Merge branch 'linux-3.0.y' into HEAD

Conflicts:
	drivers/net/tun.c

14 files changed, 610 insertions, 260 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index 9cec4f2..88d55f4 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -35,10 +35,6 @@ struct compact_control {
 	unsigned long migrate_pfn;	/* isolate_migratepages search base */
 	bool sync;			/* Synchronous migration */
 
-	/* Account for isolated anon and file pages */
-	unsigned long nr_anon;
-	unsigned long nr_file;
-
 	unsigned int order;		/* order a direct compactor needs */
 	int migratetype;		/* MOVABLE, RECLAIMABLE etc */
 	struct zone *zone;
@@ -233,17 +229,13 @@ static void isolate_freepages(struct zone *zone,
 static void acct_isolated(struct zone *zone, struct compact_control *cc)
 {
 	struct page *page;
-	unsigned int count[NR_LRU_LISTS] = { 0, };
+	unsigned int count[2] = { 0, };
 
-	list_for_each_entry(page, &cc->migratepages, lru) {
-		int lru = page_lru_base_type(page);
-		count[lru]++;
-	}
+	list_for_each_entry(page, &cc->migratepages, lru)
+		count[!!page_is_file_cache(page)]++;
 
-	cc->nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
-	cc->nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
-	__mod_zone_page_state(zone, NR_ISOLATED_ANON, cc->nr_anon);
-	__mod_zone_page_state(zone, NR_ISOLATED_FILE, cc->nr_file);
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
 }
 
 /* Similar to reclaim, but different enough that they don't share logic */
@@ -279,6 +271,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 	unsigned long last_pageblock_nr = 0, pageblock_nr;
 	unsigned long nr_scanned = 0, nr_isolated = 0;
 	struct list_head *migratelist = &cc->migratepages;
+	isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;
 
 	/* Do not scan outside zone boundaries */
 	low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn);
@@ -393,8 +386,11 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone,
 			continue;
 		}
 
+		if (!cc->sync)
+			mode |= ISOLATE_ASYNC_MIGRATE;
+
 		/* Try isolate the page */
-		if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
+		if (__isolate_lru_page(page, mode, 0) != 0)
 			continue;
 
 		VM_BUG_ON(PageTransCompound(page));
@@ -596,7 +592,7 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
 		nr_migrate = cc->nr_migratepages;
 		err = migrate_pages(&cc->migratepages, compaction_alloc,
 				(unsigned long)cc, false,
-				cc->sync);
+				cc->sync ? MIGRATE_SYNC_LIGHT : MIGRATE_ASYNC);
 		update_nr_listpages(cc);
 		nr_remaining = cc->nr_migratepages;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index b7d8603..10481eb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -516,10 +516,13 @@ struct page *__page_cache_alloc(gfp_t gfp)
 	struct page *page;
 
 	if (cpuset_do_page_mem_spread()) {
-		get_mems_allowed();
-		n = cpuset_mem_spread_node();
-		page = alloc_pages_exact_node(n, gfp, 0);
-		put_mems_allowed();
+		unsigned int cpuset_mems_cookie;
+		do {
+			cpuset_mems_cookie = get_mems_allowed();
+			n = cpuset_mem_spread_node();
+			page = alloc_pages_exact_node(n, gfp, 0);
+		} while (!put_mems_allowed(cpuset_mems_cookie) && !page);
+
 		return page;
 	}
 	return alloc_pages(gfp, 0);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 05f8fd4..037f077 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -460,8 +460,10 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 	struct zonelist *zonelist;
 	struct zone *zone;
 	struct zoneref *z;
+	unsigned int cpuset_mems_cookie;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
 	zonelist = huge_zonelist(vma, address,
 					htlb_alloc_mask, &mpol, &nodemask);
 	/*
@@ -488,10 +490,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h,
 			}
 		}
 	}
-err:
+
 	mpol_cond_put(mpol);
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
+
+err:
+	mpol_cond_put(mpol);
+	return NULL;
 }
 
 static void update_and_free_page(struct hstate *h, struct page *page)
@@ -2294,6 +2301,22 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 {
 	mutex_lock(&vma->vm_file->f_mapping->i_mmap_mutex);
 	__unmap_hugepage_range(vma, start, end, ref_page);
+	/*
+	 * Clear this flag so that x86's huge_pmd_share page_table_shareable
+	 * test will fail on a vma being torn down, and not grab a page table
+	 * on its way out.  We're lucky that the flag has such an appropriate
+	 * name, and can in fact be safely cleared here. We could clear it
+	 * before the __unmap_hugepage_range above, but all that's necessary
+	 * is to clear it before releasing the i_mmap_mutex below.
+	 *
+	 * This works because in the contexts this is called, the VMA is
+	 * going to be destroyed. It is not vunerable to madvise(DONTNEED)
+	 * because madvise is not supported on hugetlbfs. The same applies
+	 * for direct IO. unmap_hugepage_range() is only being called just
+	 * before free_pgtables() so clearing VM_MAYSHARE will not cause
+	 * surprises later.
+	 */
+	vma->vm_flags &= ~VM_MAYSHARE;
 	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
@@ -2846,9 +2869,14 @@ void hugetlb_change_protection(struct vm_area_struct *vma,
 		}
 	}
 	spin_unlock(&mm->page_table_lock);
-	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
-
+	/*
+	 * Must flush TLB before releasing i_mmap_mutex: x86's huge_pmd_unshare
+	 * may have cleared our pud entry and done put_page on the page table:
+	 * once we release i_mmap_mutex, another task can do the final put_page
+	 * and that page table be reused and filled with junk.
+	 */
 	flush_tlb_range(vma, start, end);
+	mutex_unlock(&vma->vm_file->f_mapping->i_mmap_mutex);
 }
 
 int hugetlb_reserve_pages(struct inode *inode,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ffb99b4..57cdf5a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1251,7 +1251,8 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
+					isolate_mode_t mode,
+					struct zone *z,
 					struct mem_cgroup *mem_cont,
 					int active, int file)
 {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 740c4f5..2f49dcf 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1334,8 +1334,8 @@ static int soft_offline_huge_page(struct page *page, int flags)
 	/* Keep page count to indicate a given hugepage is isolated. */
 
 	list_add(&hpage->lru, &pagelist);
-	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, 0,
-				true);
+	ret = migrate_huge_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL, false,
+				MIGRATE_SYNC);
 	if (ret) {
 		struct page *page1, *page2;
 		list_for_each_entry_safe(page1, page2, &pagelist, lru)
@@ -1464,7 +1464,7 @@ int soft_offline_page(struct page *page, int flags)
 					    page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
 		ret = migrate_pages(&pagelist, new_page, MPOL_MF_MOVE_ALL,
-								0, true);
+							false, MIGRATE_SYNC);
 		if (ret) {
 			putback_lru_pages(&pagelist);
 			pr_info("soft offline: %#lx: migration failed %d, type %lx\n",
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c46887b..ae5a3f2 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -747,7 +747,7 @@ do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		}
 		/* this function returns # of failed pages */
 		ret = migrate_pages(&source, hotremove_migrate_alloc, 0,
-								true, true);
+							true, MIGRATE_SYNC);
 		if (ret)
 			putback_lru_pages(&source);
 	}
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 3dac2d1..cff919f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -926,7 +926,7 @@ static int migrate_to_node(struct mm_struct *mm, int source, int dest,
 
