Merge branch 'akpm' (Andrew's patchbomb)

Merge misc updates from Andrew Morton: "About half of most of MM. Going very early this time due to uncertainty over the coreautounifiednumasched things. I'll send the other half of most of MM tomorrow. The rest of MM awaits a slab merge from Pekka." * emailed patches from Andrew Morton: (71 commits) memory_hotplug: ensure every online node has NORMAL memory memory_hotplug: handle empty zone when online_movable/online_kernel mm, memory-hotplug: dynamic configure movable memory and portion memory drivers/base/node.c: cleanup node_state_attr[] bootmem: fix wrong call parameter for free_bootmem() avr32, kconfig: remove HAVE_ARCH_BOOTMEM mm: cma: remove watermark hacks mm: cma: skip watermarks check for already isolated blocks in split_free_page() mm, oom: fix race when specifying a thread as the oom origin mm, oom: change type of oom_score_adj to short mm: cleanup register_node() mm, mempolicy: remove duplicate code mm/vmscan.c: try_to_freeze() returns boolean mm: introduce putback_movable_pages() virtio_balloon: introduce migration primitives to balloon pages mm: introduce compaction and migration for ballooned pages mm: introduce a common interface for balloon pages mobility mm: redefine address_space.assoc_mapping mm: adjust address_space_operations.migratepage() return code arch/sparc/kernel/sys_sparc_64.c: s/COLOUR/COLOR/ ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2012-12-11 18:05:37 -0800
committer: Linus Torvalds <torvalds@linux-foundation.org> 2012-12-11 18:05:37 -0800
commit: 608ff1a210ab0e8b969399039bf8e18693605910 (patch)
tree: faea7bb1764461c73d0953089bd5439d91733a03 /mm
parent: 414a6750e59b0b687034764c464e9ddecac0f7a6 (diff)
parent: 74d42d8fe146e870c52bde3b1c692f86cc8ff844 (diff)
download: linux-608ff1a210ab0e8b969399039bf8e18693605910.tar.bz2
29 files changed, 1493 insertions, 585 deletions
diff --git a/mm/Kconfig b/mm/Kconfig
index a3f8dddaaab3..e6651c5de14f 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -188,6 +188,21 @@ config SPLIT_PTLOCK_CPUS
 	default "4"
 
 #
+# support for memory balloon compaction
+config BALLOON_COMPACTION
+	bool "Allow for balloon memory compaction/migration"
+	def_bool y
+	depends on COMPACTION && VIRTIO_BALLOON
+	help
+	  Memory fragmentation introduced by ballooning might reduce
+	  significantly the number of 2MB contiguous memory blocks that can be
+	  used within a guest, thus imposing performance penalties associated
+	  with the reduced number of transparent huge pages that could be used
+	  by the guest workload. Allowing the compaction & migration for memory
+	  pages enlisted as being part of memory balloon devices avoids the
+	  scenario aforementioned and helps improving memory defragmentation.
+
+#
 # support for memory compaction
 config COMPACTION
 	bool "Allow for memory compaction"
diff --git a/mm/Makefile b/mm/Makefile
index 6b025f80af34..3a4628751f89 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -16,7 +16,8 @@ obj-y			:= filemap.o mempool.o oom_kill.o fadvise.o \
 			   readahead.o swap.o truncate.o vmscan.o shmem.o \
 			   util.o mmzone.o vmstat.o backing-dev.o \
 			   mm_init.o mmu_context.o percpu.o slab_common.o \
-			   compaction.o interval_tree.o $(mmu-y)
+			   compaction.o balloon_compaction.o \
+			   interval_tree.o $(mmu-y)
 
 obj-y += init-mm.o
 
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
new file mode 100644
index 000000000000..07dbc8ec46cf
--- /dev/null
+++ b/mm/balloon_compaction.c
@@ -0,0 +1,302 @@
+/*
+ * mm/balloon_compaction.c
+ *
+ * Common interface for making balloon pages movable by compaction.
+ *
+ * Copyright (C) 2012, Red Hat, Inc.  Rafael Aquini <aquini@redhat.com>
+ */
+#include <linux/mm.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/balloon_compaction.h>
+
+/*
+ * balloon_devinfo_alloc - allocates a balloon device information descriptor.
+ * @balloon_dev_descriptor: pointer to reference the balloon device which
+ *                          this struct balloon_dev_info will be servicing.
+ *
+ * Driver must call it to properly allocate and initialize an instance of
+ * struct balloon_dev_info which will be used to reference a balloon device
+ * as well as to keep track of the balloon device page list.
+ */
+struct balloon_dev_info *balloon_devinfo_alloc(void *balloon_dev_descriptor)
+{
+	struct balloon_dev_info *b_dev_info;
+	b_dev_info = kmalloc(sizeof(*b_dev_info), GFP_KERNEL);
+	if (!b_dev_info)
+		return ERR_PTR(-ENOMEM);
+
+	b_dev_info->balloon_device = balloon_dev_descriptor;
+	b_dev_info->mapping = NULL;
+	b_dev_info->isolated_pages = 0;
+	spin_lock_init(&b_dev_info->pages_lock);
+	INIT_LIST_HEAD(&b_dev_info->pages);
+
+	return b_dev_info;
+}
+EXPORT_SYMBOL_GPL(balloon_devinfo_alloc);
+
+/*
+ * balloon_page_enqueue - allocates a new page and inserts it into the balloon
+ *			  page list.
+ * @b_dev_info: balloon device decriptor where we will insert a new page to
+ *
+ * Driver must call it to properly allocate a new enlisted balloon page
+ * before definetively removing it from the guest system.
+ * This function returns the page address for the recently enqueued page or
+ * NULL in the case we fail to allocate a new page this turn.
+ */
+struct page *balloon_page_enqueue(struct balloon_dev_info *b_dev_info)
+{
+	unsigned long flags;
+	struct page *page = alloc_page(balloon_mapping_gfp_mask() |
+					__GFP_NOMEMALLOC | __GFP_NORETRY);
+	if (!page)
+		return NULL;
+
+	/*
+	 * Block others from accessing the 'page' when we get around to
+	 * establishing additional references. We should be the only one
+	 * holding a reference to the 'page' at this point.
+	 */
+	BUG_ON(!trylock_page(page));
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	balloon_page_insert(page, b_dev_info->mapping, &b_dev_info->pages);
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+	unlock_page(page);
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_enqueue);
+
+/*
+ * balloon_page_dequeue - removes a page from balloon's page list and returns
+ *			  the its address to allow the driver release the page.
+ * @b_dev_info: balloon device decriptor where we will grab a page from.
+ *
+ * Driver must call it to properly de-allocate a previous enlisted balloon page
+ * before definetively releasing it back to the guest system.
+ * This function returns the page address for the recently dequeued page or
+ * NULL in the case we find balloon's page list temporarily empty due to
+ * compaction isolated pages.
+ */
+struct page *balloon_page_dequeue(struct balloon_dev_info *b_dev_info)
+{
+	struct page *page, *tmp;
+	unsigned long flags;
+	bool dequeued_page;
+
+	dequeued_page = false;
+	list_for_each_entry_safe(page, tmp, &b_dev_info->pages, lru) {
+		/*
+		 * Block others from accessing the 'page' while we get around
+		 * establishing additional references and preparing the 'page'
+		 * to be released by the balloon driver.
+		 */
+		if (trylock_page(page)) {
+			spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+			/*
+			 * Raise the page refcount here to prevent any wrong
+			 * attempt to isolate this page, in case of coliding
+			 * with balloon_page_isolate() just after we release
+			 * the page lock.
+			 *
+			 * balloon_page_free() will take care of dropping
+			 * this extra refcount later.
+			 */
+			get_page(page);
+			balloon_page_delete(page);
+			spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+			unlock_page(page);
+			dequeued_page = true;
+			break;
+		}
+	}
+
+	if (!dequeued_page) {
+		/*
+		 * If we are unable to dequeue a balloon page because the page
+		 * list is empty and there is no isolated pages, then something
+		 * went out of track and some balloon pages are lost.
+		 * BUG() here, otherwise the balloon driver may get stuck into
+		 * an infinite loop while attempting to release all its pages.
+		 */
+		spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+		if (unlikely(list_empty(&b_dev_info->pages) &&
+			     !b_dev_info->isolated_pages))
+			BUG();
+		spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+		page = NULL;
+	}
+	return page;
+}
+EXPORT_SYMBOL_GPL(balloon_page_dequeue);
+
+#ifdef CONFIG_BALLOON_COMPACTION
+/*
+ * balloon_mapping_alloc - allocates a special ->mapping for ballooned pages.
+ * @b_dev_info: holds the balloon device information descriptor.
+ * @a_ops: balloon_mapping address_space_operations descriptor.
+ *
+ * Driver must call it to properly allocate and initialize an instance of
+ * struct address_space which will be used as the special page->mapping for
+ * balloon device enlisted page instances.
+ */
+struct address_space *balloon_mapping_alloc(struct balloon_dev_info *b_dev_info,
+				const struct address_space_operations *a_ops)
+{
+	struct address_space *mapping;
+
+	mapping = kmalloc(sizeof(*mapping), GFP_KERNEL);
+	if (!mapping)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * Give a clean 'zeroed' status to all elements of this special
+	 * balloon page->mapping struct address_space instance.
+	 */
+	address_space_init_once(mapping);
+
+	/*
+	 * Set mapping->flags appropriately, to allow balloon pages
+	 * ->mapping identification.
+	 */
+	mapping_set_balloon(mapping);
+	mapping_set_gfp_mask(mapping, balloon_mapping_gfp_mask());
+
+	/* balloon's page->mapping->a_ops callback descriptor */
+	mapping->a_ops = a_ops;
+
+	/*
+	 * Establish a pointer reference back to the balloon device descriptor
+	 * this particular page->mapping will be servicing.
+	 * This is used by compaction / migration procedures to identify and
+	 * access the balloon device pageset while isolating / migrating pages.
+	 *
+	 * As some balloon drivers can register multiple balloon devices
+	 * for a single guest, this also helps compaction / migration to
+	 * properly deal with multiple balloon pagesets, when required.
+	 */
+	mapping->private_data = b_dev_info;
+	b_dev_info->mapping = mapping;
+
+	return mapping;
+}
+EXPORT_SYMBOL_GPL(balloon_mapping_alloc);
+
+static inline void __isolate_balloon_page(struct page *page)
+{
+	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	unsigned long flags;
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	list_del(&page->lru);
+	b_dev_info->isolated_pages++;
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+}
+
+static inline void __putback_balloon_page(struct page *page)
+{
+	struct balloon_dev_info *b_dev_info = page->mapping->private_data;
+	unsigned long flags;
+	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
+	list_add(&page->lru, &b_dev_info->pages);
+	b_dev_info->isolated_pages--;
+	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
+}
+
+static inline int __migrate_balloon_page(struct address_space *mapping,
+		struct page *newpage, struct page *page, enum migrate_mode mode)
+{
+	return page->mapping->a_ops->migratepage(mapping, newpage, page, mode);
+}
+
+/* __isolate_lru_page() counterpart for a ballooned page */
+bool balloon_page_isolate(struct page *page)
+{
+	/*
+	 * Avoid burning cycles with pages that are yet under __free_pages(),
+	 * or just got freed under us.
+	 *
+	 * In case we 'win' a race for a balloon page being freed under us and
+	 * raise its refcount preventing __free_pages() from doing its job
+	 * the put_page() at the end of this block will take care of
+	 * release this page, thus avoiding a nasty leakage.
+	 */
+	if (likely(get_page_unless_zero(page))) {
+		/*
+		 * As balloon pages are not isolated from LRU lists, concurrent
+		 * compaction threads can race against page migration functions
+		 * as well as race against the balloon driver releasing a page.
+		 *
+		 * In order to avoid having an already isolated balloon page
+		 * being (wrongly) re-isolated while it is under migration,
+		 * or to avoid attempting to isolate pages being released by
+		 * the balloon driver, lets be sure we have the page lock
+		 * before proceeding with the balloon page isolation steps.
+		 */
+		if (likely(trylock_page(page))) {
+			/*
+			 * A ballooned page, by default, has just one refcount.
+			 * Prevent concurrent compaction threads from isolating
+			 * an already isolated balloon page by refcount check.
+			 */
+			if (__is_movable_balloon_page(page) &&
+			    page_count(page) == 2) {
+				__isolate_balloon_page(page);
+				unlock_page(page);
+				return true;
+			}
+			unlock_page(page);
+		}
+		put_page(page);
+	}
+	return false;
+}
+
+/* putback_lru_page() counterpart for a ballooned page */
+void balloon_page_putback(struct page *page)
+{
+	/*
+	 * 'lock_page()' stabilizes the page and prevents races against
+	 * concurrent isolation threads attempting to re-isolate it.
+	 */
+	lock_page(page);
+
+	if (__is_movable_balloon_page(page)) {
+		__putback_balloon_page(page);
+		/* drop the extra ref count taken for page isolation */
+		put_page(page);
+	} else {
+		WARN_ON(1);
+		dump_page(page);
+	}
+	unlock_page(page);
+}
+
+/* move_to_new_page() counterpart for a ballooned page */
+int balloon_page_migrate(struct page *newpage,
+			 struct page *page, enum migrate_mode mode)
+{
+	struct address_space *mapping;
+	int rc = -EAGAIN;
+
+	/*
+	 * Block others from accessing the 'newpage' when we get around to
+	 * establishing additional references. We should be the only one
+	 * holding a reference to the 'newpage' at this point.
+	 */
+	BUG_ON(!trylock_page(newpage));
+
+	if (WARN_ON(!__is_movable_balloon_page(page))) {
+		dump_page(page);
+		unlock_page(newpage);
+		return rc;
+	}
+
+	mapping = page->mapping;
+	if (mapping)
+		rc = __migrate_balloon_page(mapping, newpage, page, mode);
+
+	unlock_page(newpage);
+	return rc;
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
diff --git a/mm/bootmem.c b/mm/bootmem.c
index f468185b3b28..ecc45958ac0c 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -147,21 +147,21 @@ unsigned long __init init_bootmem(unsigned long start, unsigned long pages)
 
 /*
  * free_bootmem_late - free bootmem pages directly to page allocator
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * This is only useful when the bootmem allocator has already been torn
  * down, but we are still initializing the system.  Pages are given directly
  * to the page allocator, no bootmem metadata is updated because it is gone.
  */
-void __init free_bootmem_late(unsigned long addr, unsigned long size)
+void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
 {
 	unsigned long cursor, end;
 
