1 files changed, 327 insertions, 260 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 915dceb487c..c391c320dba 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -48,6 +48,9 @@
 
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/vmscan.h>
+
 struct scan_control {
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
@@ -213,8 +216,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		unsigned long long delta;
 		unsigned long total_scan;
-		unsigned long max_pass = (*shrinker->shrink)(0, gfp_mask);
+		unsigned long max_pass;
 
+		max_pass = (*shrinker->shrink)(shrinker, 0, gfp_mask);
 		delta = (4 * scanned) / shrinker->seeks;
 		delta *= max_pass;
 		do_div(delta, lru_pages + 1);
@@ -242,8 +246,9 @@ unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
 			int shrink_ret;
 			int nr_before;
 
-			nr_before = (*shrinker->shrink)(0, gfp_mask);
-			shrink_ret = (*shrinker->shrink)(this_scan, gfp_mask);
+			nr_before = (*shrinker->shrink)(shrinker, 0, gfp_mask);
+			shrink_ret = (*shrinker->shrink)(shrinker, this_scan,
+								gfp_mask);
 			if (shrink_ret == -1)
 				break;
 			if (shrink_ret < nr_before)
@@ -296,7 +301,7 @@ static int may_write_to_queue(struct backing_dev_info *bdi)
 static void handle_write_error(struct address_space *mapping,
 				struct page *page, int error)
 {
-	lock_page(page);
+	lock_page_nosync(page);
 	if (page_mapping(page) == mapping)
 		mapping_set_error(mapping, error);
 	unlock_page(page);
@@ -396,6 +401,8 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 			/* synchronous write or broken a_ops? */
 			ClearPageReclaim(page);
 		}
+		trace_mm_vmscan_writepage(page,
+			trace_reclaim_flags(page, sync_writeback));
 		inc_zone_page_state(page, NR_VMSCAN_WRITE);
 		return PAGE_SUCCESS;
 	}
@@ -615,6 +622,24 @@ static enum page_references page_check_references(struct page *page,
 	return PAGEREF_RECLAIM;
 }
 
+static noinline_for_stack void free_page_list(struct list_head *free_pages)
+{
+	struct pagevec freed_pvec;
+	struct page *page, *tmp;
+
+	pagevec_init(&freed_pvec, 1);
+
+	list_for_each_entry_safe(page, tmp, free_pages, lru) {
+		list_del(&page->lru);
+		if (!pagevec_add(&freed_pvec, page)) {
+			__pagevec_free(&freed_pvec);
+			pagevec_reinit(&freed_pvec);
+		}
+	}
+
+	pagevec_free(&freed_pvec);
+}
+
 /*
  * shrink_page_list() returns the number of reclaimed pages
  */
@@ -623,13 +648,12 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 					enum pageout_io sync_writeback)
 {
 	LIST_HEAD(ret_pages);
-	struct pagevec freed_pvec;
+	LIST_HEAD(free_pages);
 	int pgactivate = 0;
 	unsigned long nr_reclaimed = 0;
 
 	cond_resched();
 
-	pagevec_init(&freed_pvec, 1);
 	while (!list_empty(page_list)) {
 		enum page_references references;
 		struct address_space *mapping;
@@ -804,10 +828,12 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		__clear_page_locked(page);
 free_it:
 		nr_reclaimed++;
-		if (!pagevec_add(&freed_pvec, page)) {
-			__pagevec_free(&freed_pvec);
-			pagevec_reinit(&freed_pvec);
-		}
+
+		/*
+		 * Is there need to periodically free_page_list? It would
+		 * appear not as the counts should be low
+		 */
+		list_add(&page->lru, &free_pages);
 		continue;
 
 cull_mlocked:
@@ -830,9 +856,10 @@ keep:
 		list_add(&page->lru, &ret_pages);
 		VM_BUG_ON(PageLRU(page) || PageUnevictable(page));
 	}
+
+	free_page_list(&free_pages);
+
 	list_splice(&ret_pages, page_list);
-	if (pagevec_count(&freed_pvec))
-		__pagevec_free(&freed_pvec);
 	count_vm_events(PGACTIVATE, pgactivate);
 	return nr_reclaimed;
 }
@@ -914,6 +941,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		unsigned long *scanned, int order, int mode, int file)
 {
 	unsigned long nr_taken = 0;
+	unsigned long nr_lumpy_taken = 0;
+	unsigned long nr_lumpy_dirty = 0;
+	unsigned long nr_lumpy_failed = 0;
 	unsigned long scan;
 
 	for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
@@ -991,12 +1021,25 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 				list_move(&cursor_page->lru, dst);
 				mem_cgroup_del_lru(cursor_page);
 				nr_taken++;
+				nr_lumpy_taken++;
+				if (PageDirty(cursor_page))
+					nr_lumpy_dirty++;
 				scan++;
+			} else {
+				if (mode == ISOLATE_BOTH &&
+						page_count(cursor_page))
+					nr_lumpy_failed++;
 			}
 		}
 	}
 
 	*scanned = scan;
+
+	trace_mm_vmscan_lru_isolate(order,
+			nr_to_scan, scan,
+			nr_taken,
+			nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed,
+			mode);
 	return nr_taken;
 }
 
@@ -1033,7 +1076,8 @@ static unsigned long clear_active_flags(struct list_head *page_list,
 			ClearPageActive(page);
 			nr_active++;
 		}
-		count[lru]++;
+		if (count)
+			count[lru]++;
 	}
 
 	return nr_active;
@@ -1110,177 +1154,215 @@ static int too_many_isolated(struct zone *zone, int file,
 }
 
 /*
- * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
- * of reclaimed pages
+ * TODO: Try merging with migrations version of putback_lru_pages
  */
-static unsigned long shrink_inactive_list(unsigned long max_scan,
-			struct zone *zone, struct scan_control *sc,
-			int priority, int file)
+static noinline_for_stack void
+putback_lru_pages(struct zone *zone, struct scan_control *sc,
+				unsigned long nr_anon, unsigned long nr_file,
+				struct list_head *page_list)
 {
-	LIST_HEAD(page_list);
+	struct page *page;
 	struct pagevec pvec;
-	unsigned long nr_scanned = 0;
-	unsigned long nr_reclaimed = 0;
 	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
-	while (unlikely(too_many_isolated(zone, file, sc))) {
-		congestion_wait(BLK_RW_ASYNC, HZ/10);
+	pagevec_init(&pvec, 1);
 
-		/* We are about to die and free our memory. Return now. */
-		if (fatal_signal_pending(current))
-			return SWAP_CLUSTER_MAX;
+	/*
+	 * Put back any unfreeable pages.
+	 */
+	spin_lock(&zone->lru_lock);
+	while (!list_empty(page_list)) {
+		int lru;
+		page = lru_to_page(page_list);
+		VM_BUG_ON(PageLRU(page));
+		list_del(&page->lru);
+		if (unlikely(!page_evictable(page, NULL))) {
+			spin_unlock_irq(&zone->lru_lock);
+			putback_lru_page(page);
+			spin_lock_irq(&zone->lru_lock);
+			continue;
+		}
+		SetPageLRU(page);
+		lru = page_lru(page);
+		add_page_to_lru_list(zone, page, lru);
+		if (is_active_lru(lru)) {
+			int file = is_file_lru(lru);
+			reclaim_stat->recent_rotated[file]++;
+		}
+		if (!pagevec_add(&pvec, page)) {
+			spin_unlock_irq(&zone->lru_lock);
+			__pagevec_release(&pvec);
+			spin_lock_irq(&zone->lru_lock);
+		}
 	}
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
 
+	spin_unlock_irq(&zone->lru_lock);
+	pagevec_release(&pvec);
+}
 
-	pagevec_init(&pvec, 1);
+static noinline_for_stack void update_isolated_counts(struct zone *zone,
+					struct scan_control *sc,
+					unsigned long *nr_anon,
+					unsigned long *nr_file,
+					struct list_head *isolated_list)
+{
+	unsigned long nr_active;
+	unsigned int count[NR_LRU_LISTS] = { 0, };
+	struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
 
