From c69c3005c3b47974856ccb60f2d00e2037a4329e Mon Sep 17 00:00:00 2001 From: Glauber Costa Date: Fri, 9 Nov 2012 14:04:13 +1100 Subject: [PATCH] memcg: allow a memcg with kmem charges to be destructed Because the ultimate goal of the kmem tracking in memcg is to track slab pages as well, we can't guarantee that we'll always be able to point a page to a particular process, and migrate the charges along with it - since in the common case, a page will contain data belonging to multiple processes. Because of that, when we destroy a memcg, we only make sure the destruction will succeed by discounting the kmem charges from the user charges when we try to empty the cgroup. Signed-off-by: Glauber Costa Acked-by: Kamezawa Hiroyuki Reviewed-by: Michal Hocko Cc: Christoph Lameter Cc: David Rientjes Cc: Frederic Weisbecker Cc: Greg Thelen Cc: Johannes Weiner Cc: JoonSoo Kim Cc: Mel Gorman Cc: Pekka Enberg Cc: Rik van Riel Cc: Suleiman Souhlal Cc: Tejun Heo Signed-off-by: Andrew Morton --- mm/memcontrol.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2602324d9719..58a67f4aff03 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -545,6 +545,11 @@ static void disarm_kmem_keys(struct mem_cgroup *memcg) { if (memcg_kmem_is_active(memcg)) static_key_slow_dec(&memcg_kmem_enabled_key); + /* + * This check can't live in kmem destruction function, + * since the charges will outlive the cgroup + */ + WARN_ON(res_counter_read_u64(&memcg->kmem, RES_USAGE) != 0); } #else static void disarm_kmem_keys(struct mem_cgroup *memcg) @@ -3999,6 +4004,7 @@ static void mem_cgroup_force_empty_list(struct mem_cgroup *memcg, static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) { int node, zid; + u64 usage; do { /* This is for making all *used* pages to be on LRU. */ @@ -4019,13 +4025,20 @@ static void mem_cgroup_reparent_charges(struct mem_cgroup *memcg) cond_resched(); /* + * Kernel memory may not necessarily be trackable to a specific + * process. So they are not migrated, and therefore we can't + * expect their value to drop to 0 here. + * Having res filled up with kmem only is enough. + * * This is a safety check because mem_cgroup_force_empty_list * could have raced with mem_cgroup_replace_page_cache callers * so the lru seemed empty but the page could have been added * right after the check. RES_USAGE should be safe as we always * charge before adding to the LRU. */ - } while (res_counter_read_u64(&memcg->res, RES_USAGE) > 0); + usage = res_counter_read_u64(&memcg->res, RES_USAGE) - + res_counter_read_u64(&memcg->kmem, RES_USAGE); + } while (usage > 0); } /* -- 2.39.5