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_node_page, dest,
-								false, true);
+							false, MIGRATE_SYNC);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
@@ -1810,18 +1810,24 @@ struct page *
 alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		unsigned long addr, int node)
 {
-	struct mempolicy *pol = get_vma_policy(current, vma, addr);
+	struct mempolicy *pol;
 	struct zonelist *zl;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
+
+retry_cpuset:
+	pol = get_vma_policy(current, vma, addr);
+	cpuset_mems_cookie = get_mems_allowed();
 
-	get_mems_allowed();
 	if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
 		unsigned nid;
 
 		nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
 		mpol_cond_put(pol);
 		page = alloc_page_interleave(gfp, order, nid);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
+
 		return page;
 	}
 	zl = policy_zonelist(gfp, pol, node);
@@ -1832,7 +1838,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 		struct page *page =  __alloc_pages_nodemask(gfp, order,
 						zl, policy_nodemask(gfp, pol));
 		__mpol_put(pol);
-		put_mems_allowed();
+		if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+			goto retry_cpuset;
 		return page;
 	}
 	/*
@@ -1840,7 +1847,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	 */
 	page = __alloc_pages_nodemask(gfp, order, zl,
 				      policy_nodemask(gfp, pol));
-	put_mems_allowed();
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
 	return page;
 }
 
@@ -1867,11 +1875,14 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 {
 	struct mempolicy *pol = current->mempolicy;
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
 		pol = &default_policy;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/*
 	 * No reference counting needed for current->mempolicy
 	 * nor system default_policy
@@ -1882,7 +1893,10 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 		page = __alloc_pages_nodemask(gfp, order,
 				policy_zonelist(gfp, pol, numa_node_id()),
 				policy_nodemask(gfp, pol));
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(alloc_pages_current);
diff --git a/mm/migrate.c b/mm/migrate.c
index 14d0a6a..480714b 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -220,6 +220,56 @@ out:
 	pte_unmap_unlock(ptep, ptl);
 }
 
+#ifdef CONFIG_BLOCK
+/* Returns true if all buffers are successfully locked */
+static bool buffer_migrate_lock_buffers(struct buffer_head *head,
+							enum migrate_mode mode)
+{
+	struct buffer_head *bh = head;
+
+	/* Simple case, sync compaction */
+	if (mode != MIGRATE_ASYNC) {
+		do {
+			get_bh(bh);
+			lock_buffer(bh);
+			bh = bh->b_this_page;
+
+		} while (bh != head);
+
+		return true;
+	}
+
+	/* async case, we cannot block on lock_buffer so use trylock_buffer */
+	do {
+		get_bh(bh);
+		if (!trylock_buffer(bh)) {
+			/*
+			 * We failed to lock the buffer and cannot stall in
+			 * async migration. Release the taken locks
+			 */
+			struct buffer_head *failed_bh = bh;
+			put_bh(failed_bh);
+			bh = head;
+			while (bh != failed_bh) {
+				unlock_buffer(bh);
+				put_bh(bh);
+				bh = bh->b_this_page;
+			}
+			return false;
+		}
+
+		bh = bh->b_this_page;
+	} while (bh != head);
+	return true;
+}
+#else
+static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
+							enum migrate_mode mode)
+{
+	return true;
+}
+#endif /* CONFIG_BLOCK */
+
 /*
  * Replace the page in the mapping.
  *
@@ -229,7 +279,8 @@ out:
  * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page,
+		struct buffer_head *head, enum migrate_mode mode)
 {
 	int expected_count;
 	void **pslot;
@@ -259,6 +310,20 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	}
 
 	/*
+	 * In the async migration case of moving a page with buffers, lock the
+	 * buffers using trylock before the mapping is moved. If the mapping
+	 * was moved, we later failed to lock the buffers and could not move
+	 * the mapping back due to an elevated page count, we would have to
+	 * block waiting on other references to be dropped.
+	 */
+	if (mode == MIGRATE_ASYNC && head &&
+			!buffer_migrate_lock_buffers(head, mode)) {
+		page_unfreeze_refs(page, expected_count);
+		spin_unlock_irq(&mapping->tree_lock);
+		return -EAGAIN;
+	}
+
+	/*
 	 * Now we know that no one else is looking at the page.
 	 */
 	get_page(newpage);	/* add cache reference */
@@ -415,13 +480,14 @@ EXPORT_SYMBOL(fail_migrate_page);
  * Pages are locked upon entry and exit.
  */
 int migrate_page(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page,
+		enum migrate_mode mode)
 {
 	int rc;
 
 	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page);
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
 
 	if (rc)
 		return rc;
@@ -438,28 +504,28 @@ EXPORT_SYMBOL(migrate_page);
  * exist.
  */
 int buffer_migrate_page(struct address_space *mapping,
-		struct page *newpage, struct page *page)
+		struct page *newpage, struct page *page, enum migrate_mode mode)
 {
 	struct buffer_head *bh, *head;
 	int rc;
 
 	if (!page_has_buffers(page))
-		return migrate_page(mapping, newpage, page);
+		return migrate_page(mapping, newpage, page, mode);
 
 	head = page_buffers(page);
 
-	rc = migrate_page_move_mapping(mapping, newpage, page);
+	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
 
 	if (rc)
 		return rc;
 
-	bh = head;
-	do {
-		get_bh(bh);
-		lock_buffer(bh);
-		bh = bh->b_this_page;
-
-	} while (bh != head);
+	/*
+	 * In the async case, migrate_page_move_mapping locked the buffers
+	 * with an IRQ-safe spinlock held. In the sync case, the buffers
+	 * need to be locked now
+	 */
+	if (mode != MIGRATE_ASYNC)
+		BUG_ON(!buffer_migrate_lock_buffers(head, mode));
 
 	ClearPagePrivate(page);
 	set_page_private(newpage, page_private(page));
@@ -536,10 +602,14 @@ static int writeout(struct address_space *mapping, struct page *page)
  * Default handling if a filesystem does not provide a migration function.
  */
 static int fallback_migrate_page(struct address_space *mapping,
-	struct page *newpage, struct page *page)
+	struct page *newpage, struct page *page, enum migrate_mode mode)
 {
-	if (PageDirty(page))
+	if (PageDirty(page)) {
+		/* Only writeback pages in full synchronous migration */
+		if (mode != MIGRATE_SYNC)
+			return -EBUSY;
 		return writeout(mapping, page);
+	}
 
