X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=mm%2Fvmscan.c;h=dea7abd310980daea1fa6c5a0c850a972fe37a21;hb=1c2ffff407140adf75bb72ae375688480793a228;hp=062767d159dadb2dba166cdc4aa738a6a5a6cb91;hpb=ff30153bf9647c8646538810d4c01015a5e44787;p=safe%2Fjmp%2Flinux-2.6

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 062767d..dea7abd 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -52,11 +52,17 @@ struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
+	/* Number of pages freed so far during a call to shrink_zones() */
+	unsigned long nr_reclaimed;
+
 	/* This context's GFP mask */
 	gfp_t gfp_mask;
 
 	int may_writepage;
 
+	/* Can mapped pages be reclaimed? */
+	int may_unmap;
+
 	/* Can pages be swapped as part of reclaim? */
 	int may_swap;
 
@@ -75,6 +81,12 @@ struct scan_control {
 	/* Which cgroup do we reclaim from */
 	struct mem_cgroup *mem_cgroup;
 
+	/*
+	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
+	 * are scanned.
+	 */
+	nodemask_t	*nodemask;
+
 	/* Pluggable isolate pages callback */
 	unsigned long (*isolate_pages)(unsigned long nr, struct list_head *dst,
 			unsigned long *scanned, int order, int mode,
@@ -122,11 +134,30 @@ static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
-#define scan_global_lru(sc)	(!(sc)->mem_cgroup)
+#define scanning_global_lru(sc)	(!(sc)->mem_cgroup)
 #else
-#define scan_global_lru(sc)	(1)
+#define scanning_global_lru(sc)	(1)
 #endif
 
+static struct zone_reclaim_stat *get_reclaim_stat(struct zone *zone,
+						  struct scan_control *sc)
+{
+	if (!scanning_global_lru(sc))
+		return mem_cgroup_get_reclaim_stat(sc->mem_cgroup, zone);
+
+	return &zone->reclaim_stat;
+}
+
+static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
+				   enum lru_list lru)
+{
+	if (!scanning_global_lru(sc))
+		return mem_cgroup_zone_nr_pages(sc->mem_cgroup, zone, lru);
+
+	return zone_page_state(zone, NR_LRU_BASE + lru);
+}
+
+
 /*
  * Add a shrinker callback to be called from the vm
  */
@@ -192,8 +223,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 		do_div(delta, lru_pages + 1);
 		shrinker->nr += delta;
 		if (shrinker->nr < 0) {
-			printk(KERN_ERR "%s: nr=%ld\n",
-					__func__, shrinker->nr);
+			printk(KERN_ERR "shrink_slab: %pF negative objects to "
+			       "delete nr=%ld\n",
+			       shrinker->shrink, shrinker->nr);
 			shrinker->nr = max_pass;
 		}
 
@@ -254,7 +286,7 @@ static inline int page_mapping_inuse(struct page *page)
 
 static inline int is_page_cache_freeable(struct page *page)
 {
-	return page_count(page) - !!PagePrivate(page) == 2;
+	return page_count(page) - !!page_has_private(page) == 2;
 }
 
 static int may_write_to_queue(struct backing_dev_info *bdi)
@@ -338,7 +370,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 		 * Some data journaling orphaned pages can have
 		 * page->mapping == NULL while being dirty with clean buffers.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (try_to_free_buffers(page)) {
 				ClearPageDirty(page);
 				printk("%s: orphaned page\n", __func__);
@@ -438,10 +470,11 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 		swp_entry_t swap = { .val = page_private(page) };
 		__delete_from_swap_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
-		swap_free(swap);
+		swapcache_free(swap, page);
 	} else {
 		__remove_from_page_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
+		mem_cgroup_uncharge_cache_page(page);
 	}
 
 	return 1;
@@ -480,7 +513,6 @@ int remove_mapping(struct address_space *mapping, struct page *page)
  *
  * lru_lock must not be held, interrupts must be enabled.
  */
-#ifdef CONFIG_UNEVICTABLE_LRU
 void putback_lru_page(struct page *page)
 {
 	int lru;
@@ -509,7 +541,6 @@ redo:
 		lru = LRU_UNEVICTABLE;
 		add_page_to_unevictable_list(page);
 	}
-	mem_cgroup_move_lists(page, lru);
 
 	/*
 	 * page's status can change while we move it among lru. If an evictable
@@ -535,21 +566,6 @@ redo:
 	put_page(page);		/* drop ref from isolate */
 }
 
-#else /* CONFIG_UNEVICTABLE_LRU */
-
-void putback_lru_page(struct page *page)
-{
-	int lru;
-	VM_BUG_ON(PageLRU(page));
-
-	lru = !!TestClearPageActive(page) + page_is_file_cache(page);
-	lru_cache_add_lru(page, lru);
-	mem_cgroup_move_lists(page, lru);
-	put_page(page);
-}
-#endif /* CONFIG_UNEVICTABLE_LRU */
-
-
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -561,6 +577,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 	struct pagevec freed_pvec;
 	int pgactivate = 0;
 	unsigned long nr_reclaimed = 0;
+	unsigned long vm_flags;
 
 	cond_resched();
 
@@ -586,7 +603,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		if (unlikely(!page_evictable(page, NULL)))
 			goto cull_mlocked;
 
-		if (!sc->may_swap && page_mapped(page))
+		if (!sc->may_unmap && page_mapped(page))
 			goto keep_locked;
 
 		/* Double the slab pressure for mapped and swapcache pages */
@@ -611,7 +628,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 				goto keep_locked;
 		}
 
-		referenced = page_referenced(page, 1, sc->mem_cgroup);
+		referenced = page_referenced(page, 1,
+						sc->mem_cgroup, &vm_flags);
 		/* In active use or really unfreeable?  Activate it. */
 		if (sc->order <= PAGE_ALLOC_COSTLY_ORDER &&
 					referenced && page_mapping_inuse(page))
@@ -700,7 +718,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * process address space (page_count == 1) it can be freed.
 		 * Otherwise, leave the page on the LRU so it is swappable.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (!try_to_release_page(page, sc->gfp_mask))
 				goto activate_locked;
 			if (!mapping && page_count(page) == 1) {
@@ -810,6 +828,7 @@ int __isolate_lru_page(struct page *page, int mode, int file)
 		return ret;
 
 	ret = -EBUSY;
+
 	if (likely(get_page_unless_zero(page))) {
 		/*
 		 * Be careful not to clear PageLRU until after we're
@@ -865,12 +884,14 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		switch (__isolate_lru_page(page, mode, file)) {
 		case 0:
 			list_move(&page->lru, dst);
+			mem_cgroup_del_lru(page);
 			nr_taken++;
 			break;
 
