mm: memcontrol: fix swap counter leak from offline cgroup

Commit 6769183166b3 removed the parameter of id from swap_cgroup_record()
and get the memcg id from mem_cgroup_id(folio_memcg(folio)).  However, the
caller of it may update a different memcg's counter instead of
folio_memcg(folio).

E.g.  in the caller of mem_cgroup_swapout(), @swap_memcg could be
different with @memcg and update the counter of @swap_memcg, but
swap_cgroup_record() records the wrong memcg's ID.  When it is uncharged
from __mem_cgroup_uncharge_swap(), the swap counter will leak since the
wrong recorded ID.

Fix it by bringing the parameter of id back.

Link: https://lkml.kernel.org/r/20250306023133.44838-1-songmuchun@bytedance.com
Fixes: 6769183166b3 ("mm/swap_cgroup: decouple swap cgroup recording and clearing")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
index b5ec038069dab52accaf54cf3d6abde49c1656cc..91cdf12190a0312025ead44ef4d1771a12461819 100644 (file)
--- a/include/linux/swap_cgroup.h
+++ b/include/linux/swap_cgroup.h
@@ -6,7 +6,7 @@
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP)
 
-extern void swap_cgroup_record(struct folio *folio, swp_entry_t ent);
+extern void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent);
 extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents);
 extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
 extern int swap_cgroup_swapon(int type, unsigned long max_pages);
@@ -15,7 +15,7 @@ extern void swap_cgroup_swapoff(int type);
 #else
 
 static inline
-void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
+void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent)
 {
 }
 

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4de6acb9b8ecbd3f95e8e1211a2c1f378559a8df..8f9b35f80e24efeea787e902765900a905d620be 100644 (file)
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4993,7 +4993,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
                mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
        mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-       swap_cgroup_record(folio, entry);
+       swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry);
 
        folio_unqueue_deferred_split(folio);
        folio->memcg_data = 0;
@@ -5055,7 +5055,7 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
                mem_cgroup_id_get_many(memcg, nr_pages - 1);
        mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
-       swap_cgroup_record(folio, entry);
+       swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
 
        return 0;
 }

diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index be39078f255be78135ffc073e51f7c4a7e95898e..1007c30f12e2c86f358919423955d4f58c1cea94 100644 (file)
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -58,9 +58,11 @@ static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map,
  * entries must not have been charged
  *
  * @folio: the folio that the swap entry belongs to
+ * @id: mem_cgroup ID to be recorded
  * @ent: the first swap entry to be recorded
  */
-void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
+void swap_cgroup_record(struct folio *folio, unsigned short id,
+                       swp_entry_t ent)
 {
        unsigned int nr_ents = folio_nr_pages(folio);
        struct swap_cgroup *map;
@@ -72,8 +74,7 @@ void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
        map = swap_cgroup_ctrl[swp_type(ent)].map;
 
        do {
-               old = __swap_cgroup_id_xchg(map, offset,
-                                           mem_cgroup_id(folio_memcg(folio)));
+               old = __swap_cgroup_id_xchg(map, offset, id);
                VM_BUG_ON(old);
        } while (++offset != end);
 }