1 files changed, 62 insertions, 26 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index eca70310adb2..093f5fe6dd77 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -36,6 +36,7 @@
 #include <linux/rwsem.h>
 #include <linux/delay.h>
 #include <linux/kthread.h>
+#include <linux/freezer.h>
 
 #include <asm/tlbflush.h>
 #include <asm/div64.h>
@@ -378,6 +379,12 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
 	return PAGE_CLEAN;
 }
 
+/*
+ * Attempt to detach a locked page from its ->mapping.  If it is dirty or if
+ * someone else has a ref on the page, abort and return 0.  If it was
+ * successfully detached, return 1.  Assumes the caller has a single ref on
+ * this page.
+ */
 int remove_mapping(struct address_space *mapping, struct page *page)
 {
 	BUG_ON(!PageLocked(page));
@@ -717,6 +724,20 @@ done:
 	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;
+}
+
 static inline int zone_is_near_oom(struct zone *zone)
 {
 	return zone->pages_scanned >= (zone->nr_active + zone->nr_inactive)*3;
@@ -740,7 +761,7 @@ static inline int zone_is_near_oom(struct zone *zone)
  * But we had to alter page->flags anyway.
  */
 static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
-				struct scan_control *sc)
+				struct scan_control *sc, int priority)
 {
 	unsigned long pgmoved;
 	int pgdeactivate = 0;
@@ -764,7 +785,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
 		 * `distress' is a measure of how much trouble we're having
 		 * reclaiming pages.  0 -> no problems.  100 -> great trouble.
 		 */
-		distress = 100 >> zone->prev_priority;
+		distress = 100 >> min(zone->prev_priority, priority);
 
 		/*
 		 * The point of this algorithm is to decide when to start
@@ -916,7 +937,7 @@ static unsigned long shrink_zone(int priority, struct zone *zone,
 			nr_to_scan = min(nr_active,
 					(unsigned long)sc->swap_cluster_max);
 			nr_active -= nr_to_scan;
-			shrink_active_list(nr_to_scan, zone, sc);
+			shrink_active_list(nr_to_scan, zone, sc, priority);
 		}
 
 		if (nr_inactive) {
@@ -966,9 +987,7 @@ static unsigned long shrink_zones(int priority, struct zone **zones,
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->temp_priority = priority;
-		if (zone->prev_priority > priority)
-			zone->prev_priority = priority;
+		note_zone_scanning_priority(zone, priority);
 
 		if (zone->all_unreclaimable && priority != DEF_PRIORITY)
 			continue;	/* Let kswapd poll it */
@@ -1018,7 +1037,6 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->temp_priority = DEF_PRIORITY;
 		lru_pages += zone->nr_active + zone->nr_inactive;
 	}
 
@@ -1053,19 +1071,28 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 
 		/* Take a nap, wait for some writeback to complete */
 		if (sc.nr_scanned && priority < DEF_PRIORITY - 2)
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 	}
 	/* top priority shrink_caches still had more to do? don't OOM, then */
 	if (!sc.all_unreclaimable)
 		ret = 1;
 out:
+	/*
+	 * Now that we've scanned all the zones at this priority level, note
+	 * that level within the zone so that the next thread which performs
+	 * scanning of this zone will immediately start out at this priority
+	 * level.  This affects only the decision whether or not to bring
+	 * mapped pages onto the inactive list.
+	 */
+	if (priority < 0)
+		priority = 0;
 	for (i = 0; zones[i] != 0; i++) {
 		struct zone *zone = zones[i];
 
 		if (!cpuset_zone_allowed(zone, __GFP_HARDWALL))
 			continue;
 
-		zone->prev_priority = zone->temp_priority;
+		zone->prev_priority = priority;
 	}
 	return ret;
 }
@@ -1105,6 +1132,11 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
 		.swap_cluster_max = SWAP_CLUSTER_MAX,
 		.swappiness = vm_swappiness,
 	};
+	/*
+	 * temp_priority is used to remember the scanning priority at which
+	 * this zone was successfully refilled to free_pages == pages_high.
+	 */
+	int temp_priority[MAX_NR_ZONES];
 
 loop_again:
 	total_scanned = 0;
@@ -1112,11 +1144,8 @@ loop_again:
 	sc.may_writepage = !laptop_mode;
 	count_vm_event(PAGEOUTRUN);
 
-	for (i = 0; i < pgdat->nr_zones; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		zone->temp_priority = DEF_PRIORITY;
-	}
+	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 */
@@ -1144,11 +1173,12 @@ loop_again:
 			if (!zone_watermark_ok(zone, order, zone->pages_high,
 					       0, 0)) {
 				end_zone = i;
-				goto scan;
+				break;
 			}
 		}
-		goto out;
-scan:
+		if (i < 0)
+			goto out;
+
 		for (i = 0; i <= end_zone; i++) {
 			struct zone *zone = pgdat->node_zones + i;
 
@@ -1177,10 +1207,9 @@ scan:
 			if (!zone_watermark_ok(zone, order, zone->pages_high,
 					       end_zone, 0))
 				all_zones_ok = 0;
-			zone->temp_priority = priority;
-			if (zone->prev_priority > priority)
-				zone->prev_priority = priority;
+			temp_priority[i] = priority;
 			sc.nr_scanned = 0;
+			note_zone_scanning_priority(zone, priority);
 			nr_reclaimed += shrink_zone(priority, zone, &sc);
 			reclaim_state->reclaimed_slab = 0;
 			nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
@@ -1208,7 +1237,7 @@ scan:
 		 * another pass across the zones.
 		 */
 		if (total_scanned && priority < DEF_PRIORITY - 2)
-			blk_congestion_wait(WRITE, HZ/10);
+			congestion_wait(WRITE, HZ/10);
 
 		/*
 		 * We do this so kswapd doesn't build up large priorities for
@@ -1220,13 +1249,21 @@ scan:
 			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 = zone->temp_priority;
+		zone->prev_priority = temp_priority[i];
 	}
 	if (!all_zones_ok) {
 		cond_resched();
+
+		try_to_freeze();
+
 		goto loop_again;
 	}
 
@@ -1352,7 +1389,7 @@ static unsigned long shrink_all_zones(unsigned long nr_pages, int pass,
 			if (zone->nr_scan_active >= nr_pages || pass > 3) {
 				zone->nr_scan_active = 0;
 				nr_to_scan = min(nr_pages, zone->nr_active);
-				shrink_active_list(nr_to_scan, zone, sc);
+				shrink_active_list(nr_to_scan, zone, sc, prio);
 			}
 		}
 
@@ -1452,7 +1489,7 @@ unsigned long shrink_all_memory(unsigned long nr_pages)
 				goto out;
 
 			if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
-				blk_congestion_wait(WRITE, HZ / 10);
+				congestion_wait(WRITE, HZ / 10);
 		}
 
 		lru_pages = 0;
@@ -1476,7 +1513,6 @@ out:
 }
 #endif
 
-#ifdef CONFIG_HOTPLUG_CPU
 /* 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
    away, we get changed to run anywhere: as the first one comes back,
@@ -1497,7 +1533,6 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	}
 	return NOTIFY_OK;
 }
-#endif /* CONFIG_HOTPLUG_CPU */
 
 /*
  * This kswapd start function will be called by init and node-hot-add.
@@ -1608,6 +1643,7 @@ 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);
 			priority--;
 		} while (priority >= 0 && nr_reclaimed < nr_pages);