-	lru_add_drain();
-	spin_lock_irq(&zone->lru_lock);
-	do {
-		struct page *page;
-		unsigned long nr_taken;
-		unsigned long nr_scan;
-		unsigned long nr_freed;
-		unsigned long nr_active;
-		unsigned int count[NR_LRU_LISTS] = { 0, };
-		int mode = sc->lumpy_reclaim_mode ? ISOLATE_BOTH : ISOLATE_INACTIVE;
-		unsigned long nr_anon;
-		unsigned long nr_file;
+	nr_active = clear_active_flags(isolated_list, count);
+	__count_vm_events(PGDEACTIVATE, nr_active);
 
-		if (scanning_global_lru(sc)) {
-			nr_taken = isolate_pages_global(SWAP_CLUSTER_MAX,
-							&page_list, &nr_scan,
-							sc->order, mode,
-							zone, 0, file);
-			zone->pages_scanned += nr_scan;
-			if (current_is_kswapd())
-				__count_zone_vm_events(PGSCAN_KSWAPD, zone,
-						       nr_scan);
-			else
-				__count_zone_vm_events(PGSCAN_DIRECT, zone,
-						       nr_scan);
-		} else {
-			nr_taken = mem_cgroup_isolate_pages(SWAP_CLUSTER_MAX,
-							&page_list, &nr_scan,
-							sc->order, mode,
-							zone, sc->mem_cgroup,
-							0, file);
-			/*
-			 * mem_cgroup_isolate_pages() keeps track of
-			 * scanned pages on its own.
-			 */
-		}
+	__mod_zone_page_state(zone, NR_ACTIVE_FILE,
+			      -count[LRU_ACTIVE_FILE]);
+	__mod_zone_page_state(zone, NR_INACTIVE_FILE,
+			      -count[LRU_INACTIVE_FILE]);
+	__mod_zone_page_state(zone, NR_ACTIVE_ANON,
+			      -count[LRU_ACTIVE_ANON]);
+	__mod_zone_page_state(zone, NR_INACTIVE_ANON,
+			      -count[LRU_INACTIVE_ANON]);
 
-		if (nr_taken == 0)
-			goto done;
+	*nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
+	*nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
+	__mod_zone_page_state(zone, NR_ISOLATED_ANON, *nr_anon);
+	__mod_zone_page_state(zone, NR_ISOLATED_FILE, *nr_file);
 
-		nr_active = clear_active_flags(&page_list, count);
-		__count_vm_events(PGDEACTIVATE, nr_active);
+	reclaim_stat->recent_scanned[0] += *nr_anon;
+	reclaim_stat->recent_scanned[1] += *nr_file;
+}
+
+/*
+ * Returns true if the caller should wait to clean dirty/writeback pages.
+ *
+ * If we are direct reclaiming for contiguous pages and we do not reclaim
+ * everything in the list, try again and wait for writeback IO to complete.
+ * This will stall high-order allocations noticeably. Only do that when really
+ * need to free the pages under high memory pressure.
+ */
+static inline bool should_reclaim_stall(unsigned long nr_taken,
+					unsigned long nr_freed,
+					int priority,
+					struct scan_control *sc)
+{
+	int lumpy_stall_priority;
 
-		__mod_zone_page_state(zone, NR_ACTIVE_FILE,
-						-count[LRU_ACTIVE_FILE]);
-		__mod_zone_page_state(zone, NR_INACTIVE_FILE,
-						-count[LRU_INACTIVE_FILE]);
-		__mod_zone_page_state(zone, NR_ACTIVE_ANON,
-						-count[LRU_ACTIVE_ANON]);
-		__mod_zone_page_state(zone, NR_INACTIVE_ANON,
-						-count[LRU_INACTIVE_ANON]);
+	/* kswapd should not stall on sync IO */
+	if (current_is_kswapd())
+		return false;
 
-		nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
-		nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
-		__mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
-		__mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
+	/* Only stall on lumpy reclaim */
+	if (!sc->lumpy_reclaim_mode)
+		return false;
 
-		reclaim_stat->recent_scanned[0] += nr_anon;
-		reclaim_stat->recent_scanned[1] += nr_file;
+	/* If we have relaimed everything on the isolated list, no stall */
+	if (nr_freed == nr_taken)
+		return false;
 
