Merge branch 'master' into for-linus

Conflicts:
	fs/pipe.c

Signed-off-by: Jens Axboe <jaxboe@fusionio.com>

27 files changed, 2574 insertions, 761 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index 9c61158308dc..527136b22384 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -172,6 +172,15 @@ config SPLIT_PTLOCK_CPUS
 	default "4"
 
 #
+# support for memory compaction
+config COMPACTION
+	bool "Allow for memory compaction"
+	select MIGRATION
+	depends on EXPERIMENTAL && HUGETLB_PAGE && MMU
+	help
+	  Allows the compaction of memory for the allocation of huge pages.
+
+#
 # support for page migration
 #
 config MIGRATION
@@ -180,9 +189,11 @@ config MIGRATION
 	depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE
 	help
 	  Allows the migration of the physical location of pages of processes
-	  while the virtual addresses are not changed. This is useful for
-	  example on NUMA systems to put pages nearer to the processors accessing
-	  the page.
+	  while the virtual addresses are not changed. This is useful in
+	  two situations. The first is on NUMA systems to put pages nearer
+	  to the processors accessing. The second is when allocating huge
+	  pages as migration can relocate pages to satisfy a huge page
+	  allocation instead of reclaiming.
 
 config PHYS_ADDR_T_64BIT
 	def_bool 64BIT || ARCH_PHYS_ADDR_T_64BIT
diff --git a/mm/Makefile b/mm/Makefile
index 6c2a73a54a43..8982504bd03b 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
 obj-$(CONFIG_SLOB) += slob.o
+obj-$(CONFIG_COMPACTION) += compaction.o
 obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
 obj-$(CONFIG_KSM) += ksm.o
 obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
diff --git a/mm/compaction.c b/mm/compaction.c
new file mode 100644
index 000000000000..94cce51b0b35
--- /dev/null
+++ b/mm/compaction.c
@@ -0,0 +1,605 @@
+/*
+ * linux/mm/compaction.c
+ *
+ * Memory compaction for the reduction of external fragmentation. Note that
+ * this heavily depends upon page migration to do all the real heavy
+ * lifting
+ *
+ * Copyright IBM Corp. 2007-2010 Mel Gorman <mel@csn.ul.ie>
+ */
+#include <linux/swap.h>
+#include <linux/migrate.h>
+#include <linux/compaction.h>
+#include <linux/mm_inline.h>
+#include <linux/backing-dev.h>
+#include <linux/sysctl.h>
+#include <linux/sysfs.h>
+#include "internal.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
+ * at the end of a zone and migrate_pfn begins at the start. Movable pages
+ * are moved to the end of a zone during a compaction run and the run
+ * completes when free_pfn <= migrate_pfn
+ */
+struct compact_control {
+	struct list_head freepages;	/* List of free pages to migrate to */
+	struct list_head migratepages;	/* List of pages being migrated */
+	unsigned long nr_freepages;	/* Number of isolated free pages */
+	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 */
+
+	/* Account for isolated anon and file pages */
+	unsigned long nr_anon;
+	unsigned long nr_file;
+
+	unsigned int order;		/* order a direct compactor needs */
+	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
+	struct zone *zone;
+};
+
+static unsigned long release_freepages(struct list_head *freelist)
+{
+	struct page *page, *next;
+	unsigned long count = 0;
+
+	list_for_each_entry_safe(page, next, freelist, lru) {
+		list_del(&page->lru);
+		__free_page(page);
+		count++;
+	}
+
+	return count;
+}
+
+/* Isolate free pages onto a private freelist. Must hold zone->lock */
+static unsigned long isolate_freepages_block(struct zone *zone,
+				unsigned long blockpfn,
+				struct list_head *freelist)
+{
+	unsigned long zone_end_pfn, end_pfn;
+	int total_isolated = 0;
+	struct page *cursor;
+
+	/* Get the last PFN we should scan for free pages at */
+	zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
+	end_pfn = min(blockpfn + pageblock_nr_pages, zone_end_pfn);
+
+	/* Find the first usable PFN in the block to initialse page cursor */
+	for (; blockpfn < end_pfn; blockpfn++) {
+		if (pfn_valid_within(blockpfn))
+			break;
+	}
+	cursor = pfn_to_page(blockpfn);
+
+	/* Isolate free pages. This assumes the block is valid */
+	for (; blockpfn < end_pfn; blockpfn++, cursor++) {
+		int isolated, i;
+		struct page *page = cursor;
+