 		case -EBUSY:
 			/* else it is being freed elsewhere */
 			list_move(&page->lru, src);
+			mem_cgroup_rotate_lru_list(page, page_lru(page));
 			continue;
 
 		default:
@@ -909,18 +930,11 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			/* Check that we have not crossed a zone boundary. */
 			if (unlikely(page_zone_id(cursor_page) != zone_id))
 				continue;
-			switch (__isolate_lru_page(cursor_page, mode, file)) {
-			case 0:
+			if (__isolate_lru_page(cursor_page, mode, file) == 0) {
 				list_move(&cursor_page->lru, dst);
+				mem_cgroup_del_lru(cursor_page);
 				nr_taken++;
 				scan++;
-				break;
-
-			case -EBUSY:
-				/* else it is being freed elsewhere */
-				list_move(&cursor_page->lru, src);
-			default:
-				break;	/* ! on LRU or wrong list */
 			}
 		}
 	}
@@ -1026,6 +1040,20 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 	struct pagevec pvec;
 	unsigned long nr_scanned = 0;
 	unsigned long nr_reclaimed = 0;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+	int lumpy_reclaim = 0;
+
+	/*
+	 * If we need a large contiguous chunk of memory, or have
+	 * trouble getting a small set of contiguous pages, we
+	 * will reclaim both active and inactive pages.
+	 *
+	 * We use the same threshold as pageout congestion_wait below.
+	 */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		lumpy_reclaim = 1;
+	else if (sc->order && priority < DEF_PRIORITY - 2)
+		lumpy_reclaim = 1;
 
 	pagevec_init(&pvec, 1);
 
@@ -1038,19 +1066,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		unsigned long nr_freed;
 		unsigned long nr_active;
 		unsigned int count[NR_LRU_LISTS] = { 0, };
-		int mode = ISOLATE_INACTIVE;
-
-		/*
-		 * If we need a large contiguous chunk of memory, or have
-		 * trouble getting a small set of contiguous pages, we
-		 * will reclaim both active and inactive pages.
-		 *
-		 * We use the same threshold as pageout congestion_wait below.
-		 */
-		if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
-			mode = ISOLATE_BOTH;
-		else if (sc->order && priority < DEF_PRIORITY - 2)
-			mode = ISOLATE_BOTH;
+		int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
 
 		nr_taken = sc->isolate_pages(sc->swap_cluster_max,
 			     &page_list, &nr_scan, sc->order, mode,
@@ -1067,13 +1083,14 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
 						-count[LRU_INACTIVE_ANON]);
 
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc))
 			zone->pages_scanned += nr_scan;
-			zone->recent_scanned[0] += count[LRU_INACTIVE_ANON];
-			zone->recent_scanned[0] += count[LRU_ACTIVE_ANON];
-			zone->recent_scanned[1] += count[LRU_INACTIVE_FILE];
-			zone->recent_scanned[1] += count[LRU_ACTIVE_FILE];
-		}
+
+		reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
+		reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
+		reclaim_stat->recent_scanned[1] += count[LRU_INACTIVE_FILE];
+		reclaim_stat->recent_scanned[1] += count[LRU_ACTIVE_FILE];
+
 		spin_unlock_irq(&zone->lru_lock);
 
 		nr_scanned += nr_scan;
@@ -1086,8 +1103,8 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		 * but that should be acceptable to the caller
 		 */
 		if (nr_freed < nr_taken && !current_is_kswapd() &&
-					sc->order > PAGE_ALLOC_COSTLY_ORDER) {
-			congestion_wait(WRITE, HZ/10);
+		    lumpy_reclaim) {
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 			/*
 			 * The attempt at page out may have made some
@@ -1105,7 +1122,7 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 		if (current_is_kswapd()) {
 			__count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
 			__count_vm_events(KSWAPD_STEAL, nr_freed);
-		} else if (scan_global_lru(sc))
+		} else if (scanning_global_lru(sc))
 			__count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
 
 		__count_zone_vm_events(PGSTEAL, zone, nr_freed);
@@ -1131,10 +1148,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
 			SetPageLRU(page);
 			lru = page_lru(page);
 			add_page_to_lru_list(zone, page, lru);
-			mem_cgroup_move_lists(page, lru);
-			if (PageActive(page) && scan_global_lru(sc)) {
+			if (PageActive(page)) {
 				int file = !!page_is_file_cache(page);
-				zone->recent_rotated[file]++;
+				reclaim_stat->recent_rotated[file]++;
 			}
 			if (!pagevec_add(&pvec, page)) {
 				spin_unlock_irq(&zone->lru_lock);
@@ -1164,11 +1180,6 @@ static inline void note_zone_scanning_priority(struct zone *zone, int priority)
 		zone->prev_priority = priority;
 }
 
-static inline int zone_is_near_oom(struct zone *zone)
-{
-	return zone->pages_scanned >= (zone_lru_pages(zone) * 3);
-}
-
 /*
  * This moves pages from the active list to the inactive list.
  *
@@ -1187,18 +1198,55 @@ static inline int zone_is_near_oom(struct zone *zone)
  * But we had to alter page->flags anyway.
  */
 
+static void move_active_pages_to_lru(struct zone *zone,
+				     struct list_head *list,
+				     enum lru_list lru)
+{
+	unsigned long pgmoved = 0;
+	struct pagevec pvec;
+	struct page *page;
+
+	pagevec_init(&pvec, 1);
+
+	while (!list_empty(list)) {
+		page = lru_to_page(list);
+		prefetchw_prev_lru_page(page, list, flags);
+
+		VM_BUG_ON(PageLRU(page));
+		SetPageLRU(page);
+
+		VM_BUG_ON(!PageActive(page));
+		if (!is_active_lru(lru))
+			ClearPageActive(page);	/* we are de-activating */
+
+		list_move(&page->lru, &zone->lru[lru].list);
+		mem_cgroup_add_lru_list(page, lru);
+		pgmoved++;
+
+		if (!pagevec_add(&pvec, page) || list_empty(list)) {
+			spin_unlock_irq(&zone->lru_lock);
+			if (buffer_heads_over_limit)
+				pagevec_strip(&pvec);
+			__pagevec_release(&pvec);
+			spin_lock_irq(&zone->lru_lock);
+		}
+	}
+	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
+	if (!is_active_lru(lru))
+		__count_vm_events(PGDEACTIVATE, pgmoved);
+}
 
