Merge branch 'common/mmcif' into rmobile-latest

29 files changed, 754 insertions, 83 deletions

diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 5ac51552d908..dfa2ed4c0d26 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -11,6 +11,9 @@
 /* The full zone was compacted */
 #define COMPACT_COMPLETE	3
 
+#define COMPACT_MODE_DIRECT_RECLAIM	0
+#define COMPACT_MODE_KSWAPD		1
+
 #ifdef CONFIG_COMPACTION
 extern int sysctl_compact_memory;
 extern int sysctl_compaction_handler(struct ctl_table *table, int write,
@@ -21,7 +24,12 @@ 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);
+			int order, gfp_t gfp_mask, nodemask_t *mask,
+			bool sync);
+extern unsigned long compaction_suitable(struct zone *zone, int order);
+extern unsigned long compact_zone_order(struct zone *zone, int order,
+					gfp_t gfp_mask, bool sync,
+					int compact_mode);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
@@ -54,7 +62,20 @@ static inline bool compaction_deferred(struct zone *zone)
 
 #else
 static inline unsigned long try_to_compact_pages(struct zonelist *zonelist,
-			int order, gfp_t gfp_mask, nodemask_t *nodemask)
+			int order, gfp_t gfp_mask, nodemask_t *nodemask,
+			bool sync)
+{
+	return COMPACT_CONTINUE;
+}
+
+static inline unsigned long compaction_suitable(struct zone *zone, int order)
+{
+	return COMPACT_SKIPPED;
+}
+
+static inline unsigned long compact_zone_order(struct zone *zone, int order,
+					       gfp_t gfp_mask, bool sync,
+					       int compact_mode)
 {
 	return COMPACT_CONTINUE;
 }
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 2970022faa63..272496d1fae4 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -193,6 +193,13 @@ struct dm_target {
 	char *error;
 };
 
+/* Each target can link one of these into the table */
+struct dm_target_callbacks {
+	struct list_head list;
+	int (*congested_fn) (struct dm_target_callbacks *, int);
+	void (*unplug_fn)(struct dm_target_callbacks *);
+};
+
 int dm_register_target(struct target_type *t);
 void dm_unregister_target(struct target_type *t);
 
@@ -269,6 +276,11 @@ int dm_table_add_target(struct dm_table *t, const char *type,
 			sector_t start, sector_t len, char *params);
 
 /*
+ * Target_ctr should call this if it needs to add any callbacks.
+ */
+void dm_table_add_target_callbacks(struct dm_table *t, struct dm_target_callbacks *cb);
+
+/*
  * Finally call this to make the table ready for use.
  */
 int dm_table_complete(struct dm_table *t);
diff --git a/include/linux/dm-ioctl.h b/include/linux/dm-ioctl.h
index 49eab360d5d4..78bbf47bbb96 100644
--- a/include/linux/dm-ioctl.h
+++ b/include/linux/dm-ioctl.h
@@ -44,7 +44,7 @@
  * Remove a device, destroy any tables.
  *
  * DM_DEV_RENAME:
- * Rename a device.
+ * Rename a device or set its uuid if none was previously supplied.
  *
  * DM_SUSPEND:
  * This performs both suspend and resume, depending which flag is
@@ -267,9 +267,9 @@ enum {
 #define DM_DEV_SET_GEOMETRY	_IOWR(DM_IOCTL, DM_DEV_SET_GEOMETRY_CMD, struct dm_ioctl)
 
 #define DM_VERSION_MAJOR	4
-#define DM_VERSION_MINOR	18
-#define DM_VERSION_PATCHLEVEL	0
-#define DM_VERSION_EXTRA	"-ioctl (2010-06-29)"
+#define DM_VERSION_MINOR	19
+#define DM_VERSION_PATCHLEVEL	1
+#define DM_VERSION_EXTRA	"-ioctl (2011-01-07)"
 
 /* Status bits */
 #define DM_READONLY_FLAG	(1 << 0) /* In/Out */
@@ -322,4 +322,10 @@ enum {
  */
 #define DM_UEVENT_GENERATED_FLAG	(1 << 13) /* Out */
 
+/*
+ * If set, rename changes the uuid not the name.  Only permitted
+ * if no uuid was previously supplied: an existing uuid cannot be changed.
+ */
+#define DM_UUID_FLAG			(1 << 14) /* In */
+
 #endif				/* _LINUX_DM_IOCTL_H */
diff --git a/include/linux/dm-log-userspace.h b/include/linux/dm-log-userspace.h
index 0c3c3a2110c4..eeace7d3ff15 100644
--- a/include/linux/dm-log-userspace.h
+++ b/include/linux/dm-log-userspace.h
@@ -370,6 +370,16 @@
 #define DM_ULOG_REQUEST_TYPE(request_type) \
 	(DM_ULOG_REQUEST_MASK & (request_type))
 
+/*
+ * DM_ULOG_REQUEST_VERSION is incremented when there is a
+ * change to the way information is passed between kernel
+ * and userspace.  This could be a structure change of
+ * dm_ulog_request or a change in the way requests are
+ * issued/handled.  Changes are outlined here:
+ *	version 1:  Initial implementation
+ */
+#define DM_ULOG_REQUEST_VERSION 1
+
 struct dm_ulog_request {
 	/*
 	 * The local unique identifier (luid) and the universally unique
@@ -383,8 +393,9 @@ struct dm_ulog_request {
 	 */
 	uint64_t luid;
 	char uuid[DM_UUID_LEN];
-	char padding[7];        /* Padding because DM_UUID_LEN = 129 */
+	char padding[3];        /* Padding because DM_UUID_LEN = 129 */
 
+	uint32_t version;       /* See DM_ULOG_REQUEST_VERSION */
 	int32_t error;          /* Used to report back processing errors */
 
 	uint32_t seq;           /* Sequence number for request */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index f54adfcbec9c..a3b148a91874 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -34,6 +34,7 @@ struct vm_area_struct;
 #else
 #define ___GFP_NOTRACK		0
 #endif
+#define ___GFP_NO_KSWAPD	0x400000u
 
 /*
  * GFP bitmasks..
@@ -81,13 +82,15 @@ 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)
+
 /*
  * This may seem redundant, but it's a way of annotating false positives vs.
  * allocations that simply cannot be supported (e.g. page tables).
  */
 #define __GFP_NOTRACK_FALSE_POSITIVE (__GFP_NOTRACK)
 
-#define __GFP_BITS_SHIFT 22	/* Room for 22 __GFP_FOO bits */
+#define __GFP_BITS_SHIFT 23	/* Room for 23 __GFP_FOO bits */
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /* This equals 0, but use constants in case they ever change */
@@ -106,6 +109,9 @@ struct vm_area_struct;
 				 __GFP_HARDWALL | __GFP_HIGHMEM | \
 				 __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)
 