-		spin_unlock_irq(&zone->lru_lock);
+	/*
+	 * For high-order allocations, there are two stall thresholds.
+	 * High-cost allocations stall immediately where as lower
+	 * order allocations such as stacks require the scanning
+	 * priority to be much higher before stalling.
+	 */
+	if (sc->order > PAGE_ALLOC_COSTLY_ORDER)
+		lumpy_stall_priority = DEF_PRIORITY;
+	else
+		lumpy_stall_priority = DEF_PRIORITY / 3;
 
-		nr_scanned += nr_scan;
-		nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
+	return priority <= lumpy_stall_priority;
+}
 
+/*
+ * shrink_inactive_list() is a helper for shrink_zone().  It returns the number
+ * of reclaimed pages
+ */
+static noinline_for_stack unsigned long
+shrink_inactive_list(unsigned long nr_to_scan, struct zone *zone,
+			struct scan_control *sc, int priority, int file)
+{
+	LIST_HEAD(page_list);
+	unsigned long nr_scanned;
+	unsigned long nr_reclaimed = 0;
+	unsigned long nr_taken;
+	unsigned long nr_active;
+	unsigned long nr_anon;
+	unsigned long nr_file;
+
+	while (unlikely(too_many_isolated(zone, file, sc))) {
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
+
+		/* We are about to die and free our memory. Return now. */
+		if (fatal_signal_pending(current))
+			return SWAP_CLUSTER_MAX;
+	}
+
+
+	lru_add_drain();
+	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->lumpy_reclaim_mode ?
+				ISOLATE_BOTH : ISOLATE_INACTIVE,
+			zone, 0, file);
+		zone->pages_scanned += nr_scanned;
+		if (current_is_kswapd())
+			__count_zone_vm_events(PGSCAN_KSWAPD, zone,
+					       nr_scanned);
+		else
+			__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->lumpy_reclaim_mode ?
+				ISOLATE_BOTH : ISOLATE_INACTIVE,
+			zone, sc->mem_cgroup,
+			0, file);
 		/*
-		 * If we are direct reclaiming for contiguous pages and we do
-		 * not reclaim everything in the list, try again and wait
-		 * for IO to complete. This will stall high-order allocations
-		 * but that should be acceptable to the caller
+		 * mem_cgroup_isolate_pages() keeps track of
+		 * scanned pages on its own.
 		 */
-		if (nr_freed < nr_taken && !current_is_kswapd() &&
-		    sc->lumpy_reclaim_mode) {
-			congestion_wait(BLK_RW_ASYNC, HZ/10);
+	}
 
-			/*
-			 * The attempt at page out may have made some
-			 * of the pages active, mark them inactive again.
-			 */
-			nr_active = clear_active_flags(&page_list, count);
-			count_vm_events(PGDEACTIVATE, nr_active);
+	if (nr_taken == 0) {
+		spin_unlock_irq(&zone->lru_lock);
+		return 0;
+	}
 
-			nr_freed += shrink_page_list(&page_list, sc,
-							PAGEOUT_IO_SYNC);
-		}
+	update_isolated_counts(zone, sc, &nr_anon, &nr_file, &page_list);
+
+	spin_unlock_irq(&zone->lru_lock);
 
-		nr_reclaimed += nr_freed;
+	nr_reclaimed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
 
-		local_irq_disable();
-		if (current_is_kswapd())
-			__count_vm_events(KSWAPD_STEAL, nr_freed);
-		__count_zone_vm_events(PGSTEAL, zone, nr_freed);
+	/* Check if we should syncronously wait for writeback */
+	if (should_reclaim_stall(nr_taken, nr_reclaimed, priority, sc)) {
+		congestion_wait(BLK_RW_ASYNC, HZ/10);
 
