56 files changed, 7469 insertions, 2472 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index f0fb9124e410..e9c0c61f2ddd 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -179,7 +179,7 @@ config SPLIT_PTLOCK_CPUS
 config COMPACTION
 	bool "Allow for memory compaction"
 	select MIGRATION
-	depends on EXPERIMENTAL && HUGETLB_PAGE && MMU
+	depends on MMU
 	help
 	  Allows the compaction of memory for the allocation of huge pages.
 
@@ -301,3 +301,49 @@ config NOMMU_INITIAL_TRIM_EXCESS
 	  of 1 says that all excess pages should be trimmed.
 
 	  See Documentation/nommu-mmap.txt for more information.
+
+config TRANSPARENT_HUGEPAGE
+	bool "Transparent Hugepage Support"
+	depends on X86 && MMU
+	select COMPACTION
+	help
+	  Transparent Hugepages allows the kernel to use huge pages and
+	  huge tlb transparently to the applications whenever possible.
+	  This feature can improve computing performance to certain
+	  applications by speeding up page faults during memory
+	  allocation, by reducing the number of tlb misses and by speeding
+	  up the pagetable walking.
+
+	  If memory constrained on embedded, you may want to say N.
+
+choice
+	prompt "Transparent Hugepage Support sysfs defaults"
+	depends on TRANSPARENT_HUGEPAGE
+	default TRANSPARENT_HUGEPAGE_ALWAYS
+	help
+	  Selects the sysfs defaults for Transparent Hugepage Support.
+
+	config TRANSPARENT_HUGEPAGE_ALWAYS
+		bool "always"
+	help
+	  Enabling Transparent Hugepage always, can increase the
+	  memory footprint of applications without a guaranteed
+	  benefit but it will work automatically for all applications.
+
+	config TRANSPARENT_HUGEPAGE_MADVISE
+		bool "madvise"
+	help
+	  Enabling Transparent Hugepage madvise, will only provide a
+	  performance improvement benefit to the applications using
+	  madvise(MADV_HUGEPAGE) but it won't risk to increase the
+	  memory footprint of applications without a guaranteed
+	  benefit.
+endchoice
+
+#
+# UP and nommu archs use km based percpu allocator
+#
+config NEED_PER_CPU_KM
+	depends on !SMP
+	bool
+	default y
diff --git a/mm/Makefile b/mm/Makefile
index 34b2546a9e37..2b1b575ae712 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -5,13 +5,13 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o
+			   vmalloc.o pagewalk.o pgtable-generic.o
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   maccess.o page_alloc.o page-writeback.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
-			   page_isolation.o mm_init.o mmu_context.o \
+			   page_isolation.o mm_init.o mmu_context.o percpu.o \
 			   $(mmu-y)
 obj-y += init-mm.o
 
@@ -36,12 +36,8 @@ obj-$(CONFIG_FAILSLAB) += failslab.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
-ifdef CONFIG_SMP
-obj-y += percpu.o
-else
-obj-y += percpu_up.o
-endif
 obj-$(CONFIG_QUICKLIST) += quicklist.o
+obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o
 obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
 obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
 obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
diff --git a/mm/backing-dev.c b/mm/backing-dev.c
index 65d420499a61..027100d30227 100644
--- a/mm/backing-dev.c
+++ b/mm/backing-dev.c
@@ -74,11 +74,11 @@ static int bdi_debug_stats_show(struct seq_file *m, void *v)
 
 	nr_wb = nr_dirty = nr_io = nr_more_io = 0;
 	spin_lock(&inode_lock);
-	list_for_each_entry(inode, &wb->b_dirty, i_list)
+	list_for_each_entry(inode, &wb->b_dirty, i_wb_list)
 		nr_dirty++;
-	list_for_each_entry(inode, &wb->b_io, i_list)
+	list_for_each_entry(inode, &wb->b_io, i_wb_list)
 		nr_io++;
-	list_for_each_entry(inode, &wb->b_more_io, i_list)
+	list_for_each_entry(inode, &wb->b_more_io, i_wb_list)
 		nr_more_io++;
 	spin_unlock(&inode_lock);
 
@@ -362,7 +362,7 @@ static int bdi_forker_thread(void *ptr)
 {
 	struct bdi_writeback *me = ptr;
 
-	current->flags |= PF_FLUSHER | PF_SWAPWRITE;
+	current->flags |= PF_SWAPWRITE;
 	set_freezable();
 
 	/*
@@ -729,6 +729,7 @@ static wait_queue_head_t congestion_wqh[2] = {
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[0]),
 		__WAIT_QUEUE_HEAD_INITIALIZER(congestion_wqh[1])
 	};
+static atomic_t nr_bdi_congested[2];
 
 void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 {
@@ -736,7 +737,8 @@ void clear_bdi_congested(struct backing_dev_info *bdi, int sync)
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	clear_bit(bit, &bdi->state);
+	if (test_and_clear_bit(bit, &bdi->state))
+		atomic_dec(&nr_bdi_congested[sync]);
 	smp_mb__after_clear_bit();
 	if (waitqueue_active(wqh))
 		wake_up(wqh);
@@ -748,7 +750,8 @@ void set_bdi_congested(struct backing_dev_info *bdi, int sync)
 	enum bdi_state bit;
 
 	bit = sync ? BDI_sync_congested : BDI_async_congested;
-	set_bit(bit, &bdi->state);
+	if (!test_and_set_bit(bit, &bdi->state))
+		atomic_inc(&nr_bdi_congested[sync]);
 }
 EXPORT_SYMBOL(set_bdi_congested);
 
@@ -764,13 +767,72 @@ EXPORT_SYMBOL(set_bdi_congested);
 long congestion_wait(int sync, long timeout)
 {
 	long ret;
+	unsigned long start = jiffies;
 	DEFINE_WAIT(wait);
 	wait_queue_head_t *wqh = &congestion_wqh[sync];
 
 	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
 	ret = io_schedule_timeout(timeout);
 	finish_wait(wqh, &wait);
+
+	trace_writeback_congestion_wait(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
 	return ret;
 }
 EXPORT_SYMBOL(congestion_wait);
 
+/**
+ * wait_iff_congested - Conditionally wait for a backing_dev to become uncongested or a zone to complete writes
+ * @zone: A zone to check if it is heavily congested
+ * @sync: SYNC or ASYNC IO
+ * @timeout: timeout in jiffies
+ *
+ * In the event of a congested backing_dev (any backing_dev) and the given
+ * @zone has experienced recent congestion, this waits for up to @timeout
+ * jiffies for either a BDI to exit congestion of the given @sync queue
+ * or a write to complete.
+ *
+ * In the absense of zone congestion, cond_resched() is called to yield
+ * the processor if necessary but otherwise does not sleep.
+ *
+ * The return value is 0 if the sleep is for the full timeout. Otherwise,
+ * it is the number of jiffies that were still remaining when the function
+ * returned. return_value == timeout implies the function did not sleep.
+ */
+long wait_iff_congested(struct zone *zone, int sync, long timeout)
+{
+	long ret;
+	unsigned long start = jiffies;
+	DEFINE_WAIT(wait);
+	wait_queue_head_t *wqh = &congestion_wqh[sync];
+
+	/*
+	 * If there is no congestion, or heavy congestion is not being
+	 * encountered in the current zone, yield if necessary instead
+	 * of sleeping on the congestion queue
+	 */
+	if (atomic_read(&nr_bdi_congested[sync]) == 0 ||
+			!zone_is_reclaim_congested(zone)) {
+		cond_resched();
+
+		/* In case we scheduled, work out time remaining */
+		ret = timeout - (jiffies - start);
+		if (ret < 0)
+			ret = 0;
+
+		goto out;
+	}
+
+	/* Sleep until uncongested or a write happens */
+	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
+	ret = io_schedule_timeout(timeout);
+	finish_wait(wqh, &wait);
+
+out:
+	trace_writeback_wait_iff_congested(jiffies_to_usecs(timeout),
+					jiffies_to_usecs(jiffies - start));
+
+	return ret;
+}
+EXPORT_SYMBOL(wait_iff_congested);
diff --git a/mm/bootmem.c b/mm/bootmem.c
index 142c84a54993..13b0caa9793c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/kmemleak.h>
 #include <linux/range.h>
+#include <linux/memblock.h>
 
 #include <asm/bug.h>
 #include <asm/io.h>
@@ -434,7 +435,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 			      unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(physaddr, physaddr + size);
+	kmemleak_free_part(__va(physaddr), size);
+	memblock_x86_free_range(physaddr, physaddr + size);
 #else
 	unsigned long start, end;
 
@@ -459,7 +461,8 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 void __init free_bootmem(unsigned long addr, unsigned long size)
 {
 #ifdef CONFIG_NO_BOOTMEM
-	free_early(addr, addr + size);
+	kmemleak_free_part(__va(addr), size);
+	memblock_x86_free_range(addr, addr + size);
 #else
 	unsigned long start, end;
 
@@ -526,6 +529,12 @@ int __init reserve_bootmem(unsigned long addr, unsigned long size,
 }
 
 #ifndef CONFIG_NO_BOOTMEM
+int __weak __init reserve_bootmem_generic(unsigned long phys, unsigned long len,
+				   int flags)
+{
+	return reserve_bootmem(phys, len, flags);
+}
+
 static unsigned long __init align_idx(struct bootmem_data *bdata,
 				      unsigned long idx, unsigned long step)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index 4d709ee59013..8be430b812de 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -16,6 +16,9 @@
 #include <linux/sysfs.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/compaction.h>
+
 /*
  * compact_control is used to track pages being migrated and the free pages
  * they are being migrated to during memory compaction. The free_pfn starts
@@ -30,6 +33,7 @@ struct compact_control {
 	unsigned long nr_migratepages;	/* Number of pages to migrate */
 	unsigned long free_pfn;		/* isolate_freepages search base */
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
+	bool sync;			/* Synchronous migration */
 
 	/* Account for isolated anon and file pages */
 	unsigned long nr_anon;
@@ -38,6 +42,8 @@ struct compact_control {
 	unsigned int order;		/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
+
+	int compact_mode;
 };
 
 static unsigned long release_freepages(struct list_head *freelist)
@@ -60,7 +66,7 @@ static unsigned long isolate_freepages_block(struct zone *zone,
 				struct list_head *freelist)
 {
 	unsigned long zone_end_pfn, end_pfn;
-	int total_isolated = 0;
+	int nr_scanned = 0, total_isolated = 0;
 	struct page *cursor;
 
 	/* Get the last PFN we should scan for free pages at */
@@ -81,6 +87,7 @@ static unsigned long isolate_freepages_block(struct zone *zone,
 
 		if (!pfn_valid_within(blockpfn))
 			continue;
+		nr_scanned++;
 
 		if (!PageBuddy(page))
 			continue;
@@ -100,6 +107,7 @@ static unsigned long isolate_freepages_block(struct zone *zone,
 		}
 	}
 
+	trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated);
 	return total_isolated;
 }
 
@@ -234,6 +242,8 @@ static unsigned long isolate_migratepages(struct zone *zone,
 					struct compact_control *cc)
 {
 	unsigned long low_pfn, end_pfn;
+	unsigned long last_pageblock_nr = 0, pageblock_nr;
+	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
 
 	/* Do not scan outside zone boundaries */
@@ -266,21 +276,51 @@ static unsigned long isolate_migratepages(struct zone *zone,
 		struct page *page;
 		if (!pfn_valid_within(low_pfn))
 			continue;
+		nr_scanned++;
 
 		/* Get the page and skip if free */
 		page = pfn_to_page(low_pfn);
 		if (PageBuddy(page))
 			continue;
 
+		/*
+		 * For async migration, also only scan in MOVABLE blocks. Async
+		 * migration is optimistic to see if the minimum amount of work
+		 * satisfies the allocation
+		 */
+		pageblock_nr = low_pfn >> pageblock_order;
+		if (!cc->sync && last_pageblock_nr != pageblock_nr &&
+				get_pageblock_migratetype(page) != MIGRATE_MOVABLE) {
+			low_pfn += pageblock_nr_pages;
+			low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1;
+			last_pageblock_nr = pageblock_nr;
+			continue;
+		}
+
+		if (!PageLRU(page))
+			continue;
+
+		/*
+		 * PageLRU is set, and lru_lock excludes isolation,
+		 * splitting and collapsing (collapsing has already
+		 * happened if PageLRU is set).
+		 */
+		if (PageTransHuge(page)) {
+			low_pfn += (1 << compound_order(page)) - 1;
+			continue;
+		}
+
 		/* Try isolate the page */
 		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
 			continue;
 
+		VM_BUG_ON(PageTransCompound(page));
+
 		/* Successfully isolated */
 		del_page_from_lru_list(zone, page, page_lru(page));
 		list_add(&page->lru, migratelist);
-		mem_cgroup_del_lru(page);
 		cc->nr_migratepages++;
+		nr_isolated++;
 
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
@@ -292,6 +332,8 @@ static unsigned long isolate_migratepages(struct zone *zone,
 	spin_unlock_irq(&zone->lru_lock);
 	cc->migrate_pfn = low_pfn;
 
+	trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
+
 	return cc->nr_migratepages;
 }
 
@@ -342,10 +384,10 @@ static void update_nr_listpages(struct compact_control *cc)
 }
 
 static int compact_finished(struct zone *zone,
-						struct compact_control *cc)
+			    struct compact_control *cc)
 {
 	unsigned int order;
-	unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order);
+	unsigned long watermark;
 
 	if (fatal_signal_pending(current))
 		return COMPACT_PARTIAL;
@@ -355,12 +397,31 @@ static int compact_finished(struct zone *zone,
 		return COMPACT_COMPLETE;
 
 	/* Compaction run is not finished if the watermark is not met */
+	if (cc->compact_mode != COMPACT_MODE_KSWAPD)
+		watermark = low_wmark_pages(zone);
+	else
+		watermark = high_wmark_pages(zone);
+	watermark += (1 << cc->order);
+
 	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
 		return COMPACT_CONTINUE;
 
+	/*
+	 * order == -1 is expected when compacting via
+	 * /proc/sys/vm/compact_memory
+	 */
 	if (cc->order == -1)
 		return COMPACT_CONTINUE;
 
+	/*
+	 * Generating only one page of the right order is not enough
+	 * for kswapd, we must continue until we're above the high
+	 * watermark as a pool for high order GFP_ATOMIC allocations
+	 * too.
+	 */
+	if (cc->compact_mode == COMPACT_MODE_KSWAPD)
+		return COMPACT_CONTINUE;
+
 	/* Direct compactor: Is a suitable page free? */
 	for (order = cc->order; order < MAX_ORDER; order++) {
 		/* Job done if page is free of the right migratetype */
@@ -375,10 +436,69 @@ static int compact_finished(struct zone *zone,
 	return COMPACT_CONTINUE;
 }
 
+/*
+ * compaction_suitable: Is this suitable to run compaction on this zone now?
+ * Returns
+ *   COMPACT_SKIPPED  - If there are too few free pages for compaction
+ *   COMPACT_PARTIAL  - If the allocation would succeed without compaction
+ *   COMPACT_CONTINUE - If compaction should run now
+ */
+unsigned long compaction_suitable(struct zone *zone, int order)
+{
+	int fragindex;
+	unsigned long watermark;
+
+	/*
+	 * Watermarks for order-0 must be met for compaction. Note the 2UL.
+	 * This is because during migration, copies of pages need to be
+	 * allocated and for a short time, the footprint is higher
+	 */
+	watermark = low_wmark_pages(zone) + (2UL << order);
+	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+		return COMPACT_SKIPPED;
+
+	/*
+	 * order == -1 is expected when compacting via
+	 * /proc/sys/vm/compact_memory
+	 */
+	if (order == -1)
+		return COMPACT_CONTINUE;
+
+	/*
+	 * fragmentation index determines if allocation failures are due to
+	 * low memory or external fragmentation
+	 *
+	 * index of -1 implies allocations might succeed dependingon watermarks
+	 * index towards 0 implies failure is due to lack of memory
+	 * index towards 1000 implies failure is due to fragmentation
+	 *
+	 * Only compact if a failure would be due to fragmentation.
+	 */
+	fragindex = fragmentation_index(zone, order);
+	if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
+		return COMPACT_SKIPPED;
+
+	if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0))
+		return COMPACT_PARTIAL;
+
+	return COMPACT_CONTINUE;
+}
+
 static int compact_zone(struct zone *zone, struct compact_control *cc)
 {
 	int ret;
 
+	ret = compaction_suitable(zone, cc->order);
+	switch (ret) {
+	case COMPACT_PARTIAL:
+	case COMPACT_SKIPPED:
+		/* Compaction is likely to fail */
+		return ret;
+	case COMPACT_CONTINUE:
+		/* Fall through to compaction */
+		;
+	}
+
 	/* Setup to move all movable pages to the end of the zone */
 	cc->migrate_pfn = zone->zone_start_pfn;
 	cc->free_pfn = cc->migrate_pfn + zone->spanned_pages;
@@ -394,7 +514,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 
 		nr_migrate = cc->nr_migratepages;
 		migrate_pages(&cc->migratepages, compaction_alloc,
-						(unsigned long)cc, 0);
+				(unsigned long)cc, false,
+				cc->sync);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
@@ -402,6 +523,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		count_vm_events(COMPACTPAGES, nr_migrate - nr_remaining);
 		if (nr_remaining)
 			count_vm_events(COMPACTPAGEFAILED, nr_remaining);
+		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
+						nr_remaining);
 
 		/* Release LRU pages not migrated */
 		if (!list_empty(&cc->migratepages)) {
@@ -418,8 +541,10 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 	return ret;
 }
 
-static unsigned long compact_zone_order(struct zone *zone,
-						int order, gfp_t gfp_mask)
+unsigned long compact_zone_order(struct zone *zone,
+				 int order, gfp_t gfp_mask,
+				 bool sync,
+				 int compact_mode)
 {
 	struct compact_control cc = {
 		.nr_freepages = 0,
@@ -427,6 +552,8 @@ static unsigned long compact_zone_order(struct zone *zone,
 		.order = order,
 		.migratetype = allocflags_to_migratetype(gfp_mask),
 		.zone = zone,
+		.sync = sync,
+		.compact_mode = compact_mode,
 	};
 	INIT_LIST_HEAD(&cc.freepages);
 	INIT_LIST_HEAD(&cc.migratepages);
@@ -442,16 +569,17 @@ int sysctl_extfrag_threshold = 500;
  * @order: The order of the current allocation
  * @gfp_mask: The GFP mask of the current allocation
  * @nodemask: The allowed nodes to allocate from
+ * @sync: Whether migration is synchronous or not
  *
  * This is the main entry point for direct page compaction.
  */
 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)
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	int may_enter_fs = gfp_mask & __GFP_FS;
 	int may_perform_io = gfp_mask & __GFP_IO;
-	unsigned long watermark;
 	struct zoneref *z;
 	struct zone *zone;
 	int rc = COMPACT_SKIPPED;
@@ -461,7 +589,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	 * made because an assumption is made that the page allocator can satisfy
 	 * the "cheaper" orders without taking special steps
 	 */
-	if (order <= PAGE_ALLOC_COSTLY_ORDER || !may_enter_fs || !may_perform_io)
+	if (!order || !may_enter_fs || !may_perform_io)
 		return rc;
 
 	count_vm_event(COMPACTSTALL);
@@ -469,43 +597,14 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist,
 	/* Compact each zone in the list */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
 								nodemask) {
-		int fragindex;
 		int status;
 
-		/*
-		 * Watermarks for order-0 must be met for compaction. Note
-		 * the 2UL. This is because during migration, copies of
-		 * pages need to be allocated and for a short time, the
-		 * footprint is higher
-		 */
-		watermark = low_wmark_pages(zone) + (2UL << order);
-		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
-			continue;
-
-		/*
-		 * fragmentation index determines if allocation failures are
-		 * due to low memory or external fragmentation
-		 *
-		 * index of -1 implies allocations might succeed depending
-		 * 	on watermarks
-		 * index towards 0 implies failure is due to lack of memory
-		 * index towards 1000 implies failure is due to fragmentation
-		 *
-		 * Only compact if a failure would be due to fragmentation.
-		 */
-		fragindex = fragmentation_index(zone, order);
-		if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold)
-			continue;
-
-		if (fragindex == -1 && zone_watermark_ok(zone, order, watermark, 0, 0)) {
-			rc = COMPACT_PARTIAL;
-			break;
-		}
-
-		status = compact_zone_order(zone, order, gfp_mask);
+		status = compact_zone_order(zone, order, gfp_mask, sync,
+					    COMPACT_MODE_DIRECT_RECLAIM);
 		rc = max(status, rc);
 
-		if (zone_watermark_ok(zone, order, watermark, 0, 0))
+		/* If a normal allocation would succeed, stop compacting */
+		if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
 			break;
 	}
 
@@ -532,6 +631,7 @@ static int compact_node(int nid)
 			.nr_freepages = 0,
 			.nr_migratepages = 0,
 			.order = -1,
+			.compact_mode = COMPACT_MODE_DIRECT_RECLAIM,
 		};
 
 		zone = &pgdat->node_zones[zoneid];
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 3df063706f53..03bf3bb4519a 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -311,6 +311,8 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 	size_t offset;
 	void *retval;
 
+	might_sleep_if(mem_flags & __GFP_WAIT);
+
 	spin_lock_irqsave(&pool->lock, flags);
  restart:
 	list_for_each_entry(page, &pool->page_list, page_list) {
@@ -322,7 +324,7 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 		if (mem_flags & __GFP_WAIT) {
 			DECLARE_WAITQUEUE(wait, current);
 
-			__set_current_state(TASK_INTERRUPTIBLE);
+			__set_current_state(TASK_UNINTERRUPTIBLE);
 			__add_wait_queue(&pool->waitq, &wait);
 			spin_unlock_irqrestore(&pool->lock, flags);
 
@@ -353,20 +355,15 @@ EXPORT_SYMBOL(dma_pool_alloc);
 
 static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma)
 {
-	unsigned long flags;
 	struct dma_page *page;
 
-	spin_lock_irqsave(&pool->lock, flags);
 	list_for_each_entry(page, &pool->page_list, page_list) {
 		if (dma < page->dma)
 			continue;
 		if (dma < (page->dma + pool->allocation))
-			goto done;
+			return page;
 	}
-	page = NULL;
- done:
-	spin_unlock_irqrestore(&pool->lock, flags);
-	return page;
+	return NULL;
 }
 
 /**
@@ -384,8 +381,10 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 	unsigned long flags;
 	unsigned int offset;
 
+	spin_lock_irqsave(&pool->lock, flags);
 	page = pool_find_page(pool, dma);
 	if (!page) {
+		spin_unlock_irqrestore(&pool->lock, flags);
 		if (pool->dev)
 			dev_err(pool->dev,
 				"dma_pool_free %s, %p/%lx (bad dma)\n",
@@ -399,6 +398,7 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 	offset = vaddr - page->vaddr;
 #ifdef	DMAPOOL_DEBUG
 	if ((dma - page->dma) != offset) {
+		spin_unlock_irqrestore(&pool->lock, flags);
 		if (pool->dev)
 			dev_err(pool->dev,
 				"dma_pool_free %s, %p (bad vaddr)/%Lx\n",
@@ -416,6 +416,7 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 				chain = *(int *)(page->vaddr + chain);
 				continue;
 			}
+			spin_unlock_irqrestore(&pool->lock, flags);
 			if (pool->dev)
 				dev_err(pool->dev, "dma_pool_free %s, dma %Lx "
 					"already free\n", pool->name,
@@ -430,7 +431,6 @@ void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t dma)
 	memset(vaddr, POOL_POISON_FREED, pool->size);
 #endif
 
-	spin_lock_irqsave(&pool->lock, flags);
 	page->in_use--;
 	*(int *)vaddr = page->offset;
 	page->offset = offset;
diff --git a/mm/filemap.c b/mm/filemap.c
index 3d4df44e4221..83a45d35468b 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -102,9 +102,6 @@
  *    ->inode_lock		(zap_pte_range->set_page_dirty)
  *    ->private_lock		(zap_pte_range->__set_page_dirty_buffers)
  *
- *  ->task->proc_lock
- *    ->dcache_lock		(proc_pid_lookup)
- *
  *  (code doesn't rely on that order, so you could switch it around)
  *  ->tasklist_lock             (memory_failure, collect_procs_ao)
  *    ->i_mmap_lock
@@ -143,13 +140,18 @@ void __remove_from_page_cache(struct page *page)
 void remove_from_page_cache(struct page *page)
 {
 	struct address_space *mapping = page->mapping;
+	void (*freepage)(struct page *);
 
 	BUG_ON(!PageLocked(page));
 
+	freepage = mapping->a_ops->freepage;
 	spin_lock_irq(&mapping->tree_lock);
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
+
+	if (freepage)
+		freepage(page);
 }
 EXPORT_SYMBOL(remove_from_page_cache);
 
@@ -296,7 +298,7 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte,
 				continue;
 
 			wait_on_page_writeback(page);
-			if (PageError(page))
+			if (TestClearPageError(page))
 				ret = -EIO;
 		}
 		pagevec_release(&pvec);
@@ -612,6 +614,19 @@ void __lock_page_nosync(struct page *page)
 							TASK_UNINTERRUPTIBLE);
 }
 
+int __lock_page_or_retry(struct page *page, struct mm_struct *mm,
+			 unsigned int flags)
+{
+	if (!(flags & FAULT_FLAG_ALLOW_RETRY)) {
+		__lock_page(page);
+		return 1;
+	} else {
+		up_read(&mm->mmap_sem);
+		wait_on_page_locked(page);
+		return 0;
+	}
+}
+
 /**
  * find_get_page - find and get a page reference
  * @mapping: the address_space to search
@@ -631,7 +646,9 @@ repeat:
 	pagep = radix_tree_lookup_slot(&mapping->page_tree, offset);
 	if (pagep) {
 		page = radix_tree_deref_slot(pagep);
-		if (unlikely(!page || page == RADIX_TREE_RETRY))
+		if (unlikely(!page))
+			goto out;
+		if (radix_tree_deref_retry(page))
 			goto repeat;
 
 		if (!page_cache_get_speculative(page))
@@ -647,6 +664,7 @@ repeat:
 			goto repeat;
 		}
 	}
+out:
 	rcu_read_unlock();
 
 	return page;
@@ -764,12 +782,11 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page)) {
+			if (ret)
+				start = pages[ret-1]->index;
 			goto restart;
+		}
 
 		if (!page_cache_get_speculative(page))
 			goto repeat;
@@ -817,16 +834,9 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
-		if (page->mapping == NULL || page->index != index)
-			break;
-
 		if (!page_cache_get_speculative(page))
 			goto repeat;
 
@@ -836,6 +846,16 @@ repeat:
 			goto repeat;
 		}
 
+		/*
+		 * must check mapping and index after taking the ref.
+		 * otherwise we can get both false positives and false
+		 * negatives, which is just confusing to the caller.
+		 */
+		if (page->mapping == NULL || page->index != index) {
+			page_cache_release(page);
+			break;
+		}
+
 		pages[ret] = page;
 		ret++;
 		index++;
@@ -874,11 +894,7 @@ repeat:
 		page = radix_tree_deref_slot((void **)pages[i]);
 		if (unlikely(!page))
 			continue;
-		/*
-		 * this can only trigger if nr_found == 1, making livelock
-		 * a non issue.
-		 */
-		if (unlikely(page == RADIX_TREE_RETRY))
+		if (radix_tree_deref_retry(page))
 			goto restart;
 
 		if (!page_cache_get_speculative(page))
@@ -1016,6 +1032,9 @@ find_page:
 				goto page_not_up_to_date;
 			if (!trylock_page(page))
 				goto page_not_up_to_date;
+			/* Did it get truncated before we got the lock? */
+			if (!page->mapping)
+				goto page_not_up_to_date_locked;
 			if (!mapping->a_ops->is_partially_uptodate(page,
 								desc, offset))
 				goto page_not_up_to_date_locked;
@@ -1539,25 +1558,30 @@ int filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		 * waiting for the lock.
 		 */
 		do_async_mmap_readahead(vma, ra, file, page, offset);
-		lock_page(page);
-
-		/* Did it get truncated? */
-		if (unlikely(page->mapping != mapping)) {
-			unlock_page(page);
-			put_page(page);
-			goto no_cached_page;
-		}
 	} else {
 		/* No page in the page cache at all */
 		do_sync_mmap_readahead(vma, ra, file, offset);
 		count_vm_event(PGMAJFAULT);
 		ret = VM_FAULT_MAJOR;
 retry_find:
-		page = find_lock_page(mapping, offset);
+		page = find_get_page(mapping, offset);
 		if (!page)
 			goto no_cached_page;
 	}
 
+	if (!lock_page_or_retry(page, vma->vm_mm, vmf->flags)) {
+		page_cache_release(page);
+		return ret | VM_FAULT_RETRY;
+	}
+
+	/* Did it get truncated? */
+	if (unlikely(page->mapping != mapping)) {
+		unlock_page(page);
+		put_page(page);
+		goto retry_find;
+	}
+	VM_BUG_ON(page->index != offset);
+
 	/*
 	 * We have a locked page in the page cache, now we need to check
 	 * that it's up-to-date. If not, it is going to be due to an error.
@@ -2177,12 +2201,12 @@ generic_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	}
 
 	if (written > 0) {
-		loff_t end = pos + written;
-		if (end > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
-			i_size_write(inode,  end);
+		pos += written;
+		if (pos > i_size_read(inode) && !S_ISBLK(inode->i_mode)) {
+			i_size_write(inode, pos);
 			mark_inode_dirty(inode);
 		}
-		*ppos = end;
+		*ppos = pos;
 	}
 out:
 	return written;
@@ -2203,7 +2227,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping,
 		gfp_notmask = __GFP_FS;
 repeat:
 	page = find_lock_page(mapping, index);
-	if (likely(page))
+	if (page)
 		return page;
 
 	page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
diff --git a/mm/highmem.c b/mm/highmem.c
index 7a0aa1be4993..693394daa2ed 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -29,6 +29,11 @@
 #include <linux/kgdb.h>
 #include <asm/tlbflush.h>
 
+
+#if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32)
+DEFINE_PER_CPU(int, __kmap_atomic_idx);
+#endif
+
 /*
  * Virtual_count is not a pure "count".
  *  0 means that it is not mapped, and has not been mapped
@@ -42,6 +47,9 @@
 unsigned long totalhigh_pages __read_mostly;
 EXPORT_SYMBOL(totalhigh_pages);
 
+
+EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx);
+
 unsigned int nr_free_highpages (void)
 {
 	pg_data_t *pgdat;
@@ -422,61 +430,3 @@ void __init page_address_init(void)
 }
 