 #ifdef CONFIG_NUMA
 #define GFP_THISNODE	(__GFP_THISNODE | __GFP_NOWARN | __GFP_NORETRY)
@@ -325,14 +331,17 @@ alloc_pages(gfp_t gfp_mask, unsigned int order)
 {
 	return alloc_pages_current(gfp_mask, order);
 }
-extern struct page *alloc_page_vma(gfp_t gfp_mask,
+extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order,
 			struct vm_area_struct *vma, unsigned long addr);
 #else
 #define alloc_pages(gfp_mask, order) \
 		alloc_pages_node(numa_node_id(), gfp_mask, order)
-#define alloc_page_vma(gfp_mask, vma, addr) alloc_pages(gfp_mask, 0)
+#define alloc_pages_vma(gfp_mask, order, vma, addr)	\
+	alloc_pages(gfp_mask, order)
 #endif
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
+#define alloc_page_vma(gfp_mask, vma, addr)	\
+	alloc_pages_vma(gfp_mask, 0, vma, addr)
 
 extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
 extern unsigned long get_zeroed_page(gfp_t gfp_mask);
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index f79d67f413e4..4b47ed96f131 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -30,7 +30,7 @@ static inline int gpio_is_valid(int number)
 	return 0;
 }
 
-static inline int __must_check gpio_request(unsigned gpio, const char *label)
+static inline int gpio_request(unsigned gpio, const char *label)
 {
 	return -ENOSYS;
 }
@@ -62,12 +62,12 @@ static inline void gpio_free_array(struct gpio *array, size_t num)
 	WARN_ON(1);
 }
 
-static inline int __must_check gpio_direction_input(unsigned gpio)
+static inline int gpio_direction_input(unsigned gpio)
 {
 	return -ENOSYS;
 }
 
-static inline int __must_check gpio_direction_output(unsigned gpio, int value)
+static inline int gpio_direction_output(unsigned gpio, int value)
 {
 	return -ENOSYS;
 }
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
new file mode 100644
index 000000000000..8e6c8c42bc3c
--- /dev/null
+++ b/include/linux/huge_mm.h
@@ -0,0 +1,179 @@
+#ifndef _LINUX_HUGE_MM_H
+#define _LINUX_HUGE_MM_H
+
+extern int do_huge_pmd_anonymous_page(struct mm_struct *mm,
+				      struct vm_area_struct *vma,
+				      unsigned long address, pmd_t *pmd,
+				      unsigned int flags);
+extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+			 pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
+			 struct vm_area_struct *vma);
+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,
+					  unsigned long addr,
+					  pmd_t *pmd,
+					  unsigned int flags);
+extern int zap_huge_pmd(struct mmu_gather *tlb,
+			struct vm_area_struct *vma,
+			pmd_t *pmd);
+extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, unsigned long end,
+			unsigned char *vec);
+extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+			unsigned long addr, pgprot_t newprot);
+
+enum transparent_hugepage_flag {
+	TRANSPARENT_HUGEPAGE_FLAG,
+	TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG,
+	TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG,
+#ifdef CONFIG_DEBUG_VM
+	TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG,
+#endif
+};
+
+enum page_check_address_pmd_flag {
+	PAGE_CHECK_ADDRESS_PMD_FLAG,
+	PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG,
+	PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG,
+};
+extern pmd_t *page_check_address_pmd(struct page *page,
+				     struct mm_struct *mm,
+				     unsigned long address,
+				     enum page_check_address_pmd_flag flag);
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define HPAGE_PMD_SHIFT HPAGE_SHIFT
+#define HPAGE_PMD_MASK HPAGE_MASK
+#define HPAGE_PMD_SIZE HPAGE_SIZE
+
+#define transparent_hugepage_enabled(__vma)				\
+	((transparent_hugepage_flags &					\
+	  (1<<TRANSPARENT_HUGEPAGE_FLAG) ||				\
+	  (transparent_hugepage_flags &					\
+	   (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG) &&			\
+	   ((__vma)->vm_flags & VM_HUGEPAGE))) &&			\
+	 !((__vma)->vm_flags & VM_NOHUGEPAGE))
+#define transparent_hugepage_defrag(__vma)				\
+	((transparent_hugepage_flags &					\
+	  (1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)) ||			\
+	 (transparent_hugepage_flags &					\
+	  (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG) &&		\
+	  (__vma)->vm_flags & VM_HUGEPAGE))
+#ifdef CONFIG_DEBUG_VM
+#define transparent_hugepage_debug_cow()				\
+	(transparent_hugepage_flags &					\
+	 (1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG))
+#else /* CONFIG_DEBUG_VM */
+#define transparent_hugepage_debug_cow() 0
+#endif /* CONFIG_DEBUG_VM */
+
+extern unsigned long transparent_hugepage_flags;
+extern int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm,
+			  pmd_t *dst_pmd, pmd_t *src_pmd,
+			  struct vm_area_struct *vma,
+			  unsigned long addr, unsigned long end);
+extern int handle_pte_fault(struct mm_struct *mm,
+			    struct vm_area_struct *vma, unsigned long address,
+			    pte_t *pte, pmd_t *pmd, unsigned int flags);
+extern int split_huge_page(struct page *page);
+extern void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd);
+#define split_huge_page_pmd(__mm, __pmd)				\
+	do {								\
+		pmd_t *____pmd = (__pmd);				\
+		if (unlikely(pmd_trans_huge(*____pmd)))			\
+			__split_huge_page_pmd(__mm, ____pmd);		\
+	}  while (0)
+#define wait_split_huge_page(__anon_vma, __pmd)				\
+	do {								\
+		pmd_t *____pmd = (__pmd);				\
+		spin_unlock_wait(&(__anon_vma)->root->lock);		\
+		/*							\
+		 * spin_unlock_wait() is just a loop in C and so the	\
+		 * CPU can reorder anything around it.			\
+		 */							\
+		smp_mb();						\
+		BUG_ON(pmd_trans_splitting(*____pmd) ||			\
+		       pmd_trans_huge(*____pmd));			\
+	} while (0)
+#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
+#if HPAGE_PMD_ORDER > MAX_ORDER
+#error "hugepages can't be allocated by the buddy allocator"
+#endif
+extern int hugepage_madvise(struct vm_area_struct *vma,
+			    unsigned long *vm_flags, int advice);
+extern void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+				    unsigned long start,
+				    unsigned long end,
+				    long adjust_next);
+static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
+					 unsigned long start,
+					 unsigned long end,
+					 long adjust_next)
+{
+	if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
+		return;
+	__vma_adjust_trans_huge(vma, start, end, adjust_next);
+}
+static inline int hpage_nr_pages(struct page *page)
+{
+	if (unlikely(PageTransHuge(page)))
+		return HPAGE_PMD_NR;
+	return 1;
+}
+static inline struct page *compound_trans_head(struct page *page)
+{
+	if (PageTail(page)) {
+		struct page *head;
+		head = page->first_page;
+		smp_rmb();
+		/*
+		 * head may be a dangling pointer.
+		 * __split_huge_page_refcount clears PageTail before
+		 * overwriting first_page, so if PageTail is still
+		 * there it means the head pointer isn't dangling.
+		 */
+		if (PageTail(page))
+			return head;
+	}
+	return page;
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+#define HPAGE_PMD_SHIFT ({ BUG(); 0; })
+#define HPAGE_PMD_MASK ({ BUG(); 0; })
+#define HPAGE_PMD_SIZE ({ BUG(); 0; })
+
+#define hpage_nr_pages(x) 1
+
+#define transparent_hugepage_enabled(__vma) 0
+
+#define transparent_hugepage_flags 0UL
+static inline int split_huge_page(struct page *page)
+{
+	return 0;
+}
+#define split_huge_page_pmd(__mm, __pmd)	\
+	do { } while (0)
+#define wait_split_huge_page(__anon_vma, __pmd)	\
+	do { } while (0)
+#define compound_trans_head(page) compound_head(page)
+static inline int hugepage_madvise(struct vm_area_struct *vma,
+				   unsigned long *vm_flags, int advice)
+{
+	BUG();
+	return 0;
+}
+static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
+					 unsigned long start,
+					 unsigned long end,
+					 long adjust_next)
+{
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 979c68cc7458..6a64c6fa81af 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -57,7 +57,7 @@ struct irq_desc {
 #endif
 