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 			struct scan_control *sc, int priority, int file)
 {
 	unsigned long pgmoved;
-	int pgdeactivate = 0;
 	unsigned long pgscanned;
+	unsigned long vm_flags;
 	LIST_HEAD(l_hold);	/* The pages which were snipped off */
+	LIST_HEAD(l_active);
 	LIST_HEAD(l_inactive);
 	struct page *page;
-	struct pagevec pvec;
-	enum lru_list lru;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
 	lru_add_drain();
 	spin_lock_irq(&zone->lru_lock);
@@ -1209,18 +1257,19 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 	 * zone->pages_scanned is used for detect zone's oom
 	 * mem_cgroup remembers nr_scan by itself.
 	 */
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		zone->pages_scanned += pgscanned;
-		zone->recent_scanned[!!file] += pgmoved;
 	}
+	reclaim_stat->recent_scanned[!!file] += pgmoved;
 
+	__count_zone_vm_events(PGREFILL, zone, pgscanned);
 	if (file)
 		__mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
 	else
 		__mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
 	spin_unlock_irq(&zone->lru_lock);
 
-	pgmoved = 0;
+	pgmoved = 0;  /* count referenced (mapping) mapped pages */
 	while (!list_empty(&l_hold)) {
 		cond_resched();
 		page = lru_to_page(&l_hold);
@@ -1233,65 +1282,112 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 
 		/* page_referenced clears PageReferenced */
 		if (page_mapping_inuse(page) &&
-		    page_referenced(page, 0, sc->mem_cgroup))
+		    page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
 			pgmoved++;
+			/*
+			 * Identify referenced, file-backed active pages and
+			 * give them one more trip around the active list. So
+			 * that executable code get better chances to stay in
+			 * memory under moderate memory pressure.  Anon pages
+			 * are not likely to be evicted by use-once streaming
+			 * IO, plus JVM can create lots of anon VM_EXEC pages,
+			 * so we ignore them here.
+			 */
+			if ((vm_flags & VM_EXEC) && !PageAnon(page)) {
+				list_add(&page->lru, &l_active);
+				continue;
+			}
+		}
 
 		list_add(&page->lru, &l_inactive);
 	}
 
-	spin_lock_irq(&zone->lru_lock);
 	/*
-	 * Count referenced pages from currently used mappings as
-	 * rotated, even though they are moved to the inactive list.
-	 * This helps balance scan pressure between file and anonymous
-	 * pages in get_scan_ratio.
+	 * Move pages back to the lru list.
 	 */
-	if (scan_global_lru(sc))
-		zone->recent_rotated[!!file] += pgmoved;
-
+	spin_lock_irq(&zone->lru_lock);
 	/*
-	 * Move the pages to the [file or anon] inactive list.
+	 * Count referenced pages from currently used mappings as rotated,
+	 * even though only some of them are actually re-activated.  This
+	 * helps balance scan pressure between file and anonymous pages in
+	 * get_scan_ratio.
 	 */
-	pagevec_init(&pvec, 1);
+	reclaim_stat->recent_rotated[!!file] += pgmoved;
 
-	pgmoved = 0;
-	lru = LRU_BASE + file * LRU_FILE;
-	while (!list_empty(&l_inactive)) {
-		page = lru_to_page(&l_inactive);
-		prefetchw_prev_lru_page(page, &l_inactive, flags);
-		VM_BUG_ON(PageLRU(page));
-		SetPageLRU(page);
-		VM_BUG_ON(!PageActive(page));
-		ClearPageActive(page);
+	move_active_pages_to_lru(zone, &l_active,
+						LRU_ACTIVE + file * LRU_FILE);
+	move_active_pages_to_lru(zone, &l_inactive,
+						LRU_BASE   + file * LRU_FILE);
 
-		list_move(&page->lru, &zone->lru[lru].list);
-		mem_cgroup_move_lists(page, lru);
-		pgmoved++;
-		if (!pagevec_add(&pvec, page)) {
-			__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
-			spin_unlock_irq(&zone->lru_lock);
-			pgdeactivate += pgmoved;
-			pgmoved = 0;
-			if (buffer_heads_over_limit)
-				pagevec_strip(&pvec);
-			__pagevec_release(&pvec);
-			spin_lock_irq(&zone->lru_lock);
-		}
-	}
-	__mod_zone_page_state(zone, NR_LRU_BASE + lru, pgmoved);
-	pgdeactivate += pgmoved;
-	if (buffer_heads_over_limit) {
-		spin_unlock_irq(&zone->lru_lock);
-		pagevec_strip(&pvec);
-		spin_lock_irq(&zone->lru_lock);
-	}
-	__count_zone_vm_events(PGREFILL, zone, pgscanned);
-	__count_vm_events(PGDEACTIVATE, pgdeactivate);
 	spin_unlock_irq(&zone->lru_lock);
-	if (vm_swap_full())
-		pagevec_swap_free(&pvec);
+}
 
-	pagevec_release(&pvec);
+static int inactive_anon_is_low_global(struct zone *zone)
+{
+	unsigned long active, inactive;
+
+	active = zone_page_state(zone, NR_ACTIVE_ANON);
+	inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+
+	if (inactive * zone->inactive_ratio < active)
+		return 1;
+
+	return 0;
+}
+
+/**
+ * inactive_anon_is_low - check if anonymous pages need to be deactivated
+ * @zone: zone to check
+ * @sc:   scan control of this context
+ *
+ * Returns true if the zone does not have enough inactive anon pages,
+ * meaning some active anon pages need to be deactivated.
+ */
+static int inactive_anon_is_low(struct zone *zone, struct scan_control *sc)
+{
+	int low;
+
+	if (scanning_global_lru(sc))
+		low = inactive_anon_is_low_global(zone);
+	else
+		low = mem_cgroup_inactive_anon_is_low(sc->mem_cgroup);
+	return low;
+}
+
+static int inactive_file_is_low_global(struct zone *zone)
+{
+	unsigned long active, inactive;
+
+	active = zone_page_state(zone, NR_ACTIVE_FILE);
+	inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+
+	return (active > inactive);
+}
+
+/**
+ * inactive_file_is_low - check if file pages need to be deactivated
+ * @zone: zone to check
+ * @sc:   scan control of this context
+ *
+ * When the system is doing streaming IO, memory pressure here
+ * ensures that active file pages get deactivated, until more
+ * than half of the file pages are on the inactive list.
+ *
+ * Once we get to that situation, protect the system's working
+ * set from being evicted by disabling active file page aging.
+ *
+ * This uses a different ratio than the anonymous pages, because
+ * the page cache uses a use-once replacement algorithm.
+ */
+static int inactive_file_is_low(struct zone *zone, struct scan_control *sc)
+{
+	int low;
+
+	if (scanning_global_lru(sc))
+		low = inactive_file_is_low_global(zone);
+	else
+		low = mem_cgroup_inactive_file_is_low(sc->mem_cgroup);
+	return low;
 }
 
 static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
@@ -1299,13 +1395,12 @@ static unsigned long shrink_list(enum lru_list lru, unsigned long nr_to_scan,
 {
 	int file = is_file_lru(lru);
 
