1 files changed, 59 insertions, 9 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7037cc8c60b6..3584067800e1 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2246,11 +2246,14 @@ static int sleeping_prematurely(pg_data_t *pgdat, int order, long remaining)
  * interoperates with the page allocator fallback scheme to ensure that aging
  * of pages is balanced across the zones.
  */
-static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
+							int classzone_idx)
 {
 	int all_zones_ok;
+	int any_zone_ok;
 	int priority;
 	int i;
+	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 	unsigned long total_scanned;
 	struct reclaim_state *reclaim_state = current->reclaim_state;
 	struct scan_control sc = {
@@ -2273,7 +2276,6 @@ loop_again:
 	count_vm_event(PAGEOUTRUN);
 
 	for (priority = DEF_PRIORITY; priority >= 0; priority--) {
-		int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
 		unsigned long lru_pages = 0;
 		int has_under_min_watermark_zone = 0;
 
@@ -2282,6 +2284,7 @@ loop_again:
 			disable_swap_token();
 
 		all_zones_ok = 1;
+		any_zone_ok = 0;
 
 		/*
 		 * Scan in the highmem->dma direction for the highest
@@ -2400,10 +2403,12 @@ loop_again:
 				 * spectulatively avoid congestion waits
 				 */
 				zone_clear_flag(zone, ZONE_CONGESTED);
+				if (i <= classzone_idx)
+					any_zone_ok = 1;
 			}
 
 		}
-		if (all_zones_ok)
+		if (all_zones_ok || (order && any_zone_ok))
 			break;		/* kswapd: all done */
 		/*
 		 * OK, kswapd is getting into trouble.  Take a nap, then take
@@ -2426,7 +2431,13 @@ loop_again:
 			break;
 	}
 out:
-	if (!all_zones_ok) {
+
+	/*
+	 * order-0: All zones must meet high watermark for a balanced node
+	 * high-order: Any zone below pgdats classzone_idx must meet the high
+	 *             watermark for a balanced node
+	 */
+	if (!(all_zones_ok || (order && any_zone_ok))) {
 		cond_resched();
 
 		try_to_freeze();
@@ -2451,6 +2462,36 @@ out:
 		goto loop_again;
 	}
 
+	/*
+	 * If kswapd was reclaiming at a higher order, it has the option of
+	 * sleeping without all zones being balanced. Before it does, it must
+	 * ensure that the watermarks for order-0 on *all* zones are met and
+	 * that the congestion flags are cleared. The congestion flag must
+	 * be cleared as kswapd is the only mechanism that clears the flag
+	 * and it is potentially going to sleep here.
+	 */
+	if (order) {
+		for (i = 0; i <= end_zone; i++) {
+			struct zone *zone = pgdat->node_zones + i;
+
+			if (!populated_zone(zone))
+				continue;
+
+			if (zone->all_unreclaimable && priority != DEF_PRIORITY)
+				continue;
+
+			/* Confirm the zone is balanced for order-0 */
+			if (!zone_watermark_ok(zone, 0,
+					high_wmark_pages(zone), 0, 0)) {
+				order = sc.order = 0;
+				goto loop_again;
+			}
+
+			/* If balanced, clear the congested flag */
+			zone_clear_flag(zone, ZONE_CONGESTED);
+		}
+	}
+
 	return sc.nr_reclaimed;
 }
 
@@ -2514,6 +2555,7 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int order)
 static int kswapd(void *p)
 {
 	unsigned long order;
+	int classzone_idx;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -2544,21 +2586,27 @@ static int kswapd(void *p)
 	set_freezable();
 
 	order = 0;
+	classzone_idx = MAX_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;
-		if (order < new_order) {
+		pgdat->classzone_idx = MAX_NR_ZONES - 1;
+		if (order < new_order || classzone_idx > new_classzone_idx) {
 			/*
 			 * Don't sleep if someone wants a larger 'order'
-			 * allocation
+			 * allocation or has tigher zone constraints
 			 */
 			order = new_order;
+			classzone_idx = new_classzone_idx;
 		} else {
 			kswapd_try_to_sleep(pgdat, order);
 			order = pgdat->kswapd_max_order;
+			classzone_idx = pgdat->classzone_idx;
 		}
 
 		ret = try_to_freeze();
@@ -2571,7 +2619,7 @@ static int kswapd(void *p)
 		 */
 		if (!ret) {
 			trace_mm_vmscan_kswapd_wake(pgdat->node_id, order);
-			balance_pgdat(pgdat, order);
+			balance_pgdat(pgdat, order, classzone_idx);
 		}
 	}
 	return 0;
@@ -2580,7 +2628,7 @@ static int kswapd(void *p)
 /*
  * A zone is low on free memory, so wake its kswapd task to service it.
  */
-void wakeup_kswapd(struct zone *zone, int order)
+void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
 
@@ -2590,8 +2638,10 @@ void wakeup_kswapd(struct zone *zone, int order)
 	if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 		return;
 	pgdat = zone->zone_pgdat;
-	if (pgdat->kswapd_max_order < order)
+	if (pgdat->kswapd_max_order < order) {
 		pgdat->kswapd_max_order = order;
+		pgdat->classzone_idx = min(pgdat->classzone_idx, classzone_idx);
+	}
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 	if (zone_watermark_ok_safe(zone, order, low_wmark_pages(zone), 0, 0))