mm, memcg: assign memcg-aware shrinkers bitmap to memcg

Imagine a big node with many cpus, memory cgroups and containers.  Let
we have 200 containers, every container has 10 mounts, and 10 cgroups.
All container tasks don't touch foreign containers mounts.  If there is
intensive pages write, and global reclaim happens, a writing task has to
iterate over all memcgs to shrink slab, before it's able to go to
shrink_page_list().

Iteration over all the memcg slabs is very expensive: the task has to
visit 200 * 10 = 2000 shrinkers for every memcg, and since there are
2000 memcgs, the total calls are 2000 * 2000 = 4000000.

So, the shrinker makes 4 million do_shrink_slab() calls just to try to
isolate SWAP_CLUSTER_MAX pages in one of the actively writing memcg via
shrink_page_list().  I've observed a node spending almost 100% in
kernel, making useless iteration over already shrinked slab.

This patch adds bitmap of memcg-aware shrinkers to memcg.  The size of
the bitmap depends on bitmap_nr_ids, and during memcg life it's
maintained to be enough to fit bitmap_nr_ids shrinkers.  Every bit in
the map is related to corresponding shrinker id.

Next patches will maintain set bit only for really charged memcg.  This
will allow shrink_slab() to increase its performance in significant way.
See the last patch for the numbers.

[ktkhai@virtuozzo.com: v9]
  Link: http://lkml.kernel.org/r/153112549031.4097.3576147070498769979.stgit@localhost.localdomain
[ktkhai@virtuozzo.com: add comment to mem_cgroup_css_online()]
  Link: http://lkml.kernel.org/r/521f9e5f-c436-b388-fe83-4dc870bfb489@virtuozzo.com
Link: http://lkml.kernel.org/r/153063056619.1818.12550500883688681076.stgit@localhost.localdomain
Signed-off-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Tested-by: Shakeel Butt <shakeelb@google.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrey Ryabinin <aryabinin@virtuozzo.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Guenter Roeck <linux@roeck-us.net>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <jbacik@fb.com>
Cc: Li RongQing <lirongqing@baidu.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Matthias Kaehlcke <mka@chromium.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Philippe Ombredanne <pombredanne@nexb.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Sahitya Tummala <stummala@codeaurora.org>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 131 insertions, 1 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 313355dddf66..827c9e87ca08 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -320,6 +320,119 @@ EXPORT_SYMBOL(memcg_kmem_enabled_key);
 
 struct workqueue_struct *memcg_kmem_cache_wq;
 
+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;
+	int nid;
+
+	lockdep_assert_held(&memcg_shrinker_map_mutex);
+
+	for_each_node(nid) {
+		old = rcu_dereference_protected(
+			mem_cgroup_nodeinfo(memcg, nid)->shrinker_map, true);
+		/* Not yet online memcg */
+		if (!old)
+			return 0;
+
+		new = kvmalloc(sizeof(*new) + size, GFP_KERNEL);
+		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(memcg->nodeinfo[nid]->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 = mem_cgroup_nodeinfo(memcg, nid);
+		map = rcu_dereference_protected(pn->shrinker_map, true);
+		if (map)
+			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(sizeof(*map) + size, GFP_KERNEL);
+		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)
+			goto unlock;
+	}
+unlock:
+	if (!ret)
+		memcg_shrinker_map_size = size;
+	mutex_unlock(&memcg_shrinker_map_mutex);
+	return ret;
+}
+#else /* CONFIG_MEMCG_KMEM */
+static int memcg_alloc_shrinker_maps(struct mem_cgroup *memcg)
+{
+	return 0;
+}
+static void memcg_free_shrinker_maps(struct mem_cgroup *memcg) { }
 #endif /* CONFIG_MEMCG_KMEM */
 
 /**
@@ -4356,6 +4469,16 @@ 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()
+	 * 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)) {
+		mem_cgroup_id_remove(memcg);
+		return -ENOMEM;
+	}
+
 	/* Online state pins memcg ID, memcg ID pins CSS */
 	atomic_set(&memcg->id.ref, 1);
 	css_get(css);
@@ -4408,6 +4531,7 @@ 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);
 	memcg_free_kmem(memcg);
 	mem_cgroup_free(memcg);
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 5cb4f779ea4a..db0970ba340d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -183,8 +183,14 @@ static int prealloc_memcg_shrinker(struct shrinker *shrinker)
 	if (id < 0)
 		goto unlock;
 
-	if (id >= shrinker_nr_max)
+	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: