1 files changed, 129 insertions, 3 deletions

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d231af7cae06..bead5ae1e7e2 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -185,6 +185,132 @@ static LIST_HEAD(shrinker_list);
 static DECLARE_RWSEM(shrinker_rwsem);
 
 #ifdef CONFIG_MEMCG
+
+static int memcg_shrinker_map_size;
+static DEFINE_MUTEX(memcg_shrinker_map_mutex);
+
+static void free_shrinker_map_rcu(struct rcu_head *head)
+{
+	kvfree(container_of(head, struct memcg_shrinker_map, rcu));
+}
+
+static int expand_one_shrinker_map(struct mem_cgroup *memcg,
+				   int size, int old_size)
+{
+	struct memcg_shrinker_map *new, *old;
+	struct mem_cgroup_per_node *pn;
+	int nid;
+
+	lockdep_assert_held(&memcg_shrinker_map_mutex);
+
+	for_each_node(nid) {
+		pn = memcg->nodeinfo[nid];
+		old = rcu_dereference_protected(pn->shrinker_map, true);
+		/* Not yet online memcg */
+		if (!old)
+			return 0;
+
+		new = kvmalloc_node(sizeof(*new) + size, GFP_KERNEL, nid);
+		if (!new)
+			return -ENOMEM;
+
+		/* Set all old bits, clear all new bits */
+		memset(new->map, (int)0xff, old_size);
+		memset((void *)new->map + old_size, 0, size - old_size);
+
+		rcu_assign_pointer(pn->shrinker_map, new);
+		call_rcu(&old->rcu, free_shrinker_map_rcu);
+	}
+
+	return 0;
+}
+
+void free_shrinker_maps(struct mem_cgroup *memcg)
+{
+	struct mem_cgroup_per_node *pn;
+	struct memcg_shrinker_map *map;
+	int nid;
+
+	if (mem_cgroup_is_root(memcg))
+		return;
+
+	for_each_node(nid) {
+		pn = memcg->nodeinfo[nid];
+		map = rcu_dereference_protected(pn->shrinker_map, true);
+		kvfree(map);
+		rcu_assign_pointer(pn->shrinker_map, NULL);
+	}
+}
+
+int alloc_shrinker_maps(struct mem_cgroup *memcg)
+{
+	struct memcg_shrinker_map *map;
+	int nid, size, ret = 0;
+
+	if (mem_cgroup_is_root(memcg))
+		return 0;
+
+	mutex_lock(&memcg_shrinker_map_mutex);
+	size = memcg_shrinker_map_size;
+	for_each_node(nid) {
+		map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
+		if (!map) {
+			free_shrinker_maps(memcg);
+			ret = -ENOMEM;
+			break;
+		}
+		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
+	}
+	mutex_unlock(&memcg_shrinker_map_mutex);
+
+	return ret;
+}
+
+static int expand_shrinker_maps(int new_id)
+{
+	int size, old_size, ret = 0;
+	struct mem_cgroup *memcg;
+
+	size = DIV_ROUND_UP(new_id + 1, BITS_PER_LONG) * sizeof(unsigned long);
+	old_size = memcg_shrinker_map_size;
+	if (size <= old_size)
+		return 0;
+
+	mutex_lock(&memcg_shrinker_map_mutex);
+	if (!root_mem_cgroup)
+		goto unlock;
+
+	memcg = mem_cgroup_iter(NULL, NULL, NULL);
+	do {
+		if (mem_cgroup_is_root(memcg))
+			continue;
+		ret = expand_one_shrinker_map(memcg, size, old_size);
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
+			goto unlock;
+		}
+	} while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
+unlock:
+	if (!ret)
+		memcg_shrinker_map_size = size;
+	mutex_unlock(&memcg_shrinker_map_mutex);
+	return ret;
+}
+
+void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id)
+{
+	if (shrinker_id >= 0 && memcg && !mem_cgroup_is_root(memcg)) {
+		struct memcg_shrinker_map *map;
+
+		rcu_read_lock();
+		map = rcu_dereference(memcg->nodeinfo[nid]->shrinker_map);
+		/* Pairs with smp mb in shrink_slab() */
+		smp_mb__before_atomic();
+		set_bit(shrinker_id, map->map);
+		rcu_read_unlock();
+	}
+}
+
 /*
  * We allow subsystems to populate their shrinker-related
  * LRU lists before register_shrinker_prepared() is called
@@ -212,7 +338,7 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker)
 		goto unlock;
 
 	if (id >= shrinker_nr_max) {
-		if (memcg_expand_shrinker_maps(id)) {
+		if (expand_shrinker_maps(id)) {
 			idr_remove(&shrinker_idr, id);
 			goto unlock;
 		}
@@ -590,7 +716,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			 * 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():
+			 * set_shrinker_bit():
 			 *
 			 * list_lru_add()     shrink_slab_memcg()
 			 *   list_add_tail()    clear_bit()
@@ -602,7 +728,7 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid,
 			if (ret == SHRINK_EMPTY)
 				ret = 0;
 			else
-				memcg_set_shrinker_bit(memcg, nid, i);
+				set_shrinker_bit(memcg, nid, i);
 		}
 		freed += ret;