-	kmemleak_free_part(__va(addr), size);
+	kmemleak_free_part(__va(physaddr), size);
 
-	cursor = PFN_UP(addr);
-	end = PFN_DOWN(addr + size);
+	cursor = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
 
 	for (; cursor < end; cursor++) {
 		__free_pages_bootmem(pfn_to_page(cursor), 0);
@@ -377,21 +377,21 @@ void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
 
 /**
  * free_bootmem - mark a page range as usable
- * @addr: starting address of the range
+ * @addr: starting physical address of the range
  * @size: size of the range in bytes
  *
  * Partial pages will be considered reserved and left as they are.
  *
  * The range must be contiguous but may span node boundaries.
  */
-void __init free_bootmem(unsigned long addr, unsigned long size)
+void __init free_bootmem(unsigned long physaddr, unsigned long size)
 {
 	unsigned long start, end;
 
-	kmemleak_free_part(__va(addr), size);
+	kmemleak_free_part(__va(physaddr), size);
 
-	start = PFN_UP(addr);
-	end = PFN_DOWN(addr + size);
+	start = PFN_UP(physaddr);
+	end = PFN_DOWN(physaddr + size);
 
 	mark_bootmem(start, end, 0, 0);
 }
diff --git a/mm/compaction.c b/mm/compaction.c
index 694eaabaaebd..d24dd2d7bad4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -14,6 +14,7 @@
 #include <linux/backing-dev.h>
 #include <linux/sysctl.h>
 #include <linux/sysfs.h>
+#include <linux/balloon_compaction.h>
 #include "internal.h"
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
@@ -565,9 +566,24 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 			goto next_pageblock;
 		}
 
-		/* Check may be lockless but that's ok as we recheck later */
-		if (!PageLRU(page))
+		/*
+		 * Check may be lockless but that's ok as we recheck later.
+		 * It's possible to migrate LRU pages and balloon pages
+		 * Skip any other type of page
+		 */
+		if (!PageLRU(page)) {
+			if (unlikely(balloon_page_movable(page))) {
+				if (locked && balloon_page_isolate(page)) {
+					/* Successfully isolated */
+					cc->finished_update_migrate = true;
+					list_add(&page->lru, migratelist);
+					cc->nr_migratepages++;
+					nr_isolated++;
+					goto check_compact_cluster;
+				}
+			}
 			continue;
+		}
 
 		/*
 		 * PageLRU is set. lru_lock normally excludes isolation
@@ -621,6 +637,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
 		cc->nr_migratepages++;
 		nr_isolated++;
 
+check_compact_cluster:
 		/* Avoid isolating too much */
 		if (cc->nr_migratepages == COMPACT_CLUSTER_MAX) {
 			++low_pfn;
@@ -986,7 +1003,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		switch (isolate_migratepages(zone, cc)) {
 		case ISOLATE_ABORT:
 			ret = COMPACT_PARTIAL;
-			putback_lru_pages(&cc->migratepages);
+			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
 			goto out;
 		case ISOLATE_NONE:
@@ -1009,9 +1026,9 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		trace_mm_compaction_migratepages(nr_migrate - nr_remaining,
 						nr_remaining);
 
-		/* Release LRU pages not migrated */
+		/* Release isolated pages not migrated */
 		if (err) {
-			putback_lru_pages(&cc->migratepages);
+			putback_movable_pages(&cc->migratepages);
 			cc->nr_migratepages = 0;
 			if (err == -ENOMEM) {
 				ret = COMPACT_PARTIAL;
diff --git a/mm/dmapool.c b/mm/dmapool.c
index da1b0f0b8709..c69781e97cf9 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -332,6 +332,30 @@ void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 	retval = offset + page->vaddr;
 	*handle = offset + page->dma;
 #ifdef	DMAPOOL_DEBUG
+	{
+		int i;
+		u8 *data = retval;
+		/* page->offset is stored in first 4 bytes */
+		for (i = sizeof(page->offset); i < pool->size; i++) {
+			if (data[i] == POOL_POISON_FREED)
+				continue;
+			if (pool->dev)
+				dev_err(pool->dev,
+					"dma_pool_alloc %s, %p (corruped)\n",
+					pool->name, retval);
+			else
+				pr_err("dma_pool_alloc %s, %p (corruped)\n",
+					pool->name, retval);
+
+			/*
+			 * Dump the first 4 bytes even if they are not
+			 * POOL_POISON_FREED
+			 */
+			print_hex_dump(KERN_ERR, "", DUMP_PREFIX_OFFSET, 16, 1,
+					data, pool->size, 1);
+			break;
+		}
+	}
 	memset(retval, POOL_POISON_ALLOCATED, pool->size);
 #endif
 	spin_unlock_irqrestore(&pool->lock, flags);
diff --git a/mm/highmem.c b/mm/highmem.c
index 2da13a5c50e2..d999077431df 100644
--- a/mm/highmem.c
+++ b/mm/highmem.c
@@ -99,7 +99,7 @@ struct page *kmap_to_page(void *vaddr)
 	unsigned long addr = (unsigned long)vaddr;
 
 	if (addr >= PKMAP_ADDR(0) && addr < PKMAP_ADDR(LAST_PKMAP)) {
-		int i = (addr - PKMAP_ADDR(0)) >> PAGE_SHIFT;
+		int i = PKMAP_NR(addr);
 		return pte_page(pkmap_page_table[i]);
 	}
 
@@ -137,8 +137,7 @@ static void flush_all_zero_pkmaps(void)
 		 * So no dangers, even with speculative execution.
 		 */
 		page = pte_page(pkmap_page_table[i]);
-		pte_clear(&init_mm, (unsigned long)page_address(page),
-			  &pkmap_page_table[i]);
+		pte_clear(&init_mm, PKMAP_ADDR(i), &pkmap_page_table[i]);
 
 		set_page_address(page, NULL);
 		need_flush = 1;
@@ -324,11 +323,7 @@ struct page_address_map {
 	struct list_head list;
 };
 
-/*
- * page_address_map freelist, allocated from page_address_maps.
- */
-static struct list_head page_address_pool;	/* freelist */
-static spinlock_t pool_lock;			/* protects page_address_pool */
+static struct page_address_map page_address_maps[LAST_PKMAP];
 
 /*
  * Hash table bucket
@@ -393,14 +388,7 @@ void set_page_address(struct page *page, void *virtual)
 
 	pas = page_slot(page);
 	if (virtual) {		/* Add */
-		BUG_ON(list_empty(&page_address_pool));
-
-		spin_lock_irqsave(&pool_lock, flags);
-		pam = list_entry(page_address_pool.next,
-				struct page_address_map, list);
-		list_del(&pam->list);
-		spin_unlock_irqrestore(&pool_lock, flags);
-
+		pam = &page_address_maps[PKMAP_NR((unsigned long)virtual)];
 		pam->page = page;
 		pam->virtual = virtual;
 
@@ -413,9 +401,6 @@ void set_page_address(struct page *page, void *virtual)
 			if (pam->page == page) {
 				list_del(&pam->list);
 				spin_unlock_irqrestore(&pas->lock, flags);
-				spin_lock_irqsave(&pool_lock, flags);
-				list_add_tail(&pam->list, &page_address_pool);
-				spin_unlock_irqrestore(&pool_lock, flags);
 				goto done;
 			}
 		}
@@ -425,20 +410,14 @@ done:
 	return;
 }
 
-static struct page_address_map page_address_maps[LAST_PKMAP];
-
 void __init page_address_init(void)
 {
 	int i;
 
-	INIT_LIST_HEAD(&page_address_pool);
-	for (i = 0; i < ARRAY_SIZE(page_address_maps); i++)
-		list_add(&page_address_maps[i].list, &page_address_pool);
 	for (i = 0; i < ARRAY_SIZE(page_address_htable); i++) {
 		INIT_LIST_HEAD(&page_address_htable[i].lh);
 		spin_lock_init(&page_address_htable[i].lock);
 	}
-	spin_lock_init(&pool_lock);
 }
 
 #endif	/* defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) */
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 40f17c34b415..5f902e20e8c0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -606,6 +606,15 @@ static inline pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
 	return pmd;
 }
 
+static inline pmd_t mk_huge_pmd(struct page *page, struct vm_area_struct *vma)
+{
+	pmd_t entry;
+	entry = mk_pmd(page, vma->vm_page_prot);
+	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
+	entry = pmd_mkhuge(entry);
+	return entry;
+}
+
 static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long haddr, pmd_t *pmd,
@@ -629,9 +638,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm,
 		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);
+		entry = mk_huge_pmd(page, vma);
 		/*
 		 * The spinlocking to take the lru_lock inside
 		 * page_add_new_anon_rmap() acts as a full memory
@@ -777,6 +784,28 @@ out:
 	return ret;
 }
 
+void huge_pmd_set_accessed(struct mm_struct *mm,
+			   struct vm_area_struct *vma,
+			   unsigned long address,
+			   pmd_t *pmd, pmd_t orig_pmd,
+			   int dirty)
+{
+	pmd_t entry;
+	unsigned long haddr;
+
+	spin_lock(&mm->page_table_lock);
+	if (unlikely(!pmd_same(*pmd, orig_pmd)))
+		goto unlock;
+
+	entry = pmd_mkyoung(orig_pmd);
+	haddr = address & HPAGE_PMD_MASK;
+	if (pmdp_set_access_flags(vma, haddr, pmd, entry, dirty))
+		update_mmu_cache_pmd(vma, address, pmd);
+
+unlock:
+	spin_unlock(&mm->page_table_lock);
+}
+
 static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm,
 					struct vm_area_struct *vma,
 					unsigned long address,
@@ -951,9 +980,7 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	} 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);
+		entry = mk_huge_pmd(new_page, vma);
 		pmdp_clear_flush(vma, haddr, pmd);
 		page_add_new_anon_rmap(new_page, vma, haddr);
 		set_pmd_at(mm, haddr, pmd, entry);
@@ -1146,22 +1173,14 @@ pmd_t *page_check_address_pmd(struct page *page,
 			      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))
+	pmd = mm_find_pmd(mm, address);
+	if (!pmd)
 		goto out;
-
-	pmd = pmd_offset(pud, address);
 	if (pmd_none(*pmd))
 		goto out;
 	if (pmd_page(*pmd) != page)
@@ -1701,64 +1720,49 @@ static void release_pte_pages(pte_t *pte, pte_t *_pte)
 	}
 }
 
-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;
+	int referenced = 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);
+			else
 				goto out;
-			}
 		}
-		if (!pte_present(pteval) || !pte_write(pteval)) {
-			release_pte_pages(pte, _pte);
+		if (!pte_present(pteval) || !pte_write(pteval))
 			goto out;
-		}
 		page = vm_normal_page(vma, address, pteval);
-		if (unlikely(!page)) {
-			release_pte_pages(pte, _pte);
+		if (unlikely(!page))
 			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);
+		if (page_count(page) != 1)
 			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);
+		if (!trylock_page(page))
 			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 */
@@ -1771,12 +1775,11 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma,
 		    mmu_notifier_test_young(vma->vm_mm, address))
 			referenced = 1;
 	}
-	if (unlikely(!referenced))
-		release_all_pte_pages(pte);
-	else
-		isolated = 1;
+	if (likely(referenced))
+		return 1;
 out:
-	return isolated;
+	release_pte_pages(pte, _pte);
+	return 0;
 }
 
 static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
@@ -1918,14 +1921,26 @@ static struct page
 }
 #endif
 
+static bool hugepage_vma_check(struct vm_area_struct *vma)
+{
+	if ((!(vma->vm_flags & VM_HUGEPAGE) && !khugepaged_always()) ||
+	    (vma->vm_flags & VM_NOHUGEPAGE))
+		return false;
+
+	if (!vma->anon_vma || vma->vm_ops)
+		return false;
+	if (is_vma_temporary_stack(vma))
+		return false;
+	VM_BUG_ON(vma->vm_flags & VM_NO_THP);
+	return true;
+}
+
 static void collapse_huge_page(struct mm_struct *mm,
 				   unsigned long address,
 				   struct page **hpage,
 				   struct vm_area_struct *vma,
 				   int node)
 {
-	pgd_t *pgd;
-	pud_t *pud;
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
 	pgtable_t pgtable;
@@ -1960,28 +1975,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 	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;
-
-	if (!vma->anon_vma || vma->vm_ops)
-		goto out;
-	if (is_vma_temporary_stack(vma))
+	if (!hugepage_vma_check(vma))
 		goto out;
-	VM_BUG_ON(vma->vm_flags & VM_NO_THP);
-
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
+	pmd = mm_find_pmd(mm, address);
+	if (!pmd)
 		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))
+	if (pmd_trans_huge(*pmd))
 		goto out;
 
 	anon_vma_lock(vma->anon_vma);
@@ -2028,9 +2027,7 @@ static void collapse_huge_page(struct mm_struct *mm,
 	__SetPageUptodate(new_page);
 	pgtable = pmd_pgtable(_pmd);
 
-	_pmd = mk_pmd(new_page, vma->vm_page_prot);
-	_pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma);
-	_pmd = pmd_mkhuge(_pmd);
+	_pmd = mk_huge_pmd(new_page, vma);
 
 	/*
 	 * spin_lock() below is not the equivalent of smp_wmb(), so
@@ -2064,8 +2061,6 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 			       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;
@@ -2076,16 +2071,10 @@ static int khugepaged_scan_pmd(struct mm_struct *mm,
 
 	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))
+	pmd = mm_find_pmd(mm, address);
+	if (!pmd)
 		goto out;
-
-	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd) || pmd_trans_huge(*pmd))
+	if (pmd_trans_huge(*pmd))
 		goto out;
 
 	pte = pte_offset_map_lock(mm, pmd, address, &ptl);
@@ -2193,20 +2182,11 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages,
 			progress++;
 			break;
 		}
-
-		if ((!(vma->vm_flags & VM_HUGEPAGE) &&
-		     !khugepaged_always()) ||
-		    (vma->vm_flags & VM_NOHUGEPAGE)) {
-		skip:
+		if (!hugepage_vma_check(vma)) {
+skip:
 			progress++;
 			continue;
 		}
-		if (!vma->anon_vma || vma->vm_ops)
-			goto skip;
-		if (is_vma_temporary_stack(vma))
-			goto skip;
-		VM_BUG_ON(vma->vm_flags & VM_NO_THP);
-
 		hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK;
 		hend = vma->vm_end & HPAGE_PMD_MASK;
 		if (hstart >= hend)
@@ -2379,22 +2359,12 @@ void __split_huge_page_pmd(struct mm_struct *mm, pmd_t *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))
+	pmd = mm_find_pmd(mm, address);
+	if (!pmd)
 		return;
 	/*
 	 * Caller holds the mmap_sem write mode, so a huge pmd cannot
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 59a0059b39e2..1ef2cd4ae3c9 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1800,7 +1800,7 @@ static void hugetlb_unregister_all_nodes(void)
 	 * remove hstate attributes from any nodes that have them.
 	 */
 	for (nid = 0; nid < nr_node_ids; nid++)
-		hugetlb_unregister_node(&node_devices[nid]);
+		hugetlb_unregister_node(node_devices[nid]);
 }
 