 	struct timer_rand_state *timer_rand_state;
-	unsigned int		*kstat_irqs;
+	unsigned int __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
 	struct irqaction	*action;	/* IRQ action list */
 	unsigned int		status;		/* IRQ status */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 57dac7022b63..5a9d9059520b 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -600,6 +600,13 @@ struct sysinfo {
 #define NUMA_BUILD 0
 #endif
 
+/* This helps us avoid #ifdef CONFIG_COMPACTION */
+#ifdef CONFIG_COMPACTION
+#define COMPACTION_BUILD 1
+#else
+#define COMPACTION_BUILD 0
+#endif
+
 /* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 # define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 44e83ba12b5b..0cce2db580c3 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -46,16 +46,14 @@ DECLARE_PER_CPU(struct kernel_stat, kstat);
 extern unsigned long long nr_context_switches(void);
 
 #ifndef CONFIG_GENERIC_HARDIRQS
-#define kstat_irqs_this_cpu(irq) \
-	(this_cpu_read(kstat.irqs[irq])
 
 struct irq_desc;
 
 static inline void kstat_incr_irqs_this_cpu(unsigned int irq,
 					    struct irq_desc *desc)
 {
-	kstat_this_cpu.irqs[irq]++;
-	kstat_this_cpu.irqs_sum++;
+	__this_cpu_inc(kstat.irqs[irq]);
+	__this_cpu_inc(kstat.irqs_sum);
 }
 
 static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
@@ -65,17 +63,18 @@ static inline unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
 #else
 #include <linux/irq.h>
 extern unsigned int kstat_irqs_cpu(unsigned int irq, int cpu);
-#define kstat_irqs_this_cpu(DESC) \
-	((DESC)->kstat_irqs[smp_processor_id()])
-#define kstat_incr_irqs_this_cpu(irqno, DESC) do {\
-	((DESC)->kstat_irqs[smp_processor_id()]++);\
-	kstat_this_cpu.irqs_sum++; } while (0)
+
+#define kstat_incr_irqs_this_cpu(irqno, DESC)		\
+do {							\
+	__this_cpu_inc(*(DESC)->kstat_irqs);		\
+	__this_cpu_inc(kstat.irqs_sum);			\
+} while (0)
 
 #endif
 
 static inline void kstat_incr_softirqs_this_cpu(unsigned int irq)
 {
-	kstat_this_cpu.softirqs[irq]++;
+	__this_cpu_inc(kstat.softirqs[irq]);
 }
 
 static inline unsigned int kstat_softirqs_cpu(unsigned int irq, int cpu)
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
new file mode 100644
index 000000000000..6b394f0b5148
--- /dev/null
+++ b/include/linux/khugepaged.h
@@ -0,0 +1,67 @@
+#ifndef _LINUX_KHUGEPAGED_H
+#define _LINUX_KHUGEPAGED_H
+
+#include <linux/sched.h> /* MMF_VM_HUGEPAGE */
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern int __khugepaged_enter(struct mm_struct *mm);
+extern void __khugepaged_exit(struct mm_struct *mm);
+extern int khugepaged_enter_vma_merge(struct vm_area_struct *vma);
+
+#define khugepaged_enabled()					       \
+	(transparent_hugepage_flags &				       \
+	 ((1<<TRANSPARENT_HUGEPAGE_FLAG) |		       \
+	  (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
+#define khugepaged_always()				\
+	(transparent_hugepage_flags &			\
+	 (1<<TRANSPARENT_HUGEPAGE_FLAG))
+#define khugepaged_req_madv()					\
+	(transparent_hugepage_flags &				\
+	 (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG))
+#define khugepaged_defrag()					\
+	(transparent_hugepage_flags &				\
+	 (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG))
+
+static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags))
+		return __khugepaged_enter(mm);
+	return 0;
+}
+
+static inline void khugepaged_exit(struct mm_struct *mm)
+{
+	if (test_bit(MMF_VM_HUGEPAGE, &mm->flags))
+		__khugepaged_exit(mm);
+}
+
+static inline int khugepaged_enter(struct vm_area_struct *vma)
+{
+	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags))
+		if ((khugepaged_always() ||
+		     (khugepaged_req_madv() &&
+		      vma->vm_flags & VM_HUGEPAGE)) &&
+		    !(vma->vm_flags & VM_NOHUGEPAGE))
+			if (__khugepaged_enter(vma->vm_mm))
+				return -ENOMEM;
+	return 0;
+}
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+static inline int khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	return 0;
+}
+static inline void khugepaged_exit(struct mm_struct *mm)
+{
+}
+static inline int khugepaged_enter(struct vm_area_struct *vma)
+{
+	return 0;
+}
+static inline int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+{
+	return 0;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+#endif /* _LINUX_KHUGEPAGED_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 159a0762aeaf..6a576f989437 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -25,6 +25,11 @@ struct page_cgroup;
 struct page;
 struct mm_struct;
 
+/* Stats that can be updated by kernel. */
+enum mem_cgroup_page_stat_item {
+	MEMCG_NR_FILE_MAPPED, /* # of pages charged as file rss */
+};
+
 extern unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
@@ -93,7 +98,7 @@ extern int
 mem_cgroup_prepare_migration(struct page *page,
 	struct page *newpage, struct mem_cgroup **ptr);
 extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
-	struct page *oldpage, struct page *newpage);
+	struct page *oldpage, struct page *newpage, bool migration_ok);
 