 #endif	/* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
-
-#ifdef CONFIG_DEBUG_HIGHMEM
-
-void debug_kmap_atomic(enum km_type type)
-{
-	static int warn_count = 10;
-
-	if (unlikely(warn_count < 0))
-		return;
-
-	if (unlikely(in_interrupt())) {
-		if (in_nmi()) {
-			if (type != KM_NMI && type != KM_NMI_PTE) {
-				WARN_ON(1);
-				warn_count--;
-			}
-		} else if (in_irq()) {
-			if (type != KM_IRQ0 && type != KM_IRQ1 &&
-			    type != KM_BIO_SRC_IRQ && type != KM_BIO_DST_IRQ &&
-			    type != KM_BOUNCE_READ && type != KM_IRQ_PTE) {
-				WARN_ON(1);
-				warn_count--;
-			}
-		} else if (!irqs_disabled()) {	/* softirq */
-			if (type != KM_IRQ0 && type != KM_IRQ1 &&
-			    type != KM_SOFTIRQ0 && type != KM_SOFTIRQ1 &&
-			    type != KM_SKB_SUNRPC_DATA &&
-			    type != KM_SKB_DATA_SOFTIRQ &&
-			    type != KM_BOUNCE_READ) {
-				WARN_ON(1);
-				warn_count--;
-			}
-		}
-	}
-
-	if (type == KM_IRQ0 || type == KM_IRQ1 || type == KM_BOUNCE_READ ||
-			type == KM_BIO_SRC_IRQ || type == KM_BIO_DST_IRQ ||
-			type == KM_IRQ_PTE || type == KM_NMI ||
-			type == KM_NMI_PTE ) {
-		if (!irqs_disabled()) {
-			WARN_ON(1);
-			warn_count--;
-		}
-	} else if (type == KM_SOFTIRQ0 || type == KM_SOFTIRQ1) {
-		if (irq_count() == 0 && !irqs_disabled()) {
-			WARN_ON(1);
-			warn_count--;
-		}
-	}
-#ifdef CONFIG_KGDB_KDB
-	if (unlikely(type == KM_KDB && atomic_read(&kgdb_active) == -1)) {
-		WARN_ON(1);
-		warn_count--;
-	}
-#endif /* CONFIG_KGDB_KDB */
-}
-
-#endif
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
new file mode 100644
index 000000000000..3e29781ee762
--- /dev/null
+++ b/mm/huge_memory.c
@@ -0,0 +1,2351 @@
+/*
+ *  Copyright (C) 2009  Red Hat, Inc.
+ *
+ *  This work is licensed under the terms of the GNU GPL, version 2. See
+ *  the COPYING file in the top-level directory.
+ */
+
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/highmem.h>
+#include <linux/hugetlb.h>
+#include <linux/mmu_notifier.h>
+#include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/mm_inline.h>
+#include <linux/kthread.h>
+#include <linux/khugepaged.h>
+#include <linux/freezer.h>
+#include <linux/mman.h>
+#include <asm/tlb.h>
+#include <asm/pgalloc.h>
+#include "internal.h"
+
+/*
+ * By default transparent hugepage support is enabled for all mappings
+ * and khugepaged scans all mappings. Defrag is only invoked by
+ * khugepaged hugepage allocations and by page faults inside
+ * MADV_HUGEPAGE regions to avoid the risk of slowing down short lived
+ * allocations.
+ */
+unsigned long transparent_hugepage_flags __read_mostly =
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS
+	(1<<TRANSPARENT_HUGEPAGE_FLAG)|
+#endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE
+	(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)|
+#endif
+	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_FLAG)|
+	(1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
+
+/* default scan 8*512 pte (or vmas) every 30 second */
+static unsigned int khugepaged_pages_to_scan __read_mostly = HPAGE_PMD_NR*8;
+static unsigned int khugepaged_pages_collapsed;
+static unsigned int khugepaged_full_scans;
+static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000;
+/* during fragmentation poll the hugepage allocator once every minute */
+static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000;
+static struct task_struct *khugepaged_thread __read_mostly;
+static DEFINE_MUTEX(khugepaged_mutex);
+static DEFINE_SPINLOCK(khugepaged_mm_lock);
+static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait);
+/*
+ * default collapse hugepages if there is at least one pte mapped like
+ * it would have happened if the vma was large enough during page
+ * fault.
+ */
+static unsigned int khugepaged_max_ptes_none __read_mostly = HPAGE_PMD_NR-1;
+
+static int khugepaged(void *none);
+static int mm_slots_hash_init(void);
+static int khugepaged_slab_init(void);
+static void khugepaged_slab_free(void);
+
+#define MM_SLOTS_HASH_HEADS 1024
+static struct hlist_head *mm_slots_hash __read_mostly;
+static struct kmem_cache *mm_slot_cache __read_mostly;
+
+/**
+ * struct mm_slot - hash lookup from mm to mm_slot
+ * @hash: hash collision list
+ * @mm_node: khugepaged scan list headed in khugepaged_scan.mm_head
+ * @mm: the mm that this information is valid for
+ */
+struct mm_slot {
+	struct hlist_node hash;
+	struct list_head mm_node;
+	struct mm_struct *mm;
+};
+
+/**
+ * struct khugepaged_scan - cursor for scanning
+ * @mm_head: the head of the mm list to scan
+ * @mm_slot: the current mm_slot we are scanning
+ * @address: the next address inside that to be scanned
+ *
+ * There is only the one khugepaged_scan instance of this cursor structure.
+ */
+struct khugepaged_scan {
+	struct list_head mm_head;
+	struct mm_slot *mm_slot;
+	unsigned long address;
+} khugepaged_scan = {
+	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
+};
+
+
+static int set_recommended_min_free_kbytes(void)
+{
+	struct zone *zone;
+	int nr_zones = 0;
+	unsigned long recommended_min;
+	extern int min_free_kbytes;
+
+	if (!test_bit(TRANSPARENT_HUGEPAGE_FLAG,
+		      &transparent_hugepage_flags) &&
+	    !test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+		      &transparent_hugepage_flags))
+		return 0;
+
+	for_each_populated_zone(zone)
+		nr_zones++;
+
+	/* Make sure at least 2 hugepages are free for MIGRATE_RESERVE */
+	recommended_min = pageblock_nr_pages * nr_zones * 2;
+
+	/*
+	 * Make sure that on average at least two pageblocks are almost free
+	 * of another type, one for a migratetype to fall back to and a
+	 * second to avoid subsequent fallbacks of other types There are 3
+	 * MIGRATE_TYPES we care about.
+	 */
+	recommended_min += pageblock_nr_pages * nr_zones *
+			   MIGRATE_PCPTYPES * MIGRATE_PCPTYPES;
+
+	/* don't ever allow to reserve more than 5% of the lowmem */
+	recommended_min = min(recommended_min,
+			      (unsigned long) nr_free_buffer_pages() / 20);
+	recommended_min <<= (PAGE_SHIFT-10);
+
+	if (recommended_min > min_free_kbytes)
+		min_free_kbytes = recommended_min;
+	setup_per_zone_wmarks();
+	return 0;
+}
+late_initcall(set_recommended_min_free_kbytes);
+
+static int start_khugepaged(void)
+{
+	int err = 0;
+	if (khugepaged_enabled()) {
+		int wakeup;
+		if (unlikely(!mm_slot_cache || !mm_slots_hash)) {
+			err = -ENOMEM;
+			goto out;
+		}
+		mutex_lock(&khugepaged_mutex);
+		if (!khugepaged_thread)
+			khugepaged_thread = kthread_run(khugepaged, NULL,
+							"khugepaged");
+		if (unlikely(IS_ERR(khugepaged_thread))) {
+			printk(KERN_ERR
+			       "khugepaged: kthread_run(khugepaged) failed\n");
+			err = PTR_ERR(khugepaged_thread);
+			khugepaged_thread = NULL;
+		}
+		wakeup = !list_empty(&khugepaged_scan.mm_head);
+		mutex_unlock(&khugepaged_mutex);
+		if (wakeup)
+			wake_up_interruptible(&khugepaged_wait);
+
+		set_recommended_min_free_kbytes();
+	} else
+		/* wakeup to exit */
+		wake_up_interruptible(&khugepaged_wait);
+out:
+	return err;
+}
+
+#ifdef CONFIG_SYSFS
+
+static ssize_t double_flag_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf,
+				enum transparent_hugepage_flag enabled,
+				enum transparent_hugepage_flag req_madv)
+{
+	if (test_bit(enabled, &transparent_hugepage_flags)) {
+		VM_BUG_ON(test_bit(req_madv, &transparent_hugepage_flags));
+		return sprintf(buf, "[always] madvise never\n");
+	} else if (test_bit(req_madv, &transparent_hugepage_flags))
+		return sprintf(buf, "always [madvise] never\n");
+	else
+		return sprintf(buf, "always madvise [never]\n");
+}
+static ssize_t double_flag_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t count,
+				 enum transparent_hugepage_flag enabled,
+				 enum transparent_hugepage_flag req_madv)
+{
+	if (!memcmp("always", buf,
+		    min(sizeof("always")-1, count))) {
+		set_bit(enabled, &transparent_hugepage_flags);
+		clear_bit(req_madv, &transparent_hugepage_flags);
+	} else if (!memcmp("madvise", buf,
+			   min(sizeof("madvise")-1, count))) {
+		clear_bit(enabled, &transparent_hugepage_flags);
+		set_bit(req_madv, &transparent_hugepage_flags);
+	} else if (!memcmp("never", buf,
+			   min(sizeof("never")-1, count))) {
+		clear_bit(enabled, &transparent_hugepage_flags);
+		clear_bit(req_madv, &transparent_hugepage_flags);
+	} else
+		return -EINVAL;
+
+	return count;
+}
+
+static ssize_t enabled_show(struct kobject *kobj,
+			    struct kobj_attribute *attr, char *buf)
+{
+	return double_flag_show(kobj, attr, buf,
+				TRANSPARENT_HUGEPAGE_FLAG,
+				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
+}
+static ssize_t enabled_store(struct kobject *kobj,
+			     struct kobj_attribute *attr,
+			     const char *buf, size_t count)
+{
+	ssize_t ret;
+
+	ret = double_flag_store(kobj, attr, buf, count,
+				TRANSPARENT_HUGEPAGE_FLAG,
+				TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG);
+
+	if (ret > 0) {
+		int err = start_khugepaged();
+		if (err)
+			ret = err;
+	}
+
+	if (ret > 0 &&
+	    (test_bit(TRANSPARENT_HUGEPAGE_FLAG,
+		      &transparent_hugepage_flags) ||
+	     test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+		      &transparent_hugepage_flags)))
+		set_recommended_min_free_kbytes();
+
+	return ret;
+}
+static struct kobj_attribute enabled_attr =
+	__ATTR(enabled, 0644, enabled_show, enabled_store);
+
+static ssize_t single_flag_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf,
+				enum transparent_hugepage_flag flag)
+{
+	if (test_bit(flag, &transparent_hugepage_flags))
+		return sprintf(buf, "[yes] no\n");
+	else
+		return sprintf(buf, "yes [no]\n");
+}
+static ssize_t single_flag_store(struct kobject *kobj,
+				 struct kobj_attribute *attr,
+				 const char *buf, size_t count,
+				 enum transparent_hugepage_flag flag)
+{
+	if (!memcmp("yes", buf,
+		    min(sizeof("yes")-1, count))) {
+		set_bit(flag, &transparent_hugepage_flags);
+	} else if (!memcmp("no", buf,
+			   min(sizeof("no")-1, count))) {
+		clear_bit(flag, &transparent_hugepage_flags);
+	} else
+		return -EINVAL;
+
+	return count;
+}
+
+/*
+ * Currently defrag only disables __GFP_NOWAIT for allocation. A blind
+ * __GFP_REPEAT is too aggressive, it's never worth swapping tons of
+ * memory just to allocate one more hugepage.
+ */
+static ssize_t defrag_show(struct kobject *kobj,
+			   struct kobj_attribute *attr, char *buf)
+{
+	return double_flag_show(kobj, attr, buf,
+				TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
+				TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
+}
+static ssize_t defrag_store(struct kobject *kobj,
+			    struct kobj_attribute *attr,
+			    const char *buf, size_t count)
+{
+	return double_flag_store(kobj, attr, buf, count,
+				 TRANSPARENT_HUGEPAGE_DEFRAG_FLAG,
+				 TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG);
+}
+static struct kobj_attribute defrag_attr =
+	__ATTR(defrag, 0644, defrag_show, defrag_store);
+
+#ifdef CONFIG_DEBUG_VM
+static ssize_t debug_cow_show(struct kobject *kobj,
+				struct kobj_attribute *attr, char *buf)
+{
+	return single_flag_show(kobj, attr, buf,
+				TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
+}
+static ssize_t debug_cow_store(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       const char *buf, size_t count)
+{
+	return single_flag_store(kobj, attr, buf, count,
+				 TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG);
+}
+static struct kobj_attribute debug_cow_attr =
+	__ATTR(debug_cow, 0644, debug_cow_show, debug_cow_store);
+#endif /* CONFIG_DEBUG_VM */
+
+static struct attribute *hugepage_attr[] = {
+	&enabled_attr.attr,
+	&defrag_attr.attr,
+#ifdef CONFIG_DEBUG_VM
+	&debug_cow_attr.attr,
+#endif
+	NULL,
+};
+
+static struct attribute_group hugepage_attr_group = {
+	.attrs = hugepage_attr,
+};
+
+static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
+					 struct kobj_attribute *attr,
+					 char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_scan_sleep_millisecs);
+}
+
+static ssize_t scan_sleep_millisecs_store(struct kobject *kobj,
+					  struct kobj_attribute *attr,
+					  const char *buf, size_t count)
+{
+	unsigned long msecs;
+	int err;
+
+	err = strict_strtoul(buf, 10, &msecs);
+	if (err || msecs > UINT_MAX)
+		return -EINVAL;
+
+	khugepaged_scan_sleep_millisecs = msecs;
+	wake_up_interruptible(&khugepaged_wait);
+
+	return count;
+}
+static struct kobj_attribute scan_sleep_millisecs_attr =
+	__ATTR(scan_sleep_millisecs, 0644, scan_sleep_millisecs_show,
+	       scan_sleep_millisecs_store);
+
+static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj,
+					  struct kobj_attribute *attr,
+					  char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_alloc_sleep_millisecs);
+}
+
+static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj,
+					   struct kobj_attribute *attr,
+					   const char *buf, size_t count)
+{
+	unsigned long msecs;
+	int err;
+
+	err = strict_strtoul(buf, 10, &msecs);
+	if (err || msecs > UINT_MAX)
+		return -EINVAL;
+
+	khugepaged_alloc_sleep_millisecs = msecs;
+	wake_up_interruptible(&khugepaged_wait);
+
+	return count;
+}
+static struct kobj_attribute alloc_sleep_millisecs_attr =
+	__ATTR(alloc_sleep_millisecs, 0644, alloc_sleep_millisecs_show,
+	       alloc_sleep_millisecs_store);
+
+static ssize_t pages_to_scan_show(struct kobject *kobj,
+				  struct kobj_attribute *attr,
+				  char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_pages_to_scan);
+}
+static ssize_t pages_to_scan_store(struct kobject *kobj,
+				   struct kobj_attribute *attr,
+				   const char *buf, size_t count)
+{
+	int err;
+	unsigned long pages;
+
+	err = strict_strtoul(buf, 10, &pages);
+	if (err || !pages || pages > UINT_MAX)
+		return -EINVAL;
+
+	khugepaged_pages_to_scan = pages;
+
+	return count;
+}
+static struct kobj_attribute pages_to_scan_attr =
+	__ATTR(pages_to_scan, 0644, pages_to_scan_show,
+	       pages_to_scan_store);
+
+static ssize_t pages_collapsed_show(struct kobject *kobj,
+				    struct kobj_attribute *attr,
+				    char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_pages_collapsed);
+}
+static struct kobj_attribute pages_collapsed_attr =
+	__ATTR_RO(pages_collapsed);
+
+static ssize_t full_scans_show(struct kobject *kobj,
+			       struct kobj_attribute *attr,
+			       char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_full_scans);
+}
+static struct kobj_attribute full_scans_attr =
+	__ATTR_RO(full_scans);
+
+static ssize_t khugepaged_defrag_show(struct kobject *kobj,
+				      struct kobj_attribute *attr, char *buf)
+{
+	return single_flag_show(kobj, attr, buf,
+				TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
+}
+static ssize_t khugepaged_defrag_store(struct kobject *kobj,
+				       struct kobj_attribute *attr,
+				       const char *buf, size_t count)
+{
+	return single_flag_store(kobj, attr, buf, count,
+				 TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG);
+}
+static struct kobj_attribute khugepaged_defrag_attr =
+	__ATTR(defrag, 0644, khugepaged_defrag_show,
+	       khugepaged_defrag_store);
+
+/*
+ * max_ptes_none controls if khugepaged should collapse hugepages over
+ * any unmapped ptes in turn potentially increasing the memory
+ * footprint of the vmas. When max_ptes_none is 0 khugepaged will not
+ * reduce the available free memory in the system as it
+ * runs. Increasing max_ptes_none will instead potentially reduce the
+ * free memory in the system during the khugepaged scan.
+ */
+static ssize_t khugepaged_max_ptes_none_show(struct kobject *kobj,
+					     struct kobj_attribute *attr,
+					     char *buf)
+{
+	return sprintf(buf, "%u\n", khugepaged_max_ptes_none);
+}
+static ssize_t khugepaged_max_ptes_none_store(struct kobject *kobj,
+					      struct kobj_attribute *attr,
+					      const char *buf, size_t count)
+{
+	int err;
+	unsigned long max_ptes_none;
+
+	err = strict_strtoul(buf, 10, &max_ptes_none);
+	if (err || max_ptes_none > HPAGE_PMD_NR-1)
+		return -EINVAL;
+
+	khugepaged_max_ptes_none = max_ptes_none;
+
+	return count;
+}
+static struct kobj_attribute khugepaged_max_ptes_none_attr =
+	__ATTR(max_ptes_none, 0644, khugepaged_max_ptes_none_show,
+	       khugepaged_max_ptes_none_store);
+
+static struct attribute *khugepaged_attr[] = {
+	&khugepaged_defrag_attr.attr,
+	&khugepaged_max_ptes_none_attr.attr,
+	&pages_to_scan_attr.attr,
+	&pages_collapsed_attr.attr,
+	&full_scans_attr.attr,
+	&scan_sleep_millisecs_attr.attr,
+	&alloc_sleep_millisecs_attr.attr,
+	NULL,
+};
+
+static struct attribute_group khugepaged_attr_group = {
+	.attrs = khugepaged_attr,
+	.name = "khugepaged",
+};
+#endif /* CONFIG_SYSFS */
+
+static int __init hugepage_init(void)
+{
+	int err;
+#ifdef CONFIG_SYSFS
+	static struct kobject *hugepage_kobj;
+#endif
+
+	err = -EINVAL;
+	if (!has_transparent_hugepage()) {
+		transparent_hugepage_flags = 0;
+		goto out;
+	}
+
+#ifdef CONFIG_SYSFS
+	err = -ENOMEM;
+	hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
+	if (unlikely(!hugepage_kobj)) {
+		printk(KERN_ERR "hugepage: failed kobject create\n");
+		goto out;
+	}
+
+	err = sysfs_create_group(hugepage_kobj, &hugepage_attr_group);
+	if (err) {
+		printk(KERN_ERR "hugepage: failed register hugeage group\n");
+		goto out;
+	}
+
+	err = sysfs_create_group(hugepage_kobj, &khugepaged_attr_group);
+	if (err) {
+		printk(KERN_ERR "hugepage: failed register hugeage group\n");
+		goto out;
+	}
+#endif
+
+	err = khugepaged_slab_init();
+	if (err)
+		goto out;
+
+	err = mm_slots_hash_init();
+	if (err) {
+		khugepaged_slab_free();
+		goto out;
+	}
+
+	/*
+	 * By default disable transparent hugepages on smaller systems,
+	 * where the extra memory used could hurt more than TLB overhead
+	 * is likely to save.  The admin can still enable it through /sys.
+	 */
+	if (totalram_pages < (512 << (20 - PAGE_SHIFT)))
+		transparent_hugepage_flags = 0;
+
+	start_khugepaged();
+
+	set_recommended_min_free_kbytes();
+
+out:
+	return err;
+}
+module_init(hugepage_init)
+
+static int __init setup_transparent_hugepage(char *str)
+{
+	int ret = 0;
+	if (!str)
+		goto out;
+	if (!strcmp(str, "always")) {
+		set_bit(TRANSPARENT_HUGEPAGE_FLAG,
+			&transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+			  &transparent_hugepage_flags);
+		ret = 1;
+	} else if (!strcmp(str, "madvise")) {
+		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
+			  &transparent_hugepage_flags);
+		set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+			&transparent_hugepage_flags);
+		ret = 1;
+	} else if (!strcmp(str, "never")) {
+		clear_bit(TRANSPARENT_HUGEPAGE_FLAG,
+			  &transparent_hugepage_flags);
+		clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG,
+			  &transparent_hugepage_flags);
+		ret = 1;
+	}
+out:
+	if (!ret)
+		printk(KERN_WARNING
+		       "transparent_hugepage= cannot parse, ignored\n");
+	return ret;
+}
+__setup("transparent_hugepage=", setup_transparent_hugepage);
+
+static void prepare_pmd_huge_pte(pgtable_t pgtable,
+				 struct mm_struct *mm)
+{
+	assert_spin_locked(&mm->page_table_lock);
+
+	/* FIFO */
+	if (!mm->pmd_huge_pte)
+		INIT_LIST_HEAD(&pgtable->lru);
+	else
+		list_add(&pgtable->lru, &mm->pmd_huge_pte->lru);
+	mm->pmd_huge_pte = pgtable;
+}
+
+static inline pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
+{
+	if (likely(vma->vm_flags & VM_WRITE))
+		pmd = pmd_mkwrite(pmd);
+	return pmd;
+}
+
+static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
+					struct vm_area_struct *vma,
+					unsigned long haddr, pmd_t *pmd,
+					struct page *page)
+{
+	int ret = 0;
+	pgtable_t pgtable;
+
+	VM_BUG_ON(!PageCompound(page));
+	pgtable = pte_alloc_one(mm, haddr);
+	if (unlikely(!pgtable)) {
+		mem_cgroup_uncharge_page(page);
+		put_page(page);
+		return VM_FAULT_OOM;
+	}
+
+	clear_huge_page(page, haddr, HPAGE_PMD_NR);
+	__SetPageUptodate(page);
+
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_none(*pmd))) {
+		spin_unlock(&mm->page_table_lock);
+		mem_cgroup_uncharge_page(page);
+		put_page(page);
+		pte_free(mm, pgtable);
+	} else {
+		pmd_t entry;
+		entry = mk_pmd(page, vma->vm_page_prot);
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+		entry = pmd_mkhuge(entry);
+		/*
+		 * The spinlocking to take the lru_lock inside
+		 * page_add_new_anon_rmap() acts as a full memory
+		 * barrier to be sure clear_huge_page writes become
+		 * visible after the set_pmd_at() write.
+		 */
+		page_add_new_anon_rmap(page, vma, haddr);
+		set_pmd_at(mm, haddr, pmd, entry);
+		prepare_pmd_huge_pte(pgtable, mm);
+		add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR);
+		spin_unlock(&mm->page_table_lock);
+	}
+
+	return ret;
+}
+
+static inline gfp_t alloc_hugepage_gfpmask(int defrag)
+{
+	return GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT);
+}
+
+static inline struct page *alloc_hugepage_vma(int defrag,
+					      struct vm_area_struct *vma,
+					      unsigned long haddr)
+{
+	return alloc_pages_vma(alloc_hugepage_gfpmask(defrag),
+			       HPAGE_PMD_ORDER, vma, haddr);
+}
+
+#ifndef CONFIG_NUMA
+static inline struct page *alloc_hugepage(int defrag)
+{
+	return alloc_pages(alloc_hugepage_gfpmask(defrag),
+			   HPAGE_PMD_ORDER);
+}
+#endif
+
+int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
+			       unsigned long address, pmd_t *pmd,
+			       unsigned int flags)
+{
+	struct page *page;
+	unsigned long haddr = address & HPAGE_PMD_MASK;
+	pte_t *pte;
+
+	if (haddr >= vma->vm_start && haddr + HPAGE_PMD_SIZE <= vma->vm_end) {
+		if (unlikely(anon_vma_prepare(vma)))
+			return VM_FAULT_OOM;
+		if (unlikely(khugepaged_enter(vma)))
+			return VM_FAULT_OOM;
+		page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
+					  vma, haddr);
+		if (unlikely(!page))
+			goto out;
+		if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) {
+			put_page(page);
+			goto out;
+		}
+
+		return __do_huge_pmd_anonymous_page(mm, vma, haddr, pmd, page);
+	}
+out:
+	/*
+	 * Use __pte_alloc instead of pte_alloc_map, because we can't
+	 * run pte_offset_map on the pmd, if an huge pmd could
+	 * materialize from under us from a different thread.
+	 */
+	if (unlikely(__pte_alloc(mm, vma, pmd, address)))
+		return VM_FAULT_OOM;
+	/* if an huge pmd materialized from under us just retry later */
+	if (unlikely(pmd_trans_huge(*pmd)))
+		return 0;
+	/*
+	 * A regular pmd is established and it can't morph into a huge pmd
+	 * from under us anymore at this point because we hold the mmap_sem
+	 * read mode and khugepaged takes it in write mode. So now it's
+	 * safe to run pte_offset_map().
+	 */
+	pte = pte_offset_map(pmd, address);
+	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
+}
+
+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)
+{
+	struct page *src_page;
+	pmd_t pmd;
+	pgtable_t pgtable;
+	int ret;
+
+	ret = -ENOMEM;
+	pgtable = pte_alloc_one(dst_mm, addr);
+	if (unlikely(!pgtable))
+		goto out;
+
+	spin_lock(&dst_mm->page_table_lock);
+	spin_lock_nested(&src_mm->page_table_lock, SINGLE_DEPTH_NESTING);
+
+	ret = -EAGAIN;
+	pmd = *src_pmd;
+	if (unlikely(!pmd_trans_huge(pmd))) {
+		pte_free(dst_mm, pgtable);
+		goto out_unlock;
+	}
+	if (unlikely(pmd_trans_splitting(pmd))) {
+		/* split huge page running from under us */
+		spin_unlock(&src_mm->page_table_lock);
+		spin_unlock(&dst_mm->page_table_lock);
+		pte_free(dst_mm, pgtable);
+
+		wait_split_huge_page(vma->anon_vma, src_pmd); /* src_vma */
+		goto out;
+	}
+	src_page = pmd_page(pmd);
+	VM_BUG_ON(!PageHead(src_page));
+	get_page(src_page);
+	page_dup_rmap(src_page);
+	add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR);
+
+	pmdp_set_wrprotect(src_mm, addr, src_pmd);
+	pmd = pmd_mkold(pmd_wrprotect(pmd));
+	set_pmd_at(dst_mm, addr, dst_pmd, pmd);
+	prepare_pmd_huge_pte(pgtable, dst_mm);
+
+	ret = 0;
+out_unlock:
+	spin_unlock(&src_mm->page_table_lock);
+	spin_unlock(&dst_mm->page_table_lock);
+out:
+	return ret;
+}
+
+/* no "address" argument so destroys page coloring of some arch */
+pgtable_t get_pmd_huge_pte(struct mm_struct *mm)
+{
+	pgtable_t pgtable;
+
+	assert_spin_locked(&mm->page_table_lock);
+
+	/* FIFO */
+	pgtable = mm->pmd_huge_pte;
+	if (list_empty(&pgtable->lru))
+		mm->pmd_huge_pte = NULL;
+	else {
+		mm->pmd_huge_pte = list_entry(pgtable->lru.next,
+					      struct page, lru);
+		list_del(&pgtable->lru);
+	}
+	return pgtable;
+}
+
+static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
+					struct vm_area_struct *vma,
+					unsigned long address,
+					pmd_t *pmd, pmd_t orig_pmd,
+					struct page *page,
+					unsigned long haddr)
+{
+	pgtable_t pgtable;
+	pmd_t _pmd;
+	int ret = 0, i;
+	struct page **pages;
+
+	pages = kmalloc(sizeof(struct page *) * HPAGE_PMD_NR,
+			GFP_KERNEL);
+	if (unlikely(!pages)) {
+		ret |= VM_FAULT_OOM;
+		goto out;
+	}
+
+	for (i = 0; i < HPAGE_PMD_NR; i++) {
+		pages[i] = alloc_page_vma(GFP_HIGHUSER_MOVABLE,
+					  vma, address);
+		if (unlikely(!pages[i] ||
+			     mem_cgroup_newpage_charge(pages[i], mm,
+						       GFP_KERNEL))) {
+			if (pages[i])
+				put_page(pages[i]);
+			mem_cgroup_uncharge_start();
+			while (--i >= 0) {
+				mem_cgroup_uncharge_page(pages[i]);
+				put_page(pages[i]);
+			}
+			mem_cgroup_uncharge_end();
+			kfree(pages);
+			ret |= VM_FAULT_OOM;
+			goto out;
+		}
+	}
+
+	for (i = 0; i < HPAGE_PMD_NR; i++) {
+		copy_user_highpage(pages[i], page + i,
+				   haddr + PAGE_SHIFT*i, vma);
+		__SetPageUptodate(pages[i]);
+		cond_resched();
+	}
+
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(*pmd, orig_pmd)))
+		goto out_free_pages;
+	VM_BUG_ON(!PageHead(page));
+
+	pmdp_clear_flush_notify(vma, haddr, pmd);
+	/* leave pmd empty until pte is filled */
+
+	pgtable = get_pmd_huge_pte(mm);
+	pmd_populate(mm, &_pmd, pgtable);
+
+	for (i = 0; i < HPAGE_PMD_NR; i++, haddr += PAGE_SIZE) {
+		pte_t *pte, entry;
+		entry = mk_pte(pages[i], vma->vm_page_prot);
+		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+		page_add_new_anon_rmap(pages[i], vma, haddr);
+		pte = pte_offset_map(&_pmd, haddr);
+		VM_BUG_ON(!pte_none(*pte));
+		set_pte_at(mm, haddr, pte, entry);
+		pte_unmap(pte);
+	}
+	kfree(pages);
+
+	mm->nr_ptes++;
+	smp_wmb(); /* make pte visible before pmd */
+	pmd_populate(mm, pmd, pgtable);
+	page_remove_rmap(page);
+	spin_unlock(&mm->page_table_lock);
+
+	ret |= VM_FAULT_WRITE;
+	put_page(page);
+
+out:
+	return ret;
+
+out_free_pages:
+	spin_unlock(&mm->page_table_lock);
+	mem_cgroup_uncharge_start();
+	for (i = 0; i < HPAGE_PMD_NR; i++) {
+		mem_cgroup_uncharge_page(pages[i]);
+		put_page(pages[i]);
+	}
+	mem_cgroup_uncharge_end();
+	kfree(pages);
+	goto out;
+}
+
+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)
+{
+	int ret = 0;
+	struct page *page, *new_page;
+	unsigned long haddr;
+
+	VM_BUG_ON(!vma->anon_vma);
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(*pmd, orig_pmd)))
+		goto out_unlock;
+
+	page = pmd_page(orig_pmd);
+	VM_BUG_ON(!PageCompound(page) || !PageHead(page));
+	haddr = address & HPAGE_PMD_MASK;
+	if (page_mapcount(page) == 1) {
+		pmd_t entry;
+		entry = pmd_mkyoung(orig_pmd);
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+		if (pmdp_set_access_flags(vma, haddr, pmd, entry,  1))
+			update_mmu_cache(vma, address, entry);
+		ret |= VM_FAULT_WRITE;
+		goto out_unlock;
+	}
+	get_page(page);
+	spin_unlock(&mm->page_table_lock);
+
+	if (transparent_hugepage_enabled(vma) &&
+	    !transparent_hugepage_debug_cow())
+		new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma),
+					      vma, haddr);
+	else
+		new_page = NULL;
+
+	if (unlikely(!new_page)) {
+		ret = do_huge_pmd_wp_page_fallback(mm, vma, address,
+						   pmd, orig_pmd, page, haddr);
+		put_page(page);
+		goto out;
+	}
+
+	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
+		put_page(new_page);
+		put_page(page);
+		ret |= VM_FAULT_OOM;
+		goto out;
+	}
+
+	copy_user_huge_page(new_page, page, haddr, vma, HPAGE_PMD_NR);
+	__SetPageUptodate(new_page);
+
+	spin_lock(&mm->page_table_lock);
+	put_page(page);
+	if (unlikely(!pmd_same(*pmd, orig_pmd))) {
+		mem_cgroup_uncharge_page(new_page);
+		put_page(new_page);
+	} else {
+		pmd_t entry;
+		VM_BUG_ON(!PageHead(page));
+		entry = mk_pmd(new_page, vma->vm_page_prot);
+		entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+		entry = pmd_mkhuge(entry);
+		pmdp_clear_flush_notify(vma, haddr, pmd);
+		page_add_new_anon_rmap(new_page, vma, haddr);
+		set_pmd_at(mm, haddr, pmd, entry);
+		update_mmu_cache(vma, address, entry);
+		page_remove_rmap(page);
+		put_page(page);
+		ret |= VM_FAULT_WRITE;
+	}
+out_unlock:
+	spin_unlock(&mm->page_table_lock);
+out:
+	return ret;
+}
+
+struct page *follow_trans_huge_pmd(struct mm_struct *mm,
+				   unsigned long addr,
+				   pmd_t *pmd,
+				   unsigned int flags)
+{
+	struct page *page = NULL;
+
+	assert_spin_locked(&mm->page_table_lock);
+
+	if (flags & FOLL_WRITE && !pmd_write(*pmd))
+		goto out;
+
+	page = pmd_page(*pmd);
+	VM_BUG_ON(!PageHead(page));
+	if (flags & FOLL_TOUCH) {
+		pmd_t _pmd;
+		/*
+		 * We should set the dirty bit only for FOLL_WRITE but
+		 * for now the dirty bit in the pmd is meaningless.
+		 * And if the dirty bit will become meaningful and
+		 * we'll only set it with FOLL_WRITE, an atomic
+		 * set_bit will be required on the pmd to set the
+		 * young bit, instead of the current set_pmd_at.
+		 */
+		_pmd = pmd_mkyoung(pmd_mkdirty(*pmd));
+		set_pmd_at(mm, addr & HPAGE_PMD_MASK, pmd, _pmd);
+	}
+	page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT;
+	VM_BUG_ON(!PageCompound(page));
+	if (flags & FOLL_GET)
+		get_page(page);
+
+out:
+	return page;
+}
+
+int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		 pmd_t *pmd)
+{
+	int ret = 0;
+
+	spin_lock(&tlb->mm->page_table_lock);
+	if (likely(pmd_trans_huge(*pmd))) {
+		if (unlikely(pmd_trans_splitting(*pmd))) {
+			spin_unlock(&tlb->mm->page_table_lock);
+			wait_split_huge_page(vma->anon_vma,
+					     pmd);
+		} else {
+			struct page *page;
+			pgtable_t pgtable;
+			pgtable = get_pmd_huge_pte(tlb->mm);
+			page = pmd_page(*pmd);
+			pmd_clear(pmd);
+			page_remove_rmap(page);
+			VM_BUG_ON(page_mapcount(page) < 0);
+			add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR);
+			VM_BUG_ON(!PageHead(page));
+			spin_unlock(&tlb->mm->page_table_lock);
+			tlb_remove_page(tlb, page);
+			pte_free(tlb->mm, pgtable);
+			ret = 1;
+		}
+	} else
+		spin_unlock(&tlb->mm->page_table_lock);
+
+	return ret;
+}
+
+int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long addr, unsigned long end,
+		unsigned char *vec)
+{
+	int ret = 0;
+
+	spin_lock(&vma->vm_mm->page_table_lock);
+	if (likely(pmd_trans_huge(*pmd))) {
+		ret = !pmd_trans_splitting(*pmd);
+		spin_unlock(&vma->vm_mm->page_table_lock);
+		if (unlikely(!ret))
+			wait_split_huge_page(vma->anon_vma, pmd);
+		else {
+			/*
+			 * All logical pages in the range are present
+			 * if backed by a huge page.
+			 */
+			memset(vec, 1, (end - addr) >> PAGE_SHIFT);
+		}
+	} else
+		spin_unlock(&vma->vm_mm->page_table_lock);
+
+	return ret;
+}
+
+int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
+		unsigned long addr, pgprot_t newprot)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	int ret = 0;
+
+	spin_lock(&mm->page_table_lock);
+	if (likely(pmd_trans_huge(*pmd))) {
+		if (unlikely(pmd_trans_splitting(*pmd))) {
+			spin_unlock(&mm->page_table_lock);
+			wait_split_huge_page(vma->anon_vma, pmd);
+		} else {
+			pmd_t entry;
+
+			entry = pmdp_get_and_clear(mm, addr, pmd);
+			entry = pmd_modify(entry, newprot);
+			set_pmd_at(mm, addr, pmd, entry);
+			spin_unlock(&vma->vm_mm->page_table_lock);
+			flush_tlb_range(vma, addr, addr + HPAGE_PMD_SIZE);
+			ret = 1;
+		}
+	} else
+		spin_unlock(&vma->vm_mm->page_table_lock);
+
+	return ret;
+}
+
+pmd_t *page_check_address_pmd(struct page *page,
+			      struct mm_struct *mm,
+			      unsigned long address,
+			      enum page_check_address_pmd_flag flag)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd, *ret = NULL;
+
+	if (address & ~HPAGE_PMD_MASK)
+		goto out;
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		goto out;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		goto out;
+
+	pmd = pmd_offset(pud, address);
+	if (pmd_none(*pmd))
+		goto out;
+	if (pmd_page(*pmd) != page)
+		goto out;
+	/*
+	 * split_vma() may create temporary aliased mappings. There is
+	 * no risk as long as all huge pmd are found and have their
+	 * splitting bit set before __split_huge_page_refcount
+	 * runs. Finding the same huge pmd more than once during the
+	 * same rmap walk is not a problem.
+	 */
+	if (flag == PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG &&
+	    pmd_trans_splitting(*pmd))
+		goto out;
+	if (pmd_trans_huge(*pmd)) {
+		VM_BUG_ON(flag == PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG &&
+			  !pmd_trans_splitting(*pmd));
+		ret = pmd;
+	}
+out:
+	return ret;
+}
+
+static int __split_huge_page_splitting(struct page *page,
+				       struct vm_area_struct *vma,
+				       unsigned long address)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pmd_t *pmd;
+	int ret = 0;
+
+	spin_lock(&mm->page_table_lock);
+	pmd = page_check_address_pmd(page, mm, address,
+				     PAGE_CHECK_ADDRESS_PMD_NOTSPLITTING_FLAG);
+	if (pmd) {
+		/*
+		 * We can't temporarily set the pmd to null in order
+		 * to split it, the pmd must remain marked huge at all
+		 * times or the VM won't take the pmd_trans_huge paths
+		 * and it won't wait on the anon_vma->root->lock to
+		 * serialize against split_huge_page*.
+		 */
+		pmdp_splitting_flush_notify(vma, address, pmd);
+		ret = 1;
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	return ret;
+}
+
+static void __split_huge_page_refcount(struct page *page)
+{
+	int i;
+	unsigned long head_index = page->index;
+	struct zone *zone = page_zone(page);
+	int zonestat;
+
+	/* prevent PageLRU to go away from under us, and freeze lru stats */
+	spin_lock_irq(&zone->lru_lock);
+	compound_lock(page);
+
+	for (i = 1; i < HPAGE_PMD_NR; i++) {
+		struct page *page_tail = page + i;
+
+		/* tail_page->_count cannot change */
+		atomic_sub(atomic_read(&page_tail->_count), &page->_count);
+		BUG_ON(page_count(page) <= 0);
+		atomic_add(page_mapcount(page) + 1, &page_tail->_count);
+		BUG_ON(atomic_read(&page_tail->_count) <= 0);
+
+		/* after clearing PageTail the gup refcount can be released */
+		smp_mb();
+
+		/*
+		 * retain hwpoison flag of the poisoned tail page:
+		 *   fix for the unsuitable process killed on Guest Machine(KVM)
+		 *   by the memory-failure.
+		 */
+		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
+		page_tail->flags |= (page->flags &
+				     ((1L << PG_referenced) |
+				      (1L << PG_swapbacked) |
+				      (1L << PG_mlocked) |
+				      (1L << PG_uptodate)));
+		page_tail->flags |= (1L << PG_dirty);
+
+		/*
+		 * 1) clear PageTail before overwriting first_page
+		 * 2) clear PageTail before clearing PageHead for VM_BUG_ON
+		 */
+		smp_wmb();
+
+		/*
+		 * __split_huge_page_splitting() already set the
+		 * splitting bit in all pmd that could map this
+		 * hugepage, that will ensure no CPU can alter the
+		 * mapcount on the head page. The mapcount is only
+		 * accounted in the head page and it has to be
+		 * transferred to all tail pages in the below code. So
+		 * for this code to be safe, the split the mapcount
+		 * can't change. But that doesn't mean userland can't
+		 * keep changing and reading the page contents while
+		 * we transfer the mapcount, so the pmd splitting
+		 * status is achieved setting a reserved bit in the
+		 * pmd, not by clearing the present bit.
+		*/
+		BUG_ON(page_mapcount(page_tail));
+		page_tail->_mapcount = page->_mapcount;
+
+		BUG_ON(page_tail->mapping);
+		page_tail->mapping = page->mapping;
+
+		page_tail->index = ++head_index;
+
+		BUG_ON(!PageAnon(page_tail));
+		BUG_ON(!PageUptodate(page_tail));
+		BUG_ON(!PageDirty(page_tail));
+		BUG_ON(!PageSwapBacked(page_tail));
+
+		mem_cgroup_split_huge_fixup(page, page_tail);
+
+		lru_add_page_tail(zone, page, page_tail);
+	}
+
+	__dec_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
+	__mod_zone_page_state(zone, NR_ANON_PAGES, HPAGE_PMD_NR);
+
+	/*
+	 * A hugepage counts for HPAGE_PMD_NR pages on the LRU statistics,
+	 * so adjust those appropriately if this page is on the LRU.
+	 */
+	if (PageLRU(page)) {
+		zonestat = NR_LRU_BASE + page_lru(page);
+		__mod_zone_page_state(zone, zonestat, -(HPAGE_PMD_NR-1));
+	}
+
+	ClearPageCompound(page);
+	compound_unlock(page);
+	spin_unlock_irq(&zone->lru_lock);
+
+	for (i = 1; i < HPAGE_PMD_NR; i++) {
+		struct page *page_tail = page + i;
+		BUG_ON(page_count(page_tail) <= 0);
+		/*
+		 * Tail pages may be freed if there wasn't any mapping
+		 * like if add_to_swap() is running on a lru page that
+		 * had its mapping zapped. And freeing these pages
+		 * requires taking the lru_lock so we do the put_page
+		 * of the tail pages after the split is complete.
+		 */
+		put_page(page_tail);
+	}
+
+	/*
+	 * Only the head page (now become a regular page) is required
+	 * to be pinned by the caller.
+	 */
+	BUG_ON(page_count(page) <= 0);
+}
+
+static int __split_huge_page_map(struct page *page,
+				 struct vm_area_struct *vma,
+				 unsigned long address)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	pmd_t *pmd, _pmd;
+	int ret = 0, i;
+	pgtable_t pgtable;
+	unsigned long haddr;
+
+	spin_lock(&mm->page_table_lock);
+	pmd = page_check_address_pmd(page, mm, address,
+				     PAGE_CHECK_ADDRESS_PMD_SPLITTING_FLAG);
+	if (pmd) {
+		pgtable = get_pmd_huge_pte(mm);
+		pmd_populate(mm, &_pmd, pgtable);
+
+		for (i = 0, haddr = address; i < HPAGE_PMD_NR;
+		     i++, haddr += PAGE_SIZE) {
+			pte_t *pte, entry;
+			BUG_ON(PageCompound(page+i));
+			entry = mk_pte(page + i, vma->vm_page_prot);
+			entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+			if (!pmd_write(*pmd))
+				entry = pte_wrprotect(entry);
+			else
+				BUG_ON(page_mapcount(page) != 1);
+			if (!pmd_young(*pmd))
+				entry = pte_mkold(entry);
+			pte = pte_offset_map(&_pmd, haddr);
+			BUG_ON(!pte_none(*pte));
+			set_pte_at(mm, haddr, pte, entry);
+			pte_unmap(pte);
+		}
+
+		mm->nr_ptes++;
+		smp_wmb(); /* make pte visible before pmd */
+		/*
+		 * Up to this point the pmd is present and huge and
+		 * userland has the whole access to the hugepage
+		 * during the split (which happens in place). If we
+		 * overwrite the pmd with the not-huge version
+		 * pointing to the pte here (which of course we could
+		 * if all CPUs were bug free), userland could trigger
+		 * a small page size TLB miss on the small sized TLB
+		 * while the hugepage TLB entry is still established
+		 * in the huge TLB. Some CPU doesn't like that. See
+		 * http://support.amd.com/us/Processor_TechDocs/41322.pdf,
+		 * Erratum 383 on page 93. Intel should be safe but is
+		 * also warns that it's only safe if the permission
+		 * and cache attributes of the two entries loaded in
+		 * the two TLB is identical (which should be the case
+		 * here). But it is generally safer to never allow
+		 * small and huge TLB entries for the same virtual
+		 * address to be loaded simultaneously. So instead of
+		 * doing "pmd_populate(); flush_tlb_range();" we first
+		 * mark the current pmd notpresent (atomically because
+		 * here the pmd_trans_huge and pmd_trans_splitting
+		 * must remain set at all times on the pmd until the
+		 * split is complete for this pmd), then we flush the
+		 * SMP TLB and finally we write the non-huge version
+		 * of the pmd entry with pmd_populate.
+		 */
+		set_pmd_at(mm, address, pmd, pmd_mknotpresent(*pmd));
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+		pmd_populate(mm, pmd, pgtable);
+		ret = 1;
+	}
+	spin_unlock(&mm->page_table_lock);
+
+	return ret;
+}
+
+/* must be called with anon_vma->root->lock hold */
+static void __split_huge_page(struct page *page,
+			      struct anon_vma *anon_vma)
+{
+	int mapcount, mapcount2;
+	struct anon_vma_chain *avc;
+
+	BUG_ON(!PageHead(page));
+	BUG_ON(PageTail(page));
+
+	mapcount = 0;
+	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
+		struct vm_area_struct *vma = avc->vma;
+		unsigned long addr = vma_address(page, vma);
+		BUG_ON(is_vma_temporary_stack(vma));
+		if (addr == -EFAULT)
+			continue;
+		mapcount += __split_huge_page_splitting(page, vma, addr);
+	}
+	/*
+	 * It is critical that new vmas are added to the tail of the
+	 * anon_vma list. This guarantes that if copy_huge_pmd() runs
+	 * and establishes a child pmd before
+	 * __split_huge_page_splitting() freezes the parent pmd (so if
+	 * we fail to prevent copy_huge_pmd() from running until the
+	 * whole __split_huge_page() is complete), we will still see
+	 * the newly established pmd of the child later during the
+	 * walk, to be able to set it as pmd_trans_splitting too.
+	 */
+	if (mapcount != page_mapcount(page))
+		printk(KERN_ERR "mapcount %d page_mapcount %d\n",
+		       mapcount, page_mapcount(page));
+	BUG_ON(mapcount != page_mapcount(page));
+
+	__split_huge_page_refcount(page);
+
+	mapcount2 = 0;
+	list_for_each_entry(avc, &anon_vma->head, same_anon_vma) {
+		struct vm_area_struct *vma = avc->vma;
+		unsigned long addr = vma_address(page, vma);
+		BUG_ON(is_vma_temporary_stack(vma));
+		if (addr == -EFAULT)
+			continue;
+		mapcount2 += __split_huge_page_map(page, vma, addr);
+	}
+	if (mapcount != mapcount2)
+		printk(KERN_ERR "mapcount %d mapcount2 %d page_mapcount %d\n",
+		       mapcount, mapcount2, page_mapcount(page));
+	BUG_ON(mapcount != mapcount2);
+}
+
+int split_huge_page(struct page *page)
+{
+	struct anon_vma *anon_vma;
+	int ret = 1;
+
+	BUG_ON(!PageAnon(page));
+	anon_vma = page_lock_anon_vma(page);
+	if (!anon_vma)
+		goto out;
+	ret = 0;
+	if (!PageCompound(page))
+		goto out_unlock;
+
+	BUG_ON(!PageSwapBacked(page));
+	__split_huge_page(page, anon_vma);
+
+	BUG_ON(PageCompound(page));
+out_unlock:
+	page_unlock_anon_vma(anon_vma);
+out:
+	return ret;
+}
+
+int hugepage_madvise(struct vm_area_struct *vma,
+		     unsigned long *vm_flags, int advice)
+{
+	switch (advice) {
+	case MADV_HUGEPAGE:
+		/*
+		 * Be somewhat over-protective like KSM for now!
+		 */
+		if (*vm_flags & (VM_HUGEPAGE |
+				 VM_SHARED   | VM_MAYSHARE   |
+				 VM_PFNMAP   | VM_IO      | VM_DONTEXPAND |
+				 VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE |
+				 VM_MIXEDMAP | VM_SAO))
+			return -EINVAL;
+		*vm_flags &= ~VM_NOHUGEPAGE;
+		*vm_flags |= VM_HUGEPAGE;
+		/*
+		 * If the vma become good for khugepaged to scan,
+		 * register it here without waiting a page fault that
+		 * may not happen any time soon.
+		 */
+		if (unlikely(khugepaged_enter_vma_merge(vma)))
+			return -ENOMEM;
+		break;
+	case MADV_NOHUGEPAGE:
+		/*
+		 * Be somewhat over-protective like KSM for now!
+		 */
+		if (*vm_flags & (VM_NOHUGEPAGE |
+				 VM_SHARED   | VM_MAYSHARE   |
+				 VM_PFNMAP   | VM_IO      | VM_DONTEXPAND |
+				 VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE |
+				 VM_MIXEDMAP | VM_SAO))
+			return -EINVAL;
+		*vm_flags &= ~VM_HUGEPAGE;
+		*vm_flags |= VM_NOHUGEPAGE;
+		/*
+		 * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning
+		 * this vma even if we leave the mm registered in khugepaged if
+		 * it got registered before VM_NOHUGEPAGE was set.
+		 */
+		break;
+	}
+
+	return 0;
+}
+
+static int __init khugepaged_slab_init(void)
+{
+	mm_slot_cache = kmem_cache_create("khugepaged_mm_slot",
+					  sizeof(struct mm_slot),
+					  __alignof__(struct mm_slot), 0, NULL);
+	if (!mm_slot_cache)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void __init khugepaged_slab_free(void)
+{
+	kmem_cache_destroy(mm_slot_cache);
+	mm_slot_cache = NULL;
+}
+
+static inline struct mm_slot *alloc_mm_slot(void)
+{
+	if (!mm_slot_cache)	/* initialization failed */
+		return NULL;
+	return kmem_cache_zalloc(mm_slot_cache, GFP_KERNEL);
+}
+
+static inline void free_mm_slot(struct mm_slot *mm_slot)
+{
+	kmem_cache_free(mm_slot_cache, mm_slot);
+}
+
+static int __init mm_slots_hash_init(void)
+{
+	mm_slots_hash = kzalloc(MM_SLOTS_HASH_HEADS * sizeof(struct hlist_head),
+				GFP_KERNEL);
+	if (!mm_slots_hash)
+		return -ENOMEM;
+	return 0;
+}
+
+#if 0
+static void __init mm_slots_hash_free(void)
+{
+	kfree(mm_slots_hash);
+	mm_slots_hash = NULL;
+}
+#endif
+
+static struct mm_slot *get_mm_slot(struct mm_struct *mm)
+{
+	struct mm_slot *mm_slot;
+	struct hlist_head *bucket;
+	struct hlist_node *node;
+
+	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
+				% MM_SLOTS_HASH_HEADS];
+	hlist_for_each_entry(mm_slot, node, bucket, hash) {
+		if (mm == mm_slot->mm)
+			return mm_slot;
+	}
+	return NULL;
+}
+
+static void insert_to_mm_slots_hash(struct mm_struct *mm,
+				    struct mm_slot *mm_slot)
+{
+	struct hlist_head *bucket;
+
+	bucket = &mm_slots_hash[((unsigned long)mm / sizeof(struct mm_struct))
+				% MM_SLOTS_HASH_HEADS];
+	mm_slot->mm = mm;
+	hlist_add_head(&mm_slot->hash, bucket);
+}
+
+static inline int khugepaged_test_exit(struct mm_struct *mm)
+{
+	return atomic_read(&mm->mm_users) == 0;
+}
+
+int __khugepaged_enter(struct mm_struct *mm)
+{
+	struct mm_slot *mm_slot;
+	int wakeup;
+
+	mm_slot = alloc_mm_slot();
+	if (!mm_slot)
+		return -ENOMEM;
+
+	/* __khugepaged_exit() must not run from under us */
+	VM_BUG_ON(khugepaged_test_exit(mm));
+	if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) {
+		free_mm_slot(mm_slot);
+		return 0;
+	}
+
+	spin_lock(&khugepaged_mm_lock);
+	insert_to_mm_slots_hash(mm, mm_slot);
+	/*
+	 * Insert just behind the scanning cursor, to let the area settle
+	 * down a little.
+	 */
+	wakeup = list_empty(&khugepaged_scan.mm_head);
+	list_add_tail(&mm_slot->mm_node, &khugepaged_scan.mm_head);
+	spin_unlock(&khugepaged_mm_lock);
+
+	atomic_inc(&mm->mm_count);
+	if (wakeup)
+		wake_up_interruptible(&khugepaged_wait);
+
+	return 0;
+}
+
+int khugepaged_enter_vma_merge(struct vm_area_struct *vma)
+{
+	unsigned long hstart, hend;
+	if (!vma->anon_vma)
+		/*
+		 * Not yet faulted in so we will register later in the
+		 * page fault if needed.
+		 */
+		return 0;
+	if (vma->vm_file || vma->vm_ops)
+		/* khugepaged not yet working on file or special mappings */
+		return 0;
+	VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
+	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
+	hend = vma->vm_end & HPAGE_PMD_MASK;
+	if (hstart < hend)
+		return khugepaged_enter(vma);
+	return 0;
+}
+
+void __khugepaged_exit(struct mm_struct *mm)
+{
+	struct mm_slot *mm_slot;
+	int free = 0;
+
+	spin_lock(&khugepaged_mm_lock);
+	mm_slot = get_mm_slot(mm);
+	if (mm_slot && khugepaged_scan.mm_slot != mm_slot) {
+		hlist_del(&mm_slot->hash);
+		list_del(&mm_slot->mm_node);
+		free = 1;
+	}
+
+	if (free) {
+		spin_unlock(&khugepaged_mm_lock);
+		clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
+		free_mm_slot(mm_slot);
+		mmdrop(mm);
+	} else if (mm_slot) {
+		spin_unlock(&khugepaged_mm_lock);
+		/*
+		 * This is required to serialize against
+		 * khugepaged_test_exit() (which is guaranteed to run
+		 * under mmap sem read mode). Stop here (after we
+		 * return all pagetables will be destroyed) until
+		 * khugepaged has finished working on the pagetables
+		 * under the mmap_sem.
+		 */
+		down_write(&mm->mmap_sem);
+		up_write(&mm->mmap_sem);
+	} else
+		spin_unlock(&khugepaged_mm_lock);
+}
+
+static void release_pte_page(struct page *page)
+{
+	/* 0 stands for page_is_file_cache(page) == false */
+	dec_zone_page_state(page, NR_ISOLATED_ANON + 0);
+	unlock_page(page);
+	putback_lru_page(page);
+}
+
+static void release_pte_pages(pte_t *pte, pte_t *_pte)
+{
+	while (--_pte >= pte) {
+		pte_t pteval = *_pte;
+		if (!pte_none(pteval))
+			release_pte_page(pte_page(pteval));
+	}
+}
+
+static void release_all_pte_pages(pte_t *pte)
+{
+	release_pte_pages(pte, pte + HPAGE_PMD_NR);
+}
+
+static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
+					unsigned long address,
+					pte_t *pte)
+{
+	struct page *page;
+	pte_t *_pte;
+	int referenced = 0, isolated = 0, none = 0;
+	for (_pte = pte; _pte < pte+HPAGE_PMD_NR;
+	     _pte++, address += PAGE_SIZE) {
+		pte_t pteval = *_pte;
+		if (pte_none(pteval)) {
+			if (++none <= khugepaged_max_ptes_none)
+				continue;
+			else {
+				release_pte_pages(pte, _pte);
+				goto out;
+			}
+		}
+		if (!pte_present(pteval) || !pte_write(pteval)) {
+			release_pte_pages(pte, _pte);
+			goto out;
+		}
+		page = vm_normal_page(vma, address, pteval);
+		if (unlikely(!page)) {
+			release_pte_pages(pte, _pte);
+			goto out;
+		}
+		VM_BUG_ON(PageCompound(page));
+		BUG_ON(!PageAnon(page));
+		VM_BUG_ON(!PageSwapBacked(page));
+
+		/* cannot use mapcount: can't collapse if there's a gup pin */
+		if (page_count(page) != 1) {
+			release_pte_pages(pte, _pte);
+			goto out;
+		}
+		/*
+		 * We can do it before isolate_lru_page because the
+		 * page can't be freed from under us. NOTE: PG_lock
+		 * is needed to serialize against split_huge_page
+		 * when invoked from the VM.
+		 */
+		if (!trylock_page(page)) {
+			release_pte_pages(pte, _pte);
+			goto out;
+		}
+		/*
+		 * Isolate the page to avoid collapsing an hugepage
+		 * currently in use by the VM.
+		 */
+		if (isolate_lru_page(page)) {
+			unlock_page(page);
+			release_pte_pages(pte, _pte);
+			goto out;
+		}
+		/* 0 stands for page_is_file_cache(page) == false */
+		inc_zone_page_state(page, NR_ISOLATED_ANON + 0);
+		VM_BUG_ON(!PageLocked(page));
+		VM_BUG_ON(PageLRU(page));
+
+		/* If there is no mapped pte young don't collapse the page */
+		if (pte_young(pteval) || PageReferenced(page) ||
+		    mmu_notifier_test_young(vma->vm_mm, address))
+			referenced = 1;
+	}
+	if (unlikely(!referenced))
+		release_all_pte_pages(pte);
+	else
+		isolated = 1;
+out:
+	return isolated;
+}
+
+static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
+				      struct vm_area_struct *vma,
+				      unsigned long address,
+				      spinlock_t *ptl)
+{
+	pte_t *_pte;
+	for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) {
+		pte_t pteval = *_pte;
+		struct page *src_page;
+
+		if (pte_none(pteval)) {
+			clear_user_highpage(page, address);
+			add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1);
+		} else {
+			src_page = pte_page(pteval);
+			copy_user_highpage(page, src_page, address, vma);
+			VM_BUG_ON(page_mapcount(src_page) != 1);
+			VM_BUG_ON(page_count(src_page) != 2);
+			release_pte_page(src_page);
+			/*
+			 * ptl mostly unnecessary, but preempt has to
+			 * be disabled to update the per-cpu stats
+			 * inside page_remove_rmap().
+			 */
+			spin_lock(ptl);
+			/*
+			 * paravirt calls inside pte_clear here are
+			 * superfluous.
+			 */
+			pte_clear(vma->vm_mm, address, _pte);
+			page_remove_rmap(src_page);
+			spin_unlock(ptl);
+			free_page_and_swap_cache(src_page);
+		}
+
+		address += PAGE_SIZE;
+		page++;
+	}
+}
+
+static void collapse_huge_page(struct mm_struct *mm,
+			       unsigned long address,
+			       struct page **hpage,
+			       struct vm_area_struct *vma)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd, _pmd;
+	pte_t *pte;
+	pgtable_t pgtable;
+	struct page *new_page;
+	spinlock_t *ptl;
+	int isolated;
+	unsigned long hstart, hend;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+#ifndef CONFIG_NUMA
+	VM_BUG_ON(!*hpage);
+	new_page = *hpage;
+#else
+	VM_BUG_ON(*hpage);
+	/*
+	 * Allocate the page while the vma is still valid and under
+	 * the mmap_sem read mode so there is no memory allocation
+	 * later when we take the mmap_sem in write mode. This is more
+	 * friendly behavior (OTOH it may actually hide bugs) to
+	 * filesystems in userland with daemons allocating memory in
+	 * the userland I/O paths.  Allocating memory with the
+	 * mmap_sem in read mode is good idea also to allow greater
+	 * scalability.
+	 */
+	new_page = alloc_hugepage_vma(khugepaged_defrag(), vma, address);
+	if (unlikely(!new_page)) {
+		up_read(&mm->mmap_sem);
+		*hpage = ERR_PTR(-ENOMEM);
+		return;
+	}
+#endif
+	if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) {
+		up_read(&mm->mmap_sem);
+		put_page(new_page);
+		return;
+	}
+
+	/* after allocating the hugepage upgrade to mmap_sem write mode */
+	up_read(&mm->mmap_sem);
+
+	/*
+	 * Prevent all access to pagetables with the exception of
+	 * gup_fast later hanlded by the ptep_clear_flush and the VM
+	 * handled by the anon_vma lock + PG_lock.
+	 */
+	down_write(&mm->mmap_sem);
+	if (unlikely(khugepaged_test_exit(mm)))
+		goto out;
+
+	vma = find_vma(mm, address);
+	hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
+	hend = vma->vm_end & HPAGE_PMD_MASK;
+	if (address < hstart || address + HPAGE_PMD_SIZE > hend)
+		goto out;
+
+	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
+	    (vma->vm_flags & VM_NOHUGEPAGE))
+		goto out;
+
+	/* VM_PFNMAP vmas may have vm_ops null but vm_file set */
+	if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
+		goto out;
+	if (is_vma_temporary_stack(vma))
+		goto out;
+	VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		goto out;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		goto out;
+
+	pmd = pmd_offset(pud, address);
+	/* pmd can't go away or become huge under us */
+	if (!pmd_present(*pmd) || pmd_trans_huge(*pmd))
+		goto out;
+
+	anon_vma_lock(vma->anon_vma);
+
+	pte = pte_offset_map(pmd, address);
+	ptl = pte_lockptr(mm, pmd);
+
+	spin_lock(&mm->page_table_lock); /* probably unnecessary */
+	/*
+	 * After this gup_fast can't run anymore. This also removes
+	 * any huge TLB entry from the CPU so we won't allow
+	 * huge and small TLB entries for the same virtual address
+	 * to avoid the risk of CPU bugs in that area.
+	 */
+	_pmd = pmdp_clear_flush_notify(vma, address, pmd);
+	spin_unlock(&mm->page_table_lock);
+
+	spin_lock(ptl);
+	isolated = __collapse_huge_page_isolate(vma, address, pte);
+	spin_unlock(ptl);
+
+	if (unlikely(!isolated)) {
+		pte_unmap(pte);
+		spin_lock(&mm->page_table_lock);
+		BUG_ON(!pmd_none(*pmd));
+		set_pmd_at(mm, address, pmd, _pmd);
+		spin_unlock(&mm->page_table_lock);
+		anon_vma_unlock(vma->anon_vma);
+		goto out;
+	}
+
+	/*
+	 * All pages are isolated and locked so anon_vma rmap
+	 * can't run anymore.
+	 */
+	anon_vma_unlock(vma->anon_vma);
+
+	__collapse_huge_page_copy(pte, new_page, vma, address, ptl);
+	pte_unmap(pte);
+	__SetPageUptodate(new_page);
+	pgtable = pmd_pgtable(_pmd);
+	VM_BUG_ON(page_count(pgtable) != 1);
+	VM_BUG_ON(page_mapcount(pgtable) != 0);
+
+	_pmd = mk_pmd(new_page, vma->vm_page_prot);
+	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
+	_pmd = pmd_mkhuge(_pmd);
+
+	/*
+	 * spin_lock() below is not the equivalent of smp_wmb(), so
+	 * this is needed to avoid the copy_huge_page writes to become
+	 * visible after the set_pmd_at() write.
+	 */
+	smp_wmb();
+
+	spin_lock(&mm->page_table_lock);
+	BUG_ON(!pmd_none(*pmd));
+	page_add_new_anon_rmap(new_page, vma, address);
+	set_pmd_at(mm, address, pmd, _pmd);
+	update_mmu_cache(vma, address, entry);
+	prepare_pmd_huge_pte(pgtable, mm);
+	mm->nr_ptes--;
+	spin_unlock(&mm->page_table_lock);
+
+#ifndef CONFIG_NUMA
+	*hpage = NULL;
+#endif
+	khugepaged_pages_collapsed++;
+out_up_write:
+	up_write(&mm->mmap_sem);
+	return;
+
+out:
+	mem_cgroup_uncharge_page(new_page);
+#ifdef CONFIG_NUMA
+	put_page(new_page);
+#endif
+	goto out_up_write;
+}
+
+static int khugepaged_scan_pmd(struct mm_struct *mm,
+			       struct vm_area_struct *vma,
+			       unsigned long address,
+			       struct page **hpage)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte, *_pte;
+	int ret = 0, referenced = 0, none = 0;
+	struct page *page;
+	unsigned long _address;
+	spinlock_t *ptl;
+
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		goto out;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		goto out;
+
+	pmd = pmd_offset(pud, address);
+	if (!pmd_present(*pmd) || pmd_trans_huge(*pmd))
+		goto out;
+
+	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
+	for (_address = address, _pte = pte; _pte < pte+HPAGE_PMD_NR;
+	     _pte++, _address += PAGE_SIZE) {
+		pte_t pteval = *_pte;
+		if (pte_none(pteval)) {
+			if (++none <= khugepaged_max_ptes_none)
+				continue;
+			else
+				goto out_unmap;
+		}
+		if (!pte_present(pteval) || !pte_write(pteval))
+			goto out_unmap;
+		page = vm_normal_page(vma, _address, pteval);
+		if (unlikely(!page))
+			goto out_unmap;
+		VM_BUG_ON(PageCompound(page));
+		if (!PageLRU(page) || PageLocked(page) || !PageAnon(page))
+			goto out_unmap;
+		/* cannot use mapcount: can't collapse if there's a gup pin */
+		if (page_count(page) != 1)
+			goto out_unmap;
+		if (pte_young(pteval) || PageReferenced(page) ||
+		    mmu_notifier_test_young(vma->vm_mm, address))
+			referenced = 1;
+	}
+	if (referenced)
+		ret = 1;
+out_unmap:
+	pte_unmap_unlock(pte, ptl);
+	if (ret)
+		/* collapse_huge_page will return with the mmap_sem released */
+		collapse_huge_page(mm, address, hpage, vma);
+out:
+	return ret;
+}
+
+static void collect_mm_slot(struct mm_slot *mm_slot)
+{
+	struct mm_struct *mm = mm_slot->mm;
+
+	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+
+	if (khugepaged_test_exit(mm)) {
+		/* free mm_slot */
+		hlist_del(&mm_slot->hash);
+		list_del(&mm_slot->mm_node);
+
+		/*
+		 * Not strictly needed because the mm exited already.
+		 *
+		 * clear_bit(MMF_VM_HUGEPAGE, &mm->flags);
+		 */
+
+		/* khugepaged_mm_lock actually not necessary for the below */
+		free_mm_slot(mm_slot);
+		mmdrop(mm);
+	}
+}
+
+static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
+					    struct page **hpage)
+{
+	struct mm_slot *mm_slot;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma;
+	int progress = 0;
+
+	VM_BUG_ON(!pages);
+	VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock));
+
+	if (khugepaged_scan.mm_slot)
+		mm_slot = khugepaged_scan.mm_slot;
+	else {
+		mm_slot = list_entry(khugepaged_scan.mm_head.next,
+				     struct mm_slot, mm_node);
+		khugepaged_scan.address = 0;
+		khugepaged_scan.mm_slot = mm_slot;
+	}
+	spin_unlock(&khugepaged_mm_lock);
+
+	mm = mm_slot->mm;
+	down_read(&mm->mmap_sem);
+	if (unlikely(khugepaged_test_exit(mm)))
+		vma = NULL;
+	else
+		vma = find_vma(mm, khugepaged_scan.address);
+
+	progress++;
+	for (; vma; vma = vma->vm_next) {
+		unsigned long hstart, hend;
+
+		cond_resched();
+		if (unlikely(khugepaged_test_exit(mm))) {
+			progress++;
+			break;
+		}
+
+		if ((!(vma->vm_flags & VM_HUGEPAGE) &&
+		     !khugepaged_always()) ||
+		    (vma->vm_flags & VM_NOHUGEPAGE)) {
+		skip:
+			progress++;
+			continue;
+		}
+		/* VM_PFNMAP vmas may have vm_ops null but vm_file set */
+		if (!vma->anon_vma || vma->vm_ops || vma->vm_file)
+			goto skip;
+		if (is_vma_temporary_stack(vma))
+			goto skip;
+
+		VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma));
+
+		hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
+		hend = vma->vm_end & HPAGE_PMD_MASK;
+		if (hstart >= hend)
+			goto skip;
+		if (khugepaged_scan.address > hend)
+			goto skip;
+		if (khugepaged_scan.address < hstart)
+			khugepaged_scan.address = hstart;
+		VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK);
+
+		while (khugepaged_scan.address < hend) {
+			int ret;
+			cond_resched();
+			if (unlikely(khugepaged_test_exit(mm)))
+				goto breakouterloop;
+
+			VM_BUG_ON(khugepaged_scan.address < hstart ||
+				  khugepaged_scan.address + HPAGE_PMD_SIZE >
+				  hend);
+			ret = khugepaged_scan_pmd(mm, vma,
+						  khugepaged_scan.address,
+						  hpage);
+			/* move to next address */
+			khugepaged_scan.address += HPAGE_PMD_SIZE;
+			progress += HPAGE_PMD_NR;
+			if (ret)
+				/* we released mmap_sem so break loop */
+				goto breakouterloop_mmap_sem;
+			if (progress >= pages)
+				goto breakouterloop;
+		}
+	}
+breakouterloop:
+	up_read(&mm->mmap_sem); /* exit_mmap will destroy ptes after this */
+breakouterloop_mmap_sem:
+
+	spin_lock(&khugepaged_mm_lock);
+	VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot);
+	/*
+	 * Release the current mm_slot if this mm is about to die, or
+	 * if we scanned all vmas of this mm.
+	 */
+	if (khugepaged_test_exit(mm) || !vma) {
+		/*
+		 * Make sure that if mm_users is reaching zero while
+		 * khugepaged runs here, khugepaged_exit will find
+		 * mm_slot not pointing to the exiting mm.
+		 */
+		if (mm_slot->mm_node.next != &khugepaged_scan.mm_head) {
+			khugepaged_scan.mm_slot = list_entry(
+				mm_slot->mm_node.next,
+				struct mm_slot, mm_node);
+			khugepaged_scan.address = 0;
+		} else {
+			khugepaged_scan.mm_slot = NULL;
+			khugepaged_full_scans++;
+		}
+
+		collect_mm_slot(mm_slot);
+	}
+
+	return progress;
+}
+
+static int khugepaged_has_work(void)
+{
+	return !list_empty(&khugepaged_scan.mm_head) &&
+		khugepaged_enabled();
+}
+
+static int khugepaged_wait_event(void)
+{
+	return !list_empty(&khugepaged_scan.mm_head) ||
+		!khugepaged_enabled();
+}
+
+static void khugepaged_do_scan(struct page **hpage)
+{
+	unsigned int progress = 0, pass_through_head = 0;
+	unsigned int pages = khugepaged_pages_to_scan;
+
+	barrier(); /* write khugepaged_pages_to_scan to local stack */
+
+	while (progress < pages) {
+		cond_resched();
+
+#ifndef CONFIG_NUMA
+		if (!*hpage) {
+			*hpage = alloc_hugepage(khugepaged_defrag());
+			if (unlikely(!*hpage))
+				break;
+		}
+#else
+		if (IS_ERR(*hpage))
+			break;
+#endif
+
+		if (unlikely(kthread_should_stop() || freezing(current)))
+			break;
+
+		spin_lock(&khugepaged_mm_lock);
+		if (!khugepaged_scan.mm_slot)
+			pass_through_head++;
+		if (khugepaged_has_work() &&
+		    pass_through_head < 2)
+			progress += khugepaged_scan_mm_slot(pages - progress,
+							    hpage);
+		else
+			progress = pages;
+		spin_unlock(&khugepaged_mm_lock);
+	}
+}
+
+static void khugepaged_alloc_sleep(void)
+{
+	DEFINE_WAIT(wait);
+	add_wait_queue(&khugepaged_wait, &wait);
+	schedule_timeout_interruptible(
+		msecs_to_jiffies(
+			khugepaged_alloc_sleep_millisecs));
+	remove_wait_queue(&khugepaged_wait, &wait);
+}
+
+#ifndef CONFIG_NUMA
+static struct page *khugepaged_alloc_hugepage(void)
+{
+	struct page *hpage;
+
+	do {
+		hpage = alloc_hugepage(khugepaged_defrag());
+		if (!hpage)
+			khugepaged_alloc_sleep();
+	} while (unlikely(!hpage) &&
+		 likely(khugepaged_enabled()));
+	return hpage;
+}
+#endif
+
+static void khugepaged_loop(void)
+{
+	struct page *hpage;
+
+#ifdef CONFIG_NUMA
+	hpage = NULL;
+#endif
+	while (likely(khugepaged_enabled())) {
+#ifndef CONFIG_NUMA
+		hpage = khugepaged_alloc_hugepage();
+		if (unlikely(!hpage))
+			break;
+#else
+		if (IS_ERR(hpage)) {
+			khugepaged_alloc_sleep();
+			hpage = NULL;
+		}
+#endif
+
+		khugepaged_do_scan(&hpage);
+#ifndef CONFIG_NUMA
+		if (hpage)
+			put_page(hpage);
+#endif
+		try_to_freeze();
+		if (unlikely(kthread_should_stop()))
+			break;
+		if (khugepaged_has_work()) {
+			DEFINE_WAIT(wait);
+			if (!khugepaged_scan_sleep_millisecs)
+				continue;
+			add_wait_queue(&khugepaged_wait, &wait);
+			schedule_timeout_interruptible(
+				msecs_to_jiffies(
+					khugepaged_scan_sleep_millisecs));
+			remove_wait_queue(&khugepaged_wait, &wait);
+		} else if (khugepaged_enabled())
+			wait_event_freezable(khugepaged_wait,
+					     khugepaged_wait_event());
+	}
+}
+
+static int khugepaged(void *none)
+{
+	struct mm_slot *mm_slot;
+
+	set_freezable();
+	set_user_nice(current, 19);
+
+	/* serialize with start_khugepaged() */
+	mutex_lock(&khugepaged_mutex);
+
+	for (;;) {
+		mutex_unlock(&khugepaged_mutex);
+		VM_BUG_ON(khugepaged_thread != current);
+		khugepaged_loop();
+		VM_BUG_ON(khugepaged_thread != current);
+
+		mutex_lock(&khugepaged_mutex);
+		if (!khugepaged_enabled())
+			break;
+		if (unlikely(kthread_should_stop()))
+			break;
+	}
+
+	spin_lock(&khugepaged_mm_lock);
+	mm_slot = khugepaged_scan.mm_slot;
+	khugepaged_scan.mm_slot = NULL;
+	if (mm_slot)
+		collect_mm_slot(mm_slot);
+	spin_unlock(&khugepaged_mm_lock);
+
+	khugepaged_thread = NULL;
+	mutex_unlock(&khugepaged_mutex);
+
+	return 0;
+}
+
+void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *pmd)
+{
+	struct page *page;
+
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_trans_huge(*pmd))) {
+		spin_unlock(&mm->page_table_lock);
+		return;
+	}
+	page = pmd_page(*pmd);
+	VM_BUG_ON(!page_count(page));
+	get_page(page);
+	spin_unlock(&mm->page_table_lock);
+
+	split_huge_page(page);
+
+	put_page(page);
+	BUG_ON(pmd_trans_huge(*pmd));
+}
+
+static void split_huge_page_address(struct mm_struct *mm,
+				    unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	VM_BUG_ON(!(address & ~HPAGE_PMD_MASK));
+
+	pgd = pgd_offset(mm, address);
+	if (!pgd_present(*pgd))
+		return;
+
+	pud = pud_offset(pgd, address);
+	if (!pud_present(*pud))
+		return;
+
+	pmd = pmd_offset(pud, address);
+	if (!pmd_present(*pmd))
+		return;
+	/*
+	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
+	 * materialize from under us.
+	 */
+	split_huge_page_pmd(mm, pmd);
+}
+
+void __vma_adjust_trans_huge(struct vm_area_struct *vma,
+			     unsigned long start,
+			     unsigned long end,
+			     long adjust_next)
+{
+	/*
+	 * If the new start address isn't hpage aligned and it could
+	 * previously contain an hugepage: check if we need to split
+	 * an huge pmd.
+	 */
+	if (start & ~HPAGE_PMD_MASK &&
+	    (start & HPAGE_PMD_MASK) >= vma->vm_start &&
+	    (start & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
+		split_huge_page_address(vma->vm_mm, start);
+
+	/*
+	 * If the new end address isn't hpage aligned and it could
+	 * previously contain an hugepage: check if we need to split
+	 * an huge pmd.
+	 */
+	if (end & ~HPAGE_PMD_MASK &&
+	    (end & HPAGE_PMD_MASK) >= vma->vm_start &&
+	    (end & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= vma->vm_end)
+		split_huge_page_address(vma->vm_mm, end);
+
+	/*
+	 * If we're also updating the vma->vm_next->vm_start, if the new
+	 * vm_next->vm_start isn't page aligned and it could previously
+	 * contain an hugepage: check if we need to split an huge pmd.
+	 */
+	if (adjust_next > 0) {
+		struct vm_area_struct *next = vma->vm_next;
+		unsigned long nstart = next->vm_start;
+		nstart += adjust_next << PAGE_SHIFT;
+		if (nstart & ~HPAGE_PMD_MASK &&
+		    (nstart & HPAGE_PMD_MASK) >= next->vm_start &&
+		    (nstart & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE <= next->vm_end)
+			split_huge_page_address(next->vm_mm, nstart);
+	}
+}
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c03273807182..bb0b7c128015 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -394,67 +394,37 @@ static int vma_has_reserves(struct vm_area_struct *vma)
 	return 0;
 }
 
-static void clear_gigantic_page(struct page *page,
-			unsigned long addr, unsigned long sz)
+static void copy_gigantic_page(struct page *dst, struct page *src)
 {
 	int i;
-	struct page *p = page;
-
-	might_sleep();
-	for (i = 0; i < sz/PAGE_SIZE; i++, p = mem_map_next(p, page, i)) {
-		cond_resched();
-		clear_user_highpage(p, addr + i * PAGE_SIZE);
-	}
-}
-static void clear_huge_page(struct page *page,
-			unsigned long addr, unsigned long sz)
-{
-	int i;
-
-	if (unlikely(sz/PAGE_SIZE > MAX_ORDER_NR_PAGES)) {
-		clear_gigantic_page(page, addr, sz);
-		return;
-	}
-
-	might_sleep();
-	for (i = 0; i < sz/PAGE_SIZE; i++) {
-		cond_resched();
-		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
-	}
-}
-
-static void copy_gigantic_page(struct page *dst, struct page *src,
-			   unsigned long addr, struct vm_area_struct *vma)
-{
-	int i;
-	struct hstate *h = hstate_vma(vma);
+	struct hstate *h = page_hstate(src);
 	struct page *dst_base = dst;
 	struct page *src_base = src;
-	might_sleep();
+
 	for (i = 0; i < pages_per_huge_page(h); ) {
 		cond_resched();
-		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
+		copy_highpage(dst, src);
 
 		i++;
 		dst = mem_map_next(dst, dst_base, i);
 		src = mem_map_next(src, src_base, i);
 	}
 }
-static void copy_huge_page(struct page *dst, struct page *src,
-			   unsigned long addr, struct vm_area_struct *vma)
+
+void copy_huge_page(struct page *dst, struct page *src)
 {
 	int i;
-	struct hstate *h = hstate_vma(vma);
+	struct hstate *h = page_hstate(src);
 
 	if (unlikely(pages_per_huge_page(h) > MAX_ORDER_NR_PAGES)) {
-		copy_gigantic_page(dst, src, addr, vma);
+		copy_gigantic_page(dst, src);
 		return;
 	}
 
 	might_sleep();
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		cond_resched();
-		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
+		copy_highpage(dst + i, src + i);
 	}
 }
 
@@ -466,11 +436,24 @@ static void enqueue_huge_page(struct hstate *h, struct page *page)
 	h->free_huge_pages_node[nid]++;
 }
 
+static struct page *dequeue_huge_page_node(struct hstate *h, int nid)
+{
+	struct page *page;
+
+	if (list_empty(&h->hugepage_freelists[nid]))
+		return NULL;
+	page = list_entry(h->hugepage_freelists[nid].next, struct page, lru);
+	list_del(&page->lru);
+	set_page_refcounted(page);
+	h->free_huge_pages--;
+	h->free_huge_pages_node[nid]--;
+	return page;
+}
+
 static struct page *dequeue_huge_page_vma(struct hstate *h,
 				struct vm_area_struct *vma,
 				unsigned long address, int avoid_reserve)
 {
-	int nid;
 	struct page *page = NULL;
 	struct mempolicy *mpol;
 	nodemask_t *nodemask;
@@ -496,19 +479,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						MAX_NR_ZONES - 1, nodemask) {
-		nid = zone_to_nid(zone);
-		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask) &&
-		    !list_empty(&h->hugepage_freelists[nid])) {
-			page = list_entry(h->hugepage_freelists[nid].next,
-					  struct page, lru);
-			list_del(&page->lru);
-			h->free_huge_pages--;
-			h->free_huge_pages_node[nid]--;
-
-			if (!avoid_reserve)
-				decrement_hugepage_resv_vma(h, vma);
-
-			break;
+		if (cpuset_zone_allowed_softwall(zone, htlb_alloc_mask)) {
+			page = dequeue_huge_page_node(h, zone_to_nid(zone));
+			if (page) {
+				if (!avoid_reserve)
+					decrement_hugepage_resv_vma(h, vma);
+				break;
+			}
 		}
 	}
 err:
@@ -770,11 +747,10 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 	return ret;
 }
 
-static struct page *alloc_buddy_huge_page(struct hstate *h,
-			struct vm_area_struct *vma, unsigned long address)
+static struct page *alloc_buddy_huge_page(struct hstate *h, int nid)
 {
 	struct page *page;
-	unsigned int nid;
+	unsigned int r_nid;
 
 	if (h->order >= MAX_ORDER)
 		return NULL;
@@ -812,9 +788,14 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
 	}
 	spin_unlock(&hugetlb_lock);
 
-	page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
-					__GFP_REPEAT|__GFP_NOWARN,
-					huge_page_order(h));
+	if (nid == NUMA_NO_NODE)
+		page = alloc_pages(htlb_alloc_mask|__GFP_COMP|
+				   __GFP_REPEAT|__GFP_NOWARN,
+				   huge_page_order(h));
+	else
+		page = alloc_pages_exact_node(nid,
+			htlb_alloc_mask|__GFP_COMP|__GFP_THISNODE|
+			__GFP_REPEAT|__GFP_NOWARN, huge_page_order(h));
 
 	if (page && arch_prepare_hugepage(page)) {
 		__free_pages(page, huge_page_order(h));
@@ -823,19 +804,13 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
 
 	spin_lock(&hugetlb_lock);
 	if (page) {
-		/*
-		 * This page is now managed by the hugetlb allocator and has
-		 * no users -- drop the buddy allocator's reference.
-		 */
-		put_page_testzero(page);
-		VM_BUG_ON(page_count(page));
-		nid = page_to_nid(page);
+		r_nid = page_to_nid(page);
 		set_compound_page_dtor(page, free_huge_page);
 		/*
 		 * We incremented the global counters already
 		 */
-		h->nr_huge_pages_node[nid]++;
-		h->surplus_huge_pages_node[nid]++;
+		h->nr_huge_pages_node[r_nid]++;
+		h->surplus_huge_pages_node[r_nid]++;
 		__count_vm_event(HTLB_BUDDY_PGALLOC);
 	} else {
 		h->nr_huge_pages--;
@@ -848,6 +823,25 @@ static struct page *alloc_buddy_huge_page(struct hstate *h,
 }
 
 /*
+ * This allocation function is useful in the context where vma is irrelevant.
+ * E.g. soft-offlining uses this function because it only cares physical
+ * address of error page.
+ */
+struct page *alloc_huge_page_node(struct hstate *h, int nid)
+{
+	struct page *page;
+
+	spin_lock(&hugetlb_lock);
+	page = dequeue_huge_page_node(h, nid);
+	spin_unlock(&hugetlb_lock);
+
+	if (!page)
+		page = alloc_buddy_huge_page(h, nid);
+
+	return page;
+}
+
+/*
  * Increase the hugetlb pool such that it can accomodate a reservation
  * of size 'delta'.
  */
@@ -871,17 +865,14 @@ static int gather_surplus_pages(struct hstate *h, int delta)
 retry:
 	spin_unlock(&hugetlb_lock);
 	for (i = 0; i < needed; i++) {
-		page = alloc_buddy_huge_page(h, NULL, 0);
-		if (!page) {
+		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
+		if (!page)
 			/*
 			 * We were not able to allocate enough pages to
 			 * satisfy the entire reservation so we free what
 			 * we've allocated so far.
 			 */
-			spin_lock(&hugetlb_lock);
-			needed = 0;
 			goto free;
-		}
 
 		list_add(&page->lru, &surplus_list);
 	}
@@ -908,31 +899,31 @@ retry:
 	needed += allocated;
 	h->resv_huge_pages += delta;
 	ret = 0;
-free:
+
+	spin_unlock(&hugetlb_lock);
 	/* Free the needed pages to the hugetlb pool */
 	list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
 		if ((--needed) < 0)
 			break;
 		list_del(&page->lru);
+		/*
+		 * This page is now managed by the hugetlb allocator and has
+		 * no users -- drop the buddy allocator's reference.
+		 */
+		put_page_testzero(page);
+		VM_BUG_ON(page_count(page));
 		enqueue_huge_page(h, page);
 	}
 
 	/* Free unnecessary surplus pages to the buddy allocator */
+free:
 	if (!list_empty(&surplus_list)) {
-		spin_unlock(&hugetlb_lock);
 		list_for_each_entry_safe(page, tmp, &surplus_list, lru) {
 			list_del(&page->lru);
-			/*
-			 * The page has a reference count of zero already, so
-			 * call free_huge_page directly instead of using
-			 * put_page.  This must be done with hugetlb_lock
-			 * unlocked which is safe because free_huge_page takes
-			 * hugetlb_lock before deciding how to free the page.
-			 */
-			free_huge_page(page);
+			put_page(page);
 		}
-		spin_lock(&hugetlb_lock);
 	}
+	spin_lock(&hugetlb_lock);
 
 	return ret;
 }
@@ -1052,14 +1043,13 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
 	spin_unlock(&hugetlb_lock);
 
 	if (!page) {
-		page = alloc_buddy_huge_page(h, vma, addr);
+		page = alloc_buddy_huge_page(h, NUMA_NO_NODE);
 		if (!page) {
 			hugetlb_put_quota(inode->i_mapping, chg);
 			return ERR_PTR(-VM_FAULT_SIGBUS);
 		}
 	}
 
-	set_page_refcounted(page);
 	set_page_private(page, (unsigned long) mapping);
 
 	vma_commit_reservation(h, vma, addr);
@@ -1373,6 +1363,7 @@ static ssize_t nr_hugepages_show_common(struct kobject *kobj,
 
 	return sprintf(buf, "%lu\n", nr_huge_pages);
 }
+
 static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
 			struct kobject *kobj, struct kobj_attribute *attr,
 			const char *buf, size_t len)
@@ -1385,9 +1376,14 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
 
 	err = strict_strtoul(buf, 10, &count);
 	if (err)
-		return 0;
+		goto out;
 
 	h = kobj_to_hstate(kobj, &nid);
+	if (h->order >= MAX_ORDER) {
+		err = -EINVAL;
+		goto out;
+	}
+
 	if (nid == NUMA_NO_NODE) {
 		/*
 		 * global hstate attribute
@@ -1413,6 +1409,9 @@ static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
 		NODEMASK_FREE(nodes_allowed);
 
 	return len;
+out:
+	NODEMASK_FREE(nodes_allowed);
+	return err;
 }
 
 static ssize_t nr_hugepages_show(struct kobject *kobj,
@@ -1455,6 +1454,7 @@ static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
 	struct hstate *h = kobj_to_hstate(kobj, NULL);
 	return sprintf(buf, "%lu\n", h->nr_overcommit_huge_pages);
 }
+
 static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
 		struct kobj_attribute *attr, const char *buf, size_t count)
 {
@@ -1462,9 +1462,12 @@ static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
 	unsigned long input;
 	struct hstate *h = kobj_to_hstate(kobj, NULL);
 
+	if (h->order >= MAX_ORDER)
+		return -EINVAL;
+
 	err = strict_strtoul(buf, 10, &input);
 	if (err)
-		return 0;
+		return err;
 
 	spin_lock(&hugetlb_lock);
 	h->nr_overcommit_huge_pages = input;
@@ -1867,13 +1870,19 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 {
 	struct hstate *h = &default_hstate;
 	unsigned long tmp;
+	int ret;
 
 	if (!write)
 		tmp = h->max_huge_pages;
 
+	if (write && h->order >= MAX_ORDER)
+		return -EINVAL;
+
 	table->data = &tmp;
 	table->maxlen = sizeof(unsigned long);
-	proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	if (ret)
+		goto out;
 
 	if (write) {
 		NODEMASK_ALLOC(nodemask_t, nodes_allowed,
@@ -1888,8 +1897,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
 		if (nodes_allowed != &node_states[N_HIGH_MEMORY])
 			NODEMASK_FREE(nodes_allowed);
 	}
-
-	return 0;
+out:
+	return ret;
 }
 
 int hugetlb_sysctl_handler(struct ctl_table *table, int write,
@@ -1927,21 +1936,27 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write,
 {
 	struct hstate *h = &default_hstate;
 	unsigned long tmp;
+	int ret;
 
 	if (!write)
 		tmp = h->nr_overcommit_huge_pages;
 
+	if (write && h->order >= MAX_ORDER)
+		return -EINVAL;
+
 	table->data = &tmp;
 	table->maxlen = sizeof(unsigned long);
-	proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	ret = proc_doulongvec_minmax(table, write, buffer, length, ppos);
+	if (ret)
+		goto out;
 
 	if (write) {
 		spin_lock(&hugetlb_lock);
 		h->nr_overcommit_huge_pages = tmp;
 		spin_unlock(&hugetlb_lock);
 	}
-
-	return 0;
+out:
+	return ret;
 }
 
 #endif /* CONFIG_SYSCTL */
@@ -2153,6 +2168,19 @@ nomem:
 	return -ENOMEM;
 }
 
+static int is_hugetlb_entry_migration(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_migration_entry(swp)) {
+		return 1;
+	} else
+		return 0;
+}
+
 static int is_hugetlb_entry_hwpoisoned(pte_t pte)
 {
 	swp_entry_t swp;
@@ -2380,10 +2408,14 @@ retry_avoidcopy:
 	 * When the original hugepage is shared one, it does not have
 	 * anon_vma prepared.
 	 */
-	if (unlikely(anon_vma_prepare(vma)))
+	if (unlikely(anon_vma_prepare(vma))) {
+		/* Caller expects lock to be held */
+		spin_lock(&mm->page_table_lock);
 		return VM_FAULT_OOM;
+	}
 
-	copy_huge_page(new_page, old_page, address, vma);
+	copy_user_huge_page(new_page, old_page, address, vma,
+			    pages_per_huge_page(h));
 	__SetPageUptodate(new_page);
 
 	/*
@@ -2487,7 +2519,7 @@ retry:
 			ret = -PTR_ERR(page);
 			goto out;
 		}
-		clear_huge_page(page, address, huge_page_size(h));
+		clear_huge_page(page, address, pages_per_huge_page(h));
 		__SetPageUptodate(page);
 
 		if (vma->vm_flags & VM_MAYSHARE) {
@@ -2515,22 +2547,20 @@ retry:
 			hugepage_add_new_anon_rmap(page, vma, address);
 		}
 	} else {
+		/*
+		 * If memory error occurs between mmap() and fault, some process
+		 * don't have hwpoisoned swap entry for errored virtual address.
+		 * So we need to block hugepage fault by PG_hwpoison bit check.
+		 */
+		if (unlikely(PageHWPoison(page))) {
+			ret = VM_FAULT_HWPOISON | 
+			      VM_FAULT_SET_HINDEX(h - hstates);
+			goto backout_unlocked;
+		}
 		page_dup_rmap(page);
 	}
 
 	/*
-	 * Since memory error handler replaces pte into hwpoison swap entry
-	 * at the time of error handling, a process which reserved but not have
-	 * the mapping to the error hugepage does not have hwpoison swap entry.
-	 * So we need to block accesses from such a process by checking
-	 * PG_hwpoison bit here.
-	 */
-	if (unlikely(PageHWPoison(page))) {
-		ret = VM_FAULT_HWPOISON;
-		goto backout_unlocked;
-	}
-
-	/*
 	 * If we are going to COW a private mapping later, we examine the
 	 * pending reservations for this page now. This will ensure that
 	 * any allocations necessary to record that reservation occur outside
@@ -2587,8 +2617,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	ptep = huge_pte_offset(mm, address);
 	if (ptep) {
 		entry = huge_ptep_get(ptep);
-		if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
-			return VM_FAULT_HWPOISON;
+		if (unlikely(is_hugetlb_entry_migration(entry))) {
+			migration_entry_wait(mm, (pmd_t *)ptep, address);
+			return 0;
+		} else if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+			return VM_FAULT_HWPOISON_LARGE | 
+			       VM_FAULT_SET_HINDEX(h - hstates);
 	}
 
 	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
@@ -2665,7 +2699,8 @@ out_page_table_lock:
 		unlock_page(pagecache_page);
 		put_page(pagecache_page);
 	}
-	unlock_page(page);
+	if (page != pagecache_page)
+		unlock_page(page);
 
 out_mutex:
 	mutex_unlock(&hugetlb_instantiation_mutex);
@@ -2878,18 +2913,41 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	hugetlb_acct_memory(h, -(chg - freed));
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+
+/* Should be called in hugetlb_lock */
+static int is_hugepage_on_freelist(struct page *hpage)
+{
+	struct page *page;
+	struct page *tmp;
+	struct hstate *h = page_hstate(hpage);
+	int nid = page_to_nid(hpage);
+
+	list_for_each_entry_safe(page, tmp, &h->hugepage_freelists[nid], lru)
+		if (page == hpage)
+			return 1;
+	return 0;
+}
+
 /*
  * This function is called from memory failure code.
  * Assume the caller holds page lock of the head page.
  */
-void __isolate_hwpoisoned_huge_page(struct page *hpage)
+int dequeue_hwpoisoned_huge_page(struct page *hpage)
 {
 	struct hstate *h = page_hstate(hpage);
 	int nid = page_to_nid(hpage);
+	int ret = -EBUSY;
 
 	spin_lock(&hugetlb_lock);
-	list_del(&hpage->lru);
-	h->free_huge_pages--;
-	h->free_huge_pages_node[nid]--;
+	if (is_hugepage_on_freelist(hpage)) {
+		list_del(&hpage->lru);
+		set_page_refcounted(hpage);
+		h->free_huge_pages--;
+		h->free_huge_pages_node[nid]--;
+		ret = 0;
+	}
 	spin_unlock(&hugetlb_lock);
+	return ret;
 }
+#endif
diff --git a/mm/internal.h b/mm/internal.h
index 6a697bb97fc5..69488205723d 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -62,7 +62,7 @@ extern bool is_free_buddy_page(struct page *page);
  */
 static inline unsigned long page_order(struct page *page)
 {
-	VM_BUG_ON(!PageBuddy(page));
+	/* PageBuddy() must be checked by the caller */
 	return page_private(page);
 }
 
@@ -134,6 +134,10 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 	}
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+extern unsigned long vma_address(struct page *page,
+				 struct vm_area_struct *vma);
+#endif
 #else /* !CONFIG_MMU */
 static inline int is_mlocked_vma(struct vm_area_struct *v, struct page *p)
 {
@@ -243,7 +247,8 @@ static inline void mminit_validate_memmodel_limits(unsigned long *start_pfn,
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int len, unsigned int foll_flags,
-		     struct page **pages, struct vm_area_struct **vmas);
+		     struct page **pages, struct vm_area_struct **vmas,
+		     int *nonblocking);
 
 #define ZONE_RECLAIM_NOSCAN	-2
 #define ZONE_RECLAIM_FULL	-1
diff --git a/mm/kmemleak-test.c b/mm/kmemleak-test.c
index 177a5169bbde..ff0d9779cec8 100644
--- a/mm/kmemleak-test.c
+++ b/mm/kmemleak-test.c
@@ -75,13 +75,11 @@ static int __init kmemleak_test_init(void)
 	 * after the module is removed.
 	 */
 	for (i = 0; i < 10; i++) {
-		elem = kmalloc(sizeof(*elem), GFP_KERNEL);
-		pr_info("kmemleak: kmalloc(sizeof(*elem)) = %p\n", elem);
+		elem = kzalloc(sizeof(*elem), GFP_KERNEL);
+		pr_info("kmemleak: kzalloc(sizeof(*elem)) = %p\n", elem);
 		if (!elem)
 			return -ENOMEM;
-		memset(elem, 0, sizeof(*elem));
 		INIT_LIST_HEAD(&elem->list);
-
 		list_add_tail(&elem->list, &test_list);
 	}
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index bd9bc214091b..84225f3b7190 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -113,7 +113,9 @@
 #define BYTES_PER_POINTER	sizeof(void *)
 
 /* GFP bitmask for kmemleak internal allocations */
-#define GFP_KMEMLEAK_MASK	(GFP_KERNEL | GFP_ATOMIC)
+#define gfp_kmemleak_mask(gfp)	(((gfp) & (GFP_KERNEL | GFP_ATOMIC)) | \
+				 __GFP_NORETRY | __GFP_NOMEMALLOC | \
+				 __GFP_NOWARN)
 
 /* scanning area inside a memory block */
 struct kmemleak_scan_area {
@@ -511,9 +513,10 @@ static struct kmemleak_object *create_object(unsigned long ptr, size_t size,
 	struct kmemleak_object *object;
 	struct prio_tree_node *node;
 
-	object = kmem_cache_alloc(object_cache, gfp & GFP_KMEMLEAK_MASK);
+	object = kmem_cache_alloc(object_cache, gfp_kmemleak_mask(gfp));
 	if (!object) {
-		kmemleak_stop("Cannot allocate a kmemleak_object structure\n");
+		pr_warning("Cannot allocate a kmemleak_object structure\n");
+		kmemleak_disable();
 		return NULL;
 	}
 
@@ -734,9 +737,9 @@ static void add_scan_area(unsigned long ptr, size_t size, gfp_t gfp)
 		return;
 	}
 
-	area = kmem_cache_alloc(scan_area_cache, gfp & GFP_KMEMLEAK_MASK);
+	area = kmem_cache_alloc(scan_area_cache, gfp_kmemleak_mask(gfp));
 	if (!area) {
-		kmemleak_warn("Cannot allocate a scan area\n");
+		pr_warning("Cannot allocate a scan area\n");
 		goto out;
 	}
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 65ab5c7067d9..c2b2a94f9d67 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -34,6 +34,7 @@
 #include <linux/swap.h>
 #include <linux/ksm.h>
 #include <linux/hash.h>
+#include <linux/freezer.h>
 
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -411,6 +412,20 @@ out:
 	up_read(&mm->mmap_sem);
 }
 
+static struct page *page_trans_compound_anon(struct page *page)
+{
+	if (PageTransCompound(page)) {
+		struct page *head = compound_trans_head(page);
+		/*
+		 * head may actually be splitted and freed from under
+		 * us but it's ok here.
+		 */
+		if (PageAnon(head))
+			return head;
+	}
+	return NULL;
+}
+
 static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 {
 	struct mm_struct *mm = rmap_item->mm;
@@ -430,7 +445,7 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item)
 	page = follow_page(vma, addr, FOLL_GET);
 	if (IS_ERR_OR_NULL(page))
 		goto out;
-	if (PageAnon(page)) {
+	if (PageAnon(page) || page_trans_compound_anon(page)) {
 		flush_anon_page(vma, page, addr);
 		flush_dcache_page(page);
 	} else {
@@ -708,6 +723,7 @@ static int write_protect_page(struct vm_area_struct *vma, struct page *page,
 	if (addr == -EFAULT)
 		goto out;
 
+	BUG_ON(PageTransCompound(page));
 	ptep = page_check_address(page, mm, addr, &ptl, 0);
 	if (!ptep)
 		goto out;
@@ -783,6 +799,7 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 		goto out;
 
 	pmd = pmd_offset(pud, addr);
+	BUG_ON(pmd_trans_huge(*pmd));
 	if (!pmd_present(*pmd))
 		goto out;
 
@@ -800,6 +817,8 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	set_pte_at_notify(mm, addr, ptep, mk_pte(kpage, vma->vm_page_prot));
 
 	page_remove_rmap(page);
+	if (!page_mapped(page))
+		try_to_free_swap(page);
 	put_page(page);
 
 	pte_unmap_unlock(ptep, ptl);
@@ -808,6 +827,33 @@ out:
 	return err;
 }
 
+static int page_trans_compound_anon_split(struct page *page)
+{
+	int ret = 0;
+	struct page *transhuge_head = page_trans_compound_anon(page);
+	if (transhuge_head) {
+		/* Get the reference on the head to split it. */
+		if (get_page_unless_zero(transhuge_head)) {
+			/*
+			 * Recheck we got the reference while the head
+			 * was still anonymous.
+			 */
+			if (PageAnon(transhuge_head))
+				ret = split_huge_page(transhuge_head);
+			else
+				/*
+				 * Retry later if split_huge_page run
+				 * from under us.
+				 */
+				ret = 1;
+			put_page(transhuge_head);
+		} else
+			/* Retry later if split_huge_page run from under us. */
+			ret = 1;
+	}
+	return ret;
+}
+
 /*
  * try_to_merge_one_page - take two pages and merge them into one
  * @vma: the vma that holds the pte pointing to page
@@ -828,6 +874,9 @@ static int try_to_merge_one_page(struct vm_area_struct *vma,
 
 	if (!(vma->vm_flags & VM_MERGEABLE))
 		goto out;
+	if (PageTransCompound(page) && page_trans_compound_anon_split(page))
+		goto out;
+	BUG_ON(PageTransCompound(page));
 	if (!PageAnon(page))
 		goto out;
 
