Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6

1 files changed, 45 insertions, 18 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index f05527bf792b..518540a4a2a6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -723,6 +723,20 @@ 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;
@@ -746,7 +760,7 @@ 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;
@@ -770,7 +784,7 @@ 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
@@ -922,7 +936,7 @@ 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) {
@@ -972,9 +986,7 @@ 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 */
@@ -1024,7 +1036,6 @@ 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;
 	}
 
@@ -1065,13 +1076,22 @@ unsigned long try_to_free_pages(struct zone **zones, gfp_t gfp_mask)
 	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;
 }
@@ -1111,6 +1131,11 @@ 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;
@@ -1118,11 +1143,8 @@ 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 */
@@ -1183,10 +1205,9 @@ 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,
@@ -1226,10 +1247,15 @@ 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();
@@ -1358,7 +1384,7 @@ 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);
 			}
 		}
 
@@ -1614,6 +1640,7 @@ 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);