-		spin_lock(&zone->lru_lock);
 		/*
-		 * Put back any unfreeable pages.
+		 * The attempt at page out may have made some
+		 * of the pages active, mark them inactive again.
 		 */
-		while (!list_empty(&page_list)) {
-			int lru;
-			page = lru_to_page(&page_list);
-			VM_BUG_ON(PageLRU(page));
-			list_del(&page->lru);
-			if (unlikely(!page_evictable(page, NULL))) {
-				spin_unlock_irq(&zone->lru_lock);
-				putback_lru_page(page);
-				spin_lock_irq(&zone->lru_lock);
-				continue;
-			}
-			SetPageLRU(page);
-			lru = page_lru(page);
-			add_page_to_lru_list(zone, page, lru);
-			if (is_active_lru(lru)) {
-				int file = is_file_lru(lru);
-				reclaim_stat->recent_rotated[file]++;
-			}
-			if (!pagevec_add(&pvec, page)) {
-				spin_unlock_irq(&zone->lru_lock);
-				__pagevec_release(&pvec);
-				spin_lock_irq(&zone->lru_lock);
-			}
-		}
-		__mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
-		__mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
+		nr_active = clear_active_flags(&page_list, NULL);
+		count_vm_events(PGDEACTIVATE, nr_active);
+
+		nr_reclaimed += shrink_page_list(&page_list, sc, PAGEOUT_IO_SYNC);
+	}
 
-  	} while (nr_scanned < max_scan);
+	local_irq_disable();
+	if (current_is_kswapd())
+		__count_vm_events(KSWAPD_STEAL, nr_reclaimed);
+	__count_zone_vm_events(PGSTEAL, zone, nr_reclaimed);
 
-done:
-	spin_unlock_irq(&zone->lru_lock);
-	pagevec_release(&pvec);
+	putback_lru_pages(zone, sc, nr_anon, nr_file, &page_list);
 	return nr_reclaimed;
 }
 
 /*
- * We are about to scan this zone at a certain priority level.  If that priority
- * level is smaller (ie: more urgent) than the previous priority, then note
- * that priority level within the zone.  This is done so that when the next
- * process comes in to scan this zone, it will immediately start out at this
- * priority level rather than having to build up its own scanning priority.
- * Here, this priority affects only the reclaim-mapped threshold.
- */
-static inline void note_zone_scanning_priority(struct zone *zone, int priority)
-{
-	if (priority < zone->prev_priority)
-		zone->prev_priority = priority;
-}
-
-/*
  * This moves pages from the active list to the inactive list.
  *
  * We move them the other way if the page is referenced by one or more
@@ -1581,6 +1663,13 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	}
 
 	/*
+	 * With swappiness at 100, anonymous and file have the same priority.
+	 * This scanning priority is essentially the inverse of IO cost.
+	 */
+	anon_prio = sc->swappiness;
+	file_prio = 200 - sc->swappiness;
+
+	/*
 	 * OK, so we have swap space and a fair amount of page cache
 	 * pages.  We use the recently rotated / recently scanned
 	 * ratios to determine how valuable each cache is.
@@ -1591,28 +1680,18 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 	 *
 	 * anon in [0], file in [1]
 	 */
+	spin_lock_irq(&zone->lru_lock);
 	if (unlikely(reclaim_stat->recent_scanned[0] > anon / 4)) {
-		spin_lock_irq(&zone->lru_lock);
 		reclaim_stat->recent_scanned[0] /= 2;
 		reclaim_stat->recent_rotated[0] /= 2;
-		spin_unlock_irq(&zone->lru_lock);
 	}
 
 	if (unlikely(reclaim_stat->recent_scanned[1] > file / 4)) {
-		spin_lock_irq(&zone->lru_lock);
 		reclaim_stat->recent_scanned[1] /= 2;
 		reclaim_stat->recent_rotated[1] /= 2;
-		spin_unlock_irq(&zone->lru_lock);
 	}
 
 	/*
-	 * With swappiness at 100, anonymous and file have the same priority.
-	 * This scanning priority is essentially the inverse of IO cost.
-	 */
-	anon_prio = sc->swappiness;
-	file_prio = 200 - sc->swappiness;
-
-	/*
 	 * The amount of pressure on anon vs file pages is inversely
 	 * proportional to the fraction of recently scanned pages on
 	 * each list that were recently referenced and in active use.
@@ -1622,6 +1701,7 @@ static void get_scan_count(struct zone *zone, struct scan_control *sc,
 
 	fp = (file_prio + 1) * (reclaim_stat->recent_scanned[1] + 1);
 	fp /= reclaim_stat->recent_rotated[1] + 1;
+	spin_unlock_irq(&zone->lru_lock);
 
 	fraction[0] = ap;
 	fraction[1] = fp;
@@ -1724,16 +1804,15 @@ static void shrink_zone(int priority, struct zone *zone,
  * If a zone is deemed to be full of pinned pages then just give it a light
  * scan then give up on it.
  */
-static int shrink_zones(int priority, struct zonelist *zonelist,
+static bool shrink_zones(int priority, struct zonelist *zonelist,
 					struct scan_control *sc)
 {
-	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
 	struct zoneref *z;
 	struct zone *zone;
-	int progress = 0;
+	bool all_unreclaimable = true;
 
