1 files changed, 192 insertions, 132 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index fe715daeb8bc..8ed1b775bdc9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -139,11 +139,23 @@ static bool global_reclaim(struct scan_control *sc)
 {
 	return !sc->target_mem_cgroup;
 }
+
+static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
+{
+	struct mem_cgroup *root = sc->target_mem_cgroup;
+	return !mem_cgroup_disabled() &&
+		mem_cgroup_soft_reclaim_eligible(root, root) != SKIP_TREE;
+}
 #else
 static bool global_reclaim(struct scan_control *sc)
 {
 	return true;
 }
+
+static bool mem_cgroup_should_soft_reclaim(struct scan_control *sc)
+{
+	return false;
+}
 #endif
 
 unsigned long zone_reclaimable_pages(struct zone *zone)
@@ -174,14 +186,31 @@ static unsigned long get_lru_size(struct lruvec *lruvec, enum lru_list lru)
 }
 
 /*
- * Add a shrinker callback to be called from the vm
+ * Add a shrinker callback to be called from the vm.
  */
-void register_shrinker(struct shrinker *shrinker)
+int register_shrinker(struct shrinker *shrinker)
 {
-	atomic_long_set(&shrinker->nr_in_batch, 0);
+	size_t size = sizeof(*shrinker->nr_deferred);
+
+	/*
+	 * If we only have one possible node in the system anyway, save
+	 * ourselves the trouble and disable NUMA aware behavior. This way we
+	 * will save memory and some small loop time later.
+	 */
+	if (nr_node_ids == 1)
+		shrinker->flags &= ~SHRINKER_NUMA_AWARE;
+
+	if (shrinker->flags & SHRINKER_NUMA_AWARE)
+		size *= nr_node_ids;
+
+	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
+	if (!shrinker->nr_deferred)
+		return -ENOMEM;
+
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
 	up_write(&shrinker_rwsem);
+	return 0;
 }
 EXPORT_SYMBOL(register_shrinker);
 
@@ -196,15 +225,102 @@ void unregister_shrinker(struct shrinker *shrinker)
 }
 EXPORT_SYMBOL(unregister_shrinker);
 
-static inline int do_shrinker_shrink(struct shrinker *shrinker,
-				     struct shrink_control *sc,
-				     unsigned long nr_to_scan)
-{
-	sc->nr_to_scan = nr_to_scan;
-	return (*shrinker->shrink)(shrinker, sc);
+#define SHRINK_BATCH 128
+
+static unsigned long
+shrink_slab_node(struct shrink_control *shrinkctl, struct shrinker *shrinker,
+		 unsigned long nr_pages_scanned, unsigned long lru_pages)
+{
+	unsigned long freed = 0;
+	unsigned long long delta;
+	long total_scan;
+	long max_pass;
+	long nr;
+	long new_nr;
+	int nid = shrinkctl->nid;
+	long batch_size = shrinker->batch ? shrinker->batch
+					  : SHRINK_BATCH;
+
+	max_pass = shrinker->count_objects(shrinker, shrinkctl);
+	if (max_pass == 0)
+		return 0;
+
+	/*
+	 * copy the current shrinker scan count into a local variable
+	 * and zero it so that other concurrent shrinker invocations
+	 * don't also do this scanning work.
+	 */
+	nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0);
+
+	total_scan = nr;
+	delta = (4 * nr_pages_scanned) / shrinker->seeks;
+	delta *= max_pass;
+	do_div(delta, lru_pages + 1);
+	total_scan += delta;
+	if (total_scan < 0) {
+		printk(KERN_ERR
+		"shrink_slab: %pF negative objects to delete nr=%ld\n",
+		       shrinker->scan_objects, total_scan);
+		total_scan = max_pass;
+	}
+
+	/*
+	 * We need to avoid excessive windup on filesystem shrinkers
+	 * due to large numbers of GFP_NOFS allocations causing the
+	 * shrinkers to return -1 all the time. This results in a large
+	 * nr being built up so when a shrink that can do some work
+	 * comes along it empties the entire cache due to nr >>>
+	 * max_pass.  This is bad for sustaining a working set in
+	 * memory.
+	 *
+	 * Hence only allow the shrinker to scan the entire cache when
+	 * a large delta change is calculated directly.
+	 */
+	if (delta < max_pass / 4)
+		total_scan = min(total_scan, max_pass / 2);
+
+	/*
+	 * Avoid risking looping forever due to too large nr value:
+	 * never try to free more than twice the estimate number of
+	 * freeable entries.
+	 */
+	if (total_scan > max_pass * 2)
+		total_scan = max_pass * 2;
+
+	trace_mm_shrink_slab_start(shrinker, shrinkctl, nr,
+				nr_pages_scanned, lru_pages,
+				max_pass, delta, total_scan);
+
+	while (total_scan >= batch_size) {
+		unsigned long ret;
+
+		shrinkctl->nr_to_scan = batch_size;
+		ret = shrinker->scan_objects(shrinker, shrinkctl);
+		if (ret == SHRINK_STOP)
+			break;
+		freed += ret;
+
+		count_vm_events(SLABS_SCANNED, batch_size);
+		total_scan -= batch_size;
+
+		cond_resched();
+	}
+
+	/*
+	 * move the unused scan count back into the shrinker in a
+	 * manner that handles concurrent updates. If we exhausted the
+	 * scan, there is no need to do an update.
+	 */
+	if (total_scan > 0)
+		new_nr = atomic_long_add_return(total_scan,
+						&shrinker->nr_deferred[nid]);
+	else
+		new_nr = atomic_long_read(&shrinker->nr_deferred[nid]);
+
+	trace_mm_shrink_slab_end(shrinker, freed, nr, new_nr);
+	return freed;
 }
 
