, type, member)
 
-#define RB_EMPTY_ROOT(root)	((root)->rb_node == NULL)
-#define RB_EMPTY_NODE(node)	(rb_parent(node) == node)
-#define RB_CLEAR_NODE(node)	(rb_set_parent(node, node))
+#define RB_EMPTY_ROOT(root)  ((root)->rb_node == NULL)
+
+/* 'empty' nodes are nodes that are known not to be inserted in an rbree */
+#define RB_EMPTY_NODE(node)  \
+	((node)->__rb_parent_color == (unsigned long)(node))
+#define RB_CLEAR_NODE(node)  \
+	((node)->__rb_parent_color = (unsigned long)(node))
 
-static inline void rb_init_node(struct rb_node *rb)
-{
-	rb->rb_parent_color = 0;
-	rb->rb_right = NULL;
-	rb->rb_left = NULL;
-	RB_CLEAR_NODE(rb);
-}
 
 extern void rb_insert_color(struct rb_node *, struct rb_root *);
 extern void rb_erase(struct rb_node *, struct rb_root *);
 
-typedef void (*rb_augment_f)(struct rb_node *node, void *data);
-
-extern void rb_augment_insert(struct rb_node *node,
-			      rb_augment_f func, void *data);
-extern struct rb_node *rb_augment_erase_begin(struct rb_node *node);
-extern void rb_augment_erase_end(struct rb_node *node,
-				 rb_augment_f func, void *data);
 
 /* Find logical next and previous nodes in a tree */
 extern struct rb_node *rb_next(const struct rb_node *);
@@ -168,7 +75,7 @@ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new,
 static inline void rb_link_node(struct rb_node * node, struct rb_node * parent,
 				struct rb_node ** rb_link)
 {
-	node->rb_parent_color = (unsigned long )parent;
+	node->__rb_parent_color = (unsigned long)parent;
 	node->rb_left = node->rb_right = NULL;
 