 /*
@@ -1845,7 +1845,7 @@ static void hugetlb_register_all_nodes(void)
 	int nid;
 
 	for_each_node_state(nid, N_HIGH_MEMORY) {
-		struct node *node = &node_devices[nid];
+		struct node *node = node_devices[nid];
 		if (node->dev.id == nid)
 			hugetlb_register_node(node);
 	}
diff --git a/mm/internal.h b/mm/internal.h
index a4fa284f6bc2..52d1fa957194 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -92,6 +92,11 @@ extern int isolate_lru_page(struct page *page);
 extern void putback_lru_page(struct page *page);
 
 /*
+ * in mm/rmap.c:
+ */
+extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address);
+
+/*
  * in mm/page_alloc.c
  */
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
diff --git a/mm/ksm.c b/mm/ksm.c
index ae539f0b8aa1..382d930a0bf1 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -778,8 +778,6 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 			struct page *kpage, pte_t orig_pte)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	pgd_t *pgd;
-	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *ptep;
 	spinlock_t *ptl;
@@ -792,18 +790,10 @@ static int replace_page(struct vm_area_struct *vma, struct page *page,
 	if (addr == -EFAULT)
 		goto out;
 
-	pgd = pgd_offset(mm, addr);
-	if (!pgd_present(*pgd))
+	pmd = mm_find_pmd(mm, addr);
+	if (!pmd)
 		goto out;
-
-	pud = pud_offset(pgd, addr);
-	if (!pud_present(*pud))
-		goto out;
-
-	pmd = pmd_offset(pud, addr);
 	BUG_ON(pmd_trans_huge(*pmd));
-	if (!pmd_present(*pmd))
-		goto out;
 
 	mmun_start = addr;
 	mmun_end   = addr + PAGE_SIZE;
@@ -1929,12 +1919,9 @@ static ssize_t run_store(struct kobject *kobj, struct kobj_attribute *attr,
 	if (ksm_run != flags) {
 		ksm_run = flags;
 		if (flags & KSM_RUN_UNMERGE) {
-			int oom_score_adj;
-
-			oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
+			set_current_oom_origin();
 			err = unmerge_and_remove_all_rmap_items();
-			compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX,
-								oom_score_adj);
+			clear_current_oom_origin();
 			if (err) {
 				ksm_run = KSM_RUN_STOP;
 				count = err;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index dd39ba000b31..cf6d0df4849c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1498,8 +1498,8 @@ static u64 mem_cgroup_get_limit(struct mem_cgroup *memcg)
 	return limit;
 }
 
-void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
-			      int order)
+static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask,
+				     int order)
 {
 	struct mem_cgroup *iter;
 	unsigned long chosen_points = 0;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 8b20278be6a6..108c52fa60f6 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -781,16 +781,16 @@ static struct page_state {
 	{ compound,	compound,	"huge",		me_huge_page },
 #endif
 
-	{ sc|dirty,	sc|dirty,	"swapcache",	me_swapcache_dirty },
-	{ sc|dirty,	sc,		"swapcache",	me_swapcache_clean },
+	{ sc|dirty,	sc|dirty,	"dirty swapcache",	me_swapcache_dirty },
+	{ sc|dirty,	sc,		"clean swapcache",	me_swapcache_clean },
 
-	{ unevict|dirty, unevict|dirty,	"unevictable LRU", me_pagecache_dirty},
-	{ unevict,	unevict,	"unevictable LRU", me_pagecache_clean},
+	{ unevict|dirty, unevict|dirty,	"dirty unevictable LRU", me_pagecache_dirty },
+	{ unevict,	unevict,	"clean unevictable LRU", me_pagecache_clean },
 
-	{ mlock|dirty,	mlock|dirty,	"mlocked LRU",	me_pagecache_dirty },
-	{ mlock,	mlock,		"mlocked LRU",	me_pagecache_clean },
+	{ mlock|dirty,	mlock|dirty,	"dirty mlocked LRU",	me_pagecache_dirty },
+	{ mlock,	mlock,		"clean mlocked LRU",	me_pagecache_clean },
 
-	{ lru|dirty,	lru|dirty,	"LRU",		me_pagecache_dirty },
+	{ lru|dirty,	lru|dirty,	"dirty LRU",	me_pagecache_dirty },
 	{ lru|dirty,	lru,		"clean LRU",	me_pagecache_clean },
 
 	/*
@@ -812,14 +812,14 @@ static struct page_state {
 #undef slab
 #undef reserved
 
+/*
+ * "Dirty/Clean" indication is not 100% accurate due to the possibility of
+ * setting PG_dirty outside page lock. See also comment above set_page_dirty().
+ */
 static void action_result(unsigned long pfn, char *msg, int result)
 {
-	struct page *page = pfn_to_page(pfn);
-
-	printk(KERN_ERR "MCE %#lx: %s%s page recovery: %s\n",
-		pfn,
-		PageDirty(page) ? "dirty " : "",
-		msg, action_name[result]);
+	pr_err("MCE %#lx: %s page recovery: %s\n",
+		pfn, msg, action_name[result]);
 }
 
 static int page_action(struct page_state *ps, struct page *p,
@@ -1385,7 +1385,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags)
 	 * Isolate the page, so that it doesn't get reallocated if it
 	 * was free.
 	 */
-	set_migratetype_isolate(p);
+	set_migratetype_isolate(p, true);
 	/*
 	 * When the target page is a free hugepage, just remove it
 	 * from free hugepage list.
diff --git a/mm/memory.c b/mm/memory.c
index 221fc9ffcab1..765377385632 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3537,8 +3537,9 @@ retry:
 
 		barrier();
 		if (pmd_trans_huge(orig_pmd)) {
-			if (flags & FAULT_FLAG_WRITE &&
-			    !pmd_write(orig_pmd) &&
+			unsigned int dirty = flags & FAULT_FLAG_WRITE;
+
+			if (dirty && !pmd_write(orig_pmd) &&
 			    !pmd_trans_splitting(orig_pmd)) {
 				ret = do_huge_pmd_wp_page(mm, vma, address, pmd,
 							  orig_pmd);
@@ -3550,6 +3551,9 @@ retry:
 				if (unlikely(ret & VM_FAULT_OOM))
 					goto retry;
 				return ret;
+			} else {
+				huge_pmd_set_accessed(mm, vma, address, pmd,
+						      orig_pmd, dirty);
 			}
 			return 0;
 		}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e4eeacae2b91..de9cb14ae753 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -205,7 +205,7 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writelock(zone);
 
 	old_zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;
-	if (start_pfn < zone->zone_start_pfn)
+	if (!zone->spanned_pages || start_pfn < zone->zone_start_pfn)
 		zone->zone_start_pfn = start_pfn;
 
 	zone->spanned_pages = max(old_zone_end_pfn, end_pfn) -
@@ -214,13 +214,134 @@ static void grow_zone_span(struct zone *zone, unsigned long start_pfn,
 	zone_span_writeunlock(zone);
 }
 
+static void resize_zone(struct zone *zone, unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	zone_span_writelock(zone);
+
+	if (end_pfn - start_pfn) {
+		zone->zone_start_pfn = start_pfn;
+		zone->spanned_pages = end_pfn - start_pfn;
+	} else {
+		/*
+		 * make it consist as free_area_init_core(),
+		 * if spanned_pages = 0, then keep start_pfn = 0
+		 */
+		zone->zone_start_pfn = 0;
+		zone->spanned_pages = 0;
+	}
+
+	zone_span_writeunlock(zone);
+}
+
+static void fix_zone_id(struct zone *zone, unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	enum zone_type zid = zone_idx(zone);
+	int nid = zone->zone_pgdat->node_id;
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn++)
+		set_page_links(pfn_to_page(pfn), zid, nid, pfn);
+}
+
+static int __meminit move_pfn_range_left(struct zone *z1, struct zone *z2,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	int ret;
+	unsigned long flags;
+	unsigned long z1_start_pfn;
+
+	if (!z1->wait_table) {
+		ret = init_currently_empty_zone(z1, start_pfn,
+			end_pfn - start_pfn, MEMMAP_HOTPLUG);
+		if (ret)
+			return ret;
+	}
+
+	pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+	/* can't move pfns which are higher than @z2 */
+	if (end_pfn > z2->zone_start_pfn + z2->spanned_pages)
+		goto out_fail;
+	/* the move out part mast at the left most of @z2 */
+	if (start_pfn > z2->zone_start_pfn)
+		goto out_fail;
+	/* must included/overlap */
+	if (end_pfn <= z2->zone_start_pfn)
+		goto out_fail;
+
+	/* use start_pfn for z1's start_pfn if z1 is empty */
+	if (z1->spanned_pages)
+		z1_start_pfn = z1->zone_start_pfn;
+	else
+		z1_start_pfn = start_pfn;
+
+	resize_zone(z1, z1_start_pfn, end_pfn);
+	resize_zone(z2, end_pfn, z2->zone_start_pfn + z2->spanned_pages);
+
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+	fix_zone_id(z1, start_pfn, end_pfn);
+
+	return 0;
+out_fail:
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+	return -1;
+}
+
+static int __meminit move_pfn_range_right(struct zone *z1, struct zone *z2,
+		unsigned long start_pfn, unsigned long end_pfn)
+{
+	int ret;
+	unsigned long flags;
+	unsigned long z2_end_pfn;
+
+	if (!z2->wait_table) {
+		ret = init_currently_empty_zone(z2, start_pfn,
+			end_pfn - start_pfn, MEMMAP_HOTPLUG);
+		if (ret)
+			return ret;
+	}
+
+	pgdat_resize_lock(z1->zone_pgdat, &flags);
+
+	/* can't move pfns which are lower than @z1 */
+	if (z1->zone_start_pfn > start_pfn)
+		goto out_fail;
+	/* the move out part mast at the right most of @z1 */
+	if (z1->zone_start_pfn + z1->spanned_pages >  end_pfn)
+		goto out_fail;
+	/* must included/overlap */
+	if (start_pfn >= z1->zone_start_pfn + z1->spanned_pages)
+		goto out_fail;
+
+	/* use end_pfn for z2's end_pfn if z2 is empty */
+	if (z2->spanned_pages)
+		z2_end_pfn = z2->zone_start_pfn + z2->spanned_pages;
+	else
+		z2_end_pfn = end_pfn;
+
+	resize_zone(z1, z1->zone_start_pfn, start_pfn);
+	resize_zone(z2, start_pfn, z2_end_pfn);
+
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+
+	fix_zone_id(z2, start_pfn, end_pfn);
+
+	return 0;
+out_fail:
+	pgdat_resize_unlock(z1->zone_pgdat, &flags);
+	return -1;
+}
+
 static void grow_pgdat_span(struct pglist_data *pgdat, unsigned long start_pfn,
 			    unsigned long end_pfn)
 {
 	unsigned long old_pgdat_end_pfn =
 		pgdat->node_start_pfn + pgdat->node_spanned_pages;
 
-	if (start_pfn < pgdat->node_start_pfn)
+	if (!pgdat->node_spanned_pages || start_pfn < pgdat->node_start_pfn)
 		pgdat->node_start_pfn = start_pfn;
 
 	pgdat->node_spanned_pages = max(old_pgdat_end_pfn, end_pfn) -
@@ -460,8 +581,61 @@ static int online_pages_range(unsigned long start_pfn, unsigned long nr_pages,
 	return 0;
 }
 
+/* ensure every online node has NORMAL memory */
+static bool can_online_high_movable(struct zone *zone)
+{
+	return node_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+}
+
+/* check which state of node_states will be changed when online memory */
+static void node_states_check_changes_online(unsigned long nr_pages,
+	struct zone *zone, struct memory_notify *arg)
+{
+	int nid = zone_to_nid(zone);
+	enum zone_type zone_last = ZONE_NORMAL;
+
+	/*
+	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 *
+	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 */
+	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	/*
+	 * if the memory to be online is in a zone of 0...zone_last, and
+	 * the zones of 0...zone_last don't have memory before online, we will
+	 * need to set the node to node_states[N_NORMAL_MEMORY] after
+	 * the memory is online.
+	 */
+	if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY))
+		arg->status_change_nid_normal = nid;
+	else
+		arg->status_change_nid_normal = -1;
+
+	/*
+	 * if the node don't have memory befor online, we will need to
+	 * set the node to node_states[N_HIGH_MEMORY] after the memory
+	 * is online.
+	 */
+	if (!node_state(nid, N_HIGH_MEMORY))
+		arg->status_change_nid = nid;
+	else
+		arg->status_change_nid = -1;
+}
+
+static void node_states_set_node(int node, struct memory_notify *arg)
+{
+	if (arg->status_change_nid_normal >= 0)
+		node_set_state(node, N_NORMAL_MEMORY);
+
+	node_set_state(node, N_HIGH_MEMORY);
+}
 
