mm: memcg/slab: rework non-root kmem_cache lifecycle management

Currently each charged slab page holds a reference to the cgroup to which
it's charged.  Kmem_caches are held by the memcg and are released all
together with the memory cgroup.  It means that none of kmem_caches are
released unless at least one reference to the memcg exists, which is very
far from optimal.

Let's rework it in a way that allows releasing individual kmem_caches as
soon as the cgroup is offline, the kmem_cache is empty and there are no
pending allocations.

To make it possible, let's introduce a new percpu refcounter for non-root
kmem caches.  The counter is initialized to the percpu mode, and is
switched to the atomic mode during kmem_cache deactivation.  The counter
is bumped for every charged page and also for every running allocation.
So the kmem_cache can't be released unless all allocations complete.

To shutdown non-active empty kmem_caches, let's reuse the work queue,
previously used for the kmem_cache deactivation.  Once the reference
counter reaches 0, let's schedule an asynchronous kmem_cache release.

* I used the following simple approach to test the performance
(stolen from another patchset by T. Harding):

    time find / -name fname-no-exist
    echo 2 > /proc/sys/vm/drop_caches
    repeat 10 times

Results:

        orig		patched

real	0m1.455s	real	0m1.355s
user	0m0.206s	user	0m0.219s
sys	0m0.855s	sys	0m0.807s

real	0m1.487s	real	0m1.699s
user	0m0.221s	user	0m0.256s
sys	0m0.806s	sys	0m0.948s

real	0m1.515s	real	0m1.505s
user	0m0.183s	user	0m0.215s
sys	0m0.876s	sys	0m0.858s

real	0m1.291s	real	0m1.380s
user	0m0.193s	user	0m0.198s
sys	0m0.843s	sys	0m0.786s

real	0m1.364s	real	0m1.374s
user	0m0.180s	user	0m0.182s
sys	0m0.868s	sys	0m0.806s

real	0m1.352s	real	0m1.312s
user	0m0.201s	user	0m0.212s
sys	0m0.820s	sys	0m0.761s

real	0m1.302s	real	0m1.349s
user	0m0.205s	user	0m0.203s
sys	0m0.803s	sys	0m0.792s

real	0m1.334s	real	0m1.301s
user	0m0.194s	user	0m0.201s
sys	0m0.806s	sys	0m0.779s

real	0m1.426s	real	0m1.434s
user	0m0.216s	user	0m0.181s
sys	0m0.824s	sys	0m0.864s

real	0m1.350s	real	0m1.295s
user	0m0.200s	user	0m0.190s
sys	0m0.842s	sys	0m0.811s

So it looks like the difference is not noticeable in this test.

[cai@lca.pw: fix an use-after-free in kmemcg_workfn()]
  Link: http://lkml.kernel.org/r/1560977573-10715-1-git-send-email-cai@lca.pw
Link: http://lkml.kernel.org/r/20190611231813.3148843-9-guro@fb.com
Signed-off-by: Roman Gushchin <guro@fb.com>
Signed-off-by: Qian Cai <cai@lca.pw>
Acked-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Waiman Long <longman@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Andrei Vagin <avagin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 12 insertions, 32 deletions

diff --git a/mm/slab.h b/mm/slab.h
index 46623a576a3c..5d2b8511e6fb 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -248,31 +248,6 @@ static inline const char *cache_name(struct kmem_cache *s)
 	return s->name;
 }
 
-/*
- * Note, we protect with RCU only the memcg_caches array, not per-memcg caches.
- * That said the caller must assure the memcg's cache won't go away by either
- * taking a css reference to the owner cgroup, or holding the slab_mutex.
- */
-static inline struct kmem_cache *
-cache_from_memcg_idx(struct kmem_cache *s, int idx)
-{
-	struct kmem_cache *cachep;
-	struct memcg_cache_array *arr;
-
-	rcu_read_lock();
-	arr = rcu_dereference(s->memcg_params.memcg_caches);
-
-	/*
-	 * Make sure we will access the up-to-date value. The code updating
-	 * memcg_caches issues a write barrier to match this (see
-	 * memcg_create_kmem_cache()).
-	 */
-	cachep = READ_ONCE(arr->entries[idx]);
-	rcu_read_unlock();
-
-	return cachep;
-}
-
 static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 {
 	if (is_root_cache(s))
@@ -284,14 +259,25 @@ static __always_inline int memcg_charge_slab(struct page *page,
 					     gfp_t gfp, int order,
 					     struct kmem_cache *s)
 {
+	int ret;
+
 	if (is_root_cache(s))
 		return 0;
-	return memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg);
+
+	ret = memcg_kmem_charge_memcg(page, gfp, order, s->memcg_params.memcg);
+	if (ret)
+		return ret;
+
+	percpu_ref_get_many(&s->memcg_params.refcnt, 1 << order);
+
+	return 0;
 }
 
 static __always_inline void memcg_uncharge_slab(struct page *page, int order,
 						struct kmem_cache *s)
 {
+	if (!is_root_cache(s))
+		percpu_ref_put_many(&s->memcg_params.refcnt, 1 << order);
 	memcg_kmem_uncharge(page, order);
 }
 
@@ -323,12 +309,6 @@ static inline const char *cache_name(struct kmem_cache *s)
 	return s->name;
 }
 
-static inline struct kmem_cache *
-cache_from_memcg_idx(struct kmem_cache *s, int idx)
-{
-	return NULL;
-}
-
 static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
 {
 	return s;