 	/*
 	 * Buffers may be managed in a filesystem specific way.
@@ -549,7 +619,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
-	return migrate_page(mapping, newpage, page);
+	return migrate_page(mapping, newpage, page, mode);
 }
 
 /*
@@ -564,7 +634,7 @@ static int fallback_migrate_page(struct address_space *mapping,
  *  == 0 - success
  */
 static int move_to_new_page(struct page *newpage, struct page *page,
-					int remap_swapcache, bool sync)
+				int remap_swapcache, enum migrate_mode mode)
 {
 	struct address_space *mapping;
 	int rc;
@@ -585,29 +655,18 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 
 	mapping = page_mapping(page);
 	if (!mapping)
-		rc = migrate_page(mapping, newpage, page);
-	else {
+		rc = migrate_page(mapping, newpage, page, mode);
+	else if (mapping->a_ops->migratepage)
 		/*
-		 * Do not writeback pages if !sync and migratepage is
-		 * not pointing to migrate_page() which is nonblocking
-		 * (swapcache/tmpfs uses migratepage = migrate_page).
+		 * Most pages have a mapping and most filesystems provide a
+		 * migratepage callback. Anonymous pages are part of swap
+		 * space which also has its own migratepage callback. This
+		 * is the most common path for page migration.
 		 */
-		if (PageDirty(page) && !sync &&
-		    mapping->a_ops->migratepage != migrate_page)
-			rc = -EBUSY;
-		else if (mapping->a_ops->migratepage)
-			/*
-			 * Most pages have a mapping and most filesystems
-			 * should provide a migration function. Anonymous
-			 * pages are part of swap space which also has its
-			 * own migration function. This is the most common
-			 * path for page migration.
-			 */
-			rc = mapping->a_ops->migratepage(mapping,
-							newpage, page);
-		else
-			rc = fallback_migrate_page(mapping, newpage, page);
-	}
+		rc = mapping->a_ops->migratepage(mapping,
+						newpage, page, mode);
+	else
+		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
 	if (rc) {
 		newpage->mapping = NULL;
@@ -621,38 +680,18 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	return rc;
 }
 
-/*
- * Obtain the lock on page, remove all ptes and migrate the page
- * to the newly allocated page in newpage.
- */
-static int unmap_and_move(new_page_t get_new_page, unsigned long private,
-			struct page *page, int force, bool offlining, bool sync)
+static int __unmap_and_move(struct page *page, struct page *newpage,
+			int force, bool offlining, enum migrate_mode mode)
 {
-	int rc = 0;
-	int *result = NULL;
-	struct page *newpage = get_new_page(page, private, &result);
+	int rc = -EAGAIN;
 	int remap_swapcache = 1;
 	int charge = 0;
 	struct mem_cgroup *mem;
 	struct anon_vma *anon_vma = NULL;
 
-	if (!newpage)
-		return -ENOMEM;
-
-	if (page_count(page) == 1) {
-		/* page was freed from under us. So we are done. */
-		goto move_newpage;
-	}
-	if (unlikely(PageTransHuge(page)))
-		if (unlikely(split_huge_page(page)))
-			goto move_newpage;
-
-	/* prepare cgroup just returns 0 or -ENOMEM */
-	rc = -EAGAIN;
-
 	if (!trylock_page(page)) {
-		if (!force || !sync)
-			goto move_newpage;
+		if (!force || mode == MIGRATE_ASYNC)
+			goto out;
 
 		/*
 		 * It's not safe for direct compaction to call lock_page.
@@ -668,7 +707,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 		 * altogether.
 		 */
 		if (current->flags & PF_MEMALLOC)
-			goto move_newpage;
+			goto out;
 
 		lock_page(page);
 	}
@@ -697,10 +736,12 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 
 	if (PageWriteback(page)) {
 		/*
-		 * For !sync, there is no point retrying as the retry loop
-		 * is expected to be too short for PageWriteback to be cleared
+		 * Only in the case of a full syncronous migration is it
+		 * necessary to wait for PageWriteback. In the async case,
+		 * the retry loop is too short and in the sync-light case,
+		 * the overhead of stalling is too much
 		 */
-		if (!sync) {
+		if (mode != MIGRATE_SYNC) {
 			rc = -EBUSY;
 			goto uncharge;
 		}
@@ -771,7 +812,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 
 skip_unmap:
 	if (!page_mapped(page))
-		rc = move_to_new_page(newpage, page, remap_swapcache, sync);
+		rc = move_to_new_page(newpage, page, remap_swapcache, mode);
 
 	if (rc && remap_swapcache)
 		remove_migration_ptes(page, page);
@@ -785,27 +826,53 @@ uncharge:
 		mem_cgroup_end_migration(mem, page, newpage, rc == 0);
 unlock:
 	unlock_page(page);
+out:
+	return rc;
+}
 
-move_newpage:
+/*
+ * Obtain the lock on page, remove all ptes and migrate the page
+ * to the newly allocated page in newpage.
+ */
+static int unmap_and_move(new_page_t get_new_page, unsigned long private,
+			struct page *page, int force, bool offlining,
+			enum migrate_mode mode)
+{
+	int rc = 0;
+	int *result = NULL;
+	struct page *newpage = get_new_page(page, private, &result);
+
+	if (!newpage)
+		return -ENOMEM;
+
+	if (page_count(page) == 1) {
+		/* page was freed from under us. So we are done. */
+		goto out;
+	}
+
+	if (unlikely(PageTransHuge(page)))
+		if (unlikely(split_huge_page(page)))
+			goto out;
+
+	rc = __unmap_and_move(page, newpage, force, offlining, mode);
+out:
 	if (rc != -EAGAIN) {
- 		/*
- 		 * A page that has been migrated has all references
- 		 * removed and will be freed. A page that has not been
- 		 * migrated will have kepts its references and be
- 		 * restored.
- 		 */
- 		list_del(&page->lru);
+		/*
+		 * A page that has been migrated has all references
+		 * removed and will be freed. A page that has not been
+		 * migrated will have kepts its references and be
+		 * restored.
+		 */
+		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
 		putback_lru_page(page);
 	}
-
 	/*
 	 * Move the new page to the LRU. If migration was not successful
 	 * then this will free the page.
 	 */
 	putback_lru_page(newpage);
-
 	if (result) {
 		if (rc)
 			*result = rc;
@@ -835,7 +902,8 @@ move_newpage:
  */
 static int unmap_and_move_huge_page(new_page_t get_new_page,
 				unsigned long private, struct page *hpage,
-				int force, bool offlining, bool sync)
+				int force, bool offlining,
+				enum migrate_mode mode)
 {
 	int rc = 0;
 	int *result = NULL;
@@ -848,7 +916,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	rc = -EAGAIN;
 