+		if (!pfn_valid_within(blockpfn))
+			continue;
+
+		if (!PageBuddy(page))
+			continue;
+
+		/* Found a free page, break it into order-0 pages */
+		isolated = split_free_page(page);
+		total_isolated += isolated;
+		for (i = 0; i < isolated; i++) {
+			list_add(&page->lru, freelist);
+			page++;
+		}
+
+		/* If a page was split, advance to the end of it */
+		if (isolated) {
+			blockpfn += isolated - 1;
+			cursor += isolated - 1;
+		}
+	}
+
+	return total_isolated;
+}
+
+/* Returns true if the page is within a block suitable for migration to */
+static bool suitable_migration_target(struct page *page)
+{
+
+	int migratetype = get_pageblock_migratetype(page);
+
+	/* Don't interfere with memory hot-remove or the min_free_kbytes blocks */
+	if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE)
+		return false;
+
+	/* If the page is a large free page, then allow migration */
+	if (PageBuddy(page) && page_order(page) >= pageblock_order)
+		return true;
+
+	/* If the block is MIGRATE_MOVABLE, allow migration */
+	if (migratetype == MIGRATE_MOVABLE)
+		return true;
+
+	/* Otherwise skip the block */
+	return false;
+}
+
+/*
+ * Based on information in the current compact_control, find blocks
+ * suitable for isolating free pages from and then isolate them.
+ */
+static void isolate_freepages(struct zone *zone,
+				struct compact_control *cc)
+{
+	struct page *page;
+	unsigned long high_pfn, low_pfn, pfn;
+	unsigned long flags;
+	int nr_freepages = cc->nr_freepages;
+	struct list_head *freelist = &cc->freepages;
+
+	pfn = cc->free_pfn;
+	low_pfn = cc->migrate_pfn + pageblock_nr_pages;
+	high_pfn = low_pfn;
+
+	/*
+	 * Isolate free pages until enough are available to migrate the
+	 * pages on cc->migratepages. We stop searching if the migrate
+	 * and free page scanners meet or enough free pages are isolated.
+	 */
+	spin_lock_irqsave(&zone->lock, flags);
+	for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages;
+					pfn -= pageblock_nr_pages) {
+		unsigned long isolated;
+
+		if (!pfn_valid(pfn))
+			continue;
+
+		/*
+		 * Check for overlapping nodes/zones. It's possible on some
+		 * configurations to have a setup like
+		 * node0 node1 node0
+		 * i.e. it's possible that all pages within a zones range of
+		 * pages do not belong to a single zone.
+		 */
+		page = pfn_to_page(pfn);
+		if (page_zone(page) != zone)
+			continue;
+
+		/* Check the block is suitable for migration */
+		if (!suitable_migration_target(page))
+			continue;
+
+		/* Found a block suitable for isolating free pages from */
+		isolated = isolate_freepages_block(zone, pfn, freelist);
+		nr_freepages += isolated;
+
+		/*
+		 * Record the highest PFN we isolated pages from. When next
+		 * looking for free pages, the search will restart here as
+		 * page migration may have returned some pages to the allocator
+		 */
+		if (isolated)
+			high_pfn = max(high_pfn, pfn);
+	}
+	spin_unlock_irqrestore(&zone->lock, flags);
+
+	/* split_free_page does not map the pages */
+	list_for_each_entry(page, freelist, lru) {
+		arch_alloc_page(page, 0);
+		kernel_map_pages(page, 1, 1);
+	}
+
+	cc->free_pfn = high_pfn;
+	cc->nr_freepages = nr_freepages;
+}
+
+/* Update the number of anon and file isolated pages in the zone */
+static void acct_isolated(struct zone *zone, struct compact_control *cc)
+{
+	struct page *page;
+	unsigned int count[NR_LRU_LISTS] = { 0, };
+
+	list_for_each_entry(page, &cc->migratepages, lru) {
+		int lru = page_lru_base_type(page);
+		count[lru]++;
+	}
+
+	cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
+	cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file);
+}
+
+/* Similar to reclaim, but different enough that they don't share logic */
+static bool too_many_isolated(struct zone *zone)
+{
+
+	unsigned long inactive, isolated;
+
+	inactive = zone_page_state(zone, NR_INACTIVE_FILE) +
+					zone_page_state(zone, NR_INACTIVE_ANON);
+	isolated = zone_page_state(zone, NR_ISOLATED_FILE) +
+					zone_page_state(zone, NR_ISOLATED_ANON);
+
+	return isolated > inactive;
+}
+
+/*
+ * Isolate all pages that can be migrated from the block pointed to by
+ * the migrate scanner within compact_control.
+ */
+static unsigned long isolate_migratepages(struct zone *zone,
