1 files changed, 35 insertions, 24 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 4f49535d4cd..5ed24b94c5e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2326,7 +2326,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
 		return true;
 
 	/* Check the watermark levels */
-	for (i = 0; i < pgdat->nr_zones; i++) {
+	for (i = 0; i <= classzone_idx; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
 		if (!populated_zone(zone))
@@ -2344,7 +2344,7 @@ static bool sleeping_prematurely(pg_data_t *pgdat, int order, long remaining,
 		}
 
 		if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone),
-							classzone_idx, 0))
+							i, 0))
 			all_zones_ok = false;
 		else
 			balanced += zone->present_pages;
@@ -2451,7 +2451,6 @@ loop_again:
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), 0, 0)) {
 				end_zone = i;
-				*classzone_idx = i;
 				break;
 			}
 		}
@@ -2510,18 +2509,18 @@ loop_again:
 				KSWAPD_ZONE_BALANCE_GAP_RATIO);
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone) + balance_gap,
-					end_zone, 0))
+					end_zone, 0)) {
 				shrink_zone(priority, zone, &sc);
-			reclaim_state->reclaimed_slab = 0;
-			nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
-			sc.nr_reclaimed += reclaim_state->reclaimed_slab;
-			total_scanned += sc.nr_scanned;
 
-			if (zone->all_unreclaimable)
-				continue;
-			if (nr_slab == 0 &&
-			    !zone_reclaimable(zone))
-				zone->all_unreclaimable = 1;
+				reclaim_state->reclaimed_slab = 0;
+				nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages);
+				sc.nr_reclaimed += reclaim_state->reclaimed_slab;
+				total_scanned += sc.nr_scanned;
+
+				if (nr_slab == 0 && !zone_reclaimable(zone))
+					zone->all_unreclaimable = 1;
+			}
+
 			/*
 			 * If we've done a decent amount of scanning and
 			 * the reclaim ratio is low, start doing writepage
@@ -2531,6 +2530,12 @@ loop_again:
 			    total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
 				sc.may_writepage = 1;
 
+			if (zone->all_unreclaimable) {
+				if (end_zone && end_zone == i)
+					end_zone--;
+				continue;
+			}
+
 			if (!zone_watermark_ok_safe(zone, order,
 					high_wmark_pages(zone), end_zone, 0)) {
 				all_zones_ok = 0;
@@ -2709,8 +2714,8 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order, int classzone_idx)
  */
 static int kswapd(void *p)
 {
-	unsigned long order;
-	int classzone_idx;
+	unsigned long order, new_order;
+	int classzone_idx, new_classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -2740,17 +2745,23 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	order = 0;
-	classzone_idx = MAX_NR_ZONES - 1;
+	order = new_order = 0;
+	classzone_idx = new_classzone_idx = pgdat->nr_zones - 1;
 	for ( ; ; ) {
-		unsigned long new_order;
-		int new_classzone_idx;
 		int ret;
 
-		new_order = pgdat->kswapd_max_order;
-		new_classzone_idx = pgdat->classzone_idx;
-		pgdat->kswapd_max_order = 0;
-		pgdat->classzone_idx = MAX_NR_ZONES - 1;
+		/*
+		 * If the last balance_pgdat was unsuccessful it's unlikely a
+		 * new request of a similar or harder type will succeed soon
+		 * so consider going to sleep on the basis we reclaimed at
+		 */
+		if (classzone_idx >= new_classzone_idx && order == new_order) {
+			new_order = pgdat->kswapd_max_order;
+			new_classzone_idx = pgdat->classzone_idx;
+			pgdat->kswapd_max_order =  0;
+			pgdat->classzone_idx = pgdat->nr_zones - 1;
+		}
+
 		if (order < new_order || classzone_idx > new_classzone_idx) {
 			/*
 			 * Don't sleep if someone wants a larger 'order'
@@ -2763,7 +2774,7 @@ static int kswapd(void *p)
 			order = pgdat->kswapd_max_order;
 			classzone_idx = pgdat->classzone_idx;
 			pgdat->kswapd_max_order = 0;
-			pgdat->classzone_idx = MAX_NR_ZONES - 1;
+			pgdat->classzone_idx = pgdat->nr_zones - 1;
 		}
 
 		ret = try_to_freeze();