1 files changed, 201 insertions, 40 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index 03822f86f288..4375b1e9bd56 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -65,12 +65,6 @@ struct scan_control {
 	/* How many pages shrink_list() should reclaim */
 	unsigned long nr_to_reclaim;
 
-	/* This context's GFP mask */
-	gfp_t gfp_mask;
-
-	/* Allocation order */
-	int order;
-
 	/*
 	 * Nodemask of nodes allowed by the caller. If NULL, all nodes
 	 * are scanned.
@@ -83,12 +77,6 @@ struct scan_control {
 	 */
 	struct mem_cgroup *target_mem_cgroup;
 
-	/* Scan (total_size >> priority) pages at once */
-	int priority;
-
-	/* The highest zone to isolate pages for reclaim from */
-	enum zone_type reclaim_idx;
-
 	/* Writepage batching in laptop mode; RECLAIM_WRITE */
 	unsigned int may_writepage:1;
 
@@ -111,6 +99,18 @@ struct scan_control {
 	/* One of the zones is ready for compaction */
 	unsigned int compaction_ready:1;
 
+	/* Allocation order */
+	s8 order;
+
+	/* Scan (total_size >> priority) pages at once */
+	s8 priority;
+
+	/* The highest zone to isolate pages for reclaim from */
+	s8 reclaim_idx;
+
+	/* This context's GFP mask */
+	gfp_t gfp_mask;
+
 	/* Incremented by the number of inactive pages that were scanned */
 	unsigned long nr_scanned;
 
@@ -169,6 +169,70 @@ unsigned long vm_total_pages;
 static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
+#ifdef CONFIG_MEMCG_KMEM
+
+/*
+ * We allow subsystems to populate their shrinker-related
+ * LRU lists before register_shrinker_prepared() is called
+ * for the shrinker, since we don't want to impose
+ * restrictions on their internal registration order.
+ * In this case shrink_slab_memcg() may find corresponding
+ * bit is set in the shrinkers map.
+ *
+ * This value is used by the function to detect registering
+ * shrinkers and to skip do_shrink_slab() calls for them.
+ */
+#define SHRINKER_REGISTERING ((struct shrinker *)~0UL)
+
+static DEFINE_IDR(shrinker_idr);
+static int shrinker_nr_max;
+
+static int prealloc_memcg_shrinker(struct shrinker *shrinker)
+{
+	int id, ret = -ENOMEM;
+
+	down_write(&shrinker_rwsem);
+	/* This may call shrinker, so it must use down_read_trylock() */
+	id = idr_alloc(&shrinker_idr, SHRINKER_REGISTERING, 0, 0, GFP_KERNEL);
+	if (id < 0)
+		goto unlock;
+
+	if (id >= shrinker_nr_max) {
+		if (memcg_expand_shrinker_maps(id)) {
+			idr_remove(&shrinker_idr, id);
+			goto unlock;
+		}
+
+		shrinker_nr_max = id + 1;
+	}
+	shrinker->id = id;
+	ret = 0;
+unlock:
+	up_write(&shrinker_rwsem);
+	return ret;
+}
+
+static void unregister_memcg_shrinker(struct shrinker *shrinker)
+{
+	int id = shrinker->id;
+
+	BUG_ON(id < 0);
+
+	down_write(&shrinker_rwsem);
+	idr_remove(&shrinker_idr, id);
+	up_write(&shrinker_rwsem);
+}
+#else /* CONFIG_MEMCG_KMEM */
+static int prealloc_memcg_shrinker(struct shrinker *shrinker)
+{
+	return 0;
+}
+
+static void unregister_memcg_shrinker(struct shrinker *shrinker)
+{
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 #ifdef CONFIG_MEMCG
 static bool global_reclaim(struct scan_control *sc)
 {
@@ -313,11 +377,28 @@ int prealloc_shrinker(struct shrinker *shrinker)
 	shrinker->nr_deferred = kzalloc(size, GFP_KERNEL);
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
+
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
+		if (prealloc_memcg_shrinker(shrinker))
+			goto free_deferred;
+	}
+
 	return 0;
+
+free_deferred:
+	kfree(shrinker->nr_deferred);
+	shrinker->nr_deferred = NULL;
+	return -ENOMEM;
 }
 