 	if (!trylock_page(hpage)) {
-		if (!force || !sync)
+		if (!force || mode != MIGRATE_SYNC)
 			goto out;
 		lock_page(hpage);
 	}
@@ -859,7 +927,7 @@ static int unmap_and_move_huge_page(new_page_t get_new_page,
 	try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
 
 	if (!page_mapped(hpage))
-		rc = move_to_new_page(new_hpage, hpage, 1, sync);
+		rc = move_to_new_page(new_hpage, hpage, 1, mode);
 
 	if (rc)
 		remove_migration_ptes(hpage, hpage);
@@ -902,7 +970,7 @@ out:
  */
 int migrate_pages(struct list_head *from,
 		new_page_t get_new_page, unsigned long private, bool offlining,
-		bool sync)
+		enum migrate_mode mode)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -923,7 +991,7 @@ int migrate_pages(struct list_head *from,
 
 			rc = unmap_and_move(get_new_page, private,
 						page, pass > 2, offlining,
-						sync);
+						mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -953,7 +1021,7 @@ out:
 
 int migrate_huge_pages(struct list_head *from,
 		new_page_t get_new_page, unsigned long private, bool offlining,
-		bool sync)
+		enum migrate_mode mode)
 {
 	int retry = 1;
 	int nr_failed = 0;
@@ -970,7 +1038,7 @@ int migrate_huge_pages(struct list_head *from,
 
 			rc = unmap_and_move_huge_page(get_new_page,
 					private, page, pass > 2, offlining,
-					sync);
+					mode);
 
 			switch(rc) {
 			case -ENOMEM:
@@ -1099,7 +1167,7 @@ set_status:
 	err = 0;
 	if (!list_empty(&pagelist)) {
 		err = migrate_pages(&pagelist, new_page_node,
-				(unsigned long)pm, 0, true);
+				(unsigned long)pm, 0, MIGRATE_SYNC);
 		if (err)
 			putback_lru_pages(&pagelist);
 	}
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 8d032de..71c7811 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -33,6 +33,24 @@
 void __mmu_notifier_release(struct mm_struct *mm)
 {
 	struct mmu_notifier *mn;
+	struct hlist_node *n;
+
+	/*
+	 * RCU here will block mmu_notifier_unregister until
+	 * ->release returns.
+	 */
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(mn, n, &mm->mmu_notifier_mm->list, hlist)
+		/*
+		 * if ->release runs before mmu_notifier_unregister it
+		 * must be handled as it's the only way for the driver
+		 * to flush all existing sptes and stop the driver
+		 * from establishing any more sptes before all the
+		 * pages in the mm are freed.
+		 */
+		if (mn->ops->release)
+			mn->ops->release(mn, mm);
+	rcu_read_unlock();
 
 	spin_lock(&mm->mmu_notifier_mm->lock);
 	while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) {
@@ -46,23 +64,6 @@ void __mmu_notifier_release(struct mm_struct *mm)
 		 * mmu_notifier_unregister to return.
 		 */
 		hlist_del_init_rcu(&mn->hlist);
-		/*
-		 * RCU here will block mmu_notifier_unregister until
-		 * ->release returns.
-		 */
-		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
-		/*
-		 * if ->release runs before mmu_notifier_unregister it
-		 * must be handled as it's the only way for the driver
-		 * to flush all existing sptes and stop the driver
-		 * from establishing any more sptes before all the
-		 * pages in the mm are freed.
-		 */
-		if (mn->ops->release)
-			mn->ops->release(mn, mm);
-		rcu_read_unlock();
-		spin_lock(&mm->mmu_notifier_mm->lock);
 	}
 	spin_unlock(&mm->mmu_notifier_mm->lock);
 
@@ -284,16 +285,13 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 {
 	BUG_ON(atomic_read(&mm->mm_count) <= 0);
 
-	spin_lock(&mm->mmu_notifier_mm->lock);
 	if (!hlist_unhashed(&mn->hlist)) {
-		hlist_del_rcu(&mn->hlist);
-
 		/*
 		 * RCU here will force exit_mmap to wait ->release to finish
 		 * before freeing the pages.
 		 */
 		rcu_read_lock();
-		spin_unlock(&mm->mmu_notifier_mm->lock);
+
 		/*
 		 * exit_mmap will block in mmu_notifier_release to
 		 * guarantee ->release is called before freeing the
@@ -302,8 +300,11 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm)
 		if (mn->ops->release)
 			mn->ops->release(mn, mm);
 		rcu_read_unlock();
-	} else
+
+		spin_lock(&mm->mmu_notifier_mm->lock);
+		hlist_del_rcu(&mn->hlist);
 		spin_unlock(&mm->mmu_notifier_mm->lock);
+	}
 
 	/*
 	 * Wait any running method to finish, of course including
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index e2f474d..87b0a3f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1912,14 +1912,20 @@ static struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	struct page *page;
 
-	if (!order || compaction_deferred(preferred_zone))
+	if (!order)
 		return NULL;
 
+	if (compaction_deferred(preferred_zone)) {
+		*deferred_compaction = true;
+		return NULL;
+	}
+
 	current->flags |= PF_MEMALLOC;
 	*did_some_progress = try_to_compact_pages(zonelist, order, gfp_mask,
 						nodemask, sync_migration);
@@ -1947,7 +1953,13 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 		 * but not enough to satisfy watermarks.
 		 */
 		count_vm_event(COMPACTFAIL);
-		defer_compaction(preferred_zone);
+
+		/*
+		 * As async compaction considers a subset of pageblocks, only
+		 * defer if the failure was a sync compaction failure.
+		 */
+		if (sync_migration)
+			defer_compaction(preferred_zone);
 
 		cond_resched();
 	}
@@ -1959,8 +1971,9 @@ static inline struct page *
 __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order,
 	struct zonelist *zonelist, enum zone_type high_zoneidx,
 	nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone,
-	int migratetype, unsigned long *did_some_progress,
-	bool sync_migration)
+	int migratetype, bool sync_migration,
+	bool *deferred_compaction,
+	unsigned long *did_some_progress)
 {
 	return NULL;
 }
@@ -2110,6 +2123,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
 	bool sync_migration = false;
+	bool deferred_compaction = false;
 
 	/*
 	 * In the slowpath, we sanity check order to avoid ever trying to
@@ -2190,12 +2204,22 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 	if (page)
 		goto got_pg;
 	sync_migration = true;
 