-#define SHRINK_BATCH 128
 /*
  * Call the shrink functions to age shrinkable caches
  *
@@ -224,115 +340,45 @@ static inline int do_shrinker_shrink(struct shrinker *shrinker,
  *
  * Returns the number of slab objects which we shrunk.
  */
-unsigned long shrink_slab(struct shrink_control *shrink,
+unsigned long shrink_slab(struct shrink_control *shrinkctl,
 			  unsigned long nr_pages_scanned,
 			  unsigned long lru_pages)
 {
 	struct shrinker *shrinker;
-	unsigned long ret = 0;
+	unsigned long freed = 0;
 
 	if (nr_pages_scanned == 0)
 		nr_pages_scanned = SWAP_CLUSTER_MAX;
 
 	if (!down_read_trylock(&shrinker_rwsem)) {
-		/* Assume we'll be able to shrink next time */
-		ret = 1;
+		/*
+		 * 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;
 		goto out;
 	}
 
 	list_for_each_entry(shrinker, &shrinker_list, list) {
-		unsigned long long delta;
-		long total_scan;
-		long max_pass;
-		int shrink_ret = 0;
-		long nr;
-		long new_nr;
-		long batch_size = shrinker->batch ? shrinker->batch
-						  : SHRINK_BATCH;
-
-		max_pass = do_shrinker_shrink(shrinker, shrink, 0);
-		if (max_pass <= 0)
-			continue;
-
-		/*
-		 * copy the current shrinker scan count into a local variable
-		 * and zero it so that other concurrent shrinker invocations
-		 * don't also do this scanning work.
-		 */
-		nr = atomic_long_xchg(&shrinker->nr_in_batch, 0);
-
-		total_scan = nr;
-		delta = (4 * nr_pages_scanned) / shrinker->seeks;
-		delta *= max_pass;
-		do_div(delta, lru_pages + 1);
-		total_scan += delta;
-		if (total_scan < 0) {
-			printk(KERN_ERR "shrink_slab: %pF negative objects to "
-			       "delete nr=%ld\n",
-			       shrinker->shrink, total_scan);
-			total_scan = max_pass;
-		}
-
-		/*
-		 * We need to avoid excessive windup on filesystem shrinkers
-		 * due to large numbers of GFP_NOFS allocations causing the
-		 * shrinkers to return -1 all the time. This results in a large
-		 * nr being built up so when a shrink that can do some work
-		 * comes along it empties the entire cache due to nr >>>
-		 * max_pass.  This is bad for sustaining a working set in
-		 * memory.
-		 *
-		 * Hence only allow the shrinker to scan the entire cache when
-		 * a large delta change is calculated directly.
-		 */
-		if (delta < max_pass / 4)
-			total_scan = min(total_scan, max_pass / 2);
-
-		/*
-		 * Avoid risking looping forever due to too large nr value:
-		 * never try to free more than twice the estimate number of
-		 * freeable entries.
-		 */
-		if (total_scan > max_pass * 2)
-			total_scan = max_pass * 2;
-
-		trace_mm_shrink_slab_start(shrinker, shrink, nr,
-					nr_pages_scanned, lru_pages,
-					max_pass, delta, total_scan);
-
-		while (total_scan >= batch_size) {
-			int nr_before;
+		for_each_node_mask(shrinkctl->nid, shrinkctl->nodes_to_scan) {
+			if (!node_online(shrinkctl->nid))
+				continue;
 