 	*rb_link = node;
diff --git a/include/linux/rbtree_augmented.h b/include/linux/rbtree_augmented.h
new file mode 100644
index 00000000000..214caa33433
--- /dev/null
+++ b/include/linux/rbtree_augmented.h
@@ -0,0 +1,223 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
+  This program is free software; you can redistribute it and/or modify
+  it under the terms of the GNU General Public License as published by
+  the Free Software Foundation; either version 2 of the License, or
+  (at your option) any later version.
+
+  This program is distributed in the hope that it will be useful,
+  but WITHOUT ANY WARRANTY; without even the implied warranty of
+  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+  GNU General Public License for more details.
+
+  You should have received a copy of the GNU General Public License
+  along with this program; if not, write to the Free Software
+  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+
+  linux/include/linux/rbtree_augmented.h
+*/
+
+#ifndef _LINUX_RBTREE_AUGMENTED_H
+#define _LINUX_RBTREE_AUGMENTED_H
+
+#include <linux/rbtree.h>
+
+/*
+ * Please note - only struct rb_augment_callbacks and the prototypes for
+ * rb_insert_augmented() and rb_erase_augmented() are intended to be public.
+ * The rest are implementation details you are not expected to depend on.
+ *
+ * See Documentation/rbtree.txt for documentation and samples.
+ */
+
+struct rb_augment_callbacks {
+	void (*propagate)(struct rb_node *node, struct rb_node *stop);
+	void (*copy)(struct rb_node *old, struct rb_node *new);
+	void (*rotate)(struct rb_node *old, struct rb_node *new);
+};
+
+extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+static inline void
+rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+		    const struct rb_augment_callbacks *augment)
+{
+	__rb_insert_augmented(node, root, augment->rotate);
+}
+
+#define RB_DECLARE_CALLBACKS(rbstatic, rbname, rbstruct, rbfield,	\
+			     rbtype, rbaugmented, rbcompute)		\
+static inline void							\
+rbname ## _propagate(struct rb_node *rb, struct rb_node *stop)		\
+{									\
+	while (rb != stop) {						\
+		rbstruct *node = rb_entry(rb, rbstruct, rbfield);	\
+		rbtype augmented = rbcompute(node);			\
+		if (node->rbaugmented == augmented)			\
+			break;						\
+		node->rbaugmented = augmented;				\
+		rb = rb_parent(&node->rbfield);				\
+	}								\
+}									\
+static inline void							\
+rbname ## _copy(struct rb_node *rb_old, struct rb_node *rb_new)		\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+}									\
+static void								\
+rbname ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new)	\
+{									\
+	rbstruct *old = rb_entry(rb_old, rbstruct, rbfield);		\
+	rbstruct *new = rb_entry(rb_new, rbstruct, rbfield);		\
+	new->rbaugmented = old->rbaugmented;				\
+	old->rbaugmented = rbcompute(old);				\
+}									\
+rbstatic const struct rb_augment_callbacks rbname = {			\
+	rbname ## _propagate, rbname ## _copy, rbname ## _rotate	\
+};
+
+
+#define	RB_RED		0
+#define	RB_BLACK	1
+
+#define __rb_parent(pc)    ((struct rb_node *)(pc & ~3))
+
+#define __rb_color(pc)     ((pc) & 1)
+#define __rb_is_black(pc)  __rb_color(pc)
+#define __rb_is_red(pc)    (!__rb_color(pc))
+#define rb_color(rb)       __rb_color((rb)->__rb_parent_color)
+#define rb_is_red(rb)      __rb_is_red((rb)->__rb_parent_color)
+#define rb_is_black(rb)    __rb_is_black((rb)->__rb_parent_color)
+
+static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p)
+{
+	rb->__rb_parent_color = rb_color(rb) | (unsigned long)p;
+}
+
+static inline void rb_set_parent_color(struct rb_node *rb,
+				       struct rb_node *p, int color)
+{
+	rb->__rb_parent_color = (unsigned long)p | color;
+}
+
+static inline void
+__rb_change_child(struct rb_node *old, struct rb_node *new,
+		  struct rb_node *parent, struct rb_root *root)
+{
+	if (parent) {
+		if (parent->rb_left == old)
+			parent->rb_left = new;
+		else
+			parent->rb_right = new;
+	} else
+		root->rb_node = new;
+}
+
+extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root,
+	void (*augment_rotate)(struct rb_node *old, struct rb_node *new));
+
+static __always_inline void
+rb_erase_augmented(struct rb_node *node, struct rb_root *root,
+		   const struct rb_augment_callbacks *augment)
+{
+	struct rb_node *child = node->rb_right, *tmp = node->rb_left;
+	struct rb_node *parent, *rebalance;
+	unsigned long pc;
+
+	if (!tmp) {
+		/*
+		 * Case 1: node to erase has no more than 1 child (easy!)
+		 *
+		 * Note that if there is one child it must be red due to 5)
+		 * and node must be black due to 4). We adjust colors locally
+		 * so as to bypass __rb_erase_color() later on.
+		 */
+		pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, child, parent, root);
+		if (child) {
+			child->__rb_parent_color = pc;
+			rebalance = NULL;
+		} else
+			rebalance = __rb_is_black(pc) ? parent : NULL;
+		tmp = parent;
+	} else if (!child) {
+		/* Still case 1, but this time the child is node->rb_left */
+		tmp->__rb_parent_color = pc = node->__rb_parent_color;
+		parent = __rb_parent(pc);
+		__rb_change_child(node, tmp, parent, root);
+		rebalance = NULL;
+		tmp = parent;
+	} else {
+		struct rb_node *successor = child, *child2;
+		tmp = child->rb_left;
+		if (!tmp) {
+			/*
+			 * Case 2: node's successor is its right child
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (s)  ->  (x) (c)
+			 *        \
+			 *        (c)
+			 */
+			parent = successor;
+			child2 = successor->rb_right;
+			augment->copy(node, successor);
+		} else {
+			/*
+			 * Case 3: node's successor is leftmost under
+			 * node's right child subtree
+			 *
+			 *    (n)          (s)
+			 *    / \          / \
+			 *  (x) (y)  ->  (x) (y)
+			 *      /            /
+			 *    (p)          (p)
+			 *    /            /
+			 *  (s)          (c)
+			 *    \
+			 *    (c)
+			 */
+			do {
+				parent = successor;
+				successor = tmp;
+				tmp = tmp->rb_left;
+			} while (tmp);
+			parent->rb_left = child2 = successor->rb_right;
+			successor->rb_right = child;
+			rb_set_parent(child, successor);
+			augment->copy(node, successor);
+			augment->propagate(parent, successor);
+		}
+
+		successor->rb_left = tmp = node->rb_left;
+		rb_set_parent(tmp, successor);
+
+		pc = node->__rb_parent_color;
+		tmp = __rb_parent(pc);
+		__rb_change_child(node, successor, tmp, root);
+		if (child2) {
+			successor->__rb_parent_color = pc;
+			rb_set_parent_color(child2, parent, RB_BLACK);
+			rebalance = NULL;
+		} else {
+			unsigned long pc2 = successor->__rb_parent_color;
+			successor->__rb_parent_color = pc;
+			rebalance = __rb_is_black(pc2) ? parent : NULL;
+		}
+		tmp = successor;
+	}
+
+	augment->propagate(tmp, NULL);
+	if (rebalance)
+		__rb_erase_color(rebalance, root, augment->rotate);
+}
+
+#endif	/* _LINUX_RBTREE_AUGMENTED_H */
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 3fce545df39..bfe1f478064 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -37,14 +37,14 @@ struct anon_vma {
 	atomic_t refcount;
 