 void free_prealloced_shrinker(struct shrinker *shrinker)
 {
+	if (!shrinker->nr_deferred)
+		return;
+
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
+		unregister_memcg_shrinker(shrinker);
+
 	kfree(shrinker->nr_deferred);
 	shrinker->nr_deferred = NULL;
 }
@@ -326,6 +407,9 @@ void register_shrinker_prepared(struct shrinker *shrinker)
 {
 	down_write(&shrinker_rwsem);
 	list_add_tail(&shrinker->list, &shrinker_list);
+#ifdef CONFIG_MEMCG_KMEM
+	idr_replace(&shrinker_idr, shrinker, shrinker->id);
+#endif
 	up_write(&shrinker_rwsem);
 }
 
@@ -347,6 +431,8 @@ void unregister_shrinker(struct shrinker *shrinker)
 {
 	if (!shrinker->nr_deferred)
 		return;
+	if (shrinker->flags & SHRINKER_MEMCG_AWARE)
+		unregister_memcg_shrinker(shrinker);
 	down_write(&shrinker_rwsem);
 	list_del(&shrinker->list);
 	up_write(&shrinker_rwsem);
@@ -371,9 +457,12 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 					  : SHRINK_BATCH;
 	long scanned = 0, next_deferred;
 
+	if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
+		nid = 0;
+
 	freeable = shrinker->count_objects(shrinker, shrinkctl);
-	if (freeable == 0)
-		return 0;
+	if (freeable == 0 || freeable == SHRINK_EMPTY)
+		return freeable;
 
 	/*
 	 * copy the current shrinker scan count into a local variable
@@ -474,6 +563,84 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
 	return freed;
 }
 
+#ifdef CONFIG_MEMCG_KMEM
+static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
+			struct mem_cgroup *memcg, int priority)
+{
+	struct memcg_shrinker_map *map;
+	unsigned long freed = 0;
+	int ret, i;
+
+	if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg))
+		return 0;
+
+	if (!down_read_trylock(&shrinker_rwsem))
+		return 0;
+
+	map = rcu_dereference_protected(memcg->nodeinfo[nid]->shrinker_map,
+					true);
+	if (unlikely(!map))
+		goto unlock;
+
+	for_each_set_bit(i, map->map, shrinker_nr_max) {
+		struct shrink_control sc = {
+			.gfp_mask = gfp_mask,
+			.nid = nid,
+			.memcg = memcg,
+		};
+		struct shrinker *shrinker;
+
+		shrinker = idr_find(&shrinker_idr, i);
+		if (unlikely(!shrinker || shrinker == SHRINKER_REGISTERING)) {
+			if (!shrinker)
+				clear_bit(i, map->map);
+			continue;
+		}
+
+		ret = do_shrink_slab(&sc, shrinker, priority);
+		if (ret == SHRINK_EMPTY) {
+			clear_bit(i, map->map);
+			/*
+			 * After the shrinker reported that it had no objects to
+			 * free, but before we cleared the corresponding bit in
+			 * the memcg shrinker map, a new object might have been
+			 * added. To make sure, we have the bit set in this
+			 * case, we invoke the shrinker one more time and reset
+			 * the bit if it reports that it is not empty anymore.
+			 * The memory barrier here pairs with the barrier in
+			 * memcg_set_shrinker_bit():
+			 *
+			 * list_lru_add()     shrink_slab_memcg()
+			 *   list_add_tail()    clear_bit()
+			 *   <MB>               <MB>
+			 *   set_bit()          do_shrink_slab()
+			 */
+			smp_mb__after_atomic();
+			ret = do_shrink_slab(&sc, shrinker, priority);
+			if (ret == SHRINK_EMPTY)
+				ret = 0;
+			else
+				memcg_set_shrinker_bit(memcg, nid, i);
+		}
+		freed += ret;
+
+		if (rwsem_is_contended(&shrinker_rwsem)) {
+			freed = freed ? : 1;
+			break;
+		}
+	}
+unlock:
+	up_read(&shrinker_rwsem);
+	return freed;
+}
+#else /* CONFIG_MEMCG_KMEM */
+static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
+			struct mem_cgroup *memcg, int priority)
+{
+	return 0;
+}
+#endif /* CONFIG_MEMCG_KMEM */
+
 /**
  * shrink_slab - shrink slab caches
  * @gfp_mask: allocation context
@@ -486,10 +653,8 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl,
  * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set,
  * unaware shrinkers will receive a node id of 0 instead.
  *
- * @memcg specifies the memory cgroup to target. If it is not NULL,
- * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan
- * objects from the memory cgroup specified. Otherwise, only unaware
- * shrinkers are called.
+ * @memcg specifies the memory cgroup to target. Unaware shrinkers
+ * are called only if it is the root cgroup.
  *
  * @priority is sc->priority, we take the number of objects and >> by priority
  * in order to get the scan target.
@@ -502,9 +667,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 {
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
+	int ret;
 
-	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
-		return 0;
+	if (!mem_cgroup_is_root(memcg))
+		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
 
 	if (!down_read_trylock(&shrinker_rwsem))
 		goto out;
@@ -516,19 +682,10 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 			.memcg = memcg,
 		};
 
-		/*
-		 * If kernel memory accounting is disabled, we ignore
-		 * SHRINKER_MEMCG_AWARE flag and call all shrinkers
-		 * passing NULL for memcg.
-		 */
-		if (memcg_kmem_enabled() &&
-		    !!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE))
-			continue;
-
-		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))
-			sc.nid = 0;
-
-		freed += do_shrink_slab(&sc, shrinker, priority);
+		ret = do_shrink_slab(&sc, shrinker, priority);
+		if (ret == SHRINK_EMPTY)
+			ret = 0;
+		freed += ret;
 		/*
 		 * Bail out if someone want to register a new shrinker to
 		 * prevent the regsitration from being stalled for long periods
@@ -554,6 +711,7 @@ void drop_slab_node(int nid)
 		struct mem_cgroup *memcg = NULL;
 
 		freed = 0;
+		memcg = mem_cgroup_iter(NULL, NULL, NULL);
 		do {
 			freed += shrink_slab(GFP_KERNEL, nid, memcg, 0);
 		} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
@@ -2573,9 +2731,8 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
 			node_lru_pages += lru_pages;
 
-			if (memcg)
-				shrink_slab(sc->gfp_mask, pgdat->node_id,
-					    memcg, sc->priority);
+			shrink_slab(sc->gfp_mask, pgdat->node_id,
+				    memcg, sc->priority);
 
 			/* Record the group's reclaim efficiency */
 			vmpressure(sc->gfp_mask, memcg, false,
@@ -2599,10 +2756,6 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			}
 		} while ((memcg = mem_cgroup_iter(root, memcg, &reclaim)));
 
-		if (global_reclaim(sc))
-			shrink_slab(sc->gfp_mask, pgdat->node_id, NULL,
-				    sc->priority);
-
 		if (reclaim_state) {
 			sc->nr_reclaimed += reclaim_state->reclaimed_slab;
 			reclaim_state->reclaimed_slab = 0;
@@ -3064,6 +3217,14 @@ unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 	};
 
 	/*
+	 * scan_control uses s8 fields for order, priority, and reclaim_idx.
+	 * Confirm they are large enough for max values.
+	 */
+	BUILD_BUG_ON(MAX_ORDER > S8_MAX);
+	BUILD_BUG_ON(DEF_PRIORITY > S8_MAX);
+	BUILD_BUG_ON(MAX_NR_ZONES > S8_MAX);
+
+	/*
 	 * Do not enter reclaim if fatal signal was delivered while throttled.
 	 * 1 is returned so that the page allocator does not OOM kill at this
 	 * point.