-			nr_before = do_shrinker_shrink(shrinker, shrink, 0);
-			shrink_ret = do_shrinker_shrink(shrinker, shrink,
-							batch_size);
-			if (shrink_ret == -1)
+			if (!(shrinker->flags & SHRINKER_NUMA_AWARE) &&
+			    (shrinkctl->nid != 0))
 				break;
-			if (shrink_ret < nr_before)
-				ret += nr_before - shrink_ret;
-			count_vm_events(SLABS_SCANNED, batch_size);
-			total_scan -= batch_size;
 
-			cond_resched();
-		}
+			freed += shrink_slab_node(shrinkctl, shrinker,
+				 nr_pages_scanned, lru_pages);
 
-		/*
-		 * move the unused scan count back into the shrinker in a
-		 * manner that handles concurrent updates. If we exhausted the
-		 * scan, there is no need to do an update.
-		 */
-		if (total_scan > 0)
-			new_nr = atomic_long_add_return(total_scan,
-					&shrinker->nr_in_batch);
-		else
-			new_nr = atomic_long_read(&shrinker->nr_in_batch);
-
-		trace_mm_shrink_slab_end(shrinker, shrink_ret, nr, new_nr);
+		}
 	}
 	up_read(&shrinker_rwsem);
 out:
 	cond_resched();
-	return ret;
+	return freed;
 }
 
 static inline int is_page_cache_freeable(struct page *page)
@@ -2130,9 +2176,11 @@ static inline bool should_continue_reclaim(struct zone *zone,
 	}
 }
 
-static void shrink_zone(struct zone *zone, struct scan_control *sc)
+static int
+__shrink_zone(struct zone *zone, struct scan_control *sc, bool soft_reclaim)
 {
 	unsigned long nr_reclaimed, nr_scanned;
+	int groups_scanned = 0;
 
 	do {
 		struct mem_cgroup *root = sc->target_mem_cgroup;
@@ -2140,15 +2188,17 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
 			.zone = zone,
 			.priority = sc->priority,
 		};
-		struct mem_cgroup *memcg;
+		struct mem_cgroup *memcg = NULL;
+		mem_cgroup_iter_filter filter = (soft_reclaim) ?
+			mem_cgroup_soft_reclaim_eligible : NULL;
 
 		nr_reclaimed = sc->nr_reclaimed;
 		nr_scanned = sc->nr_scanned;
 
-		memcg = mem_cgroup_iter(root, NULL, &reclaim);
-		do {
+		while ((memcg = mem_cgroup_iter_cond(root, memcg, &reclaim, filter))) {
 			struct lruvec *lruvec;
 
+			groups_scanned++;
 			lruvec = mem_cgroup_zone_lruvec(zone, memcg);
 
 			shrink_lruvec(lruvec, sc);
@@ -2168,8 +2218,7 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
 				mem_cgroup_iter_break(root, memcg);
 				break;
 			}
-			memcg = mem_cgroup_iter(root, memcg, &reclaim);
-		} while (memcg);
+		}
 
 		vmpressure(sc->gfp_mask, sc->target_mem_cgroup,
 			   sc->nr_scanned - nr_scanned,
@@ -2177,6 +2226,37 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc)
 