-	if (lru == LRU_ACTIVE_FILE) {
+	if (lru == LRU_ACTIVE_FILE && inactive_file_is_low(zone, sc)) {
 		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
 
-	if (lru == LRU_ACTIVE_ANON &&
-	    (!scan_global_lru(sc) || inactive_anon_is_low(zone))) {
+	if (lru == LRU_ACTIVE_ANON && inactive_anon_is_low(zone, sc)) {
 		shrink_active_list(nr_to_scan, zone, sc, priority, file);
 		return 0;
 	}
@@ -1327,25 +1422,22 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	unsigned long anon, file, free;
 	unsigned long anon_prio, file_prio;
 	unsigned long ap, fp;
-
-	/* If we have no swap space, do not bother scanning anon pages. */
-	if (nr_swap_pages <= 0) {
-		percent[0] = 0;
-		percent[1] = 100;
-		return;
-	}
-
-	anon  = zone_page_state(zone, NR_ACTIVE_ANON) +
-		zone_page_state(zone, NR_INACTIVE_ANON);
-	file  = zone_page_state(zone, NR_ACTIVE_FILE) +
-		zone_page_state(zone, NR_INACTIVE_FILE);
-	free  = zone_page_state(zone, NR_FREE_PAGES);
-
-	/* If we have very few page cache pages, force-scan anon pages. */
-	if (unlikely(file + free <= zone->pages_high)) {
-		percent[0] = 100;
-		percent[1] = 0;
-		return;
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+
+	anon  = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
+		zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
+	file  = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
+		zone_nr_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,
+		   force-scan anon pages. */
+		if (unlikely(file + free <= high_wmark_pages(zone))) {
+			percent[0] = 100;
+			percent[1] = 0;
+			return;
+		}
 	}
 
 	/*
@@ -1359,17 +1451,17 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	 *
 	 * anon in [0], file in [1]
 	 */
-	if (unlikely(zone->recent_scanned[0] > anon / 4)) {
+	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
 		spin_lock_irq(&zone->lru_lock);
-		zone->recent_scanned[0] /= 2;
-		zone->recent_rotated[0] /= 2;
+		reclaim_stat->recent_scanned[0] /= 2;
+		reclaim_stat->recent_rotated[0] /= 2;
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
-	if (unlikely(zone->recent_scanned[1] > file / 4)) {
+	if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
 		spin_lock_irq(&zone->lru_lock);
-		zone->recent_scanned[1] /= 2;
-		zone->recent_rotated[1] /= 2;
+		reclaim_stat->recent_scanned[1] /= 2;
+		reclaim_stat->recent_rotated[1] /= 2;
 		spin_unlock_irq(&zone->lru_lock);
 	}
 
@@ -1385,84 +1477,111 @@ static void get_scan_ratio(struct zone *zone, struct scan_control *sc,
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
 	 */
-	ap = (anon_prio + 1) * (zone->recent_scanned[0] + 1);
-	ap /= zone->recent_rotated[0] + 1;
+	ap = (anon_prio + 1) * (reclaim_stat->recent_scanned[0] + 1);
+	ap /= reclaim_stat->recent_rotated[0] + 1;
 
-	fp = (file_prio + 1) * (zone->recent_scanned[1] + 1);
-	fp /= zone->recent_rotated[1] + 1;
+	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
+	fp /= reclaim_stat->recent_rotated[1] + 1;
 
 	/* Normalize to percentages */
 	percent[0] = 100 * ap / (ap + fp + 1);
 	percent[1] = 100 - percent[0];
 }
 
+/*
+ * Smallish @nr_to_scan's are deposited in @nr_saved_scan,
+ * until we collected @swap_cluster_max pages to scan.
+ */
+static unsigned long nr_scan_try_batch(unsigned long nr_to_scan,
+				       unsigned long *nr_saved_scan,
+				       unsigned long swap_cluster_max)
+{
+	unsigned long nr;
+
+	*nr_saved_scan += nr_to_scan;
+	nr = *nr_saved_scan;
+
+	if (nr >= swap_cluster_max)
+		*nr_saved_scan = 0;
+	else
+		nr = 0;
+
+	return nr;
+}
 
 /*
  * This is a basic per-zone page freer.  Used by both kswapd and direct reclaim.
  */
-static unsigned long shrink_zone(int priority, struct zone *zone,
+static void shrink_zone(int priority, struct zone *zone,
 				struct scan_control *sc)
 {
 	unsigned long nr[NR_LRU_LISTS];
 	unsigned long nr_to_scan;
-	unsigned long nr_reclaimed = 0;
 	unsigned long percent[2];	/* anon @ 0; file @ 1 */
 	enum lru_list l;
+	unsigned long nr_reclaimed = sc->nr_reclaimed;
+	unsigned long swap_cluster_max = sc->swap_cluster_max;
+	int noswap = 0;
 
-	get_scan_ratio(zone, sc, percent);
+	/* If we have no swap space, do not bother scanning anon pages. */
+	if (!sc->may_swap || (nr_swap_pages <= 0)) {
+		noswap = 1;
+		percent[0] = 0;
+		percent[1] = 100;
+	} else
+		get_scan_ratio(zone, sc, percent);
 
 	for_each_evictable_lru(l) {
-		if (scan_global_lru(sc)) {
-			int file = is_file_lru(l);
-			int scan;
-
-			scan = zone_page_state(zone, NR_LRU_BASE + l);
-			if (priority) {
-				scan >>= priority;
-				scan = (scan * percent[file]) / 100;
-			}
-			zone->lru[l].nr_scan += scan;
-			nr[l] = zone->lru[l].nr_scan;
-			if (nr[l] >= sc->swap_cluster_max)
-				zone->lru[l].nr_scan = 0;
-			else
-				nr[l] = 0;
-		} else {
-			/*
-			 * This reclaim occurs not because zone memory shortage
-			 * but because memory controller hits its limit.
-			 * Don't modify zone reclaim related data.
-			 */
-			nr[l] = mem_cgroup_calc_reclaim(sc->mem_cgroup, zone,
-								priority, l);
+		int file = is_file_lru(l);
+		unsigned long scan;
+
+		scan = zone_nr_pages(zone, sc, l);
+		if (priority || noswap) {
+			scan >>= priority;
+			scan = (scan * percent[file]) / 100;
 		}
+		if (scanning_global_lru(sc))
+			nr[l] = nr_scan_try_batch(scan,
+						  &zone->lru[l].nr_saved_scan,
+						  swap_cluster_max);
+		else
+			nr[l] = scan;
 	}
 
