Merge "mm, vmscan: prevent kswapd sleeping prematurely due to mismatched classzone_idx"
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index ede13734..6eb61a4 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1201,7 +1201,11 @@
 
 		arch_refresh_nodedata(nid, pgdat);
 	} else {
-		/* Reset the nr_zones, order and classzone_idx before reuse */
+		/*
+		 * Reset the nr_zones, order and classzone_idx before reuse.
+		 * Note that kswapd will init kswapd_classzone_idx properly
+		 * when it starts in the near future.
+		 */
 		pgdat->nr_zones = 0;
 		pgdat->kswapd_order = 0;
 		pgdat->kswapd_classzone_idx = 0;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 05f8da8..f23133e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3144,14 +3144,36 @@
 	} while (memcg);
 }
 
-static bool zone_balanced(struct zone *zone, int order, int classzone_idx)
+/*
+ * Returns true if there is an eligible zone balanced for the request order
+ * and classzone_idx
+ */
+static bool pgdat_balanced(pg_data_t *pgdat, int order, int classzone_idx)
 {
-	unsigned long mark = high_wmark_pages(zone);
+	int i;
+	unsigned long mark = -1;
+	struct zone *zone;
 
-	if (!zone_watermark_ok_safe(zone, order, mark, classzone_idx))
-		return false;
+	for (i = 0; i <= classzone_idx; i++) {
+		zone = pgdat->node_zones + i;
 
-	return true;
+		if (!managed_zone(zone))
+			continue;
+
+		mark = high_wmark_pages(zone);
+		if (zone_watermark_ok_safe(zone, order, mark, classzone_idx))
+			return true;
+	}
+
+	/*
+	 * If a node has no populated zone within classzone_idx, it does not
+	 * need balancing by definition. This can happen if a zone-restricted
+	 * allocation tries to wake a remote kswapd.
+	 */
+	if (mark == -1)
+		return true;
+
+	return false;
 }
 
 /* Clear pgdat state for congested, dirty or under writeback. */
@@ -3170,8 +3192,6 @@
  */
 static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx)
 {
-	int i;
-
 	/*
 	 * The throttled processes are normally woken up in balance_pgdat() as
 	 * soon as allow_direct_reclaim() is true. But there is a potential
@@ -3192,16 +3212,9 @@
 	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
 		return true;
 
-	for (i = 0; i <= classzone_idx; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		if (!managed_zone(zone))
-			continue;
-
-		if (zone_balanced(zone, order, classzone_idx)) {
-			clear_pgdat_congested(pgdat);
-			return true;
-		}
+	if (pgdat_balanced(pgdat, order, classzone_idx)) {
+		clear_pgdat_congested(pgdat);
+		return true;
 	}
 
 	return false;
@@ -3307,23 +3320,12 @@
 		}
 
 		/*
-		 * Only reclaim if there are no eligible zones. Check from
-		 * high to low zone as allocations prefer higher zones.
-		 * Scanning from low to high zone would allow congestion to be
-		 * cleared during a very small window when a small low
-		 * zone was balanced even under extreme pressure when the
-		 * overall node may be congested. Note that sc.reclaim_idx
-		 * is not used as buffer_heads_over_limit may have adjusted
-		 * it.
+		 * Only reclaim if there are no eligible zones. Note that
+		 * sc.reclaim_idx is not used as buffer_heads_over_limit may
+		 * have adjusted it.
 		 */
-		for (i = classzone_idx; i >= 0; i--) {
-			zone = pgdat->node_zones + i;
-			if (!managed_zone(zone))
-				continue;
-
-			if (zone_balanced(zone, sc.order, classzone_idx))
-				goto out;
-		}
+		if (pgdat_balanced(pgdat, sc.order, classzone_idx))
+			goto out;
 
 		/*
 		 * Do some background aging of the anon list, to give
@@ -3390,6 +3392,22 @@
 	return sc.order;
 }
 
+/*
+ * pgdat->kswapd_classzone_idx is the highest zone index that a recent
+ * allocation request woke kswapd for. When kswapd has not woken recently,
+ * the value is MAX_NR_ZONES which is not a valid index. This compares a
+ * given classzone and returns it or the highest classzone index kswapd
+ * was recently woke for.
+ */
+static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
+					   enum zone_type classzone_idx)
+{
+	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
+		return classzone_idx;
+
+	return max(pgdat->kswapd_classzone_idx, classzone_idx);
+}
+
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
 				unsigned int classzone_idx)
 {
@@ -3431,7 +3449,7 @@
 		 * the previous request that slept prematurely.
 		 */
 		if (remaining) {
-			pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+			pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
 		}
 
@@ -3485,7 +3503,8 @@
  */
 static int kswapd(void *p)
 {
-	unsigned int alloc_order, reclaim_order, classzone_idx;
+	unsigned int alloc_order, reclaim_order;
+	unsigned int classzone_idx = MAX_NR_ZONES - 1;
 	pg_data_t *pgdat = (pg_data_t*)p;
 	struct task_struct *tsk = current;
 
@@ -3515,20 +3534,23 @@
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	pgdat->kswapd_order = alloc_order = reclaim_order = 0;
-	pgdat->kswapd_classzone_idx = classzone_idx = 0;
+	pgdat->kswapd_order = 0;
+	pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
 	for ( ; ; ) {
 		bool ret;
 
+		alloc_order = reclaim_order = pgdat->kswapd_order;
+		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
+
 kswapd_try_sleep:
 		kswapd_try_to_sleep(pgdat, alloc_order, reclaim_order,
 					classzone_idx);
 
 		/* Read the new order and classzone_idx */
 		alloc_order = reclaim_order = pgdat->kswapd_order;
-		classzone_idx = pgdat->kswapd_classzone_idx;
+		classzone_idx = kswapd_classzone_idx(pgdat, 0);
 		pgdat->kswapd_order = 0;
-		pgdat->kswapd_classzone_idx = 0;
+		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3554,9 +3576,6 @@
 		reclaim_order = balance_pgdat(pgdat, alloc_order, classzone_idx);
 		if (reclaim_order < alloc_order)
 			goto kswapd_try_sleep;
-
-		alloc_order = reclaim_order = pgdat->kswapd_order;
-		classzone_idx = pgdat->kswapd_classzone_idx;
 	}
 
 	tsk->flags &= ~(PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD);
@@ -3572,7 +3591,6 @@
 void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
-	int z;
 
 	if (!managed_zone(zone))
 		return;
@@ -3580,7 +3598,8 @@
 	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
 		return;
 	pgdat = zone->zone_pgdat;
-	pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, classzone_idx);
+	pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
+							   classzone_idx);
 	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
@@ -3589,17 +3608,10 @@
 	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
 		return;
 
-	/* Only wake kswapd if all zones are unbalanced */
-	for (z = 0; z <= classzone_idx; z++) {
-		zone = pgdat->node_zones + z;
-		if (!managed_zone(zone))
-			continue;
+	if (pgdat_balanced(pgdat, order, classzone_idx))
+		return;
 
-		if (zone_balanced(zone, order, classzone_idx))
-			return;
-	}
-
-	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, zone_idx(zone), order);
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order);
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }