44 files changed, 4508 insertions, 1010 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index c2c8a4a1189..3ad483bdf50 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -302,6 +302,44 @@ config NOMMU_INITIAL_TRIM_EXCESS
 
 	  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
 #
diff --git a/mm/Makefile b/mm/Makefile
index f73f75a29f8..2b1b575ae71 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -5,7 +5,7 @@
 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 \
@@ -37,6 +37,7 @@ obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_FS_XIP) += filemap_xip.o
 obj-$(CONFIG_MIGRATION) += migrate.o
 obj-$(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/compaction.c b/mm/compaction.c
index 1a8894eadf7..6d592a02107 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 */
@@ -266,20 +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);
 		cc->nr_migratepages++;
+		nr_isolated++;
 
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
@@ -291,6 +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;
 }
 
@@ -341,10 +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;
@@ -354,12 +397,27 @@ 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;
 
 	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 */
@@ -374,10 +432,62 @@ 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;
+
+	/*
+	 * 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;
@@ -393,7 +503,8 @@ 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;
 
@@ -401,6 +512,8 @@ 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)) {
@@ -417,8 +530,10 @@ 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,
@@ -426,6 +541,8 @@ 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);
@@ -441,16 +558,17 @@ 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;
@@ -460,7 +578,7 @@ 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);
@@ -468,43 +586,14 @@ 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;
 	}
 
@@ -531,6 +620,7 @@ 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 4df2de77e06..03bf3bb4519 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -324,7 +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);
 
@@ -355,20 +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;
 }
 
 /**
@@ -386,8 +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",
@@ -401,6 +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",
@@ -418,6 +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,
@@ -432,7 +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 6b9aee20f24..83a45d35468 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
@@ -301,7 +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);
@@ -840,9 +837,6 @@ repeat:
 		if (radix_tree_deref_retry(page))
 			goto restart;
 
-		if (page->mapping == NULL || page->index != index)
-			break;
-
 		if (!page_cache_get_speculative(page))
 			goto repeat;
 
@@ -852,6 +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++;
@@ -2223,7 +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/huge_memory.c b/mm/huge_memory.c
new file mode 100644
index 00000000000..004c9c2aac7
--- /dev/null
+++ b/mm/huge_memory.c
@@ -0,0 +1,2346 @@
+/*
+ *  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 *kob