1 files changed, 34 insertions, 19 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 7fde5f904c8d..10feb872d9a4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2775,6 +2775,14 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			unsigned long reclaimed;
 			unsigned long scanned;
 
+			/*
+			 * This loop can become CPU-bound when target memcgs
+			 * aren't eligible for reclaim - either because they
+			 * don't have any reclaimable pages, or because their
+			 * memory is explicitly protected. Avoid soft lockups.
+			 */
+			cond_resched();
+
 			switch (mem_cgroup_protected(root, memcg)) {
 			case MEMCG_PROT_MIN:
 				/*
@@ -3160,8 +3168,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat)
 
 	/* kswapd must be awake if processes are being throttled */
 	if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) {
-		pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx,
-						(enum zone_type)ZONE_NORMAL);
+		if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL)
+			WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL);
+
 		wake_up_interruptible(&pgdat->kswapd_wait);
 	}
 
@@ -3793,9 +3802,9 @@ out:
 static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat,
 					   enum zone_type prev_classzone_idx)
 {
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		return prev_classzone_idx;
-	return pgdat->kswapd_classzone_idx;
+	enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx;
 }
 
 static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order,
@@ -3839,8 +3848,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o
 		 * the previous request that slept prematurely.
 		 */
 		if (remaining) {
-			pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-			pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order);
+			WRITE_ONCE(pgdat->kswapd_classzone_idx,
+				   kswapd_classzone_idx(pgdat, classzone_idx));
+
+			if (READ_ONCE(pgdat->kswapd_order) < reclaim_order)
+				WRITE_ONCE(pgdat->kswapd_order, reclaim_order);
 		}
 
 		finish_wait(&pgdat->kswapd_wait, &wait);
@@ -3917,12 +3929,12 @@ static int kswapd(void *p)
 	tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD;
 	set_freezable();
 
-	pgdat->kswapd_order = 0;
-	pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+	WRITE_ONCE(pgdat->kswapd_order, 0);
+	WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 	for ( ; ; ) {
 		bool ret;
 
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
 
 kswapd_try_sleep:
@@ -3930,10 +3942,10 @@ kswapd_try_sleep:
 					classzone_idx);
 
 		/* Read the new order and classzone_idx */
-		alloc_order = reclaim_order = pgdat->kswapd_order;
+		alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order);
 		classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx);
-		pgdat->kswapd_order = 0;
-		pgdat->kswapd_classzone_idx = MAX_NR_ZONES;
+		WRITE_ONCE(pgdat->kswapd_order, 0);
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES);
 
 		ret = try_to_freeze();
 		if (kthread_should_stop())
@@ -3977,20 +3989,23 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
 		   enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
+	enum zone_type curr_idx;
 
 	if (!managed_zone(zone))
 		return;
 
 	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
+
 	pgdat = zone->zone_pgdat;
+	curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx);
+
+	if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx)
+		WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx);
+
+	if (READ_ONCE(pgdat->kswapd_order) < order)
+		WRITE_ONCE(pgdat->kswapd_order, order);
 
-	if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES)
-		pgdat->kswapd_classzone_idx = classzone_idx;
-	else
-		pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx,
-						  classzone_idx);
-	pgdat->kswapd_order = max(pgdat->kswapd_order, order);
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;