+					struct compact_control *cc)
+{
+	unsigned long low_pfn, end_pfn;
+	struct list_head *migratelist = &cc->migratepages;
+
+	/* Do not scan outside zone boundaries */
+	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
+
+	/* Only scan within a pageblock boundary */
+	end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages);
+
+	/* Do not cross the free scanner or scan within a memory hole */
+	if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) {
+		cc->migrate_pfn = end_pfn;
+		return 0;
+	}
+
+	/*
+	 * Ensure that there are not too many pages isolated from the LRU
+	 * list by either parallel reclaimers or compaction. If there are,
+	 * delay for some time until fewer pages are isolated
+	 */
+	while (unlikely(too_many_isolated(zone))) {
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
+
+		if (fatal_signal_pending(current))
+			return 0;
+	}
+
+	/* Time to isolate some pages for migration */
+	spin_lock_irq(&zone->lru_lock);
+	for (; low_pfn < end_pfn; low_pfn++) {
+		struct page *page;
+		if (!pfn_valid_within(low_pfn))
+			continue;
+
+		/* Get the page and skip if free */
+		page = pfn_to_page(low_pfn);
+		if (PageBuddy(page))
+			continue;
+
+		/* Try isolate the page */
+		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
+			continue;
+
+		/* 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++;
+
+		/* Avoid isolating too much */
+		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX)
+			break;
+	}
+
+	acct_isolated(zone, cc);
+
+	spin_unlock_irq(&zone->lru_lock);
+	cc->migrate_pfn = low_pfn;
+
+	return cc->nr_migratepages;
+}
+
+/*
+ * This is a migrate-callback that "allocates" freepages by taking pages
+ * from the isolated freelists in the block we are migrating to.
+ */
+static struct page *compaction_alloc(struct page *migratepage,
+					unsigned long data,
+					int **result)
+{
+	struct compact_control *cc = (struct compact_control *)data;
+	struct page *freepage;
+
+	/* Isolate free pages if necessary */
+	if (list_empty(&cc->freepages)) {
+		isolate_freepages(cc->zone, cc);
+
+		if (list_empty(&cc->freepages))
+			return NULL;
+	}
+
+	freepage = list_entry(cc->freepages.next, struct page, lru);
+	list_del(&freepage->lru);
+	cc->nr_freepages--;
+
+	return freepage;
+}
+
+/*
+ * We cannot control nr_migratepages and nr_freepages fully when migration is
+ * running as migrate_pages() has no knowledge of compact_control. When
+ * migration is complete, we count the number of pages on the lists by hand.
+ */
+static void update_nr_listpages(struct compact_control *cc)
+{
+	int nr_migratepages = 0;
+	int nr_freepages = 0;
+	struct page *page;
+
+	list_for_each_entry(page, &cc->migratepages, lru)
+		nr_migratepages++;
+	list_for_each_entry(page, &cc->freepages, lru)
+		nr_freepages++;
+
+	cc->nr_migratepages = nr_migratepages;
+	cc->nr_freepages = nr_freepages;
+}
+
+static int compact_finished(struct zone *zone,
+						struct compact_control *cc)
+{
+	unsigned int order;
+	unsigned long watermark = low_wmark_pages(zone) + (1 << cc->order);
+
+	if (fatal_signal_pending(current))
+		return COMPACT_PARTIAL;
+
+	/* Compaction run completes if the migrate and free scanner meet */
+	if (cc->free_pfn <= cc->migrate_pfn)
+		return COMPACT_COMPLETE;
+
+	/* Compaction run is not finished if the watermark is not met */
+	if (!zone_watermark_ok(zone, cc->order, watermark, 0, 0))
+		return COMPACT_CONTINUE;
+
+	if (cc->order == -1)
+		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 */
+		if (!list_empty(&zone->free_area[order].free_list[cc->migratetype]))
+			return COMPACT_PARTIAL;
+
+		/* Job done if allocation would set block type */
+		if (order >= pageblock_order && zone->free_area[order].nr_free)
+			return COMPACT_PARTIAL;
+	}
+
+	return COMPACT_CONTINUE;
+}
+
+static int compact_zone(struct zone *zone, struct compact_control *cc)
+{
+	int ret;
+
+	/* 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;
+	cc->free_pfn &= ~(pageblock_nr_pages-1);
+
+	migrate_prep_local();
+
+	while ((ret = compact_finished(zone, cc)) == COMPACT_CONTINUE) {
+		unsigned long nr_migrate, nr_remaining;
+
+		if (!isolate_migratepages(zone, cc))
+			continue;
+
+		nr_migrate = cc->nr_migratepages;
+		migrate_pages(&cc->migratepages, compaction_alloc,
