mm/vmscan.c: iterate only over charged shrinkers during memcg shrink_slab()

Using the preparations made in previous patches, in case of memcg
shrink, we may avoid shrinkers, which are not set in memcg's shrinkers
bitmap.  To do that, we separate iterations over memcg-aware and
!memcg-aware shrinkers, and memcg-aware shrinkers are chosen via
for_each_set_bit() from the bitmap.  In case of big nodes, having many
isolated environments, this gives significant performance growth.  See
next patches for the details.

Note that the patch does not respect to empty memcg shrinkers, since we
never clear the bitmap bits after we set it once.  Their shrinkers will
be called again, with no shrinked objects as result.  This functionality
is provided by next patches.

[ktkhai@virtuozzo.com: v9]
  Link: http://lkml.kernel.org/r/153112558507.4097.12713813335683345488.stgit@localhost.localdomain
Link: http://lkml.kernel.org/r/153063066653.1818.976035462801487910.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>

mm/vmscan.c

@@ -364,6 +364,21 @@ int prealloc_shrinker(struct shrinker *shrinker)
 	if (!shrinker->nr_deferred)
 		return -ENOMEM;
 
+	/*
+	 * There is a window between prealloc_shrinker()
+	 * and register_shrinker_prepared(). We don't want
+	 * to clear bit of a shrinker in such the state
+	 * in shrink_slab_memcg(), since this will impose
+	 * restrictions on a code registering a shrinker
+	 * (they would have to guarantee, their LRU lists
+	 * are empty till shrinker is completely registered).
+	 * So, we differ the situation, when 1)a shrinker
+	 * is semi-registered (id is assigned, but it has
+	 * not yet linked to shrinker_list) and 2)shrinker
+	 * is not registered (id is not assigned).
+	 */
+	INIT_LIST_HEAD(&shrinker->list);
+
 	if (shrinker->flags & SHRINKER_MEMCG_AWARE) {
 		if (prealloc_memcg_shrinker(shrinker))
 			goto free_deferred;
@@ -543,6 +558,63 @@ 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)) {
+			clear_bit(i, map->map);
+			continue;
+		}
+
+		/* See comment in prealloc_shrinker() */
+		if (unlikely(list_empty(&shrinker->list)))
+			continue;
+
+		ret = do_shrink_slab(&sc, shrinker, priority);
+		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
@@ -572,8 +644,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid,
 	struct shrinker *shrinker;
 	unsigned long freed = 0;
 
-	if (memcg && (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)))
-		return 0;
+	if (memcg && !mem_cgroup_is_root(memcg))
+		return shrink_slab_memcg(gfp_mask, nid, memcg, priority);
 
 	if (!down_read_trylock(&shrinker_rwsem))
 		goto out;
@@ -585,13 +657,7 @@ 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))
+		if (!!memcg != !!(shrinker->flags & SHRINKER_MEMCG_AWARE))
 			continue;
 
 		if (!(shrinker->flags & SHRINKER_NUMA_AWARE))