+	/*
+	 * If compaction is deferred for high-order allocations, it is because
+	 * sync compaction recently failed. In this is the case and the caller
+	 * has requested the system not be heavily disrupted, fail the
+	 * allocation now instead of entering direct reclaim
+	 */
+	if (deferred_compaction && (gfp_mask & __GFP_NO_KSWAPD))
+		goto nopage;
+
 	/* Try direct reclaim and then allocating */
 	page = __alloc_pages_direct_reclaim(gfp_mask, order,
 					zonelist, high_zoneidx,
@@ -2266,8 +2290,9 @@ rebalance:
 					zonelist, high_zoneidx,
 					nodemask,
 					alloc_flags, preferred_zone,
-					migratetype, &did_some_progress,
-					sync_migration);
+					migratetype, sync_migration,
+					&deferred_compaction,
+					&did_some_progress);
 		if (page)
 			goto got_pg;
 	}
@@ -2291,8 +2316,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 {
 	enum zone_type high_zoneidx = gfp_zone(gfp_mask);
 	struct zone *preferred_zone;
-	struct page *page;
+	struct page *page = NULL;
 	int migratetype = allocflags_to_migratetype(gfp_mask);
+	unsigned int cpuset_mems_cookie;
 
 	gfp_mask &= gfp_allowed_mask;
 
@@ -2311,15 +2337,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 	if (unlikely(!zonelist->_zonerefs->zone))
 		return NULL;
 
-	get_mems_allowed();
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+
 	/* The preferred zone is used for statistics later */
 	first_zones_zonelist(zonelist, high_zoneidx,
 				nodemask ? : &cpuset_current_mems_allowed,
 				&preferred_zone);
-	if (!preferred_zone) {
-		put_mems_allowed();
-		return NULL;
-	}
+	if (!preferred_zone)
+		goto out;
 
 	/* First allocation attempt */
 	page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order,
@@ -2329,9 +2355,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order,
 		page = __alloc_pages_slowpath(gfp_mask, order,
 				zonelist, high_zoneidx, nodemask,
 				preferred_zone, migratetype);
-	put_mems_allowed();
 
 	trace_mm_page_alloc(page, order, gfp_mask, migratetype);
+
+out:
+	/*
+	 * When updating a task's mems_allowed, it is possible to race with
+	 * parallel threads in such a way that an allocation can fail while
+	 * the mask is being updated. If a page allocation is about to fail,
+	 * check if the cpuset changed during allocation and if so, retry.
+	 */
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+		goto retry_cpuset;
+
 	return page;
 }
 EXPORT_SYMBOL(__alloc_pages_nodemask);
@@ -2555,13 +2591,15 @@ void si_meminfo_node(struct sysinfo *val, int nid)
 bool skip_free_areas_node(unsigned int flags, int nid)
 {
 	bool ret = false;
+	unsigned int cpuset_mems_cookie;
 
 	if (!(flags & SHOW_MEM_FILTER_NODES))
 		goto out;
 
-	get_mems_allowed();
-	ret = !node_isset(nid, cpuset_current_mems_allowed);
-	put_mems_allowed();
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		ret = !node_isset(nid, cpuset_current_mems_allowed);
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 out:
 	return ret;
 }
@@ -3441,25 +3479,33 @@ static void setup_zone_migrate_reserve(struct zone *zone)
 		if (page_to_nid(page) != zone_to_nid(zone))
 			continue;
 
-		/* Blocks with reserved pages will never free, skip them. */
-		block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
-		if (pageblock_is_reserved(pfn, block_end_pfn))
-			continue;
-
 		block_migratetype = get_pageblock_migratetype(page);
 
-		/* If this block is reserved, account for it */
-		if (reserve > 0 && block_migratetype == MIGRATE_RESERVE) {
-			reserve--;
-			continue;
-		}
+		/* Only test what is necessary when the reserves are not met */
+		if (reserve > 0) {
+			/*
+			 * Blocks with reserved pages will never free, skip
+			 * them.
+			 */
+			block_end_pfn = min(pfn + pageblock_nr_pages, end_pfn);
+			if (pageblock_is_reserved(pfn, block_end_pfn))
+				continue;
 
-		/* Suitable for reserving if this block is movable */
-		if (reserve > 0 && block_migratetype == MIGRATE_MOVABLE) {
-			set_pageblock_migratetype(page, MIGRATE_RESERVE);
-			move_freepages_block(zone, page, MIGRATE_RESERVE);
-			reserve--;
-			continue;
+			/* If this block is reserved, account for it */
+			if (block_migratetype == MIGRATE_RESERVE) {
+				reserve--;
+				continue;
+			}
+
+			/* Suitable for reserving if this block is movable */
+			if (block_migratetype == MIGRATE_MOVABLE) {
+				set_pageblock_migratetype(page,
+							MIGRATE_RESERVE);
+				move_freepages_block(zone, page,
+							MIGRATE_RESERVE);
+				reserve--;
+				continue;
+			}
 		}
 
 		/*
diff --git a/mm/slab.c b/mm/slab.c
index d96e223..a67f812 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -3218,12 +3218,10 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
 	if (in_interrupt() || (flags & __GFP_THISNODE))
 		return NULL;
 	nid_alloc = nid_here = numa_mem_id();
-	get_mems_allowed();
 	if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
 		nid_alloc = cpuset_slab_spread_node();
 	else if (current->mempolicy)
 		nid_alloc = slab_node(current->mempolicy);
-	put_mems_allowed();
 	if (nid_alloc != nid_here)
 		return ____cache_alloc_node(cachep, flags, nid_alloc);
 	return NULL;
@@ -3246,14 +3244,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	void *obj = NULL;
 	int nid;
+	unsigned int cpuset_mems_cookie;
 
 	if (flags & __GFP_THISNODE)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
 	local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
 
+retry_cpuset:
+	cpuset_mems_cookie = get_mems_allowed();
+	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+
 retry:
 	/*
 	 * Look through allowed nodes for objects available
@@ -3306,7 +3307,9 @@ retry:
 			}
 		}
 	}
-	put_mems_allowed();
+
+	if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj))
+		goto retry_cpuset;
 	return obj;
 }
 
diff --git a/mm/slub.c b/mm/slub.c
index 10ab233..ae6e80e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1457,6 +1457,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 	struct zone *zone;
 	enum zone_type high_zoneidx = gfp_zone(flags);
 	struct page *page;
+	unsigned int cpuset_mems_cookie;
 
 	/*
 	 * The defrag ratio allows a configuration of the tradeoffs between
@@ -1480,23 +1481,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags)
 			get_cycles() % 1024 > s->remote_node_defrag_ratio)
 		return NULL;
 
