1 files changed, 47 insertions, 34 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bee53495a829..4390a8d5be41 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -442,16 +442,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
 		return 0;
 
-	if (!down_read_trylock(&shrinker_rwsem)) {
-		/*
-		 * If we would return 0, our callers would understand that we
-		 * have nothing else to shrink and give up trying. By returning
-		 * 1 we keep it going and assume we'll be able to shrink next
-		 * time.
-		 */
-		freed = 1;
+	if (!down_read_trylock(&shrinker_rwsem))
 		goto out;
-	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
 		struct shrink_control sc = {
@@ -1780,6 +1772,20 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		set_bit(PGDAT_WRITEBACK, &pgdat->flags);
 
 	/*
+	 * If dirty pages are scanned that are not queued for IO, it
+	 * implies that flushers are not doing their job. This can
+	 * happen when memory pressure pushes dirty pages to the end of
+	 * the LRU before the dirty limits are breached and the dirty
+	 * data has expired. It can also happen when the proportion of
+	 * dirty pages grows not through writes but through memory
+	 * pressure reclaiming all the clean cache. And in some cases,
+	 * the flushers simply cannot keep up with the allocation
+	 * rate. Nudge the flusher threads in case they are asleep.
+	 */
+	if (stat.nr_unqueued_dirty == nr_taken)
+		wakeup_flusher_threads(WB_REASON_VMSCAN);
+
+	/*
 	 * Legacy memcg will stall in page writeback so avoid forcibly
 	 * stalling here.
 	 */
@@ -1791,22 +1797,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec,
 		if (stat.nr_dirty && stat.nr_dirty == stat.nr_congested)
 			set_bit(PGDAT_CONGESTED, &pgdat->flags);
 
-		/*
-		 * If dirty pages are scanned that are not queued for IO, it
-		 * implies that flushers are not doing their job. This can
-		 * happen when memory pressure pushes dirty pages to the end of
-		 * the LRU before the dirty limits are breached and the dirty
-		 * data has expired. It can also happen when the proportion of
-		 * dirty pages grows not through writes but through memory
-		 * pressure reclaiming all the clean cache. And in some cases,
-		 * the flushers simply cannot keep up with the allocation
-		 * rate. Nudge the flusher threads in case they are asleep, but
-		 * also allow kswapd to start writing pages during reclaim.
-		 */
-		if (stat.nr_unqueued_dirty == nr_taken) {
-			wakeup_flusher_threads(WB_REASON_VMSCAN);
+		/* Allow kswapd to start writing pages during reclaim. */
+		if (stat.nr_unqueued_dirty == nr_taken)
 			set_bit(PGDAT_DIRTY, &pgdat->flags);
-		}
 
 		/*
 		 * If kswapd scans pages marked marked for immediate
@@ -3546,16 +3539,21 @@ kswapd_try_sleep:
 }
 
 /*
- * A zone is low on free memory, so wake its kswapd task to service it.
+ * A zone is low on free memory or too fragmented for high-order memory.  If
+ * kswapd should reclaim (direct reclaim is deferred), wake it up for the zone's
+ * pgdat.  It will wake up kcompactd after reclaiming memory.  If kswapd reclaim
+ * has failed or is not needed, still wake up kcompactd if only compaction is
+ * needed.
  */
-void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
+void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order,
+		   enum zone_type classzone_idx)
 {
 	pg_data_t *pgdat;
 
 	if (!managed_zone(zone))
 		return;
 
-	if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL))
+	if (!cpuset_zone_allowed(zone, gfp_flags))
 		return;
 	pgdat = zone->zone_pgdat;
 	pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat,
@@ -3564,14 +3562,23 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx)
 	if (!waitqueue_active(&pgdat->kswapd_wait))
 		return;
 
-	/* Hopeless node, leave it to direct reclaim */
-	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
-		return;
-
-	if (pgdat_balanced(pgdat, order, classzone_idx))
+	/* Hopeless node, leave it to direct reclaim if possible */
+	if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES ||
+	    pgdat_balanced(pgdat, order, classzone_idx)) {
+		/*
+		 * There may be plenty of free memory available, but it's too
+		 * fragmented for high-order allocations.  Wake up kcompactd
+		 * and rely on compaction_suitable() to determine if it's
+		 * needed.  If it fails, it will defer subsequent attempts to
+		 * ratelimit its work.
+		 */
+		if (!(gfp_flags & __GFP_DIRECT_RECLAIM))
+			wakeup_kcompactd(pgdat, order, classzone_idx);
 		return;
+	}
 
-	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order);
+	trace_mm_vmscan_wakeup_kswapd(pgdat->node_id, classzone_idx, order,
+				      gfp_flags);
 	wake_up_interruptible(&pgdat->kswapd_wait);
 }
 
@@ -3876,7 +3883,13 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
  */
 int page_evictable(struct page *page)
 {
-	return !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+	int ret;
+
+	/* Prevent address_space of inode and swap cache from being freed */
+	rcu_read_lock();
+	ret = !mapping_unevictable(page_mapping(page)) && !PageMlocked(page);
+	rcu_read_unlock();
+	return ret;
 }
 
 #ifdef CONFIG_SHMEM