 	while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
 					nr[LRU_INACTIVE_FILE]) {
 		for_each_evictable_lru(l) {
 			if (nr[l]) {
-				nr_to_scan = min(nr[l],
-					(unsigned long)sc->swap_cluster_max);
+				nr_to_scan = min(nr[l], swap_cluster_max);
 				nr[l] -= nr_to_scan;
 
 				nr_reclaimed += shrink_list(l, nr_to_scan,
-							zone, sc, priority);
+							    zone, sc, priority);
 			}
 		}
+		/*
+		 * On large memory systems, scan >> priority can become
+		 * really large. This is fine for the starting priority;
+		 * we want to put equal scanning pressure on each zone.
+		 * However, if the VM has a harder time of freeing pages,
+		 * with multiple processes reclaiming pages, the total
+		 * freeing target can get unreasonably large.
+		 */
+		if (nr_reclaimed > swap_cluster_max &&
+			priority < DEF_PRIORITY && !current_is_kswapd())
+			break;
 	}
 
+	sc->nr_reclaimed = nr_reclaimed;
+
 	/*
 	 * Even if we did not try to evict anon pages at all, we want to
 	 * rebalance the anon lru active/inactive ratio.
 	 */
-	if (!scan_global_lru(sc) || inactive_anon_is_low(zone))
-		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
-	else if (!scan_global_lru(sc))
+	if (inactive_anon_is_low(zone, sc) && nr_swap_pages > 0)
 		shrink_active_list(SWAP_CLUSTER_MAX, zone, sc, priority, 0);
 
 	throttle_vm_writeout(sc->gfp_mask);
-	return nr_reclaimed;
 }
 
 /*
@@ -1470,34 +1589,34 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
  * try to reclaim pages from zones which will satisfy the caller's allocation
  * request.
  *
- * We reclaim from a zone even if that zone is over pages_high.  Because:
+ * We reclaim from a zone even if that zone is over high_wmark_pages(zone).
+ * Because:
  * a) The caller may be trying to free *extra* pages to satisfy a higher-order
  *    allocation or
- * b) The zones may be over pages_high but they must go *over* pages_high to
- *    satisfy the `incremental min' zone defense algorithm.
- *
- * Returns the number of reclaimed pages.
+ * b) The target zone may be at high_wmark_pages(zone) but the lower zones
+ *    must go *over* high_wmark_pages(zone) to satisfy the `incremental min'
+ *    zone defense algorithm.
  *
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
+static void shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
-	unsigned long nr_reclaimed = 0;
 	struct zoneref *z;
 	struct zone *zone;
 
 	sc->all_unreclaimable = 1;
-	for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
+					sc->nodemask) {
 		if (!populated_zone(zone))
 			continue;
 		/*
 		 * Take care memory controller reclaiming has small influence
 		 * to global LRU.
 		 */
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc)) {
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
 			note_zone_scanning_priority(zone, priority);
@@ -1516,10 +1635,8 @@ static unsigned long shrink_zones(int priority, struct zonelist *zonelist,
 							priority);
 		}
 
-		nr_reclaimed += shrink_zone(priority, zone, sc);
+		shrink_zone(priority, zone, sc);
 	}
-
-	return nr_reclaimed;
 }
 
 /*
@@ -1544,7 +1661,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 	int priority;
 	unsigned long ret = 0;
 	unsigned long total_scanned = 0;
-	unsigned long nr_reclaimed = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	unsigned long lru_pages = 0;
 	struct zoneref *z;
@@ -1553,12 +1669,12 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 	delayacct_freepages_start();
 
-	if (scan_global_lru(sc))
+	if (scanning_global_lru(sc))
 		count_vm_event(ALLOCSTALL);
 	/*
 	 * mem_cgroup will not do shrink_slab.
 	 */
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
@@ -1572,21 +1688,21 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		nr_reclaimed += shrink_zones(priority, zonelist, sc);
+		shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
 		 */
-		if (scan_global_lru(sc)) {
+		if (scanning_global_lru(sc)) {
 			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
 			if (reclaim_state) {
-				nr_reclaimed += reclaim_state->reclaimed_slab;
+				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
 				reclaim_state->reclaimed_slab = 0;
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (nr_reclaimed >= sc->swap_cluster_max) {
-			ret = nr_reclaimed;
+		if (sc->nr_reclaimed >= sc->swap_cluster_max) {
+			ret = sc->nr_reclaimed;
 			goto out;
 		}
 
@@ -1605,11 +1721,11 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc->nr_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
 	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (!sc->all_unreclaimable && scan_global_lru(sc))
-		ret = nr_reclaimed;
+	if (!sc->all_unreclaimable && scanning_global_lru(sc))
+		ret = sc->nr_reclaimed;
 out:
 	/*
 	 * Now that we've scanned all the zones at this priority level, note
@@ -1621,7 +1737,7 @@ out:
 	if (priority < 0)
 		priority = 0;
 
-	if (scan_global_lru(sc)) {
+	if (scanning_global_lru(sc)) {
 		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
 
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
@@ -1638,17 +1754,19 @@ out:
 }
 
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
-								gfp_t gfp_mask)
+				gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
+		.may_unmap = 1,
 		.may_swap = 1,
 		.swappiness = vm_swappiness,
 		.order = order,
 		.mem_cgroup = NULL,
 		.isolate_pages = isolate_pages_global,
+		.nodemask = nodemask,
 	};
 
 	return do_try_to_free_pages(zonelist, &sc);
@@ -1657,16 +1775,20 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
 
 unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
-						gfp_t gfp_mask)
+					   gfp_t gfp_mask,
+					   bool noswap,
+					   unsigned int swappiness)
 {
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
-		.may_swap = 1,
+		.may_unmap = 1,
+		.may_swap = !noswap,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
-		.swappiness = vm_swappiness,
+		.swappiness = swappiness,
 		.order = 0,
 		.mem_cgroup = mem_cont,
 		.isolate_pages = mem_cgroup_isolate_pages,
+		.nodemask = NULL, /* we don't care the placement */
 	};
 	struct zonelist *zonelist;
 