-	get_mems_allowed();
-	zonelist = node_zonelist(slab_node(current->mempolicy), flags);
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-		struct kmem_cache_node *n;
-
-		n = get_node(s, zone_to_nid(zone));
-
-		if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
-				n->nr_partial > s->min_partial) {
-			page = get_partial_node(n);
-			if (page) {
-				put_mems_allowed();
-				return page;
+	do {
+		cpuset_mems_cookie = get_mems_allowed();
+		zonelist = node_zonelist(slab_node(current->mempolicy), flags);
+		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+			struct kmem_cache_node *n;
+
+			n = get_node(s, zone_to_nid(zone));
+
+			if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
+					n->nr_partial > s->min_partial) {
+				page = get_partial_node(n);
+				if (page) {
+					/*
+					 * Return the object even if
+					 * put_mems_allowed indicated that
+					 * the cpuset mems_allowed was
+					 * updated in parallel. It's a
+					 * harmless race between the alloc
+					 * and the cpuset update.
+					 */
+					put_mems_allowed(cpuset_mems_cookie);
+					return page;
+				}
 			}
 		}
-	}
-	put_mems_allowed();
+	} while (!put_mems_allowed(cpuset_mems_cookie));
 #endif
 	return NULL;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 1b0ed36..5326f98 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -248,35 +248,66 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		unsigned long long delta;
-		unsigned long total_scan;
-		unsigned long max_pass;
+		long total_scan;
+		long max_pass;
+		int shrink_ret = 0;
+		long nr;
+		long new_nr;
 
 		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
+		if (max_pass <= 0)
+			continue;
+
+		/*
+		 * copy the current shrinker scan count into a local variable
+		 * and zero it so that other concurrent shrinker invocations
+		 * don't also do this scanning work.
+		 */
+		do {
+			nr = shrinker->nr;
+		} while (cmpxchg(&shrinker->nr, nr, 0) != nr);
+
+		total_scan = nr;
 		delta = (4 * nr_pages_scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
-		shrinker->nr += delta;
-		if (shrinker->nr < 0) {
+		total_scan += delta;
+		if (total_scan < 0) {
 			printk(KERN_ERR "shrink_slab: %pF negative objects to "
 			       "delete nr=%ld\n",
-			       shrinker->shrink, shrinker->nr);
-			shrinker->nr = max_pass;
+			       shrinker->shrink, total_scan);
+			total_scan = max_pass;
 		}
 
 		/*
+		 * We need to avoid excessive windup on filesystem shrinkers
+		 * due to large numbers of GFP_NOFS allocations causing the
+		 * shrinkers to return -1 all the time. This results in a large
+		 * nr being built up so when a shrink that can do some work
+		 * comes along it empties the entire cache due to nr >>>
+		 * max_pass.  This is bad for sustaining a working set in
+		 * memory.
+		 *
+		 * Hence only allow the shrinker to scan the entire cache when
+		 * a large delta change is calculated directly.
+		 */
+		if (delta < max_pass / 4)
+			total_scan = min(total_scan, max_pass / 2);
+
+		/*
 		 * Avoid risking looping forever due to too large nr value:
 		 * never try to free more than twice the estimate number of
 		 * freeable entries.
 		 */
-		if (shrinker->nr > max_pass * 2)
-			shrinker->nr = max_pass * 2;
+		if (total_scan > max_pass * 2)
+			total_scan = max_pass * 2;
 
-		total_scan = shrinker->nr;
-		shrinker->nr = 0;
+		trace_mm_shrink_slab_start(shrinker, shrink, nr,
+					nr_pages_scanned, lru_pages,
+					max_pass, delta, total_scan);
 
 		while (total_scan >= SHRINK_BATCH) {
 			long this_scan = SHRINK_BATCH;
-			int shrink_ret;
 			int nr_before;
 
 			nr_before = do_shrinker_shrink(shrinker, shrink, 0);
@@ -292,7 +323,19 @@ unsigned long shrink_slab(struct shrink_control *shrink,
 			cond_resched();
 		}
 
-		shrinker->nr += total_scan;
+		/*
+		 * move the unused scan count back into the shrinker in a
+		 * manner that handles concurrent updates. If we exhausted the
+		 * scan, there is no need to do an update.
+		 */
+		do {
+			nr = shrinker->nr;
+			new_nr = total_scan + nr;
+			if (total_scan <= 0)
+				break;
+		} while (cmpxchg(&shrinker->nr, nr, new_nr) != nr);
+
+		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
 	}
 	up_read(&shrinker_rwsem);
 out:
@@ -683,7 +726,13 @@ static enum page_references page_check_references(struct page *page,
 		 */
 		SetPageReferenced(page);
 
-		if (referenced_page)
+		if (referenced_page || referenced_ptes > 1)
+			return PAGEREF_ACTIVATE;
+
+		/*
+		 * Activate file-backed executable pages after first usage.
+		 */
+		if (vm_flags & VM_EXEC)
 			return PAGEREF_ACTIVATE;
 
 		return PAGEREF_KEEP;
@@ -972,23 +1021,27 @@ keep_lumpy:
  *
  * returns 0 on success, -ve errno on failure.
  */
-int __isolate_lru_page(struct page *page, int mode, int file)
+int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file)
 {
+	bool all_lru_mode;
 	int ret = -EINVAL;
 
 	/* Only take pages on the LRU. */
 	if (!PageLRU(page))
 		return ret;
 
+	all_lru_mode = (mode & (ISOLATE_ACTIVE|ISOLATE_INACTIVE)) ==
+		(ISOLATE_ACTIVE|ISOLATE_INACTIVE);
+
 	/*
 	 * When checking the active state, we need to be sure we are
 	 * dealing with comparible boolean values.  Take the logical not
 	 * of each.
 	 */
-	if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
+	if (!all_lru_mode && !PageActive(page) != !(mode & ISOLATE_ACTIVE))
 		return ret;
 
-	if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file)
+	if (!all_lru_mode && !!page_is_file_cache(page) != file)
 		return ret;
 
 	/*
@@ -1001,6 +1054,43 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 
 	ret = -EBUSY;
 
