slab: remove synchronous synchronize_sched() from memcg cache deactivation path

With kmem cgroup support enabled, kmem_caches can be created and
destroyed frequently and a great number of near empty kmem_caches can
accumulate if there are a lot of transient cgroups and the system is not
under memory pressure.  When memory reclaim starts under such
conditions, it can lead to consecutive deactivation and destruction of
many kmem_caches, easily hundreds of thousands on moderately large
systems, exposing scalability issues in the current slab management
code.  This is one of the patches to address the issue.

slub uses synchronize_sched() to deactivate a memcg cache.
synchronize_sched() is an expensive and slow operation and doesn't scale
when a huge number of caches are destroyed back-to-back.  While there
used to be a simple batching mechanism, the batching was too restricted
to be helpful.

This patch implements slab_deactivate_memcg_cache_rcu_sched() which slub
can use to schedule sched RCU callback instead of performing
synchronize_sched() synchronously while holding cgroup_mutex.  While
this adds online cpus, mems and slab_mutex operations, operating on
these locks back-to-back from the same kworker, which is what's gonna
happen when there are many to deactivate, isn't expensive at all and
this gets rid of the scalability problem completely.

Link: http://lkml.kernel.org/r/20170117235411.9408-9-tj@kernel.org
Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Jay Vana <jsvana@fb.com>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 70 insertions, 4 deletions

diff --git a/mm/slab.h b/mm/slab.h
index 7bff1ee513c2..65e7c3fcac72 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -307,6 +307,8 @@ static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 
 extern void slab_init_memcg_params(struct kmem_cache *);
 extern void memcg_link_cache(struct kmem_cache *s);
+extern void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
+				void (*deact_fn)(struct kmem_cache *));
 
 #else /* CONFIG_MEMCG && !CONFIG_SLOB */
 
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 59e41bb81575..c549296c7981 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -627,6 +627,66 @@ out_unlock:
 	put_online_cpus();
 }
 
+static void kmemcg_deactivate_workfn(struct work_struct *work)
+{
+	struct kmem_cache *s = container_of(work, struct kmem_cache,
+					    memcg_params.deact_work);
+
+	get_online_cpus();
+	get_online_mems();
+
+	mutex_lock(&slab_mutex);
+
+	s->memcg_params.deact_fn(s);
+
+	mutex_unlock(&slab_mutex);
+
+	put_online_mems();
+	put_online_cpus();
+
+	/* done, put the ref from slab_deactivate_memcg_cache_rcu_sched() */
+	css_put(&s->memcg_params.memcg->css);
+}
+
+static void kmemcg_deactivate_rcufn(struct rcu_head *head)
+{
+	struct kmem_cache *s = container_of(head, struct kmem_cache,
+					    memcg_params.deact_rcu_head);
+
+	/*
+	 * We need to grab blocking locks.  Bounce to ->deact_work.  The
+	 * work item shares the space with the RCU head and can't be
+	 * initialized eariler.
+	 */
+	INIT_WORK(&s->memcg_params.deact_work, kmemcg_deactivate_workfn);
+	schedule_work(&s->memcg_params.deact_work);
+}
+
+/**
+ * slab_deactivate_memcg_cache_rcu_sched - schedule deactivation after a
+ *					   sched RCU grace period
+ * @s: target kmem_cache
+ * @deact_fn: deactivation function to call
+ *
+ * Schedule @deact_fn to be invoked with online cpus, mems and slab_mutex
+ * held after a sched RCU grace period.  The slab is guaranteed to stay
+ * alive until @deact_fn is finished.  This is to be used from
+ * __kmemcg_cache_deactivate().
+ */
+void slab_deactivate_memcg_cache_rcu_sched(struct kmem_cache *s,
+					   void (*deact_fn)(struct kmem_cache *))
+{
+	if (WARN_ON_ONCE(is_root_cache(s)) ||
+	    WARN_ON_ONCE(s->memcg_params.deact_fn))
+		return;
+
+	/* pin memcg so that @s doesn't get destroyed in the middle */
+	css_get(&s->memcg_params.memcg->css);
+
+	s->memcg_params.deact_fn = deact_fn;
+	call_rcu_sched(&s->memcg_params.deact_rcu_head, kmemcg_deactivate_rcufn);
+}
+
 void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg)
 {
 	int idx;
diff --git a/mm/slub.c b/mm/slub.c
index 8a4591526f37..62d0b557a596 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -3957,6 +3957,12 @@ int __kmem_cache_shrink(struct kmem_cache *s)
 }
 
 #ifdef CONFIG_MEMCG
+static void kmemcg_cache_deact_after_rcu(struct kmem_cache *s)
+{
+	/* called with all the locks held after a sched RCU grace period */
+	__kmem_cache_shrink(s);
+}
+
 void __kmemcg_cache_deactivate(struct kmem_cache *s)
 {
 	/*
@@ -3968,11 +3974,9 @@ void __kmemcg_cache_deactivate(struct kmem_cache *s)
 
 	/*
 	 * s->cpu_partial is checked locklessly (see put_cpu_partial), so
-	 * we have to make sure the change is visible.
+	 * we have to make sure the change is visible before shrinking.
 	 */
-	synchronize_sched();
-
-	__kmem_cache_shrink(s);
+	slab_deactivate_memcg_cache_rcu_sched(s, kmemcg_cache_deact_after_rcu);
 }
 #endif