@@ -1679,7 +1801,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 
 /*
  * For kswapd, balance_pgdat() will work across all this node's zones until
- * they are all at pages_high.
+ * they are all at high_wmark_pages(zone).
  *
  * Returns the number of pages which were actually freed.
  *
@@ -1692,11 +1814,11 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
  * the zone for when the problem goes away.
  *
  * kswapd scans the zones in the highmem->normal->dma direction.  It skips
- * zones which have free_pages > pages_high, but once a zone is found to have
- * free_pages <= pages_high, we scan that zone and the lower zones regardless
- * of the number of free pages in the lower zones.  This interoperates with
- * the page allocator fallback scheme to ensure that aging of pages is balanced
- * across the zones.
+ * zones which have free_pages > high_wmark_pages(zone), but once a zone is
+ * found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
+ * lower zones regardless of the number of free pages in the lower zones. This
+ * interoperates with the page allocator fallback scheme to ensure that aging
+ * of pages is balanced across the zones.
  */
 static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 {
@@ -1704,10 +1826,10 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	int priority;
 	int i;
 	unsigned long total_scanned;
-	unsigned long nr_reclaimed;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
+		.may_unmap = 1,
 		.may_swap = 1,
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
@@ -1717,13 +1839,14 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 	};
 	/*
 	 * temp_priority is used to remember the scanning priority at which
-	 * this zone was successfully refilled to free_pages == pages_high.
+	 * this zone was successfully refilled to
+	 * free_pages == high_wmark_pages(zone).
 	 */
 	int temp_priority[MAX_NR_ZONES];
 
 loop_again:
 	total_scanned = 0;
-	nr_reclaimed = 0;
+	sc.nr_reclaimed = 0;
 	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
@@ -1758,12 +1881,12 @@ loop_again:
 			 * Do some background aging of the anon list, to give
 			 * pages a chance to be referenced before reclaiming.
 			 */
-			if (inactive_anon_is_low(zone))
+			if (inactive_anon_is_low(zone, &sc))
 				shrink_active_list(SWAP_CLUSTER_MAX, zone,
 							&sc, priority, 0);
 
-			if (!zone_watermark_ok(zone, order, zone->pages_high,
-					       0, 0)) {
+			if (!zone_watermark_ok(zone, order,
+					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
 				break;
 			}
@@ -1797,8 +1920,8 @@ loop_again:
 					priority != DEF_PRIORITY)
 				continue;
 
-			if (!zone_watermark_ok(zone, order, zone->pages_high,
-					       end_zone, 0))
+			if (!zone_watermark_ok(zone, order,
+					high_wmark_pages(zone), end_zone, 0))
 				all_zones_ok = 0;
 			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
@@ -1807,13 +1930,13 @@ loop_again:
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
 			 */
-			if (!zone_watermark_ok(zone, order, 8*zone->pages_high,
-						end_zone, 0))
-				nr_reclaimed += shrink_zone(priority, zone, &sc);
+			if (!zone_watermark_ok(zone, order,
+					8*high_wmark_pages(zone), end_zone, 0))
+				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
 						lru_pages);
-			nr_reclaimed += reclaim_state->reclaimed_slab;
+			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 			if (zone_is_all_unreclaimable(zone))
 				continue;
@@ -1827,7 +1950,7 @@ loop_again:
 			 * even in laptop mode
 			 */
 			if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
-			    total_scanned > nr_reclaimed + nr_reclaimed / 2)
+			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 		}
 		if (all_zones_ok)
@@ -1837,7 +1960,7 @@ loop_again:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			congestion_wait(WRITE, HZ/10);
+			congestion_wait(BLK_RW_ASYNC, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -1845,7 +1968,7 @@ loop_again:
 		 * matches the direct reclaim path behaviour in terms of impact
 		 * on zone->*_priority.
 		 */
-		if (nr_reclaimed >= SWAP_CLUSTER_MAX)
+		if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
 			break;
 	}
 out:
@@ -1864,10 +1987,27 @@ out:
 
 		try_to_freeze();
 
+		/*
+		 * Fragmentation may mean that the system cannot be
+		 * rebalanced for high-order allocations in all zones.
+		 * At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
+		 * it means the zones have been fully scanned and are still
+		 * not balanced. For high-order allocations, there is
+		 * little point trying all over again as kswapd may
+		 * infinite loop.
+		 *
+		 * Instead, recheck all watermarks at order-0 as they
+		 * are the most important. If watermarks are ok, kswapd will go
+		 * back to sleep. High-order users can still perform direct
+		 * reclaim if they wish.
+		 */
+		if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
+			order = sc.order = 0;
+
 		goto loop_again;
 	}
 
-	return nr_reclaimed;
+	return sc.nr_reclaimed;
 }
 
 /*
@@ -1892,7 +2032,9 @@ static int kswapd(void *p)
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
-	node_to_cpumask_ptr(cpumask, pgdat->node_id);
+	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
+
+	lockdep_set_current_reclaim_state(GFP_KERNEL);
 
 	if (!cpumask_empty(cpumask))
 		set_cpus_allowed_ptr(tsk, cpumask);
@@ -1955,7 +2097,7 @@ void wakeup_kswapd(struct zone *zone, int order)
 		return;
 
 	pgdat = zone->zone_pgdat;
-	if (zone_watermark_ok(zone, order, zone->pages_low, 0, 0))
+	if (zone_watermark_ok(zone, order, low_wmark_pages(zone), 0, 0))
 		return;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;
@@ -1974,52 +2116,50 @@ unsigned long global_lru_pages(void)
 		+ global_page_state(NR_INACTIVE_FILE);
 }
 
-#ifdef CONFIG_PM
+#ifdef CONFIG_HIBERNATION
 /*
  * Helper function for shrink_all_memory().  Tries to reclaim 'nr_pages' pages
- * from LRU lists system-wide, for given pass and priority, and returns the
- * number of reclaimed pages
+ * from LRU lists system-wide, for given pass and priority.
  *
  * For pass > 3 we also try to shrink the LRU lists that contain a few pages
  */
-static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
+static void shrink_all_zones(unsigned long nr_pages, int prio,
 				      int pass, struct scan_control *sc)
 {
 	struct zone *zone;
-	unsigned long nr_to_scan, ret = 0;
-	enum lru_list l;
+	unsigned long nr_reclaimed = 0;
 