 /*
  * For memory reclaim.
@@ -121,7 +126,22 @@ static inline bool mem_cgroup_disabled(void)
 	return false;
 }
 
-void mem_cgroup_update_file_mapped(struct page *page, int val);
+void mem_cgroup_update_page_stat(struct page *page,
+				 enum mem_cgroup_page_stat_item idx,
+				 int val);
+
+static inline void mem_cgroup_inc_page_stat(struct page *page,
+					    enum mem_cgroup_page_stat_item idx)
+{
+	mem_cgroup_update_page_stat(page, idx, 1);
+}
+
+static inline void mem_cgroup_dec_page_stat(struct page *page,
+					    enum mem_cgroup_page_stat_item idx)
+{
+	mem_cgroup_update_page_stat(page, idx, -1);
+}
+
 unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order,
 						gfp_t gfp_mask);
 u64 mem_cgroup_get_limit(struct mem_cgroup *mem);
@@ -231,8 +251,7 @@ mem_cgroup_prepare_migration(struct page *page, struct page *newpage,
 }
 
 static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
-					struct page *oldpage,
-					struct page *newpage)
+		struct page *oldpage, struct page *newpage, bool migration_ok)
 {
 }
 
@@ -293,8 +312,13 @@ mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
 }
 
-static inline void mem_cgroup_update_file_mapped(struct page *page,
-							int val)
+static inline void mem_cgroup_inc_page_stat(struct page *page,
+					    enum mem_cgroup_page_stat_item idx)
+{
+}
+
+static inline void mem_cgroup_dec_page_stat(struct page *page,
+					    enum mem_cgroup_page_stat_item idx)
 {
 }
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 31c237a00c48..24376fe7ee68 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -13,12 +13,16 @@ struct mem_section;
 #ifdef CONFIG_MEMORY_HOTPLUG
 
 /*
- * Types for free bootmem.
- * The normal smallest mapcount is -1. Here is smaller value than it.
+ * Types for free bootmem stored in page->lru.next. These have to be in
+ * some random range in unsigned long space for debugging purposes.
  */
-#define SECTION_INFO		(-1 - 1)
-#define MIX_SECTION_INFO	(-1 - 2)
-#define NODE_INFO		(-1 - 3)
+enum {
+	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
+	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
+	MIX_SECTION_INFO,
+	NODE_INFO,
+	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
+};
 
 /*
  * pgdat resizing functions
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 085527fb8261..e39aeecfe9a2 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -13,9 +13,11 @@ extern void putback_lru_pages(struct list_head *l);
 extern int migrate_page(struct address_space *,
 			struct page *, struct page *);
 extern int migrate_pages(struct list_head *l, new_page_t x,
-			unsigned long private, int offlining);
+			unsigned long private, bool offlining,
+			bool sync);
 extern int migrate_huge_pages(struct list_head *l, new_page_t x,
-			unsigned long private, int offlining);
+			unsigned long private, bool offlining,
+			bool sync);
 
 extern int fail_migrate_page(struct address_space *,
 			struct page *, struct page *);
@@ -33,9 +35,11 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 static inline void putback_lru_pages(struct list_head *l) {}
 static inline int migrate_pages(struct list_head *l, new_page_t x,
-		unsigned long private, int offlining) { return -ENOSYS; }
+		unsigned long private, bool offlining,
+		bool sync) { return -ENOSYS; }
 static inline int migrate_huge_pages(struct list_head *l, new_page_t x,
-		unsigned long private, int offlining) { return -ENOSYS; }
+		unsigned long private, bool offlining,
+		bool sync) { return -ENOSYS; }
 
 static inline int migrate_prep(void) { return -ENOSYS; }
 static inline int migrate_prep_local(void) { return -ENOSYS; }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 721f451c3029..956a35532f47 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -14,6 +14,7 @@
 #include <linux/mm_types.h>
 #include <linux/range.h>
 #include <linux/pfn.h>
+#include <linux/bit_spinlock.h>
 
 struct mempolicy;
 struct anon_vma;
@@ -82,6 +83,7 @@ extern unsigned int kobjsize(const void *objp);
 #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.. */
@@ -101,7 +103,11 @@ extern unsigned int kobjsize(const void *objp);
 #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_ALWAYSDUMP	0x04000000	/* Always include in core dumps */
 
@@ -242,6 +248,7 @@ struct inode;
  * files which need it (119 of them)
  */
 #include <linux/page-flags.h>
+#include <linux/huge_mm.h>
 
 /*
  * Methods to modify the page usage count.
@@ -305,6 +312,39 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 }
 #endif
 
+static inline void compound_lock(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	bit_spin_lock(PG_compound_lock, &page->flags);
+#endif
+}
+
+static inline void compound_unlock(struct page *page)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	bit_spin_unlock(PG_compound_lock, &page->flags);
+#endif
+}
+
+static inline unsigned long compound_lock_irqsave(struct page *page)
+{
+	unsigned long uninitialized_var(flags);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	local_irq_save(flags);
+	compound_lock(page);
+#endif
+	return flags;
+}
+
+static inline void compound_unlock_irqrestore(struct page *page,
+					      unsigned long flags)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	compound_unlock(page);
+	local_irq_restore(flags);
+#endif
+}
+
 static inline struct page *compound_head(struct page *page)
 {
 	if (unlikely(PageTail(page)))
@@ -319,9 +359,29 @@ static inline int page_count(struct page *page)
 
 static inline void get_page(struct page *page)
 {
-	page = compound_head(page);
-	VM_BUG_ON(atomic_read(&page->_count) == 0);
+	/*
+	 * Getting a normal page or the head of a compound page
+	 * requires to already have an elevated page->_count. Only if
+	 * we're getting a tail page, the elevated page->_count is
+	 * required only in the head page, so for tail pages the
+	 * bugcheck only verifies that the page->_count isn't
+	 * negative.
+	 */
+	VM_BUG_ON(atomic_read(&page->_count) < !PageTail(page));
 	atomic_inc(&page->_count);
+	/*
+	 * Getting a tail page will elevate both the head and tail
+	 * page->_count(s).
+	 */
+	if (unlikely(PageTail(page))) {
+		/*
+		 * This is safe only because
+		 * __split_huge_page_refcount can't run under
+		 * get_page().
+		 */
+		VM_BUG_ON(atomic_read(&page->first_page->_count) <= 0);
+		atomic_inc(&page->first_page->_count);
+	}
 }
 
 static inline struct page *virt_to_head_page(const void *x)
@@ -339,6 +399,27 @@ static inline void init_page_count(struct page *page)
 	atomic_set(&page->_count, 1);
 }
 