@@ -1247,6 +1296,18 @@ static struct rmap_item *scan_get_next_rmap_item(struct page **page)
 
 	slot = ksm_scan.mm_slot;
 	if (slot == &ksm_mm_head) {
+		/*
+		 * A number of pages can hang around indefinitely on per-cpu
+		 * pagevecs, raised page count preventing write_protect_page
+		 * from merging them.  Though it doesn't really matter much,
+		 * it is puzzling to see some stuck in pages_volatile until
+		 * other activity jostles them out, and they also prevented
+		 * LTP's KSM test from succeeding deterministically; so drain
+		 * them here (here rather than on entry to ksm_do_scan(),
+		 * so we don't IPI too often when pages_to_scan is set low).
+		 */
+		lru_add_drain_all();
+
 		root_unstable_tree = RB_ROOT;
 
 		spin_lock(&ksm_mmlist_lock);
@@ -1277,7 +1338,13 @@ next_mm:
 			if (ksm_test_exit(mm))
 				break;
 			*page = follow_page(vma, ksm_scan.address, FOLL_GET);
-			if (!IS_ERR_OR_NULL(*page) && PageAnon(*page)) {
+			if (IS_ERR_OR_NULL(*page)) {
+				ksm_scan.address += PAGE_SIZE;
+				cond_resched();
+				continue;
+			}
+			if (PageAnon(*page) ||
+			    page_trans_compound_anon(*page)) {
 				flush_anon_page(vma, *page, ksm_scan.address);
 				flush_dcache_page(*page);
 				rmap_item = get_next_rmap_item(slot,
@@ -1291,8 +1358,7 @@ next_mm:
 				up_read(&mm->mmap_sem);
 				return rmap_item;
 			}
-			if (!IS_ERR_OR_NULL(*page))
-				put_page(*page);
+			put_page(*page);
 			ksm_scan.address += PAGE_SIZE;
 			cond_resched();
 		}
@@ -1352,7 +1418,7 @@ static void ksm_do_scan(unsigned int scan_npages)
 	struct rmap_item *rmap_item;
 	struct page *uninitialized_var(page);
 
-	while (scan_npages--) {
+	while (scan_npages-- && likely(!freezing(current))) {
 		cond_resched();
 		rmap_item = scan_get_next_rmap_item(&page);
 		if (!rmap_item)
@@ -1370,6 +1436,7 @@ static int ksmd_should_run(void)
 
 static int ksm_scan_thread(void *nothing)
 {
+	set_freezable();
 	set_user_nice(current, 5);
 
 	while (!kthread_should_stop()) {
@@ -1378,11 +1445,13 @@ static int ksm_scan_thread(void *nothing)
 			ksm_do_scan(ksm_thread_pages_to_scan);
 		mutex_unlock(&ksm_thread_mutex);
 
+		try_to_freeze();
+
 		if (ksmd_should_run()) {
 			schedule_timeout_interruptible(
 				msecs_to_jiffies(ksm_thread_sleep_millisecs));
 		} else {
-			wait_event_interruptible(ksm_thread_wait,
+			wait_event_freezable(ksm_thread_wait,
 				ksmd_should_run() || kthread_should_stop());
 		}
 	}
@@ -1724,8 +1793,13 @@ static int ksm_memory_callback(struct notifier_block *self,
 		/*
 		 * Keep it very simple for now: just lock out ksmd and
 		 * MADV_UNMERGEABLE while any memory is going offline.
+		 * mutex_lock_nested() is necessary because lockdep was alarmed
+		 * that here we take ksm_thread_mutex inside notifier chain
+		 * mutex, and later take notifier chain mutex inside
+		 * ksm_thread_mutex to unlock it.   But that's safe because both
+		 * are inside mem_hotplug_mutex.
 		 */
-		mutex_lock(&ksm_thread_mutex);
+		mutex_lock_nested(&ksm_thread_mutex, SINGLE_DEPTH_NESTING);
 		break;
 
 	case MEM_OFFLINE:
diff --git a/mm/maccess.c b/mm/maccess.c
index 4e348dbaecd7..e2b6f5634e0d 100644
--- a/mm/maccess.c
+++ b/mm/maccess.c
@@ -1,9 +1,9 @@
 /*
  * Access kernel memory without faulting.
  */
-#include <linux/uaccess.h>
 #include <linux/module.h>
 #include <linux/mm.h>
+#include <linux/uaccess.h>
 
 /**
  * probe_kernel_read(): safely attempt to read from a location
diff --git a/mm/madvise.c b/mm/madvise.c
index 319528b8db74..2221491ed503 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -71,6 +71,12 @@ static long madvise_behavior(struct vm_area_struct * vma,
 		if (error)
 			goto out;
 		break;
+	case MADV_HUGEPAGE:
+	case MADV_NOHUGEPAGE:
+		error = hugepage_madvise(vma, &new_flags, behavior);
+		if (error)
+			goto out;
+		break;
 	}
 
 	if (new_flags == vma->vm_flags) {
@@ -283,6 +289,10 @@ madvise_behavior_valid(int behavior)
 	case MADV_MERGEABLE:
 	case MADV_UNMERGEABLE:
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	case MADV_HUGEPAGE:
+	case MADV_NOHUGEPAGE:
+#endif
 		return 1;
 
 	default:
diff --git a/mm/memblock.c b/mm/memblock.c
index 43840b305ecb..4618fda975a0 100644
--- a/mm/memblock.c
+++ b/mm/memblock.c
@@ -11,237 +11,421 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/bitops.h>
+#include <linux/poison.h>
+#include <linux/pfn.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
 #include <linux/memblock.h>
 
-#define MEMBLOCK_ALLOC_ANYWHERE	0
+struct memblock memblock __initdata_memblock;
 
-struct memblock memblock;
+int memblock_debug __initdata_memblock;
+int memblock_can_resize __initdata_memblock;
+static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
+static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS + 1] __initdata_memblock;
 
-static int memblock_debug;
+/* inline so we don't get a warning when pr_debug is compiled out */
+static inline const char *memblock_type_name(struct memblock_type *type)
+{
+	if (type == &memblock.memory)
+		return "memory";
+	else if (type == &memblock.reserved)
+		return "reserved";
+	else
+		return "unknown";
+}
 
-static int __init early_memblock(char *p)
+/*
+ * Address comparison utilities
+ */
+
+static phys_addr_t __init_memblock memblock_align_down(phys_addr_t addr, phys_addr_t size)
 {
-	if (p && strstr(p, "debug"))
-		memblock_debug = 1;
+	return addr & ~(size - 1);
+}
+
+static phys_addr_t __init_memblock memblock_align_up(phys_addr_t addr, phys_addr_t size)
+{
+	return (addr + (size - 1)) & ~(size - 1);
+}
+
+static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				       phys_addr_t base2, phys_addr_t size2)
+{
+	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
+}
+
+static long __init_memblock memblock_addrs_adjacent(phys_addr_t base1, phys_addr_t size1,
+			       phys_addr_t base2, phys_addr_t size2)
+{
+	if (base2 == base1 + size1)
+		return 1;
+	else if (base1 == base2 + size2)
+		return -1;
+
 	return 0;
 }
-early_param("memblock", early_memblock);
 
-static void memblock_dump(struct memblock_region *region, char *name)
+static long __init_memblock memblock_regions_adjacent(struct memblock_type *type,
+				 unsigned long r1, unsigned long r2)
 {
-	unsigned long long base, size;
-	int i;
+	phys_addr_t base1 = type->regions[r1].base;
+	phys_addr_t size1 = type->regions[r1].size;
+	phys_addr_t base2 = type->regions[r2].base;
+	phys_addr_t size2 = type->regions[r2].size;
 
-	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+	return memblock_addrs_adjacent(base1, size1, base2, size2);
+}
 
-	for (i = 0; i < region->cnt; i++) {
-		base = region->region[i].base;
-		size = region->region[i].size;
+long __init_memblock memblock_overlaps_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
+{
+	unsigned long i;
 
-		pr_info(" %s[0x%x]\t0x%016llx - 0x%016llx, 0x%llx bytes\n",
-		    name, i, base, base + size - 1, size);
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
+		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
+			break;
 	}
+
+	return (i < type->cnt) ? i : -1;
 }
 
-void memblock_dump_all(void)
+/*
+ * Find, allocate, deallocate or reserve unreserved regions. All allocations
+ * are top-down.
+ */
+
+static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_addr_t end,
+					  phys_addr_t size, phys_addr_t align)
 {
-	if (!memblock_debug)
-		return;
+	phys_addr_t base, res_base;
+	long j;
 
-	pr_info("MEMBLOCK configuration:\n");
-	pr_info(" rmo_size    = 0x%llx\n", (unsigned long long)memblock.rmo_size);
-	pr_info(" memory.size = 0x%llx\n", (unsigned long long)memblock.memory.size);
+	/* In case, huge size is requested */
+	if (end < size)
+		return MEMBLOCK_ERROR;
 
-	memblock_dump(&memblock.memory, "memory");
-	memblock_dump(&memblock.reserved, "reserved");
+	base = memblock_align_down((end - size), align);
+
+	/* Prevent allocations returning 0 as it's also used to
+	 * indicate an allocation failure
+	 */
+	if (start == 0)
+		start = PAGE_SIZE;
+
+	while (start <= base) {
+		j = memblock_overlaps_region(&memblock.reserved, base, size);
+		if (j < 0)
+			return base;
+		res_base = memblock.reserved.regions[j].base;
+		if (res_base < size)
+			break;
+		base = memblock_align_down(res_base - size, align);
+	}
+
+	return MEMBLOCK_ERROR;
 }
 
-static unsigned long memblock_addrs_overlap(u64 base1, u64 size1, u64 base2,
-					u64 size2)
+static phys_addr_t __init_memblock memblock_find_base(phys_addr_t size,
+			phys_addr_t align, phys_addr_t start, phys_addr_t end)
 {
-	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
+	long i;
+
+	BUG_ON(0 == size);
+
+	/* Pump up max_addr */
+	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
+		end = memblock.current_limit;
+
+	/* We do a top-down search, this tends to limit memory
+	 * fragmentation by keeping early boot allocs near the
+	 * top of memory
+	 */
+	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
+		phys_addr_t memblockbase = memblock.memory.regions[i].base;
+		phys_addr_t memblocksize = memblock.memory.regions[i].size;
+		phys_addr_t bottom, top, found;
+
+		if (memblocksize < size)
+			continue;
+		if ((memblockbase + memblocksize) <= start)
+			break;
+		bottom = max(memblockbase, start);
+		top = min(memblockbase + memblocksize, end);
+		if (bottom >= top)
+			continue;
+		found = memblock_find_region(bottom, top, size, align);
+		if (found != MEMBLOCK_ERROR)
+			return found;
+	}
+	return MEMBLOCK_ERROR;
 }
 
-static long memblock_addrs_adjacent(u64 base1, u64 size1, u64 base2, u64 size2)
+/*
+ * Find a free area with specified alignment in a specific range.
+ */
+u64 __init_memblock memblock_find_in_range(u64 start, u64 end, u64 size, u64 align)
 {
-	if (base2 == base1 + size1)
-		return 1;
-	else if (base1 == base2 + size2)
-		return -1;
+	return memblock_find_base(size, align, start, end);
+}
 
-	return 0;
+/*
+ * Free memblock.reserved.regions
+ */
+int __init_memblock memblock_free_reserved_regions(void)
+{
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
+
+	return memblock_free(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
 }
 
-static long memblock_regions_adjacent(struct memblock_region *rgn,
-		unsigned long r1, unsigned long r2)
+/*
+ * Reserve memblock.reserved.regions
+ */
+int __init_memblock memblock_reserve_reserved_regions(void)
 {
-	u64 base1 = rgn->region[r1].base;
-	u64 size1 = rgn->region[r1].size;
-	u64 base2 = rgn->region[r2].base;
-	u64 size2 = rgn->region[r2].size;
+	if (memblock.reserved.regions == memblock_reserved_init_regions)
+		return 0;
 
-	return memblock_addrs_adjacent(base1, size1, base2, size2);
+	return memblock_reserve(__pa(memblock.reserved.regions),
+		 sizeof(struct memblock_region) * memblock.reserved.max);
 }
 
-static void memblock_remove_region(struct memblock_region *rgn, unsigned long r)
+static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
 {
 	unsigned long i;
 
-	for (i = r; i < rgn->cnt - 1; i++) {
-		rgn->region[i].base = rgn->region[i + 1].base;
-		rgn->region[i].size = rgn->region[i + 1].size;
+	for (i = r; i < type->cnt - 1; i++) {
+		type->regions[i].base = type->regions[i + 1].base;
+		type->regions[i].size = type->regions[i + 1].size;
 	}
-	rgn->cnt--;
+	type->cnt--;
 }
 
 /* Assumption: base addr of region 1 < base addr of region 2 */
-static void memblock_coalesce_regions(struct memblock_region *rgn,
+static void __init_memblock memblock_coalesce_regions(struct memblock_type *type,
 		unsigned long r1, unsigned long r2)
 {
-	rgn->region[r1].size += rgn->region[r2].size;
-	memblock_remove_region(rgn, r2);
+	type->regions[r1].size += type->regions[r2].size;
+	memblock_remove_region(type, r2);
 }
 
-void __init memblock_init(void)
+/* Defined below but needed now */
+static long memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size);
+
+static int __init_memblock memblock_double_array(struct memblock_type *type)
 {
-	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
-	 * This simplifies the memblock_add() code below...
+	struct memblock_region *new_array, *old_array;
+	phys_addr_t old_size, new_size, addr;
+	int use_slab = slab_is_available();
+
+	/* We don't allow resizing until we know about the reserved regions
+	 * of memory that aren't suitable for allocation
 	 */
-	memblock.memory.region[0].base = 0;
-	memblock.memory.region[0].size = 0;
-	memblock.memory.cnt = 1;
+	if (!memblock_can_resize)
+		return -1;
 
-	/* Ditto. */
-	memblock.reserved.region[0].base = 0;
-	memblock.reserved.region[0].size = 0;
-	memblock.reserved.cnt = 1;
-}
+	/* Calculate new doubled size */
+	old_size = type->max * sizeof(struct memblock_region);
+	new_size = old_size << 1;
+
+	/* Try to find some space for it.
+	 *
+	 * WARNING: We assume that either slab_is_available() and we use it or
+	 * we use MEMBLOCK for allocations. That means that this is unsafe to use
+	 * when bootmem is currently active (unless bootmem itself is implemented
+	 * on top of MEMBLOCK which isn't the case yet)
+	 *
+	 * This should however not be an issue for now, as we currently only
+	 * call into MEMBLOCK while it's still active, or much later when slab is
+	 * active for memory hotplug operations
+	 */
+	if (use_slab) {
+		new_array = kmalloc(new_size, GFP_KERNEL);
+		addr = new_array == NULL ? MEMBLOCK_ERROR : __pa(new_array);
+	} else
+		addr = memblock_find_base(new_size, sizeof(phys_addr_t), 0, MEMBLOCK_ALLOC_ACCESSIBLE);
+	if (addr == MEMBLOCK_ERROR) {
+		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
+		       memblock_type_name(type), type->max, type->max * 2);
+		return -1;
+	}
+	new_array = __va(addr);
 
-void __init memblock_analyze(void)
-{
-	int i;
+	memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
+		 memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
 
-	memblock.memory.size = 0;
+	/* Found space, we now need to move the array over before
+	 * we add the reserved region since it may be our reserved
+	 * array itself that is full.
+	 */
+	memcpy(new_array, type->regions, old_size);
+	memset(new_array + type->max, 0, old_size);
+	old_array = type->regions;
+	type->regions = new_array;
+	type->max <<= 1;
+
+	/* If we use SLAB that's it, we are done */
+	if (use_slab)
+		return 0;
 
-	for (i = 0; i < memblock.memory.cnt; i++)
-		memblock.memory.size += memblock.memory.region[i].size;
+	/* Add the new reserved region now. Should not fail ! */
+	BUG_ON(memblock_add_region(&memblock.reserved, addr, new_size) < 0);
+
+	/* If the array wasn't our static init one, then free it. We only do
+	 * that before SLAB is available as later on, we don't know whether
+	 * to use kfree or free_bootmem_pages(). Shouldn't be a big deal
+	 * anyways
+	 */
+	if (old_array != memblock_memory_init_regions &&
+	    old_array != memblock_reserved_init_regions)
+		memblock_free(__pa(old_array), old_size);
+
+	return 0;
 }
 
-static long memblock_add_region(struct memblock_region *rgn, u64 base, u64 size)
+extern int __init_memblock __weak memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+					  phys_addr_t addr2, phys_addr_t size2)
+{
+	return 1;
+}
+
+static long __init_memblock memblock_add_region(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
 	unsigned long coalesced = 0;
 	long adjacent, i;
 
-	if ((rgn->cnt == 1) && (rgn->region[0].size == 0)) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if ((type->cnt == 1) && (type->regions[0].size == 0)) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
 		return 0;
 	}
 
 	/* First try and coalesce this MEMBLOCK with another. */
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
+	for (i = 0; i < type->cnt; i++) {
+		phys_addr_t rgnbase = type->regions[i].base;
+		phys_addr_t rgnsize = type->regions[i].size;
 
 		if ((rgnbase == base) && (rgnsize == size))
 			/* Already have this region, so we're done */
 			return 0;
 
 		adjacent = memblock_addrs_adjacent(base, size, rgnbase, rgnsize);
+		/* Check if arch allows coalescing */
+		if (adjacent != 0 && type == &memblock.memory &&
+		    !memblock_memory_can_coalesce(base, size, rgnbase, rgnsize))
+			break;
 		if (adjacent > 0) {
-			rgn->region[i].base -= size;
-			rgn->region[i].size += size;
+			type->regions[i].base -= size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		} else if (adjacent < 0) {
-			rgn->region[i].size += size;
+			type->regions[i].size += size;
 			coalesced++;
 			break;
 		}
 	}
 
-	if ((i < rgn->cnt - 1) && memblock_regions_adjacent(rgn, i, i+1)) {
-		memblock_coalesce_regions(rgn, i, i+1);
+	/* If we plugged a hole, we may want to also coalesce with the
+	 * next region
+	 */
+	if ((i < type->cnt - 1) && memblock_regions_adjacent(type, i, i+1) &&
+	    ((type != &memblock.memory || memblock_memory_can_coalesce(type->regions[i].base,
+							     type->regions[i].size,
+							     type->regions[i+1].base,
+							     type->regions[i+1].size)))) {
+		memblock_coalesce_regions(type, i, i+1);
 		coalesced++;
 	}
 
 	if (coalesced)
 		return coalesced;
-	if (rgn->cnt >= MAX_MEMBLOCK_REGIONS)
+
+	/* If we are out of space, we fail. It's too late to resize the array
+	 * but then this shouldn't have happened in the first place.
+	 */
+	if (WARN_ON(type->cnt >= type->max))
 		return -1;
 
 	/* Couldn't coalesce the MEMBLOCK, so add it to the sorted table. */
-	for (i = rgn->cnt - 1; i >= 0; i--) {
-		if (base < rgn->region[i].base) {
-			rgn->region[i+1].base = rgn->region[i].base;
-			rgn->region[i+1].size = rgn->region[i].size;
+	for (i = type->cnt - 1; i >= 0; i--) {
+		if (base < type->regions[i].base) {
+			type->regions[i+1].base = type->regions[i].base;
+			type->regions[i+1].size = type->regions[i].size;
 		} else {
-			rgn->region[i+1].base = base;
-			rgn->region[i+1].size = size;
+			type->regions[i+1].base = base;
+			type->regions[i+1].size = size;
 			break;
 		}
 	}
 
-	if (base < rgn->region[0].base) {
-		rgn->region[0].base = base;
-		rgn->region[0].size = size;
+	if (base < type->regions[0].base) {
+		type->regions[0].base = base;
+		type->regions[0].size = size;
+	}
+	type->cnt++;
+
+	/* The array is full ? Try to resize it. If that fails, we undo
+	 * our allocation and return an error
+	 */
+	if (type->cnt == type->max && memblock_double_array(type)) {
+		type->cnt--;
+		return -1;
 	}
-	rgn->cnt++;
 
 	return 0;
 }
 
-long memblock_add(u64 base, u64 size)
+long __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.memory;
-
-	/* On pSeries LPAR systems, the first MEMBLOCK is our RMO region. */
-	if (base == 0)
-		memblock.rmo_size = size;
-
-	return memblock_add_region(_rgn, base, size);
+	return memblock_add_region(&memblock.memory, base, size);
 
 }
 
-static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
+static long __init_memblock __memblock_remove(struct memblock_type *type, phys_addr_t base, phys_addr_t size)
 {
-	u64 rgnbegin, rgnend;
-	u64 end = base + size;
+	phys_addr_t rgnbegin, rgnend;
+	phys_addr_t end = base + size;
 	int i;
 
 	rgnbegin = rgnend = 0; /* supress gcc warnings */
 
 	/* Find the region where (base, size) belongs to */
-	for (i=0; i < rgn->cnt; i++) {
-		rgnbegin = rgn->region[i].base;
-		rgnend = rgnbegin + rgn->region[i].size;
+	for (i=0; i < type->cnt; i++) {
+		rgnbegin = type->regions[i].base;
+		rgnend = rgnbegin + type->regions[i].size;
 
 		if ((rgnbegin <= base) && (end <= rgnend))
 			break;
 	}
 
 	/* Didn't find the region */
-	if (i == rgn->cnt)
+	if (i == type->cnt)
 		return -1;
 
 	/* Check to see if we are removing entire region */
 	if ((rgnbegin == base) && (rgnend == end)) {
-		memblock_remove_region(rgn, i);
+		memblock_remove_region(type, i);
 		return 0;
 	}
 
 	/* Check to see if region is matching at the front */
 	if (rgnbegin == base) {
-		rgn->region[i].base = end;
-		rgn->region[i].size -= size;
+		type->regions[i].base = end;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
 	/* Check to see if the region is matching at the end */
 	if (rgnend == end) {
-		rgn->region[i].size -= size;
+		type->regions[i].size -= size;
 		return 0;
 	}
 
@@ -249,208 +433,189 @@ static long __memblock_remove(struct memblock_region *rgn, u64 base, u64 size)
 	 * We need to split the entry -  adjust the current one to the
 	 * beginging of the hole and add the region after hole.
 	 */
-	rgn->region[i].size = base - rgn->region[i].base;
-	return memblock_add_region(rgn, end, rgnend - end);
+	type->regions[i].size = base - type->regions[i].base;
+	return memblock_add_region(type, end, rgnend - end);
 }
 
-long memblock_remove(u64 base, u64 size)
+long __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.memory, base, size);
 }
 
-long __init memblock_free(u64 base, u64 size)
+long __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
 {
 	return __memblock_remove(&memblock.reserved, base, size);
 }
 
-long __init memblock_reserve(u64 base, u64 size)
+long __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
 {
-	struct memblock_region *_rgn = &memblock.reserved;
+	struct memblock_type *_rgn = &memblock.reserved;
 
 	BUG_ON(0 == size);
 
 	return memblock_add_region(_rgn, base, size);
 }
 
-long memblock_overlaps_region(struct memblock_region *rgn, u64 base, u64 size)
+phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	unsigned long i;
+	phys_addr_t found;
 
-	for (i = 0; i < rgn->cnt; i++) {
-		u64 rgnbase = rgn->region[i].base;
-		u64 rgnsize = rgn->region[i].size;
-		if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
-			break;
-	}
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
+	size = memblock_align_up(size, align);
+
+	found = memblock_find_base(size, align, 0, max_addr);
+	if (found != MEMBLOCK_ERROR &&
+	    memblock_add_region(&memblock.reserved, found, size) >= 0)
+		return found;
 
-	return (i < rgn->cnt) ? i : -1;
+	return 0;
 }
 
-static u64 memblock_align_down(u64 addr, u64 size)
+phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
 {
-	return addr & ~(size - 1);
+	phys_addr_t alloc;
+
+	alloc = __memblock_alloc_base(size, align, max_addr);
+
+	if (alloc == 0)
+		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
+		      (unsigned long long) size, (unsigned long long) max_addr);
+
+	return alloc;
 }
 
-static u64 memblock_align_up(u64 addr, u64 size)
+phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
 {
-	return (addr + (size - 1)) & ~(size - 1);
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
 }
 
-static u64 __init memblock_alloc_nid_unreserved(u64 start, u64 end,
-					   u64 size, u64 align)
+
+/*
+ * Additional node-local allocators. Search for node memory is bottom up
+ * and walks memblock regions within that node bottom-up as well, but allocation
+ * within an memblock region is top-down. XXX I plan to fix that at some stage
+ *
+ * WARNING: Only available after early_node_map[] has been populated,
+ * on some architectures, that is after all the calls to add_active_range()
+ * have been done to populate it.
+ */
+
+phys_addr_t __weak __init memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid)
 {
-	u64 base, res_base;
-	long j;
+#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
+	/*
+	 * This code originates from sparc which really wants use to walk by addresses
+	 * and returns the nid. This is not very convenient for early_pfn_map[] users
+	 * as the map isn't sorted yet, and it really wants to be walked by nid.
+	 *
+	 * For now, I implement the inefficient method below which walks the early
+	 * map multiple times. Eventually we may want to use an ARCH config option
+	 * to implement a completely different method for both case.
+	 */
+	unsigned long start_pfn, end_pfn;
+	int i;
 
-	base = memblock_align_down((end - size), align);
-	while (start <= base) {
-		j = memblock_overlaps_region(&memblock.reserved, base, size);
-		if (j < 0) {
-			/* this area isn't reserved, take it */
-			if (memblock_add_region(&memblock.reserved, base, size) < 0)
-				base = ~(u64)0;
-			return base;
-		}
-		res_base = memblock.reserved.region[j].base;
-		if (res_base < size)
-			break;
-		base = memblock_align_down(res_base - size, align);
+	for (i = 0; i < MAX_NUMNODES; i++) {
+		get_pfn_range_for_nid(i, &start_pfn, &end_pfn);
+		if (start < PFN_PHYS(start_pfn) || start >= PFN_PHYS(end_pfn))
+			continue;
+		*nid = i;
+		return min(end, PFN_PHYS(end_pfn));
 	}
+#endif
+	*nid = 0;
 
-	return ~(u64)0;
+	return end;
 }
 
-static u64 __init memblock_alloc_nid_region(struct memblock_property *mp,
-				       u64 (*nid_range)(u64, u64, int *),
-				       u64 size, u64 align, int nid)
+static phys_addr_t __init memblock_alloc_nid_region(struct memblock_region *mp,
+					       phys_addr_t size,
+					       phys_addr_t align, int nid)
 {
-	u64 start, end;
+	phys_addr_t start, end;
 
 	start = mp->base;
 	end = start + mp->size;
 
 	start = memblock_align_up(start, align);
 	while (start < end) {
-		u64 this_end;
+		phys_addr_t this_end;
 		int this_nid;
 
-		this_end = nid_range(start, end, &this_nid);
+		this_end = memblock_nid_range(start, end, &this_nid);
 		if (this_nid == nid) {
-			u64 ret = memblock_alloc_nid_unreserved(start, this_end,
-							   size, align);
-			if (ret != ~(u64)0)
+			phys_addr_t ret = memblock_find_region(start, this_end, size, align);
+			if (ret != MEMBLOCK_ERROR &&
+			    memblock_add_region(&memblock.reserved, ret, size) >= 0)
 				return ret;
 		}
 		start = this_end;
 	}
 
-	return ~(u64)0;
+	return MEMBLOCK_ERROR;
 }
 
-u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-			 u64 (*nid_range)(u64 start, u64 end, int *nid))
+phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	struct memblock_region *mem = &memblock.memory;
+	struct memblock_type *mem = &memblock.memory;
 	int i;
 
 	BUG_ON(0 == size);
 
+	/* We align the size to limit fragmentation. Without this, a lot of
+	 * small allocs quickly eat up the whole reserve array on sparc
+	 */
 	size = memblock_align_up(size, align);
 
+	/* We do a bottom-up search for a region with the right
+	 * nid since that's easier considering how memblock_nid_range()
+	 * works
+	 */
 	for (i = 0; i < mem->cnt; i++) {
-		u64 ret = memblock_alloc_nid_region(&mem->region[i],
-					       nid_range,
+		phys_addr_t ret = memblock_alloc_nid_region(&mem->regions[i],
 					       size, align, nid);
-		if (ret != ~(u64)0)
+		if (ret != MEMBLOCK_ERROR)
 			return ret;
 	}
 
-	return memblock_alloc(size, align);
-}
-
-u64 __init memblock_alloc(u64 size, u64 align)
-{
-	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
+	return 0;
 }
 
-u64 __init memblock_alloc_base(u64 size, u64 align, u64 max_addr)
+phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
 {
-	u64 alloc;
-
-	alloc = __memblock_alloc_base(size, align, max_addr);
+	phys_addr_t res = memblock_alloc_nid(size, align, nid);
 
-	if (alloc == 0)
-		panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
-		      (unsigned long long) size, (unsigned long long) max_addr);
-
-	return alloc;
+	if (res)
+		return res;
+	return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ANYWHERE);
 }
 
-u64 __init __memblock_alloc_base(u64 size, u64 align, u64 max_addr)
-{
-	long i, j;
-	u64 base = 0;
-	u64 res_base;
-
-	BUG_ON(0 == size);
-
-	size = memblock_align_up(size, align);
-
-	/* On some platforms, make sure we allocate lowmem */
-	/* Note that MEMBLOCK_REAL_LIMIT may be MEMBLOCK_ALLOC_ANYWHERE */
-	if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-		max_addr = MEMBLOCK_REAL_LIMIT;
-
-	for (i = memblock.memory.cnt - 1; i >= 0; i--) {
-		u64 memblockbase = memblock.memory.region[i].base;
-		u64 memblocksize = memblock.memory.region[i].size;
-
-		if (memblocksize < size)
-			continue;
-		if (max_addr == MEMBLOCK_ALLOC_ANYWHERE)
-			base = memblock_align_down(memblockbase + memblocksize - size, align);
-		else if (memblockbase < max_addr) {
-			base = min(memblockbase + memblocksize, max_addr);
-			base = memblock_align_down(base - size, align);
-		} else
-			continue;
 
-		while (base && memblockbase <= base) {
-			j = memblock_overlaps_region(&memblock.reserved, base, size);
-			if (j < 0) {
-				/* this area isn't reserved, take it */
-				if (memblock_add_region(&memblock.reserved, base, size) < 0)
-					return 0;
-				return base;
-			}
-			res_base = memblock.reserved.region[j].base;
-			if (res_base < size)
-				break;
-			base = memblock_align_down(res_base - size, align);
-		}
-	}
-	return 0;
-}
+/*
+ * Remaining API functions
+ */
 
 /* You must call memblock_analyze() before this. */
-u64 __init memblock_phys_mem_size(void)
+phys_addr_t __init memblock_phys_mem_size(void)
 {
-	return memblock.memory.size;
+	return memblock.memory_size;
 }
 
-u64 memblock_end_of_DRAM(void)
+phys_addr_t __init_memblock memblock_end_of_DRAM(void)
 {
 	int idx = memblock.memory.cnt - 1;
 
-	return (memblock.memory.region[idx].base + memblock.memory.region[idx].size);
+	return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
 }
 
 /* You must call memblock_analyze() after this. */
-void __init memblock_enforce_memory_limit(u64 memory_limit)
+void __init memblock_enforce_memory_limit(phys_addr_t memory_limit)
 {
 	unsigned long i;
-	u64 limit;
-	struct memblock_property *p;
+	phys_addr_t limit;
+	struct memblock_region *p;
 
 	if (!memory_limit)
 		return;
@@ -458,24 +623,21 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 	/* Truncate the memblock regions to satisfy the memory limit. */
 	limit = memory_limit;
 	for (i = 0; i < memblock.memory.cnt; i++) {
-		if (limit > memblock.memory.region[i].size) {
-			limit -= memblock.memory.region[i].size;
+		if (limit > memblock.memory.regions[i].size) {
+			limit -= memblock.memory.regions[i].size;
 			continue;
 		}
 
-		memblock.memory.region[i].size = limit;
+		memblock.memory.regions[i].size = limit;
 		memblock.memory.cnt = i + 1;
 		break;
 	}
 
-	if (memblock.memory.region[0].size < memblock.rmo_size)
-		memblock.rmo_size = memblock.memory.region[0].size;
-
 	memory_limit = memblock_end_of_DRAM();
 
 	/* And truncate any reserves above the limit also. */
 	for (i = 0; i < memblock.reserved.cnt; i++) {
-		p = &memblock.reserved.region[i];
+		p = &memblock.reserved.regions[i];
 
 		if (p->base > memory_limit)
 			p->size = 0;
@@ -489,53 +651,190 @@ void __init memblock_enforce_memory_limit(u64 memory_limit)
 	}
 }
 
-int __init memblock_is_reserved(u64 addr)
+static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
+{
+	unsigned int left = 0, right = type->cnt;
+
+	do {
+		unsigned int mid = (right + left) / 2;
+
+		if (addr < type->regions[mid].base)
+			right = mid;
+		else if (addr >= (type->regions[mid].base +
+				  type->regions[mid].size))
+			left = mid + 1;
+		else
+			return mid;
+	} while (left < right);
+	return -1;
+}
+
+int __init memblock_is_reserved(phys_addr_t addr)
+{
+	return memblock_search(&memblock.reserved, addr) != -1;
+}
+
+int __init_memblock memblock_is_memory(phys_addr_t addr)
+{
+	return memblock_search(&memblock.memory, addr) != -1;
+}
+
+int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
+{
+	int idx = memblock_search(&memblock.memory, base);
+
+	if (idx == -1)
+		return 0;
+	return memblock.memory.regions[idx].base <= base &&
+		(memblock.memory.regions[idx].base +
+		 memblock.memory.regions[idx].size) >= (base + size);
+}
+
+int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
+{
+	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+}
+
+
+void __init_memblock memblock_set_current_limit(phys_addr_t limit)
+{
+	memblock.current_limit = limit;
+}
+
+static void __init_memblock memblock_dump(struct memblock_type *region, char *name)
 {
+	unsigned long long base, size;
 	int i;
 
-	for (i = 0; i < memblock.reserved.cnt; i++) {
-		u64 upper = memblock.reserved.region[i].base +
-			memblock.reserved.region[i].size - 1;
-		if ((addr >= memblock.reserved.region[i].base) && (addr <= upper))
-			return 1;
+	pr_info(" %s.cnt  = 0x%lx\n", name, region->cnt);
+
+	for (i = 0; i < region->cnt; i++) {
+		base = region->regions[i].base;
+		size = region->regions[i].size;
+
+		pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes\n",
+		    name, i, base, base + size - 1, size);
 	}
-	return 0;
 }
 
-int memblock_is_region_reserved(u64 base, u64 size)
+void __init_memblock memblock_dump_all(void)
 {
-	return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
+	if (!memblock_debug)
+		return;
+
+	pr_info("MEMBLOCK configuration:\n");
+	pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
+
+	memblock_dump(&memblock.memory, "memory");
+	memblock_dump(&memblock.reserved, "reserved");
 }
 
-/*
- * Given a <base, len>, find which memory regions belong to this range.
- * Adjust the request and return a contiguous chunk.
- */
-int memblock_find(struct memblock_property *res)
+void __init memblock_analyze(void)
 {
 	int i;
-	u64 rstart, rend;
 
-	rstart = res->base;
-	rend = rstart + res->size - 1;
+	/* Check marker in the unused last array entry */
+	WARN_ON(memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+	WARN_ON(memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS].base
+		!= (phys_addr_t)RED_INACTIVE);
+
+	memblock.memory_size = 0;
+
+	for (i = 0; i < memblock.memory.cnt; i++)
+		memblock.memory_size += memblock.memory.regions[i].size;
+
+	/* We allow resizing from there */
+	memblock_can_resize = 1;
+}
+
+void __init memblock_init(void)
+{
+	static int init_done __initdata = 0;
+
+	if (init_done)
+		return;
+	init_done = 1;
+
+	/* Hookup the initial arrays */
+	memblock.memory.regions	= memblock_memory_init_regions;
+	memblock.memory.max		= INIT_MEMBLOCK_REGIONS;
+	memblock.reserved.regions	= memblock_reserved_init_regions;
+	memblock.reserved.max	= INIT_MEMBLOCK_REGIONS;
+
+	/* Write a marker in the unused last array entry */
+	memblock.memory.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+	memblock.reserved.regions[INIT_MEMBLOCK_REGIONS].base = (phys_addr_t)RED_INACTIVE;
+
+	/* Create a dummy zero size MEMBLOCK which will get coalesced away later.
+	 * This simplifies the memblock_add() code below...
+	 */
+	memblock.memory.regions[0].base = 0;
+	memblock.memory.regions[0].size = 0;
+	memblock.memory.cnt = 1;
+
+	/* Ditto. */
+	memblock.reserved.regions[0].base = 0;
+	memblock.reserved.regions[0].size = 0;
+	memblock.reserved.cnt = 1;
+
+	memblock.current_limit = MEMBLOCK_ALLOC_ANYWHERE;
+}
+
+static int __init early_memblock(char *p)
+{
+	if (p && strstr(p, "debug"))
+		memblock_debug = 1;
+	return 0;
+}
+early_param("memblock", early_memblock);
+
+#if defined(CONFIG_DEBUG_FS) && !defined(ARCH_DISCARD_MEMBLOCK)
+
+static int memblock_debug_show(struct seq_file *m, void *private)
+{
+	struct memblock_type *type = m->private;
+	struct memblock_region *reg;
+	int i;
+
+	for (i = 0; i < type->cnt; i++) {
+		reg = &type->regions[i];
+		seq_printf(m, "%4d: ", i);
+		if (sizeof(phys_addr_t) == 4)
+			seq_printf(m, "0x%08lx..0x%08lx\n",
+				   (unsigned long)reg->base,
+				   (unsigned long)(reg->base + reg->size - 1));
+		else
+			seq_printf(m, "0x%016llx..0x%016llx\n",
+				   (unsigned long long)reg->base,
+				   (unsigned long long)(reg->base + reg->size - 1));
 
-	for (i = 0; i < memblock.memory.cnt; i++) {
-		u64 start = memblock.memory.region[i].base;
-		u64 end = start + memblock.memory.region[i].size - 1;
-
-		if (start > rend)
-			return -1;
-
-		if ((end >= rstart) && (start < rend)) {
-			/* adjust the request */
-			if (rstart < start)
-				rstart = start;
-			if (rend > end)
-				rend = end;
-			res->base = rstart;
-			res->size = rend - rstart + 1;
-			return 0;
-		}
 	}
-	return -1;
+	return 0;
+}
+
+static int memblock_debug_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, memblock_debug_show, inode->i_private);
 }
+
+static const struct file_operations memblock_debug_fops = {
+	.open = memblock_debug_open,
+	.read = seq_read,
+	.llseek = seq_lseek,
+	.release = single_release,
+};
+
+static int __init memblock_init_debugfs(void)
+{
+	struct dentry *root = debugfs_create_dir("memblock", NULL);
+	if (!root)
+		return -ENXIO;
+	debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
+	debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
+
+	return 0;
+}
+__initcall(memblock_init_debugfs);
+
+#endif /* CONFIG_DEBUG_FS */
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 9be3cf8a5da4..da53a252b259 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -61,7 +61,14 @@ struct mem_cgroup *root_mem_cgroup __read_mostly;
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 /* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */
 int do_swap_account __read_mostly;
-static int really_do_swap_account __initdata = 1; /* for remember boot option*/
+
+/* for remember boot option*/
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP_ENABLED
+static int really_do_swap_account __initdata = 1;
+#else
+static int really_do_swap_account __initdata = 0;
+#endif
+
 #else
 #define do_swap_account		(0)
 #endif
@@ -89,7 +96,10 @@ enum mem_cgroup_stat_index {
 	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
 	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
 	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
-	MEM_CGROUP_EVENTS,	/* incremented at every  pagein/pageout */
+	MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */
+	/* incremented at every  pagein/pageout */
+	MEM_CGROUP_EVENTS = MEM_CGROUP_STAT_DATA,
+	MEM_CGROUP_ON_MOVE,	/* someone is moving account between groups */
 
 	MEM_CGROUP_STAT_NSTATS,
 };
@@ -254,6 +264,12 @@ struct mem_cgroup {
 	 * percpu counter.
 	 */
 	struct mem_cgroup_stat_cpu *stat;
+	/*
+	 * used when a cpu is offlined or other synchronizations
+	 * See mem_cgroup_read_stat().
+	 */
+	struct mem_cgroup_stat_cpu nocpu_base;
+	spinlock_t pcp_counter_lock;
 };
 
 /* Stuffs for move charges at task migration. */
@@ -269,7 +285,7 @@ enum move_type {
 
 /* "mc" and its members are protected by cgroup_mutex */
 static struct move_charge_struct {
-	spinlock_t	  lock; /* for from, to, moving_task */
+	spinlock_t	  lock; /* for from, to */
 	struct mem_cgroup *from;
 	struct mem_cgroup *to;
 	unsigned long precharge;
@@ -530,14 +546,40 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 	return mz;
 }
 
+/*
+ * Implementation Note: reading percpu statistics for memcg.
+ *
+ * Both of vmstat[] and percpu_counter has threshold and do periodic
+ * synchronization to implement "quick" read. There are trade-off between
+ * reading cost and precision of value. Then, we may have a chance to implement
+ * a periodic synchronizion of counter in memcg's counter.
+ *
+ * But this _read() function is used for user interface now. The user accounts
+ * memory usage by memory cgroup and he _always_ requires exact value because
+ * he accounts memory. Even if we provide quick-and-fuzzy read, we always
+ * have to visit all online cpus and make sum. So, for now, unnecessary
+ * synchronization is not implemented. (just implemented for cpu hotplug)
+ *
+ * If there are kernel internal actions which can make use of some not-exact
+ * value, and reading all cpu value can be performance bottleneck in some
+ * common workload, threashold and synchonization as vmstat[] should be
+ * implemented.
+ */
 static s64 mem_cgroup_read_stat(struct mem_cgroup *mem,
 		enum mem_cgroup_stat_index idx)
 {
 	int cpu;
 	s64 val = 0;
 
-	for_each_possible_cpu(cpu)
+	get_online_cpus();
+	for_each_online_cpu(cpu)
 		val += per_cpu(mem->stat->count[idx], cpu);
+#ifdef CONFIG_HOTPLUG_CPU
+	spin_lock(&mem->pcp_counter_lock);
+	val += mem->nocpu_base.count[idx];
+	spin_unlock(&mem->pcp_counter_lock);
+#endif
+	put_online_cpus();
 	return val;
 }
 
@@ -558,23 +600,24 @@ static void mem_cgroup_swap_statistics(struct mem_cgroup *mem,
 }
 
 static void mem_cgroup_charge_statistics(struct mem_cgroup *mem,
-					 struct page_cgroup *pc,
-					 bool charge)
+					 bool file, int nr_pages)
 {
-	int val = (charge) ? 1 : -1;
-
 	preempt_disable();
 
-	if (PageCgroupCache(pc))
-		__this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], val);
+	if (file)
+		__this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages);
 	else
-		__this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], val);
+		__this_cpu_add(mem->stat->count[MEM_CGROUP_STAT_RSS], nr_pages);
 
-	if (charge)
+	/* pagein of a big page is an event. So, ignore page size */
+	if (nr_pages > 0)
 		__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGIN_COUNT]);
-	else
+	else {
 		__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_PGPGOUT_COUNT]);
-	__this_cpu_inc(mem->stat->count[MEM_CGROUP_EVENTS]);
+		nr_pages = -nr_pages; /* for event */
+	}
+
+	__this_cpu_add(mem->stat->count[MEM_CGROUP_EVENTS], nr_pages);
 
 	preempt_enable();
 }
@@ -659,40 +702,83 @@ static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return mem;
 }
 
-/*
- * Call callback function against all cgroup under hierarchy tree.
- */
-static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data,
-			  int (*func)(struct mem_cgroup *, void *))
+/* The caller has to guarantee "mem" exists before calling this */
+static struct mem_cgroup *mem_cgroup_start_loop(struct mem_cgroup *mem)
 {
-	int found, ret, nextid;
 	struct cgroup_subsys_state *css;
-	struct mem_cgroup *mem;
+	int found;
 
-	if (!root->use_hierarchy)
-		return (*func)(root, data);
-
-	nextid = 1;
-	do {
-		ret = 0;
+	if (!mem) /* ROOT cgroup has the smallest ID */
+		return root_mem_cgroup; /*css_put/get against root is ignored*/
+	if (!mem->use_hierarchy) {
+		if (css_tryget(&mem->css))
+			return mem;
+		return NULL;
+	}
+	rcu_read_lock();
+	/*
+	 * searching a memory cgroup which has the smallest ID under given
+	 * ROOT cgroup. (ID >= 1)
+	 */
+	css = css_get_next(&mem_cgroup_subsys, 1, &mem->css, &found);
+	if (css && css_tryget(css))
+		mem = container_of(css, struct mem_cgroup, css);
+	else
 		mem = NULL;
+	rcu_read_unlock();
+	return mem;
+}
 
+static struct mem_cgroup *mem_cgroup_get_next(struct mem_cgroup *iter,
+					struct mem_cgroup *root,
+					bool cond)
+{
+	int nextid = css_id(&iter->css) + 1;
+	int found;
+	int hierarchy_used;
+	struct cgroup_subsys_state *css;
+
+	hierarchy_used = iter->use_hierarchy;
+
+	css_put(&iter->css);
+	/* If no ROOT, walk all, ignore hierarchy */
+	if (!cond || (root && !hierarchy_used))
+		return NULL;
+
+	if (!root)
+		root = root_mem_cgroup;
+
+	do {
+		iter = NULL;
 		rcu_read_lock();
-		css = css_get_next(&mem_cgroup_subsys, nextid, &root->css,
-				   &found);
+
+		css = css_get_next(&mem_cgroup_subsys, nextid,
+				&root->css, &found);
 		if (css && css_tryget(css))
-			mem = container_of(css, struct mem_cgroup, css);
+			iter = container_of(css, struct mem_cgroup, css);
 		rcu_read_unlock();
-
-		if (mem) {
-			ret = (*func)(mem, data);
-			css_put(&mem->css);
-		}
+		/* If css is NULL, no more cgroups will be found */
 		nextid = found + 1;
-	} while (!ret && css);
+	} while (css && !iter);
 
-	return ret;
+	return iter;
 }
+/*
+ * for_eacn_mem_cgroup_tree() for visiting all cgroup under tree. Please
+ * be careful that "break" loop is not allowed. We have reference count.
+ * Instead of that modify "cond" to be false and "continue" to exit the loop.
+ */
+#define for_each_mem_cgroup_tree_cond(iter, root, cond)	\
+	for (iter = mem_cgroup_start_loop(root);\
+	     iter != NULL;\
+	     iter = mem_cgroup_get_next(iter, root, cond))
+
+#define for_each_mem_cgroup_tree(iter, root) \
+	for_each_mem_cgroup_tree_cond(iter, root, true)
+
+#define for_each_mem_cgroup_all(iter) \
+	for_each_mem_cgroup_tree_cond(iter, NULL, true)
+
 
 static inline bool mem_cgroup_is_root(struct mem_cgroup *mem)
 {
@@ -730,12 +816,12 @@ void mem_cgroup_del_lru_list(struct page *page, enum lru_list lru)
 	 * removed from global LRU.
 	 */
 	mz = page_cgroup_zoneinfo(pc);
-	MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	/* huge page split is done under lru_lock. so, we have no races. */
+	MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page);
 	if (mem_cgroup_is_root(pc->mem_cgroup))
 		return;
 	VM_BUG_ON(list_empty(&pc->lru));
 	list_del_init(&pc->lru);
-	return;
 }
 
 void mem_cgroup_del_lru(struct page *page)
@@ -752,13 +838,12 @@ void mem_cgroup_rotate_lru_list(struct page *page, enum lru_list lru)
 		return;
 
 	pc = lookup_page_cgroup(page);
-	/*
-	 * Used bit is set without atomic ops but after smp_wmb().
-	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
-	 */
-	smp_rmb();
 	/* unused or root page is not rotated. */
-	if (!PageCgroupUsed(pc) || mem_cgroup_is_root(pc->mem_cgroup))
+	if (!PageCgroupUsed(pc))
+		return;
+	/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+	smp_rmb();
+	if (mem_cgroup_is_root(pc->mem_cgroup))
 		return;
 	mz = page_cgroup_zoneinfo(pc);
 	list_move(&pc->lru, &mz->lists[lru]);
@@ -773,16 +858,13 @@ void mem_cgroup_add_lru_list(struct page *page, enum lru_list lru)
 		return;
 	pc = lookup_page_cgroup(page);
 	VM_BUG_ON(PageCgroupAcctLRU(pc));
-	/*
-	 * Used bit is set without atomic ops but after smp_wmb().
-	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
-	 */
-	smp_rmb();
 	if (!PageCgroupUsed(pc))
 		return;
-
+	/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+	smp_rmb();
 	mz = page_cgroup_zoneinfo(pc);
-	MEM_CGROUP_ZSTAT(mz, lru) += 1;
+	/* huge page split is done under lru_lock. so, we have no races. */
+	MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page);
 	SetPageCgroupAcctLRU(pc);
 	if (mem_cgroup_is_root(pc->mem_cgroup))
 		return;
@@ -946,14 +1028,10 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 		return NULL;
 
 	pc = lookup_page_cgroup(page);
-	/*
-	 * Used bit is set without atomic ops but after smp_wmb().
-	 * For making pc->mem_cgroup visible, insert smp_rmb() here.
-	 */
-	smp_rmb();
 	if (!PageCgroupUsed(pc))
 		return NULL;
-
+	/* Ensure pc->mem_cgroup is visible after reading PCG_USED. */
+	smp_rmb();
 	mz = page_cgroup_zoneinfo(pc);
 	if (!mz)
 		return NULL;
@@ -1001,7 +1079,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 		case 0:
 			list_move(&page->lru, dst);
 			mem_cgroup_del_lru(page);
-			nr_taken++;
+			nr_taken += hpage_nr_pages(page);
 			break;
 		case -EBUSY:
 			/* we don't affect global LRU but rotate in our LRU */
@@ -1035,6 +1113,23 @@ static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
 	return false;
 }
 
+/**
+ * mem_cgroup_check_margin - check if the memory cgroup allows charging
+ * @mem: memory cgroup to check
+ * @bytes: the number of bytes the caller intends to charge
+ *
+ * Returns a boolean value on whether @mem can be charged @bytes or
+ * whether this would exceed the limit.
+ */
+static bool mem_cgroup_check_margin(struct mem_cgroup *mem, unsigned long bytes)
+{
+	if (!res_counter_check_margin(&mem->res, bytes))
+		return false;
+	if (do_swap_account && !res_counter_check_margin(&mem->memsw, bytes))
+		return false;
+	return true;
+}
+
 static unsigned int get_swappiness(struct mem_cgroup *memcg)
 {
 	struct cgroup *cgrp = memcg->css.cgroup;
@@ -1051,7 +1146,52 @@ static unsigned int get_swappiness(struct mem_cgroup *memcg)
 	return swappiness;
 }
 
-/* A routine for testing mem is not under move_account */
+static void mem_cgroup_start_move(struct mem_cgroup *mem)
+{
+	int cpu;
+
+	get_online_cpus();
+	spin_lock(&mem->pcp_counter_lock);
+	for_each_online_cpu(cpu)
+		per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1;
+	mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1;
+	spin_unlock(&mem->pcp_counter_lock);
+	put_online_cpus();
+
+	synchronize_rcu();
+}
+
+static void mem_cgroup_end_move(struct mem_cgroup *mem)
+{
+	int cpu;
+
+	if (!mem)
+		return;
+	get_online_cpus();
+	spin_lock(&mem->pcp_counter_lock);
+	for_each_online_cpu(cpu)
+		per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1;
+	mem->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1;
+	spin_unlock(&mem->pcp_counter_lock);
+	put_online_cpus();
+}
+/*
+ * 2 routines for checking "mem" is under move_account() or not.
+ *
+ * mem_cgroup_stealed() - checking a cgroup is mc.from or not. This is used
+ *			  for avoiding race in accounting. If true,
+ *			  pc->mem_cgroup may be overwritten.
+ *
+ * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or
+ *			  under hierarchy of moving cgroups. This is for
+ *			  waiting at hith-memory prressure caused by "move".
+ */
+
+static bool mem_cgroup_stealed(struct mem_cgroup *mem)
+{
+	VM_BUG_ON(!rcu_read_lock_held());
+	return this_cpu_read(mem->stat->count[MEM_CGROUP_ON_MOVE]) > 0;
+}
 
 static bool mem_cgroup_under_move(struct mem_cgroup *mem)
 {
@@ -1092,13 +1232,6 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *mem)
 	return false;
 }
 
-static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
-{
-	int *val = data;
-	(*val)++;
-	return 0;
-}
-
 /**
  * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode.
  * @memcg: The memory cgroup that went over limit
@@ -1173,7 +1306,10 @@ done:
 static int mem_cgroup_count_children(struct mem_cgroup *mem)
 {
 	int num = 0;
- 	mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+	struct mem_cgroup *iter;
+
+	for_each_mem_cgroup_tree(iter, mem)
+		num++;
 	return num;
 }
 
@@ -1185,8 +1321,9 @@ u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	u64 limit;
 	u64 memsw;
 
-	limit = res_counter_read_u64(&memcg->res, RES_LIMIT) +
-			total_swap_pages;
+	limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+	limit += total_swap_pages << PAGE_SHIFT;
+
 	memsw = res_counter_read_u64(&memcg->memsw, RES_LIMIT);
 	/*
 	 * If memsw is finite and limits the amount of swap space available
@@ -1322,49 +1459,39 @@ static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
 	return total;
 }
 
-static int mem_cgroup_oom_lock_cb(struct mem_cgroup *mem, void *data)
-{
-	int *val = (int *)data;
-	int x;
-	/*
-	 * Logically, we can stop scanning immediately when we find
-	 * a memcg is already locked. But condidering unlock ops and
-	 * creation/removal of memcg, scan-all is simple operation.
-	 */
-	x = atomic_inc_return(&mem->oom_lock);
-	*val = max(x, *val);
-	return 0;
-}
 /*
  * Check OOM-Killer is already running under our hierarchy.
  * If someone is running, return false.
  */
 static bool mem_cgroup_oom_lock(struct mem_cgroup *mem)
 {
-	int lock_count = 0;
+	int x, lock_count = 0;
+	struct mem_cgroup *iter;
 
-	mem_cgroup_walk_tree(mem, &lock_count, mem_cgroup_oom_lock_cb);
+	for_each_mem_cgroup_tree(iter, mem) {
+		x = atomic_inc_return(&iter->oom_lock);
+		lock_count = max(x, lock_count);
+	}
 
 	if (lock_count == 1)
 		return true;
 	return false;
 }
 
-static int mem_cgroup_oom_unlock_cb(struct mem_cgroup *mem, void *data)
+static int mem_cgroup_oom_unlock(struct mem_cgroup *mem)
 {
+	struct mem_cgroup *iter;
+
 	/*
 	 * When a new child is created while the hierarchy is under oom,
 	 * mem_cgroup_oom_lock() may not be called. We have to use
 	 * atomic_add_unless() here.
 	 */
-	atomic_add_unless(&mem->oom_lock, -1, 0);
+	for_each_mem_cgroup_tree(iter, mem)
+		atomic_add_unless(&iter->oom_lock, -1, 0);
 	return 0;
 }
 
-static void mem_cgroup_oom_unlock(struct mem_cgroup *mem)
-{
-	mem_cgroup_walk_tree(mem, NULL,	mem_cgroup_oom_unlock_cb);
-}
 
 static DEFINE_MUTEX(memcg_oom_mutex);
 static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq);
@@ -1462,35 +1589,73 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *mem, gfp_t mask)
 /*
  * Currently used to update mapped file statistics, but the routine can be
  * generalized to update other statistics as well.
+ *
+ * Notes: Race condition
+ *
+ * We usually use page_cgroup_lock() for accessing page_cgroup member but
+ * it tends to be costly. But considering some conditions, we doesn't need
+ * to do so _always_.
+ *
+ * Considering "charge", lock_page_cgroup() is not required because all
+ * file-stat operations happen after a page is attached to radix-tree. There
+ * are no race with "charge".
+ *
+ * Considering "uncharge", we know that memcg doesn't clear pc->mem_cgroup
+ * at "uncharge" intentionally. So, we always see valid pc->mem_cgroup even
+ * if there are race with "uncharge". Statistics itself is properly handled
+ * by flags.
+ *
+ * Considering "move", this is an only case we see a race. To make the race
+ * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are
+ * possibility of race condition. If there is, we take a lock.
  */
-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)
 {
 	struct mem_cgroup *mem;
-	struct page_cgroup *pc;
+	struct page_cgroup *pc = lookup_page_cgroup(page);
+	bool need_unlock = false;
+	unsigned long uninitialized_var(flags);
 
-	pc = lookup_page_cgroup(page);
 	if (unlikely(!pc))
 		return;
 
-	lock_page_cgroup(pc);
+	rcu_read_lock();
 	mem = pc->mem_cgroup;
-	if (!mem || !PageCgroupUsed(pc))
-		goto done;
+	if (unlikely(!mem || !PageCgroupUsed(pc)))
+		goto out;
+	/* pc->mem_cgroup is unstable ? */
+	if (unlikely(mem_cgroup_stealed(mem)) || PageTransHuge(page)) {
+		/* take a lock against to access pc->mem_cgroup */
+		move_lock_page_cgroup(pc, &flags);
+		need_unlock = true;
+		mem = pc->mem_cgroup;
+		if (!mem || !PageCgroupUsed(pc))
+			goto out;
+	}
 
-	/*
-	 * Preemption is already disabled. We can use __this_cpu_xxx
-	 */
-	if (val > 0) {
-		__this_cpu_inc(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		SetPageCgroupFileMapped(pc);
-	} else {
-		__this_cpu_dec(mem->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
-		ClearPageCgroupFileMapped(pc);
+	switch (idx) {
+	case MEMCG_NR_FILE_MAPPED:
+		if (val > 0)
+			SetPageCgroupFileMapped(pc);
+		else if (!page_mapped(page))
+			ClearPageCgroupFileMapped(pc);
+		idx = MEM_CGROUP_STAT_FILE_MAPPED;
+		break;
+	default:
+		BUG();
 	}
 
-done:
-	unlock_page_cgroup(pc);
+	this_cpu_add(mem->stat->count[idx], val);
+
+out:
+	if (unlikely(need_unlock))
+		move_unlock_page_cgroup(pc, &flags);
+	rcu_read_unlock();
+	return;
 }
+EXPORT_SYMBOL(mem_cgroup_update_page_stat);
 
 /*
  * size of first charge trial. "32" comes from vmscan.c's magic value.
@@ -1605,15 +1770,55 @@ static void drain_all_stock_sync(void)
 	atomic_dec(&memcg_drain_count);
 }
 
-static int __cpuinit memcg_stock_cpu_callback(struct notifier_block *nb,
+/*
+ * This function drains percpu counter value from DEAD cpu and
+ * move it to local cpu. Note that this function can be preempted.
+ */
+static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *mem, int cpu)
+{
+	int i;
+
+	spin_lock(&mem->pcp_counter_lock);
+	for (i = 0; i < MEM_CGROUP_STAT_DATA; i++) {
+		s64 x = per_cpu(mem->stat->count[i], cpu);
+
+		per_cpu(mem->stat->count[i], cpu) = 0;
+		mem->nocpu_base.count[i] += x;
+	}
+	/* need to clear ON_MOVE value, works as a kind of lock. */
+	per_cpu(mem->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0;
+	spin_unlock(&mem->pcp_counter_lock);
+}
+
+static void synchronize_mem_cgroup_on_move(struct mem_cgroup *mem, int cpu)
+{
+	int idx = MEM_CGROUP_ON_MOVE;
+
+	spin_lock(&mem->pcp_counter_lock);
+	per_cpu(mem->stat->count[idx], cpu) = mem->nocpu_base.count[idx];
+	spin_unlock(&mem->pcp_counter_lock);
+}
+
+static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb,
 					unsigned long action,
 					void *hcpu)
 {
 	int cpu = (unsigned long)hcpu;
 	struct memcg_stock_pcp *stock;
+	struct mem_cgroup *iter;
 
-	if (action != CPU_DEAD)
+	if ((action == CPU_ONLINE)) {
+		for_each_mem_cgroup_all(iter)
+			synchronize_mem_cgroup_on_move(iter, cpu);
 		return NOTIFY_OK;
+	}
+
+	if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN)
+		return NOTIFY_OK;
+
+	for_each_mem_cgroup_all(iter)
+		mem_cgroup_drain_pcp_counter(iter, cpu);
+
 	stock = &per_cpu(memcg_stock, cpu);
 	drain_stock(stock);
 	return NOTIFY_OK;
@@ -1646,27 +1851,39 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask,
 		if (likely(!ret))
 			return CHARGE_OK;
 
+		res_counter_uncharge(&mem->res, csize);
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, memsw);
 		flags |= MEM_CGROUP_RECLAIM_NOSWAP;
 	} else
 		mem_over_limit = mem_cgroup_from_res_counter(fail_res, res);
-
-	if (csize > PAGE_SIZE) /* change csize and retry */
+	/*
+	 * csize can be either a huge page (HPAGE_SIZE), a batch of
+	 * regular pages (CHARGE_SIZE), or a single regular page
+	 * (PAGE_SIZE).
+	 *
+	 * Never reclaim on behalf of optional batching, retry with a
+	 * single page instead.
+	 */
+	if (csize == CHARGE_SIZE)
 		return CHARGE_RETRY;
 
 	if (!(gfp_mask & __GFP_WAIT))
 		return CHARGE_WOULDBLOCK;
 
 	ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, NULL,
-					gfp_mask, flags);
+					      gfp_mask, flags);
+	if (mem_cgroup_check_margin(mem_over_limit, csize))
+		return CHARGE_RETRY;
 	/*
-	 * try_to_free_mem_cgroup_pages() might not give us a full
-	 * picture of reclaim. Some pages are reclaimed and might be
-	 * moved to swap cache or just unmapped from the cgroup.
-	 * Check the limit again to see if the reclaim reduced the
-	 * current usage of the cgroup before giving up
+	 * Even though the limit is exceeded at this point, reclaim
+	 * may have been able to free some pages.  Retry the charge
+	 * before killing the task.
+	 *
+	 * Only for regular pages, though: huge pages are rather
+	 * unlikely to succeed so close to the limit, and we fall back
+	 * to regular pages anyway in case of failure.
 	 */
-	if (ret || mem_cgroup_check_under_limit(mem_over_limit))
+	if (csize == PAGE_SIZE && ret)
 		return CHARGE_RETRY;
 
 	/*
@@ -1691,12 +1908,14 @@ static int __mem_cgroup_do_charge(struct mem_cgroup *mem, gfp_t gfp_mask,
  * oom-killer can be invoked.
  */
 static int __mem_cgroup_try_charge(struct mm_struct *mm,
-		gfp_t gfp_mask, struct mem_cgroup **memcg, bool oom)
+				   gfp_t gfp_mask,
+				   struct mem_cgroup **memcg, bool oom,
+				   int page_size)
 {
 	int nr_oom_retries = MEM_CGROUP_RECLAIM_RETRIES;
 	struct mem_cgroup *mem = NULL;
 	int ret;
-	int csize = CHARGE_SIZE;
+	int csize = max(CHARGE_SIZE, (unsigned long) page_size);
 
 	/*
 	 * Unlike gloval-vm's OOM-kill, we're not in memory shortage
@@ -1721,7 +1940,7 @@ again:
 		VM_BUG_ON(css_is_removed(&mem->css));
 		if (mem_cgroup_is_root(mem))
 			goto done;
-		if (consume_stock(mem))
+		if (page_size == PAGE_SIZE && consume_stock(mem))
 			goto done;
 		css_get(&mem->css);
 	} else {
@@ -1729,23 +1948,22 @@ again:
 
 		rcu_read_lock();
 		p = rcu_dereference(mm->owner);
-		VM_BUG_ON(!p);
 		/*
-		 * because we don't have task_lock(), "p" can exit while
-		 * we're here. In that case, "mem" can point to root
-		 * cgroup but never be NULL. (and task_struct itself is freed
-		 * by RCU, cgroup itself is RCU safe.) Then, we have small
-		 * risk here to get wrong cgroup. But such kind of mis-account
-		 * by race always happens because we don't have cgroup_mutex().
-		 * It's overkill and we allow that small race, here.
+		 * Because we don't have task_lock(), "p" can exit.
+		 * In that case, "mem" can point to root or p can be NULL with
+		 * race with swapoff. Then, we have small risk of mis-accouning.
+		 * But such kind of mis-account by race always happens because
+		 * we don't have cgroup_mutex(). It's overkill and we allo that
+		 * small race, here.
+		 * (*) swapoff at el will charge against mm-struct not against
+		 * task-struct. So, mm->owner can be NULL.
 		 */
 		mem = mem_cgroup_from_task(p);
-		VM_BUG_ON(!mem);
-		if (mem_cgroup_is_root(mem)) {
+		if (!mem || mem_cgroup_is_root(mem)) {
 			rcu_read_unlock();
 			goto done;
 		}
-		if (consume_stock(mem)) {
+		if (page_size == PAGE_SIZE && consume_stock(mem)) {
 			/*
 			 * It seems dagerous to access memcg without css_get().
 			 * But considering how consume_stok works, it's not
@@ -1786,7 +2004,7 @@ again:
 		case CHARGE_OK:
 			break;
 		case CHARGE_RETRY: /* not in OOM situation but retry */
-			csize = PAGE_SIZE;
+			csize = page_size;
 			css_put(&mem->css);
 			mem = NULL;
 			goto again;
@@ -1807,8 +2025,8 @@ again:
 		}
 	} while (ret != CHARGE_OK);
 