+	/*
+	 * To minimise LRU disruption, the caller can indicate that it only
+	 * wants to isolate pages it will be able to operate on without
+	 * blocking - clean pages for the most part.
+	 *
+	 * ISOLATE_CLEAN means that only clean pages should be isolated. This
+	 * is used by reclaim when it is cannot write to backing storage
+	 *
+	 * ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
+	 * that it is possible to migrate without blocking
+	 */
+	if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
+		/* All the caller can do on PageWriteback is block */
+		if (PageWriteback(page))
+			return ret;
+
+		if (PageDirty(page)) {
+			struct address_space *mapping;
+
+			/* ISOLATE_CLEAN means only clean pages */
+			if (mode & ISOLATE_CLEAN)
+				return ret;
+
+			/*
+			 * Only pages without mappings or that have a
+			 * ->migratepage callback are possible to migrate
+			 * without blocking
+			 */
+			mapping = page_mapping(page);
+			if (mapping && !mapping->a_ops->migratepage)
+				return ret;
+		}
+	}
+
+	if ((mode & ISOLATE_UNMAPPED) && page_mapped(page))
+		return ret;
+
 	if (likely(get_page_unless_zero(page))) {
 		/*
 		 * Be careful not to clear PageLRU until after we're
@@ -1036,7 +1126,8 @@ int __isolate_lru_page(struct page *page, int mode, int file)
  */
 static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		struct list_head *src, struct list_head *dst,
-		unsigned long *scanned, int order, int mode, int file)
+		unsigned long *scanned, int order, isolate_mode_t mode,
+		int file)
 {
 	unsigned long nr_taken = 0;
 	unsigned long nr_lumpy_taken = 0;
@@ -1111,7 +1202,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			 * anon page which don't already have a swap slot is
 			 * pointless.
 			 */
-			if (nr_swap_pages <= 0 && PageAnon(cursor_page) &&
+			if (nr_swap_pages <= 0 && PageSwapBacked(cursor_page) &&
 			    !PageSwapCache(cursor_page))
 				break;
 
@@ -1161,8 +1252,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 static unsigned long isolate_pages_global(unsigned long nr,
 					struct list_head *dst,
 					unsigned long *scanned, int order,
-					int mode, struct zone *z,
-					int active, int file)
+					isolate_mode_t mode,
+					struct zone *z,	int active, int file)
 {
 	int lru = LRU_BASE;
 	if (active)
@@ -1408,6 +1499,7 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	unsigned long nr_taken;
 	unsigned long nr_anon;
 	unsigned long nr_file;
+	isolate_mode_t reclaim_mode = ISOLATE_INACTIVE;
 
 	while (unlikely(too_many_isolated(zone, file, sc))) {
 		congestion_wait(BLK_RW_ASYNC, HZ/10);
@@ -1418,15 +1510,21 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 	}
 
 	set_reclaim_mode(priority, sc, false);
+	if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)
+		reclaim_mode |= ISOLATE_ACTIVE;
+
 	lru_add_drain();
+
+	if (!sc->may_unmap)
+		reclaim_mode |= ISOLATE_UNMAPPED;
+	if (!sc->may_writepage)
+		reclaim_mode |= ISOLATE_CLEAN;
+
 	spin_lock_irq(&zone->lru_lock);
 
 	if (scanning_global_lru(sc)) {
-		nr_taken = isolate_pages_global(nr_to_scan,
-			&page_list, &nr_scanned, sc->order,
-			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
-					ISOLATE_BOTH : ISOLATE_INACTIVE,
-			zone, 0, file);
+		nr_taken = isolate_pages_global(nr_to_scan, &page_list,
+			&nr_scanned, sc->order, reclaim_mode, zone, 0, file);
 		zone->pages_scanned += nr_scanned;
 		if (current_is_kswapd())
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone,
@@ -1435,12 +1533,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
 			__count_zone_vm_events(PGSCAN_DIRECT, zone,
 					       nr_scanned);
 	} else {
-		nr_taken = mem_cgroup_isolate_pages(nr_to_scan,
-			&page_list, &nr_scanned, sc->order,
-			sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM ?
-					ISOLATE_BOTH : ISOLATE_INACTIVE,
-			zone, sc->mem_cgroup,
-			0, file);
+		nr_taken = mem_cgroup_isolate_pages(nr_to_scan, &page_list,
+			&nr_scanned, sc->order, reclaim_mode, zone,
+			sc->mem_cgroup, 0, file);
 		/*
 		 * mem_cgroup_isolate_pages() keeps track of
 		 * scanned pages on its own.
@@ -1542,19 +1637,26 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	struct page *page;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 	unsigned long nr_rotated = 0;
+	isolate_mode_t reclaim_mode = ISOLATE_ACTIVE;
 
 	lru_add_drain();
+
+	if (!sc->may_unmap)
+		reclaim_mode |= ISOLATE_UNMAPPED;
+	if (!sc->may_writepage)
+		reclaim_mode |= ISOLATE_CLEAN;
+
 	spin_lock_irq(&zone->lru_lock);
 	if (scanning_global_lru(sc)) {
 		nr_taken = isolate_pages_global(nr_pages, &l_hold,
 						&pgscanned, sc->order,
-						ISOLATE_ACTIVE, zone,
+						reclaim_mode, zone,
 						1, file);
 		zone->pages_scanned += pgscanned;
 	} else {
 		nr_taken = mem_cgroup_isolate_pages(nr_pages, &l_hold,
 						&pgscanned, sc->order,
-						ISOLATE_ACTIVE, zone,
+						reclaim_mode, zone,
 						sc->mem_cgroup, 1, file);
 		/*
 		 * mem_cgroup_isolate_pages() keeps track of
@@ -1747,23 +1849,16 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	u64 fraction[2], denominator;
 	enum lru_list l;
 	int noswap = 0;
-	int force_scan = 0;
+	bool force_scan = false;
 	unsigned long nr_force_scan[2];
 
-
-	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
-	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
-		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
-
-	if (((anon + file) >> priority) < SWAP_CLUSTER_MAX) {
-		/* kswapd does zone balancing and need to scan this zone */
-		if (scanning_global_lru(sc) && current_is_kswapd())
-			force_scan = 1;
-		/* memcg may have small limit and need to avoid priority drop */
-		if (!scanning_global_lru(sc))
-			force_scan = 1;
-	}
+	/* kswapd does zone balancing and needs to scan this zone */
+	if (scanning_global_lru(sc) && current_is_kswapd() &&
+	    zone->all_unreclaimable)
+		force_scan = true;
+	/* memcg may have small limit and need to avoid priority drop */
+	if (!scanning_global_lru(sc))
+		force_scan = true;
 
 	/* If we have no swap space, do not bother scanning anon pages. */
 	if (!sc->may_swap || (nr_swap_pages <= 0)) {
@@ -1776,6 +1871,11 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 		goto out;
 	}
 
+	anon  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+
 	if (scanning_global_lru(sc)) {
 		free  = zone_page_state(zone, NR_FREE_PAGES);
 		/* If we have very few page cache pages,
@@ -1912,8 +2012,9 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	 * inactive lists are large enough, continue reclaiming
 	 */
 	pages_for_compaction = (2UL << sc->order);
-	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON) +
-				zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	inactive_lru_pages = zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
+	if (nr_swap_pages > 0)
+		inactive_lru_pages += zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
 	if (sc->nr_reclaimed < pages_for_compaction &&
 			inactive_lru_pages > pages_for_compaction)
 		return true;
@@ -1985,6 +2086,42 @@ restart:
 	throttle_vm_writeout(sc->gfp_mask);
 }
 