+/*
+ * PageBuddy() indicate that the page is free and in the buddy system
+ * (see mm/page_alloc.c).
+ */
+static inline int PageBuddy(struct page *page)
+{
+	return atomic_read(&page->_mapcount) == -2;
+}
+
+static inline void __SetPageBuddy(struct page *page)
+{
+	VM_BUG_ON(atomic_read(&page->_mapcount) != -1);
+	atomic_set(&page->_mapcount, -2);
+}
+
+static inline void __ClearPageBuddy(struct page *page)
+{
+	VM_BUG_ON(!PageBuddy(page));
+	atomic_set(&page->_mapcount, -1);
+}
+
 void put_page(struct page *page);
 void put_pages_list(struct list_head *pages);
 
@@ -370,12 +451,39 @@ static inline int compound_order(struct page *page)
 	return (unsigned long)page[1].lru.prev;
 }
 
+static inline int compound_trans_order(struct page *page)
+{
+	int order;
+	unsigned long flags;
+
+	if (!PageHead(page))
+		return 0;
+
+	flags = compound_lock_irqsave(page);
+	order = compound_order(page);
+	compound_unlock_irqrestore(page, flags);
+	return order;
+}
+
 static inline void set_compound_order(struct page *page, unsigned long order)
 {
 	page[1].lru.prev = (void *)order;
 }
 
 /*
+ * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
+ * servicing faults for write access.  In the normal case, do always want
+ * pte_mkwrite.  But get_user_pages can cause write faults for mappings
+ * that do not have writing enabled, when used by access_process_vm.
+ */
+static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pte = pte_mkwrite(pte);
+	return pte;
+}
+
+/*
  * Multiple processes may "see" the same page. E.g. for untouched
  * mappings of /dev/null, all processes see the same page full of
  * zeroes, and text pages of executables and shared libraries have
@@ -657,7 +765,7 @@ static inline struct address_space *page_mapping(struct page *page)
 	VM_BUG_ON(PageSlab(page));
 	if (unlikely(PageSwapCache(page)))
 		mapping = &swapper_space;
-	else if (unlikely((unsigned long)mapping & PAGE_MAPPING_ANON))
+	else if ((unsigned long)mapping & PAGE_MAPPING_ANON)
 		mapping = NULL;
 	return mapping;
 }
@@ -1064,7 +1172,8 @@ static inline int __pmd_alloc(struct mm_struct *mm, pud_t *pud,
 int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address);
 #endif
 
-int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address);
+int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
+		pmd_t *pmd, unsigned long address);
 int __pte_alloc_kernel(pmd_t *pmd, unsigned long address);
 
 /*
@@ -1133,16 +1242,18 @@ static inline void pgtable_page_dtor(struct page *page)
 	pte_unmap(pte);					\
 } while (0)
 
-#define pte_alloc_map(mm, pmd, address)			\
-	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
-		NULL: pte_offset_map(pmd, address))
+#define pte_alloc_map(mm, vma, pmd, address)				\
+	((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, vma,	\
+							pmd, address))?	\
+	 NULL: pte_offset_map(pmd, address))
 
 #define pte_alloc_map_lock(mm, pmd, address, ptlp)	\
-	((unlikely(!pmd_present(*(pmd))) && __pte_alloc(mm, pmd, address))? \
+	((unlikely(pmd_none(*(pmd))) && __pte_alloc(mm, NULL,	\
+							pmd, address))?	\
 		NULL: pte_offset_map_lock(mm, pmd, address, ptlp))
 
 #define pte_alloc_kernel(pmd, address)			\
-	((unlikely(!pmd_present(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
+	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd, address))? \
 		NULL: pte_offset_kernel(pmd, address))
 
 extern void free_area_init(unsigned long * zones_size);
@@ -1415,6 +1526,8 @@ struct page *follow_page(struct vm_area_struct *, unsigned long address,
 #define FOLL_GET	0x04	/* do get_page on page */
 #define FOLL_DUMP	0x08	/* give error on hole if it would be zero */
 #define FOLL_FORCE	0x10	/* get_user_pages read/write w/o permission */
+#define FOLL_MLOCK	0x40	/* mark page as mlocked */
+#define FOLL_SPLIT	0x80	/* don't return transhuge pages, split them */
 
 typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
 			void *data);
@@ -1518,5 +1631,14 @@ static inline int is_hwpoison_address(unsigned long addr)
 
 extern void dump_page(struct page *page);
 
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
+extern void clear_huge_page(struct page *page,
+			    unsigned long addr,
+			    unsigned int pages_per_huge_page);
+extern void copy_user_huge_page(struct page *dst, struct page *src,
+				unsigned long addr, struct vm_area_struct *vma,
+				unsigned int pages_per_huge_page);
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 8835b877b8db..8f7d24712dc1 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -1,6 +1,8 @@
 #ifndef LINUX_MM_INLINE_H
 #define LINUX_MM_INLINE_H
 
+#include <linux/huge_mm.h>
+
 /**
  * page_is_file_cache - should the page be on a file LRU or anon LRU?
  * @page: the page to test
@@ -20,18 +22,25 @@ static inline int page_is_file_cache(struct page *page)
 }
 
 static inline void
-add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
+__add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l,
+		       struct list_head *head)
 {
-	list_add(&page->lru, &zone->lru[l].list);
-	__inc_zone_state(zone, NR_LRU_BASE + l);
+	list_add(&page->lru, head);
+	__mod_zone_page_state(zone, NR_LRU_BASE + l, hpage_nr_pages(page));
 	mem_cgroup_add_lru_list(page, l);
 }
 
 static inline void
+add_page_to_lru_list(struct zone *zone, struct page *page, enum lru_list l)
+{
+	__add_page_to_lru_list(zone, page, l, &zone->lru[l].list);
+}
+
+static inline void
 del_page_from_lru_list(struct zone *zone, struct page *page, enum lru_list l)
 {
 	list_del(&page->lru);
-	__dec_zone_state(zone, NR_LRU_BASE + l);
+	__mod_zone_page_state(zone, NR_LRU_BASE + l, -hpage_nr_pages(page));
 	mem_cgroup_del_lru_list(page, l);
 }
 
@@ -66,7 +75,7 @@ del_page_from_lru(struct zone *zone, struct page *page)
 			l += LRU_ACTIVE;
 		}
 	}
-	__dec_zone_state(zone, NR_LRU_BASE + l);
+	__mod_zone_page_state(zone, NR_LRU_BASE + l, -hpage_nr_pages(page));
 	mem_cgroup_del_lru_list(page, l);
 }
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bb7288a782fd..26bc4e2cd275 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -310,6 +310,9 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
 	struct mmu_notifier_mm *mmu_notifier_mm;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	pgtable_t pmd_huge_pte; /* protected by page_table_lock */
+#endif
 	/* How many tasks sharing this mm are OOM_DISABLE */
 	atomic_t oom_disable_count;
 };
diff --git a/include/linux/mmc/sh_mmcif.h b/include/linux/mmc/sh_mmcif.h
index bf173502d744..38d393092812 100644
--- a/include/linux/mmc/sh_mmcif.h
+++ b/include/linux/mmc/sh_mmcif.h
@@ -94,12 +94,12 @@ struct sh_mmcif_plat_data {
 
 static inline u32 sh_mmcif_readl(void __iomem *addr, int reg)
 {
-	return readl(addr + reg);
+	return __raw_readl(addr + reg);
 }
 
 static inline void sh_mmcif_writel(void __iomem *addr, int reg, u32 val)
 {
-	writel(val, addr + reg);
+	__raw_writel(val, addr + reg);
 }
 