-	if (csize > PAGE_SIZE)
-		refill_stock(mem, csize - PAGE_SIZE);
+	if (csize > page_size)
+		refill_stock(mem, csize - page_size);
 	css_put(&mem->css);
 done:
 	*memcg = mem;
@@ -1836,9 +2054,10 @@ static void __mem_cgroup_cancel_charge(struct mem_cgroup *mem,
 	}
 }
 
-static void mem_cgroup_cancel_charge(struct mem_cgroup *mem)
+static void mem_cgroup_cancel_charge(struct mem_cgroup *mem,
+				     int page_size)
 {
-	__mem_cgroup_cancel_charge(mem, 1);
+	__mem_cgroup_cancel_charge(mem, page_size >> PAGE_SHIFT);
 }
 
 /*
@@ -1888,15 +2107,13 @@ struct mem_cgroup *try_get_mem_cgroup_from_page(struct page *page)
 	return mem;
 }
 
-/*
- * commit a charge got by __mem_cgroup_try_charge() and makes page_cgroup to be
- * USED state. If already USED, uncharge and return.
- */
-
 static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
-				     struct page_cgroup *pc,
-				     enum charge_type ctype)
+				       struct page_cgroup *pc,
+				       enum charge_type ctype,
+				       int page_size)
 {
+	int nr_pages = page_size >> PAGE_SHIFT;
+
 	/* try_charge() can return NULL to *memcg, taking care of it. */
 	if (!mem)
 		return;
@@ -1904,10 +2121,13 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
 	lock_page_cgroup(pc);
 	if (unlikely(PageCgroupUsed(pc))) {
 		unlock_page_cgroup(pc);
-		mem_cgroup_cancel_charge(mem);
+		mem_cgroup_cancel_charge(mem, page_size);
 		return;
 	}
-
+	/*
+	 * we don't need page_cgroup_lock about tail pages, becase they are not
+	 * accessed by any other context at this point.
+	 */
 	pc->mem_cgroup = mem;
 	/*
 	 * We access a page_cgroup asynchronously without lock_page_cgroup().
@@ -1931,8 +2151,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
 		break;
 	}
 
-	mem_cgroup_charge_statistics(mem, pc, true);
-
+	mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), nr_pages);
 	unlock_page_cgroup(pc);
 	/*
 	 * "charge_statistics" updated event counter. Then, check it.
@@ -1942,6 +2161,48 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
 	memcg_check_events(mem, pc->page);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+
+#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\
+			(1 << PCG_ACCT_LRU) | (1 << PCG_MIGRATION))
+/*
+ * Because tail pages are not marked as "used", set it. We're under
+ * zone->lru_lock, 'splitting on pmd' and compund_lock.
+ */
+void mem_cgroup_split_huge_fixup(struct page *head, struct page *tail)
+{
+	struct page_cgroup *head_pc = lookup_page_cgroup(head);
+	struct page_cgroup *tail_pc = lookup_page_cgroup(tail);
+	unsigned long flags;
+
+	if (mem_cgroup_disabled())
+		return;
+	/*
+	 * We have no races with charge/uncharge but will have races with
+	 * page state accounting.
+	 */
+	move_lock_page_cgroup(head_pc, &flags);
+
+	tail_pc->mem_cgroup = head_pc->mem_cgroup;
+	smp_wmb(); /* see __commit_charge() */
+	if (PageCgroupAcctLRU(head_pc)) {
+		enum lru_list lru;
+		struct mem_cgroup_per_zone *mz;
+
+		/*
+		 * LRU flags cannot be copied because we need to add tail
+		 *.page to LRU by generic call and our hook will be called.
+		 * We hold lru_lock, then, reduce counter directly.
+		 */
+		lru = page_lru(head);
+		mz = page_cgroup_zoneinfo(head_pc);
+		MEM_CGROUP_ZSTAT(mz, lru) -= 1;
+	}
+	tail_pc->flags = head_pc->flags & ~PCGF_NOCOPY_AT_SPLIT;
+	move_unlock_page_cgroup(head_pc, &flags);
+}
+#endif
+
 /**
  * __mem_cgroup_move_account - move account of the page
  * @pc:	page_cgroup of the page.
@@ -1960,11 +2221,14 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *mem,
  */
 
 static void __mem_cgroup_move_account(struct page_cgroup *pc,
-	struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge)
+	struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge,
+	int charge_size)
 {
+	int nr_pages = charge_size >> PAGE_SHIFT;
+
 	VM_BUG_ON(from == to);
 	VM_BUG_ON(PageLRU(pc->page));
-	VM_BUG_ON(!PageCgroupLocked(pc));
+	VM_BUG_ON(!page_is_cgroup_locked(pc));
 	VM_BUG_ON(!PageCgroupUsed(pc));
 	VM_BUG_ON(pc->mem_cgroup != from);
 
@@ -1975,14 +2239,14 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc,
 		__this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]);
 		preempt_enable();
 	}
-	mem_cgroup_charge_statistics(from, pc, false);
+	mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages);
 	if (uncharge)
 		/* This is not "cancel", but cancel_charge does all we need. */
-		mem_cgroup_cancel_charge(from);
+		mem_cgroup_cancel_charge(from, charge_size);
 
 	/* caller should have done css_get */
 	pc->mem_cgroup = to;
-	mem_cgroup_charge_statistics(to, pc, true);
+	mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages);
 	/*
 	 * We charges against "to" which may not have any tasks. Then, "to"
 	 * can be under rmdir(). But in current implementation, caller of
@@ -1997,12 +2261,25 @@ static void __mem_cgroup_move_account(struct page_cgroup *pc,
  * __mem_cgroup_move_account()
  */
 static int mem_cgroup_move_account(struct page_cgroup *pc,
-		struct mem_cgroup *from, struct mem_cgroup *to, bool uncharge)
+		struct mem_cgroup *from, struct mem_cgroup *to,
+		bool uncharge, int charge_size)
 {
 	int ret = -EINVAL;
+	unsigned long flags;
+	/*
+	 * The page is isolated from LRU. So, collapse function
+	 * will not handle this page. But page splitting can happen.
+	 * Do this check under compound_page_lock(). The caller should
+	 * hold it.
+	 */
+	if ((charge_size > PAGE_SIZE) && !PageTransHuge(pc->page))
+		return -EBUSY;
+
 	lock_page_cgroup(pc);
 	if (PageCgroupUsed(pc) && pc->mem_cgroup == from) {
-		__mem_cgroup_move_account(pc, from, to, uncharge);
+		move_lock_page_cgroup(pc, &flags);
+		__mem_cgroup_move_account(pc, from, to, uncharge, charge_size);
+		move_unlock_page_cgroup(pc, &flags);
 		ret = 0;
 	}
 	unlock_page_cgroup(pc);
@@ -2026,6 +2303,8 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 	struct cgroup *cg = child->css.cgroup;
 	struct cgroup *pcg = cg->parent;
 	struct mem_cgroup *parent;
+	int page_size = PAGE_SIZE;
+	unsigned long flags;
 	int ret;
 
 	/* Is ROOT ? */
@@ -2038,14 +2317,24 @@ static int mem_cgroup_move_parent(struct page_cgroup *pc,
 	if (isolate_lru_page(page))
 		goto put;
 
+	if (PageTransHuge(page))
+		page_size = HPAGE_SIZE;
+
 	parent = mem_cgroup_from_cont(pcg);
-	ret = __mem_cgroup_try_charge(NULL, gfp_mask, &parent, false);
+	ret = __mem_cgroup_try_charge(NULL, gfp_mask,
+				&parent, false, page_size);
 	if (ret || !parent)
 		goto put_back;
 
-	ret = mem_cgroup_move_account(pc, child, parent, true);
+	if (page_size > PAGE_SIZE)
+		flags = compound_lock_irqsave(page);
+
+	ret = mem_cgroup_move_account(pc, child, parent, true, page_size);
 	if (ret)
-		mem_cgroup_cancel_charge(parent);
+		mem_cgroup_cancel_charge(parent, page_size);
+
+	if (page_size > PAGE_SIZE)
+		compound_unlock_irqrestore(page, flags);
 put_back:
 	putback_lru_page(page);
 put:
@@ -2064,20 +2353,32 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask, enum charge_type ctype)
 {
 	struct mem_cgroup *mem = NULL;
+	int page_size = PAGE_SIZE;
 	struct page_cgroup *pc;
+	bool oom = true;
 	int ret;
 
+	if (PageTransHuge(page)) {
+		page_size <<= compound_order(page);
+		VM_BUG_ON(!PageTransHuge(page));
+		/*
+		 * Never OOM-kill a process for a huge page.  The
+		 * fault handler will fall back to regular pages.
+		 */
+		oom = false;
+	}
+
 	pc = lookup_page_cgroup(page);
 	/* can happen at boot */
 	if (unlikely(!pc))
 		return 0;
 	prefetchw(pc);
 
-	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, true);
+	ret = __mem_cgroup_try_charge(mm, gfp_mask, &mem, oom, page_size);
 	if (ret || !mem)
 		return ret;
 
-	__mem_cgroup_commit_charge(mem, pc, ctype);
+	__mem_cgroup_commit_charge(mem, pc, ctype, page_size);
 	return 0;
 }
 
@@ -2086,8 +2387,6 @@ int mem_cgroup_newpage_charge(struct page *page,
 {
 	if (mem_cgroup_disabled())
 		return 0;
-	if (PageCompound(page))
-		return 0;
 	/*
 	 * If already mapped, we don't have to account.
 	 * If page cache, page->mapping has address_space.
@@ -2193,13 +2492,13 @@ int mem_cgroup_try_charge_swapin(struct mm_struct *mm,
 	if (!mem)
 		goto charge_cur_mm;
 	*ptr = mem;
-	ret = __mem_cgroup_try_charge(NULL, mask, ptr, true);
+	ret = __mem_cgroup_try_charge(NULL, mask, ptr, true, PAGE_SIZE);
 	css_put(&mem->css);
 	return ret;
 charge_cur_mm:
 	if (unlikely(!mm))
 		mm = &init_mm;
-	return __mem_cgroup_try_charge(mm, mask, ptr, true);
+	return __mem_cgroup_try_charge(mm, mask, ptr, true, PAGE_SIZE);
 }
 
 static void
@@ -2215,7 +2514,7 @@ __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
 	cgroup_exclude_rmdir(&ptr->css);
 	pc = lookup_page_cgroup(page);
 	mem_cgroup_lru_del_before_commit_swapcache(page);
-	__mem_cgroup_commit_charge(ptr, pc, ctype);
+	__mem_cgroup_commit_charge(ptr, pc, ctype, PAGE_SIZE);
 	mem_cgroup_lru_add_after_commit_swapcache(page);
 	/*
 	 * Now swap is on-memory. This means this page may be
@@ -2264,11 +2563,12 @@ void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
 		return;
 	if (!mem)
 		return;
-	mem_cgroup_cancel_charge(mem);
+	mem_cgroup_cancel_charge(mem, PAGE_SIZE);
 }
 
 static void
-__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
+__do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype,
+	      int page_size)
 {
 	struct memcg_batch_info *batch = NULL;
 	bool uncharge_memsw = true;
@@ -2295,6 +2595,9 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
 	if (!batch->do_batch || test_thread_flag(TIF_MEMDIE))
 		goto direct_uncharge;
 
+	if (page_size != PAGE_SIZE)
+		goto direct_uncharge;
+
 	/*
 	 * In typical case, batch->memcg == mem. This means we can
 	 * merge a series of uncharges to an uncharge of res_counter.
@@ -2308,9 +2611,9 @@ __do_uncharge(struct mem_cgroup *mem, const enum charge_type ctype)
 		batch->memsw_bytes += PAGE_SIZE;
 	return;
 direct_uncharge:
-	res_counter_uncharge(&mem->res, PAGE_SIZE);
+	res_counter_uncharge(&mem->res, page_size);
 	if (uncharge_memsw)
-		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
+		res_counter_uncharge(&mem->memsw, page_size);
 	if (unlikely(batch->memcg != mem))
 		memcg_oom_recover(mem);
 	return;
@@ -2322,8 +2625,10 @@ direct_uncharge:
 static struct mem_cgroup *
 __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 {
+	int count;
 	struct page_cgroup *pc;
 	struct mem_cgroup *mem = NULL;
+	int page_size = PAGE_SIZE;
 
 	if (mem_cgroup_disabled())
 		return NULL;
@@ -2331,6 +2636,12 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	if (PageSwapCache(page))
 		return NULL;
 
+	if (PageTransHuge(page)) {
+		page_size <<= compound_order(page);
+		VM_BUG_ON(!PageTransHuge(page));
+	}
+
+	count = page_size >> PAGE_SHIFT;
 	/*
 	 * Check if our page_cgroup is valid
 	 */
@@ -2363,7 +2674,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		break;
 	}
 
-	mem_cgroup_charge_statistics(mem, pc, false);
+	mem_cgroup_charge_statistics(mem, PageCgroupCache(pc), -count);
 
 	ClearPageCgroupUsed(pc);
 	/*
@@ -2384,7 +2695,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 		mem_cgroup_get(mem);
 	}
 	if (!mem_cgroup_is_root(mem))
-		__do_uncharge(mem, ctype);
+		__do_uncharge(mem, ctype, page_size);
 
 	return mem;
 
@@ -2579,6 +2890,7 @@ int mem_cgroup_prepare_migration(struct page *page,
 	enum charge_type ctype;
 	int ret = 0;
 
+	VM_BUG_ON(PageTransHuge(page));
 	if (mem_cgroup_disabled())
 		return 0;
 
@@ -2628,7 +2940,7 @@ int mem_cgroup_prepare_migration(struct page *page,
 		return 0;
 
 	*ptr = mem;
-	ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false);
+	ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, ptr, false, PAGE_SIZE);
 	css_put(&mem->css);/* drop extra refcnt */
 	if (ret || *ptr == NULL) {
 		if (PageAnon(page)) {
@@ -2655,13 +2967,13 @@ int mem_cgroup_prepare_migration(struct page *page,
 		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
 	else
 		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-	__mem_cgroup_commit_charge(mem, pc, ctype);
+	__mem_cgroup_commit_charge(mem, pc, ctype, PAGE_SIZE);
 	return ret;
 }
 
 /* remove redundant charge if migration failed*/
 void mem_cgroup_end_migration(struct mem_cgroup *mem,
-	struct page *oldpage, struct page *newpage)
+	struct page *oldpage, struct page *newpage, bool migration_ok)
 {
 	struct page *used, *unused;
 	struct page_cgroup *pc;
@@ -2670,8 +2982,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *mem,
 		return;
 	/* blocks rmdir() */
 	cgroup_exclude_rmdir(&mem->css);
-	/* at migration success, oldpage->mapping is NULL. */
-	if (oldpage->mapping) {
+	if (!migration_ok) {
 		used = oldpage;
 		unused = newpage;
 	} else {
@@ -3038,6 +3349,7 @@ move_account:
 		lru_add_drain_all();
 		drain_all_stock_sync();
 		ret = 0;
+		mem_cgroup_start_move(mem);
 		for_each_node_state(node, N_HIGH_MEMORY) {
 			for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) {
 				enum lru_list l;
@@ -3051,6 +3363,7 @@ move_account:
 			if (ret)
 				break;
 		}
+		mem_cgroup_end_move(mem);
 		memcg_oom_recover(mem);
 		/* it seems parent cgroup doesn't have enough mem */
 		if (ret == -ENOMEM)
@@ -3137,33 +3450,25 @@ static int mem_cgroup_hierarchy_write(struct cgroup *cont, struct cftype *cft,
 	return retval;
 }
 
-struct mem_cgroup_idx_data {
-	s64 val;
-	enum mem_cgroup_stat_index idx;
-};
 
-static int
-mem_cgroup_get_idx_stat(struct mem_cgroup *mem, void *data)
+static u64 mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem,
+				enum mem_cgroup_stat_index idx)
 {
-	struct mem_cgroup_idx_data *d = data;
-	d->val += mem_cgroup_read_stat(mem, d->idx);
-	return 0;
-}
+	struct mem_cgroup *iter;
+	s64 val = 0;
 
-static void
-mem_cgroup_get_recursive_idx_stat(struct mem_cgroup *mem,
-				enum mem_cgroup_stat_index idx, s64 *val)
-{
-	struct mem_cgroup_idx_data d;
-	d.idx = idx;
-	d.val = 0;
-	mem_cgroup_walk_tree(mem, &d, mem_cgroup_get_idx_stat);
-	*val = d.val;
+	/* each per cpu's value can be minus.Then, use s64 */
+	for_each_mem_cgroup_tree(iter, mem)
+		val += mem_cgroup_read_stat(iter, idx);
+
+	if (val < 0) /* race ? */
+		val = 0;
+	return val;
 }
 
 static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap)
 {
-	u64 idx_val, val;
+	u64 val;
 
 	if (!mem_cgroup_is_root(mem)) {
 		if (!swap)
@@ -3172,16 +3477,12 @@ static inline u64 mem_cgroup_usage(struct mem_cgroup *mem, bool swap)
 			return res_counter_read_u64(&mem->memsw, RES_USAGE);
 	}
 
-	mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_CACHE, &idx_val);
-	val = idx_val;
-	mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_RSS, &idx_val);
-	val += idx_val;
+	val = mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_CACHE);
+	val += mem_cgroup_get_recursive_idx_stat(mem, MEM_CGROUP_STAT_RSS);
 
-	if (swap) {
-		mem_cgroup_get_recursive_idx_stat(mem,
-				MEM_CGROUP_STAT_SWAPOUT, &idx_val);
-		val += idx_val;
-	}
+	if (swap)
+		val += mem_cgroup_get_recursive_idx_stat(mem,
+				MEM_CGROUP_STAT_SWAPOUT);
 
 	return val << PAGE_SHIFT;
 }
@@ -3389,9 +3690,9 @@ struct {
 };
 
 
-static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
+static void
+mem_cgroup_get_local_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
 {
-	struct mcs_total_stat *s = data;
 	s64 val;
 
 	/* per cpu stat */
@@ -3421,13 +3722,15 @@ static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
 	s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE;
 	val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE);
 	s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE;
-	return 0;
 }
 
 static void
 mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
 {
-	mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat);
+	struct mem_cgroup *iter;
+
+	for_each_mem_cgroup_tree(iter, mem)
+		mem_cgroup_get_local_stat(iter, s);
 }
 
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
@@ -3604,7 +3907,7 @@ static int compare_thresholds(const void *a, const void *b)
 	return _a->threshold - _b->threshold;
 }
 
-static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem, void *data)
+static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem)
 {
 	struct mem_cgroup_eventfd_list *ev;
 
@@ -3615,7 +3918,10 @@ static int mem_cgroup_oom_notify_cb(struct mem_cgroup *mem, void *data)
 
 static void mem_cgroup_oom_notify(struct mem_cgroup *mem)
 {
-	mem_cgroup_walk_tree(mem, NULL, mem_cgroup_oom_notify_cb);
+	struct mem_cgroup *iter;
+
+	for_each_mem_cgroup_tree(iter, mem)
+		mem_cgroup_oom_notify_cb(iter);
 }
 
 static int mem_cgroup_usage_register_event(struct cgroup *cgrp,
@@ -3986,13 +4292,11 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
 	 */
 	if (!node_state(node, N_NORMAL_MEMORY))
 		tmp = -1;
-	pn = kmalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
+	pn = kzalloc_node(sizeof(*pn), GFP_KERNEL, tmp);
 	if (!pn)
 		return 1;
 
 	mem->info.nodeinfo[node] = pn;
-	memset(pn, 0, sizeof(*pn));
-
 	for (zone = 0; zone < MAX_NR_ZONES; zone++) {
 		mz = &pn->zoneinfo[zone];
 		for_each_lru(l)
@@ -4016,23 +4320,25 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 
 	/* Can be very big if MAX_NUMNODES is very big */
 	if (size < PAGE_SIZE)
-		mem = kmalloc(size, GFP_KERNEL);
+		mem = kzalloc(size, GFP_KERNEL);
 	else
-		mem = vmalloc(size);
+		mem = vzalloc(size);
 
 	if (!mem)
 		return NULL;
 
-	memset(mem, 0, size);
 	mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu);
-	if (!mem->stat) {
-		if (size < PAGE_SIZE)
-			kfree(mem);
-		else
-			vfree(mem);
-		mem = NULL;
-	}
+	if (!mem->stat)
+		goto out_free;
+	spin_lock_init(&mem->pcp_counter_lock);
 	return mem;
+
+out_free:
+	if (size < PAGE_SIZE)
+		kfree(mem);
+	else
+		vfree(mem);
+	return NULL;
 }
 
 /*
@@ -4158,7 +4464,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 						&per_cpu(memcg_stock, cpu);
 			INIT_WORK(&stock->work, drain_local_stock);
 		}
-		hotcpu_notifier(memcg_stock_cpu_callback, 0);
+		hotcpu_notifier(memcg_cpu_hotplug_callback, 0);
 	} else {
 		parent = mem_cgroup_from_cont(cont->parent);
 		mem->use_hierarchy = parent->use_hierarchy;
@@ -4268,7 +4574,8 @@ one_by_one:
 			batch_count = PRECHARGE_COUNT_AT_ONCE;
 			cond_resched();
 		}
-		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false);
+		ret = __mem_cgroup_try_charge(NULL, GFP_KERNEL, &mem, false,
+					      PAGE_SIZE);
 		if (ret || !mem)
 			/* mem_cgroup_clear_mc() will do uncharge later */
 			return -ENOMEM;
@@ -4430,6 +4737,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd,
 	pte_t *pte;
 	spinlock_t *ptl;
 
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE)
 		if (is_target_pte_for_mc(vma, addr, *pte, NULL))
@@ -4467,10 +4775,15 @@ static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm)
 
 static int mem_cgroup_precharge_mc(struct mm_struct *mm)
 {
-	return mem_cgroup_do_precharge(mem_cgroup_count_precharge(mm));
+	unsigned long precharge = mem_cgroup_count_precharge(mm);
+
+	VM_BUG_ON(mc.moving_task);
+	mc.moving_task = current;
+	return mem_cgroup_do_precharge(precharge);
 }
 
-static void mem_cgroup_clear_mc(void)
+/* cancels all extra charges on mc.from and mc.to, and wakes up all waiters. */
+static void __mem_cgroup_clear_mc(void)
 {
 	struct mem_cgroup *from = mc.from;
 	struct mem_cgroup *to = mc.to;
@@ -4505,17 +4818,28 @@ static void mem_cgroup_clear_mc(void)
 						PAGE_SIZE * mc.moved_swap);
 		}
 		/* we've already done mem_cgroup_get(mc.to) */
-
 		mc.moved_swap = 0;
 	}
+	memcg_oom_recover(from);
+	memcg_oom_recover(to);
+	wake_up_all(&mc.waitq);
+}
+
+static void mem_cgroup_clear_mc(void)
+{
+	struct mem_cgroup *from = mc.from;
+
+	/*
+	 * we must clear moving_task before waking up waiters at the end of
+	 * task migration.
+	 */
+	mc.moving_task = NULL;
+	__mem_cgroup_clear_mc();
 	spin_lock(&mc.lock);
 	mc.from = NULL;
 	mc.to = NULL;
-	mc.moving_task = NULL;
 	spin_unlock(&mc.lock);
-	memcg_oom_recover(from);
-	memcg_oom_recover(to);
-	wake_up_all(&mc.waitq);
+	mem_cgroup_end_move(from);
 }
 
 static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
@@ -4542,15 +4866,12 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss,
 			VM_BUG_ON(mc.precharge);
 			VM_BUG_ON(mc.moved_charge);
 			VM_BUG_ON(mc.moved_swap);
-			VM_BUG_ON(mc.moving_task);
+			mem_cgroup_start_move(from);
 			spin_lock(&mc.lock);
 			mc.from = from;
 			mc.to = mem;
-			mc.precharge = 0;
-			mc.moved_charge = 0;
-			mc.moved_swap = 0;
-			mc.moving_task = current;
 			spin_unlock(&mc.lock);
+			/* We set mc.moving_task later */
 
 			ret = mem_cgroup_precharge_mc(mm);
 			if (ret)
@@ -4579,6 +4900,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd,
 	spinlock_t *ptl;
 
 retry:
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; addr += PAGE_SIZE) {
 		pte_t ptent = *(pte++);
@@ -4599,7 +4921,7 @@ retry:
 				goto put;
 			pc = lookup_page_cgroup(page);
 			if (!mem_cgroup_move_account(pc,
-						mc.from, mc.to, false)) {
+					mc.from, mc.to, false, PAGE_SIZE)) {
 				mc.precharge--;
 				/* we uncharge from mc.from later. */
 				mc.moved_charge++;
@@ -4644,7 +4966,19 @@ static void mem_cgroup_move_charge(struct mm_struct *mm)
 	struct vm_area_struct *vma;
 
 	lru_add_drain_all();
-	down_read(&mm->mmap_sem);
+retry:
+	if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
+		/*
+		 * Someone who are holding the mmap_sem might be waiting in
+		 * waitq. So we cancel all extra charges, wake up all waiters,
+		 * and retry. Because we cancel precharges, we might not be able
+		 * to move enough charges, but moving charge is a best-effort
+		 * feature anyway, so it wouldn't be a big problem.
+		 */
+		__mem_cgroup_clear_mc();
+		cond_resched();
+		goto retry;
+	}
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		int ret;
 		struct mm_walk mem_cgroup_move_charge_walk = {
@@ -4723,10 +5057,21 @@ struct cgroup_subsys mem_cgroup_subsys = {
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
+static int __init enable_swap_account(char *s)
+{
+	/* consider enabled if no parameter or 1 is given */
+	if (!(*s) || !strcmp(s, "=1"))
+		really_do_swap_account = 1;
+	else if (!strcmp(s, "=0"))
+		really_do_swap_account = 0;
+	return 1;
+}
+__setup("swapaccount", enable_swap_account);
 
 static int __init disable_swap_account(char *s)
 {
-	really_do_swap_account = 0;
+	printk_once("noswapaccount is deprecated and will be removed in 2.6.40. Use swapaccount=0 instead\n");
+	enable_swap_account("=0");
 	return 1;
 }
 __setup("noswapaccount", disable_swap_account);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 757f6b0accfe..0207c2f6f8bd 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -7,21 +7,26 @@
  * Free Software Foundation.
  *
  * High level machine check handler. Handles pages reported by the
- * hardware as being corrupted usually due to a 2bit ECC memory or cache
+ * hardware as being corrupted usually due to a multi-bit ECC memory or cache
  * failure.
+ * 
+ * In addition there is a "soft offline" entry point that allows stop using
+ * not-yet-corrupted-by-suspicious pages without killing anything.
  *
  * Handles page cache pages in various states.	The tricky part
- * here is that we can access any page asynchronous to other VM
- * users, because memory failures could happen anytime and anywhere,
- * possibly violating some of their assumptions. This is why this code
- * has to be extremely careful. Generally it tries to use normal locking
- * rules, as in get the standard locks, even if that means the
- * error handling takes potentially a long time.
- *
- * The operation to map back from RMAP chains to processes has to walk
- * the complete process list and has non linear complexity with the number
- * mappings. In short it can be quite slow. But since memory corruptions
- * are rare we hope to get away with this.
+ * here is that we can access any page asynchronously in respect to 
+ * other VM users, because memory failures could happen anytime and 
+ * anywhere. This could violate some of their assumptions. This is why 
+ * this code has to be extremely careful. Generally it tries to use 
+ * normal locking rules, as in get the standard locks, even if that means 
+ * the error handling takes potentially a long time.
+ * 
+ * There are several operations here with exponential complexity because
+ * of unsuitable VM data structures. For example the operation to map back 
+ * from RMAP chains to processes has to walk the complete process list and 
+ * has non linear complexity with the number. But since memory corruptions
+ * are rare we hope to get away with this. This avoids impacting the core 
+ * VM.
  */
 
 /*
@@ -30,7 +35,6 @@
  * - kcore/oldmem/vmcore/mem/kmem check for hwpoison pages
  * - pass bad pages to kdump next kernel
  */
-#define DEBUG 1		/* remove me in 2.6.34 */
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/page-flags.h>
@@ -47,6 +51,7 @@
 #include <linux/slab.h>
 #include <linux/swapops.h>
 #include <linux/hugetlb.h>
+#include <linux/memory_hotplug.h>
 #include "internal.h"
 
 int sysctl_memory_failure_early_kill __read_mostly = 0;
@@ -78,7 +83,7 @@ static int hwpoison_filter_dev(struct page *p)
 		return 0;
 
 	/*
-	 * page_mapping() does not accept slab page
+	 * page_mapping() does not accept slab pages.
 	 */
 	if (PageSlab(p))
 		return -EINVAL;
@@ -198,7 +203,7 @@ static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno,
 #ifdef __ARCH_SI_TRAPNO
 	si.si_trapno = trapno;
 #endif
-	si.si_addr_lsb = compound_order(compound_head(page)) + PAGE_SHIFT;
+	si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT;
 	/*
 	 * Don't use force here, it's convenient if the signal
 	 * can be temporarily blocked.
@@ -228,8 +233,8 @@ void shake_page(struct page *p, int access)
 	}
 
 	/*
-	 * Only all shrink_slab here (which would also
-	 * shrink other caches) if access is not potentially fatal.
+	 * Only call shrink_slab here (which would also shrink other caches) if
+	 * access is not potentially fatal.
 	 */
 	if (access) {
 		int nr;
@@ -268,7 +273,7 @@ struct to_kill {
 	struct list_head nd;
 	struct task_struct *tsk;
 	unsigned long addr;
-	unsigned addr_valid:1;
+	char addr_valid;
 };
 
 /*
@@ -309,7 +314,7 @@ static void add_to_kill(struct task_struct *tsk, struct page *p,
 	 * a SIGKILL because the error is not contained anymore.
 	 */
 	if (tk->addr == -EFAULT) {
-		pr_debug("MCE: Unable to find user space address %lx in %s\n",
+		pr_info("MCE: Unable to find user space address %lx in %s\n",
 			page_to_pfn(p), tsk->comm);
 		tk->addr_valid = 0;
 	}
@@ -577,7 +582,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn)
 					pfn, err);
 		} else if (page_has_private(p) &&
 				!try_to_release_page(p, GFP_NOIO)) {
-			pr_debug("MCE %#lx: failed to release buffers\n", pfn);
+			pr_info("MCE %#lx: failed to release buffers\n", pfn);
 		} else {
 			ret = RECOVERED;
 		}
@@ -693,11 +698,10 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn)
  * Issues:
  * - Error on hugepage is contained in hugepage unit (not in raw page unit.)
  *   To narrow down kill region to one page, we need to break up pmd.
- * - To support soft-offlining for hugepage, we need to support hugepage
- *   migration.
  */
 static int me_huge_page(struct page *p, unsigned long pfn)
 {
+	int res = 0;
 	struct page *hpage = compound_head(p);
 	/*
 	 * We can safely recover from error on free or reserved (i.e.
@@ -710,8 +714,9 @@ static int me_huge_page(struct page *p, unsigned long pfn)
 	 * so there is no race between isolation and mapping/unmapping.
 	 */
 	if (!(page_mapping(hpage) || PageAnon(hpage))) {
-		__isolate_hwpoisoned_huge_page(hpage);
-		return RECOVERED;
+		res = dequeue_hwpoisoned_huge_page(hpage);
+		if (!res)
+			return RECOVERED;
 	}
 	return DELAYED;
 }
@@ -836,8 +841,6 @@ static int page_action(struct page_state *ps, struct page *p,
 	return (result == RECOVERED || result == DELAYED) ? 0 : -EBUSY;
 }
 
-#define N_UNMAP_TRIES 5
-
 /*
  * Do all that is necessary to remove user space mappings. Unmap
  * the pages and send SIGBUS to the processes if the data was dirty.
@@ -849,9 +852,9 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	int ret;
-	int i;
 	int kill = 1;
 	struct page *hpage = compound_head(p);
+	struct page *ppage;
 
 	if (PageReserved(p) || PageSlab(p))
 		return SWAP_SUCCESS;
@@ -893,6 +896,44 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	}
 
 	/*
+	 * ppage: poisoned page
+	 *   if p is regular page(4k page)
+	 *        ppage == real poisoned page;
+	 *   else p is hugetlb or THP, ppage == head page.
+	 */
+	ppage = hpage;
+
+	if (PageTransHuge(hpage)) {
+		/*
+		 * Verify that this isn't a hugetlbfs head page, the check for
+		 * PageAnon is just for avoid tripping a split_huge_page
+		 * internal debug check, as split_huge_page refuses to deal with
+		 * anything that isn't an anon page. PageAnon can't go away fro
+		 * under us because we hold a refcount on the hpage, without a
+		 * refcount on the hpage. split_huge_page can't be safely called
+		 * in the first place, having a refcount on the tail isn't
+		 * enough * to be safe.
+		 */
+		if (!PageHuge(hpage) && PageAnon(hpage)) {
+			if (unlikely(split_huge_page(hpage))) {
+				/*
+				 * FIXME: if splitting THP is failed, it is
+				 * better to stop the following operation rather
+				 * than causing panic by unmapping. System might
+				 * survive if the page is freed later.
+				 */
+				printk(KERN_INFO
+					"MCE %#lx: failed to split THP\n", pfn);
+
+				BUG_ON(!PageHWPoison(p));
+				return SWAP_FAIL;
+			}
+			/* THP is split, so ppage should be the real poisoned page. */
+			ppage = p;
+		}
+	}
+
+	/*
 	 * First collect all the processes that have the page
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
 	 * because ttu takes the rmap data structures down.
@@ -901,22 +942,18 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(hpage, &tokill);
+		collect_procs(ppage, &tokill);
 
-	/*
-	 * try_to_unmap can fail temporarily due to races.
-	 * Try a few times (RED-PEN better strategy?)
-	 */
-	for (i = 0; i < N_UNMAP_TRIES; i++) {
-		ret = try_to_unmap(hpage, ttu);
-		if (ret == SWAP_SUCCESS)
-			break;
-		pr_debug("MCE %#lx: try_to_unmap retry needed %d\n", pfn,  ret);
-	}
+	if (hpage != ppage)
+		lock_page_nosync(ppage);
 
+	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
 		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
-				pfn, page_mapcount(hpage));
+				pfn, page_mapcount(ppage));
+
+	if (hpage != ppage)
+		unlock_page(ppage);
 
 	/*
 	 * Now that the dirty bit has been propagated to the
@@ -927,7 +964,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * use a more force-full uncatchable kill to prevent
 	 * any accesses to the poisoned memory.
 	 */
-	kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
+	kill_procs_ao(&tokill, !!PageDirty(ppage), trapno,
 		      ret != SWAP_SUCCESS, p, pfn);
 
 	return ret;
@@ -936,7 +973,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 static void set_page_hwpoison_huge_page(struct page *hpage)
 {
 	int i;
-	int nr_pages = 1 << compound_order(hpage);
+	int nr_pages = 1 << compound_trans_order(hpage);
 	for (i = 0; i < nr_pages; i++)
 		SetPageHWPoison(hpage + i);
 }
@@ -944,7 +981,7 @@ static void set_page_hwpoison_huge_page(struct page *hpage)
 static void clear_page_hwpoison_huge_page(struct page *hpage)
 {
 	int i;
-	int nr_pages = 1 << compound_order(hpage);
+	int nr_pages = 1 << compound_trans_order(hpage);
 	for (i = 0; i < nr_pages; i++)
 		ClearPageHWPoison(hpage + i);
 }
@@ -974,14 +1011,17 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 		return 0;
 	}
 
-	nr_pages = 1 << compound_order(hpage);
+	nr_pages = 1 << compound_trans_order(hpage);
 	atomic_long_add(nr_pages, &mce_bad_pages);
 
 	/*
 	 * We need/can do nothing about count=0 pages.
 	 * 1) it's a free page, and therefore in safe hand:
 	 *    prep_new_page() will be the gate keeper.
-	 * 2) it's part of a non-compound high order page.
+	 * 2) it's a free hugepage, which is also safe:
+	 *    an affected hugepage will be dequeued from hugepage freelist,
+	 *    so there's no concern about reusing it ever after.
+	 * 3) it's part of a non-compound high order page.
 	 *    Implies some kernel user: cannot stop them from
 	 *    R/W the page; let's pray that the page has been
 	 *    used and will be freed some time later.
@@ -993,6 +1033,24 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 		if (is_free_buddy_page(p)) {
 			action_result(pfn, "free buddy", DELAYED);
 			return 0;
+		} else if (PageHuge(hpage)) {
+			/*
+			 * Check "just unpoisoned", "filter hit", and
+			 * "race with other subpage."
+			 */
+			lock_page_nosync(hpage);
+			if (!PageHWPoison(hpage)
+			    || (hwpoison_filter(p) && TestClearPageHWPoison(p))
+			    || (p != hpage && TestSetPageHWPoison(hpage))) {
+				atomic_long_sub(nr_pages, &mce_bad_pages);
+				return 0;
+			}
+			set_page_hwpoison_huge_page(hpage);
+			res = dequeue_hwpoisoned_huge_page(hpage);
+			action_result(pfn, "free huge",
+				      res ? IGNORED : DELAYED);
+			unlock_page(hpage);
+			return res;
 		} else {
 			action_result(pfn, "high order kernel", IGNORED);
 			return -EBUSY;
@@ -1007,19 +1065,22 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
 	 */
-	if (!PageLRU(p) && !PageHuge(p))
-		shake_page(p, 0);
-	if (!PageLRU(p) && !PageHuge(p)) {
-		/*
-		 * shake_page could have turned it free.
-		 */
-		if (is_free_buddy_page(p)) {
-			action_result(pfn, "free buddy, 2nd try", DELAYED);
-			return 0;
+	if (!PageHuge(p) && !PageTransCompound(p)) {
+		if (!PageLRU(p))
+			shake_page(p, 0);
+		if (!PageLRU(p)) {
+			/*
+			 * shake_page could have turned it free.
+			 */
+			if (is_free_buddy_page(p)) {
+				action_result(pfn, "free buddy, 2nd try",
+						DELAYED);
+				return 0;
+			}
+			action_result(pfn, "non LRU", IGNORED);
+			put_page(p);
+			return -EBUSY;
 		}
-		action_result(pfn, "non LRU", IGNORED);
-		put_page(p);
-		return -EBUSY;
 	}
 
 	/*
@@ -1049,7 +1110,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * For error on the tail page, we should set PG_hwpoison
 	 * on the head page to show that the hugepage is hwpoisoned
 	 */
-	if (PageTail(p) && TestSetPageHWPoison(hpage)) {
+	if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) {
 		action_result(pfn, "hugepage already hardware poisoned",
 				IGNORED);
 		unlock_page(hpage);
@@ -1147,16 +1208,26 @@ int unpoison_memory(unsigned long pfn)
 	page = compound_head(p);
 
 	if (!PageHWPoison(p)) {
-		pr_debug("MCE: Page was already unpoisoned %#lx\n", pfn);
+		pr_info("MCE: Page was already unpoisoned %#lx\n", pfn);
 		return 0;
 	}
 
-	nr_pages = 1 << compound_order(page);
+	nr_pages = 1 << compound_trans_order(page);
 
 	if (!get_page_unless_zero(page)) {
+		/*
+		 * Since HWPoisoned hugepage should have non-zero refcount,
+		 * race between memory failure and unpoison seems to happen.
+		 * In such case unpoison fails and memory failure runs
+		 * to the end.
+		 */
+		if (PageHuge(page)) {
+			pr_debug("MCE: Memory failure is now running on free hugepage %#lx\n", pfn);
+			return 0;
+		}
 		if (TestClearPageHWPoison(p))
 			atomic_long_sub(nr_pages, &mce_bad_pages);
-		pr_debug("MCE: Software-unpoisoned free page %#lx\n", pfn);
+		pr_info("MCE: Software-unpoisoned free page %#lx\n", pfn);
 		return 0;
 	}
 
@@ -1168,12 +1239,12 @@ int unpoison_memory(unsigned long pfn)
 	 * the free buddy page pool.
 	 */
 	if (TestClearPageHWPoison(page)) {
-		pr_debug("MCE: Software-unpoisoned page %#lx\n", pfn);
+		pr_info("MCE: Software-unpoisoned page %#lx\n", pfn);
 		atomic_long_sub(nr_pages, &mce_bad_pages);
 		freeit = 1;
+		if (PageHuge(page))
+			clear_page_hwpoison_huge_page(page);
 	}
-	if (PageHuge(p))
-		clear_page_hwpoison_huge_page(page);
 	unlock_page(page);
 
 	put_page(page);
@@ -1187,7 +1258,11 @@ EXPORT_SYMBOL(unpoison_memory);
 static struct page *new_page(struct page *p, unsigned long private, int **x)
 {
 	int nid = page_to_nid(p);
-	return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
+	if (PageHuge(p))
+		return alloc_huge_page_node(page_hstate(compound_head(p)),
+						   nid);
+	else
+		return alloc_pages_exact_node(nid, GFP_HIGHUSER_MOVABLE, 0);
 }
 
 /*
@@ -1204,25 +1279,31 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 		return 1;
 
 	/*
-	 * The lock_system_sleep prevents a race with memory hotplug,
-	 * because the isolation assumes there's only a single user.
+	 * The lock_memory_hotplug prevents a race with memory hotplug.
 	 * This is a big hammer, a better would be nicer.
 	 */
-	lock_system_sleep();
+	lock_memory_hotplug();
 
 	/*
 	 * Isolate the page, so that it doesn't get reallocated if it
 	 * was free.
 	 */
 	set_migratetype_isolate(p);
+	/*
+	 * When the target page is a free hugepage, just remove it
+	 * from free hugepage list.
+	 */
 	if (!get_page_unless_zero(compound_head(p))) {
-		if (is_free_buddy_page(p)) {
-			pr_debug("get_any_page: %#lx free buddy page\n", pfn);
+		if (PageHuge(p)) {
+			pr_info("get_any_page: %#lx free huge page\n", pfn);
+			ret = dequeue_hwpoisoned_huge_page(compound_head(p));
+		} else if (is_free_buddy_page(p)) {
+			pr_info("get_any_page: %#lx free buddy page\n", pfn);
 			/* Set hwpoison bit while page is still isolated */
 			SetPageHWPoison(p);
 			ret = 0;
 		} else {
-			pr_debug("get_any_page: %#lx: unknown zero refcount page type %lx\n",
+			pr_info("get_any_page: %#lx: unknown zero refcount page type %lx\n",
 				pfn, p->flags);
 			ret = -EIO;
 		}
@@ -1231,7 +1312,51 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 		ret = 1;
 	}
 	unset_migratetype_isolate(p);
-	unlock_system_sleep();
+	unlock_memory_hotplug();
+	return ret;
+}
+
+static int soft_offline_huge_page(struct page *page, int flags)
+{
+	int ret;
+	unsigned long pfn = page_to_pfn(page);
+	struct page *hpage = compound_head(page);
+	LIST_HEAD(pagelist);
+
+	ret = get_any_page(page, pfn, flags);
+	if (ret < 0)
+		return ret;
+	if (ret == 0)
+		goto done;
+
+	if (PageHWPoison(hpage)) {
+		put_page(hpage);
+		pr_debug("soft offline: %#lx hugepage already poisoned\n", pfn);
+		return -EBUSY;
+	}
+
+	/* Keep page count to indicate a given hugepage is isolated. */
+
+	list_add(&hpage->lru, &pagelist);
+	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0,
+				true);
+	if (ret) {
+		struct page *page1, *page2;
+		list_for_each_entry_safe(page1, page2, &pagelist, lru)
+			put_page(page1);
+
+		pr_debug("soft offline: %#lx: migration failed %d, type %lx\n",
+			 pfn, ret, page->flags);
+		if (ret > 0)
+			ret = -EIO;
+		return ret;
+	}
+done:
+	if (!PageHWPoison(hpage))
+		atomic_long_add(1 << compound_trans_order(hpage), &mce_bad_pages);
+	set_page_hwpoison_huge_page(hpage);
+	dequeue_hwpoisoned_huge_page(hpage);
+	/* keep elevated page count for bad page */
 	return ret;
 }
 
@@ -1262,6 +1387,9 @@ int soft_offline_page(struct page *page, int flags)
 	int ret;
 	unsigned long pfn = page_to_pfn(page);
 
+	if (PageHuge(page))
+		return soft_offline_huge_page(page, flags);
+
 	ret = get_any_page(page, pfn, flags);
 	if (ret < 0)
 		return ret;
@@ -1288,7 +1416,7 @@ int soft_offline_page(struct page *page, int flags)
 			goto done;
 	}
 	if (!PageLRU(page)) {
-		pr_debug("soft_offline: %#lx: unknown non LRU page type %lx\n",
+		pr_info("soft_offline: %#lx: unknown non LRU page type %lx\n",
 				pfn, page->flags);
 		return -EIO;
 	}
@@ -1302,7 +1430,7 @@ int soft_offline_page(struct page *page, int flags)
 	if (PageHWPoison(page)) {
 		unlock_page(page);
 		put_page(page);
-		pr_debug("soft offline: %#lx page already poisoned\n", pfn);
+		pr_info("soft offline: %#lx page already poisoned\n", pfn);
 		return -EBUSY;
 	}
 
@@ -1323,7 +1451,7 @@ int soft_offline_page(struct page *page, int flags)
 	put_page(page);
 	if (ret == 1) {
 		ret = 0;
-		pr_debug("soft_offline: %#lx: invalidated\n", pfn);
+		pr_info("soft_offline: %#lx: invalidated\n", pfn);
 		goto done;
 	}
 
@@ -1337,15 +1465,17 @@ int soft_offline_page(struct page *page, int flags)
 		LIST_HEAD(pagelist);
 
 		list_add(&page->lru, &pagelist);
-		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0);
+		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
+								0, true);
 		if (ret) {
-			pr_debug("soft offline: %#lx: migration failed %d, type %lx\n",
+			putback_lru_pages(&pagelist);
+			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
 		}
 	} else {
-		pr_debug("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
+		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
 				pfn, ret, page_count(page), page->flags);
 	}
 	if (ret)
diff --git a/mm/memory.c b/mm/memory.c
index 0e18b4d649ec..5823698c2b71 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -394,9 +394,11 @@ void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma,
 	}
 }
 
-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)
 {
 	pgtable_t new = pte_alloc_one(mm, address);
+	int wait_split_huge_page;
 	if (!new)
 		return -ENOMEM;
 
@@ -416,14 +418,18 @@ int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address)
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
 	spin_lock(&mm->page_table_lock);
-	if (!pmd_present(*pmd)) {	/* Has another populated it ? */
+	wait_split_huge_page = 0;
+	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		mm->nr_ptes++;
 		pmd_populate(mm, pmd, new);
 		new = NULL;
-	}
+	} else if (unlikely(pmd_trans_splitting(*pmd)))
+		wait_split_huge_page = 1;
 	spin_unlock(&mm->page_table_lock);
 	if (new)
 		pte_free(mm, new);
+	if (wait_split_huge_page)
+		wait_split_huge_page(vma->anon_vma, pmd);
 	return 0;
 }
 
@@ -436,10 +442,11 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
 	smp_wmb(); /* See comment in __pte_alloc */
 
 	spin_lock(&init_mm.page_table_lock);
-	if (!pmd_present(*pmd)) {	/* Has another populated it ? */
+	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		pmd_populate_kernel(&init_mm, pmd, new);
 		new = NULL;
-	}
+	} else
+		VM_BUG_ON(pmd_trans_splitting(*pmd));
 	spin_unlock(&init_mm.page_table_lock);
 	if (new)
 		pte_free_kernel(&init_mm, new);
@@ -719,9 +726,9 @@ out_set_pte:
 	return 0;
 }
 
-static 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)
+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)
 {
 	pte_t *orig_src_pte, *orig_dst_pte;
 	pte_t *src_pte, *dst_pte;
@@ -736,7 +743,7 @@ again:
 	dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl);
 	if (!dst_pte)
 		return -ENOMEM;
-	src_pte = pte_offset_map_nested(src_pmd, addr);
+	src_pte = pte_offset_map(src_pmd, addr);
 	src_ptl = pte_lockptr(src_mm, src_pmd);
 	spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 	orig_src_pte = src_pte;
@@ -767,7 +774,7 @@ again:
 
 	arch_leave_lazy_mmu_mode();
 	spin_unlock(src_ptl);
-	pte_unmap_nested(orig_src_pte);
+	pte_unmap(orig_src_pte);
 	add_mm_rss_vec(dst_mm, rss);
 	pte_unmap_unlock(orig_dst_pte, dst_ptl);
 	cond_resched();
@@ -795,6 +802,17 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 	src_pmd = pmd_offset(src_pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		if (pmd_trans_huge(*src_pmd)) {
+			int err;
+			VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
+			err = copy_huge_pmd(dst_mm, src_mm,
+					    dst_pmd, src_pmd, addr, vma);
+			if (err == -ENOMEM)
+				return -ENOMEM;
+			if (!err)
+				continue;
+			/* fall through */
+		}
 		if (pmd_none_or_clear_bad(src_pmd))
 			continue;
 		if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd,
@@ -997,6 +1015,16 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		if (pmd_trans_huge(*pmd)) {
+			if (next-addr != HPAGE_PMD_SIZE) {
+				VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem));
+				split_huge_page_pmd(vma->vm_mm, pmd);
+			} else if (zap_huge_pmd(tlb, vma, pmd)) {
+				(*zap_work)--;
+				continue;
+			}
+			/* fall through */
+		}
 		if (pmd_none_or_clear_bad(pmd)) {
 			(*zap_work)--;
 			continue;
@@ -1262,7 +1290,7 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	pud = pud_offset(pgd, address);
 	if (pud_none(*pud))
 		goto no_page_table;
-	if (pud_huge(*pud)) {
+	if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) {
 		BUG_ON(flags & FOLL_GET);
 		page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE);
 		goto out;
@@ -1273,11 +1301,32 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
 		goto no_page_table;
-	if (pmd_huge(*pmd)) {
+	if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) {
 		BUG_ON(flags & FOLL_GET);
 		page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE);
 		goto out;
 	}
+	if (pmd_trans_huge(*pmd)) {
+		if (flags & FOLL_SPLIT) {
+			split_huge_page_pmd(mm, pmd);
+			goto split_fallthrough;
+		}
+		spin_lock(&mm->page_table_lock);
+		if (likely(pmd_trans_huge(*pmd))) {
+			if (unlikely(pmd_trans_splitting(*pmd))) {
+				spin_unlock(&mm->page_table_lock);
+				wait_split_huge_page(vma->anon_vma, pmd);
+			} else {
+				page = follow_trans_huge_pmd(mm, address,
+							     pmd, flags);
+				spin_unlock(&mm->page_table_lock);
+				goto out;
+			}
+		} else
+			spin_unlock(&mm->page_table_lock);
+		/* fall through */
+	}
+split_fallthrough:
 	if (unlikely(pmd_bad(*pmd)))
 		goto no_page_table;
 
@@ -1310,6 +1359,28 @@ struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
 		 */
 		mark_page_accessed(page);
 	}
+	if (flags & FOLL_MLOCK) {
+		/*
+		 * The preliminary mapping check is mainly to avoid the
+		 * pointless overhead of lock_page on the ZERO_PAGE
+		 * which might bounce very badly if there is contention.
+		 *
+		 * If the page is already locked, we don't need to
+		 * handle it now - vmscan will handle it later if and
+		 * when it attempts to reclaim the page.
+		 */
+		if (page->mapping && trylock_page(page)) {
+			lru_add_drain();  /* push cached pages to LRU */
+			/*
+			 * Because we lock page here and migration is
+			 * blocked by the pte's page reference, we need
+			 * only check for file-cache page truncation.
+			 */
+			if (page->mapping)
+				mlock_vma_page(page);
+			unlock_page(page);
+		}
+	}
 unlock:
 	pte_unmap_unlock(ptep, ptl);
 out:
@@ -1341,7 +1412,8 @@ no_page_table:
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int nr_pages, unsigned int gup_flags,
-		     struct page **pages, struct vm_area_struct **vmas)
+		     struct page **pages, struct vm_area_struct **vmas,
+		     int *nonblocking)
 {
 	int i;
 	unsigned long vm_flags;
@@ -1386,6 +1458,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			pmd = pmd_offset(pud, pg);
 			if (pmd_none(*pmd))
 				return i ? : -EFAULT;
+			VM_BUG_ON(pmd_trans_huge(*pmd));
 			pte = pte_offset_map(pmd, pg);
 			if (pte_none(*pte)) {
 				pte_unmap(pte);
@@ -1441,16 +1514,22 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 			cond_resched();
 			while (!(page = follow_page(vma, start, foll_flags))) {
 				int ret;
+				unsigned int fault_flags = 0;
+
+				if (foll_flags & FOLL_WRITE)
+					fault_flags |= FAULT_FLAG_WRITE;
+				if (nonblocking)
+					fault_flags |= FAULT_FLAG_ALLOW_RETRY;
 
 				ret = handle_mm_fault(mm, vma, start,
-					(foll_flags & FOLL_WRITE) ?
-					FAULT_FLAG_WRITE : 0);
+							fault_flags);
 
 				if (ret & VM_FAULT_ERROR) {
 					if (ret & VM_FAULT_OOM)
 						return i ? i : -ENOMEM;
 					if (ret &
-					    (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
+					    (VM_FAULT_HWPOISON|VM_FAULT_HWPOISON_LARGE|
+					     VM_FAULT_SIGBUS))
 						return i ? i : -EFAULT;
 					BUG();
 				}
@@ -1459,6 +1538,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 				else
 					tsk->min_flt++;
 
+				if (ret & VM_FAULT_RETRY) {
+					*nonblocking = 0;
+					return i;
+				}
+
 				/*
 				 * The VM_FAULT_WRITE bit tells us that
 				 * do_wp_page has broken COW when necessary,
@@ -1558,7 +1642,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (force)
 		flags |= FOLL_FORCE;
 
-	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
+	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
+				NULL);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -1583,22 +1668,25 @@ struct page *get_dump_page(unsigned long addr)
 	struct page *page;
 
 	if (__get_user_pages(current, current->mm, addr, 1,
-			FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
+			     FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma,
+			     NULL) < 1)
 		return NULL;
 	flush_cache_page(vma, addr, page_to_pfn(page));
 	return page;
 }
 #endif /* CONFIG_ELF_CORE */
 
-pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
+pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			spinlock_t **ptl)
 {
 	pgd_t * pgd = pgd_offset(mm, addr);
 	pud_t * pud = pud_alloc(mm, pgd, addr);
 	if (pud) {
 		pmd_t * pmd = pmd_alloc(mm, pud, addr);
-		if (pmd)
+		if (pmd) {
+			VM_BUG_ON(pmd_trans_huge(*pmd));
 			return pte_alloc_map_lock(mm, pmd, addr, ptl);
+		}
 	}
 	return NULL;
 }
@@ -1817,6 +1905,7 @@ static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud,
 	pmd = pmd_alloc(mm, pud, addr);
 	if (!pmd)
 		return -ENOMEM;
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	do {
 		next = pmd_addr_end(addr, end);
 		if (remap_pte_range(mm, pmd, addr, next,
@@ -2047,19 +2136,6 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
 	return same;
 }
 
-/*
- * 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;
-}
-
 static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
 {
 	/*
@@ -2079,7 +2155,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 		 * zeroes.
 		 */
 		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
-			memset(kaddr, 0, PAGE_SIZE);
+			clear_page(kaddr);
 		kunmap_atomic(kaddr, KM_USER0);
 		flush_dcache_page(dst);
 	} else
@@ -2107,10 +2183,11 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		unsigned long address, pte_t *page_table, pmd_t *pmd,
 		spinlock_t *ptl, pte_t orig_pte)
+	__releases(ptl)
 {
 	struct page *old_page, *new_page;
 	pte_t entry;
-	int reuse = 0, ret = 0;
+	int ret = 0;
 	int page_mkwrite = 0;
 	struct page *dirty_page = NULL;
 
@@ -2142,19 +2219,20 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 							 &ptl);
 			if (!pte_same(*page_table, orig_pte)) {
 				unlock_page(old_page);
-				page_cache_release(old_page);
 				goto unlock;
 			}
 			page_cache_release(old_page);
 		}
-		reuse = reuse_swap_page(old_page);
-		if (reuse)
+		if (reuse_swap_page(old_page)) {
 			/*
 			 * The page is all ours.  Move it to our anon_vma so
 			 * the rmap code will not search our parent or siblings.
 			 * Protected against the rmap code by the page lock.
 			 */
 			page_move_anon_rmap(old_page, vma, address);
+			unlock_page(old_page);
+			goto reuse;
+		}
 		unlock_page(old_page);
 	} else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) ==
 					(VM_WRITE|VM_SHARED))) {
@@ -2210,7 +2288,6 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 							 &ptl);
 			if (!pte_same(*page_table, orig_pte)) {
 				unlock_page(old_page);
-				page_cache_release(old_page);
 				goto unlock;
 			}
 
@@ -2218,18 +2295,52 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		}
 		dirty_page = old_page;
 		get_page(dirty_page);
-		reuse = 1;
-	}
 
-	if (reuse) {
 reuse:
 		flush_cache_page(vma, address, pte_pfn(orig_pte));
 		entry = pte_mkyoung(orig_pte);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 		if (ptep_set_access_flags(vma, address, page_table, entry,1))
 			update_mmu_cache(vma, address, page_table);
+		pte_unmap_unlock(page_table, ptl);
 		ret |= VM_FAULT_WRITE;
-		goto unlock;
+
+		if (!dirty_page)
+			return ret;
+
+		/*
+		 * Yes, Virginia, this is actually required to prevent a race
+		 * with clear_page_dirty_for_io() from clearing the page dirty
+		 * bit after it clear all dirty ptes, but before a racing
+		 * do_wp_page installs a dirty pte.
+		 *
+		 * do_no_page is protected similarly.
+		 */
+		if (!page_mkwrite) {
+			wait_on_page_locked(dirty_page);
+			set_page_dirty_balance(dirty_page, page_mkwrite);
+		}
+		put_page(dirty_page);
+		if (page_mkwrite) {
+			struct address_space *mapping = dirty_page->mapping;
+
+			set_page_dirty(dirty_page);
+			unlock_page(dirty_page);
+			page_cache_release(dirty_page);
+			if (mapping)	{
+				/*
+				 * Some device drivers do not set page.mapping
+				 * but still dirty their pages
+				 */
+				balance_dirty_pages_ratelimited(mapping);
+			}
+		}
+
+		/* file_update_time outside page_lock */
+		if (vma->vm_file)
+			file_update_time(vma->vm_file);
+
+		return ret;
 	}
 
 	/*
@@ -2254,16 +2365,6 @@ gotten:
 	}
 	__SetPageUptodate(new_page);
 
-	/*
-	 * Don't let another task, with possibly unlocked vma,
-	 * keep the mlocked page.
-	 */
-	if ((vma->vm_flags & VM_LOCKED) && old_page) {
-		lock_page(old_page);	/* for LRU manipulation */
-		clear_page_mlock(old_page);
-		unlock_page(old_page);
-	}
-
 	if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
 		goto oom_free_new;
 
@@ -2331,42 +2432,19 @@ gotten:
 
 	if (new_page)
 		page_cache_release(new_page);
-	if (old_page)
-		page_cache_release(old_page);
 unlock:
 	pte_unmap_unlock(page_table, ptl);
-	if (dirty_page) {
+	if (old_page) {
 		/*
-		 * Yes, Virginia, this is actually required to prevent a race
-		 * with clear_page_dirty_for_io() from clearing the page dirty
-		 * bit after it clear all dirty ptes, but before a racing
-		 * do_wp_page installs a dirty pte.
-		 *
-		 * do_no_page is protected similarly.
+		 * Don't let another task, with possibly unlocked vma,
+		 * keep the mlocked page.
 		 */
-		if (!page_mkwrite) {
-			wait_on_page_locked(dirty_page);
-			set_page_dirty_balance(dirty_page, page_mkwrite);
-		}
-		put_page(dirty_page);
-		if (page_mkwrite) {
-			struct address_space *mapping = dirty_page->mapping;
-
-			set_page_dirty(dirty_page);
-			unlock_page(dirty_page);
-			page_cache_release(dirty_page);
-			if (mapping)	{
-				/*
-				 * Some device drivers do not set page.mapping
-				 * but still dirty their pages
-				 */
-				balance_dirty_pages_ratelimited(mapping);
-			}
+		if ((ret & VM_FAULT_WRITE) && (vma->vm_flags & VM_LOCKED)) {
+			lock_page(old_page);	/* LRU manipulation */
+			munlock_vma_page(old_page);
+			unlock_page(old_page);
 		}
-
-		/* file_update_time outside page_lock */
-		if (vma->vm_file)
-			file_update_time(vma->vm_file);
+		page_cache_release(old_page);
 	}
 	return ret;
 oom_free_new:
@@ -2570,6 +2648,7 @@ void unmap_mapping_range(struct address_space *mapping,
 		details.last_index = ULONG_MAX;
 	details.i_mmap_lock = &mapping->i_mmap_lock;
 
+	mutex_lock(&mapping->unmap_mutex);
 	spin_lock(&mapping->i_mmap_lock);
 
 	/* Protect against endless unmapping loops */
@@ -2586,6 +2665,7 @@ void unmap_mapping_range(struct address_space *mapping,
 	if (unlikely(!list_empty(&mapping->i_mmap_nonlinear)))
 		unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details);
 	spin_unlock(&mapping->i_mmap_lock);
+	mutex_unlock(&mapping->unmap_mutex);
 }
 EXPORT_SYMBOL(unmap_mapping_range);
 
@@ -2626,6 +2706,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	struct page *page, *swapcache = NULL;
 	swp_entry_t entry;
 	pte_t pte;
+	int locked;
 	struct mem_cgroup *ptr = NULL;
 	int exclusive = 0;
 	int ret = 0;
@@ -2676,8 +2757,12 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_release;
 	}
 
-	lock_page(page);
+	locked = lock_page_or_retry(page, mm, flags);
 	delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+	if (!locked) {
+		ret |= VM_FAULT_RETRY;
+		goto out_release;
+	}
 
 	/*
 	 * Make sure try_to_free_swap or reuse_swap_page or swapoff did not
@@ -2926,7 +3011,8 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	vmf.page = NULL;
 
 	ret = vma->vm_ops->fault(vma, &vmf);
-	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
+	if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE |
+			    VM_FAULT_RETRY)))
 		return ret;
 
 	if (unlikely(PageHWPoison(vmf.page))) {
@@ -2967,12 +3053,6 @@ static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 				goto out;
 			}
 			charged = 1;
-			/*
-			 * Don't let another task, with possibly unlocked vma,
-			 * keep the mlocked page.
-			 */
-			if (vma->vm_flags & VM_LOCKED)
-				clear_page_mlock(vmf.page);
 			copy_user_highpage(page, vmf.page, address, vma);
 			__SetPageUptodate(page);
 		} else {
@@ -3139,9 +3219,9 @@ static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma,
  * but allow concurrent faults), and pte mapped but not yet locked.
  * We return with mmap_sem still held, but pte unmapped and unlocked.
  */
-static inline 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)
+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)
 {
 	pte_t entry;
 	spinlock_t *ptl;
@@ -3185,7 +3265,7 @@ static inline int handle_pte_fault(struct mm_struct *mm,
 		 * with threads.
 		 */
 		if (flags & FAULT_FLAG_WRITE)
-			flush_tlb_page(vma, address);
+			flush_tlb_fix_spurious_fault(vma, address);
 	}
 unlock:
 	pte_unmap_unlock(pte, ptl);
@@ -3220,9 +3300,40 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pmd = pmd_alloc(mm, pud, address);
 	if (!pmd)
 		return VM_FAULT_OOM;
-	pte = pte_alloc_map(mm, pmd, address);
-	if (!pte)
+	if (pmd_none(*pmd) && transparent_hugepage_enabled(vma)) {
+		if (!vma->vm_ops)
+			return do_huge_pmd_anonymous_page(mm, vma, address,
+							  pmd, flags);
+	} else {
+		pmd_t orig_pmd = *pmd;
+		barrier();
+		if (pmd_trans_huge(orig_pmd)) {
+			if (flags & FAULT_FLAG_WRITE &&
+			    !pmd_write(orig_pmd) &&
+			    !pmd_trans_splitting(orig_pmd))
+				return do_huge_pmd_wp_page(mm, vma, address,
+							   pmd, orig_pmd);
+			return 0;
+		}
+	}
+
+	/*
+	 * Use __pte_alloc instead of pte_alloc_map, because we can't
+	 * run pte_offset_map on the pmd, if an huge pmd could
+	 * materialize from under us from a different thread.
+	 */
+	if (unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
+	/* if an huge pmd materialized from under us just retry later */
+	if (unlikely(pmd_trans_huge(*pmd)))
+		return 0;
+	/*
+	 * A regular pmd is established and it can't morph into a huge pmd
+	 * from under us anymore at this point because we hold the mmap_sem
+	 * read mode and khugepaged takes it in write mode. So now it's
+	 * safe to run pte_offset_map().
+	 */
+	pte = pte_offset_map(pmd, address);
 
 	return handle_pte_fault(mm, vma, address, pte, pmd, flags);
 }
@@ -3288,7 +3399,12 @@ int make_pages_present(unsigned long addr, unsigned long end)
 	vma = find_vma(current->mm, addr);
 	if (!vma)
 		return -ENOMEM;
-	write = (vma->vm_flags & VM_WRITE) != 0;
+	/*
+	 * We want to touch writable mappings with a write fault in order
+	 * to break COW, except for shared mappings because these don't COW
+	 * and we would not want to dirty them for nothing.
+	 */
+	write = (vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE;
 	BUG_ON(addr >= end);
 	BUG_ON(end > vma->vm_end);
 	len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE;
@@ -3343,7 +3459,7 @@ int in_gate_area_no_task(unsigned long addr)
 
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
-static int follow_pte(struct mm_struct *mm, unsigned long address,
+static int __follow_pte(struct mm_struct *mm, unsigned long address,
 		pte_t **ptepp, spinlock_t **ptlp)
 {
 	pgd_t *pgd;
@@ -3360,6 +3476,7 @@ static int follow_pte(struct mm_struct *mm, unsigned long address,
 		goto out;
 
 	pmd = pmd_offset(pud, address);
+	VM_BUG_ON(pmd_trans_huge(*pmd));
 	if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
 		goto out;
 