+						(unsigned long)cc, 0);
+		update_nr_listpages(cc);
+		nr_remaining = cc->nr_migratepages;
+
+		count_vm_event(COMPACTBLOCKS);
+		count_vm_events(COMPACTPAGES, nr_migrate - nr_remaining);
+		if (nr_remaining)
+			count_vm_events(COMPACTPAGEFAILED, nr_remaining);
+
+		/* Release LRU pages not migrated */
+		if (!list_empty(&cc->migratepages)) {
+			putback_lru_pages(&cc->migratepages);
+			cc->nr_migratepages = 0;
+		}
+
+	}
+
+	/* Release free pages and check accounting */
+	cc->nr_freepages -= release_freepages(&cc->freepages);
+	VM_BUG_ON(cc->nr_freepages != 0);
+
+	return ret;
+}
+
+static unsigned long compact_zone_order(struct zone *zone,
+						int order, gfp_t gfp_mask)
+{
+	struct compact_control cc = {
+		.nr_freepages = 0,
+		.nr_migratepages = 0,
+		.order = order,
+		.migratetype = allocflags_to_migratetype(gfp_mask),
+		.zone = zone,
+	};
+	INIT_LIST_HEAD(&cc.freepages);
+	INIT_LIST_HEAD(&cc.migratepages);
+
+	return compact_zone(zone, &cc);
+}
+
+int sysctl_extfrag_threshold = 500;
+
+/**
+ * try_to_compact_pages - Direct compact to satisfy a high-order allocation
+ * @zonelist: The zonelist used for the current allocation
+ * @order: The order of the current allocation
+ * @gfp_mask: The GFP mask of the current allocation
+ * @nodemask: The allowed nodes to allocate from
+ *
+ * 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)
+{
+	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;
+
+	/*
+	 * Check whether it is worth even starting compaction. The order check is
+	 * 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)
+		return rc;
+
+	count_vm_event(COMPACTSTALL);
+
+	/* 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);
+		rc = max(status, rc);
+
+		if (zone_watermark_ok(zone, order, watermark, 0, 0))
+			break;
+	}
+
+	return rc;
+}
+
+
+/* Compact all zones within a node */
+static int compact_node(int nid)
+{
+	int zoneid;
+	pg_data_t *pgdat;
+	struct zone *zone;
+
+	if (nid < 0 || nid >= nr_node_ids || !node_online(nid))
+		return -EINVAL;
+	pgdat = NODE_DATA(nid);
+
+	/* Flush pending updates to the LRU lists */
+	lru_add_drain_all();
+
+	for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) {
+		struct compact_control cc = {
+			.nr_freepages = 0,
+			.nr_migratepages = 0,
+			.order = -1,
+		};
+
+		zone = &pgdat->node_zones[zoneid];
+		if (!populated_zone(zone))
+			continue;
+
+		cc.zone = zone;
+		INIT_LIST_HEAD(&cc.freepages);
+		INIT_LIST_HEAD(&cc.migratepages);
+
+		compact_zone(zone, &cc);
+
+		VM_BUG_ON(!list_empty(&cc.freepages));
+		VM_BUG_ON(!list_empty(&cc.migratepages));
+	}
+
+	return 0;
+}
+
+/* Compact all nodes in the system */
+static int compact_nodes(void)
+{
+	int nid;
+
+	for_each_online_node(nid)
+		compact_node(nid);
+
+	return COMPACT_COMPLETE;
+}
+
+/* The written value is actually unused, all memory is compacted */
+int sysctl_compact_memory;
+
+/* This is the entry point for compacting all nodes via /proc/sys/vm */
+int sysctl_compaction_handler(struct ctl_table *table, int write,
+			void __user *buffer, size_t *length, loff_t *ppos)
+{
+	if (write)
+		return compact_nodes();
+
+	return 0;
+}
+
+int sysctl_extfrag_handler(struct ctl_table *table, int write,
+			void __user *buffer, size_t *length, loff_t *ppos)
+{
+	proc_dointvec_minmax(table, write, buffer, length, ppos);
+
+	return 0;
+}
+
+#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
+ssize_t sysfs_compact_node(struct sys_device *dev,
+			struct sysdev_attribute *attr,
+			const char *buf, size_t count)
+{
+	compact_node(dev->id);
+
+	return count;
+}
+static SYSDEV_ATTR(compact, S_IWUSR, NULL, sysfs_compact_node);
+
+int compaction_register_node(struct node *node)
+{
+	return sysdev_create_file(&node->sysdev, &attr_compact);
+}
+
+void compaction_unregister_node(struct node *node)
+{
+	return sysdev_remove_file(&node->sysdev, &attr_compact);
+}
+#endif /* CONFIG_SYSFS && CONFIG_NUMA */
diff --git a/mm/filemap.c b/mm/filemap.c
index 140ebda9640f..20e5642e9f9f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -151,6 +151,7 @@ void remove_from_page_cache(struct page *page)
 	spin_unlock_irq(&mapping->tree_lock);
 	mem_cgroup_uncharge_cache_page(page);
 }
+EXPORT_SYMBOL(remove_from_page_cache);
 
