mm: vmscan: use shrinker_rwsem to protect shrinker_maps allocation

Since memcg_shrinker_map_size just can be changed under holding
shrinker_rwsem exclusively, the read side can be protected by holding read
lock, so it sounds superfluous to have a dedicated mutex.

Kirill Tkhai suggested use write lock since:

  * We want the assignment to shrinker_maps is visible for shrink_slab_memcg().
  * The rcu_dereference_protected() dereferrencing in shrink_slab_memcg(), but
    in case of we use READ lock in alloc_shrinker_maps(), the dereferrencing
    is not actually protected.
  * READ lock makes alloc_shrinker_info() racy against memory allocation fail.
    alloc_shrinker_info()->free_shrinker_info() may free memory right after
    shrink_slab_memcg() dereferenced it. You may say
    shrink_slab_memcg()->mem_cgroup_online() protects us from it? Yes, sure,
    but this is not the thing we want to remember in the future, since this
    spreads modularity.

And a test with heavy paging workload didn't show write lock makes things worse.

Link: https://lkml.kernel.org/r/20210311190845.9708-4-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Kirill Tkhai <ktkhai@virtuozzo.com>
Acked-by: Roman Gushchin <guro@fb.com>
Reviewed-by: Shakeel Butt <shakeelb@google.com>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/mm/vmscan.c b/mm/vmscan.c
index bead5ae1e7e297610fcd364b2049f9d2ca0cf392..d3fba55a0028c638613190c76a57e4e1b8e71c6e 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -187,7 +187,6 @@ static DECLARE_RWSEM(shrinker_rwsem);
 #ifdef CONFIG_MEMCG
 
 static int memcg_shrinker_map_size;
-static DEFINE_MUTEX(memcg_shrinker_map_mutex);
 
 static void free_shrinker_map_rcu(struct rcu_head *head)
 {
@@ -201,8 +200,6 @@ static int expand_one_shrinker_map(struct mem_cgroup *memcg,
        struct mem_cgroup_per_node *pn;
        int nid;
 
-       lockdep_assert_held(&memcg_shrinker_map_mutex);
-
        for_each_node(nid) {
                pn = memcg->nodeinfo[nid];
                old = rcu_dereference_protected(pn->shrinker_map, true);
@@ -250,7 +247,7 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg)
        if (mem_cgroup_is_root(memcg))
                return 0;
 
-       mutex_lock(&memcg_shrinker_map_mutex);
+       down_write(&shrinker_rwsem);
        size = memcg_shrinker_map_size;
        for_each_node(nid) {
                map = kvzalloc_node(sizeof(*map) + size, GFP_KERNEL, nid);
@@ -261,7 +258,7 @@ int alloc_shrinker_maps(struct mem_cgroup *memcg)
                }
                rcu_assign_pointer(memcg->nodeinfo[nid]->shrinker_map, map);
        }
-       mutex_unlock(&memcg_shrinker_map_mutex);
+       up_write(&shrinker_rwsem);
 
        return ret;
 }
@@ -276,9 +273,10 @@ static int expand_shrinker_maps(int new_id)
        if (size <= old_size)
                return 0;
 
-       mutex_lock(&memcg_shrinker_map_mutex);
        if (!root_mem_cgroup)
-               goto unlock;
+               goto out;
+
+       lockdep_assert_held(&shrinker_rwsem);
 
        memcg = mem_cgroup_iter(NULL, NULL, NULL);
        do {
@@ -287,13 +285,13 @@ static int expand_shrinker_maps(int new_id)
                ret = expand_one_shrinker_map(memcg, size, old_size);
                if (ret) {
                        mem_cgroup_iter_break(NULL, memcg);
-                       goto unlock;
+                       goto out;
                }
        } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL);
-unlock:
+out:
        if (!ret)
                memcg_shrinker_map_size = size;
-       mutex_unlock(&memcg_shrinker_map_mutex);
+
        return ret;
 }