-	for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx,
-					sc->nodemask) {
+	for_each_zone_zonelist_nodemask(zone, z, zonelist,
+					gfp_zone(sc->gfp_mask), sc->nodemask) {
 		if (!populated_zone(zone))
 			continue;
 		/*
@@ -1743,23 +1822,14 @@ static int shrink_zones(int priority, struct zonelist *zonelist,
 		if (scanning_global_lru(sc)) {
 			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 				continue;
-			note_zone_scanning_priority(zone, priority);
-
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;	/* Let kswapd poll it */
-		} else {
-			/*
-			 * Ignore cpuset limitation here. We just want to reduce
-			 * # of used pages by us regardless of memory shortage.
-			 */
-			mem_cgroup_note_reclaim_priority(sc->mem_cgroup,
-							priority);
 		}
 
 		shrink_zone(priority, zone, sc);
-		progress = 1;
+		all_unreclaimable = false;
 	}
-	return progress;
+	return all_unreclaimable;
 }
 
 /*
@@ -1782,13 +1852,11 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 					struct scan_control *sc)
 {
 	int priority;
-	unsigned long ret = 0;
+	bool all_unreclaimable;
 	unsigned long total_scanned = 0;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
-	unsigned long lru_pages = 0;
 	struct zoneref *z;
 	struct zone *zone;
-	enum zone_type high_zoneidx = gfp_zone(sc->gfp_mask);
 	unsigned long writeback_threshold;
 
 	get_mems_allowed();
@@ -1796,29 +1864,26 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 
 	if (scanning_global_lru(sc))
 		count_vm_event(ALLOCSTALL);
-	/*
-	 * mem_cgroup will not do shrink_slab.
-	 */
-	if (scanning_global_lru(sc)) {
-		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-
-			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-				continue;
-
-			lru_pages += zone_reclaimable_pages(zone);
-		}
-	}
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		sc->nr_scanned = 0;
 		if (!priority)
 			disable_swap_token();
-		ret = shrink_zones(priority, zonelist, sc);
+		all_unreclaimable = shrink_zones(priority, zonelist, sc);
 		/*
 		 * Don't shrink slabs when reclaiming memory from
 		 * over limit cgroups
 		 */
 		if (scanning_global_lru(sc)) {
+			unsigned long lru_pages = 0;
+			for_each_zone_zonelist(zone, z, zonelist,
+					gfp_zone(sc->gfp_mask)) {
+				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
+					continue;
+
+				lru_pages += zone_reclaimable_pages(zone);
+			}
+
 			shrink_slab(sc->nr_scanned, sc->gfp_mask, lru_pages);
 			if (reclaim_state) {
 				sc->nr_reclaimed += reclaim_state->reclaimed_slab;
@@ -1826,10 +1891,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 			}
 		}
 		total_scanned += sc->nr_scanned;
-		if (sc->nr_reclaimed >= sc->nr_to_reclaim) {
-			ret = sc->nr_reclaimed;
+		if (sc->nr_reclaimed >= sc->nr_to_reclaim)
 			goto out;
-		}
 
 		/*
 		 * Try to write back as many pages as we just scanned.  This
@@ -1849,9 +1912,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		    priority < DEF_PRIORITY - 2)
 			congestion_wait(BLK_RW_ASYNC, HZ/10);
 	}
-	/* top priority shrink_zones still had more to do? don't OOM, then */
-	if (ret && scanning_global_lru(sc))
-		ret = sc->nr_reclaimed;
+
 out:
 	/*
 	 * Now that we've scanned all the zones at this priority level, note
@@ -1863,26 +1924,23 @@ out:
 	if (priority < 0)
 		priority = 0;
 