@@ -3380,6 +3497,17 @@ out:
 	return -EINVAL;
 }
 
+static inline int follow_pte(struct mm_struct *mm, unsigned long address,
+			     pte_t **ptepp, spinlock_t **ptlp)
+{
+	int res;
+
+	/* (void) is needed to make gcc happy */
+	(void) __cond_lock(*ptlp,
+			   !(res = __follow_pte(mm, address, ptepp, ptlp)));
+	return res;
+}
+
 /**
  * follow_pfn - look up PFN at a user virtual address
  * @vma: memory mapping
@@ -3589,3 +3717,74 @@ void might_fault(void)
 }
 EXPORT_SYMBOL(might_fault);
 #endif
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
+static void clear_gigantic_page(struct page *page,
+				unsigned long addr,
+				unsigned int pages_per_huge_page)
+{
+	int i;
+	struct page *p = page;
+
+	might_sleep();
+	for (i = 0; i < pages_per_huge_page;
+	     i++, p = mem_map_next(p, page, i)) {
+		cond_resched();
+		clear_user_highpage(p, addr + i * PAGE_SIZE);
+	}
+}
+void clear_huge_page(struct page *page,
+		     unsigned long addr, unsigned int pages_per_huge_page)
+{
+	int i;
+
+	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
+		clear_gigantic_page(page, addr, pages_per_huge_page);
+		return;
+	}
+
+	might_sleep();
+	for (i = 0; i < pages_per_huge_page; i++) {
+		cond_resched();
+		clear_user_highpage(page + i, addr + i * PAGE_SIZE);
+	}
+}
+
+static void copy_user_gigantic_page(struct page *dst, struct page *src,
+				    unsigned long addr,
+				    struct vm_area_struct *vma,
+				    unsigned int pages_per_huge_page)
+{
+	int i;
+	struct page *dst_base = dst;
+	struct page *src_base = src;
+
+	for (i = 0; i < pages_per_huge_page; ) {
+		cond_resched();
+		copy_user_highpage(dst, src, addr + i*PAGE_SIZE, vma);
+
+		i++;
+		dst = mem_map_next(dst, dst_base, i);
+		src = mem_map_next(src, src_base, i);
+	}
+}
+
+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)
+{
+	int i;
+
+	if (unlikely(pages_per_huge_page > MAX_ORDER_NR_PAGES)) {
+		copy_user_gigantic_page(dst, src, addr, vma,
+					pages_per_huge_page);
+		return;
+	}
+
+	might_sleep();
+	for (i = 0; i < pages_per_huge_page; i++) {
+		cond_resched();
+		copy_user_highpage(dst + i, src + i, addr + i*PAGE_SIZE, vma);
+	}
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dd186c1a5d53..321fc7455df7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -34,6 +34,23 @@
 
 #include "internal.h"
 
+DEFINE_MUTEX(mem_hotplug_mutex);
+
+void lock_memory_hotplug(void)
+{
+	mutex_lock(&mem_hotplug_mutex);
+
+	/* for exclusive hibernation if CONFIG_HIBERNATION=y */
+	lock_system_sleep();
+}
+
+void unlock_memory_hotplug(void)
+{
+	unlock_system_sleep();
+	mutex_unlock(&mem_hotplug_mutex);
+}
+
+
 /* add this memory to iomem resource */
 static struct resource *register_memory_resource(u64 start, u64 size)
 {
@@ -65,9 +82,10 @@ static void release_memory_resource(struct resource *res)
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void get_page_bootmem(unsigned long info,  struct page *page, int type)
+static void get_page_bootmem(unsigned long info,  struct page *page,
+			     unsigned long type)
 {
-	atomic_set(&page->_mapcount, type);
+	page->lru.next = (struct list_head *) type;
 	SetPagePrivate(page);
 	set_page_private(page, info);
 	atomic_inc(&page->_count);
@@ -77,15 +95,16 @@ static void get_page_bootmem(unsigned long info,  struct page *page, int type)
  * so use __ref to tell modpost not to generate a warning */
 void __ref put_page_bootmem(struct page *page)
 {
-	int type;
+	unsigned long type;
 
-	type = atomic_read(&page->_mapcount);
-	BUG_ON(type >= -1);
+	type = (unsigned long) page->lru.next;
+	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
 
 	if (atomic_dec_return(&page->_count) == 1) {
 		ClearPagePrivate(page);
 		set_page_private(page, 0);
-		reset_page_mapcount(page);
+		INIT_LIST_HEAD(&page->lru);
 		__free_pages_bootmem(page, 0);
 	}
 
@@ -390,6 +409,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 	int ret;
 	struct memory_notify arg;
 
+	lock_memory_hotplug();
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
 	arg.status_change_nid = -1;
@@ -402,6 +422,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
+		unlock_memory_hotplug();
 		return ret;
 	}
 	/*
@@ -426,6 +447,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 		printk(KERN_DEBUG "online_pages %lx at %lx failed\n",
 			nr_pages, pfn);
 		memory_notify(MEM_CANCEL_ONLINE, &arg);
+		unlock_memory_hotplug();
 		return ret;
 	}
 
@@ -450,6 +472,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages)
 
 	if (onlined_pages)
 		memory_notify(MEM_ONLINE, &arg);
+	unlock_memory_hotplug();
 
 	return 0;
 }
@@ -493,7 +516,7 @@ int mem_online_node(int nid)
 	pg_data_t	*pgdat;
 	int	ret;
 
-	lock_system_sleep();
+	lock_memory_hotplug();
 	pgdat = hotadd_new_pgdat(nid, 0);
 	if (pgdat) {
 		ret = -ENOMEM;
@@ -504,7 +527,7 @@ int mem_online_node(int nid)
 	BUG_ON(ret);
 
 out:
-	unlock_system_sleep();
+	unlock_memory_hotplug();
 	return ret;
 }
 
@@ -516,7 +539,7 @@ int __ref add_memory(int nid, u64 start, u64 size)
 	struct resource *res;
 	int ret;
 
-	lock_system_sleep();
+	lock_memory_hotplug();
 
 	res = register_memory_resource(start, size);
 	ret = -EEXIST;
@@ -563,7 +586,7 @@ error:
 		release_memory_resource(res);
 
 out:
-	unlock_system_sleep();
+	unlock_memory_hotplug();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(add_memory);
@@ -602,27 +625,14 @@ static struct page *next_active_pageblock(struct page *page)
 /* Checks if this range of memory is likely to be hot-removable. */
 int is_mem_section_removable(unsigned long start_pfn, unsigned long nr_pages)
 {
-	int type;
 	struct page *page = pfn_to_page(start_pfn);
 	struct page *end_page = page + nr_pages;
 
 	/* Check the starting page of each pageblock within the range */
 	for (; page < end_page; page = next_active_pageblock(page)) {
-		type = get_pageblock_migratetype(page);
-
-		/*
-		 * A pageblock containing MOVABLE or free pages is considered
-		 * removable
-		 */
-		if (type != MIGRATE_MOVABLE && !pageblock_free(page))
-			return 0;
-
-		/*
-		 * A pageblock starting with a PageReserved page is not
-		 * considered removable.
-		 */
-		if (PageReserved(page))
+		if (!is_pageblock_removable_nolock(page))
 			return 0;
+		cond_resched();
 	}
 
 	/* All pageblocks in the memory block are likely to be hot-removable */
@@ -659,7 +669,7 @@ static int test_pages_in_a_zone(unsigned long start_pfn, unsigned long end_pfn)
  * Scanning pfn is much easier than scanning lru list.
  * Scan pfn from start to end and Find LRU page.
  */
-int scan_lru_pages(unsigned long start, unsigned long end)
+static unsigned long scan_lru_pages(unsigned long start, unsigned long end)
 {
 	unsigned long pfn;
 	struct page *page;
@@ -709,29 +719,31 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 					    page_is_file_cache(page));
 
 		} else {
-			/* Becasue we don't have big zone->lock. we should
-			   check this again here. */
-			if (page_count(page))
-				not_managed++;
 #ifdef CONFIG_DEBUG_VM
 			printk(KERN_ALERT "removing pfn %lx from LRU failed\n",
 			       pfn);
 			dump_page(page);
 #endif
+			/* Becasue we don't have big zone->lock. we should
+			   check this again here. */
+			if (page_count(page)) {
+				not_managed++;
+				ret = -EBUSY;
+				break;
+			}
 		}
 	}
-	ret = -EBUSY;
-	if (not_managed) {
-		if (!list_empty(&source))
+	if (!list_empty(&source)) {
+		if (not_managed) {
+			putback_lru_pages(&source);
+			goto out;
+		}
+		/* this function returns # of failed pages */
+		ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
+								true, true);
+		if (ret)
 			putback_lru_pages(&source);
-		goto out;
 	}
-	ret = 0;
-	if (list_empty(&source))
-		goto out;
-	/* this function returns # of failed pages */
-	ret = migrate_pages(&source, hotremove_migrate_alloc, 0, 1);
-
 out:
 	return ret;
 }
@@ -803,7 +815,7 @@ static int offline_pages(unsigned long start_pfn,
 	if (!test_pages_in_a_zone(start_pfn, end_pfn))
 		return -EINVAL;
 
-	lock_system_sleep();
+	lock_memory_hotplug();
 
 	zone = page_zone(pfn_to_page(start_pfn));
 	node = zone_to_nid(zone);
@@ -840,7 +852,6 @@ repeat:
 	ret = 0;
 	if (drain) {
 		lru_add_drain_all();
-		flush_scheduled_work();
 		cond_resched();
 		drain_all_pages();
 	}
@@ -862,7 +873,6 @@ repeat:
 	}
 	/* drain all zone's lru pagevec, this is asyncronous... */
 	lru_add_drain_all();
-	flush_scheduled_work();
 	yield();
 	/* drain pcp pages , this is synchrouns. */
 	drain_all_pages();
@@ -894,7 +904,7 @@ repeat:
 	writeback_set_ratelimit();
 
 	memory_notify(MEM_OFFLINE, &arg);
-	unlock_system_sleep();
+	unlock_memory_hotplug();
 	return 0;
 
 failed_removal:
@@ -905,7 +915,7 @@ failed_removal:
 	undo_isolate_page_range(start_pfn, end_pfn);
 
 out:
-	unlock_system_sleep();
+	unlock_memory_hotplug();
 	return ret;
 }
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f969da5dd8a2..368fc9d23610 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -514,6 +514,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		split_huge_page_pmd(vma->vm_mm, pmd);
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		if (check_pte_range(vma, pmd, addr, next, nodes,
@@ -924,15 +925,22 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 	nodemask_t nmask;
 	LIST_HEAD(pagelist);
 	int err = 0;
+	struct vm_area_struct *vma;
 
 	nodes_clear(nmask);
 	node_set(source, nmask);
 
-	check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
+	vma = check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
 			flags | MPOL_MF_DISCONTIG_OK, &pagelist);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
 
-	if (!list_empty(&pagelist))
-		err = migrate_pages(&pagelist, new_node_page, dest, 0);
+	if (!list_empty(&pagelist)) {
+		err = migrate_pages(&pagelist, new_node_page, dest,
+								false, true);
+		if (err)
+			putback_lru_pages(&pagelist);
+	}
 
 	return err;
 }
@@ -1147,9 +1155,13 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		err = mbind_range(mm, start, end, new);
 
-		if (!list_empty(&pagelist))
+		if (!list_empty(&pagelist)) {
 			nr_failed = migrate_pages(&pagelist, new_vma_page,
-						(unsigned long)vma, 0);
+						(unsigned long)vma,
+						false, true);
+			if (nr_failed)
+				putback_lru_pages(&pagelist);
+		}
 
 		if (!err && nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
@@ -1298,15 +1310,15 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode,
 		goto out;
 
 	/* Find the mm_struct */
-	read_lock(&tasklist_lock);
+	rcu_read_lock();
 	task = pid ? find_task_by_vpid(pid) : current;
 	if (!task) {
-		read_unlock(&tasklist_lock);
+		rcu_read_unlock();
 		err = -ESRCH;
 		goto out;
 	}
 	mm = get_task_mm(task);
-	read_unlock(&tasklist_lock);
+	rcu_read_unlock();
 
 	err = -EINVAL;
 	if (!mm)
@@ -1588,7 +1600,7 @@ unsigned slab_node(struct mempolicy *policy)
 		(void)first_zones_zonelist(zonelist, highest_zoneidx,
 							&policy->v.nodes,
 							&zone);
-		return zone->node;
+		return zone ? zone->node : numa_node_id();
 	}
 
 	default:
@@ -1784,7 +1796,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
 }
 
 /**
- * 	alloc_page_vma	- Allocate a page for a VMA.
+ * 	alloc_pages_vma	- Allocate a page for a VMA.
  *
  * 	@gfp:
  *      %GFP_USER    user allocation.
@@ -1793,6 +1805,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *      %GFP_FS      allocation should not call back into a file system.
  *      %GFP_ATOMIC  don't sleep.
  *
+ *	@order:Order of the GFP allocation.
  * 	@vma:  Pointer to VMA or NULL if not available.
  *	@addr: Virtual Address of the allocation. Must be inside the VMA.
  *
@@ -1806,7 +1819,8 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
  *	Should be called with the mm_sem of the vma hold.
  */
 struct page *
-alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
+alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
+		unsigned long addr)
 {
 	struct mempolicy *pol = get_vma_policy(current, vma, addr);
 	struct zonelist *zl;
@@ -1818,7 +1832,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
 		mpol_cond_put(pol);
-		page = alloc_page_interleave(gfp, 0, nid);
+		page = alloc_page_interleave(gfp, order, nid);
 		put_mems_allowed();
 		return page;
 	}
@@ -1827,7 +1841,7 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 		/*
 		 * slow path: ref counted shared policy
 		 */
-		struct page *page =  __alloc_pages_nodemask(gfp, 0,
+		struct page *page =  __alloc_pages_nodemask(gfp, order,
 						zl, policy_nodemask(gfp, pol));
 		__mpol_put(pol);
 		put_mems_allowed();
@@ -1836,7 +1850,8 @@ alloc_page_vma(gfp_t gfp, struct vm_area_struct *vma, unsigned long addr)
 	/*
 	 * fast path:  default or task policy
 	 */
-	page = __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol));
+	page = __alloc_pages_nodemask(gfp, order, zl,
+				      policy_nodemask(gfp, pol));
 	put_mems_allowed();
 	return page;
 }
diff --git a/mm/migrate.c b/mm/migrate.c
index 38e7cad782f4..766115253807 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -32,8 +32,11 @@
 #include <linux/security.h>
 #include <linux/memcontrol.h>
 #include <linux/syscalls.h>
+#include <linux/hugetlb.h>
 #include <linux/gfp.h>
 
+#include <asm/tlbflush.h>
+
 #include "internal.h"
 
 #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
@@ -95,26 +98,36 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	pte_t *ptep, pte;
  	spinlock_t *ptl;
 
- 	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
-		goto out;
+	if (unlikely(PageHuge(new))) {
+		ptep = huge_pte_offset(mm, addr);
+		if (!ptep)
+			goto out;
+		ptl = &mm->page_table_lock;
+	} else {
+		pgd = pgd_offset(mm, addr);
+		if (!pgd_present(*pgd))
+			goto out;
 
-	pud = pud_offset(pgd, addr);
-	if (!pud_present(*pud))
-		goto out;
+		pud = pud_offset(pgd, addr);
+		if (!pud_present(*pud))
+			goto out;
 
-	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd))
-		goto out;
+		pmd = pmd_offset(pud, addr);
+		if (pmd_trans_huge(*pmd))
+			goto out;
+		if (!pmd_present(*pmd))
+			goto out;
 
-	ptep = pte_offset_map(pmd, addr);
+		ptep = pte_offset_map(pmd, addr);
 
-	if (!is_swap_pte(*ptep)) {
-		pte_unmap(ptep);
-		goto out;
- 	}
+		if (!is_swap_pte(*ptep)) {
+			pte_unmap(ptep);
+			goto out;
+		}
+
+		ptl = pte_lockptr(mm, pmd);
+	}
 
- 	ptl = pte_lockptr(mm, pmd);
  	spin_lock(ptl);
 	pte = *ptep;
 	if (!is_swap_pte(pte))
@@ -130,10 +143,19 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 	pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
 	if (is_write_migration_entry(entry))
 		pte = pte_mkwrite(pte);
+#ifdef CONFIG_HUGETLB_PAGE
+	if (PageHuge(new))
+		pte = pte_mkhuge(pte);
+#endif
 	flush_cache_page(vma, addr, pte_pfn(pte));
 	set_pte_at(mm, addr, ptep, pte);
 
-	if (PageAnon(new))
+	if (PageHuge(new)) {
+		if (PageAnon(new))
+			hugepage_add_anon_rmap(new, vma, addr);
+		else
+			page_dup_rmap(new);
+	} else if (PageAnon(new))
 		page_add_anon_rmap(new, vma, addr);
 	else
 		page_add_file_rmap(new);
@@ -226,7 +248,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 
 	expected_count = 2 + page_has_private(page);
 	if (page_count(page) != expected_count ||
-			(struct page *)radix_tree_deref_slot(pslot) != page) {
+		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
 		spin_unlock_irq(&mapping->tree_lock);
 		return -EAGAIN;
 	}
@@ -276,11 +298,59 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 }
 
 /*
+ * The expected number of remaining references is the same as that
+ * of migrate_page_move_mapping().
+ */
+int migrate_huge_page_move_mapping(struct address_space *mapping,
+				   struct page *newpage, struct page *page)
+{
+	int expected_count;
+	void **pslot;
+
+	if (!mapping) {
+		if (page_count(page) != 1)
+			return -EAGAIN;
+		return 0;
+	}
+
+	spin_lock_irq(&mapping->tree_lock);
+
+	pslot = radix_tree_lookup_slot(&mapping->page_tree,
+					page_index(page));
+
+	expected_count = 2 + page_has_private(page);
+	if (page_count(page) != expected_count ||
+		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	if (!page_freeze_refs(page, expected_count)) {
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	get_page(newpage);
+
+	radix_tree_replace_slot(pslot, newpage);
+
+	page_unfreeze_refs(page, expected_count);
+
+	__put_page(page);
+
+	spin_unlock_irq(&mapping->tree_lock);
+	return 0;
+}
+
+/*
  * Copy the page to its new location
  */
-static void migrate_page_copy(struct page *newpage, struct page *page)
+void migrate_page_copy(struct page *newpage, struct page *page)
 {
-	copy_highpage(newpage, page);
+	if (PageHuge(page))
+		copy_huge_page(newpage, page);
+	else
+		copy_highpage(newpage, page);
 
 	if (PageError(page))
 		SetPageError(newpage);
@@ -431,7 +501,6 @@ static int writeout(struct address_space *mapping, struct page *page)
 		.nr_to_write = 1,
 		.range_start = 0,
 		.range_end = LLONG_MAX,
-		.nonblocking = 1,
 		.for_reclaim = 1
 	};
 	int rc;
@@ -547,13 +616,12 @@ static int move_to_new_page(struct page *newpage, struct page *page,
  * to the newly allocated page in newpage.
  */
 static int unmap_and_move(new_page_t get_new_page, unsigned long private,
-			struct page *page, int force, int offlining)
+			struct page *page, int force, bool offlining, bool sync)
 {
 	int rc = 0;
 	int *result = NULL;
 	struct page *newpage = get_new_page(page, private, &result);
 	int remap_swapcache = 1;
-	int rcu_locked = 0;
 	int charge = 0;
 	struct mem_cgroup *mem = NULL;
 	struct anon_vma *anon_vma = NULL;
@@ -565,6 +633,9 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		/* page was freed from under us. So we are done. */
 		goto move_newpage;
 	}
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page(page)))
+			goto move_newpage;
 
 	/* prepare cgroup just returns 0 or -ENOMEM */
 	rc = -EAGAIN;
@@ -572,6 +643,23 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	if (!trylock_page(page)) {
 		if (!force)
 			goto move_newpage;
+
+		/*
+		 * It's not safe for direct compaction to call lock_page.
+		 * For example, during page readahead pages are added locked
+		 * to the LRU. Later, when the IO completes the pages are
+		 * marked uptodate and unlocked. However, the queueing
+		 * could be merging multiple pages for one bio (e.g.
+		 * mpage_readpages). If an allocation happens for the
+		 * second or third page, the process can end up locking
+		 * the same page twice and deadlocking. Rather than
+		 * trying to be clever about what pages can be locked,
+		 * avoid the use of lock_page for direct compaction
+		 * altogether.
+		 */
+		if (current->flags & PF_MEMALLOC)
+			goto move_newpage;
+
 		lock_page(page);
 	}
 
@@ -598,27 +686,33 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	BUG_ON(charge);
 
 	if (PageWriteback(page)) {
-		if (!force)
+		if (!force || !sync)
 			goto uncharge;
 		wait_on_page_writeback(page);
 	}
 	/*
 	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
 	 * we cannot notice that anon_vma is freed while we migrates a page.
-	 * This rcu_read_lock() delays freeing anon_vma pointer until the end
+	 * This get_anon_vma() delays freeing anon_vma pointer until the end
 	 * of migration. File cache pages are no problem because of page_lock()
 	 * File Caches may use write_page() or lock_page() in migration, then,
 	 * just care Anon page here.
 	 */
 	if (PageAnon(page)) {
-		rcu_read_lock();
-		rcu_locked = 1;
-
-		/* Determine how to safely use anon_vma */
-		if (!page_mapped(page)) {
-			if (!PageSwapCache(page))
-				goto rcu_unlock;
-
+		/*
+		 * Only page_lock_anon_vma() understands the subtleties of
+		 * getting a hold on an anon_vma from outside one of its mms.
+		 */
+		anon_vma = page_lock_anon_vma(page);
+		if (anon_vma) {
+			/*
+			 * Take a reference count on the anon_vma if the
+			 * page is mapped so that it is guaranteed to
+			 * exist when the page is remapped later
+			 */
+			get_anon_vma(anon_vma);
+			page_unlock_anon_vma(anon_vma);
+		} else if (PageSwapCache(page)) {
 			/*
 			 * We cannot be sure that the anon_vma of an unmapped
 			 * swapcache page is safe to use because we don't
@@ -633,13 +727,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 			 */
 			remap_swapcache = 0;
 		} else {
-			/*
-			 * Take a reference count on the anon_vma if the
-			 * page is mapped so that it is guaranteed to
-			 * exist when the page is remapped later
-			 */
-			anon_vma = page_anon_vma(page);
-			get_anon_vma(anon_vma);
+			goto uncharge;
 		}
 	}
 
@@ -656,16 +744,10 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	 * free the metadata, so the page can be freed.
 	 */
 	if (!page->mapping) {
-		if (!PageAnon(page) && page_has_private(page)) {
-			/*
-			 * Go direct to try_to_free_buffers() here because
-			 * a) that's what try_to_release_page() would do anyway
-			 * b) we may be under rcu_read_lock() here, so we can't
-			 *    use GFP_KERNEL which is what try_to_release_page()
-			 *    needs to be effective.
-			 */
+		VM_BUG_ON(PageAnon(page));
+		if (page_has_private(page)) {
 			try_to_free_buffers(page);
-			goto rcu_unlock;
+			goto uncharge;
 		}
 		goto skip_unmap;
 	}
@@ -679,20 +761,18 @@ skip_unmap:
 
 	if (rc && remap_swapcache)
 		remove_migration_ptes(page, page);
-rcu_unlock:
 
 	/* Drop an anon_vma reference if we took one */
 	if (anon_vma)
 		drop_anon_vma(anon_vma);
 
-	if (rcu_locked)
-		rcu_read_unlock();
 uncharge:
 	if (!charge)
-		mem_cgroup_end_migration(mem, page, newpage);
+		mem_cgroup_end_migration(mem, page, newpage, rc == 0);
 unlock:
 	unlock_page(page);
 
+move_newpage:
 	if (rc != -EAGAIN) {
  		/*
  		 * A page that has been migrated has all references
@@ -706,8 +786,6 @@ unlock:
 		putback_lru_page(page);
 	}
 
-move_newpage:
-
 	/*
 	 * Move the new page to the LRU. If migration was not successful
 	 * then this will free the page.
@@ -724,6 +802,81 @@ move_newpage:
 }
 
 /*
+ * Counterpart of unmap_and_move_page() for hugepage migration.
+ *
+ * This function doesn't wait the completion of hugepage I/O
+ * because there is no race between I/O and migration for hugepage.
+ * Note that currently hugepage I/O occurs only in direct I/O
+ * where no lock is held and PG_writeback is irrelevant,
+ * and writeback status of all subpages are counted in the reference
+ * count of the head page (i.e. if all subpages of a 2MB hugepage are
+ * under direct I/O, the reference of the head page is 512 and a bit more.)
+ * This means that when we try to migrate hugepage whose subpages are
+ * doing direct I/O, some references remain after try_to_unmap() and
+ * hugepage migration fails without data corruption.
+ *
+ * There is also no race when direct I/O is issued on the page under migration,
+ * because then pte is replaced with migration swap entry and direct I/O code
+ * will wait in the page fault for migration to complete.
+ */
+static int unmap_and_move_huge_page(new_page_t get_new_page,
+				unsigned long private, struct page *hpage,
+				int force, bool offlining, bool sync)
+{
+	int rc = 0;
+	int *result = NULL;
+	struct page *new_hpage = get_new_page(hpage, private, &result);
+	struct anon_vma *anon_vma = NULL;
+
+	if (!new_hpage)
+		return -ENOMEM;
+
+	rc = -EAGAIN;
+
+	if (!trylock_page(hpage)) {
+		if (!force || !sync)
+			goto out;
+		lock_page(hpage);
+	}
+
+	if (PageAnon(hpage)) {
+		anon_vma = page_lock_anon_vma(hpage);
+		if (anon_vma) {
+			get_anon_vma(anon_vma);
+			page_unlock_anon_vma(anon_vma);
+		}
+	}
+
+	try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+
+	if (!page_mapped(hpage))
+		rc = move_to_new_page(new_hpage, hpage, 1);
+
+	if (rc)
+		remove_migration_ptes(hpage, hpage);
+
+	if (anon_vma)
+		drop_anon_vma(anon_vma);
+out:
+	unlock_page(hpage);
+
+	if (rc != -EAGAIN) {
+		list_del(&hpage->lru);
+		put_page(hpage);
+	}
+
+	put_page(new_hpage);
+
+	if (result) {
+		if (rc)
+			*result = rc;
+		else
+			*result = page_to_nid(new_hpage);
+	}
+	return rc;
+}
+
+/*
  * migrate_pages
  *
  * The function takes one list of pages to migrate and a function
@@ -732,13 +885,15 @@ move_newpage:
  *
  * The function returns after 10 attempts or if no pages
  * are movable anymore because to has become empty
- * or no retryable pages exist anymore. All pages will be
- * returned to the LRU or freed.
+ * or no retryable pages exist anymore.
+ * Caller should call putback_lru_pages to return pages to the LRU
+ * or free list only if ret != 0.
  *
  * Return: Number of pages not migrated or error code.
  */
 int migrate_pages(struct list_head *from,
-		new_page_t get_new_page, unsigned long private, int offlining)
+		new_page_t get_new_page, unsigned long private, bool offlining,
+		bool sync)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -758,7 +913,8 @@ int migrate_pages(struct list_head *from,
 			cond_resched();
 
 			rc = unmap_and_move(get_new_page, private,
-						page, pass > 2, offlining);
+						page, pass > 2, offlining,
+						sync);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -780,8 +936,50 @@ out:
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
 
-	putback_lru_pages(from);
+	if (rc)
+		return rc;
+
+	return nr_failed + retry;
+}
+
+int migrate_huge_pages(struct list_head *from,
+		new_page_t get_new_page, unsigned long private, bool offlining,
+		bool sync)
+{
+	int retry = 1;
+	int nr_failed = 0;
+	int pass = 0;
+	struct page *page;
+	struct page *page2;
+	int rc;
+
+	for (pass = 0; pass < 10 && retry; pass++) {
+		retry = 0;
+
+		list_for_each_entry_safe(page, page2, from, lru) {
+			cond_resched();
 
+			rc = unmap_and_move_huge_page(get_new_page,
+					private, page, pass > 2, offlining,
+					sync);
+
+			switch(rc) {
+			case -ENOMEM:
+				goto out;
+			case -EAGAIN:
+				retry++;
+				break;
+			case 0:
+				break;
+			default:
+				/* Permanent failure */
+				nr_failed++;
+				break;
+			}
+		}
+	}
+	rc = 0;
+out:
 	if (rc)
 		return rc;
 
@@ -841,10 +1039,10 @@ static int do_move_page_to_node_array(struct mm_struct *mm,
 
 		err = -EFAULT;
 		vma = find_vma(mm, pp->addr);
-		if (!vma || !vma_migratable(vma))
+		if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma))
 			goto set_status;
 
-		page = follow_page(vma, pp->addr, FOLL_GET);
+		page = follow_page(vma, pp->addr, FOLL_GET|FOLL_SPLIT);
 
 		err = PTR_ERR(page);
 		if (IS_ERR(page))
@@ -890,9 +1088,12 @@ set_status:
 	}
 
 	err = 0;
-	if (!list_empty(&pagelist))
+	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_page_node,
-				(unsigned long)pm, 0);
+				(unsigned long)pm, 0, true);
+		if (err)
+			putback_lru_pages(&pagelist);
+	}
 
 	up_read(&mm->mmap_sem);
 	return err;
@@ -1005,7 +1206,7 @@ static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
 		int err = -EFAULT;
 
 		vma = find_vma(mm, addr);
-		if (!vma)
+		if (!vma || addr < vma->vm_start)
 			goto set_status;
 
 		page = follow_page(vma, addr, 0);
diff --git a/mm/mincore.c b/mm/mincore.c
index 9ac42dc6d7b6..a4e6b9d75c76 100644
--- a/mm/mincore.c
+++ b/mm/mincore.c
@@ -154,6 +154,13 @@ static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		if (pmd_trans_huge(*pmd)) {
+			if (mincore_huge_pmd(vma, pmd, addr, next, vec)) {
+				vec += (next - addr) >> PAGE_SHIFT;
+				continue;
+			}
+			/* fall through */
+		}
 		if (pmd_none_or_clear_bad(pmd))
 			mincore_unmapped_range(vma, addr, next, vec);
 		else
diff --git a/mm/mlock.c b/mm/mlock.c
index b70919ce4f72..c3924c7f00be 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -155,13 +155,12 @@ static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long add
  * vma->vm_mm->mmap_sem must be held for at least read.
  */
 static long __mlock_vma_pages_range(struct vm_area_struct *vma,
-				    unsigned long start, unsigned long end)
+				    unsigned long start, unsigned long end,
+				    int *nonblocking)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long addr = start;
-	struct page *pages[16]; /* 16 gives a reasonable batch */
 	int nr_pages = (end - start) / PAGE_SIZE;
-	int ret = 0;
 	int gup_flags;
 
 	VM_BUG_ON(start & ~PAGE_MASK);
@@ -170,73 +169,33 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma,
 	VM_BUG_ON(end   > vma->vm_end);
 	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
 
-	gup_flags = FOLL_TOUCH | FOLL_GET;
-	if (vma->vm_flags & VM_WRITE)
+	gup_flags = FOLL_TOUCH;
+	/*
+	 * We want to touch writable mappings with a write fault in order
+	 * to break COW, except for shared mappings because these don't COW
+	 * and we would not want to dirty them for nothing.
+	 */
+	if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
 		gup_flags |= FOLL_WRITE;
 
+	/*
+	 * We want mlock to succeed for regions that have any permissions
+	 * other than PROT_NONE.
+	 */
+	if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC))
+		gup_flags |= FOLL_FORCE;
+
+	if (vma->vm_flags & VM_LOCKED)
+		gup_flags |= FOLL_MLOCK;
+
 	/* We don't try to access the guard page of a stack vma */
 	if (stack_guard_page(vma, start)) {
 		addr += PAGE_SIZE;
 		nr_pages--;
 	}
 
-	while (nr_pages > 0) {
-		int i;
-
-		cond_resched();
-
-		/*
-		 * get_user_pages makes pages present if we are
-		 * setting mlock. and this extra reference count will
-		 * disable migration of this page.  However, page may
-		 * still be truncated out from under us.
-		 */
-		ret = __get_user_pages(current, mm, addr,
-				min_t(int, nr_pages, ARRAY_SIZE(pages)),
-				gup_flags, pages, NULL);
-		/*
-		 * This can happen for, e.g., VM_NONLINEAR regions before
-		 * a page has been allocated and mapped at a given offset,
-		 * or for addresses that map beyond end of a file.
-		 * We'll mlock the pages if/when they get faulted in.
-		 */
-		if (ret < 0)
-			break;
-
-		lru_add_drain();	/* push cached pages to LRU */
-
-		for (i = 0; i < ret; i++) {
-			struct page *page = pages[i];
-
-			if (page->mapping) {
-				/*
-				 * That preliminary check is mainly to avoid
-				 * the pointless overhead of lock_page on the
-				 * ZERO_PAGE: which might bounce very badly if
-				 * there is contention.  However, we're still
-				 * dirtying its cacheline with get/put_page:
-				 * we'll add another __get_user_pages flag to
-				 * avoid it if that case turns out to matter.
-				 */
-				lock_page(page);
-				/*
-				 * Because we lock page here and migration is
-				 * blocked by the elevated reference, we need
-				 * only check for file-cache page truncation.
-				 */
-				if (page->mapping)
-					mlock_vma_page(page);
-				unlock_page(page);
-			}
-			put_page(page);	/* ref from get_user_pages() */
-		}
-
-		addr += ret * PAGE_SIZE;
-		nr_pages -= ret;
-		ret = 0;
-	}
-
-	return ret;	/* 0 or negative error code */
+	return __get_user_pages(current, mm, addr, nr_pages, gup_flags,
+				NULL, NULL, nonblocking);
 }
 
 /*
@@ -280,7 +239,7 @@ long mlock_vma_pages_range(struct vm_area_struct *vma,
 			is_vm_hugetlb_page(vma) ||
 			vma == get_gate_vma(current))) {
 
-		__mlock_vma_pages_range(vma, start, end);
+		__mlock_vma_pages_range(vma, start, end, NULL);
 
 		/* Hide errors from mmap() and other callers */
 		return 0;
@@ -372,18 +331,10 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	int ret = 0;
 	int lock = newflags & VM_LOCKED;
 
-	if (newflags == vma->vm_flags ||
-			(vma->vm_flags & (VM_IO | VM_PFNMAP)))
+	if (newflags == vma->vm_flags || (vma->vm_flags & VM_SPECIAL) ||
+	    is_vm_hugetlb_page(vma) || vma == get_gate_vma(current))
 		goto out;	/* don't set VM_LOCKED,  don't count */
 
-	if ((vma->vm_flags & (VM_DONTEXPAND | VM_RESERVED)) ||
-			is_vm_hugetlb_page(vma) ||
-			vma == get_gate_vma(current)) {
-		if (lock)
-			make_pages_present(start, end);
-		goto out;	/* don't set VM_LOCKED,  don't count */
-	}
-
 	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
 	*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
 			  vma->vm_file, pgoff, vma_policy(vma));
@@ -419,14 +370,10 @@ success:
 	 * set VM_LOCKED, __mlock_vma_pages_range will bring it back.
 	 */
 
-	if (lock) {
+	if (lock)
 		vma->vm_flags = newflags;
-		ret = __mlock_vma_pages_range(vma, start, end);
-		if (ret < 0)
-			ret = __mlock_posix_error_return(ret);
-	} else {
+	else
 		munlock_vma_pages_range(vma, start, end);
-	}
 
 out:
 	*prev = vma;
@@ -439,7 +386,8 @@ static int do_mlock(unsigned long start, size_t len, int on)
 	struct vm_area_struct * vma, * prev;
 	int error;
 
-	len = PAGE_ALIGN(len);
+	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(len != PAGE_ALIGN(len));
 	end = start + len;
 	if (end < start)
 		return -EINVAL;
@@ -482,6 +430,62 @@ static int do_mlock(unsigned long start, size_t len, int on)
 	return error;
 }
 
+static int do_mlock_pages(unsigned long start, size_t len, int ignore_errors)
+{
+	struct mm_struct *mm = current->mm;
+	unsigned long end, nstart, nend;
+	struct vm_area_struct *vma = NULL;
+	int locked = 0;
+	int ret = 0;
+
+	VM_BUG_ON(start & ~PAGE_MASK);
+	VM_BUG_ON(len != PAGE_ALIGN(len));
+	end = start + len;
+
+	for (nstart = start; nstart < end; nstart = nend) {
+		/*
+		 * We want to fault in pages for [nstart; end) address range.
+		 * Find first corresponding VMA.
+		 */
+		if (!locked) {
+			locked = 1;
+			down_read(&mm->mmap_sem);
+			vma = find_vma(mm, nstart);
+		} else if (nstart >= vma->vm_end)
+			vma = vma->vm_next;
+		if (!vma || vma->vm_start >= end)
+			break;
+		/*
+		 * Set [nstart; nend) to intersection of desired address
+		 * range with the first VMA. Also, skip undesirable VMA types.
+		 */
+		nend = min(end, vma->vm_end);
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
+			continue;
+		if (nstart < vma->vm_start)
+			nstart = vma->vm_start;
+		/*
+		 * Now fault in a range of pages. __mlock_vma_pages_range()
+		 * double checks the vma flags, so that it won't mlock pages
+		 * if the vma was already munlocked.
+		 */
+		ret = __mlock_vma_pages_range(vma, nstart, nend, &locked);
+		if (ret < 0) {
+			if (ignore_errors) {
+				ret = 0;
+				continue;	/* continue at next VMA */
+			}
+			ret = __mlock_posix_error_return(ret);
+			break;
+		}
+		nend = nstart + ret * PAGE_SIZE;
+		ret = 0;
+	}
+	if (locked)
+		up_read(&mm->mmap_sem);
+	return ret;	/* 0 or negative error code */
+}
+
 SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 {
 	unsigned long locked;
@@ -507,6 +511,8 @@ SYSCALL_DEFINE2(mlock, unsigned long, start, size_t, len)
 	if ((locked <= lock_limit) || capable(CAP_IPC_LOCK))
 		error = do_mlock(start, len, 1);
 	up_write(&current->mm->mmap_sem);
+	if (!error)
+		error = do_mlock_pages(start, len, 0);
 	return error;
 }
 
@@ -571,6 +577,10 @@ SYSCALL_DEFINE1(mlockall, int, flags)
 	    capable(CAP_IPC_LOCK))
 		ret = do_mlockall(flags);
 	up_write(&current->mm->mmap_sem);
+	if (!ret && (flags & MCL_CURRENT)) {
+		/* Ignore errors */
+		do_mlock_pages(0, TASK_SIZE, 1);
+	}
 out:
 	return ret;
 }
diff --git a/mm/mmap.c b/mm/mmap.c
index 00161a48a451..2ec8eb5a9cdd 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -28,6 +28,8 @@
 #include <linux/rmap.h>
 #include <linux/mmu_notifier.h>
 #include <linux/perf_event.h>
+#include <linux/audit.h>
+#include <linux/khugepaged.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -252,7 +254,15 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	down_write(&mm->mmap_sem);
 
 #ifdef CONFIG_COMPAT_BRK
-	min_brk = mm->end_code;
+	/*
+	 * CONFIG_COMPAT_BRK can still be overridden by setting
+	 * randomize_va_space to 2, which will still cause mm->start_brk
+	 * to be arbitrarily shifted
+	 */
+	if (mm->start_brk > PAGE_ALIGN(mm->end_data))
+		min_brk = mm->start_brk;
+	else
+		min_brk = mm->end_data;
 #else
 	min_brk = mm->start_brk;
 #endif
@@ -587,6 +597,8 @@ again:			remove_next = 1 + (end > next->vm_end);
 		}
 	}
 
+	vma_adjust_trans_huge(vma, start, end, adjust_next);
+
 	/*
 	 * When changing only vma->vm_end, we don't really need anon_vma
 	 * lock. This is a fairly rare case by itself, but the anon_vma
@@ -814,6 +826,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				end, prev->vm_pgoff, NULL);
 		if (err)
 			return NULL;
+		khugepaged_enter_vma_merge(prev);
 		return prev;
 	}
 
@@ -832,6 +845,7 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
 				next->vm_pgoff - pglen, NULL);
 		if (err)
 			return NULL;
+		khugepaged_enter_vma_merge(area);
 		return area;
 	}
 
@@ -1108,6 +1122,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 	unsigned long retval = -EBADF;
 
 	if (!(flags & MAP_ANONYMOUS)) {
+		audit_mmap_fd(fd, flags);
 		if (unlikely(flags & MAP_HUGETLB))
 			return -EINVAL;
 		file = fget(fd);
@@ -1759,6 +1774,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 		}
 	}
 	vma_unlock_anon_vma(vma);
+	khugepaged_enter_vma_merge(vma);
 	return error;
 }
 #endif /* CONFIG_STACK_GROWSUP || CONFIG_IA64 */
@@ -1806,6 +1822,7 @@ static int expand_downwards(struct vm_area_struct *vma,
 		}
 	}
 	vma_unlock_anon_vma(vma);
+	khugepaged_enter_vma_merge(vma);
 	return error;
 }
 
@@ -2460,6 +2477,7 @@ int install_special_mapping(struct mm_struct *mm,
 			    unsigned long addr, unsigned long len,
 			    unsigned long vm_flags, struct page **pages)
 {
+	int ret;
 	struct vm_area_struct *vma;
 
 	vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
@@ -2477,16 +2495,23 @@ int install_special_mapping(struct mm_struct *mm,
 	vma->vm_ops = &special_mapping_vmops;
 	vma->vm_private_data = pages;
 
-	if (unlikely(insert_vm_struct(mm, vma))) {
-		kmem_cache_free(vm_area_cachep, vma);
-		return -ENOMEM;
-	}
+	ret = security_file_mmap(NULL, 0, 0, 0, vma->vm_start, 1);
+	if (ret)
+		goto out;
+
+	ret = insert_vm_struct(mm, vma);
+	if (ret)
+		goto out;
 
 	mm->total_vm += len >> PAGE_SHIFT;
 
 	perf_event_mmap(vma);
 
 	return 0;
+
+out:
+	kmem_cache_free(vm_area_cachep, vma);
+	return ret;
 }
 
 static DEFINE_MUTEX(mm_all_locks_mutex);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 438951d366f2..8d032de4088e 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -100,6 +100,26 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	return young;
 }
 
+int __mmu_notifier_test_young(struct mm_struct *mm,
+			      unsigned long address)
+{
+	struct mmu_notifier *mn;
+	struct hlist_node *n;
+	int young = 0;
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist) {
+		if (mn->ops->test_young) {
+			young = mn->ops->test_young(mn, mm, address);
+			if (young)
+				break;
+		}
+	}
+	rcu_read_unlock();
+
+	return young;
+}
+
 void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 			       pte_t pte)
 {
diff --git a/mm/mmzone.c b/mm/mmzone.c
index e35bfb82c855..f5b7d1760213 100644
--- a/mm/mmzone.c
+++ b/mm/mmzone.c
@@ -87,24 +87,3 @@ int memmap_valid_within(unsigned long pfn,
 	return 1;
 }
 #endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
-
-#ifdef CONFIG_SMP
-/* Called when a more accurate view of NR_FREE_PAGES is needed */
-unsigned long zone_nr_free_pages(struct zone *zone)
-{
-	unsigned long nr_free_pages = zone_page_state(zone, NR_FREE_PAGES);
-
-	/*
-	 * While kswapd is awake, it is considered the zone is under some
-	 * memory pressure. Under pressure, there is a risk that
-	 * per-cpu-counter-drift will allow the min watermark to be breached
-	 * potentially causing a live-lock. While kswapd is awake and
-	 * free pages are low, get a better estimate for free pages
-	 */
-	if (nr_free_pages < zone->percpu_drift_mark &&
-			!waitqueue_active(&zone->zone_pgdat->kswapd_wait))
-		return zone_page_state_snapshot(zone, NR_FREE_PAGES);
-
-	return nr_free_pages;
-}
-#endif /* CONFIG_SMP */
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 2d1bf7cf8851..5a688a2756be 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -78,7 +78,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd,
 	pte_unmap_unlock(pte - 1, ptl);
 }
 
-static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
+static inline void change_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
@@ -88,13 +88,21 @@ static inline void change_pmd_range(struct mm_struct *mm, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		if (pmd_trans_huge(*pmd)) {
+			if (next - addr != HPAGE_PMD_SIZE)
+				split_huge_page_pmd(vma->vm_mm, pmd);
+			else if (change_huge_pmd(vma, pmd, addr, newprot))
+				continue;
+			/* fall through */
+		}
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
-		change_pte_range(mm, pmd, addr, next, newprot, dirty_accountable);
+		change_pte_range(vma->vm_mm, pmd, addr, next, newprot,
+				 dirty_accountable);
 	} while (pmd++, addr = next, addr != end);
 }
 
-static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd,
+static inline void change_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
 		unsigned long addr, unsigned long end, pgprot_t newprot,
 		int dirty_accountable)
 {
@@ -106,7 +114,8 @@ static inline void change_pud_range(struct mm_struct *mm, pgd_t *pgd,
 		next = pud_addr_end(addr, end);
 		if (pud_none_or_clear_bad(pud))
 			continue;
-		change_pmd_range(mm, pud, addr, next, newprot, dirty_accountable);
+		change_pmd_range(vma, pud, addr, next, newprot,
+				 dirty_accountable);
 	} while (pud++, addr = next, addr != end);
 }
 
@@ -126,7 +135,8 @@ static void change_protection(struct vm_area_struct *vma,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
 			continue;
-		change_pud_range(mm, pgd, addr, next, newprot, dirty_accountable);
+		change_pud_range(vma, pgd, addr, next, newprot,
+				 dirty_accountable);
 	} while (pgd++, addr = next, addr != end);
 	flush_tlb_range(vma, start, end);
 }
@@ -211,6 +221,7 @@ success:
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	vm_stat_account(mm, oldflags, vma->vm_file, -nrpages);
 	vm_stat_account(mm, newflags, vma->vm_file, nrpages);
+	perf_event_mmap(vma);
 	return 0;
 
 fail:
@@ -299,7 +310,6 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
 		error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
 		if (error)
 			goto out;
-		perf_event_mmap(vma);
 		nstart = tmp;
 
 		if (nstart < prev->vm_end)
diff --git a/mm/mremap.c b/mm/mremap.c
index cde56ee51ef7..1de98d492ddc 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -41,13 +41,15 @@ static pmd_t *get_old_pmd(struct mm_struct *mm, unsigned long addr)
 		return NULL;
 
 	pmd = pmd_offset(pud, addr);
+	split_huge_page_pmd(mm, pmd);
 	if (pmd_none_or_clear_bad(pmd))
 		return NULL;
 
 	return pmd;
 }
 
-static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
+static pmd_t *alloc_new_pmd(struct mm_struct *mm, struct vm_area_struct *vma,
+			    unsigned long addr)
 {
 	pgd_t *pgd;
 	pud_t *pud;
@@ -62,7 +64,8 @@ static pmd_t *alloc_new_pmd(struct mm_struct *mm, unsigned long addr)
 	if (!pmd)
 		return NULL;
 
-	if (!pmd_present(*pmd) && __pte_alloc(mm, pmd, addr))
+	VM_BUG_ON(pmd_trans_huge(*pmd));
+	if (pmd_none(*pmd) && __pte_alloc(mm, vma, pmd, addr))
 		return NULL;
 
 	return pmd;
@@ -91,9 +94,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		 */
 		mapping = vma->vm_file->f_mapping;
 		spin_lock(&mapping->i_mmap_lock);
-		if (new_vma->vm_truncate_count &&
-		    new_vma->vm_truncate_count != vma->vm_truncate_count)
-			new_vma->vm_truncate_count = 0;
+		new_vma->vm_truncate_count = 0;
 	}
 
 	/*
@@ -101,7 +102,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	 * pte locks because exclusive mmap_sem prevents deadlock.
 	 */
 	old_pte = pte_offset_map_lock(mm, old_pmd, old_addr, &old_ptl);
- 	new_pte = pte_offset_map_nested(new_pmd, new_addr);
+	new_pte = pte_offset_map(new_pmd, new_addr);
 	new_ptl = pte_lockptr(mm, new_pmd);
 	if (new_ptl != old_ptl)
 		spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
@@ -119,7 +120,7 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	arch_leave_lazy_mmu_mode();
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
-	pte_unmap_nested(new_pte - 1);
+	pte_unmap(new_pte - 1);
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (mapping)
 		spin_unlock(&mapping->i_mmap_lock);
@@ -147,7 +148,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 		old_pmd = get_old_pmd(vma->vm_mm, old_addr);
 		if (!old_pmd)
 			continue;
-		new_pmd = alloc_new_pmd(vma->vm_mm, new_addr);
+		new_pmd = alloc_new_pmd(vma->vm_mm, vma, new_addr);
 		if (!new_pmd)
 			break;
 		next = (new_addr + PMD_SIZE) & PMD_MASK;
diff --git a/mm/nommu.c b/mm/nommu.c
index 88ff091eb07a..f59e1424d3db 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -10,7 +10,7 @@
  *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
  *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
  *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
- *  Copyright (c) 2007-2009 Paul Mundt <lethal@linux-sh.org>
+ *  Copyright (c) 2007-2010 Paul Mundt <lethal@linux-sh.org>
  */
 
 #include <linux/module.h>
@@ -29,6 +29,7 @@
 #include <linux/personality.h>
 #include <linux/security.h>
 #include <linux/syscalls.h>
+#include <linux/audit.h>
 
 #include <asm/uaccess.h>
 #include <asm/tlb.h>
@@ -126,7 +127,8 @@ unsigned int kobjsize(const void *objp)
 
 int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		     unsigned long start, int nr_pages, unsigned int foll_flags,
-		     struct page **pages, struct vm_area_struct **vmas)
+		     struct page **pages, struct vm_area_struct **vmas,
+		     int *retry)
 {
 	struct vm_area_struct *vma;
 	unsigned long vm_flags;
@@ -184,7 +186,8 @@ int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 	if (force)
 		flags |= FOLL_FORCE;
 
-	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
+	return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas,
+				NULL);
 }
 EXPORT_SYMBOL(get_user_pages);
 
@@ -293,12 +296,60 @@ void *vmalloc(unsigned long size)
 }
 EXPORT_SYMBOL(vmalloc);
 
+/*
+ *	vzalloc - allocate virtually continguos memory with zero fill
+ *
+ *	@size:		allocation size
+ *
+ *	Allocate enough pages to cover @size from the page level
+ *	allocator and map them into continguos kernel virtual space.
+ *	The memory allocated is set to zero.
+ *
+ *	For tight control over page level allocator and protection flags
+ *	use __vmalloc() instead.
+ */
+void *vzalloc(unsigned long size)
+{
+	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
+			PAGE_KERNEL);
+}
+EXPORT_SYMBOL(vzalloc);
+
+/**
+ * vmalloc_node - allocate memory on a specific node
+ * @size:	allocation size
+ * @node:	numa node
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc() instead.
+ */
 void *vmalloc_node(unsigned long size, int node)
 {
 	return vmalloc(size);
 }
 EXPORT_SYMBOL(vmalloc_node);
 
+/**
+ * vzalloc_node - allocate memory on a specific node with zero fill
+ * @size:	allocation size
+ * @node:	numa node
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
+ * The memory allocated is set to zero.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc() instead.
+ */
+void *vzalloc_node(unsigned long size, int node)
+{
+	return vzalloc(size);
+}
+EXPORT_SYMBOL(vzalloc_node);
+
 #ifndef PAGE_KERNEL_EXEC
 # define PAGE_KERNEL_EXEC PAGE_KERNEL
 #endif
@@ -392,6 +443,31 @@ void  __attribute__((weak)) vmalloc_sync_all(void)
 {
 }
 
+/**
+ *	alloc_vm_area - allocate a range of kernel address space
+ *	@size:		size of the area
+ *
+ *	Returns:	NULL on failure, vm_struct on success
+ *
+ *	This function reserves a range of kernel address space, and
+ *	allocates pagetables to map that range.  No actual mappings
+ *	are created.  If the kernel address space is not shared
+ *	between processes, it syncs the pagetable across all
+ *	processes.
+ */
+struct vm_struct *alloc_vm_area(size_t size)
+{
+	BUG();
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(alloc_vm_area);
+
+void free_vm_area(struct vm_struct *area)
+{
+	BUG();
+}
+EXPORT_SYMBOL_GPL(free_vm_area);
+
 int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 		   struct page *page)
 {
@@ -1411,6 +1487,7 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 	struct file *file = NULL;
 	unsigned long retval = -EBADF;
 
+	audit_mmap_fd(fd, flags);
 	if (!(flags & MAP_ANONYMOUS)) {
 		file = fget(fd);
 		if (!file)
@@ -1668,6 +1745,7 @@ void exit_mmap(struct mm_struct *mm)
 		mm->mmap = vma->vm_next;
 		delete_vma_from_mm(vma);
 		delete_vma(mm, vma);
+		cond_resched();
 	}
 
 	kleave("");
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 4029583a1024..7dcca55ede7c 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -162,10 +162,11 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem,
 		return 0;
 
 	/*
-	 * Shortcut check for OOM_SCORE_ADJ_MIN so the entire heuristic doesn't
-	 * need to be executed for something that cannot be killed.
+	 * Shortcut check for a thread sharing p->mm that is OOM_SCORE_ADJ_MIN
+	 * so the entire heuristic doesn't need to be executed for something
+	 * that cannot be killed.
 	 */
-	if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) {
+	if (atomic_read(&p->mm->oom_disable_count)) {
 		task_unlock(p);
 		return 0;
 	}
@@ -403,16 +404,40 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 #define K(x) ((x) << (PAGE_SHIFT-10))
 static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem)
 {
+	struct task_struct *q;
+	struct mm_struct *mm;
+
 	p = find_lock_task_mm(p);
 	if (!p)
 		return 1;
 
+	/* mm cannot be safely dereferenced after task_unlock(p) */
+	mm = p->mm;
+
 	pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n",
 		task_pid_nr(p), p->comm, K(p->mm->total_vm),
 		K(get_mm_counter(p->mm, MM_ANONPAGES)),
 		K(get_mm_counter(p->mm, MM_FILEPAGES)));
 	task_unlock(p);
 
+	/*
+	 * Kill all processes sharing p->mm in other thread groups, if any.
+	 * They don't get access to memory reserves or a higher scheduler
+	 * priority, though, to avoid depletion of all memory or task
+	 * starvation.  This prevents mm->mmap_sem livelock when an oom killed
+	 * task cannot exit because it requires the semaphore and its contended
+	 * by another thread trying to allocate memory itself.  That thread will
+	 * now get access to memory reserves since it has a pending fatal
+	 * signal.
+	 */
+	for_each_process(q)
+		if (q->mm == mm && !same_thread_group(q, p)) {
+			task_lock(q);	/* Protect ->comm from prctl() */
+			pr_err("Kill process %d (%s) sharing same memory\n",
+				task_pid_nr(q), q->comm);
+			task_unlock(q);
+			force_sig(SIGKILL, q);
+		}
 
 	set_tsk_thread_flag(p, TIF_MEMDIE);
 	force_sig(SIGKILL, p);
@@ -680,7 +705,7 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 	read_lock(&tasklist_lock);
 	if (sysctl_oom_kill_allocating_task &&
 	    !oom_unkillable_task(current, NULL, nodemask) &&
-	    (current->signal->oom_adj != OOM_DISABLE)) {
+	    current->mm && !atomic_read(&current->mm->oom_disable_count)) {
 		/*
 		 * oom_kill_process() needs tasklist_lock held.  If it returns
 		 * non-zero, current could not be killed so we must fallback to
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index e3bccac1f025..2cb01f6ec5d0 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -404,25 +404,22 @@ unsigned long determine_dirtyable_memory(void)
  * - vm.dirty_background_ratio  or  vm.dirty_background_bytes
  * - vm.dirty_ratio             or  vm.dirty_bytes
  * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
- * runtime tasks.
+ * real-time tasks.
  */
 void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
 {
 	unsigned long background;
 	unsigned long dirty;
-	unsigned long available_memory = determine_dirtyable_memory();
+	unsigned long uninitialized_var(available_memory);
 	struct task_struct *tsk;
 
+	if (!vm_dirty_bytes || !dirty_background_bytes)
+		available_memory = determine_dirtyable_memory();
+
 	if (vm_dirty_bytes)
 		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
-	else {
-		int dirty_ratio;
-
-		dirty_ratio = vm_dirty_ratio;
-		if (dirty_ratio < 5)
-			dirty_ratio = 5;
-		dirty = (dirty_ratio * available_memory) / 100;
-	}
+	else
+		dirty = (vm_dirty_ratio * available_memory) / 100;
 
 	if (dirty_background_bytes)
 		background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
@@ -510,7 +507,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * catch-up. This avoids (excessively) small writeouts
 		 * when the bdi limits are ramping up.
 		 */
-		if (nr_reclaimable + nr_writeback <
+		if (nr_reclaimable + nr_writeback <=
 				(background_thresh + dirty_thresh) / 2)
 			break;
 
@@ -542,8 +539,8 @@ static void balance_dirty_pages(struct address_space *mapping,
 		 * the last resort safeguard.
 		 */
 		dirty_exceeded =
-			(bdi_nr_reclaimable + bdi_nr_writeback >= bdi_thresh)
-			|| (nr_reclaimable + nr_writeback >= dirty_thresh);
+			(bdi_nr_reclaimable + bdi_nr_writeback > bdi_thresh)
+			|| (nr_reclaimable + nr_writeback > dirty_thresh);
 
 		if (!dirty_exceeded)
 			break;
@@ -569,7 +566,7 @@ static void balance_dirty_pages(struct address_space *mapping,
 				break;		/* We've done our duty */
 		}
 		trace_wbc_balance_dirty_wait(&wbc, bdi);
-		__set_current_state(TASK_INTERRUPTIBLE);
+		__set_current_state(TASK_UNINTERRUPTIBLE);
 		io_schedule_timeout(pause);
 
 		/*
@@ -1109,7 +1106,7 @@ EXPORT_SYMBOL(write_one_page);
 int __set_page_dirty_no_writeback(struct page *page)
 {
 	if (!PageDirty(page))
-		SetPageDirty(page);
+		return !TestSetPageDirty(page);
 	return 0;
 }
 
@@ -1121,6 +1118,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 {
 	if (mapping_cap_account_dirty(mapping)) {
 		__inc_zone_page_state(page, NR_FILE_DIRTY);
+		__inc_zone_page_state(page, NR_DIRTIED);
 		__inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE);
 		task_dirty_inc(current);
 		task_io_account_write(PAGE_CACHE_SIZE);
@@ -1129,6 +1127,18 @@ void account_page_dirtied(struct page *page, struct address_space *mapping)
 EXPORT_SYMBOL(account_page_dirtied);
 
 /*
+ * Helper function for set_page_writeback family.
+ * NOTE: Unlike account_page_dirtied this does not rely on being atomic
+ * wrt interrupts.
+ */
+void account_page_writeback(struct page *page)
+{
+	inc_zone_page_state(page, NR_WRITEBACK);
+	inc_zone_page_state(page, NR_WRITTEN);
+}
+EXPORT_SYMBOL(account_page_writeback);
+
+/*
  * For address_spaces which do not use buffers.  Just tag the page as dirty in
  * its radix tree.
  *
@@ -1366,7 +1376,7 @@ int test_set_page_writeback(struct page *page)
 		ret = TestSetPageWriteback(page);
 	}
 	if (!ret)
-		inc_zone_page_state(page, NR_WRITEBACK);
+		account_page_writeback(page);
 	return ret;
 
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f12ad1836abe..a873e61e312e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -21,6 +21,7 @@
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/compiler.h>
 #include <linux/kernel.h>
 #include <linux/kmemcheck.h>
@@ -103,19 +104,24 @@ gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
  * only be modified with pm_mutex held, unless the suspend/hibernate code is
  * guaranteed not to run in parallel with that modification).
  */
-void set_gfp_allowed_mask(gfp_t mask)
+
+static gfp_t saved_gfp_mask;
+
+void pm_restore_gfp_mask(void)
 {
 	WARN_ON(!mutex_is_locked(&pm_mutex));
-	gfp_allowed_mask = mask;
+	if (saved_gfp_mask) {
+		gfp_allowed_mask = saved_gfp_mask;
+		saved_gfp_mask = 0;
+	}
 }
 
-gfp_t clear_gfp_allowed_mask(gfp_t mask)
+void pm_restrict_gfp_mask(void)
 {
-	gfp_t ret = gfp_allowed_mask;
-
 	WARN_ON(!mutex_is_locked(&pm_mutex));
-	gfp_allowed_mask &= ~mask;
-	return ret;
+	WARN_ON(saved_gfp_mask);
+	saved_gfp_mask = gfp_allowed_mask;
+	gfp_allowed_mask &= ~GFP_IOFS;
 }
 #endif /* CONFIG_PM_SLEEP */
 
@@ -351,6 +357,7 @@ void prep_compound_page(struct page *page, unsigned long order)
 	}
 }
 
+/* update __split_huge_page_refcount if you change this function */
 static int destroy_compound_page(struct page *page, unsigned long order)
 {
 	int i;
@@ -420,18 +427,10 @@ static inline void rmv_page_order(struct page *page)
  *
  * Assumption: *_mem_map is contiguous at least up to MAX_ORDER
  */
-static inline struct page *
-__page_find_buddy(struct page *page, unsigned long page_idx, unsigned int order)
-{
-	unsigned long buddy_idx = page_idx ^ (1 << order);
-
-	return page + (buddy_idx - page_idx);
-}
-
 static inline unsigned long
-__find_combined_index(unsigned long page_idx, unsigned int order)
+__find_buddy_index(unsigned long page_idx, unsigned int order)
 {
-	return (page_idx & ~(1 << order));
+	return page_idx ^ (1 << order);
 }
 
 /*
@@ -442,8 +441,8 @@ __find_combined_index(unsigned long page_idx, unsigned int order)
  * (c) a page and its buddy have the same order &&
  * (d) a page and its buddy are in the same zone.
  *
- * For recording whether a page is in the buddy system, we use PG_buddy.
- * Setting, clearing, and testing PG_buddy is serialized by zone->lock.
+ * For recording whether a page is in the buddy system, we set ->_mapcount -2.
+ * Setting, clearing, and testing _mapcount -2 is serialized by zone->lock.
  *
  * For recording page's order, we use page_private(page).
  */
@@ -476,7 +475,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy,
  * as necessary, plus some accounting needed to play nicely with other
  * parts of the VM system.
  * At each level, we keep a list of pages, which are heads of continuous
- * free pages of length of (1 << order) and marked with PG_buddy. Page's
+ * free pages of length of (1 << order) and marked with _mapcount -2. Page's
  * order is recorded in page_private(page) field.
  * So when we are allocating or freeing one, we can derive the state of the
  * other.  That is, if we allocate a small block, and both were   
@@ -493,6 +492,7 @@ static inline void __free_one_page(struct page *page,
 {
 	unsigned long page_idx;
 	unsigned long combined_idx;
+	unsigned long uninitialized_var(buddy_idx);
 	struct page *buddy;
 
 	if (unlikely(PageCompound(page)))
@@ -507,7 +507,8 @@ static inline void __free_one_page(struct page *page,
 	VM_BUG_ON(bad_range(zone, page));
 
 	while (order < MAX_ORDER-1) {
-		buddy = __page_find_buddy(page, page_idx, order);
+		buddy_idx = __find_buddy_index(page_idx, order);
+		buddy = page + (buddy_idx - page_idx);
 		if (!page_is_buddy(page, buddy, order))
 			break;
 
@@ -515,7 +516,7 @@ static inline void __free_one_page(struct page *page,
 		list_del(&buddy->lru);
 		zone->free_area[order].nr_free--;
 		rmv_page_order(buddy);
-		combined_idx = __find_combined_index(page_idx, order);
+		combined_idx = buddy_idx & page_idx;
 		page = page + (combined_idx - page_idx);
 		page_idx = combined_idx;
 		order++;
@@ -530,11 +531,12 @@ static inline void __free_one_page(struct page *page,
 	 * so it's less likely to be used soon and more likely to be merged
 	 * as a higher order page
 	 */
-	if ((order < MAX_ORDER-1) && pfn_valid_within(page_to_pfn(buddy))) {
+	if ((order < MAX_ORDER-2) && pfn_valid_within(page_to_pfn(buddy))) {
 		struct page *higher_page, *higher_buddy;
-		combined_idx = __find_combined_index(page_idx, order);
-		higher_page = page + combined_idx - page_idx;
-		higher_buddy = __page_find_buddy(higher_page, combined_idx, order + 1);
+		combined_idx = buddy_idx & page_idx;
+		higher_page = page + (combined_idx - page_idx);
+		buddy_idx = __find_buddy_index(combined_idx, order + 1);
+		higher_buddy = page + (buddy_idx - combined_idx);
 		if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
 			list_add_tail(&page->lru,
 				&zone->free_area[order].free_list[migratetype]);
@@ -645,13 +647,10 @@ static bool free_pages_prepare(struct page *page, unsigned int order)
 	trace_mm_page_free_direct(page, order);
 	kmemcheck_free_shadow(page, order);
 
-	for (i = 0; i < (1 << order); i++) {
-		struct page *pg = page + i;
-
-		if (PageAnon(pg))
-			pg->mapping = NULL;
-		bad += free_pages_check(pg);
-	}
+	if (PageAnon(page))
+		page->mapping = NULL;
+	for (i = 0; i < (1 << order); i++)
+		bad += free_pages_check(page + i);
 	if (bad)
 		return false;
 
@@ -1089,8 +1088,10 @@ static void drain_pages(unsigned int cpu)
 		pset = per_cpu_ptr(zone->pageset, cpu);
 
 		pcp = &pset->pcp;
-		free_pcppages_bulk(zone, pcp->count, pcp);
-		pcp->count = 0;
+		if (pcp->count) {
+			free_pcppages_bulk(zone, pcp->count, pcp);
+			pcp->count = 0;
+		}
 		local_irq_restore(flags);
 	}
 }
@@ -1454,24 +1455,24 @@ static inline int should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
 /*
- * Return 1 if free pages are above 'mark'. This takes into account the order
+ * Return true if free pages are above 'mark'. This takes into account the order
  * of the allocation.
  */
-int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
-		      int classzone_idx, int alloc_flags)
+static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags, long free_pages)
 {
 	/* free_pages my go negative - that's OK */
 	long min = mark;
-	long free_pages = zone_nr_free_pages(z) - (1 << order) + 1;
 	int o;
 
+	free_pages -= (1 << order) + 1;
 	if (alloc_flags & ALLOC_HIGH)
 		min -= min / 2;
 	if (alloc_flags & ALLOC_HARDER)
 		min -= min / 4;
 
