mm: memcontrol: flush percpu vmevents before releasing memcg

commit bb65f89b7d3d305c14951f49860711fbcae70692 upstream.

Similar to vmstats, percpu caching of local vmevents leads to an
accumulation of errors on non-leaf levels.  This happens because some
leftovers may remain in percpu caches, so that they are never propagated
up by the cgroup tree and just disappear into nonexistence with on
releasing of the memory cgroup.

To fix this issue let's accumulate and propagate percpu vmevents values
before releasing the memory cgroup similar to what we're doing with
vmstats.

Since on cpu hotplug we do flush percpu vmstats anyway, we can iterate
only over online cpus.

Link: http://lkml.kernel.org/r/20190819202338.363363-4-guro@fb.com
Fixes: 42a300353577 ("mm: memcontrol: fix recursive statistics correctness & scalabilty")
Signed-off-by: Roman Gushchin <guro@fb.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 0f8a930b0517caa39c68dfb1c663f9f86a2f78a1..bb783c27ba215ac8765c40758bdb8f5f15e16848 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3185,6 +3185,25 @@ static void memcg_flush_percpu_vmstats(struct mem_cgroup *memcg)
        }
 }
 
+static void memcg_flush_percpu_vmevents(struct mem_cgroup *memcg)
+{
+       unsigned long events[NR_VM_EVENT_ITEMS];
+       struct mem_cgroup *mi;
+       int cpu, i;
+
+       for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+               events[i] = 0;
+
+       for_each_online_cpu(cpu)
+               for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+                       events[i] += raw_cpu_read(
+                               memcg->vmstats_percpu->events[i]);
+
+       for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
+               for (i = 0; i < NR_VM_EVENT_ITEMS; i++)
+                       atomic_long_add(events[i], &mi->vmevents[i]);
+}
+
 #ifdef CONFIG_MEMCG_KMEM
 static int memcg_online_kmem(struct mem_cgroup *memcg)
 {
@@ -4587,10 +4606,11 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
        int node;
 
        /*
-        * Flush percpu vmstats to guarantee the value correctness
+        * Flush percpu vmstats and vmevents to guarantee the value correctness
         * on parent's and all ancestor levels.
         */
        memcg_flush_percpu_vmstats(memcg);
+       memcg_flush_percpu_vmevents(memcg);
        for_each_node(node)
                free_mem_cgroup_per_node_info(memcg, node);
        free_percpu(memcg->vmstats_percpu);