-int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
+
+int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type)
 {
 	unsigned long onlined_pages = 0;
 	struct zone *zone;
@@ -471,13 +645,40 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 	struct memory_notify arg;
 
 	lock_memory_hotplug();
+	/*
+	 * This doesn't need a lock to do pfn_to_page().
+	 * The section can't be removed here because of the
+	 * memory_block->state_mutex.
+	 */
+	zone = page_zone(pfn_to_page(pfn));
+
+	if ((zone_idx(zone) > ZONE_NORMAL || online_type == ONLINE_MOVABLE) &&
+	    !can_online_high_movable(zone)) {
+		unlock_memory_hotplug();
+		return -1;
+	}
+
+	if (online_type == ONLINE_KERNEL && zone_idx(zone) == ZONE_MOVABLE) {
+		if (move_pfn_range_left(zone - 1, zone, pfn, pfn + nr_pages)) {
+			unlock_memory_hotplug();
+			return -1;
+		}
+	}
+	if (online_type == ONLINE_MOVABLE && zone_idx(zone) == ZONE_MOVABLE - 1) {
+		if (move_pfn_range_right(zone, zone + 1, pfn, pfn + nr_pages)) {
+			unlock_memory_hotplug();
+			return -1;
+		}
+	}
+
+	/* Previous code may changed the zone of the pfn range */
+	zone = page_zone(pfn_to_page(pfn));
+
 	arg.start_pfn = pfn;
 	arg.nr_pages = nr_pages;
-	arg.status_change_nid = -1;
+	node_states_check_changes_online(nr_pages, zone, &arg);
 
 	nid = page_to_nid(pfn_to_page(pfn));
-	if (node_present_pages(nid) == 0)
-		arg.status_change_nid = nid;
 
 	ret = memory_notify(MEM_GOING_ONLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -487,23 +688,21 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 		return ret;
 	}
 	/*
-	 * This doesn't need a lock to do pfn_to_page().
-	 * The section can't be removed here because of the
-	 * memory_block->state_mutex.
-	 */
-	zone = page_zone(pfn_to_page(pfn));
-	/*
 	 * If this zone is not populated, then it is not in zonelist.
 	 * This means the page allocator ignores this zone.
 	 * So, zonelist must be updated after online.
 	 */
 	mutex_lock(&zonelists_mutex);
-	if (!populated_zone(zone))
+	if (!populated_zone(zone)) {
 		need_zonelists_rebuild = 1;
+		build_all_zonelists(NULL, zone);
+	}
 
 	ret = walk_system_ram_range(pfn, nr_pages, &onlined_pages,
 		online_pages_range);
 	if (ret) {
+		if (need_zonelists_rebuild)
+			zone_pcp_reset(zone);
 		mutex_unlock(&zonelists_mutex);
 		printk(KERN_DEBUG "online_pages [mem %#010llx-%#010llx] failed\n",
 		       (unsigned long long) pfn << PAGE_SHIFT,
@@ -517,9 +716,9 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages)
 	zone->present_pages += onlined_pages;
 	zone->zone_pgdat->node_present_pages += onlined_pages;
 	if (onlined_pages) {
-		node_set_state(zone_to_nid(zone), N_HIGH_MEMORY);
+		node_states_set_node(zone_to_nid(zone), &arg);
 		if (need_zonelists_rebuild)
-			build_all_zonelists(NULL, zone);
+			build_all_zonelists(NULL, NULL);
 		else
 			zone_pcp_update(zone);
 	}
@@ -847,7 +1046,7 @@ check_pages_isolated_cb(unsigned long start_pfn, unsigned long nr_pages,
 {
 	int ret;
 	long offlined = *(long *)data;
-	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages);
+	ret = test_pages_isolated(start_pfn, start_pfn + nr_pages, true);
 	offlined = nr_pages;
 	if (!ret)
 		*(long *)data += offlined;
@@ -867,6 +1066,91 @@ check_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	return offlined;
 }
 
+/* ensure the node has NORMAL memory if it is still online */
+static bool can_offline_normal(struct zone *zone, unsigned long nr_pages)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	unsigned long present_pages = 0;
+	enum zone_type zt;
+
+	for (zt = 0; zt <= ZONE_NORMAL; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+
+	if (present_pages > nr_pages)
+		return true;
+
+	present_pages = 0;
+	for (; zt <= ZONE_MOVABLE; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+
+	/*
+	 * we can't offline the last normal memory until all
+	 * higher memory is offlined.
+	 */
+	return present_pages == 0;
+}
+
+/* check which state of node_states will be changed when offline memory */
+static void node_states_check_changes_offline(unsigned long nr_pages,
+		struct zone *zone, struct memory_notify *arg)
+{
+	struct pglist_data *pgdat = zone->zone_pgdat;
+	unsigned long present_pages = 0;
+	enum zone_type zt, zone_last = ZONE_NORMAL;
+
+	/*
+	 * If we have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_NORMAL, set zone_last to ZONE_NORMAL.
+	 *
+	 * If we don't have HIGHMEM, node_states[N_NORMAL_MEMORY] contains nodes
+	 * which have 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE.
+	 */
+	if (N_HIGH_MEMORY == N_NORMAL_MEMORY)
+		zone_last = ZONE_MOVABLE;
+
+	/*
+	 * check whether node_states[N_NORMAL_MEMORY] will be changed.
+	 * If the memory to be offline is in a zone of 0...zone_last,
+	 * and it is the last present memory, 0...zone_last will
+	 * become empty after offline , thus we can determind we will
+	 * need to clear the node from node_states[N_NORMAL_MEMORY].
+	 */
+	for (zt = 0; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (zone_idx(zone) <= zone_last && nr_pages >= present_pages)
+		arg->status_change_nid_normal = zone_to_nid(zone);
+	else
+		arg->status_change_nid_normal = -1;
+
+	/*
+	 * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE
+	 */
+	zone_last = ZONE_MOVABLE;
+
+	/*
+	 * check whether node_states[N_HIGH_MEMORY] will be changed
+	 * If we try to offline the last present @nr_pages from the node,
+	 * we can determind we will need to clear the node from
+	 * node_states[N_HIGH_MEMORY].
+	 */
+	for (; zt <= zone_last; zt++)
+		present_pages += pgdat->node_zones[zt].present_pages;
+	if (nr_pages >= present_pages)
+		arg->status_change_nid = zone_to_nid(zone);
+	else
+		arg->status_change_nid = -1;
+}
+
+static void node_states_clear_node(int node, struct memory_notify *arg)
+{
+	if (arg->status_change_nid_normal >= 0)
+		node_clear_state(node, N_NORMAL_MEMORY);
+
+	if ((N_HIGH_MEMORY != N_NORMAL_MEMORY) &&
+	    (arg->status_change_nid >= 0))
+		node_clear_state(node, N_HIGH_MEMORY);
+}
+
 static int __ref __offline_pages(unsigned long start_pfn,
 		  unsigned long end_pfn, unsigned long timeout)
 {
@@ -893,16 +1177,19 @@ static int __ref __offline_pages(unsigned long start_pfn,
 	node = zone_to_nid(zone);
 	nr_pages = end_pfn - start_pfn;
 
+	ret = -EINVAL;
+	if (zone_idx(zone) <= ZONE_NORMAL && !can_offline_normal(zone, nr_pages))
+		goto out;
+
 	/* set above range as isolated */
-	ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+	ret = start_isolate_page_range(start_pfn, end_pfn,
+				       MIGRATE_MOVABLE, true);
 	if (ret)
 		goto out;
 
 	arg.start_pfn = start_pfn;
 	arg.nr_pages = nr_pages;
-	arg.status_change_nid = -1;
-	if (nr_pages >= node_present_pages(node))
-		arg.status_change_nid = node;
+	node_states_check_changes_offline(nr_pages, zone, &arg);
 
 	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
 	ret = notifier_to_errno(ret);
@@ -975,10 +1262,9 @@ repeat:
 	} else
 		zone_pcp_update(zone);
 
-	if (!node_present_pages(node)) {
-		node_clear_state(node, N_HIGH_MEMORY);
+	node_states_clear_node(node, &arg);
+	if (arg.status_change_nid >= 0)
 		kswapd_stop(node);
-	}
 
 	vm_total_pages = nr_free_pagecache_pages();
 	writeback_set_ratelimit();
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4ea600da8940..05b28361a39b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1907,7 +1907,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, int node)
 {
 	struct mempolicy *pol;
-	struct zonelist *zl;
 	struct page *page;
 	unsigned int cpuset_mems_cookie;
 
@@ -1926,23 +1925,11 @@ retry_cpuset:
 
 		return page;
 	}
-	zl = policy_zonelist(gfp, pol, node);
-	if (unlikely(mpol_needs_cond_ref(pol))) {
-		/*
-		 * slow path: ref counted shared policy
-		 */
-		struct page *page =  __alloc_pages_nodemask(gfp, order,
-						zl, policy_nodemask(gfp, pol));
-		__mpol_put(pol);
-		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
-			goto retry_cpuset;
-		return page;
-	}
-	/*
-	 * fast path:  default or task policy
-	 */
-	page = __alloc_pages_nodemask(gfp, order, zl,
+	page = __alloc_pages_nodemask(gfp, order,
+				      policy_zonelist(gfp, pol, node),
 				      policy_nodemask(gfp, pol));
+	if (unlikely(mpol_needs_cond_ref(pol)))
+		__mpol_put(pol);
 	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
 		goto retry_cpuset;
 	return page;
diff --git a/mm/migrate.c b/mm/migrate.c
index 77ed2d773705..3f675ca08279 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -35,6 +35,7 @@
 #include <linux/hugetlb.h>
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
+#include <linux/balloon_compaction.h>
 
 #include <asm/tlbflush.h>
 
@@ -79,7 +80,30 @@ void putback_lru_pages(struct list_head *l)
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		putback_lru_page(page);
+			putback_lru_page(page);
+	}
+}
+
+/*
+ * Put previously isolated pages back onto the appropriate lists
+ * from where they were once taken off for compaction/migration.
+ *
+ * This function shall be used instead of putback_lru_pages(),
+ * whenever the isolated pageset has been built by isolate_migratepages_range()
+ */
+void putback_movable_pages(struct list_head *l)
+{
+	struct page *page;
+	struct page *page2;
+
+	list_for_each_entry_safe(page, page2, l, lru) {
+		list_del(&page->lru);
+		dec_zone_page_state(page, NR_ISOLATED_ANON +
+				page_is_file_cache(page));
+		if (unlikely(balloon_page_movable(page)))
+			balloon_page_putback(page);
+		else
+			putback_lru_page(page);
 	}
 }
 
@@ -91,8 +115,6 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	swp_entry_t entry;
- 	pgd_t *pgd;
- 	pud_t *pud;
  	pmd_t *pmd;
 	pte_t *ptep, pte;
  	spinlock_t *ptl;
@@ -103,19 +125,11 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma,
 			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))
+		pmd = mm_find_pmd(mm, addr);
+		if (!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);
 
@@ -286,7 +300,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 		/* Anonymous page without mapping */
 		if (page_count(page) != 1)
 			return -EAGAIN;
-		return 0;
+		return MIGRATEPAGE_SUCCESS;
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -356,7 +370,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 	spin_unlock_irq(&mapping->tree_lock);
 
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 
 /*
@@ -372,7 +386,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	if (!mapping) {
 		if (page_count(page) != 1)
 			return -EAGAIN;
-		return 0;
+		return MIGRATEPAGE_SUCCESS;
 	}
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -399,7 +413,7 @@ int migrate_huge_page_move_mapping(struct address_space *mapping,
 	page_unfreeze_refs(page, expected_count - 1);
 
 	spin_unlock_irq(&mapping->tree_lock);
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 
 /*
@@ -486,11 +500,11 @@ int migrate_page(struct address_space *mapping,
 
 	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
 
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
 	migrate_page_copy(newpage, page);
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 EXPORT_SYMBOL(migrate_page);
 
@@ -513,7 +527,7 @@ int buffer_migrate_page(struct address_space *mapping,
 
 	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
 
-	if (rc)
+	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
 
 	/*
@@ -549,7 +563,7 @@ int buffer_migrate_page(struct address_space *mapping,
 
 	} while (bh != head);
 
-	return 0;
+	return MIGRATEPAGE_SUCCESS;
 }
 EXPORT_SYMBOL(buffer_migrate_page);
 #endif
@@ -628,7 +642,7 @@ static int fallback_migrate_page(struct address_space *mapping,
  *
  * Return value:
  *   < 0 - error code
- *  == 0 - success
+ *  MIGRATEPAGE_SUCCESS - success
  */
 static int move_to_new_page(struct page *newpage, struct page *page,
 				int remap_swapcache, enum migrate_mode mode)
@@ -665,7 +679,7 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	else
 		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
-	if (rc) {
+	if (rc != MIGRATEPAGE_SUCCESS) {
 		newpage->mapping = NULL;
 	} else {
 		if (remap_swapcache)
@@ -778,6 +792,18 @@ static int __unmap_and_move(struct page *page, struct page *newpage,
 		}
 	}
 
+	if (unlikely(balloon_page_movable(page))) {
+		/*
+		 * A ballooned page does not need any special attention from
+		 * physical to virtual reverse mapping procedures.
+		 * Skip any attempt to unmap PTEs or to remap swap cache,
+		 * in order to avoid burning cycles at rmap level, and perform
+		 * the page migration right away (proteced by page lock).
+		 */
+		rc = balloon_page_migrate(newpage, page, mode);
+		goto uncharge;
+	}
+
 	/*
 	 * Corner case handling:
 	 * 1. When a new swap-cache page is read into, it is added to the LRU
@@ -814,7 +840,9 @@ skip_unmap:
 		put_anon_vma(anon_vma);
 
 uncharge:
-	mem_cgroup_end_migration(mem, page, newpage, rc == 0);
+	mem_cgroup_end_migration(mem, page, newpage,
+				 (rc == MIGRATEPAGE_SUCCESS ||
+				  rc == MIGRATEPAGE_BALLOON_SUCCESS));
 unlock:
 	unlock_page(page);
 out:
@@ -846,6 +874,18 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 			goto out;
 
 	rc = __unmap_and_move(page, newpage, force, offlining, mode);
+
+	if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) {
+		/*
+		 * A ballooned page has been migrated already.
+		 * Now, it's the time to wrap-up counters,
+		 * handle the page back to Buddy and return.
+		 */
+		dec_zone_page_state(page, NR_ISOLATED_ANON +
+				    page_is_file_cache(page));
+		balloon_page_free(page);
+		return MIGRATEPAGE_SUCCESS;
+	}
 out:
 	if (rc != -EAGAIN) {
 		/*
@@ -987,7 +1027,7 @@ int migrate_pages(struct list_head *from,
 			case -EAGAIN:
 				retry++;
 				break;
-			case 0:
+			case MIGRATEPAGE_SUCCESS:
 				break;
 			default:
 				/* Permanent failure */
@@ -996,15 +1036,12 @@ int migrate_pages(struct list_head *from,
 			}
 		}
 	}
-	rc = 0;
+	rc = nr_failed + retry;
 out:
 	if (!swapwrite)
 		current->flags &= ~PF_SWAPWRITE;
 