 	/*
-	 * NOTE: the LSB of the head.next is set by
+	 * NOTE: the LSB of the rb_root.rb_node is set by
 	 * mm_take_all_locks() _after_ taking the above lock. So the
-	 * head must only be read/written after taking the above lock
+	 * rb_root must only be read/written after taking the above lock
 	 * to be sure to see a valid next pointer. The LSB bit itself
 	 * is serialized by a system wide lock only visible to
 	 * mm_take_all_locks() (mm_all_locks_mutex).
 	 */
-	struct list_head head;	/* Chain of private "related" vmas */
+	struct rb_root rb_root;	/* Interval tree of private "related" vmas */
 };
 
 /*
@@ -57,14 +57,29 @@ struct anon_vma {
  * with a VMA, or the VMAs associated with an anon_vma.
  * The "same_vma" list contains the anon_vma_chains linking
  * all the anon_vmas associated with this VMA.
- * The "same_anon_vma" list contains the anon_vma_chains
+ * The "rb" field indexes on an interval tree the anon_vma_chains
  * which link all the VMAs associated with this anon_vma.
  */
 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 list_head same_anon_vma;	/* locked by anon_vma->mutex */
+	struct rb_node rb;			/* locked by anon_vma->mutex */
+	unsigned long rb_subtree_last;
+#ifdef CONFIG_DEBUG_VM_RB
+	unsigned long cached_vma_start, cached_vma_last;
+#endif
+};
+
+enum ttu_flags {
+	TTU_UNMAP = 0,			/* unmap mode */
+	TTU_MIGRATION = 1,		/* migration mode */
+	TTU_MUNLOCK = 2,		/* munlock mode */
+	TTU_ACTION_MASK = 0xff,
+
+	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
+	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */
+	TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */
 };
 
 #ifdef CONFIG_MMU
@@ -120,7 +135,6 @@ void anon_vma_init(void);	/* create anon_vma_cachep */
 int  anon_vma_prepare(struct vm_area_struct *);
 void unlink_anon_vmas(struct vm_area_struct *);
 int anon_vma_clone(struct vm_area_struct *, struct vm_area_struct *);
-void anon_vma_moveto_tail(struct vm_area_struct *);
 int anon_vma_fork(struct vm_area_struct *, struct vm_area_struct *);
 
 static inline void anon_vma_merge(struct vm_area_struct *vma,
@@ -161,16 +175,6 @@ int page_referenced(struct page *, int is_locked,
 int page_referenced_one(struct page *, struct vm_area_struct *,
 	unsigned long address, unsigned int *mapcount, unsigned long *vm_flags);
 