-	for_each_zone(zone) {
-
-		if (!populated_zone(zone))
-			continue;
+	for_each_populated_zone(zone) {
+		enum lru_list l;
 
 		if (zone_is_all_unreclaimable(zone) && prio != DEF_PRIORITY)
 			continue;
 
 		for_each_evictable_lru(l) {
+			enum zone_stat_item ls = NR_LRU_BASE + l;
+			unsigned long lru_pages = zone_page_state(zone, ls);
+
 			/* For pass = 0, we don't shrink the active list */
-			if (pass == 0 &&
-				(l == LRU_ACTIVE || l == LRU_ACTIVE_FILE))
+			if (pass == 0 && (l == LRU_ACTIVE_ANON ||
+						l == LRU_ACTIVE_FILE))
 				continue;
 
-			zone->lru[l].nr_scan +=
-				(zone_page_state(zone, NR_LRU_BASE + l)
-								>> prio) + 1;
-			if (zone->lru[l].nr_scan >= nr_pages || pass > 3) {
-				zone->lru[l].nr_scan = 0;
-				nr_to_scan = min(nr_pages,
-					zone_page_state(zone,
-							NR_LRU_BASE + l));
-				ret += shrink_list(l, nr_to_scan, zone,
+			zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
+			if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
+				unsigned long nr_to_scan;
+
+				zone->lru[l].nr_saved_scan = 0;
+				nr_to_scan = min(nr_pages, lru_pages);
+				nr_reclaimed += shrink_list(l, nr_to_scan, zone,
 								sc, prio);
-				if (ret >= nr_pages)
-					return ret;
+				if (nr_reclaimed >= nr_pages) {
+					sc->nr_reclaimed += nr_reclaimed;
+					return;
+				}
 			}
 		}
 	}
-
-	return ret;
+	sc->nr_reclaimed += nr_reclaimed;
 }
 
 /*
@@ -2033,16 +2173,14 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int prio,
 unsigned long shrink_all_memory(unsigned long nr_pages)
 {
 	unsigned long lru_pages, nr_slab;
-	unsigned long ret = 0;
 	int pass;
 	struct reclaim_state reclaim_state;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
-		.may_swap = 0,
-		.swap_cluster_max = nr_pages,
+		.may_unmap = 0,
 		.may_writepage = 1,
-		.swappiness = vm_swappiness,
 		.isolate_pages = isolate_pages_global,
+		.nr_reclaimed = 0,
 	};
 
 	current->reclaim_state = &reclaim_state;
@@ -2056,8 +2194,8 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 		if (!reclaim_state.reclaimed_slab)
 			break;
 
-		ret += reclaim_state.reclaimed_slab;
-		if (ret >= nr_pages)
+		sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+		if (sc.nr_reclaimed >= nr_pages)
 			goto out;
 
 		nr_slab -= reclaim_state.reclaimed_slab;
@@ -2075,49 +2213,50 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 		int prio;
 
 		/* Force reclaiming mapped pages in the passes #3 and #4 */
-		if (pass > 2) {
-			sc.may_swap = 1;
-			sc.swappiness = 100;
-		}
+		if (pass > 2)
+			sc.may_unmap = 1;
 
 		for (prio = DEF_PRIORITY; prio >= 0; prio--) {
-			unsigned long nr_to_scan = nr_pages - ret;
+			unsigned long nr_to_scan = nr_pages - sc.nr_reclaimed;
 
 			sc.nr_scanned = 0;
-			ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
-			if (ret >= nr_pages)
+			sc.swap_cluster_max = nr_to_scan;
+			shrink_all_zones(nr_to_scan, prio, pass, &sc);
+			if (sc.nr_reclaimed >= nr_pages)
 				goto out;
 
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(sc.nr_scanned, sc.gfp_mask,
 					global_lru_pages());
-			ret += reclaim_state.reclaimed_slab;
-			if (ret >= nr_pages)
+			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+			if (sc.nr_reclaimed >= nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				congestion_wait(WRITE, HZ / 10);
+				congestion_wait(BLK_RW_ASYNC, HZ / 10);
 		}
 	}
 
 	/*
-	 * If ret = 0, we could not shrink LRUs, but there may be something
-	 * in slab caches
+	 * If sc.nr_reclaimed = 0, we could not shrink LRUs, but there may be
+	 * something in slab caches
 	 */
-	if (!ret) {
+	if (!sc.nr_reclaimed) {
 		do {
 			reclaim_state.reclaimed_slab = 0;
 			shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
-			ret += reclaim_state.reclaimed_slab;
-		} while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+			sc.nr_reclaimed += reclaim_state.reclaimed_slab;
+		} while (sc.nr_reclaimed < nr_pages &&
+				reclaim_state.reclaimed_slab > 0);
 	}
 
+
 out:
 	current->reclaim_state = NULL;
 
-	return ret;
+	return sc.nr_reclaimed;
 }
-#endif
+#endif /* CONFIG_HIBERNATION */
 
 /* It's optimal to keep kswapds on the same CPUs as their memory, but
    not required for correctness.  So if the last cpu in a node goes
@@ -2131,7 +2270,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
 		for_each_node_state(nid, N_HIGH_MEMORY) {
 			pg_data_t *pgdat = NODE_DATA(nid);
-			node_to_cpumask_ptr(mask, pgdat->node_id);
+			const struct cpumask *mask;
+
+			mask = cpumask_of_node(pgdat->node_id);
 
 			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
 				/* One of our CPUs online: restore mask */
@@ -2209,6 +2350,48 @@ int sysctl_min_unmapped_ratio = 1;
  */
 int sysctl_min_slab_ratio = 5;
 