 #define SH_MMCIF_BBS 512 /* boot block size */
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 43dcfbdc39de..cc2e7dfea9d7 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -62,6 +62,16 @@ struct mmu_notifier_ops {
 				 unsigned long address);
 
 	/*
+	 * test_young is called to check the young/accessed bitflag in
+	 * the secondary pte. This is used to know if the page is
+	 * frequently used without actually clearing the flag or tearing
+	 * down the secondary mapping on the page.
+	 */
+	int (*test_young)(struct mmu_notifier *mn,
+			  struct mm_struct *mm,
+			  unsigned long address);
+
+	/*
 	 * change_pte is called in cases that pte mapping to page is changed:
 	 * for example, when ksm remaps pte to point to a new shared page.
 	 */
@@ -163,6 +173,8 @@ extern void __mmu_notifier_mm_destroy(struct mm_struct *mm);
 extern void __mmu_notifier_release(struct mm_struct *mm);
 extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 					  unsigned long address);
+extern int __mmu_notifier_test_young(struct mm_struct *mm,
+				     unsigned long address);
 extern void __mmu_notifier_change_pte(struct mm_struct *mm,
 				      unsigned long address, pte_t pte);
 extern void __mmu_notifier_invalidate_page(struct mm_struct *mm,
@@ -186,6 +198,14 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mmu_notifier_test_young(struct mm_struct *mm,
+					  unsigned long address)
+{
+	if (mm_has_notifiers(mm))
+		return __mmu_notifier_test_young(mm, address);
+	return 0;
+}
+
 static inline void mmu_notifier_change_pte(struct mm_struct *mm,
 					   unsigned long address, pte_t pte)
 {
@@ -243,6 +263,32 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	__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;							\
@@ -254,6 +300,17 @@ static inline void mmu_notifier_mm_destroy(struct mm_struct *mm)
 	__young;							\
 })
 
+#define pmdp_clear_flush_young_notify(__vma, __address, __pmdp)		\
+({									\
+	int __young;							\
+	struct vm_area_struct *___vma = __vma;				\
+	unsigned long ___address = __address;				\
+	__young = pmdp_clear_flush_young(___vma, ___address, __pmdp);	\
+	__young |= mmu_notifier_clear_flush_young(___vma->vm_mm,	\
+						  ___address);		\
+	__young;							\
+})
+
 #define set_pte_at_notify(__mm, __address, __ptep, __pte)		\
 ({									\
 	struct mm_struct *___mm = __mm;					\
@@ -276,6 +333,12 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	return 0;
 }
 
+static inline int mmu_notifier_test_young(struct mm_struct *mm,
+					  unsigned long address)
+{
+	return 0;
+}
+
 static inline void mmu_notifier_change_pte(struct mm_struct *mm,
 					   unsigned long address, pte_t pte)
 {
@@ -305,7 +368,10 @@ 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 39c24ebe9cfd..02ecb0189b1d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -114,6 +114,7 @@ enum zone_stat_item {
 	NUMA_LOCAL,		/* allocation from local node */
 	NUMA_OTHER,		/* allocation from other node */
 #endif
+	NR_ANON_TRANSPARENT_HUGEPAGES,
 	NR_VM_ZONE_STAT_ITEMS };
 
 /*
@@ -458,12 +459,6 @@ static inline int zone_is_oom_locked(const struct zone *zone)
 	return test_bit(ZONE_OOM_LOCKED, &zone->flags);
 }
 
-#ifdef CONFIG_SMP
-unsigned long zone_nr_free_pages(struct zone *zone);
-#else
-#define zone_nr_free_pages(zone) zone_page_state(zone, NR_FREE_PAGES)
-#endif /* CONFIG_SMP */
-
 /*
  * The "priority" of VM scanning is how much of the queues we will scan in one
  * go. A value of 12 for DEF_PRIORITY implies that we will scan 1/4096th of the
@@ -645,6 +640,7 @@ typedef struct pglist_data {
 	wait_queue_head_t kswapd_wait;
 	struct task_struct *kswapd;
 	int kswapd_max_order;
+	enum zone_type classzone_idx;
 } pg_data_t;
 
 #define node_present_pages(nid)	(NODE_DATA(nid)->node_present_pages)
@@ -660,8 +656,10 @@ typedef struct pglist_data {
 
 extern struct mutex zonelists_mutex;
 void build_all_zonelists(void *data);
-void wakeup_kswapd(struct zone *zone, int order);
-int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx);
+bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		int classzone_idx, int alloc_flags);
+bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
 		int classzone_idx, int alloc_flags);
 enum memmap_context {
 	MEMMAP_EARLY,
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 5f38c460367e..0db8037e2725 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -48,9 +48,6 @@
  * struct page (these bits with information) are always mapped into kernel
  * address space...
  *
- * PG_buddy is set to indicate that the page is free and in the buddy system
- * (see mm/page_alloc.c).
- *
  * PG_hwpoison indicates that a page got corrupted in hardware and contains
  * data with incorrect ECC bits that triggered a machine check. Accessing is
  * not safe since it may cause another machine check. Don't touch!
@@ -96,7 +93,6 @@ enum pageflags {
 	PG_swapcache,		/* Swap page: swp_entry_t in private */
 	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
-	PG_buddy,		/* Page is free, on buddy lists */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
 #ifdef CONFIG_MMU
@@ -108,6 +104,9 @@ enum pageflags {
 #ifdef CONFIG_MEMORY_FAILURE
 	PG_hwpoison,		/* hardware poisoned page. Don't touch */
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	PG_compound_lock,
+#endif
 	__NR_PAGEFLAGS,
 
 	/* Filesystems */
@@ -198,7 +197,7 @@ static inline int __TestClearPage##uname(struct page *page) { return 0; }
 struct page;	/* forward declaration */
 
 TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked)
-PAGEFLAG(Error, error)
+PAGEFLAG(Error, error) TESTCLEARFLAG(Error, error)
 PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
 PAGEFLAG(LRU, lru) __CLEARPAGEFLAG(LRU, lru)
@@ -230,7 +229,6 @@ PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
  * risky: they bypass page accounting.
  */
 TESTPAGEFLAG(Writeback, writeback) TESTSCFLAG(Writeback, writeback)
-__PAGEFLAG(Buddy, buddy)
 PAGEFLAG(MappedToDisk, mappedtodisk)
 