-	if (scanning_global_lru(sc)) {
-		for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
-
-			if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
-				continue;
-
-			zone->prev_priority = priority;
-		}
-	} else
-		mem_cgroup_record_reclaim_priority(sc->mem_cgroup, priority);
-
 	delayacct_freepages_end();
 	put_mems_allowed();
 
-	return ret;
+	if (sc->nr_reclaimed)
+		return sc->nr_reclaimed;
+
+	/* top priority shrink_zones still had more to do? don't OOM, then */
+	if (scanning_global_lru(sc) && !all_unreclaimable)
+		return 1;
+
+	return 0;
 }
 
 unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 				gfp_t gfp_mask, nodemask_t *nodemask)
 {
+	unsigned long nr_reclaimed;
 	struct scan_control sc = {
 		.gfp_mask = gfp_mask,
 		.may_writepage = !laptop_mode,
@@ -1895,7 +1953,15 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 		.nodemask = nodemask,
 	};
 
-	return do_try_to_free_pages(zonelist, &sc);
+	trace_mm_vmscan_direct_reclaim_begin(order,
+				sc.may_writepage,
+				gfp_mask);
+
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
+	trace_mm_vmscan_direct_reclaim_end(nr_reclaimed);
+
+	return nr_reclaimed;
 }
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR
@@ -1903,9 +1969,10 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 						gfp_t gfp_mask, bool noswap,
 						unsigned int swappiness,
-						struct zone *zone, int nid)
+						struct zone *zone)
 {
 	struct scan_control sc = {
+		.nr_to_reclaim = SWAP_CLUSTER_MAX,
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
 		.may_swap = !noswap,
@@ -1913,13 +1980,13 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 		.order = 0,
 		.mem_cgroup = mem,
 	};
-	nodemask_t nm  = nodemask_of_node(nid);
-
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
-	sc.nodemask = &nm;
-	sc.nr_reclaimed = 0;
-	sc.nr_scanned = 0;
+
+	trace_mm_vmscan_memcg_softlimit_reclaim_begin(0,
+						      sc.may_writepage,
+						      sc.gfp_mask);
+
 	/*
 	 * NOTE: Although we can get the priority field, using it
 	 * here is not a good idea, since it limits the pages we can scan.
@@ -1928,6 +1995,9 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
 	 * the priority and make it zero.
 	 */
 	shrink_zone(0, zone, &sc);
+
+	trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed);
+
 	return sc.nr_reclaimed;
 }
 
@@ -1937,6 +2007,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 					   unsigned int swappiness)
 {
 	struct zonelist *zonelist;
+	unsigned long nr_reclaimed;
 	struct scan_control sc = {
 		.may_writepage = !laptop_mode,
 		.may_unmap = 1,
@@ -1951,7 +2022,16 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
 	sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
 			(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
 	zonelist = NODE_DATA(numa_node_id())->node_zonelists;
-	return do_try_to_free_pages(zonelist, &sc);
+
+	trace_mm_vmscan_memcg_reclaim_begin(0,
+					    sc.may_writepage,
+					    sc.gfp_mask);
+
+	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+
+	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);
+
+	return nr_reclaimed;
 }
 #endif
 
@@ -2023,22 +2103,12 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.order = order,
 		.mem_cgroup = NULL,
 	};
-	/*
-	 * temp_priority is used to remember the scanning priority at which
-	 * this zone was successfully refilled to
-	 * free_pages == high_wmark_pages(zone).
-	 */
-	int temp_priority[MAX_NR_ZONES];
-
 loop_again:
 	total_scanned = 0;
 	sc.nr_reclaimed = 0;
 	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
-	for (i = 0; i < pgdat->nr_zones; i++)
-		temp_priority[i] = DEF_PRIORITY;
-
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
 		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 		unsigned long lru_pages = 0;
@@ -2098,7 +2168,6 @@ loop_again:
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 			int nr_slab;
-			int nid, zid;
 
 			if (!populated_zone(zone))
 				continue;
@@ -2106,18 +2175,14 @@ loop_again:
 			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 				continue;
 
-			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
-			note_zone_scanning_priority(zone, priority);
 