 static int sync_page(void *word)
 {
@@ -441,7 +442,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 	/*
 	 * Splice_read and readahead add shmem/tmpfs pages into the page cache
 	 * before shmem_readpage has a chance to mark them as SwapBacked: they
-	 * need to go on the active_anon lru below, and mem_cgroup_cache_charge
+	 * need to go on the anon lru below, and mem_cgroup_cache_charge
 	 * (called in add_to_page_cache) needs to know where they're going too.
 	 */
 	if (mapping_cap_swap_backed(mapping))
@@ -452,7 +453,7 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
 		if (page_is_file_cache(page))
 			lru_cache_add_file(page);
 		else
-			lru_cache_add_active_anon(page);
+			lru_cache_add_anon(page);
 	}
 	return ret;
 }
@@ -461,9 +462,15 @@ EXPORT_SYMBOL_GPL(add_to_page_cache_lru);
 #ifdef CONFIG_NUMA
 struct page *__page_cache_alloc(gfp_t gfp)
 {
+	int n;
+	struct page *page;
+
 	if (cpuset_do_page_mem_spread()) {
-		int n = cpuset_mem_spread_node();
-		return alloc_pages_exact_node(n, gfp, 0);
+		get_mems_allowed();
+		n = cpuset_mem_spread_node();
+		page = alloc_pages_exact_node(n, gfp, 0);
+		put_mems_allowed();
+		return page;
 	}
 	return alloc_pages(gfp, 0);
 }
@@ -1099,6 +1106,12 @@ page_not_up_to_date_locked:
 		}
 