 /* PG_readahead is only used for file reads; PG_reclaim is only for writes */
@@ -344,7 +342,7 @@ static inline void set_page_writeback(struct page *page)
  * tests can be used in performance sensitive paths. PageCompound is
  * generally not used in hot code paths.
  */
-__PAGEFLAG(Head, head)
+__PAGEFLAG(Head, head) CLEARPAGEFLAG(Head, head)
 __PAGEFLAG(Tail, tail)
 
 static inline int PageCompound(struct page *page)
@@ -352,6 +350,13 @@ static inline int PageCompound(struct page *page)
 	return page->flags & ((1L << PG_head) | (1L << PG_tail));
 
 }
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void ClearPageCompound(struct page *page)
+{
+	BUG_ON(!PageHead(page));
+	ClearPageHead(page);
+}
+#endif
 #else
 /*
  * Reduce page flag use as much as possible by overlapping
@@ -389,14 +394,61 @@ static inline void __ClearPageTail(struct page *page)
 	page->flags &= ~PG_head_tail_mask;
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static inline void ClearPageCompound(struct page *page)
+{
+	BUG_ON((page->flags & PG_head_tail_mask) != (1 << PG_compound));
+	clear_bit(PG_compound, &page->flags);
+}
+#endif
+
 #endif /* !PAGEFLAGS_EXTENDED */
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * PageHuge() only returns true for hugetlbfs pages, but not for
+ * normal or transparent huge pages.
+ *
+ * PageTransHuge() returns true for both transparent huge and
+ * hugetlbfs pages, but not normal pages. PageTransHuge() can only be
+ * called only in the core VM paths where hugetlbfs pages can't exist.
+ */
+static inline int PageTransHuge(struct page *page)
+{
+	VM_BUG_ON(PageTail(page));
+	return PageHead(page);
+}
+
+static inline int PageTransCompound(struct page *page)
+{
+	return PageCompound(page);
+}
+
+#else
+
+static inline int PageTransHuge(struct page *page)
+{
+	return 0;
+}
+
+static inline int PageTransCompound(struct page *page)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_MMU
 #define __PG_MLOCKED		(1 << PG_mlocked)
 #else
 #define __PG_MLOCKED		0
 #endif
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define __PG_COMPOUND_LOCK		(1 << PG_compound_lock)
+#else
+#define __PG_COMPOUND_LOCK		0
+#endif
+
 /*
  * Flags checked when a page is freed.  Pages being freed should not have
  * these flags set.  It they are, there is a problem.
@@ -404,9 +456,10 @@ static inline void __ClearPageTail(struct page *page)
 #define PAGE_FLAGS_CHECK_AT_FREE \
 	(1 << PG_lru	 | 1 << PG_locked    | \
 	 1 << PG_private | 1 << PG_private_2 | \
-	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
+	 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
-	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON)
+	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
+	 __PG_COMPOUND_LOCK)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index b02195dfc1b0..5b0c971d7cae 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -35,12 +35,18 @@ struct page_cgroup *lookup_page_cgroup(struct page *page);
 
 enum {
 	/* flags for mem_cgroup */
-	PCG_LOCK,  /* page cgroup is locked */
+	PCG_LOCK,  /* Lock for pc->mem_cgroup and following bits. */
 	PCG_CACHE, /* charged as cache */
 	PCG_USED, /* this object is in use. */
-	PCG_ACCT_LRU, /* page has been accounted for */
-	PCG_FILE_MAPPED, /* page is accounted as "mapped" */
 	PCG_MIGRATION, /* under page migration */
+	/* flags for mem_cgroup and file and I/O status */
+	PCG_MOVE_LOCK, /* For race between move_account v.s. following bits */
+	PCG_FILE_MAPPED, /* page is accounted as "mapped" */
+	PCG_FILE_DIRTY, /* page is dirty */
+	PCG_FILE_WRITEBACK, /* page is under writeback */
+	PCG_FILE_UNSTABLE_NFS, /* page is NFS unstable */
+	/* No lock in page_cgroup */
+	PCG_ACCT_LRU, /* page has been accounted for (under lru_lock) */
 };
 
 #define TESTPCGFLAG(uname, lname)			\
@@ -59,6 +65,10 @@ static inline void ClearPageCgroup##uname(struct page_cgroup *pc)	\
 static inline int TestClearPageCgroup##uname(struct page_cgroup *pc)	\
 	{ return test_and_clear_bit(PCG_##lname, &pc->flags);  }
 
+#define TESTSETPCGFLAG(uname, lname)			\
+static inline int TestSetPageCgroup##uname(struct page_cgroup *pc)	\
+	{ return test_and_set_bit(PCG_##lname, &pc->flags);  }
+
 /* Cache flag is set only once (at allocation) */
 TESTPCGFLAG(Cache, CACHE)
 CLEARPCGFLAG(Cache, CACHE)
@@ -78,6 +88,22 @@ SETPCGFLAG(FileMapped, FILE_MAPPED)
 CLEARPCGFLAG(FileMapped, FILE_MAPPED)
 TESTPCGFLAG(FileMapped, FILE_MAPPED)
 
+SETPCGFLAG(FileDirty, FILE_DIRTY)
+CLEARPCGFLAG(FileDirty, FILE_DIRTY)
+TESTPCGFLAG(FileDirty, FILE_DIRTY)
+TESTCLEARPCGFLAG(FileDirty, FILE_DIRTY)
+TESTSETPCGFLAG(FileDirty, FILE_DIRTY)
+
+SETPCGFLAG(FileWriteback, FILE_WRITEBACK)
+CLEARPCGFLAG(FileWriteback, FILE_WRITEBACK)
+TESTPCGFLAG(FileWriteback, FILE_WRITEBACK)
+
+SETPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS)
+CLEARPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS)
+TESTPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS)
+TESTCLEARPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS)
+TESTSETPCGFLAG(FileUnstableNFS, FILE_UNSTABLE_NFS)
+
 SETPCGFLAG(Migration, MIGRATION)
 CLEARPCGFLAG(Migration, MIGRATION)
 TESTPCGFLAG(Migration, MIGRATION)
@@ -94,6 +120,10 @@ static inline enum zone_type page_cgroup_zid(struct page_cgroup *pc)
 
 static inline void lock_page_cgroup(struct page_cgroup *pc)
 {
+	/*
+	 * Don't take this lock in IRQ context.
+	 * This lock is for pc->mem_cgroup, USED, CACHE, MIGRATION
+	 */
 	bit_spin_lock(PCG_LOCK, &pc->flags);
 }
 
@@ -107,6 +137,24 @@ static inline int page_is_cgroup_locked(struct page_cgroup *pc)
 	return bit_spin_is_locked(PCG_LOCK, &pc->flags);
 }
 