-	if (rc)
-		return rc;
-
-	return nr_failed + retry;
+	return rc;
 }
 
 int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
@@ -1024,7 +1061,7 @@ int migrate_huge_page(struct page *hpage, new_page_t get_new_page,
 			/* try again */
 			cond_resched();
 			break;
-		case 0:
+		case MIGRATEPAGE_SUCCESS:
 			goto out;
 		default:
 			rc = -EIO;
diff --git a/mm/mmap.c b/mm/mmap.c
index 7d416055f08c..f940062c8d4b 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -31,6 +31,7 @@
 #include <linux/audit.h>
 #include <linux/khugepaged.h>
 #include <linux/uprobes.h>
+#include <linux/rbtree_augmented.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -311,40 +312,88 @@ out:
 	return retval;
 }
 
+static long vma_compute_subtree_gap(struct vm_area_struct *vma)
+{
+	unsigned long max, subtree_gap;
+	max = vma->vm_start;
+	if (vma->vm_prev)
+		max -= vma->vm_prev->vm_end;
+	if (vma->vm_rb.rb_left) {
+		subtree_gap = rb_entry(vma->vm_rb.rb_left,
+				struct vm_area_struct, vm_rb)->rb_subtree_gap;
+		if (subtree_gap > max)
+			max = subtree_gap;
+	}
+	if (vma->vm_rb.rb_right) {
+		subtree_gap = rb_entry(vma->vm_rb.rb_right,
+				struct vm_area_struct, vm_rb)->rb_subtree_gap;
+		if (subtree_gap > max)
+			max = subtree_gap;
+	}
+	return max;
+}
+
 #ifdef CONFIG_DEBUG_VM_RB
 static int browse_rb(struct rb_root *root)
 {
-	int i = 0, j;
+	int i = 0, j, bug = 0;
 	struct rb_node *nd, *pn = NULL;
 	unsigned long prev = 0, pend = 0;
 
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct vm_area_struct *vma;
 		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
-		if (vma->vm_start < prev)
-			printk("vm_start %lx prev %lx\n", vma->vm_start, prev), i = -1;
-		if (vma->vm_start < pend)
+		if (vma->vm_start < prev) {
+			printk("vm_start %lx prev %lx\n", vma->vm_start, prev);
+			bug = 1;
+		}
+		if (vma->vm_start < pend) {
 			printk("vm_start %lx pend %lx\n", vma->vm_start, pend);
-		if (vma->vm_start > vma->vm_end)
-			printk("vm_end %lx < vm_start %lx\n", vma->vm_end, vma->vm_start);
+			bug = 1;
+		}
+		if (vma->vm_start > vma->vm_end) {
+			printk("vm_end %lx < vm_start %lx\n",
+				vma->vm_end, vma->vm_start);
+			bug = 1;
+		}
+		if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) {
+			printk("free gap %lx, correct %lx\n",
+			       vma->rb_subtree_gap,
+			       vma_compute_subtree_gap(vma));
+			bug = 1;
+		}
 		i++;
 		pn = nd;
 		prev = vma->vm_start;
 		pend = vma->vm_end;
 	}
 	j = 0;
-	for (nd = pn; nd; nd = rb_prev(nd)) {
+	for (nd = pn; nd; nd = rb_prev(nd))
 		j++;
+	if (i != j) {
+		printk("backwards %d, forwards %d\n", j, i);
+		bug = 1;
+	}
+	return bug ? -1 : i;
+}
+
+static void validate_mm_rb(struct rb_root *root, struct vm_area_struct *ignore)
+{
+	struct rb_node *nd;
+
+	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
+		struct vm_area_struct *vma;
+		vma = rb_entry(nd, struct vm_area_struct, vm_rb);
+		BUG_ON(vma != ignore &&
+		       vma->rb_subtree_gap != vma_compute_subtree_gap(vma));
 	}
-	if (i != j)
-		printk("backwards %d, forwards %d\n", j, i), i = 0;
-	return i;
 }
 
 void validate_mm(struct mm_struct *mm)
 {
 	int bug = 0;
 	int i = 0;
+	unsigned long highest_address = 0;
 	struct vm_area_struct *vma = mm->mmap;
 	while (vma) {
 		struct anon_vma_chain *avc;
@@ -352,20 +401,73 @@ void validate_mm(struct mm_struct *mm)
 		list_for_each_entry(avc, &vma->anon_vma_chain, same_vma)
 			anon_vma_interval_tree_verify(avc);
 		vma_unlock_anon_vma(vma);
+		highest_address = vma->vm_end;
 		vma = vma->vm_next;
 		i++;
 	}
-	if (i != mm->map_count)
-		printk("map_count %d vm_next %d\n", mm->map_count, i), bug = 1;
+	if (i != mm->map_count) {
+		printk("map_count %d vm_next %d\n", mm->map_count, i);
+		bug = 1;
+	}
+	if (highest_address != mm->highest_vm_end) {
+		printk("mm->highest_vm_end %lx, found %lx\n",
+		       mm->highest_vm_end, highest_address);
+		bug = 1;
+	}
 	i = browse_rb(&mm->mm_rb);
-	if (i != mm->map_count)
-		printk("map_count %d rb %d\n", mm->map_count, i), bug = 1;
+	if (i != mm->map_count) {
+		printk("map_count %d rb %d\n", mm->map_count, i);
+		bug = 1;
+	}
 	BUG_ON(bug);
 }
 #else
+#define validate_mm_rb(root, ignore) do { } while (0)
 #define validate_mm(mm) do { } while (0)
 #endif
 
+RB_DECLARE_CALLBACKS(static, vma_gap_callbacks, struct vm_area_struct, vm_rb,
+		     unsigned long, rb_subtree_gap, vma_compute_subtree_gap)
+
+/*
+ * Update augmented rbtree rb_subtree_gap values after vma->vm_start or
+ * vma->vm_prev->vm_end values changed, without modifying the vma's position
+ * in the rbtree.
+ */
+static void vma_gap_update(struct vm_area_struct *vma)
+{
+	/*
+	 * As it turns out, RB_DECLARE_CALLBACKS() already created a callback
+	 * function that does exacltly what we want.
+	 */
+	vma_gap_callbacks_propagate(&vma->vm_rb, NULL);
+}
+
+static inline void vma_rb_insert(struct vm_area_struct *vma,
+				 struct rb_root *root)
+{
+	/* All rb_subtree_gap values must be consistent prior to insertion */
+	validate_mm_rb(root, NULL);
+
+	rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
+}
+
+static void vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
+{
+	/*
+	 * All rb_subtree_gap values must be consistent prior to erase,
+	 * with the possible exception of the vma being erased.
+	 */
+	validate_mm_rb(root, vma);
+
+	/*
+	 * Note rb_erase_augmented is a fairly large inline function,
+	 * so make sure we instantiate it only once with our desired
+	 * augmented rbtree callbacks.
+	 */
+	rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
+}
+
 /*
  * vma has some anon_vma assigned, and is already inserted on that
  * anon_vma's interval trees.
@@ -435,8 +537,25 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr,
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct rb_node **rb_link, struct rb_node *rb_parent)
 {
+	/* Update tracking information for the gap following the new vma. */
+	if (vma->vm_next)
+		vma_gap_update(vma->vm_next);
+	else
+		mm->highest_vm_end = vma->vm_end;
+
+	/*
+	 * vma->vm_prev wasn't known when we followed the rbtree to find the
+	 * correct insertion point for that vma. As a result, we could not
+	 * update the vma vm_rb parents rb_subtree_gap values on the way down.
+	 * So, we first insert the vma with a zero rb_subtree_gap value
+	 * (to be consistent with what we did on the way down), and then
+	 * immediately update the gap to the correct value. Finally we
+	 * rebalance the rbtree after all augmented values have been set.
+	 */
 	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
-	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
+	vma->rb_subtree_gap = 0;
+	vma_gap_update(vma);
+	vma_rb_insert(vma, &mm->mm_rb);
 }
 
 static void __vma_link_file(struct vm_area_struct *vma)
@@ -512,12 +631,12 @@ static inline void
 __vma_unlink(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev)
 {
-	struct vm_area_struct *next = vma->vm_next;
+	struct vm_area_struct *next;
 
-	prev->vm_next = next;
+	vma_rb_erase(vma, &mm->mm_rb);
+	prev->vm_next = next = vma->vm_next;
 	if (next)
 		next->vm_prev = prev;
-	rb_erase(&vma->vm_rb, &mm->mm_rb);
 	if (mm->mmap_cache == vma)
 		mm->mmap_cache = prev;
 }
@@ -539,6 +658,7 @@ int vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	struct rb_root *root = NULL;
 	struct anon_vma *anon_vma = NULL;
 	struct file *file = vma->vm_file;
+	bool start_changed = false, end_changed = false;
 	long adjust_next = 0;
 	int remove_next = 0;
 
@@ -629,8 +749,14 @@ again:			remove_next = 1 + (end > next->vm_end);
 			vma_interval_tree_remove(next, root);
 	}
 
-	vma->vm_start = start;
-	vma->vm_end = end;
+	if (start != vma->vm_start) {
+		vma->vm_start = start;
+		start_changed = true;
+	}
+	if (end != vma->vm_end) {
+		vma->vm_end = end;
+		end_changed = true;
+	}
 	vma->vm_pgoff = pgoff;
 	if (adjust_next) {
 		next->vm_start += adjust_next << PAGE_SHIFT;
@@ -659,6 +785,15 @@ again:			remove_next = 1 + (end > next->vm_end);
 		 * (it may either follow vma or precede it).
 		 */
 		__insert_vm_struct(mm, insert);
+	} else {
+		if (start_changed)
+			vma_gap_update(vma);
+		if (end_changed) {
+			if (!next)
+				mm->highest_vm_end = end;
+			else if (!adjust_next)
+				vma_gap_update(next);
+		}
 	}
 
 	if (anon_vma) {
@@ -692,10 +827,13 @@ again:			remove_next = 1 + (end > next->vm_end);
 		 * we must remove another next too. It would clutter
 		 * up the code too much to do both in one go.
 		 */
-		if (remove_next == 2) {
-			next = vma->vm_next;
+		next = vma->vm_next;
+		if (remove_next == 2)
 			goto again;
-		}
+		else if (next)
+			vma_gap_update(next);
+		else
+			mm->highest_vm_end = end;
 	}
 	if (insert && file)
 		uprobe_mmap(insert);
@@ -1167,8 +1305,9 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len,
 		 * memory so no accounting is necessary
 		 */
 		file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len,
-						VM_NORESERVE, &user,
-						HUGETLB_ANONHUGE_INODE);
+				VM_NORESERVE,
+				&user, HUGETLB_ANONHUGE_INODE,
+				(flags >> MAP_HUGE_SHIFT) & MAP_HUGE_MASK);
 		if (IS_ERR(file))
 			return PTR_ERR(file);
 	}
@@ -1414,6 +1553,206 @@ unacct_error:
 	return error;
 }
 
+unsigned long unmapped_area(struct vm_unmapped_area_info *info)
+{
+	/*
+	 * We implement the search by looking for an rbtree node that
+	 * immediately follows a suitable gap. That is,
+	 * - gap_start = vma->vm_prev->vm_end <= info->high_limit - length;
+	 * - gap_end   = vma->vm_start        >= info->low_limit  + length;
+	 * - gap_end - gap_start >= length
+	 */
+
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long length, low_limit, high_limit, gap_start, gap_end;
+
+	/* Adjust search length to account for worst case alignment overhead */
+	length = info->length + info->align_mask;
+	if (length < info->length)
+		return -ENOMEM;
+
+	/* Adjust search limits by the desired length */
+	if (info->high_limit < length)
+		return -ENOMEM;
+	high_limit = info->high_limit - length;
+
+	if (info->low_limit > high_limit)
+		return -ENOMEM;
+	low_limit = info->low_limit + length;
+
+	/* Check if rbtree root looks promising */
+	if (RB_EMPTY_ROOT(&mm->mm_rb))
+		goto check_highest;
+	vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb);
+	if (vma->rb_subtree_gap < length)
+		goto check_highest;
+
+	while (true) {
+		/* Visit left subtree if it looks promising */
+		gap_end = vma->vm_start;
+		if (gap_end >= low_limit && vma->vm_rb.rb_left) {
+			struct vm_area_struct *left =
+				rb_entry(vma->vm_rb.rb_left,
+					 struct vm_area_struct, vm_rb);
+			if (left->rb_subtree_gap >= length) {
+				vma = left;
+				continue;
+			}
+		}
+
+		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+check_current:
+		/* Check if current node has a suitable gap */
+		if (gap_start > high_limit)
+			return -ENOMEM;
+		if (gap_end >= low_limit && gap_end - gap_start >= length)
+			goto found;
+
+		/* Visit right subtree if it looks promising */
+		if (vma->vm_rb.rb_right) {
+			struct vm_area_struct *right =
+				rb_entry(vma->vm_rb.rb_right,
+					 struct vm_area_struct, vm_rb);
+			if (right->rb_subtree_gap >= length) {
+				vma = right;
+				continue;
+			}
+		}
+
+		/* Go back up the rbtree to find next candidate node */
+		while (true) {
+			struct rb_node *prev = &vma->vm_rb;
+			if (!rb_parent(prev))
+				goto check_highest;
+			vma = rb_entry(rb_parent(prev),
+				       struct vm_area_struct, vm_rb);
+			if (prev == vma->vm_rb.rb_left) {
+				gap_start = vma->vm_prev->vm_end;
+				gap_end = vma->vm_start;
+				goto check_current;
+			}
+		}
+	}
+
+check_highest:
+	/* Check highest gap, which does not precede any rbtree node */
+	gap_start = mm->highest_vm_end;
+	gap_end = ULONG_MAX;  /* Only for VM_BUG_ON below */
+	if (gap_start > high_limit)
+		return -ENOMEM;
+
+found:
+	/* We found a suitable gap. Clip it with the original low_limit. */
+	if (gap_start < info->low_limit)
+		gap_start = info->low_limit;
+
+	/* Adjust gap address to the desired alignment */
+	gap_start += (info->align_offset - gap_start) & info->align_mask;
+
+	VM_BUG_ON(gap_start + info->length > info->high_limit);
+	VM_BUG_ON(gap_start + info->length > gap_end);
+	return gap_start;
+}
+
+unsigned long unmapped_area_topdown(struct vm_unmapped_area_info *info)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	unsigned long length, low_limit, high_limit, gap_start, gap_end;
+
+	/* Adjust search length to account for worst case alignment overhead */
+	length = info->length + info->align_mask;
+	if (length < info->length)
+		return -ENOMEM;
+
+	/*
+	 * Adjust search limits by the desired length.
+	 * See implementation comment at top of unmapped_area().
+	 */
+	gap_end = info->high_limit;
+	if (gap_end < length)
+		return -ENOMEM;
+	high_limit = gap_end - length;
+
+	if (info->low_limit > high_limit)
+		return -ENOMEM;
+	low_limit = info->low_limit + length;
+
+	/* Check highest gap, which does not precede any rbtree node */
+	gap_start = mm->highest_vm_end;
+	if (gap_start <= high_limit)
+		goto found_highest;
+
+	/* Check if rbtree root looks promising */
+	if (RB_EMPTY_ROOT(&mm->mm_rb))
+		return -ENOMEM;
+	vma = rb_entry(mm->mm_rb.rb_node, struct vm_area_struct, vm_rb);
+	if (vma->rb_subtree_gap < length)
+		return -ENOMEM;
+
+	while (true) {
+		/* Visit right subtree if it looks promising */
+		gap_start = vma->vm_prev ? vma->vm_prev->vm_end : 0;
+		if (gap_start <= high_limit && vma->vm_rb.rb_right) {
+			struct vm_area_struct *right =
+				rb_entry(vma->vm_rb.rb_right,
+					 struct vm_area_struct, vm_rb);
+			if (right->rb_subtree_gap >= length) {
+				vma = right;
+				continue;
+			}
+		}
+
+check_current:
+		/* Check if current node has a suitable gap */
+		gap_end = vma->vm_start;
+		if (gap_end < low_limit)
+			return -ENOMEM;
+		if (gap_start <= high_limit && gap_end - gap_start >= length)
+			goto found;
+
+		/* Visit left subtree if it looks promising */
+		if (vma->vm_rb.rb_left) {
+			struct vm_area_struct *left =
+				rb_entry(vma->vm_rb.rb_left,
+					 struct vm_area_struct, vm_rb);
+			if (left->rb_subtree_gap >= length) {
+				vma = left;
+				continue;
+			}
+		}
+
+		/* Go back up the rbtree to find next candidate node */
+		while (true) {
+			struct rb_node *prev = &vma->vm_rb;
+			if (!rb_parent(prev))
+				return -ENOMEM;
+			vma = rb_entry(rb_parent(prev),
+				       struct vm_area_struct, vm_rb);
+			if (prev == vma->vm_rb.rb_right) {
+				gap_start = vma->vm_prev ?
+					vma->vm_prev->vm_end : 0;
+				goto check_current;
+			}
+		}
+	}
+
+found:
+	/* We found a suitable gap. Clip it with the original high_limit. */
+	if (gap_end > info->high_limit)
+		gap_end = info->high_limit;
+
+found_highest:
+	/* Compute highest gap address at the desired alignment */
+	gap_end -= info->length;
+	gap_end -= (gap_end - info->align_offset) & info->align_mask;
+
+	VM_BUG_ON(gap_end < info->low_limit);
+	VM_BUG_ON(gap_end < gap_start);
+	return gap_end;
+}
+
 /* Get an address range which is currently unmapped.
  * For shmat() with addr=0.
  *
@@ -1432,7 +1771,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
-	unsigned long start_addr;
+	struct vm_unmapped_area_info info;
 