+static inline unsigned long zone_unmapped_file_pages(struct zone *zone)
+{
+	unsigned long file_mapped = zone_page_state(zone, NR_FILE_MAPPED);
+	unsigned long file_lru = zone_page_state(zone, NR_INACTIVE_FILE) +
+		zone_page_state(zone, NR_ACTIVE_FILE);
+
+	/*
+	 * It's possible for there to be more file mapped pages than
+	 * accounted for by the pages on the file LRU lists because
+	 * tmpfs pages accounted for as ANON can also be FILE_MAPPED
+	 */
+	return (file_lru > file_mapped) ? (file_lru - file_mapped) : 0;
+}
+
+/* Work out how many page cache pages we can reclaim in this reclaim_mode */
+static long zone_pagecache_reclaimable(struct zone *zone)
+{
+	long nr_pagecache_reclaimable;
+	long delta = 0;
+
+	/*
+	 * If RECLAIM_SWAP is set, then all file pages are considered
+	 * potentially reclaimable. Otherwise, we have to worry about
+	 * pages like swapcache and zone_unmapped_file_pages() provides
+	 * a better estimate
+	 */
+	if (zone_reclaim_mode & RECLAIM_SWAP)
+		nr_pagecache_reclaimable = zone_page_state(zone, NR_FILE_PAGES);
+	else
+		nr_pagecache_reclaimable = zone_unmapped_file_pages(zone);
+
+	/* If we can't clean pages, remove dirty pages from consideration */
+	if (!(zone_reclaim_mode & RECLAIM_WRITE))
+		delta += zone_page_state(zone, NR_FILE_DIRTY);
+
+	/* Watch for any possible underflows due to delta */
+	if (unlikely(delta > nr_pagecache_reclaimable))
+		delta = nr_pagecache_reclaimable;
+
+	return nr_pagecache_reclaimable - delta;
+}
+
 /*
  * Try to free up some pages from this zone through reclaim.
  */
@@ -2219,14 +2402,15 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	struct task_struct *p = current;
 	struct reclaim_state reclaim_state;
 	int priority;
-	unsigned long nr_reclaimed = 0;
 	struct scan_control sc = {
 		.may_writepage = !!(zone_reclaim_mode & RECLAIM_WRITE),
-		.may_swap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_unmap = !!(zone_reclaim_mode & RECLAIM_SWAP),
+		.may_swap = 1,
 		.swap_cluster_max = max_t(unsigned long, nr_pages,
 					SWAP_CLUSTER_MAX),
 		.gfp_mask = gfp_mask,
 		.swappiness = vm_swappiness,
+		.order = order,
 		.isolate_pages = isolate_pages_global,
 	};
 	unsigned long slab_reclaimable;
@@ -2242,9 +2426,7 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	reclaim_state.reclaimed_slab = 0;
 	p->reclaim_state = &reclaim_state;
 
-	if (zone_page_state(zone, NR_FILE_PAGES) -
-		zone_page_state(zone, NR_FILE_MAPPED) >
-		zone->min_unmapped_pages) {
+	if (zone_pagecache_reclaimable(zone) > zone->min_unmapped_pages) {
 		/*
 		 * Free memory by calling shrink zone with increasing
 		 * priorities until we have enough memory freed.
@@ -2252,9 +2434,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		priority = ZONE_RECLAIM_PRIORITY;
 		do {
 			note_zone_scanning_priority(zone, priority);
-			nr_reclaimed += shrink_zone(priority, zone, &sc);
+			shrink_zone(priority, zone, &sc);
 			priority--;
-		} while (priority >= 0 && nr_reclaimed < nr_pages);
+		} while (priority >= 0 && sc.nr_reclaimed < nr_pages);
 	}
 
 	slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
@@ -2278,13 +2460,13 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * Update nr_reclaimed by the number of slab pages we
 		 * reclaimed from this zone.
 		 */
-		nr_reclaimed += slab_reclaimable -
+		sc.nr_reclaimed += slab_reclaimable -
 			zone_page_state(zone, NR_SLAB_RECLAIMABLE);
 	}
 
 	p->reclaim_state = NULL;
 	current->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE);
-	return nr_reclaimed >= nr_pages;
+	return sc.nr_reclaimed >= nr_pages;
 }
 
 int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
@@ -2302,20 +2484,18 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 * if less than a specified percentage of the zone is used by
 	 * unmapped file backed pages.
 	 */
-	if (zone_page_state(zone, NR_FILE_PAGES) -
-	    zone_page_state(zone, NR_FILE_MAPPED) <= zone->min_unmapped_pages
-	    && zone_page_state(zone, NR_SLAB_RECLAIMABLE)
-			<= zone->min_slab_pages)
-		return 0;
+	if (zone_pagecache_reclaimable(zone) <= zone->min_unmapped_pages &&
+	    zone_page_state(zone, NR_SLAB_RECLAIMABLE) <= zone->min_slab_pages)
+		return ZONE_RECLAIM_FULL;
 
 	if (zone_is_all_unreclaimable(zone))
-		return 0;
+		return ZONE_RECLAIM_FULL;
 
 	/*
 	 * Do not scan if the allocation should not be delayed.
 	 */
 	if (!(gfp_mask & __GFP_WAIT) || (current->flags & PF_MEMALLOC))
-			return 0;
+		return ZONE_RECLAIM_NOSCAN;
 
 	/*
 	 * Only run zone reclaim on the local zone or on zones that do not
@@ -2325,18 +2505,21 @@ int zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 	 */
 	node_id = zone_to_nid(zone);
 	if (node_state(node_id, N_CPU) && node_id != numa_node_id())
-		return 0;
+		return ZONE_RECLAIM_NOSCAN;
 
 	if (zone_test_and_set_flag(zone, ZONE_RECLAIM_LOCKED))
-		return 0;
+		return ZONE_RECLAIM_NOSCAN;
+
 	ret = __zone_reclaim(zone, gfp_mask, order);
 	zone_clear_flag(zone, ZONE_RECLAIM_LOCKED);
 
+	if (!ret)
+		count_vm_event(PGSCAN_ZONE_RECLAIM_FAILED);
+
 	return ret;
 }
 #endif
 
-#ifdef CONFIG_UNEVICTABLE_LRU
 /*
  * page_evictable - test whether a page is evictable
  * @page: the page to test
@@ -2385,6 +2568,7 @@ retry:
 
 		__dec_zone_state(zone, NR_UNEVICTABLE);
 		list_move(&page->lru, &zone->lru[l].list);
+		mem_cgroup_move_lists(page, LRU_UNEVICTABLE, l);
 		__inc_zone_state(zone, NR_INACTIVE_ANON + l);
 		__count_vm_event(UNEVICTABLE_PGRESCUED);
 	} else {
@@ -2393,6 +2577,7 @@ retry:
 		 */
 		SetPageUnevictable(page);
 		list_move(&page->lru, &zone->lru[LRU_UNEVICTABLE].list);
+		mem_cgroup_rotate_lru_list(page, LRU_UNEVICTABLE);
 		if (page_evictable(page, NULL))
 			goto retry;
 	}
@@ -2464,7 +2649,7 @@ void scan_mapping_unevictable_pages(struct address_space *mapping)
  * back onto @zone's unevictable list.
  */
 #define SCAN_UNEVICTABLE_BATCH_SIZE 16UL /* arbitrary lock hold batch size */
-void scan_zone_unevictable_pages(struct zone *zone)
+static void scan_zone_unevictable_pages(struct zone *zone)
 {
 	struct list_head *l_unevictable = &zone->lru[LRU_UNEVICTABLE].list;
 	unsigned long scan;
@@ -2581,4 +2766,3 @@ void scan_unevictable_unregister_node(struct node *node)
 	sysdev_remove_file(&node->sysdev, &attr_scan_unevictable_pages);
 }
 
-#endif