 readpage:
+		/*
+		 * A previous I/O error may have been due to temporary
+		 * failures, eg. multipath errors.
+		 * PG_error will be set again if readpage fails.
+		 */
+		ClearPageError(page);
 		/* Start the actual read. The read will unlock the page. */
 		error = mapping->a_ops->readpage(filp, page);
 
@@ -1263,7 +1276,7 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 {
 	struct file *filp = iocb->ki_filp;
 	ssize_t retval;
-	unsigned long seg;
+	unsigned long seg = 0;
 	size_t count;
 	loff_t *ppos = &iocb->ki_pos;
 
@@ -1290,21 +1303,47 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov,
 				retval = mapping->a_ops->direct_IO(READ, iocb,
 							iov, pos, nr_segs);
 			}
-			if (retval > 0)
+			if (retval > 0) {
 				*ppos = pos + retval;
-			if (retval) {
+				count -= retval;
+			}
+
+			/*
+			 * Btrfs can have a short DIO read if we encounter
+			 * compressed extents, so if there was an error, or if
+			 * we've already read everything we wanted to, or if
+			 * there was a short read because we hit EOF, go ahead
+			 * and return.  Otherwise fallthrough to buffered io for
+			 * the rest of the read.
+			 */
+			if (retval < 0 || !count || *ppos >= size) {
 				file_accessed(filp);
 				goto out;
 			}
 		}
 	}
 
+	count = retval;
 	for (seg = 0; seg < nr_segs; seg++) {
 		read_descriptor_t desc;
+		loff_t offset = 0;
+
+		/*
+		 * If we did a short DIO read we need to skip the section of the
+		 * iov that we've already read data into.
+		 */
+		if (count) {
+			if (count > iov[seg].iov_len) {
+				count -= iov[seg].iov_len;
+				continue;
+			}
+			offset = count;
+			count = 0;
+		}
 
 		desc.written = 0;
-		desc.arg.buf = iov[seg].iov_base;
-		desc.count = iov[seg].iov_len;
+		desc.arg.buf = iov[seg].iov_base + offset;
+		desc.count = iov[seg].iov_len - offset;
 		if (desc.count == 0)
 			continue;
 		desc.error = 0;
diff --git a/mm/highmem.c b/mm/highmem.c
index bed8a8bfd01f..66baa20f78f5 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -422,7 +422,7 @@ void __init page_address_init(void)
 
 #endif	/* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
 
-#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
+#ifdef CONFIG_DEBUG_HIGHMEM
 
 void debug_kmap_atomic(enum km_type type)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 4c9e6bbf3772..54d42b009dbe 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -465,11 +465,13 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	struct page *page = NULL;
 	struct mempolicy *mpol;
 	nodemask_t *nodemask;
-	struct zonelist *zonelist = huge_zonelist(vma, address,
-					htlb_alloc_mask, &mpol, &nodemask);
+	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
 
+	get_mems_allowed();
+	zonelist = huge_zonelist(vma, address,
+					htlb_alloc_mask, &mpol, &nodemask);
 	/*
 	 * A child process with MAP_PRIVATE mappings created by their parent
 	 * have no page reserves. This check ensures that reservations are
@@ -477,11 +479,11 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	 */
 	if (!vma_has_reserves(vma) &&
 			h->free_huge_pages - h->resv_huge_pages == 0)
-		return NULL;
+		goto err;
 