 	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
-		return 0;
+		return false;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
 		free_pages -= z->free_area[o].nr_free << o;
@@ -1480,9 +1481,28 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 		min >>= 1;
 
 		if (free_pages <= min)
-			return 0;
+			return false;
 	}
-	return 1;
+	return true;
+}
+
+bool zone_watermark_ok(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+					zone_page_state(z, NR_FREE_PAGES));
+}
+
+bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
+		      int classzone_idx, int alloc_flags)
+{
+	long free_pages = zone_page_state(z, NR_FREE_PAGES);
+
+	if (z->percpu_drift_mark && free_pages < z->percpu_drift_mark)
+		free_pages = zone_page_state_snapshot(z, NR_FREE_PAGES);
+
+	return __zone_watermark_ok(z, order, mark, classzone_idx, alloc_flags,
+								free_pages);
 }
 
 #ifdef CONFIG_NUMA
@@ -1787,15 +1807,18 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress)
+	int migratetype, unsigned long *did_some_progress,
+	bool sync_migration)
 {
 	struct page *page;
 
 	if (!order || compaction_deferred(preferred_zone))
 		return NULL;
 
+	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
-								nodemask);
+						nodemask, sync_migration);
+	current->flags &= ~PF_MEMALLOC;
 	if (*did_some_progress != COMPACT_SKIPPED) {
 
 		/* Page migration frees to the PCP lists but we want merging */
@@ -1831,7 +1854,8 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress)
+	int migratetype, unsigned long *did_some_progress,
+	bool sync_migration)
 {
 	return NULL;
 }
@@ -1846,23 +1870,22 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 {
 	struct page *page = NULL;
 	struct reclaim_state reclaim_state;
-	struct task_struct *p = current;
 	bool drained = false;
 
 	cond_resched();
 
 	/* We now go into synchronous reclaim */
 	cpuset_memory_pressure_bump();
-	p->flags |= PF_MEMALLOC;
+	current->flags |= PF_MEMALLOC;
 	lockdep_set_current_reclaim_state(gfp_mask);
 	reclaim_state.reclaimed_slab = 0;
-	p->reclaim_state = &reclaim_state;
+	current->reclaim_state = &reclaim_state;
 
 	*did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask);
 
-	p->reclaim_state = NULL;
+	current->reclaim_state = NULL;
 	lockdep_clear_current_reclaim_state();
-	p->flags &= ~PF_MEMALLOC;
+	current->flags &= ~PF_MEMALLOC;
 
 	cond_resched();
 
@@ -1906,7 +1929,7 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 			preferred_zone, migratetype);
 
 		if (!page && gfp_mask & __GFP_NOFAIL)
-			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 	} while (!page && (gfp_mask & __GFP_NOFAIL));
 
 	return page;
@@ -1914,24 +1937,24 @@ __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order,
 
 static inline
 void wake_all_kswapd(unsigned int order, struct zonelist *zonelist,
-						enum zone_type high_zoneidx)
+						enum zone_type high_zoneidx,
+						enum zone_type classzone_idx)
 {
 	struct zoneref *z;
 	struct zone *zone;
 
 	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx)
-		wakeup_kswapd(zone, order);
+		wakeup_kswapd(zone, order, classzone_idx);
 }
 
 static inline int
 gfp_to_alloc_flags(gfp_t gfp_mask)
 {
-	struct task_struct *p = current;
 	int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET;
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
 
 	/* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */
-	BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH);
+	BUILD_BUG_ON(__GFP_HIGH != (__force gfp_t) ALLOC_HIGH);
 
 	/*
 	 * The caller may dip into page reserves a bit more if the caller
@@ -1939,21 +1962,26 @@ gfp_to_alloc_flags(gfp_t gfp_mask)
 	 * policy or is asking for __GFP_HIGH memory.  GFP_ATOMIC requests will
 	 * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH).
 	 */
-	alloc_flags |= (gfp_mask & __GFP_HIGH);
+	alloc_flags |= (__force int) (gfp_mask & __GFP_HIGH);
 
 	if (!wait) {
-		alloc_flags |= ALLOC_HARDER;
+		/*
+		 * Not worth trying to allocate harder for
+		 * __GFP_NOMEMALLOC even if it can't schedule.
+		 */
+		if  (!(gfp_mask & __GFP_NOMEMALLOC))
+			alloc_flags |= ALLOC_HARDER;
 		/*
 		 * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc.
 		 * See also cpuset_zone_allowed() comment in kernel/cpuset.c.
 		 */
 		alloc_flags &= ~ALLOC_CPUSET;
-	} else if (unlikely(rt_task(p)) && !in_interrupt())
+	} else if (unlikely(rt_task(current)) && !in_interrupt())
 		alloc_flags |= ALLOC_HARDER;
 
 	if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) {
 		if (!in_interrupt() &&
-		    ((p->flags & PF_MEMALLOC) ||
+		    ((current->flags & PF_MEMALLOC) ||
 		     unlikely(test_thread_flag(TIF_MEMDIE))))
 			alloc_flags |= ALLOC_NO_WATERMARKS;
 	}
@@ -1972,7 +2000,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	int alloc_flags;
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
-	struct task_struct *p = current;
+	bool sync_migration = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -1997,7 +2025,9 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 		goto nopage;
 
 restart:
-	wake_all_kswapd(order, zonelist, high_zoneidx);
+	if (!(gfp_mask & __GFP_NO_KSWAPD))
+		wake_all_kswapd(order, zonelist, high_zoneidx,
+						zone_idx(preferred_zone));
 
 	/*
 	 * OK, we're below the kswapd watermark and have kicked background
@@ -2006,6 +2036,14 @@ restart:
 	 */
 	alloc_flags = gfp_to_alloc_flags(gfp_mask);
 
+	/*
+	 * Find the true preferred zone if the allocation is unconstrained by
+	 * cpusets.
+	 */
+	if (!(alloc_flags & ALLOC_CPUSET) && !nodemask)
+		first_zones_zonelist(zonelist, high_zoneidx, NULL,
+					&preferred_zone);
+
 	/* This is the last chance, in general, before the goto nopage. */
 	page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
 			high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
@@ -2028,21 +2066,26 @@ rebalance:
 		goto nopage;
 
 	/* Avoid recursion of direct reclaim */
-	if (p->flags & PF_MEMALLOC)
+	if (current->flags & PF_MEMALLOC)
 		goto nopage;
 
 	/* Avoid allocations with no watermarks from looping endlessly */
 	if (test_thread_flag(TIF_MEMDIE) && !(gfp_mask & __GFP_NOFAIL))
 		goto nopage;
 
-	/* Try direct compaction */
+	/*
+	 * Try direct compaction. The first pass is asynchronous. Subsequent
+	 * attempts after direct reclaim are synchronous
+	 */
 	page = __alloc_pages_direct_compact(gfp_mask, order,
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress);
+					migratetype, &did_some_progress,
+					sync_migration);
 	if (page)
 		goto got_pg;
+	sync_migration = true;
 
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
@@ -2094,15 +2137,29 @@ rebalance:
 	pages_reclaimed += did_some_progress;
 	if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) {
 		/* Wait for some write requests to complete then retry */
-		congestion_wait(BLK_RW_ASYNC, HZ/50);
+		wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50);
 		goto rebalance;
+	} else {
+		/*
+		 * High-order allocations do not necessarily loop after
+		 * direct reclaim and reclaim/compaction depends on compaction
+		 * being called after reclaim so call directly if necessary
+		 */
+		page = __alloc_pages_direct_compact(gfp_mask, order,
+					zonelist, high_zoneidx,
+					nodemask,
+					alloc_flags, preferred_zone,
+					migratetype, &did_some_progress,
+					sync_migration);
+		if (page)
+			goto got_pg;
 	}
 
 nopage:
 	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
 		printk(KERN_WARNING "%s: page allocation failure."
 			" order:%d, mode:0x%x\n",
-			p->comm, order, gfp_mask);
+			current->comm, order, gfp_mask);
 		dump_stack();
 		show_mem();
 	}
@@ -2145,7 +2202,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 
 	get_mems_allowed();
 	/* The preferred zone is used for statistics later */
-	first_zones_zonelist(zonelist, high_zoneidx, nodemask, &preferred_zone);
+	first_zones_zonelist(zonelist, high_zoneidx,
+				nodemask ? : &cpuset_current_mems_allowed,
+				&preferred_zone);
 	if (!preferred_zone) {
 		put_mems_allowed();
 		return NULL;
@@ -2436,7 +2495,7 @@ void show_free_areas(void)
 			" all_unreclaimable? %s"
 			"\n",
 			zone->name,
-			K(zone_nr_free_pages(zone)),
+			K(zone_page_state(zone, NR_FREE_PAGES)),
 			K(min_wmark_pages(zone)),
 			K(low_wmark_pages(zone)),
 			K(high_wmark_pages(zone)),
@@ -2579,9 +2638,16 @@ static int __parse_numa_zonelist_order(char *s)
 
 static __init int setup_numa_zonelist_order(char *s)
 {
-	if (s)
-		return __parse_numa_zonelist_order(s);
-	return 0;
+	int ret;
+
+	if (!s)
+		return 0;
+
+	ret = __parse_numa_zonelist_order(s);
+	if (ret == 0)
+		strlcpy(numa_zonelist_order, s, NUMA_ZONELIST_ORDER_LEN);
+
+	return ret;
 }
 early_param("numa_zonelist_order", setup_numa_zonelist_order);
 
@@ -3007,14 +3073,6 @@ static __init_refok int __build_all_zonelists(void *data)
 		build_zonelist_cache(pgdat);
 	}
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-	/* Setup real pagesets for the new zone */
-	if (data) {
-		struct zone *zone = data;
-		setup_zone_pageset(zone);
-	}
-#endif
-
 	/*
 	 * Initialize the boot_pagesets that are going to be used
 	 * for bootstrapping processors. The real pagesets for
@@ -3063,7 +3121,11 @@ void build_all_zonelists(void *data)
 	} else {
 		/* we have to stop all cpus to guarantee there is no user
 		   of zonelist */
-		stop_machine(__build_all_zonelists, data, NULL);
+#ifdef CONFIG_MEMORY_HOTPLUG
+		if (data)
+			setup_zone_pageset((struct zone *)data);
+#endif
+		stop_machine(__build_all_zonelists, NULL, NULL);
 		/* cpuset refresh routine should be here */
 	}
 	vm_total_pages = nr_free_pagecache_pages();
@@ -3636,6 +3698,41 @@ void __init free_bootmem_with_active_regions(int nid,
 	}
 }
 
+#ifdef CONFIG_HAVE_MEMBLOCK
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit)
+{
+	int i;
+
+	/* Need to go over early_node_map to find out good range for node */
+	for_each_active_range_index_in_nid(i, nid) {
+		u64 addr;
+		u64 ei_start, ei_last;
+		u64 final_start, final_end;
+
+		ei_last = early_node_map[i].end_pfn;
+		ei_last <<= PAGE_SHIFT;
+		ei_start = early_node_map[i].start_pfn;
+		ei_start <<= PAGE_SHIFT;
+
+		final_start = max(ei_start, goal);
+		final_end = min(ei_last, limit);
+
+		if (final_start >= final_end)
+			continue;
+
+		addr = memblock_find_in_range(final_start, final_end, size, align);
+
+		if (addr == MEMBLOCK_ERROR)
+			continue;
+
+		return addr;
+	}
+
+	return MEMBLOCK_ERROR;
+}
+#endif
+
 int __init add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid)
 {
@@ -3655,46 +3752,26 @@ int __init add_from_early_node_map(struct range *range, int az,
 void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
 					u64 goal, u64 limit)
 {
-	int i;
 	void *ptr;
+	u64 addr;
 
-	if (limit > get_max_mapped())
-		limit = get_max_mapped();
+	if (limit > memblock.current_limit)
+		limit = memblock.current_limit;
 
-	/* need to go over early_node_map to find out good range for node */
-	for_each_active_range_index_in_nid(i, nid) {
-		u64 addr;
-		u64 ei_start, ei_last;
+	addr = find_memory_core_early(nid, size, align, goal, limit);
 
-		ei_last = early_node_map[i].end_pfn;
-		ei_last <<= PAGE_SHIFT;
-		ei_start = early_node_map[i].start_pfn;
-		ei_start <<= PAGE_SHIFT;
-		addr = find_early_area(ei_start, ei_last,
-					 goal, limit, size, align);
-
-		if (addr == -1ULL)
-			continue;
-
-#if 0
-		printk(KERN_DEBUG "alloc (nid=%d %llx - %llx) (%llx - %llx) %llx %llx => %llx\n",
-				nid,
-				ei_start, ei_last, goal, limit, size,
-				align, addr);
-#endif
-
-		ptr = phys_to_virt(addr);
-		memset(ptr, 0, size);
-		reserve_early_without_check(addr, addr + size, "BOOTMEM");
-		/*
-		 * The min_count is set to 0 so that bootmem allocated blocks
-		 * are never reported as leaks.
-		 */
-		kmemleak_alloc(ptr, size, 0, 0);
-		return ptr;
-	}
+	if (addr == MEMBLOCK_ERROR)
+		return NULL;
 
-	return NULL;
+	ptr = phys_to_virt(addr);
+	memset(ptr, 0, size);
+	memblock_x86_reserve_range(addr, addr + size, "BOOTMEM");
+	/*
+	 * The min_count is set to 0 so that bootmem allocated blocks
+	 * are never reported as leaks.
+	 */
+	kmemleak_alloc(ptr, size, 0, 0);
+	return ptr;
 }
 #endif
 
@@ -3997,7 +4074,7 @@ static void __init setup_usemap(struct pglist_data *pgdat,
 		zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize);
 }
 #else
-static void inline setup_usemap(struct pglist_data *pgdat,
+static inline void setup_usemap(struct pglist_data *pgdat,
 				struct zone *zone, unsigned long zonesize) {}
 #endif /* CONFIG_SPARSEMEM */
 
@@ -5281,12 +5358,65 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
  * page allocater never alloc memory from ISOLATE block.
  */
 
+static int
+__count_immobile_pages(struct zone *zone, struct page *page, int count)
+{
+	unsigned long pfn, iter, found;
+	/*
+	 * For avoiding noise data, lru_add_drain_all() should be called
+	 * If ZONE_MOVABLE, the zone never contains immobile pages
+	 */
+	if (zone_idx(zone) == ZONE_MOVABLE)
+		return true;
+
+	if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE)
+		return true;
+
+	pfn = page_to_pfn(page);
+	for (found = 0, iter = 0; iter < pageblock_nr_pages; iter++) {
+		unsigned long check = pfn + iter;
+
+		if (!pfn_valid_within(check)) {
+			iter++;
+			continue;
+		}
+		page = pfn_to_page(check);
+		if (!page_count(page)) {
+			if (PageBuddy(page))
+				iter += (1 << page_order(page)) - 1;
+			continue;
+		}
+		if (!PageLRU(page))
+			found++;
+		/*
+		 * If there are RECLAIMABLE pages, we need to check it.
+		 * But now, memory offline itself doesn't call shrink_slab()
+		 * and it still to be fixed.
+		 */
+		/*
+		 * If the page is not RAM, page_count()should be 0.
+		 * we don't need more check. This is an _used_ not-movable page.
+		 *
+		 * The problematic thing here is PG_reserved pages. PG_reserved
+		 * is set to both of a memory hole page and a _used_ kernel
+		 * page at boot.
+		 */
+		if (found > count)
+			return false;
+	}
+	return true;
+}
+
+bool is_pageblock_removable_nolock(struct page *page)
+{
+	struct zone *zone = page_zone(page);
+	return __count_immobile_pages(zone, page, 0);
+}
+
 int set_migratetype_isolate(struct page *page)
 {
 	struct zone *zone;
-	struct page *curr_page;
-	unsigned long flags, pfn, iter;
-	unsigned long immobile = 0;
+	unsigned long flags, pfn;
 	struct memory_isolate_notify arg;
 	int notifier_ret;
 	int ret = -EBUSY;
@@ -5296,11 +5426,6 @@ int set_migratetype_isolate(struct page *page)
 	zone_idx = zone_idx(zone);
 
 	spin_lock_irqsave(&zone->lock, flags);
-	if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE ||
-	    zone_idx == ZONE_MOVABLE) {
-		ret = 0;
-		goto out;
-	}
 
 	pfn = page_to_pfn(page);
 	arg.start_pfn = pfn;
@@ -5320,23 +5445,20 @@ int set_migratetype_isolate(struct page *page)
 	 */
 	notifier_ret = memory_isolate_notify(MEM_ISOLATE_COUNT, &arg);
 	notifier_ret = notifier_to_errno(notifier_ret);
-	if (notifier_ret || !arg.pages_found)
+	if (notifier_ret)
 		goto out;
-
-	for (iter = pfn; iter < (pfn + pageblock_nr_pages); iter++) {
-		if (!pfn_valid_within(pfn))
-			continue;
-
-		curr_page = pfn_to_page(iter);
-		if (!page_count(curr_page) || PageLRU(curr_page))
-			continue;
-
-		immobile++;
-	}
-
-	if (arg.pages_found == immobile)
+	/*
+	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
+	 * We just check MOVABLE pages.
+	 */
+	if (__count_immobile_pages(zone, page, arg.pages_found))
 		ret = 0;
 
+	/*
+	 * immobile means "not-on-lru" paes. If immobile is larger than
+	 * removable-by-driver pages reported by notifier, we'll fail.
+	 */
+
 out:
 	if (!ret) {
 		set_pageblock_migratetype(page, MIGRATE_ISOLATE);
@@ -5455,7 +5577,6 @@ static struct trace_print_flags pageflag_names[] = {
 	{1UL << PG_swapcache,		"swapcache"	},
 	{1UL << PG_mappedtodisk,	"mappedtodisk"	},
 	{1UL << PG_reclaim,		"reclaim"	},
-	{1UL << PG_buddy,		"buddy"		},
 	{1UL << PG_swapbacked,		"swapbacked"	},
 	{1UL << PG_unevictable,		"unevictable"	},
 #ifdef CONFIG_MMU
@@ -5503,7 +5624,7 @@ void dump_page(struct page *page)
 {
 	printk(KERN_ALERT
 	       "page:%p count:%d mapcount:%d mapping:%p index:%#lx\n",
-		page, page_count(page), page_mapcount(page),
+		page, atomic_read(&page->_count), page_mapcount(page),
 		page->mapping, page->index);
 	dump_page_flags(page->flags);
 }
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 5e0ffd967452..4ae42bb40892 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -86,7 +86,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
  * all pages in [start_pfn...end_pfn) must be in the same zone.
  * zone->lock must be held before call this.
  *
- * Returns 0 if all pages in the range is isolated.
+ * Returns 1 if all pages in the range is isolated.
  */
 static int
 __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
@@ -119,7 +119,6 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	struct zone *zone;
 	int ret;
 
-	pfn = start_pfn;
 	/*
 	 * Note: pageblock_nr_page != MAX_ORDER. Then, chunks of free page
 	 * is not aligned to pageblock_nr_pages.
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index 8b1a2ce21ee5..7cfa6ae02303 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -34,6 +34,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		split_huge_page_pmd(walk->mm, pmd);
 		if (pmd_none_or_clear_bad(pmd)) {
 			if (walk->pte_hole)
 				err = walk->pte_hole(addr, next, walk);
@@ -139,7 +140,6 @@ int walk_page_range(unsigned long addr, unsigned long end,
 	pgd_t *pgd;
 	unsigned long next;
 	int err = 0;
-	struct vm_area_struct *vma;
 
 	if (addr >= end)
 		return err;
@@ -149,15 +149,17 @@ int walk_page_range(unsigned long addr, unsigned long end,
 
 	pgd = pgd_offset(walk->mm, addr);
 	do {
+		struct vm_area_struct *uninitialized_var(vma);
+
 		next = pgd_addr_end(addr, end);
 
+#ifdef CONFIG_HUGETLB_PAGE
 		/*
 		 * handle hugetlb vma individually because pagetable walk for
 		 * the hugetlb page is dependent on the architecture and
 		 * we can't handled it in the same manner as non-huge pages.
 		 */
 		vma = find_vma(walk->mm, addr);
-#ifdef CONFIG_HUGETLB_PAGE
 		if (vma && is_vm_hugetlb_page(vma)) {
 			if (vma->vm_end < next)
 				next = vma->vm_end;
diff --git a/mm/percpu-km.c b/mm/percpu-km.c
index df680855540a..89633fefc6a2 100644
--- a/mm/percpu-km.c
+++ b/mm/percpu-km.c
@@ -27,7 +27,7 @@
  *   chunk size is not aligned.  percpu-km code will whine about it.
  */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#if defined(CONFIG_SMP) && defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
 #error "contiguous percpu allocation is incompatible with paged first chunk"
 #endif
 
@@ -35,7 +35,11 @@
 
 static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
 {
-	/* noop */
+	unsigned int cpu;
+
+	for_each_possible_cpu(cpu)
+		memset((void *)pcpu_chunk_addr(chunk, cpu, 0) + off, 0, size);
+
 	return 0;
 }
 
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 7d9c1d0ebd3f..ea534960a04b 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -421,7 +421,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void)
 		return NULL;
 
 	vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes,
-				pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL);
+				pcpu_nr_groups, pcpu_atom_size);
 	if (!vms) {
 		pcpu_free_chunk(chunk);
 		return NULL;
diff --git a/mm/percpu.c b/mm/percpu.c
index c76ef3891e0d..3f930018aa60 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -31,7 +31,7 @@
  * as small as 4 bytes.  The allocator organizes chunks into lists
  * according to free size and tries to allocate from the fullest one.
  * Each chunk keeps the maximum contiguous area size hint which is
- * guaranteed to be eqaul to or larger than the maximum contiguous
+ * guaranteed to be equal to or larger than the maximum contiguous
  * area in the chunk.  This helps the allocator not to iterate the
  * chunk maps unnecessarily.
  *
@@ -76,6 +76,7 @@
 #define PCPU_SLOT_BASE_SHIFT		5	/* 1-31 shares the same slot */
 #define PCPU_DFL_MAP_ALLOC		16	/* start a map with 16 ents */
 
+#ifdef CONFIG_SMP
 /* default addr <-> pcpu_ptr mapping, override in asm/percpu.h if necessary */
 #ifndef __addr_to_pcpu_ptr
 #define __addr_to_pcpu_ptr(addr)					\
@@ -89,6 +90,11 @@
 			 (unsigned long)pcpu_base_addr -		\
 			 (unsigned long)__per_cpu_start)
 #endif
+#else	/* CONFIG_SMP */
+/* on UP, it's always identity mapped */
+#define __addr_to_pcpu_ptr(addr)	(void __percpu *)(addr)
+#define __pcpu_ptr_to_addr(ptr)		(void __force *)(ptr)
+#endif	/* CONFIG_SMP */
 
 struct pcpu_chunk {
 	struct list_head	list;		/* linked to pcpu_slot lists */
@@ -252,7 +258,7 @@ static void __maybe_unused pcpu_next_pop(struct pcpu_chunk *chunk,
 
 /*
  * (Un)populated page region iterators.  Iterate over (un)populated
- * page regions betwen @start and @end in @chunk.  @rs and @re should
+ * page regions between @start and @end in @chunk.  @rs and @re should
  * be integer variables and will be set to start and end page index of
  * the current region.
  */
@@ -287,12 +293,8 @@ static void *pcpu_mem_alloc(size_t size)
 
 	if (size <= PAGE_SIZE)
 		return kzalloc(size, GFP_KERNEL);
-	else {
-		void *ptr = vmalloc(size);
-		if (ptr)
-			memset(ptr, 0, size);
-		return ptr;
-	}
+	else
+		return vzalloc(size);
 }
 
 /**
@@ -820,8 +822,8 @@ fail_unlock_mutex:
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align.  Might
- * sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align.
+ * Might sleep.  Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -840,9 +842,10 @@ EXPORT_SYMBOL_GPL(__alloc_percpu);
  * @size: size of area to allocate in bytes
  * @align: alignment of area (max PAGE_SIZE)
  *
- * Allocate percpu area of @size bytes aligned at @align from reserved
- * percpu area if arch has set it up; otherwise, allocation is served
- * from the same dynamic area.  Might sleep.  Might trigger writeouts.
+ * Allocate zero-filled percpu area of @size bytes aligned at @align
+ * from reserved percpu area if arch has set it up; otherwise,
+ * allocation is served from the same dynamic area.  Might sleep.
+ * Might trigger writeouts.
  *
  * CONTEXT:
  * Does GFP_KERNEL allocation.
@@ -949,6 +952,7 @@ EXPORT_SYMBOL_GPL(free_percpu);
  */
 bool is_kernel_percpu_address(unsigned long addr)
 {
+#ifdef CONFIG_SMP
 	const size_t static_size = __per_cpu_end - __per_cpu_start;
 	void __percpu *base = __addr_to_pcpu_ptr(pcpu_base_addr);
 	unsigned int cpu;
@@ -959,6 +963,8 @@ bool is_kernel_percpu_address(unsigned long addr)
 		if ((void *)addr >= start && (void *)addr < start + static_size)
 			return true;
         }
+#endif
+	/* on UP, can't distinguish from other static vars, always false */
 	return false;
 }
 
@@ -1067,161 +1073,6 @@ void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai)
 }
 
 /**
- * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
- * @reserved_size: the size of reserved percpu area in bytes
- * @dyn_size: minimum free size for dynamic allocation in bytes
- * @atom_size: allocation atom size
- * @cpu_distance_fn: callback to determine distance between cpus, optional
- *
- * This function determines grouping of units, their mappings to cpus
- * and other parameters considering needed percpu size, allocation
- * atom size and distances between CPUs.
- *
- * Groups are always mutliples of atom size and CPUs which are of
- * LOCAL_DISTANCE both ways are grouped together and share space for
- * units in the same group.  The returned configuration is guaranteed
- * to have CPUs on different nodes on different groups and >=75% usage
- * of allocated virtual address space.
- *
- * RETURNS:
- * On success, pointer to the new allocation_info is returned.  On
- * failure, ERR_PTR value is returned.
- */
-static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
-				size_t reserved_size, size_t dyn_size,
-				size_t atom_size,
-				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
-{
-	static int group_map[NR_CPUS] __initdata;
-	static int group_cnt[NR_CPUS] __initdata;
-	const size_t static_size = __per_cpu_end - __per_cpu_start;
-	int nr_groups = 1, nr_units = 0;
-	size_t size_sum, min_unit_size, alloc_size;
-	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
-	int last_allocs, group, unit;
-	unsigned int cpu, tcpu;
-	struct pcpu_alloc_info *ai;
-	unsigned int *cpu_map;
-
-	/* this function may be called multiple times */
-	memset(group_map, 0, sizeof(group_map));
-	memset(group_cnt, 0, sizeof(group_cnt));
-
-	/* calculate size_sum and ensure dyn_size is enough for early alloc */
-	size_sum = PFN_ALIGN(static_size + reserved_size +
-			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
-	dyn_size = size_sum - static_size - reserved_size;
-
-	/*
-	 * Determine min_unit_size, alloc_size and max_upa such that
-	 * alloc_size is multiple of atom_size and is the smallest
-	 * which can accomodate 4k aligned segments which are equal to
-	 * or larger than min_unit_size.
-	 */
-	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
-
-	alloc_size = roundup(min_unit_size, atom_size);
-	upa = alloc_size / min_unit_size;
-	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
-		upa--;
-	max_upa = upa;
-
-	/* group cpus according to their proximity */
-	for_each_possible_cpu(cpu) {
-		group = 0;
-	next_group:
-		for_each_possible_cpu(tcpu) {
-			if (cpu == tcpu)
-				break;
-			if (group_map[tcpu] == group && cpu_distance_fn &&
-			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
-			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
-				group++;
-				nr_groups = max(nr_groups, group + 1);
-				goto next_group;
-			}
-		}
-		group_map[cpu] = group;
-		group_cnt[group]++;
-	}
-
-	/*
-	 * Expand unit size until address space usage goes over 75%
-	 * and then as much as possible without using more address
-	 * space.
-	 */
-	last_allocs = INT_MAX;
-	for (upa = max_upa; upa; upa--) {
-		int allocs = 0, wasted = 0;
-
-		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
-			continue;
-
-		for (group = 0; group < nr_groups; group++) {
-			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
-			allocs += this_allocs;
-			wasted += this_allocs * upa - group_cnt[group];
-		}
-
-		/*
-		 * Don't accept if wastage is over 1/3.  The
-		 * greater-than comparison ensures upa==1 always
-		 * passes the following check.
-		 */
-		if (wasted > num_possible_cpus() / 3)
-			continue;
-
-		/* and then don't consume more memory */
-		if (allocs > last_allocs)
-			break;
-		last_allocs = allocs;
-		best_upa = upa;
-	}
-	upa = best_upa;
-
-	/* allocate and fill alloc_info */
-	for (group = 0; group < nr_groups; group++)
-		nr_units += roundup(group_cnt[group], upa);
-
-	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
-	if (!ai)
-		return ERR_PTR(-ENOMEM);
-	cpu_map = ai->groups[0].cpu_map;
-
-	for (group = 0; group < nr_groups; group++) {
-		ai->groups[group].cpu_map = cpu_map;
-		cpu_map += roundup(group_cnt[group], upa);
-	}
-
-	ai->static_size = static_size;
-	ai->reserved_size = reserved_size;
-	ai->dyn_size = dyn_size;
-	ai->unit_size = alloc_size / upa;
-	ai->atom_size = atom_size;
-	ai->alloc_size = alloc_size;
-
-	for (group = 0, unit = 0; group_cnt[group]; group++) {
-		struct pcpu_group_info *gi = &ai->groups[group];
-
-		/*
-		 * Initialize base_offset as if all groups are located
-		 * back-to-back.  The caller should update this to
-		 * reflect actual allocation.
-		 */
-		gi->base_offset = unit * ai->unit_size;
-
-		for_each_possible_cpu(cpu)
-			if (group_map[cpu] == group)
-				gi->cpu_map[gi->nr_units++] = cpu;
-		gi->nr_units = roundup(gi->nr_units, upa);
-		unit += gi->nr_units;
-	}
-	BUG_ON(unit != nr_units);
-
-	return ai;
-}
-
-/**
  * pcpu_dump_alloc_info - print out information about pcpu_alloc_info
  * @lvl: loglevel
  * @ai: allocation info to dump
@@ -1363,7 +1214,9 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* sanity checks */
 	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
+#ifdef CONFIG_SMP
 	PCPU_SETUP_BUG_ON(!ai->static_size);
+#endif
 	PCPU_SETUP_BUG_ON(!base_addr);
 	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
 	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
@@ -1411,7 +1264,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 
 	/* we're done parsing the input, undefine BUG macro and dump config */
 #undef PCPU_SETUP_BUG_ON
-	pcpu_dump_alloc_info(KERN_INFO, ai);
+	pcpu_dump_alloc_info(KERN_DEBUG, ai);
 
 	pcpu_nr_groups = ai->nr_groups;
 	pcpu_group_offsets = group_offsets;
@@ -1488,6 +1341,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
 	return 0;
 }
 
+#ifdef CONFIG_SMP
+
 const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
 	[PCPU_FC_AUTO]	= "auto",
 	[PCPU_FC_EMBED]	= "embed",
@@ -1515,8 +1370,180 @@ static int __init percpu_alloc_setup(char *str)
 }
 early_param("percpu_alloc", percpu_alloc_setup);
 
+/*
+ * pcpu_embed_first_chunk() is used by the generic percpu setup.
+ * Build it if needed by the arch config or the generic setup is going
+ * to be used.
+ */
 #if defined(CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK) || \
 	!defined(CONFIG_HAVE_SETUP_PER_CPU_AREA)
+#define BUILD_EMBED_FIRST_CHUNK
+#endif
+
+/* build pcpu_page_first_chunk() iff needed by the arch config */
+#if defined(CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK)
+#define BUILD_PAGE_FIRST_CHUNK
+#endif
+
+/* pcpu_build_alloc_info() is used by both embed and page first chunk */
+#if defined(BUILD_EMBED_FIRST_CHUNK) || defined(BUILD_PAGE_FIRST_CHUNK)
+/**
+ * pcpu_build_alloc_info - build alloc_info considering distances between CPUs
+ * @reserved_size: the size of reserved percpu area in bytes
+ * @dyn_size: minimum free size for dynamic allocation in bytes
+ * @atom_size: allocation atom size
+ * @cpu_distance_fn: callback to determine distance between cpus, optional
+ *
+ * This function determines grouping of units, their mappings to cpus
+ * and other parameters considering needed percpu size, allocation
+ * atom size and distances between CPUs.
+ *
+ * Groups are always mutliples of atom size and CPUs which are of
+ * LOCAL_DISTANCE both ways are grouped together and share space for
+ * units in the same group.  The returned configuration is guaranteed
+ * to have CPUs on different nodes on different groups and >=75% usage
+ * of allocated virtual address space.
+ *
+ * RETURNS:
+ * On success, pointer to the new allocation_info is returned.  On
+ * failure, ERR_PTR value is returned.
+ */
+static struct pcpu_alloc_info * __init pcpu_build_alloc_info(
+				size_t reserved_size, size_t dyn_size,
+				size_t atom_size,
+				pcpu_fc_cpu_distance_fn_t cpu_distance_fn)
+{
+	static int group_map[NR_CPUS] __initdata;
+	static int group_cnt[NR_CPUS] __initdata;
+	const size_t static_size = __per_cpu_end - __per_cpu_start;
+	int nr_groups = 1, nr_units = 0;
+	size_t size_sum, min_unit_size, alloc_size;
+	int upa, max_upa, uninitialized_var(best_upa);	/* units_per_alloc */
+	int last_allocs, group, unit;
+	unsigned int cpu, tcpu;
+	struct pcpu_alloc_info *ai;
+	unsigned int *cpu_map;
+
+	/* this function may be called multiple times */
+	memset(group_map, 0, sizeof(group_map));
+	memset(group_cnt, 0, sizeof(group_cnt));
+
+	/* calculate size_sum and ensure dyn_size is enough for early alloc */
+	size_sum = PFN_ALIGN(static_size + reserved_size +
+			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
+	dyn_size = size_sum - static_size - reserved_size;
+
+	/*
+	 * Determine min_unit_size, alloc_size and max_upa such that
+	 * alloc_size is multiple of atom_size and is the smallest
+	 * which can accomodate 4k aligned segments which are equal to
+	 * or larger than min_unit_size.
+	 */
+	min_unit_size = max_t(size_t, size_sum, PCPU_MIN_UNIT_SIZE);
+
+	alloc_size = roundup(min_unit_size, atom_size);
+	upa = alloc_size / min_unit_size;
+	while (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+		upa--;
+	max_upa = upa;
+
+	/* group cpus according to their proximity */
+	for_each_possible_cpu(cpu) {
+		group = 0;
+	next_group:
+		for_each_possible_cpu(tcpu) {
+			if (cpu == tcpu)
+				break;
+			if (group_map[tcpu] == group && cpu_distance_fn &&
+			    (cpu_distance_fn(cpu, tcpu) > LOCAL_DISTANCE ||
+			     cpu_distance_fn(tcpu, cpu) > LOCAL_DISTANCE)) {
+				group++;
+				nr_groups = max(nr_groups, group + 1);
+				goto next_group;
+			}
+		}
+		group_map[cpu] = group;
+		group_cnt[group]++;
+	}
+
+	/*
+	 * Expand unit size until address space usage goes over 75%
+	 * and then as much as possible without using more address
+	 * space.
+	 */
+	last_allocs = INT_MAX;
+	for (upa = max_upa; upa; upa--) {
+		int allocs = 0, wasted = 0;
+
+		if (alloc_size % upa || ((alloc_size / upa) & ~PAGE_MASK))
+			continue;
+
+		for (group = 0; group < nr_groups; group++) {
+			int this_allocs = DIV_ROUND_UP(group_cnt[group], upa);
+			allocs += this_allocs;
+			wasted += this_allocs * upa - group_cnt[group];
+		}
+
+		/*
+		 * Don't accept if wastage is over 1/3.  The
+		 * greater-than comparison ensures upa==1 always
+		 * passes the following check.
+		 */
+		if (wasted > num_possible_cpus() / 3)
+			continue;
+
+		/* and then don't consume more memory */
+		if (allocs > last_allocs)
+			break;
+		last_allocs = allocs;
+		best_upa = upa;
+	}
+	upa = best_upa;
+
+	/* allocate and fill alloc_info */
+	for (group = 0; group < nr_groups; group++)
+		nr_units += roundup(group_cnt[group], upa);
+
+	ai = pcpu_alloc_alloc_info(nr_groups, nr_units);
+	if (!ai)
+		return ERR_PTR(-ENOMEM);
+	cpu_map = ai->groups[0].cpu_map;
+
+	for (group = 0; group < nr_groups; group++) {
+		ai->groups[group].cpu_map = cpu_map;
+		cpu_map += roundup(group_cnt[group], upa);
+	}
+
+	ai->static_size = static_size;
+	ai->reserved_size = reserved_size;
+	ai->dyn_size = dyn_size;
+	ai->unit_size = alloc_size / upa;
+	ai->atom_size = atom_size;
+	ai->alloc_size = alloc_size;
+
+	for (group = 0, unit = 0; group_cnt[group]; group++) {
+		struct pcpu_group_info *gi = &ai->groups[group];
+
+		/*
+		 * Initialize base_offset as if all groups are located
+		 * back-to-back.  The caller should update this to
+		 * reflect actual allocation.
+		 */
+		gi->base_offset = unit * ai->unit_size;
+
+		for_each_possible_cpu(cpu)
+			if (group_map[cpu] == group)
+				gi->cpu_map[gi->nr_units++] = cpu;
+		gi->nr_units = roundup(gi->nr_units, upa);
+		unit += gi->nr_units;
+	}
+	BUG_ON(unit != nr_units);
+
+	return ai;
+}
+#endif /* BUILD_EMBED_FIRST_CHUNK || BUILD_PAGE_FIRST_CHUNK */
+
+#if defined(BUILD_EMBED_FIRST_CHUNK)
 /**
  * pcpu_embed_first_chunk - embed the first percpu chunk into bootmem
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1645,10 +1672,9 @@ out_free:
 		free_bootmem(__pa(areas), areas_size);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_EMBED_FIRST_CHUNK ||
-	  !CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif /* BUILD_EMBED_FIRST_CHUNK */
 
-#ifdef CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK
+#ifdef BUILD_PAGE_FIRST_CHUNK
 /**
  * pcpu_page_first_chunk - map the first chunk using PAGE_SIZE pages
  * @reserved_size: the size of reserved percpu area in bytes
@@ -1756,10 +1782,11 @@ out_free_ar:
 	pcpu_free_alloc_info(ai);
 	return rc;
 }
-#endif /* CONFIG_NEED_PER_CPU_PAGE_FIRST_CHUNK */
+#endif /* BUILD_PAGE_FIRST_CHUNK */
 
+#ifndef	CONFIG_HAVE_SETUP_PER_CPU_AREA
 /*
- * Generic percpu area setup.
+ * Generic SMP percpu area setup.
  *
  * The embedding helper is used because its behavior closely resembles
  * the original non-dynamic generic percpu area setup.  This is
@@ -1770,7 +1797,6 @@ out_free_ar:
  * on the physical linear memory mapping which uses large page
  * mappings on applicable archs.
  */
-#ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
 EXPORT_SYMBOL(__per_cpu_offset);
 
@@ -1799,13 +1825,48 @@ void __init setup_per_cpu_areas(void)
 				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE, NULL,
 				    pcpu_dfl_fc_alloc, pcpu_dfl_fc_free);
 	if (rc < 0)
-		panic("Failed to initialized percpu areas.");
+		panic("Failed to initialize percpu areas.");
 
 	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
 	for_each_possible_cpu(cpu)
 		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
 }
-#endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+#endif	/* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+
+#else	/* CONFIG_SMP */
+
+/*
+ * UP percpu area setup.
+ *
+ * UP always uses km-based percpu allocator with identity mapping.
+ * Static percpu variables are indistinguishable from the usual static
+ * variables and don't require any special preparation.
+ */
+void __init setup_per_cpu_areas(void)
+{
+	const size_t unit_size =
+		roundup_pow_of_two(max_t(size_t, PCPU_MIN_UNIT_SIZE,
+					 PERCPU_DYNAMIC_RESERVE));
+	struct pcpu_alloc_info *ai;
+	void *fc;
+
+	ai = pcpu_alloc_alloc_info(1, 1);
+	fc = __alloc_bootmem(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
+	if (!ai || !fc)
+		panic("Failed to allocate memory for percpu areas.");
+
+	ai->dyn_size = unit_size;
+	ai->unit_size = unit_size;
+	ai->atom_size = unit_size;
+	ai->alloc_size = unit_size;
+	ai->groups[0].nr_units = 1;
+	ai->groups[0].cpu_map[0] = 0;
+
+	if (pcpu_setup_first_chunk(ai, fc) < 0)
+		panic("Failed to initialize percpu areas.");
+}
+
+#endif	/* CONFIG_SMP */
 
 /*
  * First and reserved chunks are initialized with temporary allocation
diff --git a/mm/percpu_up.c b/mm/percpu_up.c
deleted file mode 100644
index db884fae5721..000000000000
--- a/mm/percpu_up.c
+++ /dev/null
@@ -1,30 +0,0 @@
-/*
- * mm/percpu_up.c - dummy percpu memory allocator implementation for UP
- */
-
-#include <linux/module.h>
-#include <linux/percpu.h>
-#include <linux/slab.h>
-
-void __percpu *__alloc_percpu(size_t size, size_t align)
-{
-	/*
-	 * Can't easily make larger alignment work with kmalloc.  WARN
-	 * on it.  Larger alignment should only be used for module
-	 * percpu sections on SMP for which this path isn't used.
-	 */
-	WARN_ON_ONCE(align > SMP_CACHE_BYTES);
-	return (void __percpu __force *)kzalloc(size, GFP_KERNEL);
-}
-EXPORT_SYMBOL_GPL(__alloc_percpu);
-
-void free_percpu(void __percpu *p)
-{
-	kfree(this_cpu_ptr(p));
-}
-EXPORT_SYMBOL_GPL(free_percpu);
-
-phys_addr_t per_cpu_ptr_to_phys(void *addr)
-{
-	return __pa(addr);
-}
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
new file mode 100644
index 000000000000..eb663fb533e0
--- /dev/null
+++ b/mm/pgtable-generic.c
@@ -0,0 +1,121 @@
+/*
+ *  mm/pgtable-generic.c
+ *
+ *  Generic pgtable methods declared in asm-generic/pgtable.h
+ *
+ *  Copyright (C) 2010  Linus Torvalds
+ */
+
+#include <linux/pagemap.h>
+#include <asm/tlb.h>
+#include <asm-generic/pgtable.h>
+
+#ifndef __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS
+/*
+ * Only sets the access flags (dirty, accessed, and
+ * writable). Furthermore, we know it always gets set to a "more
+ * permissive" setting, which allows most architectures to optimize
+ * this. We return whether the PTE actually changed, which in turn
+ * instructs the caller to do things like update__mmu_cache.  This
+ * used to be done in the caller, but sparc needs minor faults to
+ * force that call on sun4c so we changed this macro slightly
+ */
+int ptep_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pte_t *ptep,
+			  pte_t entry, int dirty)
+{
+	int changed = !pte_same(*ptep, entry);
+	if (changed) {
+		set_pte_at(vma->vm_mm, address, ptep, entry);
+		flush_tlb_page(vma, address);
+	}
+	return changed;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
+int pmdp_set_access_flags(struct vm_area_struct *vma,
+			  unsigned long address, pmd_t *pmdp,
+			  pmd_t entry, int dirty)
+{
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	int changed = !pmd_same(*pmdp, entry);
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	if (changed) {
+		set_pmd_at(vma->vm_mm, address, pmdp, entry);
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	}
+	return changed;
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+	BUG();
+	return 0;
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH
+int ptep_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pte_t *ptep)
+{
+	int young;
+	young = ptep_test_and_clear_young(vma, address, ptep);
+	if (young)
+		flush_tlb_page(vma, address);
+	return young;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_CLEAR_YOUNG_FLUSH
+int pmdp_clear_flush_young(struct vm_area_struct *vma,
+			   unsigned long address, pmd_t *pmdp)
+{
+	int young;
+#ifndef CONFIG_TRANSPARENT_HUGEPAGE
+	BUG();
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	young = pmdp_test_and_clear_young(vma, address, pmdp);
+	if (young)
+		flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	return young;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PTEP_CLEAR_FLUSH
+pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
+		       pte_t *ptep)
+{
+	pte_t pte;
+	pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
+	flush_tlb_page(vma, address);
+	return pte;
+}
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_CLEAR_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t pmdp_clear_flush(struct vm_area_struct *vma, unsigned long address,
+		       pmd_t *pmdp)
+{
+	pmd_t pmd;
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	pmd = pmdp_get_and_clear(vma->vm_mm, address, pmdp);
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+	return pmd;
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
+
+#ifndef __HAVE_ARCH_PMDP_SPLITTING_FLUSH
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+pmd_t pmdp_splitting_flush(struct vm_area_struct *vma, unsigned long address,
+			   pmd_t *pmdp)
+{
+	pmd_t pmd = pmd_mksplitting(*pmdp);
+	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
+	set_pmd_at(vma->vm_mm, address, pmdp, pmd);
+	/* tlb flush only to serialize against gup-fast */
+	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif
diff --git a/mm/rmap.c b/mm/rmap.c
index 92e6757f196e..f21f4a1d6a1c 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -80,7 +80,7 @@ static inline struct anon_vma_chain *anon_vma_chain_alloc(void)
 	return kmem_cache_alloc(anon_vma_chain_cachep, GFP_KERNEL);
 }
 
-void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
+static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
 {
 	kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain);
 }
@@ -94,7 +94,7 @@ void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain)
  * anonymous pages mapped into it with that anon_vma.
  *
  * The common case will be that we already have one, but if
- * if not we either need to find an adjacent mapping that we
+ * not we either need to find an adjacent mapping that we
  * can re-use the anon_vma from (very common when the only
  * reason for splitting a vma has been mprotect()), or we
  * allocate a new one.
@@ -177,6 +177,10 @@ static void anon_vma_chain_link(struct vm_area_struct *vma,
 	list_add(&avc->same_vma, &vma->anon_vma_chain);
 
 	anon_vma_lock(anon_vma);
+	/*
+	 * It's critical to add new vmas to the tail of the anon_vma,
+	 * see comment in huge_memory.c:__split_huge_page().
+	 */
 	list_add_tail(&avc->same_anon_vma, &anon_vma->head);
 	anon_vma_unlock(anon_vma);
 }
@@ -314,7 +318,7 @@ void __init anon_vma_init(void)
  * Getting a lock on a stable anon_vma from a page off the LRU is
  * tricky: page_lock_anon_vma rely on RCU to guard against the races.
  */
-struct anon_vma *page_lock_anon_vma(struct page *page)
+struct anon_vma *__page_lock_anon_vma(struct page *page)
 {
 	struct anon_vma *anon_vma, *root_anon_vma;
 	unsigned long anon_mapping;
@@ -348,6 +352,8 @@ out:
 }
 
 void page_unlock_anon_vma(struct anon_vma *anon_vma)
+	__releases(&anon_vma->root->lock)
+	__releases(RCU)
 {
 	anon_vma_unlock(anon_vma);
 	rcu_read_unlock();
@@ -358,7 +364,7 @@ void page_unlock_anon_vma(struct anon_vma *anon_vma)
  * Returns virtual address or -EFAULT if page's index/offset is not
  * within the range mapped the @vma.
  */
-static inline unsigned long
+inline unsigned long
 vma_address(struct page *page, struct vm_area_struct *vma)
 {
 	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
@@ -407,7 +413,7 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
  *
  * On success returns with pte mapped and locked.
  */
-pte_t *page_check_address(struct page *page, struct mm_struct *mm,
+pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 			  unsigned long address, spinlock_t **ptlp, int sync)
 {
 	pgd_t *pgd;
@@ -433,6 +439,8 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
 	pmd = pmd_offset(pud, address);
 	if (!pmd_present(*pmd))
 		return NULL;
+	if (pmd_trans_huge(*pmd))
+		return NULL;
 
 	pte = pte_offset_map(pmd, address);
 	/* Make a quick check before getting the lock */
@@ -487,35 +495,17 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			unsigned long *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	pte_t *pte;
-	spinlock_t *ptl;
 	int referenced = 0;
 
-	pte = page_check_address(page, mm, address, &ptl, 0);
-	if (!pte)
-		goto out;
-
 	/*
 	 * Don't want to elevate referenced for mlocked page that gets this far,
 	 * in order that it progresses to try_to_unmap and is moved to the
 	 * unevictable list.
 	 */
 	if (vma->vm_flags & VM_LOCKED) {
-		*mapcount = 1;	/* break early from loop */
+		*mapcount = 0;	/* break early from loop */
 		*vm_flags |= VM_LOCKED;
-		goto out_unmap;
-	}
-
-	if (ptep_clear_flush_young_notify(vma, address, pte)) {
-		/*
-		 * Don't treat a reference through a sequentially read
-		 * mapping as such.  If the page has been used in
-		 * another mapping, we will catch it; if this other
-		 * mapping is already gone, the unmap path will have
-		 * set PG_referenced or activated the page.
-		 */
-		if (likely(!VM_SequentialReadHint(vma)))
-			referenced++;
+		goto out;
 	}
 
 	/* Pretend the page is referenced if the task has the
@@ -524,9 +514,39 @@ int page_referenced_one(struct page *page, struct vm_area_struct *vma,
 			rwsem_is_locked(&mm->mmap_sem))
 		referenced++;
 
-out_unmap:
+	if (unlikely(PageTransHuge(page))) {
+		pmd_t *pmd;
+
+		spin_lock(&mm->page_table_lock);
+		pmd = page_check_address_pmd(page, mm, address,
+					     PAGE_CHECK_ADDRESS_PMD_FLAG);
+		if (pmd && !pmd_trans_splitting(*pmd) &&
+		    pmdp_clear_flush_young_notify(vma, address, pmd))
+			referenced++;
+		spin_unlock(&mm->page_table_lock);
+	} else {
+		pte_t *pte;
+		spinlock_t *ptl;
+
+		pte = page_check_address(page, mm, address, &ptl, 0);
+		if (!pte)
+			goto out;
+
+		if (ptep_clear_flush_young_notify(vma, address, pte)) {
+			/*
+			 * Don't treat a reference through a sequentially read
+			 * mapping as such.  If the page has been used in
+			 * another mapping, we will catch it; if this other
+			 * mapping is already gone, the unmap path will have
+			 * set PG_referenced or activated the page.
+			 */
+			if (likely(!VM_SequentialReadHint(vma)))
+				referenced++;
+		}
+		pte_unmap_unlock(pte, ptl);
+	}
+
 	(*mapcount)--;
-	pte_unmap_unlock(pte, ptl);
 
 	if (referenced)
 		*vm_flags |= vma->vm_flags;
@@ -745,7 +765,7 @@ int page_mkclean(struct page *page)
 		if (mapping) {
 			ret = page_mkclean_file(mapping, page);
 			if (page_test_dirty(page)) {
-				page_clear_dirty(page);
+				page_clear_dirty(page, 1);
 				ret = 1;
 			}
 		}
@@ -780,10 +800,10 @@ void page_move_anon_rmap(struct page *page,
 }
 
 /**
- * __page_set_anon_rmap - setup new anonymous rmap
- * @page:	the page to add the mapping to
- * @vma:	the vm area in which the mapping is added
- * @address:	the user virtual address mapped
+ * __page_set_anon_rmap - set up new anonymous rmap
+ * @page:	Page to add to rmap	
+ * @vma:	VM area to add page to.
+ * @address:	User virtual address of the mapping	
  * @exclusive:	the page is exclusively owned by the current process
  */
 static void __page_set_anon_rmap(struct page *page,
@@ -793,25 +813,16 @@ static void __page_set_anon_rmap(struct page *page,
 
 	BUG_ON(!anon_vma);
 
+	if (PageAnon(page))
+		return;
+
 	/*
 	 * If the page isn't exclusively mapped into this vma,
 	 * we must use the _oldest_ possible anon_vma for the
 	 * page mapping!
 	 */
-	if (!exclusive) {
-		if (PageAnon(page))
-			return;
+	if (!exclusive)
 		anon_vma = anon_vma->root;
-	} else {
-		/*
-		 * In this case, swapped-out-but-not-discarded swap-cache
-		 * is remapped. So, no need to update page->mapping here.
-		 * We convice anon_vma poitned by page->mapping is not obsolete
-		 * because vma->anon_vma is necessary to be a family of it.
-		 */
-		if (PageAnon(page))
-			return;
-	}
 
 	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
 	page->mapping = (struct address_space *) anon_vma;
@@ -871,8 +882,13 @@ void do_page_add_anon_rmap(struct page *page,
 	struct vm_area_struct *vma, unsigned long address, int exclusive)
 {
 	int first = atomic_inc_and_test(&page->_mapcount);
-	if (first)
-		__inc_zone_page_state(page, NR_ANON_PAGES);
+	if (first) {
+		if (!PageTransHuge(page))
+			__inc_zone_page_state(page, NR_ANON_PAGES);
+		else
+			__inc_zone_page_state(page,
+					      NR_ANON_TRANSPARENT_HUGEPAGES);
+	}
 	if (unlikely(PageKsm(page)))
 		return;
 
@@ -900,7 +916,10 @@ void page_add_new_anon_rmap(struct page *page,
 	VM_BUG_ON(address < vma->vm_start || address >= vma->vm_end);
 	SetPageSwapBacked(page);
 	atomic_set(&page->_mapcount, 0); /* increment count (starts at -1) */
-	__inc_zone_page_state(page, NR_ANON_PAGES);
+	if (!PageTransHuge(page))
+		__inc_zone_page_state(page, NR_ANON_PAGES);
+	else
+		__inc_zone_page_state(page, NR_ANON_TRANSPARENT_HUGEPAGES);
 	__page_set_anon_rmap(page, vma, address, 1);
 	if (page_evictable(page, vma))
 		lru_cache_add_lru(page, LRU_ACTIVE_ANON);
@@ -918,7 +937,7 @@ void page_add_file_rmap(struct page *page)
 {
 	if (atomic_inc_and_test(&page->_mapcount)) {
 		__inc_zone_page_state(page, NR_FILE_MAPPED);
-		mem_cgroup_update_file_mapped(page, 1);
+		mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED);
 	}
 }
 
@@ -942,7 +961,7 @@ void page_remove_rmap(struct page *page)
 	 * containing the swap entry, but page not yet written to swap.
 	 */
 	if ((!PageAnon(page) || PageSwapCache(page)) && page_test_dirty(page)) {
-		page_clear_dirty(page);
+		page_clear_dirty(page, 1);
 		set_page_dirty(page);
 	}
 	/*
@@ -953,10 +972,14 @@ void page_remove_rmap(struct page *page)
 		return;
 	if (PageAnon(page)) {
 		mem_cgroup_uncharge_page(page);
-		__dec_zone_page_state(page, NR_ANON_PAGES);
+		if (!PageTransHuge(page))
+			__dec_zone_page_state(page, NR_ANON_PAGES);
+		else
+			__dec_zone_page_state(page,
+					      NR_ANON_TRANSPARENT_HUGEPAGES);
 	} else {
 		__dec_zone_page_state(page, NR_FILE_MAPPED);
-		mem_cgroup_update_file_mapped(page, -1);
+		mem_cgroup_dec_page_stat(page, MEMCG_NR_FILE_MAPPED);
 	}
 	/*
 	 * It would be tidy to reset the PageAnon mapping here,
@@ -1209,7 +1232,7 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 	return ret;
 }
 
-static bool is_vma_temporary_stack(struct vm_area_struct *vma)
+bool is_vma_temporary_stack(struct vm_area_struct *vma)
 {
 	int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
 
@@ -1407,6 +1430,7 @@ int try_to_unmap(struct page *page, enum ttu_flags flags)
 	int ret;
 
 	BUG_ON(!PageLocked(page));
+	VM_BUG_ON(!PageHuge(page) && PageTransHuge(page));
 
 	if (unlikely(PageKsm(page)))
 		ret = try_to_unmap_ksm(page, flags);
diff --git a/mm/shmem.c b/mm/shmem.c
index 080b09a57a8f..5ee67c990602 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1586,6 +1586,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
 
 	inode = new_inode(sb);
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		inode->i_blocks = 0;
 		inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
@@ -1903,7 +1904,7 @@ static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentr
 	dir->i_size += BOGO_DIRENT_SIZE;
 	inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
 	inc_nlink(inode);
-	atomic_inc(&inode->i_count);	/* New dentry reference */
+	ihold(inode);	/* New dentry reference */
 	dget(dentry);		/* Extra pinning count for the created dentry */
 	d_instantiate(dentry, inode);
 out:
@@ -2146,7 +2147,7 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
 	if (*len < 3)
 		return 255;
 
-	if (hlist_unhashed(&inode->i_hash)) {
+	if (inode_unhashed(inode)) {
 		/* Unfortunately insert_inode_hash is not idempotent,
 		 * so as we hash inodes here rather than at creation
 		 * time, we need a lock to ensure we only try
@@ -2154,7 +2155,7 @@ static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
 		 */
 		static DEFINE_SPINLOCK(lock);
 		spin_lock(&lock);
-		if (hlist_unhashed(&inode->i_hash))
+		if (inode_unhashed(inode))
 			__insert_inode_hash(inode,
 					    inode->i_ino + inode->i_generation);
 		spin_unlock(&lock);
@@ -2414,13 +2415,20 @@ static struct inode *shmem_alloc_inode(struct super_block *sb)
 	return &p->vfs_inode;
 }
 
+static void shmem_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	INIT_LIST_HEAD(&inode->i_dentry);
+	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
+}
+
 static void shmem_destroy_inode(struct inode *inode)
 {
 	if ((inode->i_mode & S_IFMT) == S_IFREG) {
 		/* only struct inode is valid if it's an inline symlink */
 		mpol_free_shared_policy(&SHMEM_I(inode)->policy);
 	}
-	kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
+	call_rcu(&inode->i_rcu, shmem_i_callback);
 }
 
 static void init_once(void *foo)
@@ -2537,16 +2545,16 @@ static const struct vm_operations_struct shmem_vm_ops = {
 };
 
 
-static int shmem_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *shmem_mount(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *data)
 {
-	return get_sb_nodev(fs_type, flags, data, shmem_fill_super, mnt);
+	return mount_nodev(fs_type, flags, data, shmem_fill_super);
 }
 
 static struct file_system_type tmpfs_fs_type = {
 	.owner		= THIS_MODULE,
 	.name		= "tmpfs",
-	.get_sb		= shmem_get_sb,
+	.mount		= shmem_mount,
 	.kill_sb	= kill_litter_super,
 };
 
@@ -2642,7 +2650,7 @@ out:
 
 static struct file_system_type tmpfs_fs_type = {
 	.name		= "tmpfs",
-	.get_sb		= ramfs_get_sb,
+	.mount		= ramfs_mount,
 	.kill_sb	= kill_litter_super,
 };
 
diff --git a/mm/slab.c b/mm/slab.c
index fcae9815d3b3..37961d1f584f 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -284,7 +284,7 @@ struct kmem_list3 {
  * Need this for bootstrapping a per node allocator.
  */
 #define NUM_INIT_LISTS (3 * MAX_NUMNODES)
-struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
+static struct kmem_list3 __initdata initkmem_list3[NUM_INIT_LISTS];
 #define	CACHE_CACHE 0
 #define	SIZE_AC MAX_NUMNODES
 #define	SIZE_L3 (2 * MAX_NUMNODES)
@@ -829,12 +829,12 @@ static void init_reap_node(int cpu)
 
 static void next_reap_node(void)
 {
-	int node = __get_cpu_var(slab_reap_node);
+	int node = __this_cpu_read(slab_reap_node);
 
 	node = next_node(node, node_online_map);
 	if (unlikely(node >= MAX_NUMNODES))
 		node = first_node(node_online_map);
-	__get_cpu_var(slab_reap_node) = node;
+	__this_cpu_write(slab_reap_node, node);
 }
 
 #else
@@ -901,7 +901,7 @@ static int transfer_objects(struct array_cache *to,
 		struct array_cache *from, unsigned int max)
 {
 	/* Figure out how many entries to transfer */
-	int nr = min(min(from->avail, max), to->limit - to->avail);
+	int nr = min3(from->avail, max, to->limit - to->avail);
 
 	if (!nr)
 		return 0;
@@ -1012,7 +1012,7 @@ static void __drain_alien_cache(struct kmem_cache *cachep,
  */
 static void reap_alien(struct kmem_cache *cachep, struct kmem_list3 *l3)
 {
-	int node = __get_cpu_var(slab_reap_node);
+	int node = __this_cpu_read(slab_reap_node);
 
 	if (l3->alien) {
 		struct array_cache *ac = l3->alien[node];
@@ -1293,7 +1293,7 @@ static int __cpuinit cpuup_callback(struct notifier_block *nfb,
 		 * anything expensive but will only modify reap_work
 		 * and reschedule the timer.
 		*/
-		cancel_rearming_delayed_work(&per_cpu(slab_reap_work, cpu));
+		cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
 		/* Now the cache_reaper is guaranteed to be not running. */
 		per_cpu(slab_reap_work, cpu).work.func = NULL;
   		break;
@@ -2781,7 +2781,7 @@ static void slab_put_obj(struct kmem_cache *cachep, struct slab *slabp,
 /*
  * Map pages beginning at addr to the given cache and slab. This is required
  * for the slab allocator to be able to lookup the cache and slab of a
- * virtual address for kfree, ksize, kmem_ptr_validate, and slab debugging.
+ * virtual address for kfree, ksize, and slab debugging.
  */
 static void slab_map_pages(struct kmem_cache *cache, struct slab *slab,
 			   void *addr)
@@ -3653,42 +3653,19 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
 EXPORT_SYMBOL(kmem_cache_alloc);
 
 #ifdef CONFIG_TRACING
-void *kmem_cache_alloc_notrace(struct kmem_cache *cachep, gfp_t flags)
+void *
+kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags)
 {
-	return __cache_alloc(cachep, flags, __builtin_return_address(0));
-}
-EXPORT_SYMBOL(kmem_cache_alloc_notrace);
-#endif
+	void *ret;
 
-/**
- * kmem_ptr_validate - check if an untrusted pointer might be a slab entry.
- * @cachep: the cache we're checking against
- * @ptr: pointer to validate
- *
- * This verifies that the untrusted pointer looks sane;
- * it is _not_ a guarantee that the pointer is actually
- * part of the slab cache in question, but it at least
- * validates that the pointer can be dereferenced and
- * looks half-way sane.
- *
- * Currently only used for dentry validation.
- */
-int kmem_ptr_validate(struct kmem_cache *cachep, const void *ptr)
-{
-	unsigned long size = cachep->buffer_size;
-	struct page *page;
+	ret = __cache_alloc(cachep, flags, __builtin_return_address(0));
 
-	if (unlikely(!kern_ptr_validate(ptr, size)))
-		goto out;
-	page = virt_to_page(ptr);
-	if (unlikely(!PageSlab(page)))
-		goto out;
-	if (unlikely(page_get_cache(page) != cachep))
-		goto out;
-	return 1;
-out:
-	return 0;
+	trace_kmalloc(_RET_IP_, ret,
+		      size, slab_buffer_size(cachep), flags);
+	return ret;
 }
+EXPORT_SYMBOL(kmem_cache_alloc_trace);
+#endif
 
 #ifdef CONFIG_NUMA
 void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
@@ -3705,31 +3682,32 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
 EXPORT_SYMBOL(kmem_cache_alloc_node);
 
 #ifdef CONFIG_TRACING
-void *kmem_cache_alloc_node_notrace(struct kmem_cache *cachep,
-				    gfp_t flags,
-				    int nodeid)
+void *kmem_cache_alloc_node_trace(size_t size,
+				  struct kmem_cache *cachep,
+				  gfp_t flags,
+				  int nodeid)
 {
-	return __cache_alloc_node(cachep, flags, nodeid,
+	void *ret;
+
+	ret = __cache_alloc_node(cachep, flags, nodeid,
 				  __builtin_return_address(0));
+	trace_kmalloc_node(_RET_IP_, ret,
+			   size, slab_buffer_size(cachep),
+			   flags, nodeid);
+	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
 #endif
 
 static __always_inline void *
 __do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
 {
 	struct kmem_cache *cachep;
-	void *ret;
 
 	cachep = kmem_find_general_cachep(size, flags);
 	if (unlikely(ZERO_OR_NULL_PTR(cachep)))
 		return cachep;
-	ret = kmem_cache_alloc_node_notrace(cachep, flags, node);
-
-	trace_kmalloc_node((unsigned long) caller, ret,
-			   size, cachep->buffer_size, flags, node);
-
-	return ret;
+	return kmem_cache_alloc_node_trace(size, cachep, flags, node);
 }
 
 #if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
@@ -4075,7 +4053,7 @@ static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp)
  * necessary. Note that the l3 listlock also protects the array_cache
  * if drain_array() is used on the shared array.
  */
-void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
+static void drain_array(struct kmem_cache *cachep, struct kmem_list3 *l3,
 			 struct array_cache *ac, int force, int node)
 {
 	int tofree;
@@ -4339,7 +4317,7 @@ static const struct seq_operations slabinfo_op = {
  * @count: data length
  * @ppos: unused
  */
-ssize_t slabinfo_write(struct file *file, const char __user * buffer,
+static ssize_t slabinfo_write(struct file *file, const char __user *buffer,
 		       size_t count, loff_t *ppos)
 {
 	char kbuf[MAX_SLABINFO_WRITE + 1], *tmp;
diff --git a/mm/slob.c b/mm/slob.c
index d582171c8101..3588eaaef726 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -500,7 +500,9 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
 	} else {
 		unsigned int order = get_order(size);
 
-		ret = slob_new_pages(gfp | __GFP_COMP, get_order(size), node);
+		if (likely(order))
+			gfp |= __GFP_COMP;
+		ret = slob_new_pages(gfp, order, node);
 		if (ret) {
 			struct page *page;
 			page = virt_to_page(ret);
@@ -676,11 +678,6 @@ int kmem_cache_shrink(struct kmem_cache *d)
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
-int kmem_ptr_validate(struct kmem_cache *a, const void *b)
-{
-	return 0;
-}
-
 static unsigned int slob_ready __read_mostly;
 
 int slab_is_available(void)
diff --git a/mm/slub.c b/mm/slub.c
index 13fffe1f0f3d..e15aa7f193c9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -28,6 +28,8 @@
 #include <linux/math64.h>
 #include <linux/fault-inject.h>
 
