mm/memcontrol.c: keep local VM counters in sync with the hierarchical ones

After commit 815744d75152 ("mm: memcontrol: don't batch updates of local
VM stats and events"), the local VM counter are not in sync with the
hierarchical ones.

Below is one example in a leaf memcg on my server (with 8 CPUs):

	inactive_file 3567570944
	total_inactive_file 3568029696

We find that the deviation is very great because the 'val' in
__mod_memcg_state() is in pages while the effective value in
memcg_stat_show() is in bytes.

So the maximum of this deviation between local VM stats and total VM
stats can be (32 * number_of_cpu * PAGE_SIZE), that may be an
unacceptably great value.

We should keep the local VM stats in sync with the total stats.  In
order to keep this behavior the same across counters, this patch updates
__mod_lruvec_state() and __count_memcg_events() as well.

Link: http://lkml.kernel.org/r/1562851979-10610-1-git-send-email-laoar.shao@gmail.com
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Yafang Shao <shaoyafang@didiglobal.com>
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 2496718..cdbb7a8 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -695,12 +695,15 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
        if (mem_cgroup_disabled())
                return;
 
-       __this_cpu_add(memcg->vmstats_local->stat[idx], val);
-
        x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]);
        if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
                struct mem_cgroup *mi;
 
+               /*
+                * Batch local counters to keep them in sync with
+                * the hierarchical ones.
+                */
+               __this_cpu_add(memcg->vmstats_local->stat[idx], x);
                for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
                        atomic_long_add(x, &mi->vmstats[idx]);
                x = 0;
@@ -749,13 +752,15 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
        /* Update memcg */
        __mod_memcg_state(memcg, idx, val);
 
-       /* Update lruvec */
-       __this_cpu_add(pn->lruvec_stat_local->count[idx], val);
-
        x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]);
        if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) {
                struct mem_cgroup_per_node *pi;
 
+               /*
+                * Batch local counters to keep them in sync with
+                * the hierarchical ones.
+                */
+               __this_cpu_add(pn->lruvec_stat_local->count[idx], x);
                for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id))
                        atomic_long_add(x, &pi->lruvec_stat[idx]);
                x = 0;
@@ -777,12 +782,15 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
        if (mem_cgroup_disabled())
                return;
 
-       __this_cpu_add(memcg->vmstats_local->events[idx], count);
-
        x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]);
        if (unlikely(x > MEMCG_CHARGE_BATCH)) {
                struct mem_cgroup *mi;
 
+               /*
+                * Batch local counters to keep them in sync with
+                * the hierarchical ones.
+                */
+               __this_cpu_add(memcg->vmstats_local->events[idx], x);
                for (mi = memcg; mi; mi = parent_mem_cgroup(mi))
                        atomic_long_add(x, &mi->vmevents[idx]);
                x = 0;