 	/* If reserves cannot be used, ensure enough pages are in the pool */
 	if (avoid_reserve && h->free_huge_pages - h->resv_huge_pages == 0)
-		return NULL;
+		goto err;;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						MAX_NR_ZONES - 1, nodemask) {
@@ -500,7 +502,9 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 			break;
 		}
 	}
+err:
 	mpol_cond_put(mpol);
+	put_mems_allowed();
 	return page;
 }
 
diff --git a/mm/ksm.c b/mm/ksm.c
index 956880f2ff49..6c3e99b4ae7c 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -318,14 +318,14 @@ static void hold_anon_vma(struct rmap_item *rmap_item,
 			  struct anon_vma *anon_vma)
 {
 	rmap_item->anon_vma = anon_vma;
-	atomic_inc(&anon_vma->ksm_refcount);
+	atomic_inc(&anon_vma->external_refcount);
 }
 
 static void drop_anon_vma(struct rmap_item *rmap_item)
 {
 	struct anon_vma *anon_vma = rmap_item->anon_vma;
 
-	if (atomic_dec_and_lock(&anon_vma->ksm_refcount, &anon_vma->lock)) {
+	if (atomic_dec_and_lock(&anon_vma->external_refcount, &anon_vma->lock)) {
 		int empty = list_empty(&anon_vma->head);
 		spin_unlock(&anon_vma->lock);
 		if (empty)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c8569bc298ff..c6ece0a57595 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -149,16 +149,35 @@ struct mem_cgroup_threshold {
 	u64 threshold;
 };
 
+/* For threshold */
 struct mem_cgroup_threshold_ary {
 	/* An array index points to threshold just below usage. */
-	atomic_t current_threshold;
+	int current_threshold;
 	/* Size of entries[] */
 	unsigned int size;
 	/* Array of thresholds */
 	struct mem_cgroup_threshold entries[0];
 };
 
+struct mem_cgroup_thresholds {
+	/* Primary thresholds array */
+	struct mem_cgroup_threshold_ary *primary;
+	/*
+	 * Spare threshold array.
+	 * This is needed to make mem_cgroup_unregister_event() "never fail".
+	 * It must be able to store at least primary->size - 1 entries.
+	 */
+	struct mem_cgroup_threshold_ary *spare;
+};
+
+/* for OOM */
+struct mem_cgroup_eventfd_list {
+	struct list_head list;
+	struct eventfd_ctx *eventfd;
+};
+
 static void mem_cgroup_threshold(struct mem_cgroup *mem);
+static void mem_cgroup_oom_notify(struct mem_cgroup *mem);
 
 /*
  * The memory controller data structure. The memory controller controls both
@@ -207,6 +226,8 @@ struct mem_cgroup {
 	atomic_t	refcnt;
 
 	unsigned int	swappiness;
+	/* OOM-Killer disable */
+	int		oom_kill_disable;
 
 	/* set when res.limit == memsw.limit */
 	bool		memsw_is_minimum;
@@ -215,17 +236,19 @@ struct mem_cgroup {
 	struct mutex thresholds_lock;
 
 	/* thresholds for memory usage. RCU-protected */
-	struct mem_cgroup_threshold_ary *thresholds;
+	struct mem_cgroup_thresholds thresholds;
 
 	/* thresholds for mem+swap usage. RCU-protected */
-	struct mem_cgroup_threshold_ary *memsw_thresholds;
+	struct mem_cgroup_thresholds memsw_thresholds;
+
+	/* For oom notifier event fd */
+	struct list_head oom_notify;
 
 	/*
 	 * Should we move charges of a task when a task is moved into this
 	 * mem_cgroup ? And what type of charges should we move ?
 	 */
 	unsigned long 	move_charge_at_immigrate;
-
 	/*
 	 * percpu counter.
 	 */
@@ -239,6 +262,7 @@ struct mem_cgroup {
  */
 enum move_type {
 	MOVE_CHARGE_TYPE_ANON,	/* private anonymous page and swap of it */
+	MOVE_CHARGE_TYPE_FILE,	/* file page(including tmpfs) and swap of it */