+static inline void move_lock_page_cgroup(struct page_cgroup *pc,
+	unsigned long *flags)
+{
+	/*
+	 * We know updates to pc->flags of page cache's stats are from both of
+	 * usual context or IRQ context. Disable IRQ to avoid deadlock.
+	 */
+	local_irq_save(*flags);
+	bit_spin_lock(PCG_MOVE_LOCK, &pc->flags);
+}
+
+static inline void move_unlock_page_cgroup(struct page_cgroup *pc,
+	unsigned long *flags)
+{
+	bit_spin_unlock(PCG_MOVE_LOCK, &pc->flags);
+	local_irq_restore(*flags);
+}
+
 #else /* CONFIG_CGROUP_MEM_RES_CTLR */
 struct page_cgroup;
 
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 2d1ffe3cf1ee..9c66e994540f 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -48,7 +48,7 @@ static inline void mapping_clear_unevictable(struct address_space *mapping)
 
 static inline int mapping_unevictable(struct address_space *mapping)
 {
-	if (likely(mapping))
+	if (mapping)
 		return test_bit(AS_UNEVICTABLE, &mapping->flags);
 	return !!mapping;
 }
diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h
index ab2baa5c4884..23241c2fecce 100644
--- a/include/linux/radix-tree.h
+++ b/include/linux/radix-tree.h
@@ -146,6 +146,22 @@ static inline void *radix_tree_deref_slot(void **pslot)
 }
 
 /**
+ * radix_tree_deref_slot_protected	- dereference a slot without RCU lock but with tree lock held
+ * @pslot:	pointer to slot, returned by radix_tree_lookup_slot
+ * Returns:	item that was stored in that slot with any direct pointer flag
+ *		removed.
+ *
+ * Similar to radix_tree_deref_slot but only used during migration when a pages
+ * mapping is being moved. The caller does not hold the RCU read lock but it
+ * must hold the tree lock to prevent parallel updates.
+ */
+static inline void *radix_tree_deref_slot_protected(void **pslot,
+							spinlock_t *treelock)
+{
+	return rcu_dereference_protected(*pslot, lockdep_is_held(treelock));
+}
+
+/**
  * radix_tree_deref_retry	- check radix_tree_deref_slot
  * @arg:	pointer returned by radix_tree_deref_slot
  * Returns:	0 if retry is not required, otherwise retry is required
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index bb83c0da2071..e9fd04ca1e51 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -198,6 +198,8 @@ enum ttu_flags {
 };
 #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
 
+bool is_vma_temporary_stack(struct vm_area_struct *vma);
+
 int try_to_unmap(struct page *, enum ttu_flags flags);
 int try_to_unmap_one(struct page *, struct vm_area_struct *,
 			unsigned long address, enum ttu_flags flags);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 96e23215e276..d747f948b34e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -21,7 +21,8 @@
 #define CLONE_DETACHED		0x00400000	/* Unused, ignored */
 #define CLONE_UNTRACED		0x00800000	/* set if the tracing process can't force CLONE_PTRACE on this clone */
 #define CLONE_CHILD_SETTID	0x01000000	/* set the TID in the child */
-#define CLONE_STOPPED		0x02000000	/* Start in stopped state */
+/* 0x02000000 was previously the unused CLONE_STOPPED (Start in stopped state)
+   and is now available for re-use. */
 #define CLONE_NEWUTS		0x04000000	/* New utsname group? */
 #define CLONE_NEWIPC		0x08000000	/* New ipcs */
 #define CLONE_NEWUSER		0x10000000	/* New user namespace */
@@ -433,6 +434,7 @@ extern int get_dumpable(struct mm_struct *mm);
 #endif
 					/* leave room for more dump flags */
 #define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
+#define MMF_VM_HUGEPAGE		17	/* set when VM_HUGEPAGE is set on vma */
 
 #define MMF_INIT_MASK		(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
 
@@ -633,6 +635,8 @@ struct signal_struct {
 
 	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. */
 
 	struct mutex cred_guard_mutex;	/* guard against foreign influences on
 					 * credential calculations
diff --git a/include/linux/swap.h b/include/linux/swap.h
index eba53e71d2cc..4d559325d919 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -208,6 +208,8 @@ extern unsigned int nr_free_pagecache_pages(void);
 /* linux/mm/swap.c */
 extern void __lru_cache_add(struct page *, enum lru_list lru);
 extern void lru_cache_add_lru(struct page *, enum lru_list lru);
+extern void lru_add_page_tail(struct zone* zone,
+			      struct page *page, struct page *page_tail);
 extern void activate_page(struct page *);
 extern void mark_page_accessed(struct page *);
 extern void lru_add_drain(void);
diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h
index 44b54f619ac6..4ed6fcd6b726 100644
--- a/include/linux/vmalloc.h
+++ b/include/linux/vmalloc.h
@@ -59,8 +59,9 @@ extern void *vmalloc_exec(unsigned long size);
 extern void *vmalloc_32(unsigned long size);
 extern void *vmalloc_32_user(unsigned long size);
 extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot);
-extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask,
-				pgprot_t prot);
+extern void *__vmalloc_node_range(unsigned long size, unsigned long align,
+			unsigned long start, unsigned long end, gfp_t gfp_mask,
+			pgprot_t prot, int node, void *caller);
 extern void vfree(const void *addr);
 
 extern void *vmap(struct page **pages, unsigned int count,
@@ -90,9 +91,6 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size,
 					unsigned long flags,
 					unsigned long start, unsigned long end,
 					void *caller);
-extern struct vm_struct *get_vm_area_node(unsigned long size,
-					  unsigned long flags, int node,
-					  gfp_t gfp_mask);
 extern struct vm_struct *remove_vm_area(const void *addr);
 
 extern int map_vm_area(struct vm_struct *area, pgprot_t prot,
@@ -120,7 +118,7 @@ extern __init void vm_area_register_early(struct vm_struct *vm, size_t align);
 #ifdef CONFIG_SMP
 struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 				     const size_t *sizes, int nr_vms,
-				     size_t align, gfp_t gfp_mask);
+				     size_t align);
 
 void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms);
 #endif
diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index eaaea37b3b75..833e676d6d92 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -254,6 +254,11 @@ extern void dec_zone_state(struct zone *, enum zone_stat_item);
 extern void __dec_zone_state(struct zone *, enum zone_stat_item);
 
 void refresh_cpu_vm_stats(int);
+
+int calculate_pressure_threshold(struct zone *zone);
+int calculate_normal_threshold(struct zone *zone);
+void set_pgdat_percpu_threshold(pg_data_t *pgdat,
+				int (*calculate_pressure)(struct zone *));
 #else /* CONFIG_SMP */
 
 /*
@@ -298,6 +303,8 @@ static inline void __dec_zone_page_state(struct page *page,
 #define dec_zone_page_state __dec_zone_page_state
 #define mod_zone_page_state __mod_zone_page_state
 
+#define set_pgdat_percpu_threshold(pgdat, callback) { }
+
 static inline void refresh_cpu_vm_stats(int cpu) { }
 #endif