memcg: pin execution to current cpu while draining stock

Commit d1a05b6973c7 ("memcg do not try to drain per-cpu caches without
pages") added a drain_local_stock() call to a preemptible section.

The draining task looks up the cpu-local stock twice to set the
draining-flag, then to drain the stock and clear the flag again.  If the
task is migrated to a different CPU in between, noone will clear the
flag on the first stock and it will be forever undrainable.  Its charge
can not be recovered and the cgroup can not be deleted anymore.

Properly pin the task to the executing CPU while draining stocks.

Signed-off-by: Johannes Weiner <jweiner@redhat.com>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com
Acked-by: Michal Hocko <mhocko@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 930de943727117043c0274f35cbe6e70d5eb8160..0e40f020573261e5b1b597d5b67a5ba8f25f31d6 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2169,13 +2169,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
 
        /* Notify other cpus that system-wide "drain" is running */
        get_online_cpus();
-       /*
-        * Get a hint for avoiding draining charges on the current cpu,
-        * which must be exhausted by our charging.  It is not required that
-        * this be a precise check, so we use raw_smp_processor_id() instead of
-        * getcpu()/putcpu().
-        */
-       curcpu = raw_smp_processor_id();
+       curcpu = get_cpu();
        for_each_online_cpu(cpu) {
                struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
                struct mem_cgroup *mem;
@@ -2192,6 +2186,7 @@ static void drain_all_stock(struct mem_cgroup *root_mem, bool sync)
                                schedule_work_on(cpu, &stock->work);
                }
        }
+       put_cpu();
 
        if (!sync)
                goto out;