+#include <trace/events/kmem.h>
+
 /*
  * Lock order:
  *   1. slab_lock(page)
@@ -168,7 +170,6 @@ static inline int kmem_cache_debug(struct kmem_cache *s)
 
 /* Internal SLUB flags */
 #define __OBJECT_POISON		0x80000000UL /* Poison object */
-#define __SYSFS_ADD_DEFERRED	0x40000000UL /* Not yet visible via sysfs */
 
 static int kmem_size = sizeof(struct kmem_cache);
 
@@ -178,7 +179,7 @@ static struct notifier_block slab_notifier;
 
 static enum {
 	DOWN,		/* No slab functionality available */
-	PARTIAL,	/* kmem_cache_open() works but kmalloc does not */
+	PARTIAL,	/* Kmem_cache_node works */
 	UP,		/* Everything works but does not show up in sysfs */
 	SYSFS		/* Sysfs up */
 } slab_state = DOWN;
@@ -199,7 +200,7 @@ struct track {
 
 enum track_item { TRACK_ALLOC, TRACK_FREE };
 
-#ifdef CONFIG_SLUB_DEBUG
+#ifdef CONFIG_SYSFS
 static int sysfs_slab_add(struct kmem_cache *);
 static int sysfs_slab_alias(struct kmem_cache *, const char *);
 static void sysfs_slab_remove(struct kmem_cache *);
@@ -210,6 +211,7 @@ static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
 							{ return 0; }
 static inline void sysfs_slab_remove(struct kmem_cache *s)
 {
+	kfree(s->name);
 	kfree(s);
 }
 
@@ -233,11 +235,7 @@ int slab_is_available(void)
 
 static inline struct kmem_cache_node *get_node(struct kmem_cache *s, int node)
 {
-#ifdef CONFIG_NUMA
 	return s->node[node];
-#else
-	return &s->local_node;
-#endif
 }
 
 /* Verify that a pointer has an address that is valid within a slab page */
@@ -494,7 +492,7 @@ static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...)
 	dump_stack();
 }
 
-static void init_object(struct kmem_cache *s, void *object, int active)
+static void init_object(struct kmem_cache *s, void *object, u8 val)
 {
 	u8 *p = object;
 
@@ -504,9 +502,7 @@ static void init_object(struct kmem_cache *s, void *object, int active)
 	}
 
 	if (s->flags & SLAB_RED_ZONE)
-		memset(p + s->objsize,
-			active ? SLUB_RED_ACTIVE : SLUB_RED_INACTIVE,
-			s->inuse - s->objsize);
+		memset(p + s->objsize, val, s->inuse - s->objsize);
 }
 
 static u8 *check_bytes(u8 *start, unsigned int value, unsigned int bytes)
@@ -641,17 +637,14 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page)
 }
 
 static int check_object(struct kmem_cache *s, struct page *page,
-					void *object, int active)
+					void *object, u8 val)
 {
 	u8 *p = object;
 	u8 *endobject = object + s->objsize;
 
 	if (s->flags & SLAB_RED_ZONE) {
-		unsigned int red =
-			active ? SLUB_RED_ACTIVE : SLUB_RED_INACTIVE;
-
 		if (!check_bytes_and_report(s, page, object, "Redzone",
-			endobject, red, s->inuse - s->objsize))
+			endobject, val, s->inuse - s->objsize))
 			return 0;
 	} else {
 		if ((s->flags & SLAB_POISON) && s->objsize < s->inuse) {
@@ -661,7 +654,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
 	}
 
 	if (s->flags & SLAB_POISON) {
-		if (!active && (s->flags & __OBJECT_POISON) &&
+		if (val != SLUB_RED_ACTIVE && (s->flags & __OBJECT_POISON) &&
 			(!check_bytes_and_report(s, page, p, "Poison", p,
 					POISON_FREE, s->objsize - 1) ||
 			 !check_bytes_and_report(s, page, p, "Poison",
@@ -673,7 +666,7 @@ static int check_object(struct kmem_cache *s, struct page *page,
 		check_pad_bytes(s, page, p);
 	}
 
-	if (!s->offset && active)
+	if (!s->offset && val == SLUB_RED_ACTIVE)
 		/*
 		 * Object and freepointer overlap. Cannot check
 		 * freepointer while object is allocated.
@@ -792,6 +785,39 @@ static void trace(struct kmem_cache *s, struct page *page, void *object,
 }
 
 /*
+ * Hooks for other subsystems that check memory allocations. In a typical
+ * production configuration these hooks all should produce no code at all.
+ */
+static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
+{
+	flags &= gfp_allowed_mask;
+	lockdep_trace_alloc(flags);
+	might_sleep_if(flags & __GFP_WAIT);
+
+	return should_failslab(s->objsize, flags, s->flags);
+}
+
+static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, void *object)
+{
+	flags &= gfp_allowed_mask;
+	kmemcheck_slab_alloc(s, flags, object, s->objsize);
+	kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, flags);
+}
+
+static inline void slab_free_hook(struct kmem_cache *s, void *x)
+{
+	kmemleak_free_recursive(x, s->flags);
+}
+
+static inline void slab_free_hook_irq(struct kmem_cache *s, void *object)
+{
+	kmemcheck_slab_free(s, object, s->objsize);
+	debug_check_no_locks_freed(object, s->objsize);
+	if (!(s->flags & SLAB_DEBUG_OBJECTS))
+		debug_check_no_obj_freed(object, s->objsize);
+}
+
+/*
  * Tracking of fully allocated slabs for debugging purposes.
  */
 static void add_full(struct kmem_cache_node *n, struct page *page)
@@ -838,7 +864,7 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node, int objects)
 	 * dilemma by deferring the increment of the count during
 	 * bootstrap (see early_kmem_cache_node_alloc).
 	 */
-	if (!NUMA_BUILD || n) {
+	if (n) {
 		atomic_long_inc(&n->nr_slabs);
 		atomic_long_add(objects, &n->total_objects);
 	}
@@ -858,11 +884,11 @@ static void setup_object_debug(struct kmem_cache *s, struct page *page,
 	if (!(s->flags & (SLAB_STORE_USER|SLAB_RED_ZONE|__OBJECT_POISON)))
 		return;
 
-	init_object(s, object, 0);
+	init_object(s, object, SLUB_RED_INACTIVE);
 	init_tracking(s, object);
 }
 
-static int alloc_debug_processing(struct kmem_cache *s, struct page *page,
+static noinline int alloc_debug_processing(struct kmem_cache *s, struct page *page,
 					void *object, unsigned long addr)
 {
 	if (!check_slab(s, page))
@@ -878,14 +904,14 @@ static int alloc_debug_processing(struct kmem_cache *s, struct page *page,
 		goto bad;
 	}
 
-	if (!check_object(s, page, object, 0))
+	if (!check_object(s, page, object, SLUB_RED_INACTIVE))
 		goto bad;
 
 	/* Success perform special debug activities for allocs */
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_ALLOC, addr);
 	trace(s, page, object, 1);
-	init_object(s, object, 1);
+	init_object(s, object, SLUB_RED_ACTIVE);
 	return 1;
 
 bad:
@@ -902,8 +928,8 @@ bad:
 	return 0;
 }
 
-static int free_debug_processing(struct kmem_cache *s, struct page *page,
-					void *object, unsigned long addr)
+static noinline int free_debug_processing(struct kmem_cache *s,
+		 struct page *page, void *object, unsigned long addr)
 {
 	if (!check_slab(s, page))
 		goto fail;
@@ -918,7 +944,7 @@ static int free_debug_processing(struct kmem_cache *s, struct page *page,
 		goto fail;
 	}
 
-	if (!check_object(s, page, object, 1))
+	if (!check_object(s, page, object, SLUB_RED_ACTIVE))
 		return 0;
 
 	if (unlikely(s != page->slab)) {
@@ -942,7 +968,7 @@ static int free_debug_processing(struct kmem_cache *s, struct page *page,
 	if (s->flags & SLAB_STORE_USER)
 		set_track(s, object, TRACK_FREE, addr);
 	trace(s, page, object, 0);
-	init_object(s, object, 0);
+	init_object(s, object, SLUB_RED_INACTIVE);
 	return 1;
 
 fail:
@@ -1046,7 +1072,7 @@ static inline int free_debug_processing(struct kmem_cache *s,
 static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
 			{ return 1; }
 static inline int check_object(struct kmem_cache *s, struct page *page,
-			void *object, int active) { return 1; }
+			void *object, u8 val) { return 1; }
 static inline void add_full(struct kmem_cache_node *n, struct page *page) {}
 static inline unsigned long kmem_cache_flags(unsigned long objsize,
 	unsigned long flags, const char *name,
@@ -1066,7 +1092,19 @@ static inline void inc_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
 static inline void dec_slabs_node(struct kmem_cache *s, int node,
 							int objects) {}
-#endif
+
+static inline int slab_pre_alloc_hook(struct kmem_cache *s, gfp_t flags)
+							{ return 0; }
+
+static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags,
+		void *object) {}
+
+static inline void slab_free_hook(struct kmem_cache *s, void *x) {}
+
+static inline void slab_free_hook_irq(struct kmem_cache *s,
+		void *object) {}
+
+#endif /* CONFIG_SLUB_DEBUG */
 
 /*
  * Slab allocation and freeing
@@ -1194,7 +1232,7 @@ static void __free_slab(struct kmem_cache *s, struct page *page)
 		slab_pad_check(s, page);
 		for_each_object(p, s, page_address(page),
 						page->objects)
-			check_object(s, page, p, 0);
+			check_object(s, page, p, SLUB_RED_INACTIVE);
 	}
 
 	kmemcheck_free_shadow(page, compound_order(page));
@@ -1274,13 +1312,19 @@ static void add_partial(struct kmem_cache_node *n,
 	spin_unlock(&n->list_lock);
 }
 
+static inline void __remove_partial(struct kmem_cache_node *n,
+					struct page *page)
+{
+	list_del(&page->lru);
+	n->nr_partial--;
+}
+
 static void remove_partial(struct kmem_cache *s, struct page *page)
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
 	spin_lock(&n->list_lock);
-	list_del(&page->lru);
-	n->nr_partial--;
+	__remove_partial(n, page);
 	spin_unlock(&n->list_lock);
 }
 
@@ -1293,8 +1337,7 @@ static inline int lock_and_freeze_slab(struct kmem_cache_node *n,
 							struct page *page)
 {
 	if (slab_trylock(page)) {
-		list_del(&page->lru);
-		n->nr_partial--;
+		__remove_partial(n, page);
 		__SetPageSlubFrozen(page);
 		return 1;
 	}
@@ -1405,6 +1448,7 @@ static struct page *get_partial(struct kmem_cache *s, gfp_t flags, int node)
  * On exit the slab lock will have been dropped.
  */
 static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
+	__releases(bitlock)
 {
 	struct kmem_cache_node *n = get_node(s, page_to_nid(page));
 
@@ -1447,6 +1491,7 @@ static void unfreeze_slab(struct kmem_cache *s, struct page *page, int tail)
  * Remove the cpu slab
  */
 static void deactivate_slab(struct kmem_cache *s, struct kmem_cache_cpu *c)
+	__releases(bitlock)
 {
 	struct page *page = c->page;
 	int tail = 1;
@@ -1647,6 +1692,7 @@ new_slab:
 		goto load_freelist;
 	}
 
+	gfpflags &= gfp_allowed_mask;
 	if (gfpflags & __GFP_WAIT)
 		local_irq_enable();
 
@@ -1674,7 +1720,7 @@ debug:
 
 	c->page->inuse++;
 	c->page->freelist = get_freepointer(s, object);
-	c->node = -1;
+	c->node = NUMA_NO_NODE;
 	goto unlock_out;
 }
 
@@ -1695,12 +1741,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	struct kmem_cache_cpu *c;
 	unsigned long flags;
 
-	gfpflags &= gfp_allowed_mask;
-
-	lockdep_trace_alloc(gfpflags);
-	might_sleep_if(gfpflags & __GFP_WAIT);
-
-	if (should_failslab(s->objsize, gfpflags, s->flags))
+	if (slab_pre_alloc_hook(s, gfpflags))
 		return NULL;
 
 	local_irq_save(flags);
@@ -1719,8 +1760,7 @@ static __always_inline void *slab_alloc(struct kmem_cache *s,
 	if (unlikely(gfpflags & __GFP_ZERO) && object)
 		memset(object, 0, s->objsize);
 
-	kmemcheck_slab_alloc(s, gfpflags, object, s->objsize);
-	kmemleak_alloc_recursive(object, s->objsize, 1, s->flags, gfpflags);
+	slab_post_alloc_hook(s, gfpflags, object);
 
 	return object;
 }
@@ -1736,11 +1776,21 @@ void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
 EXPORT_SYMBOL(kmem_cache_alloc);
 
 #ifdef CONFIG_TRACING
-void *kmem_cache_alloc_notrace(struct kmem_cache *s, gfp_t gfpflags)
+void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
 {
-	return slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+	trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
+	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_notrace);
+EXPORT_SYMBOL(kmem_cache_alloc_trace);
+
+void *kmalloc_order_trace(size_t size, gfp_t flags, unsigned int order)
+{
+	void *ret = kmalloc_order(size, flags, order);
+	trace_kmalloc(_RET_IP_, ret, size, PAGE_SIZE << order, flags);
+	return ret;
+}
+EXPORT_SYMBOL(kmalloc_order_trace);
 #endif
 
 #ifdef CONFIG_NUMA
@@ -1754,16 +1804,20 @@ void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
 	return ret;
 }
 EXPORT_SYMBOL(kmem_cache_alloc_node);
-#endif
 
 #ifdef CONFIG_TRACING
-void *kmem_cache_alloc_node_notrace(struct kmem_cache *s,
+void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
 				    gfp_t gfpflags,
-				    int node)
+				    int node, size_t size)
 {
-	return slab_alloc(s, gfpflags, node, _RET_IP_);
+	void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+
+	trace_kmalloc_node(_RET_IP_, ret,
+			   size, s->size, gfpflags, node);
+	return ret;
 }
-EXPORT_SYMBOL(kmem_cache_alloc_node_notrace);
+EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
+#endif
 #endif
 
 /*
@@ -1850,14 +1904,14 @@ static __always_inline void slab_free(struct kmem_cache *s,
 	struct kmem_cache_cpu *c;
 	unsigned long flags;
 
-	kmemleak_free_recursive(x, s->flags);
+	slab_free_hook(s, x);
+
 	local_irq_save(flags);
 	c = __this_cpu_ptr(s->cpu_slab);
-	kmemcheck_slab_free(s, object, s->objsize);
-	debug_check_no_locks_freed(object, s->objsize);
-	if (!(s->flags & SLAB_DEBUG_OBJECTS))
-		debug_check_no_obj_freed(object, s->objsize);
-	if (likely(page == c->page && c->node >= 0)) {
+
+	slab_free_hook_irq(s, x);
+
+	if (likely(page == c->page && c->node != NUMA_NO_NODE)) {
 		set_freepointer(s, object, c->freelist);
 		c->freelist = object;
 		stat(s, FREE_FASTPATH);
@@ -1879,17 +1933,6 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
 }
 EXPORT_SYMBOL(kmem_cache_free);
 
-/* Figure out on which slab page the object resides */
-static struct page *get_object_page(const void *x)
-{
-	struct page *page = virt_to_head_page(x);
-
-	if (!PageSlab(page))
-		return NULL;
-
-	return page;
-}
-
 /*
  * Object placement in a slab is made very easy because we always start at
  * offset 0. If we tune the size of the object to the alignment then we can
@@ -2062,26 +2105,18 @@ init_kmem_cache_node(struct kmem_cache_node *n, struct kmem_cache *s)
 #endif
 }
 
-static DEFINE_PER_CPU(struct kmem_cache_cpu, kmalloc_percpu[KMALLOC_CACHES]);
-
-static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
+static inline int alloc_kmem_cache_cpus(struct kmem_cache *s)
 {
-	if (s < kmalloc_caches + KMALLOC_CACHES && s >= kmalloc_caches)
-		/*
-		 * Boot time creation of the kmalloc array. Use static per cpu data
-		 * since the per cpu allocator is not available yet.
-		 */
-		s->cpu_slab = kmalloc_percpu + (s - kmalloc_caches);
-	else
-		s->cpu_slab =  alloc_percpu(struct kmem_cache_cpu);
+	BUILD_BUG_ON(PERCPU_DYNAMIC_EARLY_SIZE <
+			SLUB_PAGE_SHIFT * sizeof(struct kmem_cache_cpu));
 
-	if (!s->cpu_slab)
-		return 0;
+	s->cpu_slab = alloc_percpu(struct kmem_cache_cpu);
 
-	return 1;
+	return s->cpu_slab != NULL;
 }
 
-#ifdef CONFIG_NUMA
+static struct kmem_cache *kmem_cache_node;
+
 /*
  * No kmalloc_node yet so do it by hand. We know that this is the first
  * slab on the node for this slabcache. There are no concurrent accesses
@@ -2091,15 +2126,15 @@ static inline int alloc_kmem_cache_cpus(struct kmem_cache *s, gfp_t flags)
  * when allocating for the kmalloc_node_cache. This is used for bootstrapping
  * memory on a fresh node that has no slab structures yet.
  */
-static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node)
+static void early_kmem_cache_node_alloc(int node)
 {
 	struct page *page;
 	struct kmem_cache_node *n;
 	unsigned long flags;
 
-	BUG_ON(kmalloc_caches->size < sizeof(struct kmem_cache_node));
+	BUG_ON(kmem_cache_node->size < sizeof(struct kmem_cache_node));
 
-	page = new_slab(kmalloc_caches, gfpflags, node);
+	page = new_slab(kmem_cache_node, GFP_NOWAIT, node);
 
 	BUG_ON(!page);
 	if (page_to_nid(page) != node) {
@@ -2111,15 +2146,15 @@ static void early_kmem_cache_node_alloc(gfp_t gfpflags, int node)
 
 	n = page->freelist;
 	BUG_ON(!n);
-	page->freelist = get_freepointer(kmalloc_caches, n);
+	page->freelist = get_freepointer(kmem_cache_node, n);
 	page->inuse++;
-	kmalloc_caches->node[node] = n;
+	kmem_cache_node->node[node] = n;
 #ifdef CONFIG_SLUB_DEBUG
-	init_object(kmalloc_caches, n, 1);
-	init_tracking(kmalloc_caches, n);
+	init_object(kmem_cache_node, n, SLUB_RED_ACTIVE);
+	init_tracking(kmem_cache_node, n);
 #endif
-	init_kmem_cache_node(n, kmalloc_caches);
-	inc_slabs_node(kmalloc_caches, node, page->objects);
+	init_kmem_cache_node(n, kmem_cache_node);
+	inc_slabs_node(kmem_cache_node, node, page->objects);
 
 	/*
 	 * lockdep requires consistent irq usage for each lock
@@ -2137,13 +2172,15 @@ static void free_kmem_cache_nodes(struct kmem_cache *s)
 
 	for_each_node_state(node, N_NORMAL_MEMORY) {
 		struct kmem_cache_node *n = s->node[node];
+
 		if (n)
-			kmem_cache_free(kmalloc_caches, n);
+			kmem_cache_free(kmem_cache_node, n);
+
 		s->node[node] = NULL;
 	}
 }
 
-static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
+static int init_kmem_cache_nodes(struct kmem_cache *s)
 {
 	int node;
 
@@ -2151,11 +2188,11 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 		struct kmem_cache_node *n;
 
 		if (slab_state == DOWN) {
-			early_kmem_cache_node_alloc(gfpflags, node);
+			early_kmem_cache_node_alloc(node);
 			continue;
 		}
-		n = kmem_cache_alloc_node(kmalloc_caches,
-						gfpflags, node);
+		n = kmem_cache_alloc_node(kmem_cache_node,
+						GFP_KERNEL, node);
 
 		if (!n) {
 			free_kmem_cache_nodes(s);
@@ -2167,17 +2204,6 @@ static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
 	}
 	return 1;
 }
-#else
-static void free_kmem_cache_nodes(struct kmem_cache *s)
-{
-}
-
-static int init_kmem_cache_nodes(struct kmem_cache *s, gfp_t gfpflags)
-{
-	init_kmem_cache_node(&s->local_node, s);
-	return 1;
-}
-#endif
 
 static void set_min_partial(struct kmem_cache *s, unsigned long min)
 {
@@ -2312,7 +2338,7 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
 
 }
 
-static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
+static int kmem_cache_open(struct kmem_cache *s,
 		const char *name, size_t size,
 		size_t align, unsigned long flags,
 		void (*ctor)(void *))
@@ -2348,10 +2374,10 @@ static int kmem_cache_open(struct kmem_cache *s, gfp_t gfpflags,
 #ifdef CONFIG_NUMA
 	s->remote_node_defrag_ratio = 1000;
 #endif
-	if (!init_kmem_cache_nodes(s, gfpflags & ~SLUB_DMA))
+	if (!init_kmem_cache_nodes(s))
 		goto error;
 
-	if (alloc_kmem_cache_cpus(s, gfpflags & ~SLUB_DMA))
+	if (alloc_kmem_cache_cpus(s))
 		return 1;
 
 	free_kmem_cache_nodes(s);
@@ -2365,35 +2391,6 @@ error:
 }
 
 /*
- * Check if a given pointer is valid
- */
-int kmem_ptr_validate(struct kmem_cache *s, const void *object)
-{
-	struct page *page;
-
-	if (!kern_ptr_validate(object, s->size))
-		return 0;
-
-	page = get_object_page(object);
-
-	if (!page || s != page->slab)
-		/* No slab or wrong slab */
-		return 0;
-
-	if (!check_valid_pointer(s, page, object))
-		return 0;
-
-	/*
-	 * We could also check if the object is on the slabs freelist.
-	 * But this would be too expensive and it seems that the main
-	 * purpose of kmem_ptr_valid() is to check if the object belongs
-	 * to a certain slab.
-	 */
-	return 1;
-}
-EXPORT_SYMBOL(kmem_ptr_validate);
-
-/*
  * Determine the size of a slab object
  */
 unsigned int kmem_cache_size(struct kmem_cache *s)
@@ -2414,9 +2411,8 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
 #ifdef CONFIG_SLUB_DEBUG
 	void *addr = page_address(page);
 	void *p;
-	long *map = kzalloc(BITS_TO_LONGS(page->objects) * sizeof(long),
-			    GFP_ATOMIC);
-
+	unsigned long *map = kzalloc(BITS_TO_LONGS(page->objects) *
+				     sizeof(long), GFP_ATOMIC);
 	if (!map)
 		return;
 	slab_err(s, page, "%s", text);
@@ -2448,9 +2444,8 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
 	spin_lock_irqsave(&n->list_lock, flags);
 	list_for_each_entry_safe(page, h, &n->partial, lru) {
 		if (!page->inuse) {
-			list_del(&page->lru);
+			__remove_partial(n, page);
 			discard_slab(s, page);
-			n->nr_partial--;
 		} else {
 			list_slab_objects(s, page,
 				"Objects remaining on kmem_cache_close()");
@@ -2507,9 +2502,15 @@ EXPORT_SYMBOL(kmem_cache_destroy);
  *		Kmalloc subsystem
  *******************************************************************/
 
-struct kmem_cache kmalloc_caches[KMALLOC_CACHES] __cacheline_aligned;
+struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
 EXPORT_SYMBOL(kmalloc_caches);
 
+static struct kmem_cache *kmem_cache;
+
+#ifdef CONFIG_ZONE_DMA
+static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
+#endif
+
 static int __init setup_slub_min_order(char *str)
 {
 	get_option(&str, &slub_min_order);
@@ -2546,116 +2547,29 @@ static int __init setup_slub_nomerge(char *str)
 
 __setup("slub_nomerge", setup_slub_nomerge);
 
-static struct kmem_cache *create_kmalloc_cache(struct kmem_cache *s,
-		const char *name, int size, gfp_t gfp_flags)
+static struct kmem_cache *__init create_kmalloc_cache(const char *name,
+						int size, unsigned int flags)
 {
-	unsigned int flags = 0;
+	struct kmem_cache *s;
 
-	if (gfp_flags & SLUB_DMA)
-		flags = SLAB_CACHE_DMA;
+	s = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
 
 	/*
 	 * This function is called with IRQs disabled during early-boot on
 	 * single CPU so there's no need to take slub_lock here.
 	 */
-	if (!kmem_cache_open(s, gfp_flags, name, size, ARCH_KMALLOC_MINALIGN,
+	if (!kmem_cache_open(s, name, size, ARCH_KMALLOC_MINALIGN,
 								flags, NULL))
 		goto panic;
 
 	list_add(&s->list, &slab_caches);
-
-	if (sysfs_slab_add(s))
-		goto panic;
 	return s;
 
 panic:
 	panic("Creation of kmalloc slab %s size=%d failed.\n", name, size);
+	return NULL;
 }
 
-#ifdef CONFIG_ZONE_DMA
-static struct kmem_cache *kmalloc_caches_dma[SLUB_PAGE_SHIFT];
-
-static void sysfs_add_func(struct work_struct *w)
-{
-	struct kmem_cache *s;
-
-	down_write(&slub_lock);
-	list_for_each_entry(s, &slab_caches, list) {
-		if (s->flags & __SYSFS_ADD_DEFERRED) {
-			s->flags &= ~__SYSFS_ADD_DEFERRED;
-			sysfs_slab_add(s);
-		}
-	}
-	up_write(&slub_lock);
-}
-
-static DECLARE_WORK(sysfs_add_work, sysfs_add_func);
-
-static noinline struct kmem_cache *dma_kmalloc_cache(int index, gfp_t flags)
-{
-	struct kmem_cache *s;
-	char *text;
-	size_t realsize;
-	unsigned long slabflags;
-	int i;
-
-	s = kmalloc_caches_dma[index];
-	if (s)
-		return s;
-
-	/* Dynamically create dma cache */
-	if (flags & __GFP_WAIT)
-		down_write(&slub_lock);
-	else {
-		if (!down_write_trylock(&slub_lock))
-			goto out;
-	}
-
-	if (kmalloc_caches_dma[index])
-		goto unlock_out;
-
-	realsize = kmalloc_caches[index].objsize;
-	text = kasprintf(flags & ~SLUB_DMA, "kmalloc_dma-%d",
-			 (unsigned int)realsize);
-
-	s = NULL;
-	for (i = 0; i < KMALLOC_CACHES; i++)
-		if (!kmalloc_caches[i].size)
-			break;
-
-	BUG_ON(i >= KMALLOC_CACHES);
-	s = kmalloc_caches + i;
-
-	/*
-	 * Must defer sysfs creation to a workqueue because we don't know
-	 * what context we are called from. Before sysfs comes up, we don't
-	 * need to do anything because our sysfs initcall will start by
-	 * adding all existing slabs to sysfs.
-	 */
-	slabflags = SLAB_CACHE_DMA|SLAB_NOTRACK;
-	if (slab_state >= SYSFS)
-		slabflags |= __SYSFS_ADD_DEFERRED;
-
-	if (!text || !kmem_cache_open(s, flags, text,
-			realsize, ARCH_KMALLOC_MINALIGN, slabflags, NULL)) {
-		s->size = 0;
-		kfree(text);
-		goto unlock_out;
-	}
-
-	list_add(&s->list, &slab_caches);
-	kmalloc_caches_dma[index] = s;
-
-	if (slab_state >= SYSFS)
-		schedule_work(&sysfs_add_work);
-
-unlock_out:
-	up_write(&slub_lock);
-out:
-	return kmalloc_caches_dma[index];
-}
-#endif
-
 /*
  * Conversion table for small slabs sizes / 8 to the index in the
  * kmalloc array. This is necessary for slabs < 192 since we have non power
@@ -2708,10 +2622,10 @@ static struct kmem_cache *get_slab(size_t size, gfp_t flags)
 
 #ifdef CONFIG_ZONE_DMA
 	if (unlikely((flags & SLUB_DMA)))
-		return dma_kmalloc_cache(index, flags);
+		return kmalloc_dma_caches[index];
 
 #endif
-	return &kmalloc_caches[index];
+	return kmalloc_caches[index];
 }
 
 void *__kmalloc(size_t size, gfp_t flags)
@@ -2735,6 +2649,7 @@ void *__kmalloc(size_t size, gfp_t flags)
 }
 EXPORT_SYMBOL(__kmalloc);
 
+#ifdef CONFIG_NUMA
 static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 {
 	struct page *page;
@@ -2749,7 +2664,6 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node)
 	return ptr;
 }
 
-#ifdef CONFIG_NUMA
 void *__kmalloc_node(size_t size, gfp_t flags, int node)
 {
 	struct kmem_cache *s;
@@ -2889,8 +2803,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 				 * may have freed the last object and be
 				 * waiting to release the slab.
 				 */
-				list_del(&page->lru);
-				n->nr_partial--;
+				__remove_partial(n, page);
 				slab_unlock(page);
 				discard_slab(s, page);
 			} else {
@@ -2914,7 +2827,7 @@ int kmem_cache_shrink(struct kmem_cache *s)
 }
 EXPORT_SYMBOL(kmem_cache_shrink);
 
-#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
+#if defined(CONFIG_MEMORY_HOTPLUG)
 static int slab_mem_going_offline_callback(void *arg)
 {
 	struct kmem_cache *s;
@@ -2956,7 +2869,7 @@ static void slab_mem_offline_callback(void *arg)
 			BUG_ON(slabs_node(s, offline_node));
 
 			s->node[offline_node] = NULL;
-			kmem_cache_free(kmalloc_caches, n);
+			kmem_cache_free(kmem_cache_node, n);
 		}
 	}
 	up_read(&slub_lock);
@@ -2989,7 +2902,7 @@ static int slab_mem_going_online_callback(void *arg)
 		 *      since memory is not yet available from the node that
 		 *      is brought up.
 		 */
-		n = kmem_cache_alloc(kmalloc_caches, GFP_KERNEL);
+		n = kmem_cache_alloc(kmem_cache_node, GFP_KERNEL);
 		if (!n) {
 			ret = -ENOMEM;
 			goto out;
@@ -3035,46 +2948,92 @@ static int slab_memory_callback(struct notifier_block *self,
  *			Basic setup of slabs
  *******************************************************************/
 
+/*
+ * Used for early kmem_cache structures that were allocated using
+ * the page allocator
+ */
+
+static void __init kmem_cache_bootstrap_fixup(struct kmem_cache *s)
+{
+	int node;
+
+	list_add(&s->list, &slab_caches);
+	s->refcount = -1;
+
+	for_each_node_state(node, N_NORMAL_MEMORY) {
+		struct kmem_cache_node *n = get_node(s, node);
+		struct page *p;
+
+		if (n) {
+			list_for_each_entry(p, &n->partial, lru)
+				p->slab = s;
+
+#ifdef CONFIG_SLAB_DEBUG
+			list_for_each_entry(p, &n->full, lru)
+				p->slab = s;
+#endif
+		}
+	}
+}
+
 void __init kmem_cache_init(void)
 {
 	int i;
 	int caches = 0;
+	struct kmem_cache *temp_kmem_cache;
+	int order;
+	struct kmem_cache *temp_kmem_cache_node;
+	unsigned long kmalloc_size;
+
+	kmem_size = offsetof(struct kmem_cache, node) +
+				nr_node_ids * sizeof(struct kmem_cache_node *);
+
+	/* Allocate two kmem_caches from the page allocator */
+	kmalloc_size = ALIGN(kmem_size, cache_line_size());
+	order = get_order(2 * kmalloc_size);
+	kmem_cache = (void *)__get_free_pages(GFP_NOWAIT, order);
 
-#ifdef CONFIG_NUMA
 	/*
 	 * Must first have the slab cache available for the allocations of the
 	 * struct kmem_cache_node's. There is special bootstrap code in
 	 * kmem_cache_open for slab_state == DOWN.
 	 */
-	create_kmalloc_cache(&kmalloc_caches[0], "kmem_cache_node",
-		sizeof(struct kmem_cache_node), GFP_NOWAIT);
-	kmalloc_caches[0].refcount = -1;
-	caches++;
+	kmem_cache_node = (void *)kmem_cache + kmalloc_size;
+
+	kmem_cache_open(kmem_cache_node, "kmem_cache_node",
+		sizeof(struct kmem_cache_node),
+		0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
 
 	hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
-#endif
 
 	/* Able to allocate the per node structures */
 	slab_state = PARTIAL;
 
-	/* Caches that are not of the two-to-the-power-of size */
-	if (KMALLOC_MIN_SIZE <= 32) {
-		create_kmalloc_cache(&kmalloc_caches[1],
-				"kmalloc-96", 96, GFP_NOWAIT);
-		caches++;
-	}
-	if (KMALLOC_MIN_SIZE <= 64) {
-		create_kmalloc_cache(&kmalloc_caches[2],
-				"kmalloc-192", 192, GFP_NOWAIT);
-		caches++;
-	}
+	temp_kmem_cache = kmem_cache;
+	kmem_cache_open(kmem_cache, "kmem_cache", kmem_size,
+		0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+	kmem_cache = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+	memcpy(kmem_cache, temp_kmem_cache, kmem_size);
 
-	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
-		create_kmalloc_cache(&kmalloc_caches[i],
-			"kmalloc", 1 << i, GFP_NOWAIT);
-		caches++;
-	}
+	/*
+	 * Allocate kmem_cache_node properly from the kmem_cache slab.
+	 * kmem_cache_node is separately allocated so no need to
+	 * update any list pointers.
+	 */
+	temp_kmem_cache_node = kmem_cache_node;
 
+	kmem_cache_node = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+	memcpy(kmem_cache_node, temp_kmem_cache_node, kmem_size);
+
+	kmem_cache_bootstrap_fixup(kmem_cache_node);
+
+	caches++;
+	kmem_cache_bootstrap_fixup(kmem_cache);
+	caches++;
+	/* Free temporary boot structure */
+	free_pages((unsigned long)temp_kmem_cache, order);
+
+	/* Now we can use the kmem_cache to allocate kmalloc slabs */
 
 	/*
 	 * Patch up the size_index table if we have strange large alignment
@@ -3114,26 +3073,60 @@ void __init kmem_cache_init(void)
 			size_index[size_index_elem(i)] = 8;
 	}
 
+	/* Caches that are not of the two-to-the-power-of size */
+	if (KMALLOC_MIN_SIZE <= 32) {
+		kmalloc_caches[1] = create_kmalloc_cache("kmalloc-96", 96, 0);
+		caches++;
+	}
+
+	if (KMALLOC_MIN_SIZE <= 64) {
+		kmalloc_caches[2] = create_kmalloc_cache("kmalloc-192", 192, 0);
+		caches++;
+	}
+
+	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
+		kmalloc_caches[i] = create_kmalloc_cache("kmalloc", 1 << i, 0);
+		caches++;
+	}
+
 	slab_state = UP;
 
 	/* Provide the correct kmalloc names now that the caches are up */
+	if (KMALLOC_MIN_SIZE <= 32) {
+		kmalloc_caches[1]->name = kstrdup(kmalloc_caches[1]->name, GFP_NOWAIT);
+		BUG_ON(!kmalloc_caches[1]->name);
+	}
+
+	if (KMALLOC_MIN_SIZE <= 64) {
+		kmalloc_caches[2]->name = kstrdup(kmalloc_caches[2]->name, GFP_NOWAIT);
+		BUG_ON(!kmalloc_caches[2]->name);
+	}
+
 	for (i = KMALLOC_SHIFT_LOW; i < SLUB_PAGE_SHIFT; i++) {
 		char *s = kasprintf(GFP_NOWAIT, "kmalloc-%d", 1 << i);
 
 		BUG_ON(!s);
-		kmalloc_caches[i].name = s;
+		kmalloc_caches[i]->name = s;
 	}
 
 #ifdef CONFIG_SMP
 	register_cpu_notifier(&slab_notifier);
 #endif
-#ifdef CONFIG_NUMA
-	kmem_size = offsetof(struct kmem_cache, node) +
-				nr_node_ids * sizeof(struct kmem_cache_node *);
-#else
-	kmem_size = sizeof(struct kmem_cache);
-#endif
 
+#ifdef CONFIG_ZONE_DMA
+	for (i = 0; i < SLUB_PAGE_SHIFT; i++) {
+		struct kmem_cache *s = kmalloc_caches[i];
+
+		if (s && s->size) {
+			char *name = kasprintf(GFP_NOWAIT,
+				 "dma-kmalloc-%d", s->objsize);
+
+			BUG_ON(!name);
+			kmalloc_dma_caches[i] = create_kmalloc_cache(name,
+				s->objsize, SLAB_CACHE_DMA);
+		}
+	}
+#endif
 	printk(KERN_INFO
 		"SLUB: Genslabs=%d, HWalign=%d, Order=%d-%d, MinObjects=%d,"
 		" CPUs=%d, Nodes=%d\n",
@@ -3211,6 +3204,7 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		size_t align, unsigned long flags, void (*ctor)(void *))
 {
 	struct kmem_cache *s;
+	char *n;
 
 	if (WARN_ON(!name))
 		return NULL;
@@ -3234,24 +3228,30 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size,
 		return s;
 	}
 
+	n = kstrdup(name, GFP_KERNEL);
+	if (!n)
+		goto err;
+
 	s = kmalloc(kmem_size, GFP_KERNEL);
 	if (s) {
-		if (kmem_cache_open(s, GFP_KERNEL, name,
+		if (kmem_cache_open(s, n,
 				size, align, flags, ctor)) {
 			list_add(&s->list, &slab_caches);
 			if (sysfs_slab_add(s)) {
 				list_del(&s->list);
+				kfree(n);
 				kfree(s);
 				goto err;
 			}
 			up_write(&slub_lock);
 			return s;
 		}
+		kfree(n);
 		kfree(s);
 	}
+err:
 	up_write(&slub_lock);
 
-err:
 	if (flags & SLAB_PANIC)
 		panic("Cannot create slabcache %s\n", name);
 	else
@@ -3318,6 +3318,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 	return ret;
 }
 
+#ifdef CONFIG_NUMA
 void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 					int node, unsigned long caller)
 {
@@ -3346,8 +3347,9 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
 
 	return ret;
 }
+#endif
 
-#ifdef CONFIG_SLUB_DEBUG
+#ifdef CONFIG_SYSFS
 static int count_inuse(struct page *page)
 {
 	return page->inuse;
@@ -3357,7 +3359,9 @@ static int count_total(struct page *page)
 {
 	return page->objects;
 }
+#endif
 
+#ifdef CONFIG_SLUB_DEBUG
 static int validate_slab(struct kmem_cache *s, struct page *page,
 						unsigned long *map)
 {
@@ -3373,13 +3377,13 @@ static int validate_slab(struct kmem_cache *s, struct page *page,
 
 	for_each_free_object(p, s, page->freelist) {
 		set_bit(slab_index(p, s, addr), map);
-		if (!check_object(s, page, p, 0))
+		if (!check_object(s, page, p, SLUB_RED_INACTIVE))
 			return 0;
 	}
 
 	for_each_object(p, s, addr, page->objects)
 		if (!test_bit(slab_index(p, s, addr), map))
-			if (!check_object(s, page, p, 1))
+			if (!check_object(s, page, p, SLUB_RED_ACTIVE))
 				return 0;
 	return 1;
 }
@@ -3448,65 +3452,6 @@ static long validate_slab_cache(struct kmem_cache *s)
 	kfree(map);
 	return count;
 }
-
-#ifdef SLUB_RESILIENCY_TEST
-static void resiliency_test(void)
-{
-	u8 *p;
-
-	printk(KERN_ERR "SLUB resiliency testing\n");
-	printk(KERN_ERR "-----------------------\n");
-	printk(KERN_ERR "A. Corruption after allocation\n");
-
-	p = kzalloc(16, GFP_KERNEL);
-	p[16] = 0x12;
-	printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
-			" 0x12->0x%p\n\n", p + 16);
-
-	validate_slab_cache(kmalloc_caches + 4);
-
-	/* Hmmm... The next two are dangerous */
-	p = kzalloc(32, GFP_KERNEL);
-	p[32 + sizeof(void *)] = 0x34;
-	printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
-			" 0x34 -> -0x%p\n", p);
-	printk(KERN_ERR
-		"If allocated object is overwritten then not detectable\n\n");
-
-	validate_slab_cache(kmalloc_caches + 5);
-	p = kzalloc(64, GFP_KERNEL);
-	p += 64 + (get_cycles() & 0xff) * sizeof(void *);
-	*p = 0x56;
-	printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
-									p);
-	printk(KERN_ERR
-		"If allocated object is overwritten then not detectable\n\n");
-	validate_slab_cache(kmalloc_caches + 6);
-
-	printk(KERN_ERR "\nB. Corruption after free\n");
-	p = kzalloc(128, GFP_KERNEL);
-	kfree(p);
-	*p = 0x78;
-	printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
-	validate_slab_cache(kmalloc_caches + 7);
-
-	p = kzalloc(256, GFP_KERNEL);
-	kfree(p);
-	p[50] = 0x9a;
-	printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n",
-			p);
-	validate_slab_cache(kmalloc_caches + 8);
-
-	p = kzalloc(512, GFP_KERNEL);
-	kfree(p);
-	p[512] = 0xab;
-	printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
-	validate_slab_cache(kmalloc_caches + 9);
-}
-#else
-static void resiliency_test(void) {};
-#endif
-
 /*
  * Generate lists of code addresses where slabcache objects are allocated
  * and freed.
@@ -3635,7 +3580,7 @@ static int add_location(struct loc_track *t, struct kmem_cache *s,
 
 static void process_slab(struct loc_track *t, struct kmem_cache *s,
 		struct page *page, enum track_item alloc,
-		long *map)
+		unsigned long *map)
 {
 	void *addr = page_address(page);
 	void *p;
@@ -3691,7 +3636,7 @@ static int list_locations(struct kmem_cache *s, char *buf,
 		len += sprintf(buf + len, "%7ld ", l->count);
 
 		if (l->addr)
-			len += sprint_symbol(buf + len, (unsigned long)l->addr);
+			len += sprintf(buf + len, "%pS", (void *)l->addr);
 		else
 			len += sprintf(buf + len, "<not-available>");
 
@@ -3735,7 +3680,71 @@ static int list_locations(struct kmem_cache *s, char *buf,
 		len += sprintf(buf, "No data\n");
 	return len;
 }
+#endif
+
+#ifdef SLUB_RESILIENCY_TEST
+static void resiliency_test(void)
+{
+	u8 *p;
+
+	BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || SLUB_PAGE_SHIFT < 10);
 
+	printk(KERN_ERR "SLUB resiliency testing\n");
+	printk(KERN_ERR "-----------------------\n");
+	printk(KERN_ERR "A. Corruption after allocation\n");
+
+	p = kzalloc(16, GFP_KERNEL);
+	p[16] = 0x12;
+	printk(KERN_ERR "\n1. kmalloc-16: Clobber Redzone/next pointer"
+			" 0x12->0x%p\n\n", p + 16);
+
+	validate_slab_cache(kmalloc_caches[4]);
+
+	/* Hmmm... The next two are dangerous */
+	p = kzalloc(32, GFP_KERNEL);
+	p[32 + sizeof(void *)] = 0x34;
+	printk(KERN_ERR "\n2. kmalloc-32: Clobber next pointer/next slab"
+			" 0x34 -> -0x%p\n", p);
+	printk(KERN_ERR
+		"If allocated object is overwritten then not detectable\n\n");
+
+	validate_slab_cache(kmalloc_caches[5]);
+	p = kzalloc(64, GFP_KERNEL);
+	p += 64 + (get_cycles() & 0xff) * sizeof(void *);
+	*p = 0x56;
+	printk(KERN_ERR "\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n",
+									p);
+	printk(KERN_ERR
+		"If allocated object is overwritten then not detectable\n\n");
+	validate_slab_cache(kmalloc_caches[6]);
+
+	printk(KERN_ERR "\nB. Corruption after free\n");
+	p = kzalloc(128, GFP_KERNEL);
+	kfree(p);
+	*p = 0x78;
+	printk(KERN_ERR "1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p);
+	validate_slab_cache(kmalloc_caches[7]);
+
+	p = kzalloc(256, GFP_KERNEL);
+	kfree(p);
+	p[50] = 0x9a;
+	printk(KERN_ERR "\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n",
+			p);
+	validate_slab_cache(kmalloc_caches[8]);
+
+	p = kzalloc(512, GFP_KERNEL);
+	kfree(p);
+	p[512] = 0xab;
+	printk(KERN_ERR "\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p);
+	validate_slab_cache(kmalloc_caches[9]);
+}
+#else
+#ifdef CONFIG_SYSFS
+static void resiliency_test(void) {};
+#endif
+#endif
+
+#ifdef CONFIG_SYSFS
 enum slab_stat_type {
 	SL_ALL,			/* All slabs */
 	SL_PARTIAL,		/* Only partially allocated slabs */
@@ -3788,6 +3797,8 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 		}
 	}
 
+	lock_memory_hotplug();
+#ifdef CONFIG_SLUB_DEBUG
 	if (flags & SO_ALL) {
 		for_each_node_state(node, N_NORMAL_MEMORY) {
 			struct kmem_cache_node *n = get_node(s, node);
@@ -3804,7 +3815,9 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 			nodes[node] += x;
 		}
 
-	} else if (flags & SO_PARTIAL) {
+	} else
+#endif
+	if (flags & SO_PARTIAL) {
 		for_each_node_state(node, N_NORMAL_MEMORY) {
 			struct kmem_cache_node *n = get_node(s, node);
 
@@ -3825,10 +3838,12 @@ static ssize_t show_slab_objects(struct kmem_cache *s,
 			x += sprintf(buf + x, " N%d=%lu",
 					node, nodes[node]);
 #endif
+	unlock_memory_hotplug();
 	kfree(nodes);
 	return x + sprintf(buf + x, "\n");
 }
 
+#ifdef CONFIG_SLUB_DEBUG
 static int any_slab_objects(struct kmem_cache *s)
 {
 	int node;
@@ -3844,6 +3859,7 @@ static int any_slab_objects(struct kmem_cache *s)
 	}
 	return 0;
 }
+#endif
 
 #define to_slab_attr(n) container_of(n, struct slab_attribute, attr)
 #define to_slab(n) container_of(n, struct kmem_cache, kobj);
@@ -3930,12 +3946,9 @@ SLAB_ATTR(min_partial);
 
 static ssize_t ctor_show(struct kmem_cache *s, char *buf)
 {
-	if (s->ctor) {
-		int n = sprint_symbol(buf, (unsigned long)s->ctor);
-
-		return n + sprintf(buf + n, "\n");
-	}
-	return 0;
+	if (!s->ctor)
+		return 0;
+	return sprintf(buf, "%pS\n", s->ctor);
 }
 SLAB_ATTR_RO(ctor);
 
@@ -3945,12 +3958,6 @@ static ssize_t aliases_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(aliases);
 
-static ssize_t slabs_show(struct kmem_cache *s, char *buf)
-{
-	return show_slab_objects(s, buf, SO_ALL);
-}
-SLAB_ATTR_RO(slabs);
-
 static ssize_t partial_show(struct kmem_cache *s, char *buf)
 {
 	return show_slab_objects(s, buf, SO_PARTIAL);
@@ -3975,93 +3982,83 @@ static ssize_t objects_partial_show(struct kmem_cache *s, char *buf)
 }
 SLAB_ATTR_RO(objects_partial);
 
-static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
-{
-	return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
-}
-SLAB_ATTR_RO(total_objects);
-
-static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
+static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT));
 }
 
-static ssize_t sanity_checks_store(struct kmem_cache *s,
+static ssize_t reclaim_account_store(struct kmem_cache *s,
 				const char *buf, size_t length)
 {
-	s->flags &= ~SLAB_DEBUG_FREE;
+	s->flags &= ~SLAB_RECLAIM_ACCOUNT;
 	if (buf[0] == '1')
-		s->flags |= SLAB_DEBUG_FREE;
+		s->flags |= SLAB_RECLAIM_ACCOUNT;
 	return length;
 }
-SLAB_ATTR(sanity_checks);
+SLAB_ATTR(reclaim_account);
 
-static ssize_t trace_show(struct kmem_cache *s, char *buf)
+static ssize_t hwcache_align_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_TRACE));
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_HWCACHE_ALIGN));
 }
+SLAB_ATTR_RO(hwcache_align);
 
-static ssize_t trace_store(struct kmem_cache *s, const char *buf,
-							size_t length)
+#ifdef CONFIG_ZONE_DMA
+static ssize_t cache_dma_show(struct kmem_cache *s, char *buf)
 {
-	s->flags &= ~SLAB_TRACE;
-	if (buf[0] == '1')
-		s->flags |= SLAB_TRACE;
-	return length;
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_CACHE_DMA));
 }
-SLAB_ATTR(trace);
+SLAB_ATTR_RO(cache_dma);
+#endif
 
-#ifdef CONFIG_FAILSLAB
-static ssize_t failslab_show(struct kmem_cache *s, char *buf)
+static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_FAILSLAB));
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DESTROY_BY_RCU));
 }
+SLAB_ATTR_RO(destroy_by_rcu);
 
-static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
-							size_t length)
+#ifdef CONFIG_SLUB_DEBUG
+static ssize_t slabs_show(struct kmem_cache *s, char *buf)
 {
-	s->flags &= ~SLAB_FAILSLAB;
-	if (buf[0] == '1')
-		s->flags |= SLAB_FAILSLAB;
-	return length;
+	return show_slab_objects(s, buf, SO_ALL);
 }
-SLAB_ATTR(failslab);
-#endif
+SLAB_ATTR_RO(slabs);
 
-static ssize_t reclaim_account_show(struct kmem_cache *s, char *buf)
+static ssize_t total_objects_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_RECLAIM_ACCOUNT));
+	return show_slab_objects(s, buf, SO_ALL|SO_TOTAL);
 }
+SLAB_ATTR_RO(total_objects);
 
-static ssize_t reclaim_account_store(struct kmem_cache *s,
-				const char *buf, size_t length)
+static ssize_t sanity_checks_show(struct kmem_cache *s, char *buf)
 {
-	s->flags &= ~SLAB_RECLAIM_ACCOUNT;
-	if (buf[0] == '1')
-		s->flags |= SLAB_RECLAIM_ACCOUNT;
-	return length;
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DEBUG_FREE));
 }
-SLAB_ATTR(reclaim_account);
 
-static ssize_t hwcache_align_show(struct kmem_cache *s, char *buf)
+static ssize_t sanity_checks_store(struct kmem_cache *s,
+				const char *buf, size_t length)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_HWCACHE_ALIGN));
+	s->flags &= ~SLAB_DEBUG_FREE;
+	if (buf[0] == '1')
+		s->flags |= SLAB_DEBUG_FREE;
+	return length;
 }
-SLAB_ATTR_RO(hwcache_align);
+SLAB_ATTR(sanity_checks);
 
-#ifdef CONFIG_ZONE_DMA
-static ssize_t cache_dma_show(struct kmem_cache *s, char *buf)
+static ssize_t trace_show(struct kmem_cache *s, char *buf)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_CACHE_DMA));
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_TRACE));
 }
-SLAB_ATTR_RO(cache_dma);
-#endif
 
-static ssize_t destroy_by_rcu_show(struct kmem_cache *s, char *buf)
+static ssize_t trace_store(struct kmem_cache *s, const char *buf,
+							size_t length)
 {
-	return sprintf(buf, "%d\n", !!(s->flags & SLAB_DESTROY_BY_RCU));
+	s->flags &= ~SLAB_TRACE;
+	if (buf[0] == '1')
+		s->flags |= SLAB_TRACE;
+	return length;
 }
-SLAB_ATTR_RO(destroy_by_rcu);
+SLAB_ATTR(trace);
 
 static ssize_t red_zone_show(struct kmem_cache *s, char *buf)
 {
@@ -4139,6 +4136,40 @@ static ssize_t validate_store(struct kmem_cache *s,
 }
 SLAB_ATTR(validate);
 
+static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf)
+{
+	if (!(s->flags & SLAB_STORE_USER))
+		return -ENOSYS;
+	return list_locations(s, buf, TRACK_ALLOC);
+}
+SLAB_ATTR_RO(alloc_calls);
+
+static ssize_t free_calls_show(struct kmem_cache *s, char *buf)
+{
+	if (!(s->flags & SLAB_STORE_USER))
+		return -ENOSYS;
+	return list_locations(s, buf, TRACK_FREE);
+}
+SLAB_ATTR_RO(free_calls);
+#endif /* CONFIG_SLUB_DEBUG */
+
+#ifdef CONFIG_FAILSLAB
+static ssize_t failslab_show(struct kmem_cache *s, char *buf)
+{
+	return sprintf(buf, "%d\n", !!(s->flags & SLAB_FAILSLAB));
+}
+
+static ssize_t failslab_store(struct kmem_cache *s, const char *buf,
+							size_t length)
+{
+	s->flags &= ~SLAB_FAILSLAB;
+	if (buf[0] == '1')
+		s->flags |= SLAB_FAILSLAB;
+	return length;
+}
+SLAB_ATTR(failslab);
+#endif
+
 static ssize_t shrink_show(struct kmem_cache *s, char *buf)
 {
 	return 0;
@@ -4158,22 +4189,6 @@ static ssize_t shrink_store(struct kmem_cache *s,
 }
 SLAB_ATTR(shrink);
 
-static ssize_t alloc_calls_show(struct kmem_cache *s, char *buf)
-{
-	if (!(s->flags & SLAB_STORE_USER))
-		return -ENOSYS;
-	return list_locations(s, buf, TRACK_ALLOC);
-}
-SLAB_ATTR_RO(alloc_calls);
-
-static ssize_t free_calls_show(struct kmem_cache *s, char *buf)
-{
-	if (!(s->flags & SLAB_STORE_USER))
-		return -ENOSYS;
-	return list_locations(s, buf, TRACK_FREE);
-}
-SLAB_ATTR_RO(free_calls);
-
 #ifdef CONFIG_NUMA
 static ssize_t remote_node_defrag_ratio_show(struct kmem_cache *s, char *buf)
 {
@@ -4279,25 +4294,27 @@ static struct attribute *slab_attrs[] = {
 	&min_partial_attr.attr,
 	&objects_attr.attr,
 	&objects_partial_attr.attr,
-	&total_objects_attr.attr,
-	&slabs_attr.attr,
 	&partial_attr.attr,
 	&cpu_slabs_attr.attr,
 	&ctor_attr.attr,
 	&aliases_attr.attr,
 	&align_attr.attr,
-	&sanity_checks_attr.attr,
-	&trace_attr.attr,
 	&hwcache_align_attr.attr,
 	&reclaim_account_attr.attr,
 	&destroy_by_rcu_attr.attr,
+	&shrink_attr.attr,
+#ifdef CONFIG_SLUB_DEBUG
+	&total_objects_attr.attr,
+	&slabs_attr.attr,
+	&sanity_checks_attr.attr,
+	&trace_attr.attr,
 	&red_zone_attr.attr,
 	&poison_attr.attr,
 	&store_user_attr.attr,
 	&validate_attr.attr,
-	&shrink_attr.attr,
 	&alloc_calls_attr.attr,
 	&free_calls_attr.attr,
+#endif
 #ifdef CONFIG_ZONE_DMA
 	&cache_dma_attr.attr,
 #endif
@@ -4377,6 +4394,7 @@ static void kmem_cache_release(struct kobject *kobj)
 {
 	struct kmem_cache *s = to_slab(kobj);
 
+	kfree(s->name);
 	kfree(s);
 }
 
@@ -4579,7 +4597,7 @@ static int __init slab_sysfs_init(void)
 }
 
 __initcall(slab_sysfs_init);
-#endif
+#endif /* CONFIG_SYSFS */
 
 /*
  * The /proc/slabinfo ABI
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index aa33fd67fa41..64b984091edb 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -9,7 +9,7 @@
  *
  * However, virtual mappings need a page table and TLBs. Many Linux
  * architectures already map their physical space using 1-1 mappings
- * via TLBs. For those arches the virtual memmory map is essentially
+ * via TLBs. For those arches the virtual memory map is essentially
  * for free if we use the same page size as the 1-1 mappings. In that
  * case the overhead consists of a few additional pages that are
  * allocated to create a view of memory for vmemmap.
@@ -220,18 +220,7 @@ void __init sparse_mem_maps_populate_node(struct page **map_map,
 
 	if (vmemmap_buf_start) {
 		/* need to free left buf */
-#ifdef CONFIG_NO_BOOTMEM
-		free_early(__pa(vmemmap_buf_start), __pa(vmemmap_buf_end));
-		if (vmemmap_buf_start < vmemmap_buf) {
-			char name[15];
-
-			snprintf(name, sizeof(name), "MEMMAP %d", nodeid);
-			reserve_early_without_check(__pa(vmemmap_buf_start),
-						    __pa(vmemmap_buf), name);
-		}
-#else
 		free_bootmem(__pa(vmemmap_buf), vmemmap_buf_end - vmemmap_buf);
-#endif
 		vmemmap_buf = NULL;
 		vmemmap_buf_end = NULL;
 	}
diff --git a/mm/sparse.c b/mm/sparse.c
index 95ac219af379..93250207c5cf 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -671,10 +671,10 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
 static void free_map_bootmem(struct page *page, unsigned long nr_pages)
 {
 	unsigned long maps_section_nr, removing_section_nr, i;
-	int magic;
+	unsigned long magic;
 
 	for (i = 0; i < nr_pages; i++, page++) {
-		magic = atomic_read(&page->_mapcount);
+		magic = (unsigned long) page->lru.next;
 
 		BUG_ON(magic == NODE_INFO);
 
diff --git a/mm/swap.c b/mm/swap.c
index 3ce7bc373a52..c02f93611a84 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -56,17 +56,97 @@ static void __page_cache_release(struct page *page)
 		del_page_from_lru(zone, page);
 		spin_unlock_irqrestore(&zone->lru_lock, flags);
 	}
+}
+
+static void __put_single_page(struct page *page)
+{
+	__page_cache_release(page);
 	free_hot_cold_page(page, 0);
 }
 
-static void put_compound_page(struct page *page)
+static void __put_compound_page(struct page *page)
 {
-	page = compound_head(page);
-	if (put_page_testzero(page)) {
-		compound_page_dtor *dtor;
+	compound_page_dtor *dtor;
 
-		dtor = get_compound_page_dtor(page);
-		(*dtor)(page);
+	__page_cache_release(page);
+	dtor = get_compound_page_dtor(page);
+	(*dtor)(page);
+}
+
+static void put_compound_page(struct page *page)
+{
+	if (unlikely(PageTail(page))) {
+		/* __split_huge_page_refcount can run under us */
+		struct page *page_head = page->first_page;
+		smp_rmb();
+		/*
+		 * If PageTail is still set after smp_rmb() we can be sure
+		 * that the page->first_page we read wasn't a dangling pointer.
+		 * See __split_huge_page_refcount() smp_wmb().
+		 */
+		if (likely(PageTail(page) && get_page_unless_zero(page_head))) {
+			unsigned long flags;
+			/*
+			 * Verify that our page_head wasn't converted
+			 * to a a regular page before we got a
+			 * reference on it.
+			 */
+			if (unlikely(!PageHead(page_head))) {
+				/* PageHead is cleared after PageTail */
+				smp_rmb();
+				VM_BUG_ON(PageTail(page));
+				goto out_put_head;
+			}
+			/*
+			 * Only run compound_lock on a valid PageHead,
+			 * after having it pinned with
+			 * get_page_unless_zero() above.
+			 */
+			smp_mb();
+			/* page_head wasn't a dangling pointer */
+			flags = compound_lock_irqsave(page_head);
+			if (unlikely(!PageTail(page))) {
+				/* __split_huge_page_refcount run before us */
+				compound_unlock_irqrestore(page_head, flags);
+				VM_BUG_ON(PageHead(page_head));
+			out_put_head:
+				if (put_page_testzero(page_head))
+					__put_single_page(page_head);
+			out_put_single:
+				if (put_page_testzero(page))
+					__put_single_page(page);
+				return;
+			}
+			VM_BUG_ON(page_head != page->first_page);
+			/*
+			 * We can release the refcount taken by
+			 * get_page_unless_zero now that
+			 * split_huge_page_refcount is blocked on the
+			 * compound_lock.
+			 */
+			if (put_page_testzero(page_head))
+				VM_BUG_ON(1);
+			/* __split_huge_page_refcount will wait now */
+			VM_BUG_ON(atomic_read(&page->_count) <= 0);
+			atomic_dec(&page->_count);
+			VM_BUG_ON(atomic_read(&page_head->_count) <= 0);
+			compound_unlock_irqrestore(page_head, flags);
+			if (put_page_testzero(page_head)) {
+				if (PageHead(page_head))
+					__put_compound_page(page_head);
+				else
+					__put_single_page(page_head);
+			}
+		} else {
+			/* page_head is a dangling pointer */
+			VM_BUG_ON(PageTail(page));
+			goto out_put_single;
+		}
+	} else if (put_page_testzero(page)) {
+		if (PageHead(page))
+			__put_compound_page(page);
+		else
+			__put_single_page(page);
 	}
 }
 
@@ -75,7 +155,7 @@ void put_page(struct page *page)
 	if (unlikely(PageCompound(page)))
 		put_compound_page(page);
 	else if (put_page_testzero(page))
-		__page_cache_release(page);
+		__put_single_page(page);
 }
 EXPORT_SYMBOL(put_page);
 
@@ -378,6 +458,7 @@ void release_pages(struct page **pages, int nr, int cold)
 
 	pagevec_free(&pages_to_free);
 }
+EXPORT_SYMBOL(release_pages);
 
 /*
  * The pages which we're about to release may be in the deferred lru-addition
@@ -398,6 +479,43 @@ void __pagevec_release(struct pagevec *pvec)
 
 EXPORT_SYMBOL(__pagevec_release);
 
+/* used by __split_huge_page_refcount() */
+void lru_add_page_tail(struct zone* zone,
+		       struct page *page, struct page *page_tail)
+{
+	int active;
+	enum lru_list lru;
+	const int file = 0;
+	struct list_head *head;
+
+	VM_BUG_ON(!PageHead(page));
+	VM_BUG_ON(PageCompound(page_tail));
+	VM_BUG_ON(PageLRU(page_tail));
+	VM_BUG_ON(!spin_is_locked(&zone->lru_lock));
+
+	SetPageLRU(page_tail);
+
+	if (page_evictable(page_tail, NULL)) {
+		if (PageActive(page)) {
+			SetPageActive(page_tail);
+			active = 1;
+			lru = LRU_ACTIVE_ANON;
+		} else {
+			active = 0;
+			lru = LRU_INACTIVE_ANON;
+		}
+		update_page_reclaim_stat(zone, page_tail, file, active);
+		if (likely(PageLRU(page)))
+			head = page->lru.prev;
+		else
+			head = &zone->lru[lru].list;
+		__add_page_to_lru_list(zone, page_tail, lru, head);
+	} else {
+		SetPageUnevictable(page_tail);
+		add_page_to_lru_list(zone, page_tail, LRU_UNEVICTABLE);
+	}
+}
+
 /*
  * Add the passed pages to the LRU, then drop the caller's refcount
  * on them.  Reinitialises the caller's pagevec.
diff --git a/mm/swap_state.c b/mm/swap_state.c
index e10f5833167f..5c8cfabbc9bc 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -157,6 +157,12 @@ int add_to_swap(struct page *page)
 	if (!entry.val)
 		return 0;
 
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page(page))) {
+			swapcache_free(entry, NULL);
+			return 0;
+		}
+
 	/*
 	 * Radix-tree node allocations from PF_MEMALLOC contexts could
 	 * completely exhaust the page allocator. __GFP_NOMEMALLOC
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 7c703ff2f36f..0341c5700e34 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -30,6 +30,7 @@
 #include <linux/capability.h>
 #include <linux/syscalls.h>
 #include <linux/memcontrol.h>
+#include <linux/poll.h>
 
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
@@ -58,6 +59,10 @@ static struct swap_info_struct *swap_info[MAX_SWAPFILES];
 
 static DEFINE_MUTEX(swapon_mutex);
 
+static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait);
+/* Activity counter to indicate that a swapon or swapoff has occurred */
+static atomic_t proc_poll_event = ATOMIC_INIT(0);
+
 static inline unsigned char swap_count(unsigned char ent)
 {
 	return ent & ~SWAP_HAS_CACHE;	/* may include SWAP_HAS_CONT flag */
@@ -139,7 +144,7 @@ static int discard_swap(struct swap_info_struct *si)
 	nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9);
 	if (nr_blocks) {
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
+				nr_blocks, GFP_KERNEL, 0);
 		if (err)
 			return err;
 		cond_resched();
@@ -150,7 +155,7 @@ static int discard_swap(struct swap_info_struct *si)
 		nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9);
 
 		err = blkdev_issue_discard(si->bdev, start_block,
-				nr_blocks, GFP_KERNEL, BLKDEV_IFL_WAIT);
+				nr_blocks, GFP_KERNEL, 0);
 		if (err)
 			break;
 
@@ -189,7 +194,7 @@ static void discard_swap_cluster(struct swap_info_struct *si,
 			start_block <<= PAGE_SHIFT - 9;
 			nr_blocks <<= PAGE_SHIFT - 9;
 			if (blkdev_issue_discard(si->bdev, start_block,
-				    nr_blocks, GFP_NOIO, BLKDEV_IFL_WAIT))
+				    nr_blocks, GFP_NOIO, 0))
 				break;
 		}
 