-enum ttu_flags {
-	TTU_UNMAP = 0,			/* unmap mode */
-	TTU_MIGRATION = 1,		/* migration mode */
-	TTU_MUNLOCK = 2,		/* munlock mode */
-	TTU_ACTION_MASK = 0xff,
-
-	TTU_IGNORE_MLOCK = (1 << 8),	/* ignore mlock */
-	TTU_IGNORE_ACCESS = (1 << 9),	/* don't age */
-	TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */
-};
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
 int try_to_unmap(struct page *, enum ttu_flags flags);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9c5612f0374..c2070e92a9d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -671,7 +671,6 @@ struct signal_struct {
 	struct rw_semaphore group_rwsem;
 #endif
 
-	int oom_adj;		/* OOM kill score adjustment (bit shift) */
 	int oom_score_adj;	/* OOM kill score adjustment */
 	int oom_score_adj_min;	/* OOM kill score adjustment minimum value.
 				 * Only settable by CAP_SYS_RESOURCE. */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 388e7060141..68df9c17fbb 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -281,7 +281,7 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
 }
 #endif
 
-extern int page_evictable(struct page *page, struct vm_area_struct *vma);
+extern int page_evictable(struct page *page);
 extern void check_move_unevictable_pages(struct page **, int nr_pages);
 
 extern unsigned long scan_unevictable_pages;
diff --git a/include/linux/timerqueue.h b/include/linux/timerqueue.h
index 5088727478f..a520fd70a59 100644
--- a/include/linux/timerqueue.h
+++ b/include/linux/timerqueue.h
@@ -39,7 +39,7 @@ struct timerqueue_node *timerqueue_getnext(struct timerqueue_head *head)
 
 static inline void timerqueue_init(struct timerqueue_node *node)
 {
-	rb_init_node(&node->node);
+	RB_CLEAR_NODE(&node->node);
 }
 
 static inline void timerqueue_init_head(struct timerqueue_head *head)
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 57f7b109151..3d311459437 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -52,7 +52,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		UNEVICTABLE_PGMUNLOCKED,
 		UNEVICTABLE_PGCLEARED,	/* on COW, page truncate */
 		UNEVICTABLE_PGSTRANDED,	/* unable to isolate on unlock */
-		UNEVICTABLE_MLOCKFREED,
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 		THP_FAULT_ALLOC,
 		THP_FAULT_FALLBACK,
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index ad2cfd53dad..92a86b2cce3 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -198,6 +198,8 @@ extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 void refresh_cpu_vm_stats(int);
 void refresh_zone_stat_thresholds(void);
 
+void drain_zonestat(struct zone *zone, struct per_cpu_pageset *);
+
 int calculate_pressure_threshold(struct zone *zone);
 int calculate_normal_threshold(struct zone *zone);
 void set_pgdat_percpu_threshold(pg_data_t *pgdat,
@@ -251,8 +253,18 @@ static inline void __dec_zone_page_state(struct page *page,
 static inline void refresh_cpu_vm_stats(int cpu) { }
 static inline void refresh_zone_stat_thresholds(void) { }
 
+static inline void drain_zonestat(struct zone *zone,
+			struct per_cpu_pageset *pset) { }
 #endif		/* CONFIG_SMP */
 
+static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages,
+					     int migratetype)
+{
+	__mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages);
+	if (is_migrate_cma(migratetype))
+		__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages);
+}
+
 extern const char * const vmstat_text[];
 
 #endif /* _LINUX_VMSTAT_H */
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
index d6fd8e5b14b..9391706e925 100644
--- a/include/trace/events/gfpflags.h
+++ b/include/trace/events/gfpflags.h
@@ -36,7 +36,6 @@
 	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
 	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"},		\
 	{(unsigned long)__GFP_NOTRACK,		"GFP_NOTRACK"},		\
-	{(unsigned long)__GFP_NO_KSWAPD,	"GFP_NO_KSWAPD"},	\
 	{(unsigned long)__GFP_OTHER_NODE,	"GFP_OTHER_NODE"}	\
 	) : "GFP_NOWAIT"