 	} while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed,
 					 sc->nr_scanned - nr_scanned, sc));
+
+	return groups_scanned;
+}
+
+
+static void shrink_zone(struct zone *zone, struct scan_control *sc)
+{
+	bool do_soft_reclaim = mem_cgroup_should_soft_reclaim(sc);
+	unsigned long nr_scanned = sc->nr_scanned;
+	int scanned_groups;
+
+	scanned_groups = __shrink_zone(zone, sc, do_soft_reclaim);
+	/*
+	 * memcg iterator might race with other reclaimer or start from
+	 * a incomplete tree walk so the tree walk in __shrink_zone
+	 * might have missed groups that are above the soft limit. Try
+	 * another loop to catch up with others. Do it just once to
+	 * prevent from reclaim latencies when other reclaimers always
+	 * preempt this one.
+	 */
+	if (do_soft_reclaim && !scanned_groups)
+		__shrink_zone(zone, sc, do_soft_reclaim);
+
+	/*
+	 * No group is over the soft limit or those that are do not have
+	 * pages in the zone we are reclaiming so we have to reclaim everybody
+	 */
+	if (do_soft_reclaim && (sc->nr_scanned == nr_scanned)) {
+		__shrink_zone(zone, sc, false);
+		return;
+	}
 }
 
 /* Returns true if compaction should go ahead for a high-order request */
@@ -2240,8 +2320,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 {
 	struct zoneref *z;
 	struct zone *zone;
-	unsigned long nr_soft_reclaimed;
-	unsigned long nr_soft_scanned;
 	bool aborted_reclaim = false;
 
 	/*
@@ -2281,18 +2359,6 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc)
 					continue;
 				}
 			}
-			/*
-			 * This steals pages from memory cgroups over softlimit
-			 * and returns the number of reclaimed pages and
-			 * scanned pages. This works for global memory pressure
-			 * and balancing, not for a memcg's limit.
-			 */
-			nr_soft_scanned = 0;
-			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-						sc->order, sc->gfp_mask,
-						&nr_soft_scanned);
-			sc->nr_reclaimed += nr_soft_reclaimed;
-			sc->nr_scanned += nr_soft_scanned;
 			/* need some check for avoid more shrink_zone() */
 		}
 
@@ -2368,12 +2434,16 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
 		 */
 		if (global_reclaim(sc)) {
 			unsigned long lru_pages = 0;
+
+			nodes_clear(shrink->nodes_to_scan);
 			for_each_zone_zonelist(zone, z, zonelist,
 					gfp_zone(sc->gfp_mask)) {
 				if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
 					continue;
 
 				lru_pages += zone_reclaimable_pages(zone);
+				node_set(zone_to_nid(zone),
+					 shrink->nodes_to_scan);
 			}
 
 			shrink_slab(shrink, sc->nr_scanned, lru_pages);
@@ -2829,6 +2899,8 @@ static bool kswapd_shrink_zone(struct zone *zone,
 		return true;
 
 	shrink_zone(zone, sc);
+	nodes_clear(shrink.nodes_to_scan);
+	node_set(zone_to_nid(zone), shrink.nodes_to_scan);
 
 	reclaim_state->reclaimed_slab = 0;
 	shrink_slab(&shrink, sc->nr_scanned, lru_pages);
@@ -2880,8 +2952,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 {
 	int i;
 	int end_zone = 0;	/* Inclusive.  0 = ZONE_DMA */
-	unsigned long nr_soft_reclaimed;
-	unsigned long nr_soft_scanned;
 	struct scan_control sc = {
 		.gfp_mask = GFP_KERNEL,
 		.priority = DEF_PRIORITY,
@@ -2996,15 +3066,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order,
 
 			sc.nr_scanned = 0;
 
-			nr_soft_scanned = 0;
-			/*
-			 * Call soft limit reclaim before calling shrink_zone.
-			 */
-			nr_soft_reclaimed = mem_cgroup_soft_limit_reclaim(zone,
-							order, sc.gfp_mask,
-							&nr_soft_scanned);
-			sc.nr_reclaimed += nr_soft_reclaimed;
-
 			/*
 			 * There should be no need to raise the scanning
 			 * priority if enough pages are already being scanned
@@ -3520,10 +3581,9 @@ static int __zone_reclaim(struct zone *zone, gfp_t gfp_mask, unsigned int order)
 		 * number of slab pages and shake the slab until it is reduced
 		 * by the same nr_pages that we used for reclaiming unmapped
 		 * pages.
-		 *
-		 * Note that shrink_slab will free memory on all zones and may
-		 * take a long time.
 		 */
+		nodes_clear(shrink.nodes_to_scan);
+		node_set(zone_to_nid(zone), shrink.nodes_to_scan);
 		for (;;) {
 			unsigned long lru_pages = zone_reclaimable_pages(zone);