mm: memcontrol: fix root_mem_cgroup charging

The below scenario can cause the page counters of the root_mem_cgroup to
be out of balance.

CPU0:                                   CPU1:

objcg = get_obj_cgroup_from_current()
obj_cgroup_charge_pages(objcg)
                                        memcg_reparent_objcgs()
                                            // reparent to root_mem_cgroup
                                            WRITE_ONCE(iter->memcg, parent)
    // memcg == root_mem_cgroup
    memcg = get_mem_cgroup_from_objcg(objcg)
    // do not charge to the root_mem_cgroup
    try_charge(memcg)

obj_cgroup_uncharge_pages(objcg)
    memcg = get_mem_cgroup_from_objcg(objcg)
    // uncharge from the root_mem_cgroup
    refill_stock(memcg)
        drain_stock(memcg)
            page_counter_uncharge(&memcg->memory)

get_obj_cgroup_from_current() never returns a root_mem_cgroup's objcg, so
we never explicitly charge the root_mem_cgroup.  And it's not going to
change.  It's all about a race when we got an obj_cgroup pointing at some
non-root memcg, but before we were able to charge it, the cgroup was gone,
objcg was reparented to the root and so we're skipping the charging.  Then
we store the objcg pointer and later use to uncharge the root_mem_cgroup.

This can cause the page counter to be less than the actual value.
Although we do not display the value (mem_cgroup_usage) so there shouldn't
be any actual problem, but there is a WARN_ON_ONCE in the
page_counter_cancel().  Who knows if it will trigger?  So it is better to
fix it.

Link: https://lkml.kernel.org/r/20210425075410.19255-1-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov.dev@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, 5 deletions

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index b913950b9f64..70690fdf53cc 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2568,8 +2568,8 @@ out:
 	css_put(&memcg->css);
 }
 
-static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
-		      unsigned int nr_pages)
+static int try_charge_memcg(struct mem_cgroup *memcg, gfp_t gfp_mask,
+			unsigned int nr_pages)
 {
 	unsigned int batch = max(MEMCG_CHARGE_BATCH, nr_pages);
 	int nr_retries = MAX_RECLAIM_RETRIES;
@@ -2581,8 +2581,6 @@ static int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
 	bool drained = false;
 	unsigned long pflags;
 
-	if (mem_cgroup_is_root(memcg))
-		return 0;
 retry:
 	if (consume_stock(memcg, nr_pages))
 		return 0;
@@ -2762,6 +2760,15 @@ done_restock:
 	return 0;
 }
 
+static inline int try_charge(struct mem_cgroup *memcg, gfp_t gfp_mask,
+			     unsigned int nr_pages)
+{
+	if (mem_cgroup_is_root(memcg))
+		return 0;
+
+	return try_charge_memcg(memcg, gfp_mask, nr_pages);
+}
+
 #if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MMU)
 static void cancel_charge(struct mem_cgroup *memcg, unsigned int nr_pages)
 {
@@ -2997,7 +3004,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp,
 
 	memcg = get_mem_cgroup_from_objcg(objcg);
 
-	ret = try_charge(memcg, gfp, nr_pages);
+	ret = try_charge_memcg(memcg, gfp, nr_pages);
 	if (ret)
 		goto out;