Merge branch 'master' into for-next

Fast-forwarded to current state of Linus' tree as there are patches to be
applied for files that didn't exist on the old branch.

1 files changed, 31 insertions, 35 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6771ea70bfe..f6b435c8007 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -41,6 +41,7 @@
 #include <linux/memcontrol.h>
 #include <linux/delayacct.h>
 #include <linux/sysctl.h>
+#include <linux/oom.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -358,7 +359,7 @@ 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_nosync(page);
+	lock_page(page);
 	if (page_mapping(page) == mapping)
 		mapping_set_error(mapping, error);
 	unlock_page(page);
@@ -514,7 +515,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page)
 
 		freepage = mapping->a_ops->freepage;
 
-		__remove_from_page_cache(page);
+		__delete_from_page_cache(page);
 		spin_unlock_irq(&mapping->tree_lock);
 		mem_cgroup_uncharge_cache_page(page);
 
@@ -1065,7 +1066,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 		 * surrounding the tag page.  Only take those pages of
 		 * the same active state as that tag page.  We may safely
 		 * round the target page pfn down to the requested order
-		 * as the mem_map is guarenteed valid out to MAX_ORDER,
+		 * as the mem_map is guaranteed valid out to MAX_ORDER,
 		 * where that page is in a different zone we will detect
 		 * it from its zone id and abort this block scan.
 		 */
@@ -1988,17 +1989,12 @@ static bool zone_reclaimable(struct zone *zone)
 	return zone->pages_scanned < zone_reclaimable_pages(zone) * 6;
 }
 
-/*
- * As hibernation is going on, kswapd is freezed so that it can't mark
- * the zone into all_unreclaimable. It can't handle OOM during hibernation.
- * So let's check zone's unreclaimable in direct reclaim as well as kswapd.
- */
+/* All zones in zonelist are unreclaimable? */
 static bool all_unreclaimable(struct zonelist *zonelist,
 		struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
-	bool all_unreclaimable = true;
 
 	for_each_zone_zonelist_nodemask(zone, z, zonelist,
 			gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2006,13 +2002,11 @@ static bool all_unreclaimable(struct zonelist *zonelist,
 			continue;
 		if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 			continue;
-		if (zone_reclaimable(zone)) {
-			all_unreclaimable = false;
-			break;
-		}
+		if (!zone->all_unreclaimable)
+			return false;
 	}
 
-	return all_unreclaimable;
+	return true;
 }
 
 /*
@@ -2108,6 +2102,14 @@ out:
 	if (sc->nr_reclaimed)
 		return sc->nr_reclaimed;
 
+	/*
+	 * As hibernation is going on, kswapd is freezed so that it can't mark
+	 * the zone into all_unreclaimable. Thus bypassing all_unreclaimable
+	 * check.
+	 */
+	if (oom_killer_disabled)
+		return 0;
+
 	/* top priority shrink_zones still had more to do? don't OOM, then */
 	if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc))
 		return 1;
@@ -2224,7 +2226,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
  *   o a 16M DMA zone that is balanced will not balance a zone on any
  *     reasonable sized machine
  *   o On all other machines, the top zone must be at least a reasonable
- *     precentage of the middle zones. For example, on 32-bit x86, highmem
+ *     percentage of the middle zones. For example, on 32-bit x86, highmem
  *     would need to be at least 256M for it to be balance a whole node.
  *     Similarly, on x86-64 the Normal zone would need to be at least 1G
  *     to balance a node on its own. These seemed like reasonable ratios.
@@ -2397,9 +2399,9 @@ loop_again:
 		 * cause too much scanning of the lower zones.
 		 */
 		for (i = 0; i <= end_zone; i++) {
-			int compaction;
 			struct zone *zone = pgdat->node_zones + i;
 			int nr_slab;
+			unsigned long balance_gap;
 
 			if (!populated_zone(zone))
 				continue;
@@ -2416,11 +2418,20 @@ loop_again:
 			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.
+			 * We put equal pressure on every zone, unless
+			 * one zone has way too many pages free
+			 * already. The "too many pages" is defined
+			 * as the high wmark plus a "gap" where the
+			 * gap is either the low watermark or 1%
+			 * of the zone, whichever is smaller.
 			 */
+			balance_gap = min(low_wmark_pages(zone),
+				(zone->present_pages +
+					KSWAPD_ZONE_BALANCE_GAP_RATIO-1) /
+				KSWAPD_ZONE_BALANCE_GAP_RATIO);
 			if (!zone_watermark_ok_safe(zone, order,
-					8*high_wmark_pages(zone), end_zone, 0))
+					high_wmark_pages(zone) + balance_gap,
+					end_zone, 0))
 				shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
@@ -2428,24 +2439,9 @@ loop_again:
 			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
 			total_scanned += sc.nr_scanned;
 
-			compaction = 0;
-			if (order &&
-			    zone_watermark_ok(zone, 0,
-					       high_wmark_pages(zone),
-					      end_zone, 0) &&
-			    !zone_watermark_ok(zone, order,
-					       high_wmark_pages(zone),
-					       end_zone, 0)) {
-				compact_zone_order(zone,
-						   order,
-						   sc.gfp_mask, false,
-						   COMPACT_MODE_KSWAPD);
-				compaction = 1;
-			}
-
 			if (zone->all_unreclaimable)
 				continue;
-			if (!compaction && nr_slab == 0 &&
+			if (nr_slab == 0 &&
 			    !zone_reclaimable(zone))
 				zone->all_unreclaimable = 1;
 			/*