 	if (len > TASK_SIZE)
 		return -ENOMEM;
@@ -1447,40 +1786,13 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 		    (!vma || addr + len <= vma->vm_start))
 			return addr;
 	}
-	if (len > mm->cached_hole_size) {
-	        start_addr = addr = mm->free_area_cache;
-	} else {
-	        start_addr = addr = TASK_UNMAPPED_BASE;
-	        mm->cached_hole_size = 0;
-	}
 
-full_search:
-	for (vma = find_vma(mm, addr); ; vma = vma->vm_next) {
-		/* At this point:  (!vma || addr < vma->vm_end). */
-		if (TASK_SIZE - len < addr) {
-			/*
-			 * Start a new search - just in case we missed
-			 * some holes.
-			 */
-			if (start_addr != TASK_UNMAPPED_BASE) {
-				addr = TASK_UNMAPPED_BASE;
-			        start_addr = addr;
-				mm->cached_hole_size = 0;
-				goto full_search;
-			}
-			return -ENOMEM;
-		}
-		if (!vma || addr + len <= vma->vm_start) {
-			/*
-			 * Remember the place where we stopped the search:
-			 */
-			mm->free_area_cache = addr + len;
-			return addr;
-		}
-		if (addr + mm->cached_hole_size < vma->vm_start)
-		        mm->cached_hole_size = vma->vm_start - addr;
-		addr = vma->vm_end;
-	}
+	info.flags = 0;
+	info.length = len;
+	info.low_limit = TASK_UNMAPPED_BASE;
+	info.high_limit = TASK_SIZE;
+	info.align_mask = 0;
+	return vm_unmapped_area(&info);
 }
 #endif	
 
@@ -1505,7 +1817,8 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 {
 	struct vm_area_struct *vma;
 	struct mm_struct *mm = current->mm;
-	unsigned long addr = addr0, start_addr;
+	unsigned long addr = addr0;
+	struct vm_unmapped_area_info info;
 
 	/* requested length too big for entire address space */
 	if (len > TASK_SIZE)
@@ -1523,53 +1836,12 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 			return addr;
 	}
 
-	/* check if free_area_cache is useful for us */
-	if (len <= mm->cached_hole_size) {
- 	        mm->cached_hole_size = 0;
- 		mm->free_area_cache = mm->mmap_base;
- 	}
-
-try_again:
-	/* either no address requested or can't fit in requested address hole */
-	start_addr = addr = mm->free_area_cache;
-
-	if (addr < len)
-		goto fail;
-
-	addr -= len;
-	do {
-		/*
-		 * Lookup failure means no vma is above this address,
-		 * else if new region fits below vma->vm_start,
-		 * return with success:
-		 */
-		vma = find_vma(mm, addr);
-		if (!vma || addr+len <= vma->vm_start)
-			/* remember the address as a hint for next time */
-			return (mm->free_area_cache = addr);
-
- 		/* remember the largest hole we saw so far */
- 		if (addr + mm->cached_hole_size < vma->vm_start)
- 		        mm->cached_hole_size = vma->vm_start - addr;
-
-		/* try just below the current vma->vm_start */
-		addr = vma->vm_start-len;
-	} while (len < vma->vm_start);
-
-fail:
-	/*
-	 * if hint left us with no space for the requested
-	 * mapping then try again:
-	 *
-	 * Note: this is different with the case of bottomup
-	 * which does the fully line-search, but we use find_vma
-	 * here that causes some holes skipped.
-	 */
-	if (start_addr != mm->mmap_base) {
-		mm->free_area_cache = mm->mmap_base;
-		mm->cached_hole_size = 0;
-		goto try_again;
-	}
+	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
+	info.length = len;
+	info.low_limit = PAGE_SIZE;
+	info.high_limit = mm->mmap_base;
+	info.align_mask = 0;
+	addr = vm_unmapped_area(&info);
 
 	/*
 	 * A failed mmap() very likely causes application failure,
@@ -1577,14 +1849,13 @@ fail:
 	 * can happen with large stack limits and large mmap()
 	 * allocations.
 	 */
-	mm->cached_hole_size = ~0UL;
-  	mm->free_area_cache = TASK_UNMAPPED_BASE;
-	addr = arch_get_unmapped_area(filp, addr0, len, pgoff, flags);
-	/*
-	 * Restore the topdown base:
-	 */
-	mm->free_area_cache = mm->mmap_base;
-	mm->cached_hole_size = ~0UL;
+	if (addr & ~PAGE_MASK) {
+		VM_BUG_ON(addr != -ENOMEM);
+		info.flags = 0;
+		info.low_limit = TASK_UNMAPPED_BASE;
+		info.high_limit = TASK_SIZE;
+		addr = vm_unmapped_area(&info);
+	}
 
 	return addr;
 }
@@ -1797,6 +2068,10 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address)
 				anon_vma_interval_tree_pre_update_vma(vma);
 				vma->vm_end = address;
 				anon_vma_interval_tree_post_update_vma(vma);
+				if (vma->vm_next)
+					vma_gap_update(vma->vm_next);
+				else
+					vma->vm_mm->highest_vm_end = address;
 				perf_event_mmap(vma);
 			}
 		}
@@ -1851,6 +2126,7 @@ int expand_downwards(struct vm_area_struct *vma,
 				vma->vm_start = address;
 				vma->vm_pgoff -= grow;
 				anon_vma_interval_tree_post_update_vma(vma);
+				vma_gap_update(vma);
 				perf_event_mmap(vma);
 			}
 		}
@@ -1973,14 +2249,17 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
 	insertion_point = (prev ? &prev->vm_next : &mm->mmap);
 	vma->vm_prev = NULL;
 	do {
-		rb_erase(&vma->vm_rb, &mm->mm_rb);
+		vma_rb_erase(vma, &mm->mm_rb);
 		mm->map_count--;
 		tail_vma = vma;
 		vma = vma->vm_next;
 	} while (vma && vma->vm_start < end);
 	*insertion_point = vma;
-	if (vma)
+	if (vma) {
 		vma->vm_prev = prev;
+		vma_gap_update(vma);
+	} else
+		mm->highest_vm_end = prev ? prev->vm_end : 0;
 	tail_vma->vm_next = NULL;
 	if (mm->unmap_area == arch_unmap_area)
 		addr = prev ? prev->vm_end : mm->mmap_base;
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 79e0f3e24831..18f1ae2b45de 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -44,48 +44,6 @@ int sysctl_oom_kill_allocating_task;
 int sysctl_oom_dump_tasks = 1;
 static DEFINE_SPINLOCK(zone_scan_lock);
 
-/*
- * compare_swap_oom_score_adj() - compare and swap current's oom_score_adj
- * @old_val: old oom_score_adj for compare
- * @new_val: new oom_score_adj for swap
- *
- * Sets the oom_score_adj value for current to @new_val iff its present value is
- * @old_val.  Usually used to reinstate a previous value to prevent racing with
- * userspacing tuning the value in the interim.
- */
-void compare_swap_oom_score_adj(int old_val, int new_val)
-{
-	struct sighand_struct *sighand = current->sighand;
-
-	spin_lock_irq(&sighand->siglock);
-	if (current->signal->oom_score_adj == old_val)
-		current->signal->oom_score_adj = new_val;
-	trace_oom_score_adj_update(current);
-	spin_unlock_irq(&sighand->siglock);
-}
-
-/**
- * test_set_oom_score_adj() - set current's oom_score_adj and return old value
- * @new_val: new oom_score_adj value
- *
- * Sets the oom_score_adj value for current to @new_val with proper
- * synchronization and returns the old value.  Usually used to temporarily
- * set a value, save the old value in the caller, and then reinstate it later.
- */
-int test_set_oom_score_adj(int new_val)
-{
-	struct sighand_struct *sighand = current->sighand;
-	int old_val;
-
-	spin_lock_irq(&sighand->siglock);
-	old_val = current->signal->oom_score_adj;
-	current->signal->oom_score_adj = new_val;
-	trace_oom_score_adj_update(current);
-	spin_unlock_irq(&sighand->siglock);
-
-	return old_val;
-}
-
 #ifdef CONFIG_NUMA
 /**
  * has_intersects_mems_allowed() - check task eligiblity for kill
@@ -193,7 +151,7 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg,
 	if (!p)
 		return 0;
 
-	adj = p->signal->oom_score_adj;
+	adj = (long)p->signal->oom_score_adj;
 	if (adj == OOM_SCORE_ADJ_MIN) {
 		task_unlock(p);
 		return 0;
@@ -310,26 +268,20 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task,
 	if (!task->mm)
 		return OOM_SCAN_CONTINUE;
 
-	if (task->flags & PF_EXITING) {
+	/*
+	 * If task is allocating a lot of memory and has been marked to be
+	 * killed first if it triggers an oom, then select it.
+	 */
+	if (oom_task_origin(task))
+		return OOM_SCAN_SELECT;
+
+	if (task->flags & PF_EXITING && !force_kill) {
 		/*
-		 * If task is current and is in the process of releasing memory,
-		 * allow the "kill" to set TIF_MEMDIE, which will allow it to
-		 * access memory reserves.  Otherwise, it may stall forever.
-		 *
-		 * The iteration isn't broken here, however, in case other
-		 * threads are found to have already been oom killed.
+		 * If this task is not being ptraced on exit, then wait for it
+		 * to finish before killing some other task unnecessarily.
 		 */
-		if (task == current)
-			return OOM_SCAN_SELECT;
-		else if (!force_kill) {
-			/*
-			 * If this task is not being ptraced on exit, then wait
-			 * for it to finish before killing some other task
-			 * unnecessarily.
-			 */
-			if (!(task->group_leader->ptrace & PT_TRACE_EXIT))
-				return OOM_SCAN_ABORT;
-		}
+		if (!(task->group_leader->ptrace & PT_TRACE_EXIT))
+			return OOM_SCAN_ABORT;
 	}
 	return OOM_SCAN_OK;
 }
@@ -412,7 +364,7 @@ static void dump_tasks(const struct mem_cgroup *memcg, const nodemask_t *nodemas
 			continue;
 		}
 
-		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5d %s\n",
+		pr_info("[%5d] %5d %5d %8lu %8lu %7lu %8lu         %5hd %s\n",
 			task->pid, from_kuid(&init_user_ns, task_uid(task)),
 			task->tgid, task->mm->total_vm, get_mm_rss(task->mm),
 			task->mm->nr_ptes,
@@ -428,7 +380,7 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order,
 {
 	task_lock(current);
 	pr_warning("%s invoked oom-killer: gfp_mask=0x%x, order=%d, "
-		"oom_score_adj=%d\n",
+		"oom_score_adj=%hd\n",
 		current->comm, gfp_mask, order,
 		current->signal->oom_score_adj);
 	cpuset_print_task_mems_allowed(current);
@@ -706,11 +658,11 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask,
 		return;
 
 	/*
-	 * If current has a pending SIGKILL, then automatically select it.  The
-	 * goal is to allow it to allocate so that it may quickly exit and free
-	 * its memory.
+	 * If current has a pending SIGKILL or is exiting, then automatically
+	 * select it.  The goal is to allow it to allocate so that it may
+	 * quickly exit and free its memory.
 	 */
-	if (fatal_signal_pending(current)) {
+	if (fatal_signal_pending(current) || current->flags & PF_EXITING) {
 		set_thread_flag(TIF_MEMDIE);
 		return;
 	}
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 830893b2b3c7..6f4271224493 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1069,7 +1069,7 @@ static void bdi_update_bandwidth(struct backing_dev_info *bdi,
 }
 