+/* Returns true if compaction should go ahead for a high-order request */
+static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
+{
+	unsigned long balance_gap, watermark;
+	bool watermark_ok;
+
+	/* Do not consider compaction for orders reclaim is meant to satisfy */
+	if (sc->order <= PAGE_ALLOC_COSTLY_ORDER)
+		return false;
+
+	/*
+	 * Compaction takes time to run and there are potentially other
+	 * callers using the pages just freed. Continue reclaiming until
+	 * there is a buffer of free pages available to give compaction
+	 * a reasonable chance of completing and allocating the page
+	 */
+	balance_gap = min(low_wmark_pages(zone),
+		(zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+			KSWAPD_ZONE_BALANCE_GAP_RATIO);
+	watermark = high_wmark_pages(zone) + balance_gap + (2UL << sc->order);
+	watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, 0, 0);
+
+	/*
+	 * If compaction is deferred, reclaim up to a point where
+	 * compaction will have a chance of success when re-enabled
+	 */
+	if (compaction_deferred(zone))
+		return watermark_ok;
+
+	/* If compaction is not ready to start, keep reclaiming */
+	if (!compaction_suitable(zone, sc->order))
+		return false;
+
+	return watermark_ok;
+}
+
 /*
  * This is the direct reclaim path, for page-allocating processes.  We only
  * try to reclaim pages from zones which will satisfy the caller's allocation
@@ -2000,14 +2137,20 @@ restart:
  *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
+ *
+ * This function returns true if a zone is being reclaimed for a costly
+ * high-order allocation and compaction is ready to begin. This indicates to
+ * the caller that it should consider retrying the allocation instead of
+ * further reclaim.
  */
-static void shrink_zones(int priority, struct zonelist *zonelist,
+static bool shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long nr_soft_reclaimed;
 	unsigned long nr_soft_scanned;
+	bool aborted_reclaim = false;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2022,6 +2165,21 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 				continue;
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
+			if (COMPACTION_BUILD) {
+				/*
+				 * If we already have plenty of memory free for
+				 * compaction in this zone, don't free any more.
+				 * Even though compaction is invoked for any
+				 * non-zero order, only frequent costly order
+				 * reclamation is disruptive enough to become a
+				 * noticable problem, like transparent huge page
+				 * allocations.
+				 */
+				if (compaction_ready(zone, sc)) {
+					aborted_reclaim = true;
+					continue;
+				}
+			}
 			/*
 			 * This steals pages from memory cgroups over softlimit
 			 * and returns the number of reclaimed pages and
@@ -2039,6 +2197,8 @@ static void shrink_zones(int priority, struct zonelist *zonelist,
 
 		shrink_zone(priority, zone, sc);
 	}
+
+	return aborted_reclaim;
 }
 
 static bool zone_reclaimable(struct zone *zone)
@@ -2092,8 +2252,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	struct zoneref *z;
 	struct zone *zone;
 	unsigned long writeback_threshold;
+	bool aborted_reclaim;
 
-	get_mems_allowed();
 	delayacct_freepages_start();
 
 	if (scanning_global_lru(sc))
@@ -2103,7 +2263,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token(sc->mem_cgroup);
-		shrink_zones(priority, zonelist, sc);
+		aborted_reclaim = shrink_zones(priority, zonelist, sc);
+
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
@@ -2155,7 +2316,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 out:
 	delayacct_freepages_end();
-	put_mems_allowed();
 
 	if (sc->nr_reclaimed)
 		return sc->nr_reclaimed;
@@ -2168,6 +2328,10 @@ out:
 	if (oom_killer_disabled)
 		return 0;
 
+	/* Aborted reclaim to try compaction? don't OOM, then */
+	if (aborted_reclaim)
+		return 1;
+
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
@@ -2459,6 +2623,9 @@ loop_again:
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
+			} else {
+				/* If balanced, clear the congested flag */
+				zone_clear_flag(zone, ZONE_CONGESTED);
 			}
 		}
 		if (i < 0)
@@ -2695,7 +2862,10 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 		 * them before going back to sleep.
 		 */
 		set_pgdat_percpu_threshold(pgdat, calculate_normal_threshold);
-		schedule();
+
+		if (!kthread_should_stop())
+			schedule();
+
 		set_pgdat_percpu_threshold(pgdat, calculate_pressure_threshold);
 	} else {
 		if (remaining)
@@ -2722,7 +2892,9 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 static int kswapd(void *p)
 {
 	unsigned long order, new_order;
+	unsigned balanced_order;
 	int classzone_idx, new_classzone_idx;
+	int balanced_classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -2753,7 +2925,9 @@ static int kswapd(void *p)
 	set_freezable();
 
 	order = new_order = 0;
+	balanced_order = 0;
 	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
+	balanced_classzone_idx = classzone_idx;
 	for ( ; ; ) {
 		int ret;
 
@@ -2762,7 +2936,8 @@ static int kswapd(void *p)
 		 * new request of a similar or harder type will succeed soon
 		 * so consider going to sleep on the basis we reclaimed at
 		 */
-		if (classzone_idx >= new_classzone_idx && order == new_order) {
+		if (balanced_classzone_idx >= new_classzone_idx &&
+					balanced_order == new_order) {
 			new_order = pgdat->kswapd_max_order;
 			new_classzone_idx = pgdat->classzone_idx;
 			pgdat->kswapd_max_order =  0;
@@ -2777,9 +2952,12 @@ static int kswapd(void *p)
 			order = new_order;
 			classzone_idx = new_classzone_idx;
 		} else {
-			kswapd_try_to_sleep(pgdat, order, classzone_idx);
+			kswapd_try_to_sleep(pgdat, balanced_order,
+						balanced_classzone_idx);
 			order = pgdat->kswapd_max_order;
 			classzone_idx = pgdat->classzone_idx;
+			new_order = order;
+			new_classzone_idx = classzone_idx;
 			pgdat->kswapd_max_order = 0;
 			pgdat->classzone_idx = pgdat->nr_zones - 1;
 		}
@@ -2794,7 +2972,9 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			order = balance_pgdat(pgdat, order, &classzone_idx);
+			balanced_classzone_idx = classzone_idx;
+			balanced_order = balance_pgdat(pgdat, order,
+						&balanced_classzone_idx);
 		}
 	}
 	return 0;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 20c18b7..6559013 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -78,7 +78,7 @@ void vm_events_fold_cpu(int cpu)
  *
  * vm_stat contains the global counters
  */
-atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS];
+atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS] __cacheline_aligned_in_smp;
 EXPORT_SYMBOL(vm_stat);
 
 #ifdef CONFIG_SMP