-			nid = pgdat->node_id;
-			zid = zone_idx(zone);
 			/*
 			 * Call soft limit reclaim before calling shrink_zone.
 			 * For now we ignore the return value
 			 */
-			mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask,
-							nid, zid);
+			mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask);
+
 			/*
 			 * We put equal pressure on every zone, unless one
 			 * zone has way too many pages free already.
@@ -2181,16 +2246,6 @@ loop_again:
 			break;
 	}
 out:
-	/*
-	 * Note within each zone the priority level at which this zone was
-	 * brought into a happy state.  So that the next thread which scans this
-	 * zone will start out at that priority level.
-	 */
-	for (i = 0; i < pgdat->nr_zones; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		zone->prev_priority = temp_priority[i];
-	}
 	if (!all_zones_ok) {
 		cond_resched();
 
@@ -2294,9 +2349,10 @@ static int kswapd(void *p)
 				 * premature sleep. If not, then go fully
 				 * to sleep until explicitly woken up
 				 */
-				if (!sleeping_prematurely(pgdat, order, remaining))
+				if (!sleeping_prematurely(pgdat, order, remaining)) {
+					trace_mm_vmscan_kswapd_sleep(pgdat->node_id);
 					schedule();
-				else {
+				} else {
 					if (remaining)
 						count_vm_event(KSWAPD_LOW_WMARK_HIT_QUICKLY);
 					else
@@ -2316,8 +2372,10 @@ static int kswapd(void *p)
 		 * We can speed up thawing tasks if we don't call balance_pgdat
 		 * after returning from the refrigerator
 		 */
-		if (!ret)
+		if (!ret) {
+			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
 			balance_pgdat(pgdat, order);
+		}
 	}
 	return 0;
 }
@@ -2337,6 +2395,7 @@ void wakeup_kswapd(struct zone *zone, int order)
 		return;
 	if (pgdat->kswapd_max_order < order)
 		pgdat->kswapd_max_order = order;
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
 	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 		return;
 	if (!waitqueue_active(&pgdat->kswapd_wait))
@@ -2585,9 +2644,8 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		.swappiness = vm_swappiness,
 		.order = order,
 	};
-	unsigned long slab_reclaimable;
+	unsigned long nr_slab_pages0, nr_slab_pages1;
 
-	disable_swap_token();
 	cond_resched();
 	/*
 	 * We need to be able to allocate from the reserves for RECLAIM_SWAP
@@ -2606,14 +2664,13 @@ 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);
 			shrink_zone(priority, zone, &sc);
 			priority--;
 		} while (priority >= 0 && sc.nr_reclaimed < nr_pages);
 	}
 
-	slab_reclaimable = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
-	if (slab_reclaimable > zone->min_slab_pages) {
+	nr_slab_pages0 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+	if (nr_slab_pages0 > zone->min_slab_pages) {
 		/*
 		 * shrink_slab() does not currently allow us to determine how
 		 * many pages were freed in this zone. So we take the current
@@ -2624,17 +2681,27 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * Note that shrink_slab will free memory on all zones and may
 		 * take a long time.
 		 */
-		while (shrink_slab(sc.nr_scanned, gfp_mask, order) &&
-			zone_page_state(zone, NR_SLAB_RECLAIMABLE) >
-				slab_reclaimable - nr_pages)
-			;
+		for (;;) {
+			unsigned long lru_pages = zone_reclaimable_pages(zone);
+
+			/* No reclaimable slab or very low memory pressure */
+			if (!shrink_slab(sc.nr_scanned, gfp_mask, lru_pages))
+				break;
+
+			/* Freed enough memory */
+			nr_slab_pages1 = zone_page_state(zone,
+							NR_SLAB_RECLAIMABLE);
+			if (nr_slab_pages1 + nr_pages <= nr_slab_pages0)
+				break;
+		}
 
 		/*
 		 * Update nr_reclaimed by the number of slab pages we
 		 * reclaimed from this zone.
 		 */
-		sc.nr_reclaimed += slab_reclaimable -
-			zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+		nr_slab_pages1 = zone_page_state(zone, NR_SLAB_RECLAIMABLE);
+		if (nr_slab_pages1 < nr_slab_pages0)
+			sc.nr_reclaimed += nr_slab_pages0 - nr_slab_pages1;
 	}
 
 	p->reclaim_state = NULL;