 /*
- * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr()
+ * After a task dirtied this many pages, balance_dirty_pages_ratelimited()
  * will look to see if it needs to start dirty throttling.
  *
  * If dirty_poll_interval is too low, big NUMA machines will call the expensive
@@ -1436,9 +1436,8 @@ static DEFINE_PER_CPU(int, bdp_ratelimits);
 DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
 
 /**
- * balance_dirty_pages_ratelimited_nr - balance dirty memory state
+ * balance_dirty_pages_ratelimited - balance dirty memory state
  * @mapping: address_space which was dirtied
- * @nr_pages_dirtied: number of pages which the caller has just dirtied
  *
  * Processes which are dirtying memory should call in here once for each page
  * which was newly dirtied.  The function will periodically check the system's
@@ -1449,8 +1448,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
  * limit we decrease the ratelimiting by a lot, to prevent individual processes
  * from overshooting the limit by (ratelimit_pages) each.
  */
-void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
-					unsigned long nr_pages_dirtied)
+void balance_dirty_pages_ratelimited(struct address_space *mapping)
 {
 	struct backing_dev_info *bdi = mapping->backing_dev_info;
 	int ratelimit;
@@ -1484,6 +1482,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	 */
 	p = &__get_cpu_var(dirty_throttle_leaks);
 	if (*p > 0 && current->nr_dirtied < ratelimit) {
+		unsigned long nr_pages_dirtied;
 		nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
 		*p -= nr_pages_dirtied;
 		current->nr_dirtied += nr_pages_dirtied;
@@ -1493,7 +1492,7 @@ void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
 	if (unlikely(current->nr_dirtied >= ratelimit))
 		balance_dirty_pages(mapping, current->nr_dirtied);
 }
-EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
+EXPORT_SYMBOL(balance_dirty_pages_ratelimited);
 
 void throttle_vm_writeout(gfp_t gfp_mask)
 {
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7e208f0ad68c..5a8d339d282a 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -667,11 +667,13 @@ static void free_pcppages_bulk(struct zone *zone, int count,
 			/* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */
 			__free_one_page(page, zone, 0, mt);
 			trace_mm_page_pcpu_drain(page, 0, mt);
-			if (is_migrate_cma(mt))
-				__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
+			if (likely(get_pageblock_migratetype(page) != MIGRATE_ISOLATE)) {
+				__mod_zone_page_state(zone, NR_FREE_PAGES, 1);
+				if (is_migrate_cma(mt))
+					__mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1);
+			}
 		} while (--to_free && --batch_free && !list_empty(list));
 	}
-	__mod_zone_page_state(zone, NR_FREE_PAGES, count);
 	spin_unlock(&zone->lock);
 }
 
@@ -1392,21 +1394,22 @@ int capture_free_page(struct page *page, int alloc_order, int migratetype)
 
 	zone = page_zone(page);
 	order = page_order(page);
+	mt = get_pageblock_migratetype(page);
 
-	/* Obey watermarks as if the page was being allocated */
-	watermark = low_wmark_pages(zone) + (1 << order);
-	if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
-		return 0;
+	if (mt != MIGRATE_ISOLATE) {
+		/* Obey watermarks as if the page was being allocated */
+		watermark = low_wmark_pages(zone) + (1 << order);
+		if (!zone_watermark_ok(zone, 0, watermark, 0, 0))
+			return 0;
+
+		__mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
+	}
 
 	/* Remove page from free list */
 	list_del(&page->lru);
 	zone->free_area[order].nr_free--;
 	rmv_page_order(page);
 
-	mt = get_pageblock_migratetype(page);
-	if (unlikely(mt != MIGRATE_ISOLATE))
-		__mod_zone_freepage_state(zone, -(1UL << alloc_order), mt);
-
 	if (alloc_order != order)
 		expand(zone, page, alloc_order, order,
 			&zone->free_area[order], migratetype);
@@ -1871,7 +1874,7 @@ zonelist_scan:
 	 */
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 						high_zoneidx, nodemask) {
-		if (NUMA_BUILD && zlc_active &&
+		if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
 			!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
 		if ((alloc_flags & ALLOC_CPUSET) &&
@@ -1917,7 +1920,8 @@ zonelist_scan:
 				    classzone_idx, alloc_flags))
 				goto try_this_zone;
 
-			if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) {
+			if (IS_ENABLED(CONFIG_NUMA) &&
+					!did_zlc_setup && nr_online_nodes > 1) {
 				/*
 				 * we do zlc_setup if there are multiple nodes
 				 * and before considering the first zone allowed
@@ -1936,7 +1940,7 @@ zonelist_scan:
 			 * As we may have just activated ZLC, check if the first
 			 * eligible zone has failed zone_reclaim recently.
 			 */
-			if (NUMA_BUILD && zlc_active &&
+			if (IS_ENABLED(CONFIG_NUMA) && zlc_active &&
 				!zlc_zone_worth_trying(zonelist, z, allowednodes))
 				continue;
 
@@ -1962,11 +1966,11 @@ try_this_zone:
 		if (page)
 			break;
 this_zone_full:
-		if (NUMA_BUILD)
+		if (IS_ENABLED(CONFIG_NUMA))
 			zlc_mark_zone_full(zonelist, z);
 	}
 
-	if (unlikely(NUMA_BUILD && page == NULL && zlc_active)) {
+	if (unlikely(IS_ENABLED(CONFIG_NUMA) && page == NULL && zlc_active)) {
 		/* Disable zlc cache for second zonelist scan */
 		zlc_active = 0;
 		goto zonelist_scan;
@@ -2266,7 +2270,7 @@ __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order,
 		return NULL;
 
 	/* After successful reclaim, reconsider all zones for allocation */
-	if (NUMA_BUILD)
+	if (IS_ENABLED(CONFIG_NUMA))
 		zlc_clear_zones_full(zonelist);
 
 retry:
@@ -2412,7 +2416,8 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	 * allowed per node queues are empty and that nodes are
 	 * over allocated.
 	 */
-	if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE)
+	if (IS_ENABLED(CONFIG_NUMA) &&
+			(gfp_mask & GFP_THISNODE) == GFP_THISNODE)
 		goto nopage;
 
 restart:
@@ -2819,7 +2824,7 @@ unsigned int nr_free_pagecache_pages(void)
 
 static inline void show_node(struct zone *zone)
 {
-	if (NUMA_BUILD)
+	if (IS_ENABLED(CONFIG_NUMA))
 		printk("Node %d ", zone_to_nid(zone));
 }
 
@@ -2877,6 +2882,31 @@ out:
 
 #define K(x) ((x) << (PAGE_SHIFT-10))
 
+static void show_migration_types(unsigned char type)
+{
+	static const char types[MIGRATE_TYPES] = {
+		[MIGRATE_UNMOVABLE]	= 'U',
+		[MIGRATE_RECLAIMABLE]	= 'E',
+		[MIGRATE_MOVABLE]	= 'M',
+		[MIGRATE_RESERVE]	= 'R',
+#ifdef CONFIG_CMA
+		[MIGRATE_CMA]		= 'C',
+#endif
+		[MIGRATE_ISOLATE]	= 'I',
+	};
+	char tmp[MIGRATE_TYPES + 1];
+	char *p = tmp;
+	int i;
+
+	for (i = 0; i < MIGRATE_TYPES; i++) {
+		if (type & (1 << i))
+			*p++ = types[i];
+	}
+
+	*p = '\0';
+	printk("(%s) ", tmp);
+}
+
 /*
  * Show free area list (used inside shift_scroll-lock stuff)
  * We also calculate the percentage fragmentation. We do this by counting the
@@ -3005,6 +3035,7 @@ void show_free_areas(unsigned int filter)
 
 	for_each_populated_zone(zone) {
  		unsigned long nr[MAX_ORDER], flags, order, total = 0;
+		unsigned char types[MAX_ORDER];
 
 		if (skip_free_areas_node(filter, zone_to_nid(zone)))
 			continue;
@@ -3013,12 +3044,24 @@ void show_free_areas(unsigned int filter)
 
 		spin_lock_irqsave(&zone->lock, flags);
 		for (order = 0; order < MAX_ORDER; order++) {
-			nr[order] = zone->free_area[order].nr_free;
+			struct free_area *area = &zone->free_area[order];
+			int type;
+
+			nr[order] = area->nr_free;
 			total += nr[order] << order;
+
+			types[order] = 0;
+			for (type = 0; type < MIGRATE_TYPES; type++) {
+				if (!list_empty(&area->free_list[type]))
+					types[order] |= 1 << type;
+			}
 		}
 		spin_unlock_irqrestore(&zone->lock, flags);
-		for (order = 0; order < MAX_ORDER; order++)
+		for (order = 0; order < MAX_ORDER; order++) {
 			printk("%lu*%lukB ", nr[order], K(1UL) << order);
+			if (nr[order])
+				show_migration_types(types[order]);
+		}
 		printk("= %lukB\n", K(total));
 	}
 
@@ -5175,10 +5218,6 @@ static void __setup_per_zone_wmarks(void)
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
 		zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1);
 
-		zone->watermark[WMARK_MIN] += cma_wmark_pages(zone);
-		zone->watermark[WMARK_LOW] += cma_wmark_pages(zone);
-		zone->watermark[WMARK_HIGH] += cma_wmark_pages(zone);
-
 		setup_zone_migrate_reserve(zone);
 		spin_unlock_irqrestore(&zone->lock, flags);
 	}
@@ -5576,7 +5615,8 @@ void set_pageblock_flags_group(struct page *page, unsigned long flags,
  * MIGRATE_MOVABLE block might include unmovable pages. It means you can't
  * expect this function should be exact.
  */
-bool has_unmovable_pages(struct zone *zone, struct page *page, int count)
+bool has_unmovable_pages(struct zone *zone, struct page *page, int count,
+			 bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn, iter, found;
 	int mt;
@@ -5611,6 +5651,13 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count)
 			continue;
 		}
 
+		/*
+		 * The HWPoisoned page may be not in buddy system, and
+		 * page_count() is not 0.
+		 */
+		if (skip_hwpoisoned_pages && PageHWPoison(page))
+			continue;
+
 		if (!PageLRU(page))
 			found++;
 		/*
@@ -5653,7 +5700,7 @@ bool is_pageblock_removable_nolock(struct page *page)
 			zone->zone_start_pfn + zone->spanned_pages <= pfn)
 		return false;
 
-	return !has_unmovable_pages(zone, page, 0);
+	return !has_unmovable_pages(zone, page, 0, true);
 }
 
 #ifdef CONFIG_CMA
@@ -5711,58 +5758,10 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 				    0, false, MIGRATE_SYNC);
 	}
 
-	putback_lru_pages(&cc->migratepages);
+	putback_movable_pages(&cc->migratepages);
 	return ret > 0 ? 0 : ret;
 }
 
-/*
- * Update zone's cma pages counter used for watermark level calculation.
- */
-static inline void __update_cma_watermarks(struct zone *zone, int count)
-{
-	unsigned long flags;
-	spin_lock_irqsave(&zone->lock, flags);
-	zone->min_cma_pages += count;
-	spin_unlock_irqrestore(&zone->lock, flags);
-	setup_per_zone_wmarks();
-}
-
-/*
- * Trigger memory pressure bump to reclaim some pages in order to be able to
- * allocate 'count' pages in single page units. Does similar work as
- *__alloc_pages_slowpath() function.
- */
-static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
-{
-	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
-	struct zonelist *zonelist = node_zonelist(0, gfp_mask);
-	int did_some_progress = 0;
-	int order = 1;
-
-	/*
-	 * Increase level of watermarks to force kswapd do his job
-	 * to stabilise at new watermark level.
-	 */
-	__update_cma_watermarks(zone, count);
-
-	/* Obey watermarks as if the page was being allocated */
-	while (!zone_watermark_ok(zone, 0, low_wmark_pages(zone), 0, 0)) {
-		wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone));
-
-		did_some_progress = __perform_reclaim(gfp_mask, order, zonelist,
-						      NULL);
-		if (!did_some_progress) {
-			/* Exhausted what can be done so it's blamo time */
-			out_of_memory(zonelist, gfp_mask, order, NULL, false);
-		}
-	}
-
-	/* Restore original watermark levels. */
-	__update_cma_watermarks(zone, -count);
-
-	return count;
-}
-
 /**
  * alloc_contig_range() -- tries to allocate given range of pages
  * @start:	start PFN to allocate
@@ -5786,7 +5785,6 @@ static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count)
 int alloc_contig_range(unsigned long start, unsigned long end,
 		       unsigned migratetype)
 {
-	struct zone *zone = page_zone(pfn_to_page(start));
 	unsigned long outer_start, outer_end;
 	int ret = 0, order;
 
@@ -5824,7 +5822,8 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	 */
 
 	ret = start_isolate_page_range(pfn_max_align_down(start),
-				       pfn_max_align_up(end), migratetype);
+				       pfn_max_align_up(end), migratetype,
+				       false);
 	if (ret)
 		return ret;
 
@@ -5863,18 +5862,13 @@ int alloc_contig_range(unsigned long start, unsigned long end,
 	}
 
 	/* Make sure the range is really isolated. */
-	if (test_pages_isolated(outer_start, end)) {
+	if (test_pages_isolated(outer_start, end, false)) {
 		pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n",
 		       outer_start, end);
 		ret = -EBUSY;
 		goto done;
 	}
 
-	/*
-	 * Reclaim enough pages to make sure that contiguous allocation
-	 * will not starve the system.
-	 */
-	__reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start);
 
 	/* Grab isolated pages from freelists. */
 	outer_end = isolate_freepages_range(&cc, outer_start, end);
@@ -5932,7 +5926,6 @@ void __meminit zone_pcp_update(struct zone *zone)
 }
 #endif
 