@@ -959,6 +964,8 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
+		if (unlikely(pmd_trans_huge(*pmd)))
+			continue;
 		if (pmd_none_or_clear_bad(pmd))
 			continue;
 		ret = unuse_pte_range(vma, pmd, addr, next, entry, page);
@@ -1672,7 +1679,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	if (S_ISBLK(inode->i_mode)) {
 		struct block_device *bdev = I_BDEV(inode);
 		set_blocksize(bdev, p->old_block_size);
-		bd_release(bdev);
+		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 	} else {
 		mutex_lock(&inode->i_mutex);
 		inode->i_flags &= ~S_SWAPFILE;
@@ -1680,6 +1687,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	}
 	filp_close(swap_file, NULL);
 	err = 0;
+	atomic_inc(&proc_poll_event);
+	wake_up_interruptible(&proc_poll_wait);
 
 out_dput:
 	filp_close(victim, NULL);
@@ -1688,6 +1697,25 @@ out:
 }
 
 #ifdef CONFIG_PROC_FS
+struct proc_swaps {
+	struct seq_file seq;
+	int event;
+};
+
+static unsigned swaps_poll(struct file *file, poll_table *wait)
+{
+	struct proc_swaps *s = file->private_data;
+
+	poll_wait(file, &proc_poll_wait, wait);
+
+	if (s->event != atomic_read(&proc_poll_event)) {
+		s->event = atomic_read(&proc_poll_event);
+		return POLLIN | POLLRDNORM | POLLERR | POLLPRI;
+	}
+
+	return POLLIN | POLLRDNORM;
+}
+
 /* iterator */
 static void *swap_start(struct seq_file *swap, loff_t *pos)
 {
@@ -1771,7 +1799,24 @@ static const struct seq_operations swaps_op = {
 
 static int swaps_open(struct inode *inode, struct file *file)
 {
-	return seq_open(file, &swaps_op);
+	struct proc_swaps *s;
+	int ret;
+
+	s = kmalloc(sizeof(struct proc_swaps), GFP_KERNEL);
+	if (!s)
+		return -ENOMEM;
+
+	file->private_data = s;
+
+	ret = seq_open(file, &swaps_op);
+	if (ret) {
+		kfree(s);
+		return ret;
+	}
+
+	s->seq.private = s;
+	s->event = atomic_read(&proc_poll_event);
+	return ret;
 }
 
 static const struct file_operations proc_swaps_operations = {
@@ -1779,6 +1824,7 @@ static const struct file_operations proc_swaps_operations = {
 	.read		= seq_read,
 	.llseek		= seq_lseek,
 	.release	= seq_release,
+	.poll		= swaps_poll,
 };
 
 static int __init procswaps_init(void)
@@ -1894,8 +1940,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 
 	error = -EINVAL;
 	if (S_ISBLK(inode->i_mode)) {
-		bdev = I_BDEV(inode);
-		error = bd_claim(bdev, sys_swapon);
+		bdev = bdgrab(I_BDEV(inode));
+		error = blkdev_get(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL,
+				   sys_swapon);
 		if (error < 0) {
 			bdev = NULL;
 			error = -EINVAL;
@@ -2084,12 +2131,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 		swap_info[prev]->next = type;
 	spin_unlock(&swap_lock);
 	mutex_unlock(&swapon_mutex);
+	atomic_inc(&proc_poll_event);
+	wake_up_interruptible(&proc_poll_wait);
+
 	error = 0;
 	goto out;
 bad_swap:
 	if (bdev) {
 		set_blocksize(bdev, p->old_block_size);
-		bd_release(bdev);
+		blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL);
 	}
 	destroy_swap_extents(p);
 	swap_cgroup_swapoff(type);
diff --git a/mm/truncate.c b/mm/truncate.c
index ba887bff48c5..49feb46e77b8 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -390,6 +390,10 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
+
+	if (mapping->a_ops->freepage)
+		mapping->a_ops->freepage(page);
+
 	page_cache_release(page);	/* pagecache ref */
 	return 1;
 failed:
@@ -545,13 +549,12 @@ EXPORT_SYMBOL(truncate_pagecache);
  * @inode: inode
  * @newsize: new file size
  *
- * truncate_setsize updastes i_size update and performs pagecache
- * truncation (if necessary) for a file size updates. It will be
- * typically be called from the filesystem's setattr function when
- * ATTR_SIZE is passed in.
+ * truncate_setsize updates i_size and performs pagecache truncation (if
+ * necessary) to @newsize. It will be typically be called from the filesystem's
+ * setattr function when ATTR_SIZE is passed in.
  *
- * Must be called with inode_mutex held and after all filesystem
- * specific block truncation has been performed.
+ * Must be called with inode_mutex held and before all filesystem specific
+ * block truncation has been performed.
  */
 void truncate_setsize(struct inode *inode, loff_t newsize)
 {
diff --git a/mm/util.c b/mm/util.c
index 4735ea481816..f126975ef23e 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -186,27 +186,6 @@ void kzfree(const void *p)
 }
 EXPORT_SYMBOL(kzfree);
 
-int kern_ptr_validate(const void *ptr, unsigned long size)
-{
-	unsigned long addr = (unsigned long)ptr;
-	unsigned long min_addr = PAGE_OFFSET;
-	unsigned long align_mask = sizeof(void *) - 1;
-
-	if (unlikely(addr < min_addr))
-		goto out;
-	if (unlikely(addr > (unsigned long)high_memory - size))
-		goto out;
-	if (unlikely(addr & align_mask))
-		goto out;
-	if (unlikely(!kern_addr_valid(addr)))
-		goto out;
-	if (unlikely(!kern_addr_valid(addr + size - 1)))
-		goto out;
-	return 1;
-out:
-	return 0;
-}
-
 /*
  * strndup_user - duplicate an existing string from user space
  * @s: The string to duplicate
@@ -245,6 +224,19 @@ void arch_pick_mmap_layout(struct mm_struct *mm)
 }
 #endif
 
+/*
+ * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
+ * back to the regular GUP.
+ * If the architecture not support this fucntion, simply return with no
+ * page pinned
+ */
+int __attribute__((weak)) __get_user_pages_fast(unsigned long start,
+				 int nr_pages, int write, struct page **pages)
+{
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+
 /**
  * get_user_pages_fast() - pin user pages in memory
  * @start:	starting user address
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6b8889da69a6..f9b166732e70 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -31,8 +31,6 @@
 #include <asm/tlbflush.h>
 #include <asm/shmparam.h>
 
-bool vmap_lazy_unmap __read_mostly = true;
-
 /*** Page table manipulation functions ***/
 
 static void vunmap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end)
@@ -293,13 +291,13 @@ static void __insert_vmap_area(struct vmap_area *va)
 	struct rb_node *tmp;
 
 	while (*p) {
-		struct vmap_area *tmp;
+		struct vmap_area *tmp_va;
 
 		parent = *p;
-		tmp = rb_entry(parent, struct vmap_area, rb_node);
-		if (va->va_start < tmp->va_end)
+		tmp_va = rb_entry(parent, struct vmap_area, rb_node);
+		if (va->va_start < tmp_va->va_end)
 			p = &(*p)->rb_left;
-		else if (va->va_end > tmp->va_start)
+		else if (va->va_end > tmp_va->va_start)
 			p = &(*p)->rb_right;
 		else
 			BUG();
@@ -503,9 +501,6 @@ static unsigned long lazy_max_pages(void)
 {
 	unsigned int log;
 
-	if (!vmap_lazy_unmap)
-		return 0;
-
 	log = fls(num_online_cpus());
 
 	return log * (32UL * 1024 * 1024 / PAGE_SIZE);
@@ -517,6 +512,15 @@ static atomic_t vmap_lazy_nr = ATOMIC_INIT(0);
 static void purge_fragmented_blocks_allcpus(void);
 
 /*
+ * called before a call to iounmap() if the caller wants vm_area_struct's
+ * immediately freed.
+ */
+void set_iounmap_nonlazy(void)
+{
+	atomic_set(&vmap_lazy_nr, lazy_max_pages()+1);
+}
+
+/*
  * Purges all lazily-freed vmap areas.
  *
  * If sync is 0 then don't purge if there is already a purge in progress.
@@ -557,7 +561,6 @@ static void __purge_vmap_area_lazy(unsigned long *start, unsigned long *end,
 			if (va->va_end > *end)
 				*end = va->va_end;
 			nr += (va->va_end - va->va_start) >> PAGE_SHIFT;
-			unmap_vmap_area(va);
 			list_add_tail(&va->purge_list, &valist);
 			va->flags |= VM_LAZY_FREEING;
 			va->flags &= ~VM_LAZY_FREE;
@@ -602,10 +605,11 @@ static void purge_vmap_area_lazy(void)
 }
 
 /*
- * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
- * called for the correct range previously.
+ * Free a vmap area, caller ensuring that the area has been unmapped
+ * and flush_cache_vunmap had been called for the correct range
+ * previously.
  */
-static void free_unmap_vmap_area_noflush(struct vmap_area *va)
+static void free_vmap_area_noflush(struct vmap_area *va)
 {
 	va->flags |= VM_LAZY_FREE;
 	atomic_add((va->va_end - va->va_start) >> PAGE_SHIFT, &vmap_lazy_nr);
@@ -614,6 +618,16 @@ static void free_unmap_vmap_area_noflush(struct vmap_area *va)
 }
 
 /*
+ * Free and unmap a vmap area, caller ensuring flush_cache_vunmap had been
+ * called for the correct range previously.
+ */
+static void free_unmap_vmap_area_noflush(struct vmap_area *va)
+{
+	unmap_vmap_area(va);
+	free_vmap_area_noflush(va);
+}
+
+/*
  * Free and unmap a vmap area
  */
 static void free_unmap_vmap_area(struct vmap_area *va)
@@ -734,7 +748,7 @@ static struct vmap_block *new_vmap_block(gfp_t gfp_mask)
 	va = alloc_vmap_area(VMAP_BLOCK_SIZE, VMAP_BLOCK_SIZE,
 					VMALLOC_START, VMALLOC_END,
 					node, gfp_mask);
-	if (unlikely(IS_ERR(va))) {
+	if (IS_ERR(va)) {
 		kfree(vb);
 		return ERR_CAST(va);
 	}
@@ -789,7 +803,7 @@ static void free_vmap_block(struct vmap_block *vb)
 	spin_unlock(&vmap_block_tree_lock);
 	BUG_ON(tmp != vb);
 
-	free_unmap_vmap_area_noflush(vb->va);
+	free_vmap_area_noflush(vb->va);
 	call_rcu(&vb->rcu_head, rcu_free_vb);
 }
 
@@ -927,6 +941,8 @@ static void vb_free(const void *addr, unsigned long size)
 	rcu_read_unlock();
 	BUG_ON(!vb);
 
+	vunmap_page_range((unsigned long)addr, (unsigned long)addr + size);
+
 	spin_lock(&vb->lock);
 	BUG_ON(bitmap_allocate_region(vb->dirty_map, offset >> PAGE_SHIFT, order));
 
@@ -979,7 +995,6 @@ void vm_unmap_aliases(void)
 
 				s = vb->va->va_start + (i << PAGE_SHIFT);
 				e = vb->va->va_start + (j << PAGE_SHIFT);
-				vunmap_page_range(s, e);
 				flush = 1;
 
 				if (s < start)
@@ -1160,6 +1175,7 @@ void unmap_kernel_range_noflush(unsigned long addr, unsigned long size)
 {
 	vunmap_page_range(addr, addr + size);
 }
+EXPORT_SYMBOL_GPL(unmap_kernel_range_noflush);
 
 /**
  * unmap_kernel_range - unmap kernel VM area and flush cache and TLB
@@ -1300,13 +1316,6 @@ struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags,
 						-1, GFP_KERNEL, caller);
 }
 
-struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags,
-				   int node, gfp_t gfp_mask)
-{
-	return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END,
-				  node, gfp_mask, __builtin_return_address(0));
-}
-
 static struct vm_struct *find_vm_area(const void *addr)
 {
 	struct vmap_area *va;
@@ -1522,25 +1531,12 @@ fail:
 	return NULL;
 }
 
-void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
-{
-	void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1,
-					 __builtin_return_address(0));
-
-	/*
-	 * A ref_count = 3 is needed because the vm_struct and vmap_area
-	 * structures allocated in the __get_vm_area_node() function contain
-	 * references to the virtual address of the vmalloc'ed block.
-	 */
-	kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask);
-
-	return addr;
-}
-
 /**
- *	__vmalloc_node  -  allocate virtually contiguous memory
+ *	__vmalloc_node_range  -  allocate virtually contiguous memory
  *	@size:		allocation size
  *	@align:		desired alignment
+ *	@start:		vm area range start
+ *	@end:		vm area range end
  *	@gfp_mask:	flags for the page level allocator
  *	@prot:		protection mask for the allocated pages
  *	@node:		node to use for allocation or -1
@@ -1550,9 +1546,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot)
  *	allocator with @gfp_mask flags.  Map them into contiguous
  *	kernel virtual space, using a pagetable protection of @prot.
  */
-static void *__vmalloc_node(unsigned long size, unsigned long align,
-			    gfp_t gfp_mask, pgprot_t prot,
-			    int node, void *caller)
+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)
 {
 	struct vm_struct *area;
 	void *addr;
@@ -1562,8 +1558,8 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 	if (!size || (size >> PAGE_SHIFT) > totalram_pages)
 		return NULL;
 
-	area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START,
-				  VMALLOC_END, node, gfp_mask, caller);
+	area = __get_vm_area_node(size, align, VM_ALLOC, start, end, node,
+				  gfp_mask, caller);
 
 	if (!area)
 		return NULL;
@@ -1580,6 +1576,27 @@ static void *__vmalloc_node(unsigned long size, unsigned long align,
 	return addr;
 }
 
+/**
+ *	__vmalloc_node  -  allocate virtually contiguous memory
+ *	@size:		allocation size
+ *	@align:		desired alignment
+ *	@gfp_mask:	flags for the page level allocator
+ *	@prot:		protection mask for the allocated pages
+ *	@node:		node to use for allocation or -1
+ *	@caller:	caller's return address
+ *
+ *	Allocate enough pages to cover @size from the page level
+ *	allocator with @gfp_mask flags.  Map them into contiguous
+ *	kernel virtual space, using a pagetable protection of @prot.
+ */
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+			    gfp_t gfp_mask, pgprot_t prot,
+			    int node, void *caller)
+{
+	return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END,
+				gfp_mask, prot, node, caller);
+}
+
 void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 {
 	return __vmalloc_node(size, 1, gfp_mask, prot, -1,
@@ -1587,6 +1604,13 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 }
 EXPORT_SYMBOL(__vmalloc);
 
+static inline void *__vmalloc_node_flags(unsigned long size,
+					int node, gfp_t flags)
+{
+	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
+					node, __builtin_return_address(0));
+}
+
 /**
  *	vmalloc  -  allocate virtually contiguous memory
  *	@size:		allocation size
@@ -1598,12 +1622,28 @@ EXPORT_SYMBOL(__vmalloc);
  */
 void *vmalloc(unsigned long size)
 {
-	return __vmalloc_node(size, 1, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL,
-					-1, __builtin_return_address(0));
+	return __vmalloc_node_flags(size, -1, GFP_KERNEL | __GFP_HIGHMEM);
 }
 EXPORT_SYMBOL(vmalloc);
 
 /**
+ *	vzalloc - allocate virtually contiguous memory with zero fill
+ *	@size:	allocation size
+ *	Allocate enough pages to cover @size from the page level
+ *	allocator and map them into contiguous kernel virtual space.
+ *	The memory allocated is set to zero.
+ *
+ *	For tight control over page level allocator and protection flags
+ *	use __vmalloc() instead.
+ */
+void *vzalloc(unsigned long size)
+{
+	return __vmalloc_node_flags(size, -1,
+				GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+}
+EXPORT_SYMBOL(vzalloc);
+
+/**
  * vmalloc_user - allocate zeroed virtually contiguous memory for userspace
  * @size: allocation size
  *
@@ -1644,6 +1684,25 @@ void *vmalloc_node(unsigned long size, int node)
 }
 EXPORT_SYMBOL(vmalloc_node);
 
+/**
+ * vzalloc_node - allocate memory on a specific node with zero fill
+ * @size:	allocation size
+ * @node:	numa node
+ *
+ * Allocate enough pages to cover @size from the page level
+ * allocator and map them into contiguous kernel virtual space.
+ * The memory allocated is set to zero.
+ *
+ * For tight control over page level allocator and protection flags
+ * use __vmalloc_node() instead.
+ */
+void *vzalloc_node(unsigned long size, int node)
+{
+	return __vmalloc_node_flags(size, node,
+			 GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO);
+}
+EXPORT_SYMBOL(vzalloc_node);
+
 #ifndef PAGE_KERNEL_EXEC
 # define PAGE_KERNEL_EXEC PAGE_KERNEL
 #endif
@@ -2056,6 +2115,7 @@ void free_vm_area(struct vm_struct *area)
 }
 EXPORT_SYMBOL_GPL(free_vm_area);
 
+#ifdef CONFIG_SMP
 static struct vmap_area *node_to_va(struct rb_node *n)
 {
 	return n ? rb_entry(n, struct vmap_area, rb_node) : NULL;
@@ -2145,17 +2205,16 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext,
  * @sizes: array containing size of each area
  * @nr_vms: the number of areas to allocate
  * @align: alignment, all entries in @offsets and @sizes must be aligned to this
- * @gfp_mask: allocation mask
  *
  * Returns: kmalloc'd vm_struct pointer array pointing to allocated
  *	    vm_structs on success, %NULL on failure
  *
  * Percpu allocator wants to use congruent vm areas so that it can
  * maintain the offsets among percpu areas.  This function allocates
- * congruent vmalloc areas for it.  These areas tend to be scattered
- * pretty far, distance between two areas easily going up to
- * gigabytes.  To avoid interacting with regular vmallocs, these areas
- * are allocated from top.
+ * congruent vmalloc areas for it with GFP_KERNEL.  These areas tend to
+ * be scattered pretty far, distance between two areas easily going up
+ * to gigabytes.  To avoid interacting with regular vmallocs, these
+ * areas are allocated from top.
  *
  * Despite its complicated look, this allocator is rather simple.  It
  * does everything top-down and scans areas from the end looking for
@@ -2166,7 +2225,7 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext,
  */
 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)
 {
 	const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align);
 	const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1);
@@ -2176,8 +2235,6 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 	unsigned long base, start, end, last_end;
 	bool purged = false;
 
-	gfp_mask &= GFP_RECLAIM_MASK;
-
 	/* verify parameters and allocate data structures */
 	BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align));
 	for (last_area = 0, area = 0; area < nr_vms; area++) {
@@ -2210,14 +2267,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets,
 		return NULL;
 	}
 
-	vms = kzalloc(sizeof(vms[0]) * nr_vms, gfp_mask);
-	vas = kzalloc(sizeof(vas[0]) * nr_vms, gfp_mask);
+	vms = kzalloc(sizeof(vms[0]) * nr_vms, GFP_KERNEL);
+	vas = kzalloc(sizeof(vas[0]) * nr_vms, GFP_KERNEL);
 	if (!vas || !vms)
 		goto err_free;
 
 	for (area = 0; area < nr_vms; area++) {
-		vas[area] = kzalloc(sizeof(struct vmap_area), gfp_mask);
-		vms[area] = kzalloc(sizeof(struct vm_struct), gfp_mask);
+		vas[area] = kzalloc(sizeof(struct vmap_area), GFP_KERNEL);
+		vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL);
 		if (!vas[area] || !vms[area])
 			goto err_free;
 	}
@@ -2336,9 +2393,11 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms)
 		free_vm_area(vms[i]);
 	kfree(vms);
 }
+#endif	/* CONFIG_SMP */
 
 #ifdef CONFIG_PROC_FS
 static void *s_start(struct seq_file *m, loff_t *pos)
+	__acquires(&vmlist_lock)
 {
 	loff_t n = *pos;
 	struct vm_struct *v;
@@ -2365,6 +2424,7 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 }
 
 static void s_stop(struct seq_file *m, void *p)
+	__releases(&vmlist_lock)
 {
 	read_unlock(&vmlist_lock);
 }
@@ -2395,13 +2455,8 @@ static int s_show(struct seq_file *m, void *p)
 	seq_printf(m, "0x%p-0x%p %7ld",
 		v->addr, v->addr + v->size, v->size);
 
-	if (v->caller) {
-		char buff[KSYM_SYMBOL_LEN];
-
-		seq_putc(m, ' ');
-		sprint_symbol(buff, (unsigned long)v->caller);
-		seq_puts(m, buff);
-	}
+	if (v->caller)
+		seq_printf(m, " %pS", v->caller);
 
 	if (v->nr_pages)
 		seq_printf(m, " pages=%d", v->nr_pages);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c5dfabf25f11..17497d0cd8b9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -32,6 +32,7 @@
 #include <linux/topology.h>
 #include <linux/cpu.h>
 #include <linux/cpuset.h>
+#include <linux/compaction.h>
 #include <linux/notifier.h>
 #include <linux/rwsem.h>
 #include <linux/delay.h>
@@ -51,6 +52,24 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/vmscan.h>
 
+/*
+ * reclaim_mode determines how the inactive list is shrunk
+ * RECLAIM_MODE_SINGLE: Reclaim only order-0 pages
+ * RECLAIM_MODE_ASYNC:  Do not block
+ * RECLAIM_MODE_SYNC:   Allow blocking e.g. call wait_on_page_writeback
+ * RECLAIM_MODE_LUMPYRECLAIM: For high-order allocations, take a reference
+ *			page from the LRU and reclaim all pages within a
+ *			naturally aligned range
+ * RECLAIM_MODE_COMPACTION: For high-order allocations, reclaim a number of
+ *			order-0 pages and then compact the zone
+ */
+typedef unsigned __bitwise__ reclaim_mode_t;
+#define RECLAIM_MODE_SINGLE		((__force reclaim_mode_t)0x01u)
+#define RECLAIM_MODE_ASYNC		((__force reclaim_mode_t)0x02u)
+#define RECLAIM_MODE_SYNC		((__force reclaim_mode_t)0x04u)
+#define RECLAIM_MODE_LUMPYRECLAIM	((__force reclaim_mode_t)0x08u)
+#define RECLAIM_MODE_COMPACTION		((__force reclaim_mode_t)0x10u)
+
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -79,10 +98,10 @@ struct scan_control {
 	int order;
 
 	/*
-	 * Intend to reclaim enough contenious memory rather than to reclaim
-	 * enough amount memory. I.e, it's the mode for high order allocation.
+	 * Intend to reclaim enough continuous memory rather than reclaim
+	 * enough amount of memory. i.e, mode for high order allocation.
 	 */
-	bool lumpy_reclaim_mode;
+	reclaim_mode_t reclaim_mode;
 
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
@@ -265,6 +284,39 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 	return ret;
 }
 
+static void set_reclaim_mode(int priority, struct scan_control *sc,
+				   bool sync)
+{
+	reclaim_mode_t syncmode = sync ? RECLAIM_MODE_SYNC : RECLAIM_MODE_ASYNC;
+
+	/*
+	 * Initially assume we are entering either lumpy reclaim or
+	 * reclaim/compaction.Depending on the order, we will either set the
+	 * sync mode or just reclaim order-0 pages later.
+	 */
+	if (COMPACTION_BUILD)
+		sc->reclaim_mode = RECLAIM_MODE_COMPACTION;
+	else
+		sc->reclaim_mode = RECLAIM_MODE_LUMPYRECLAIM;
+
+	/*
+	 * Avoid using lumpy reclaim or reclaim/compaction if possible by
+	 * restricting when its set to either costly allocations or when
+	 * under memory pressure
+	 */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		sc->reclaim_mode |= syncmode;
+	else if (sc->order && priority < DEF_PRIORITY - 2)
+		sc->reclaim_mode |= syncmode;
+	else
+		sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
+}
+
+static void reset_reclaim_mode(struct scan_control *sc)
+{
+	sc->reclaim_mode = RECLAIM_MODE_SINGLE | RECLAIM_MODE_ASYNC;
+}
+
 static inline int is_page_cache_freeable(struct page *page)
 {
 	/*
@@ -275,7 +327,8 @@ static inline int is_page_cache_freeable(struct page *page)
 	return page_count(page) - page_has_private(page) == 2;
 }
 
-static int may_write_to_queue(struct backing_dev_info *bdi)
+static int may_write_to_queue(struct backing_dev_info *bdi,
+			      struct scan_control *sc)
 {
 	if (current->flags & PF_SWAPWRITE)
 		return 1;
@@ -283,6 +336,10 @@ static int may_write_to_queue(struct backing_dev_info *bdi)
 		return 1;
 	if (bdi == current->backing_dev_info)
 		return 1;
+
+	/* lumpy reclaim for hugepage often need a lot of write */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		return 1;
 	return 0;
 }
 
@@ -307,12 +364,6 @@ static void handle_write_error(struct address_space *mapping,
 	unlock_page(page);
 }
 
-/* Request for sync pageout. */
-enum pageout_io {
-	PAGEOUT_IO_ASYNC,
-	PAGEOUT_IO_SYNC,
-};
-
 /* possible outcome of pageout() */
 typedef enum {
 	/* failed to write page out, page is locked */
@@ -330,7 +381,7 @@ typedef enum {
  * Calls ->writepage().
  */
 static pageout_t pageout(struct page *page, struct address_space *mapping,
-						enum pageout_io sync_writeback)
+			 struct scan_control *sc)
 {
 	/*
 	 * If the page is dirty, only perform writeback if that write
@@ -366,7 +417,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 	}
 	if (mapping->a_ops->writepage == NULL)
 		return PAGE_ACTIVATE;
-	if (!may_write_to_queue(mapping->backing_dev_info))
+	if (!may_write_to_queue(mapping->backing_dev_info, sc))
 		return PAGE_KEEP;
 
 	if (clear_page_dirty_for_io(page)) {
@@ -376,7 +427,6 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 			.nr_to_write = SWAP_CLUSTER_MAX,
 			.range_start = 0,
 			.range_end = LLONG_MAX,
-			.nonblocking = 1,
 			.for_reclaim = 1,
 		};
 
@@ -394,7 +444,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 		 * direct reclaiming a large contiguous area and the
 		 * first attempt to free a range of pages fails.
 		 */
-		if (PageWriteback(page) && sync_writeback == PAGEOUT_IO_SYNC)
+		if (PageWriteback(page) &&
+		    (sc->reclaim_mode & RECLAIM_MODE_SYNC))
 			wait_on_page_writeback(page);
 
 		if (!PageWriteback(page)) {
@@ -402,7 +453,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 			ClearPageReclaim(page);
 		}
 		trace_mm_vmscan_writepage(page,
-			trace_reclaim_flags(page, sync_writeback));
+			trace_reclaim_flags(page, sc->reclaim_mode));
 		inc_zone_page_state(page, NR_VMSCAN_WRITE);
 		return PAGE_SUCCESS;
 	}
@@ -459,9 +510,16 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 		spin_unlock_irq(&mapping->tree_lock);
 		swapcache_free(swap, page);
 	} else {
+		void (*freepage)(struct page *);
+
+		freepage = mapping->a_ops->freepage;
+
 		__remove_from_page_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
 		mem_cgroup_uncharge_cache_page(page);
+
+		if (freepage != NULL)
+			freepage(page);
 	}
 
 	return 1;
@@ -580,7 +638,7 @@ static enum page_references page_check_references(struct page *page,
 	referenced_page = TestClearPageReferenced(page);
 
 	/* Lumpy reclaim - ignore references */
-	if (sc->lumpy_reclaim_mode)
+	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
 		return PAGEREF_RECLAIM;
 
 	/*
@@ -616,7 +674,7 @@ static enum page_references page_check_references(struct page *page,
 	}
 
 	/* Reclaim if clean, defer dirty pages to writeback */
-	if (referenced_page)
+	if (referenced_page && !PageSwapBacked(page))
 		return PAGEREF_RECLAIM_CLEAN;
 
 	return PAGEREF_RECLAIM;
@@ -644,12 +702,14 @@ static noinline_for_stack void free_page_list(struct list_head *free_pages)
  * shrink_page_list() returns the number of reclaimed pages
  */
 static unsigned long shrink_page_list(struct list_head *page_list,
-					struct scan_control *sc,
-					enum pageout_io sync_writeback)
+				      struct zone *zone,
+				      struct scan_control *sc)
 {
 	LIST_HEAD(ret_pages);
 	LIST_HEAD(free_pages);
 	int pgactivate = 0;
+	unsigned long nr_dirty = 0;
+	unsigned long nr_congested = 0;
 	unsigned long nr_reclaimed = 0;
 
 	cond_resched();
@@ -669,6 +729,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			goto keep;
 
 		VM_BUG_ON(PageActive(page));
+		VM_BUG_ON(page_zone(page) != zone);
 
 		sc->nr_scanned++;
 
@@ -694,10 +755,13 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 			 * for any page for which writeback has already
 			 * started.
 			 */
-			if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs)
+			if ((sc->reclaim_mode & RECLAIM_MODE_SYNC) &&
+			    may_enter_fs)
 				wait_on_page_writeback(page);
-			else
-				goto keep_locked;
+			else {
+				unlock_page(page);
+				goto keep_lumpy;
+			}
 		}
 
 		references = page_check_references(page, sc);
@@ -743,6 +807,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		}
 
 		if (PageDirty(page)) {
+			nr_dirty++;
+
 			if (references == PAGEREF_RECLAIM_CLEAN)
 				goto keep_locked;
 			if (!may_enter_fs)
@@ -751,14 +817,18 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 
 			/* Page is dirty, try to write it out here */
-			switch (pageout(page, mapping, sync_writeback)) {
+			switch (pageout(page, mapping, sc)) {
 			case PAGE_KEEP:
+				nr_congested++;
 				goto keep_locked;
 			case PAGE_ACTIVATE:
 				goto activate_locked;
 			case PAGE_SUCCESS:
-				if (PageWriteback(page) || PageDirty(page))
+				if (PageWriteback(page))
+					goto keep_lumpy;
+				if (PageDirty(page))
 					goto keep;
+
 				/*
 				 * A synchronous write - probably a ramdisk.  Go
 				 * ahead and try to reclaim the page.
@@ -841,6 +911,7 @@ cull_mlocked:
 			try_to_free_swap(page);
 		unlock_page(page);
 		putback_lru_page(page);
+		reset_reclaim_mode(sc);
 		continue;
 
 activate_locked:
@@ -853,10 +924,21 @@ activate_locked:
 keep_locked:
 		unlock_page(page);
 keep:
+		reset_reclaim_mode(sc);
+keep_lumpy:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
 
+	/*
+	 * Tag a zone as congested if all the dirty pages encountered were
+	 * backed by a congested BDI. In this case, reclaimers should just
+	 * back off and wait for congestion to clear because further reclaim
+	 * will encounter the same problem
+	 */
+	if (nr_dirty == nr_congested && nr_dirty != 0)
+		zone_set_flag(zone, ZONE_CONGESTED);
+
 	free_page_list(&free_pages);
 
 	list_splice(&ret_pages, page_list);
@@ -962,7 +1044,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		case 0:
 			list_move(&page->lru, dst);
 			mem_cgroup_del_lru(page);
-			nr_taken++;
+			nr_taken += hpage_nr_pages(page);
 			break;
 
 		case -EBUSY:
@@ -1006,7 +1088,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 
 			/* Check that we have not crossed a zone boundary. */
 			if (unlikely(page_zone_id(cursor_page) != zone_id))
-				continue;
+				break;
 
 			/*
 			 * If we don't have enough swap space, reclaiming of
@@ -1014,23 +1096,28 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			 * pointless.
 			 */
 			if (nr_swap_pages <= 0 && PageAnon(cursor_page) &&
-					!PageSwapCache(cursor_page))
-				continue;
+			    !PageSwapCache(cursor_page))
+				break;
 
 			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
 				list_move(&cursor_page->lru, dst);
 				mem_cgroup_del_lru(cursor_page);
-				nr_taken++;
+				nr_taken += hpage_nr_pages(page);
 				nr_lumpy_taken++;
 				if (PageDirty(cursor_page))
 					nr_lumpy_dirty++;
 				scan++;
 			} else {
-				if (mode == ISOLATE_BOTH &&
-						page_count(cursor_page))
-					nr_lumpy_failed++;
+				/* the page is freed already. */
+				if (!page_count(cursor_page))
+					continue;
+				break;
 			}
 		}
+
+		/* If we break out of the loop above, lumpy reclaim failed */
+		if (pfn < end_pfn)
+			nr_lumpy_failed++;
 	}
 
 	*scanned = scan;
@@ -1070,14 +1157,15 @@ static unsigned long clear_active_flags(struct list_head *page_list,
 	struct page *page;
 
 	list_for_each_entry(page, page_list, lru) {
+		int numpages = hpage_nr_pages(page);
 		lru = page_lru_base_type(page);
 		if (PageActive(page)) {
 			lru += LRU_ACTIVE;
 			ClearPageActive(page);
-			nr_active++;
+			nr_active += numpages;
 		}
 		if (count)
-			count[lru]++;
+			count[lru] += numpages;
 	}
 
 	return nr_active;
@@ -1187,7 +1275,8 @@ putback_lru_pages(struct zone *zone, struct scan_control *sc,
 		add_page_to_lru_list(zone, page, lru);
 		if (is_active_lru(lru)) {
 			int file = is_file_lru(lru);
-			reclaim_stat->recent_rotated[file]++;
+			int numpages = hpage_nr_pages(page);
+			reclaim_stat->recent_rotated[file] += numpages;
 		}
 		if (!pagevec_add(&pvec, page)) {
 			spin_unlock_irq(&zone->lru_lock);
@@ -1253,7 +1342,7 @@ static inline bool should_reclaim_stall(unsigned long nr_taken,
 		return false;
 
 	/* Only stall on lumpy reclaim */
-	if (!sc->lumpy_reclaim_mode)
+	if (sc->reclaim_mode & RECLAIM_MODE_SINGLE)
 		return false;
 
 	/* If we have relaimed everything on the isolated list, no stall */
@@ -1286,7 +1375,6 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	unsigned long nr_scanned;
 	unsigned long nr_reclaimed = 0;
 	unsigned long nr_taken;
-	unsigned long nr_active;
 	unsigned long nr_anon;
 	unsigned long nr_file;
 
@@ -1298,15 +1386,15 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 			return SWAP_CLUSTER_MAX;
 	}
 
-
+	set_reclaim_mode(priority, sc, false);
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
 
 	if (scanning_global_lru(sc)) {
 		nr_taken = isolate_pages_global(nr_to_scan,
 			&page_list, &nr_scanned, sc->order,
-			sc->lumpy_reclaim_mode ?
-				ISOLATE_BOTH : ISOLATE_INACTIVE,
+			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
+					ISOLATE_BOTH : ISOLATE_INACTIVE,
 			zone, 0, file);
 		zone->pages_scanned += nr_scanned;
 		if (current_is_kswapd())
@@ -1318,8 +1406,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	} else {
 		nr_taken = mem_cgroup_isolate_pages(nr_to_scan,
 			&page_list, &nr_scanned, sc->order,
-			sc->lumpy_reclaim_mode ?
-				ISOLATE_BOTH : ISOLATE_INACTIVE,
+			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
+					ISOLATE_BOTH : ISOLATE_INACTIVE,
 			zone, sc->mem_cgroup,
 			0, file);
 		/*
@@ -1337,20 +1425,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 
 	spin_unlock_irq(&zone->lru_lock);
 
-	nr_reclaimed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
+	nr_reclaimed = shrink_page_list(&page_list, zone, sc);
 
 	/* Check if we should syncronously wait for writeback */
 	if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
-		congestion_wait(BLK_RW_ASYNC, HZ/10);
-
-		/*
-		 * The attempt at page out may have made some
-		 * of the pages active, mark them inactive again.
-		 */
-		nr_active = clear_active_flags(&page_list, NULL);
-		count_vm_events(PGDEACTIVATE, nr_active);
-
-		nr_reclaimed += shrink_page_list(&page_list, sc, PAGEOUT_IO_SYNC);
+		set_reclaim_mode(priority, sc, true);
+		nr_reclaimed += shrink_page_list(&page_list, zone, sc);
 	}
 
 	local_irq_disable();
@@ -1359,6 +1439,12 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
 
 	putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list);
+
+	trace_mm_vmscan_lru_shrink_inactive(zone->zone_pgdat->node_id,
+		zone_idx(zone),
+		nr_scanned, nr_reclaimed,
+		priority,
+		trace_shrink_flags(file, sc->reclaim_mode));
 	return nr_reclaimed;
 }
 
@@ -1398,7 +1484,7 @@ static void move_active_pages_to_lru(struct zone *zone,
 
 		list_move(&page->lru, &zone->lru[lru].list);
 		mem_cgroup_add_lru_list(page, lru);
-		pgmoved++;
+		pgmoved += hpage_nr_pages(page);
 
 		if (!pagevec_add(&pvec, page) || list_empty(list)) {
 			spin_unlock_irq(&zone->lru_lock);
@@ -1466,7 +1552,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		}
 
 		if (page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
-			nr_rotated++;
+			nr_rotated += hpage_nr_pages(page);
 			/*
 			 * Identify referenced, file-backed active pages and
 			 * give them one more trip around the active list. So
@@ -1506,6 +1592,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	spin_unlock_irq(&zone->lru_lock);
 }
 
+#ifdef CONFIG_SWAP
 static int inactive_anon_is_low_global(struct zone *zone)
 {
 	unsigned long active, inactive;
@@ -1531,12 +1618,26 @@ static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
 {
 	int low;
 
+	/*
+	 * If we don't have swap space, anonymous page deactivation
+	 * is pointless.
+	 */
+	if (!total_swap_pages)
+		return 0;
+
 	if (scanning_global_lru(sc))
 		low = inactive_anon_is_low_global(zone);
 	else
 		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
 	return low;
 }
+#else
+static inline int inactive_anon_is_low(struct zone *zone,
+					struct scan_control *sc)
+{
+	return 0;
+}
+#endif
 
 static int inactive_file_is_low_global(struct zone *zone)
 {
@@ -1721,19 +1822,55 @@ out:
 	}
 }
 
-static void set_lumpy_reclaim_mode(int priority, struct scan_control *sc)
+/*
+ * Reclaim/compaction depends on a number of pages being freed. To avoid
+ * disruption to the system, a small number of order-0 pages continue to be
+ * rotated and reclaimed in the normal fashion. However, by the time we get
+ * back to the allocator and call try_to_compact_zone(), we ensure that
+ * there are enough free pages for it to be likely successful
+ */
+static inline bool should_continue_reclaim(struct zone *zone,
+					unsigned long nr_reclaimed,
+					unsigned long nr_scanned,
+					struct scan_control *sc)
 {
+	unsigned long pages_for_compaction;
+	unsigned long inactive_lru_pages;
+
+	/* If not in reclaim/compaction mode, stop */
+	if (!(sc->reclaim_mode & RECLAIM_MODE_COMPACTION))
+		return false;
+
 	/*
-	 * If we need a large contiguous chunk of memory, or have
-	 * trouble getting a small set of contiguous pages, we
-	 * will reclaim both active and inactive pages.
+	 * If we failed to reclaim and have scanned the full list, stop.
+	 * NOTE: Checking just nr_reclaimed would exit reclaim/compaction far
+	 *       faster but obviously would be less likely to succeed
+	 *       allocation. If this is desirable, use GFP_REPEAT to decide
+	 *       if both reclaimed and scanned should be checked or just
+	 *       reclaimed
 	 */
-	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-		sc->lumpy_reclaim_mode = 1;
-	else if (sc->order && priority < DEF_PRIORITY - 2)
-		sc->lumpy_reclaim_mode = 1;
-	else
-		sc->lumpy_reclaim_mode = 0;
+	if (!nr_reclaimed && !nr_scanned)
+		return false;
+
+	/*
+	 * If we have not reclaimed enough pages for compaction and the
+	 * inactive lists are large enough, continue reclaiming
+	 */
+	pages_for_compaction = (2UL << sc->order);
+	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) +
+				zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	if (sc->nr_reclaimed < pages_for_compaction &&
+			inactive_lru_pages > pages_for_compaction)
+		return true;
+
+	/* If compaction would go ahead or the allocation would succeed, stop */
+	switch (compaction_suitable(zone, sc->order)) {
+	case COMPACT_PARTIAL:
+	case COMPACT_CONTINUE:
+		return false;
+	default:
+		return true;
+	}
 }
 
 /*
@@ -1745,13 +1882,14 @@ static void shrink_zone(int priority, struct zone *zone,
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
 	enum lru_list l;
-	unsigned long nr_reclaimed = sc->nr_reclaimed;
+	unsigned long nr_reclaimed, nr_scanned;
 	unsigned long nr_to_reclaim = sc->nr_to_reclaim;
 
+restart:
+	nr_reclaimed = 0;
+	nr_scanned = sc->nr_scanned;
 	get_scan_count(zone, sc, nr, priority);
 
-	set_lumpy_reclaim_mode(priority, sc);
-
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
@@ -1775,16 +1913,20 @@ static void shrink_zone(int priority, struct zone *zone,
 		if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY)
 			break;
 	}
-
-	sc->nr_reclaimed = nr_reclaimed;
+	sc->nr_reclaimed += nr_reclaimed;
 
 	/*
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0)
+	if (inactive_anon_is_low(zone, sc))
 		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
 
+	/* reclaim/compaction might need reclaim to continue */
+	if (should_continue_reclaim(zone, nr_reclaimed,
+					sc->nr_scanned - nr_scanned, sc))
+		goto restart;
+
 	throttle_vm_writeout(sc->gfp_mask);
 }
 
@@ -1937,21 +2079,17 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 		/* Take a nap, wait for some writeback to complete */
 		if (!sc->hibernation_mode && sc->nr_scanned &&
-		    priority < DEF_PRIORITY - 2)
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
+		    priority < DEF_PRIORITY - 2) {
+			struct zone *preferred_zone;
+
+			first_zones_zonelist(zonelist, gfp_zone(sc->gfp_mask),
+						&cpuset_current_mems_allowed,
+						&preferred_zone);
+			wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/10);
+		}
 	}
 
 out:
-	/*
-	 * Now that we've scanned all the zones at this priority level, note
-	 * that level within the zone so that the next thread which performs
-	 * scanning of this zone will immediately start out at this priority
-	 * level.  This affects only the decision whether or not to bring
-	 * mapped pages onto the inactive list.
-	 */
-	if (priority < 0)
-		priority = 0;
-
 	delayacct_freepages_end();
 	put_mems_allowed();
 
@@ -2063,38 +2201,87 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 }
 #endif
 
+/*
+ * pgdat_balanced is used when checking if a node is balanced for high-order
+ * allocations. Only zones that meet watermarks and are in a zone allowed
+ * by the callers classzone_idx are added to balanced_pages. The total of
+ * balanced pages must be at least 25% of the zones allowed by classzone_idx
+ * for the node to be considered balanced. Forcing all zones to be balanced
+ * for high orders can cause excessive reclaim when there are imbalanced zones.
+ * The choice of 25% is due to
+ *   o a 16M DMA zone that is balanced will not balance a zone on any
+ *     reasonable sized machine
+ *   o On all other machines, the top zone must be at least a reasonable
+ *     precentage of the middle zones. For example, on 32-bit x86, highmem
+ *     would need to be at least 256M for it to be balance a whole node.
+ *     Similarly, on x86-64 the Normal zone would need to be at least 1G
+ *     to balance a node on its own. These seemed like reasonable ratios.
+ */
+static bool pgdat_balanced(pg_data_t *pgdat, unsigned long balanced_pages,
+						int classzone_idx)
+{
+	unsigned long present_pages = 0;
+	int i;
+
+	for (i = 0; i <= classzone_idx; i++)
+		present_pages += pgdat->node_zones[i].present_pages;
+
+	return balanced_pages > (present_pages >> 2);
+}
+
 /* is kswapd sleeping prematurely? */
-static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
+static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
+					int classzone_idx)
 {
 	int i;
+	unsigned long balanced = 0;
+	bool all_zones_ok = true;
 
 	/* If a direct reclaimer woke kswapd within HZ/10, it's premature */
 	if (remaining)
-		return 1;
+		return true;
 
-	/* If after HZ/10, a zone is below the high mark, it's premature */
+	/* Check the watermark levels */
 	for (i = 0; i < pgdat->nr_zones; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
 		if (!populated_zone(zone))
 			continue;
 
-		if (zone->all_unreclaimable)
+		/*
+		 * balance_pgdat() skips over all_unreclaimable after
+		 * DEF_PRIORITY. Effectively, it considers them balanced so
+		 * they must be considered balanced here as well if kswapd
+		 * is to sleep
+		 */
+		if (zone->all_unreclaimable) {
+			balanced += zone->present_pages;
 			continue;
+		}
 
-		if (!zone_watermark_ok(zone, order, high_wmark_pages(zone),
-								0, 0))
-			return 1;
+		if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
+							classzone_idx, 0))
+			all_zones_ok = false;
+		else
+			balanced += zone->present_pages;
 	}
 
-	return 0;
+	/*
+	 * For high-order requests, the balanced zones must contain at least
+	 * 25% of the nodes pages for kswapd to sleep. For order-0, all zones
+	 * must be balanced
+	 */
+	if (order)
+		return pgdat_balanced(pgdat, balanced, classzone_idx);
+	else
+		return !all_zones_ok;
 }
 
 /*
  * For kswapd, balance_pgdat() will work across all this node's zones until
  * they are all at high_wmark_pages(zone).
  *
- * Returns the number of pages which were actually freed.
+ * Returns the final order kswapd was reclaiming at
  *
  * There is special handling here for zones which are full of pinned pages.
  * This can happen if the pages are all mlocked, or if they are all used by
@@ -2111,11 +2298,14 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
  * interoperates with the page allocator fallback scheme to ensure that aging
  * of pages is balanced across the zones.
  */
-static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
+							int *classzone_idx)
 {
 	int all_zones_ok;
+	unsigned long balanced;
 	int priority;
 	int i;
+	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 	unsigned long total_scanned;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct scan_control sc = {
@@ -2138,7 +2328,6 @@ loop_again:
 	count_vm_event(PAGEOUTRUN);
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
-		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 		unsigned long lru_pages = 0;
 		int has_under_min_watermark_zone = 0;
 
@@ -2147,6 +2336,7 @@ loop_again:
 			disable_swap_token();
 
 		all_zones_ok = 1;
+		balanced = 0;
 
 		/*
 		 * Scan in the highmem->dma direction for the highest
@@ -2169,9 +2359,10 @@ loop_again:
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
+				*classzone_idx = i;
 				break;
 			}
 		}
@@ -2194,6 +2385,7 @@ loop_again:
 		 * cause too much scanning of the lower zones.
 		 */
 		for (i = 0; i <= end_zone; i++) {
+			int compaction;
 			struct zone *zone = pgdat->node_zones + i;
 			int nr_slab;
 
@@ -2215,7 +2407,7 @@ loop_again:
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
 			 */
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					8*high_wmark_pages(zone), end_zone, 0))
 				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
@@ -2223,9 +2415,26 @@ loop_again:
 						lru_pages);
 			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
+
+			compaction = 0;
+			if (order &&
+			    zone_watermark_ok(zone, 0,
+					       high_wmark_pages(zone),
+					      end_zone, 0) &&
+			    !zone_watermark_ok(zone, order,
+					       high_wmark_pages(zone),
+					       end_zone, 0)) {
+				compact_zone_order(zone,
+						   order,
+						   sc.gfp_mask, false,
+						   COMPACT_MODE_KSWAPD);
+				compaction = 1;
+			}
+
 			if (zone->all_unreclaimable)
 				continue;
-			if (nr_slab == 0 && !zone_reclaimable(zone))
+			if (!compaction && nr_slab == 0 &&
+			    !zone_reclaimable(zone))
 				zone->all_unreclaimable = 1;
 			/*
 			 * If we've done a decent amount of scanning and
@@ -2236,7 +2445,7 @@ loop_again:
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 
-			if (!zone_watermark_ok(zone, order,
+			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
 				/*
@@ -2244,13 +2453,24 @@ loop_again:
 				 * means that we have a GFP_ATOMIC allocation
 				 * failure risk. Hurry up!
 				 */
-				if (!zone_watermark_ok(zone, order,
+				if (!zone_watermark_ok_safe(zone, order,
 					    min_wmark_pages(zone), end_zone, 0))
 					has_under_min_watermark_zone = 1;
+			} else {
+				/*
+				 * If a zone reaches its high watermark,
+				 * consider it to be no longer congested. It's
+				 * possible there are dirty pages backed by
+				 * congested BDIs but as pressure is relieved,
+				 * spectulatively avoid congestion waits
+				 */
+				zone_clear_flag(zone, ZONE_CONGESTED);
+				if (i <= *classzone_idx)
+					balanced += zone->present_pages;
 			}
 
 		}
-		if (all_zones_ok)
+		if (all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))
 			break;		/* kswapd: all done */
 		/*
 		 * OK, kswapd is getting into trouble.  Take a nap, then take
@@ -2273,7 +2493,13 @@ loop_again:
 			break;
 	}
 out:
-	if (!all_zones_ok) {
+
+	/*
+	 * order-0: All zones must meet high watermark for a balanced node
+	 * high-order: Balanced zones must make up at least 25% of the node
+	 *             for the node to be balanced
+	 */
+	if (!(all_zones_ok || (order && pgdat_balanced(pgdat, balanced, *classzone_idx)))) {
 		cond_resched();
 
 		try_to_freeze();
@@ -2298,7 +2524,88 @@ out:
 		goto loop_again;
 	}
 
-	return sc.nr_reclaimed;
+	/*
+	 * If kswapd was reclaiming at a higher order, it has the option of
+	 * sleeping without all zones being balanced. Before it does, it must
+	 * ensure that the watermarks for order-0 on *all* zones are met and
+	 * that the congestion flags are cleared. The congestion flag must
+	 * be cleared as kswapd is the only mechanism that clears the flag
+	 * and it is potentially going to sleep here.
+	 */
+	if (order) {
+		for (i = 0; i <= end_zone; i++) {
+			struct zone *zone = pgdat->node_zones + i;
+
+			if (!populated_zone(zone))
+				continue;
+
+			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+				continue;
+
+			/* Confirm the zone is balanced for order-0 */
+			if (!zone_watermark_ok(zone, 0,
+					high_wmark_pages(zone), 0, 0)) {
+				order = sc.order = 0;
+				goto loop_again;
+			}
+
+			/* If balanced, clear the congested flag */
+			zone_clear_flag(zone, ZONE_CONGESTED);
+		}
+	}
+
+	/*
+	 * Return the order we were reclaiming at so sleeping_prematurely()
+	 * makes a decision on the order we were last reclaiming at. However,
+	 * if another caller entered the allocator slow path while kswapd
+	 * was awake, order will remain at the higher level
+	 */
+	*classzone_idx = end_zone;
+	return order;
+}
+
+static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
+{
+	long remaining = 0;
+	DEFINE_WAIT(wait);
+
+	if (freezing(current) || kthread_should_stop())
+		return;
+
+	prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+
+	/* Try to sleep for a short interval */
+	if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+		remaining = schedule_timeout(HZ/10);
+		finish_wait(&pgdat->kswapd_wait, &wait);
+		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
+	}
+
+	/*
+	 * After a short sleep, check if it was a premature sleep. If not, then
+	 * go fully to sleep until explicitly woken up.
+	 */
+	if (!sleeping_prematurely(pgdat, order, remaining, classzone_idx)) {
+		trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
+
+		/*
+		 * vmstat counters are not perfectly accurate and the estimated
+		 * value for counters such as NR_FREE_PAGES can deviate from the
+		 * true value by nr_online_cpus * threshold. To avoid the zone
+		 * watermarks being breached while under pressure, we reduce the
+		 * per-cpu vmstat threshold while kswapd is awake and restore
+		 * them before going back to sleep.
+		 */
+		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
+		schedule();
+		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
+	} else {
+		if (remaining)
+			count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
+		else
+			count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
+	}
+	finish_wait(&pgdat->kswapd_wait, &wait);
 }
 
 /*
@@ -2317,9 +2624,10 @@ out:
 static int kswapd(void *p)
 {
 	unsigned long order;
+	int classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
-	DEFINE_WAIT(wait);
+
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
@@ -2347,49 +2655,30 @@ static int kswapd(void *p)
 	set_freezable();
 
 	order = 0;
+	classzone_idx = MAX_NR_ZONES - 1;
 	for ( ; ; ) {
 		unsigned long new_order;
+		int new_classzone_idx;
 		int ret;
 
-		prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
 		new_order = pgdat->kswapd_max_order;
+		new_classzone_idx = pgdat->classzone_idx;
 		pgdat->kswapd_max_order = 0;
-		if (order < new_order) {
+		pgdat->classzone_idx = MAX_NR_ZONES - 1;
+		if (order < new_order || classzone_idx > new_classzone_idx) {
 			/*
 			 * Don't sleep if someone wants a larger 'order'
-			 * allocation
+			 * allocation or has tigher zone constraints
 			 */
 			order = new_order;
+			classzone_idx = new_classzone_idx;
 		} else {
-			if (!freezing(current) && !kthread_should_stop()) {
-				long remaining = 0;
-
-				/* Try to sleep for a short interval */
-				if (!sleeping_prematurely(pgdat, order, remaining)) {
-					remaining = schedule_timeout(HZ/10);
-					finish_wait(&pgdat->kswapd_wait, &wait);
-					prepare_to_wait(&pgdat->kswapd_wait, &wait, TASK_INTERRUPTIBLE);
-				}
-
-				/*
-				 * After a short sleep, check if it was a
-				 * premature sleep. If not, then go fully
-				 * to sleep until explicitly woken up
-				 */
-				if (!sleeping_prematurely(pgdat, order, remaining)) {
-					trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
-					schedule();
-				} else {
-					if (remaining)
-						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
-					else
-						count_vm_event(KSWAPD_HIGH_WMARK_HIT_QUICKLY);
-				}
-			}
-
+			kswapd_try_to_sleep(pgdat, order, classzone_idx);
 			order = pgdat->kswapd_max_order;
+			classzone_idx = pgdat->classzone_idx;
+			pgdat->kswapd_max_order = 0;
+			pgdat->classzone_idx = MAX_NR_ZONES - 1;
 		}
-		finish_wait(&pgdat->kswapd_wait, &wait);
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -2401,7 +2690,7 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			balance_pgdat(pgdat, order);
+			order = balance_pgdat(pgdat, order, &classzone_idx);
 		}
 	}
 	return 0;
@@ -2410,23 +2699,26 @@ static int kswapd(void *p)
 /*
  * A zone is low on free memory, so wake its kswapd task to service it.
  */
-void wakeup_kswapd(struct zone *zone, int order)
+void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
 
 	if (!populated_zone(zone))
 		return;
 
-	pgdat = zone->zone_pgdat;
-	if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
-		return;
-	if (pgdat->kswapd_max_order < order)
-		pgdat->kswapd_max_order = order;
-	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 		return;
+	pgdat = zone->zone_pgdat;
+	if (pgdat->kswapd_max_order < order) {
+		pgdat->kswapd_max_order = order;
+		pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
+	}
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
+	if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))
+		return;
+
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
@@ -2987,6 +3279,7 @@ int scan_unevictable_handler(struct ctl_table *table, int write,
 	return 0;
 }
 
+#ifdef CONFIG_NUMA
 /*
  * per node 'scan_unevictable_pages' attribute.  On demand re-scan of
  * a specified node's per zone unevictable lists for evictable pages.
@@ -3033,4 +3326,4 @@ void scan_unevictable_unregister_node(struct node *node)
 {
 	sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
 }
-
+#endif
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 355a9e669aaa..0c3b5048773e 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -17,6 +17,8 @@
 #include <linux/vmstat.h>
 #include <linux/sched.h>
 #include <linux/math64.h>
+#include <linux/writeback.h>
+#include <linux/compaction.h>
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 DEFINE_PER_CPU(struct vm_event_state, vm_event_states) = {{0}};
@@ -81,7 +83,31 @@ EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP
 
-static int calculate_threshold(struct zone *zone)
+int calculate_pressure_threshold(struct zone *zone)
+{
+	int threshold;
+	int watermark_distance;
+
+	/*
+	 * As vmstats are not up to date, there is drift between the estimated
+	 * and real values. For high thresholds and a high number of CPUs, it
+	 * is possible for the min watermark to be breached while the estimated
+	 * value looks fine. The pressure threshold is a reduced value such
+	 * that even the maximum amount of drift will not accidentally breach
+	 * the min watermark
+	 */
+	watermark_distance = low_wmark_pages(zone) - min_wmark_pages(zone);
+	threshold = max(1, (int)(watermark_distance / num_online_cpus()));
+
+	/*
+	 * Maximum threshold is 125
+	 */
+	threshold = min(125, threshold);
+
+	return threshold;
+}
+
+int calculate_normal_threshold(struct zone *zone)
 {
 	int threshold;
 	int mem;	/* memory in 128 MB units */
@@ -140,7 +166,7 @@ static void refresh_zone_stat_thresholds(void)
 	for_each_populated_zone(zone) {
 		unsigned long max_drift, tolerate_drift;
 
-		threshold = calculate_threshold(zone);
+		threshold = calculate_normal_threshold(zone);
 
 		for_each_online_cpu(cpu)
 			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
@@ -159,42 +185,50 @@ static void refresh_zone_stat_thresholds(void)
 	}
 }
 
+void set_pgdat_percpu_threshold(pg_data_t *pgdat,
+				int (*calculate_pressure)(struct zone *))
+{
+	struct zone *zone;
+	int cpu;
+	int threshold;
+	int i;
+
+	for (i = 0; i < pgdat->nr_zones; i++) {
+		zone = &pgdat->node_zones[i];
+		if (!zone->percpu_drift_mark)
+			continue;
+
+		threshold = (*calculate_pressure)(zone);
+		for_each_possible_cpu(cpu)
+			per_cpu_ptr(zone->pageset, cpu)->stat_threshold
+							= threshold;
+	}
+}
+
 /*
  * For use when we know that interrupts are disabled.
  */
 void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
 				int delta)
 {
-	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-
-	s8 *p = pcp->vm_stat_diff + item;
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
 	long x;
+	long t;
+
+	x = delta + __this_cpu_read(*p);
 
-	x = delta + *p;
+	t = __this_cpu_read(pcp->stat_threshold);
 
-	if (unlikely(x > pcp->stat_threshold || x < -pcp->stat_threshold)) {
+	if (unlikely(x > t || x < -t)) {
 		zone_page_state_add(x, zone, item);
 		x = 0;
 	}
-	*p = x;
+	__this_cpu_write(*p, x);
 }
 EXPORT_SYMBOL(__mod_zone_page_state);
 
 /*
- * For an unknown interrupt state
- */
-void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
-					int delta)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_zone_page_state(zone, item, delta);
-	local_irq_restore(flags);
-}
-EXPORT_SYMBOL(mod_zone_page_state);
-
-/*
  * Optimized increment and decrement functions.
  *
  * These are only for a single page and therefore can take a struct page *
@@ -219,16 +253,17 @@ EXPORT_SYMBOL(mod_zone_page_state);
  */
 void __inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-	s8 *p = pcp->vm_stat_diff + item;
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
+	s8 v, t;
 
-	(*p)++;
+	v = __this_cpu_inc_return(*p);
+	t = __this_cpu_read(pcp->stat_threshold);
+	if (unlikely(v > t)) {
+		s8 overstep = t >> 1;
 
-	if (unlikely(*p > pcp->stat_threshold)) {
-		int overstep = pcp->stat_threshold / 2;
-
-		zone_page_state_add(*p + overstep, zone, item);
-		*p = -overstep;
+		zone_page_state_add(v + overstep, zone, item);
+		__this_cpu_write(*p, -overstep);
 	}
 }
 
@@ -240,16 +275,17 @@ EXPORT_SYMBOL(__inc_zone_page_state);
 
 void __dec_zone_state(struct zone *zone, enum zone_stat_item item)
 {
-	struct per_cpu_pageset *pcp = this_cpu_ptr(zone->pageset);
-	s8 *p = pcp->vm_stat_diff + item;
-
-	(*p)--;
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
+	s8 v, t;
 
-	if (unlikely(*p < - pcp->stat_threshold)) {
-		int overstep = pcp->stat_threshold / 2;
+	v = __this_cpu_dec_return(*p);
+	t = __this_cpu_read(pcp->stat_threshold);
+	if (unlikely(v < - t)) {
+		s8 overstep = t >> 1;
 
-		zone_page_state_add(*p - overstep, zone, item);
-		*p = overstep;
+		zone_page_state_add(v - overstep, zone, item);
+		__this_cpu_write(*p, overstep);
 	}
 }
 
@@ -259,6 +295,92 @@ void __dec_zone_page_state(struct page *page, enum zone_stat_item item)
 }
 EXPORT_SYMBOL(__dec_zone_page_state);
 
+#ifdef CONFIG_CMPXCHG_LOCAL
+/*
+ * If we have cmpxchg_local support then we do not need to incur the overhead
+ * that comes with local_irq_save/restore if we use this_cpu_cmpxchg.
+ *
+ * mod_state() modifies the zone counter state through atomic per cpu
+ * operations.
+ *
+ * Overstep mode specifies how overstep should handled:
+ *     0       No overstepping
+ *     1       Overstepping half of threshold
+ *     -1      Overstepping minus half of threshold
+*/
+static inline void mod_state(struct zone *zone,
+       enum zone_stat_item item, int delta, int overstep_mode)
+{
+	struct per_cpu_pageset __percpu *pcp = zone->pageset;
+	s8 __percpu *p = pcp->vm_stat_diff + item;
+	long o, n, t, z;
+
+	do {
+		z = 0;  /* overflow to zone counters */
+
+		/*
+		 * The fetching of the stat_threshold is racy. We may apply
+		 * a counter threshold to the wrong the cpu if we get
+		 * rescheduled while executing here. However, the following
+		 * will apply the threshold again and therefore bring the
+		 * counter under the threshold.
+		 */
+		t = this_cpu_read(pcp->stat_threshold);
+
+		o = this_cpu_read(*p);
+		n = delta + o;
+
+		if (n > t || n < -t) {
+			int os = overstep_mode * (t >> 1) ;
+
+			/* Overflow must be added to zone counters */
+			z = n + os;
+			n = -os;
+		}
+	} while (this_cpu_cmpxchg(*p, o, n) != o);
+
+	if (z)
+		zone_page_state_add(z, zone, item);
+}
+
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+					int delta)
+{
+	mod_state(zone, item, delta, 0);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
+void inc_zone_state(struct zone *zone, enum zone_stat_item item)
+{
+	mod_state(zone, item, 1, 1);
+}
+
+void inc_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+	mod_state(page_zone(page), item, 1, 1);
+}
+EXPORT_SYMBOL(inc_zone_page_state);
+
+void dec_zone_page_state(struct page *page, enum zone_stat_item item)
+{
+	mod_state(page_zone(page), item, -1, -1);
+}
+EXPORT_SYMBOL(dec_zone_page_state);
+#else
+/*
+ * Use interrupt disable to serialize counter updates
+ */
+void mod_zone_page_state(struct zone *zone, enum zone_stat_item item,
+					int delta)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	__mod_zone_page_state(zone, item, delta);
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL(mod_zone_page_state);
+
 void inc_zone_state(struct zone *zone, enum zone_stat_item item)
 {
 	unsigned long flags;
@@ -289,6 +411,7 @@ void dec_zone_page_state(struct page *page, enum zone_stat_item item)
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL(dec_zone_page_state);
+#endif
 
 /*
  * Update the zone counters for one cpu.
@@ -394,6 +517,7 @@ void zone_statistics(struct zone *preferred_zone, struct zone *z)
 #endif
 
 #ifdef CONFIG_COMPACTION
+
 struct contig_page_info {
 	unsigned long free_pages;
 	unsigned long free_blocks_total;
@@ -745,6 +869,9 @@ static const char * const vmstat_text[] = {
 	"nr_isolated_anon",
 	"nr_isolated_file",
 	"nr_shmem",
+	"nr_dirtied",
+	"nr_written",
+
 #ifdef CONFIG_NUMA
 	"numa_hit",
 	"numa_miss",
@@ -753,6 +880,9 @@ static const char * const vmstat_text[] = {
 	"numa_local",
 	"numa_other",
 #endif
+	"nr_anon_transparent_hugepages",
+	"nr_dirty_threshold",
+	"nr_dirty_background_threshold",
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
 	"pgpgin",
@@ -826,7 +956,7 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        scanned  %lu"
 		   "\n        spanned  %lu"
 		   "\n        present  %lu",
-		   zone_nr_free_pages(zone),
+		   zone_page_state(zone, NR_FREE_PAGES),
 		   min_wmark_pages(zone),
 		   low_wmark_pages(zone),
 		   high_wmark_pages(zone),
@@ -904,36 +1034,44 @@ static const struct file_operations proc_zoneinfo_file_operations = {
 	.release	= seq_release,
 };
 
+enum writeback_stat_item {
+	NR_DIRTY_THRESHOLD,
+	NR_DIRTY_BG_THRESHOLD,
+	NR_VM_WRITEBACK_STAT_ITEMS,
+};
+
 static void *vmstat_start(struct seq_file *m, loff_t *pos)
 {
 	unsigned long *v;
-#ifdef CONFIG_VM_EVENT_COUNTERS
-	unsigned long *e;
-#endif
-	int i;
+	int i, stat_items_size;
 
 	if (*pos >= ARRAY_SIZE(vmstat_text))
 		return NULL;
+	stat_items_size = NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long) +
+			  NR_VM_WRITEBACK_STAT_ITEMS * sizeof(unsigned long);
 
 #ifdef CONFIG_VM_EVENT_COUNTERS
-	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long)
-			+ sizeof(struct vm_event_state), GFP_KERNEL);
-#else
-	v = kmalloc(NR_VM_ZONE_STAT_ITEMS * sizeof(unsigned long),
-			GFP_KERNEL);
+	stat_items_size += sizeof(struct vm_event_state);
 #endif
+
+	v = kmalloc(stat_items_size, GFP_KERNEL);
 	m->private = v;
 	if (!v)
 		return ERR_PTR(-ENOMEM);
 	for (i = 0; i < NR_VM_ZONE_STAT_ITEMS; i++)
 		v[i] = global_page_state(i);
+	v += NR_VM_ZONE_STAT_ITEMS;
+
+	global_dirty_limits(v + NR_DIRTY_BG_THRESHOLD,
+			    v + NR_DIRTY_THRESHOLD);
+	v += NR_VM_WRITEBACK_STAT_ITEMS;
+
 #ifdef CONFIG_VM_EVENT_COUNTERS
-	e = v + NR_VM_ZONE_STAT_ITEMS;
-	all_vm_events(e);
-	e[PGPGIN] /= 2;		/* sectors -> kbytes */
-	e[PGPGOUT] /= 2;
+	all_vm_events(v);
+	v[PGPGIN] /= 2;		/* sectors -> kbytes */
+	v[PGPGOUT] /= 2;
 #endif
-	return v + *pos;
+	return (unsigned long *)m->private + *pos;
 }
 
 static void *vmstat_next(struct seq_file *m, void *arg, loff_t *pos)
@@ -1017,7 +1155,7 @@ static int __cpuinit vmstat_cpuup_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DOWN_PREPARE:
 	case CPU_DOWN_PREPARE_FROZEN:
-		cancel_rearming_delayed_work(&per_cpu(vmstat_work, cpu));
+		cancel_delayed_work_sync(&per_cpu(vmstat_work, cpu));
 		per_cpu(vmstat_work, cpu).work.func = NULL;
 		break;
 	case CPU_DOWN_FAILED: