1 files changed, 13 insertions, 136 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c100265dc393..64ada9e650a5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -215,7 +215,7 @@ enum res_type {
 #define MEMFILE_PRIVATE(x, val)	((x) << 16 | (val))
 #define MEMFILE_TYPE(val)	((val) >> 16 & 0xffff)
 #define MEMFILE_ATTR(val)	((val) & 0xffff)
-/* Used for OOM nofiier */
+/* Used for OOM notifier */
 #define OOM_CONTROL		(0)
 
 /*
@@ -400,130 +400,6 @@ DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key);
 EXPORT_SYMBOL(memcg_kmem_enabled_key);
 #endif
 
-static int memcg_shrinker_map_size;
-static DEFINE_MUTEX(memcg_shrinker_map_mutex);
-
-static void memcg_free_shrinker_map_rcu(struct rcu_head *head)
-{
-	kvfree(container_of(head, struct memcg_shrinker_map, rcu));
-}
-
-static int memcg_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, memcg_free_shrinker_map_rcu);
-	}
-
-	return 0;
-}
-
-static void memcg_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);
-	}
-}
-
-static int memcg_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) {
-			memcg_free_shrinker_maps(memcg);
-			ret = -ENOMEM;
-			break;
-		}
-		rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
-	}
-	mutex_unlock(&memcg_shrinker_map_mutex);
-
-	return ret;
-}
-
-int memcg_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;
-
-	for_each_mem_cgroup(memcg) {
-		if (mem_cgroup_is_root(memcg))
-			continue;
-		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
-		if (ret) {
-			mem_cgroup_iter_break(NULL, memcg);
-			goto unlock;
-		}
-	}
-unlock:
-	if (!ret)
-		memcg_shrinker_map_size = size;
-	mutex_unlock(&memcg_shrinker_map_mutex);
-	return ret;
-}
-
-void memcg_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();
-	}
-}
-
 /**
  * mem_cgroup_css_from_page - css of the memcg associated with a page
  * @page: page of interest
@@ -910,7 +786,7 @@ void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val)
  * __count_memcg_events - account VM events in a cgroup
  * @memcg: the memory cgroup
  * @idx: the event item
- * @count: the number of events that occured
+ * @count: the number of events that occurred
  */
 void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
 			  unsigned long count)
@@ -1028,7 +904,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	rcu_read_lock();
 	do {
 		/*
-		 * Page cache insertions can happen withou an
+		 * Page cache insertions can happen without an
 		 * actual mm context, e.g. during disk probing
 		 * on boot, loopback IO, acct() writes etc.
 		 */
@@ -1836,7 +1712,7 @@ static void mem_cgroup_unmark_under_oom(struct mem_cgroup *memcg)
 	struct mem_cgroup *iter;
 
 	/*
-	 * Be careful about under_oom underflows becase a child memcg
+	 * Be careful about under_oom underflows because a child memcg
 	 * could have been added after mem_cgroup_mark_under_oom.
 	 */
 	spin_lock(&memcg_oom_lock);
@@ -2008,7 +1884,7 @@ bool mem_cgroup_oom_synchronize(bool handle)
 		/*
 		 * There is no guarantee that an OOM-lock contender
 		 * sees the wakeups triggered by the OOM kill
-		 * uncharges.  Wake any sleepers explicitely.
+		 * uncharges.  Wake any sleepers explicitly.
 		 */
 		memcg_oom_recover(memcg);
 	}
@@ -4488,7 +4364,7 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
  * Foreign dirty flushing
  *
  * There's an inherent mismatch between memcg and writeback.  The former
- * trackes ownership per-page while the latter per-inode.  This was a
+ * tracks ownership per-page while the latter per-inode.  This was a
  * deliberate design decision because honoring per-page ownership in the
  * writeback path is complicated, may lead to higher CPU and IO overheads
  * and deemed unnecessary given that write-sharing an inode across
@@ -4503,9 +4379,9 @@ void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages,
  * triggering background writeback.  A will be slowed down without a way to
  * make writeback of the dirty pages happen.
  *
- * Conditions like the above can lead to a cgroup getting repatedly and
+ * Conditions like the above can lead to a cgroup getting repeatedly and
  * severely throttled after making some progress after each
- * dirty_expire_interval while the underyling IO device is almost
+ * dirty_expire_interval while the underlying IO device is almost
  * completely idle.
  *
  * Solving this problem completely requires matching the ownership tracking
@@ -5242,11 +5118,11 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
 
 	/*
-	 * A memcg must be visible for memcg_expand_shrinker_maps()
+	 * A memcg must be visible for expand_shrinker_info()
 	 * by the time the maps are allocated. So, we allocate maps
 	 * here, when for_each_mem_cgroup() can't skip it.
 	 */
-	if (memcg_alloc_shrinker_maps(memcg)) {
+	if (alloc_shrinker_info(memcg)) {
 		mem_cgroup_id_remove(memcg);
 		return -ENOMEM;
 	}
@@ -5278,6 +5154,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 	page_counter_set_low(&memcg->memory, 0);
 
 	memcg_offline_kmem(memcg);
+	reparent_shrinker_deferred(memcg);
 	wb_memcg_offline(memcg);
 
 	drain_all_stock(memcg);
@@ -5310,7 +5187,7 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 	vmpressure_cleanup(&memcg->vmpressure);
 	cancel_work_sync(&memcg->high_work);
 	mem_cgroup_remove_from_trees(memcg);
-	memcg_free_shrinker_maps(memcg);
+	free_shrinker_info(memcg);
 	memcg_free_kmem(memcg);
 	mem_cgroup_free(memcg);
 }
@@ -5897,7 +5774,7 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset)
 		return 0;
 
 	/*
-	 * We are now commited to this value whatever it is. Changes in this
+	 * We are now committed to this value whatever it is. Changes in this
 	 * tunable will only affect upcoming migrations, not the current one.
 	 * So we need to save it, and keep it going.
 	 */