-#ifdef CONFIG_MEMORY_HOTREMOVE
 void zone_pcp_reset(struct zone *zone)
 {
 	unsigned long flags;
@@ -5952,6 +5945,7 @@ void zone_pcp_reset(struct zone *zone)
 	local_irq_restore(flags);
 }
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
 /*
  * All pages in the range must be isolated before calling this.
  */
@@ -5978,6 +5972,16 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 			continue;
 		}
 		page = pfn_to_page(pfn);
+		/*
+		 * The HWPoisoned page may be not in buddy system, and
+		 * page_count() is not 0.
+		 */
+		if (unlikely(!PageBuddy(page) && PageHWPoison(page))) {
+			pfn++;
+			SetPageReserved(page);
+			continue;
+		}
+
 		BUG_ON(page_count(page));
 		BUG_ON(!PageBuddy(page));
 		order = page_order(page);
@@ -5988,8 +5992,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
 		list_del(&page->lru);
 		rmv_page_order(page);
 		zone->free_area[order].nr_free--;
-		__mod_zone_page_state(zone, NR_FREE_PAGES,
-				      - (1UL << order));
 		for (i = 0; i < (1 << order); i++)
 			SetPageReserved((page+i));
 		pfn += (1 << order);
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index 5ddad0c6daa6..44db00e253ed 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -251,6 +251,9 @@ static int __meminit page_cgroup_callback(struct notifier_block *self,
 				mn->nr_pages, mn->status_change_nid);
 		break;
 	case MEM_CANCEL_ONLINE:
+		offline_page_cgroup(mn->start_pfn,
+				mn->nr_pages, mn->status_change_nid);
+		break;
 	case MEM_GOING_OFFLINE:
 		break;
 	case MEM_ONLINE:
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index f2f5b4818e94..9d2264ea4606 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -30,7 +30,7 @@ static void restore_pageblock_isolate(struct page *page, int migratetype)
 	zone->nr_pageblock_isolate--;
 }
 
-int set_migratetype_isolate(struct page *page)
+int set_migratetype_isolate(struct page *page, bool skip_hwpoisoned_pages)
 {
 	struct zone *zone;
 	unsigned long flags, pfn;
@@ -66,7 +66,8 @@ int set_migratetype_isolate(struct page *page)
 	 * FIXME: Now, memory hotplug doesn't call shrink_slab() by itself.
 	 * We just check MOVABLE pages.
 	 */
-	if (!has_unmovable_pages(zone, page, arg.pages_found))
+	if (!has_unmovable_pages(zone, page, arg.pages_found,
+				 skip_hwpoisoned_pages))
 		ret = 0;
 
 	/*
@@ -134,7 +135,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * Returns 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     unsigned migratetype)
+			     unsigned migratetype, bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn;
 	unsigned long undo_pfn;
@@ -147,7 +148,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	     pfn < end_pfn;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page && set_migratetype_isolate(page)) {
+		if (page &&
+		    set_migratetype_isolate(page, skip_hwpoisoned_pages)) {
 			undo_pfn = pfn;
 			goto undo;
 		}
@@ -190,7 +192,8 @@ int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * Returns 1 if all pages in the range are isolated.
  */
 static int
-__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
+__test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
+				  bool skip_hwpoisoned_pages)
 {
 	struct page *page;
 
@@ -220,6 +223,14 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
 		else if (page_count(page) == 0 &&
 			get_freepage_migratetype(page) == MIGRATE_ISOLATE)
 			pfn += 1;
+		else if (skip_hwpoisoned_pages && PageHWPoison(page)) {
+			/*
+			 * The HWPoisoned page may be not in buddy
+			 * system, and page_count() is not 0.
+			 */
+			pfn++;
+			continue;
+		}
 		else
 			break;
 	}
@@ -228,7 +239,8 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)
 	return 1;
 }
 
-int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
+int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
+			bool skip_hwpoisoned_pages)
 {
 	unsigned long pfn, flags;
 	struct page *page;
@@ -251,7 +263,8 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn)
 	/* Check all pages are free or Marked as ISOLATED */
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lock, flags);
-	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn);
+	ret = __test_page_isolated_in_pageblock(start_pfn, end_pfn,
+						skip_hwpoisoned_pages);
 	spin_unlock_irqrestore(&zone->lock, flags);
 	return ret ? 0 : -EBUSY;
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 2ee1ef0f317b..cf7e99a87c32 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -562,6 +562,27 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 	return address;
 }
 
+pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd = NULL;
+
+	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 = NULL;
+out:
+	return pmd;
+}
+
 /*
  * Check that @page is mapped at @address into @mm.
  *
@@ -574,8 +595,6 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma)
 pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 			  unsigned long address, spinlock_t **ptlp, int sync)
 {
-	pgd_t *pgd;
-	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	spinlock_t *ptl;
@@ -586,17 +605,10 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 		goto check;
 	}
 
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
-		return NULL;
-
-	pud = pud_offset(pgd, address);
-	if (!pud_present(*pud))
+	pmd = mm_find_pmd(mm, address);
+	if (!pmd)
 		return NULL;
 
-	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd))
-		return NULL;
 	if (pmd_trans_huge(*pmd))
 		return NULL;
 
@@ -1139,9 +1151,11 @@ void page_remove_rmap(struct page *page)
 	 * containing the swap entry, but page not yet written to swap.
 	 *
 	 * And we can skip it on file pages, so long as the filesystem
-	 * participates in dirty tracking; but need to catch shm and tmpfs
-	 * and ramfs pages which have been modified since creation by read
-	 * fault.
+	 * participates in dirty tracking (note that this is not only an
+	 * optimization but also solves problems caused by dirty flag in
+	 * storage key getting set by a write from inside kernel); but need to
+	 * catch shm and tmpfs and ramfs pages which have been modified since
+	 * creation by read fault.
 	 *
 	 * Note that mapping must be decided above, before decrementing
 	 * mapcount (which luckily provides a barrier): once page is unmapped,
@@ -1345,8 +1359,6 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 		struct vm_area_struct *vma, struct page *check_page)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	pgd_t *pgd;
-	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
 	pte_t pteval;
@@ -1366,16 +1378,8 @@ static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount,
 	if (end > vma->vm_end)
 		end = vma->vm_end;
 
-	pgd = pgd_offset(mm, address);
-	if (!pgd_present(*pgd))
-		return ret;
-
-	pud = pud_offset(pgd, address);
-	if (!pud_present(*pud))
-		return ret;
-
-	pmd = pmd_offset(pud, address);
-	if (!pmd_present(*pmd))
+	pmd = mm_find_pmd(mm, address);
+	if (!pmd)
 		return ret;
 
 	mmun_start = address;
diff --git a/mm/slub.c b/mm/slub.c
index a0d698467f70..487f0bdd53c0 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3573,7 +3573,7 @@ static void slab_mem_offline_callback(void *arg)
 	struct memory_notify *marg = arg;
 	int offline_node;
 
-	offline_node = marg->status_change_nid;
+	offline_node = marg->status_change_nid_normal;
 
 	/*
 	 * If the node still has available memory. we need kmem_cache_node
@@ -3606,7 +3606,7 @@ static int slab_mem_going_online_callback(void *arg)
 	struct kmem_cache_node *n;
 	struct kmem_cache *s;
 	struct memory_notify *marg = arg;
-	int nid = marg->status_change_nid;
+	int nid = marg->status_change_nid_normal;
 	int ret = 0;
 
 	/*
diff --git a/mm/sparse.c b/mm/sparse.c
index a83de2f72b30..6b5fb762e2ca 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -638,7 +638,6 @@ static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
 got_map_page:
 	ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
 got_map_ptr:
-	memset(ret, 0, memmap_size);
 
 	return ret;
 }
@@ -758,6 +757,8 @@ int __meminit sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
 		goto out;
 	}
 
+	memset(memmap, 0, sizeof(struct page) * nr_pages);
+
 	ms->section_mem_map |= SECTION_MARKED_PRESENT;
 
 	ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
@@ -771,6 +772,27 @@ out:
 	return ret;
 }
 
+#ifdef CONFIG_MEMORY_FAILURE
+static void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+	int i;
+
+	if (!memmap)
+		return;
+
+	for (i = 0; i < PAGES_PER_SECTION; i++) {
+		if (PageHWPoison(&memmap[i])) {
+			atomic_long_sub(1, &mce_bad_pages);
+			ClearPageHWPoison(&memmap[i]);
+		}
+	}
+}
+#else
+static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages)
+{
+}
+#endif
+
 void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
 {
 	struct page *memmap = NULL;
@@ -784,6 +806,7 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms)
 		ms->pageblock_flags = NULL;
 	}
 
+	clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION);
 	free_section_usemap(memmap, usemap);
 }
 #endif
diff --git a/mm/swapfile.c b/mm/swapfile.c
index f91a25547ffe..e97a0e5aea91 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1443,13 +1443,12 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span)
 	return generic_swapfile_activate(sis, swap_file, span);
 }
 
-static void enable_swap_info(struct swap_info_struct *p, int prio,
+static void _enable_swap_info(struct swap_info_struct *p, int prio,
 				unsigned char *swap_map,
 				unsigned long *frontswap_map)
 {
 	int i, prev;
 
-	spin_lock(&swap_lock);
 	if (prio >= 0)
 		p->prio = prio;
 	else
@@ -1472,10 +1471,25 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
 		swap_list.head = swap_list.next = p->type;
 	else
 		swap_info[prev]->next = p->type;
+}
+
+static void enable_swap_info(struct swap_info_struct *p, int prio,
+				unsigned char *swap_map,
+				unsigned long *frontswap_map)
+{
+	spin_lock(&swap_lock);
+	_enable_swap_info(p, prio, swap_map, frontswap_map);
 	frontswap_init(p->type);
 	spin_unlock(&swap_lock);
 }
 
+static void reinsert_swap_info(struct swap_info_struct *p)
+{
+	spin_lock(&swap_lock);
+	_enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
+	spin_unlock(&swap_lock);
+}
+
 SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 {
 	struct swap_info_struct *p = NULL;
@@ -1484,7 +1498,6 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	struct address_space *mapping;
 	struct inode *inode;
 	struct filename *pathname;
-	int oom_score_adj;
 	int i, type, prev;
 	int err;
 
@@ -1543,19 +1556,13 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	p->flags &= ~SWP_WRITEOK;
 	spin_unlock(&swap_lock);
 
-	oom_score_adj = test_set_oom_score_adj(OOM_SCORE_ADJ_MAX);
+	set_current_oom_origin();
 	err = try_to_unuse(type, false, 0); /* force all pages to be unused */
-	compare_swap_oom_score_adj(OOM_SCORE_ADJ_MAX, oom_score_adj);
+	clear_current_oom_origin();
 
 	if (err) {
-		/*
-		 * reading p->prio and p->swap_map outside the lock is
-		 * safe here because only sys_swapon and sys_swapoff
-		 * change them, and there can be no other sys_swapon or
-		 * sys_swapoff for this swap_info_struct at this point.
-		 */
 		/* re-insert swap space back into swap_list */
-		enable_swap_info(p, p->prio, p->swap_map, frontswap_map_get(p));
+		reinsert_swap_info(p);
 		goto out_dput;
 	}
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 78e08300db21..5123a169ab7b 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2550,7 +2550,7 @@ static void s_stop(struct seq_file *m, void *p)
 
 static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 {
-	if (NUMA_BUILD) {
+	if (IS_ENABLED(CONFIG_NUMA)) {
 		unsigned int nr, *counters = m->private;
 
 		if (!counters)
@@ -2615,7 +2615,7 @@ static int vmalloc_open(struct inode *inode, struct file *file)
 	unsigned int *ptr = NULL;
 	int ret;
 
-	if (NUMA_BUILD) {
+	if (IS_ENABLED(CONFIG_NUMA)) {
 		ptr = kmalloc(nr_node_ids * sizeof(unsigned int), GFP_KERNEL);
 		if (ptr == NULL)
 			return -ENOMEM;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b7ed37675644..157bb116dec8 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1679,13 +1679,24 @@ static void get_scan_count(struct lruvec *lruvec, struct scan_control *sc,
 
 	if (global_reclaim(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
-		/* If we have very few page cache pages,
-		   force-scan anon pages. */
 		if (unlikely(file + free <= high_wmark_pages(zone))) {
+			/*
+			 * If we have very few page cache pages, force-scan
+			 * anon pages.
+			 */
 			fraction[0] = 1;
 			fraction[1] = 0;
 			denominator = 1;
 			goto out;
+		} else if (!inactive_file_is_low_global(zone)) {
+			/*
+			 * There is enough inactive page cache, do not
+			 * reclaim anything from the working set right now.
+			 */
+			fraction[0] = 0;
+			fraction[1] = 1;
+			denominator = 1;
+			goto out;
 		}
 	}
 
@@ -1752,7 +1763,7 @@ out:
 /* Use reclaim/compaction for costly allocs or under memory pressure */
 static bool in_reclaim_compaction(struct scan_control *sc)
 {
-	if (COMPACTION_BUILD && sc->order &&
+	if (IS_ENABLED(CONFIG_COMPACTION) && sc->order &&
 			(sc->order > PAGE_ALLOC_COSTLY_ORDER ||
 			 sc->priority < DEF_PRIORITY - 2))
 		return true;
@@ -2005,7 +2016,7 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 			if (zone->all_unreclaimable &&
 					sc->priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
-			if (COMPACTION_BUILD) {
+			if (IS_ENABLED(CONFIG_COMPACTION)) {
 				/*
 				 * If we already have plenty of memory free for
 				 * compaction in this zone, don't free any more.
@@ -2421,7 +2432,8 @@ static bool zone_balanced(struct zone *zone, int order,
 				    balance_gap, classzone_idx, 0))
 		return false;
 
-	if (COMPACTION_BUILD && order && !compaction_suitable(zone, order))
+	if (IS_ENABLED(CONFIG_COMPACTION) && order &&
+	    !compaction_suitable(zone, order))
 		return false;
 
 	return true;
@@ -2684,7 +2696,7 @@ loop_again:
 			 * Do not reclaim more than needed for compaction.
 			 */
 			testorder = order;
-			if (COMPACTION_BUILD && order &&
+			if (IS_ENABLED(CONFIG_COMPACTION) && order &&
 					compaction_suitable(zone, order) !=
 						COMPACT_SKIPPED)
 				testorder = 0;
@@ -2951,7 +2963,7 @@ static int kswapd(void *p)
 	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
 	balanced_classzone_idx = classzone_idx;
 	for ( ; ; ) {
-		int ret;
+		bool ret;
 
 		/*
 		 * If the last balance_pgdat was unsuccessful it's unlikely a
author	Linus Torvalds <torvalds@linux-foundation.org>	2012-12-11 18:05:37 -0800
committer	Linus Torvalds <torvalds@linux-foundation.org>	2012-12-11 18:05:37 -0800
commit	608ff1a210ab0e8b969399039bf8e18693605910 (patch)
tree	faea7bb1764461c73d0953089bd5439d91733a03 /mm
parent	414a6750e59b0b687034764c464e9ddecac0f7a6 (diff)
parent	74d42d8fe146e870c52bde3b1c692f86cc8ff844 (diff)
download	linux-608ff1a210ab0e8b969399039bf8e18693605910.tar.bz2