[patch] mm: memcg: update the correct soft limit tree during migration

[Johannes Weiner]

end_migration() passes the old page instead of the new page to commit
the charge.  This page descriptor is not used for committing itself,
though, since we also pass the (correct) page_cgroup descriptor.  But
it's used to find the soft limit tree through the page's zone, so the
soft limit tree of the old page's zone is updated instead of that of
the new page's, which might get slightly out of date until the next
charge reaches the ratelimit point.

This glitch has been present since '5564e88 memcg: condense
page_cgroup-to-page lookup points'.

Reported-by: Hugh Dickins <hughd@xxxxxxxxxx>
Signed-off-by: Johannes Weiner <hannes@xxxxxxxxxxx>
---
 mm/memcontrol.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)

This fixes a bug that I introduced in 2.6.38.  It's benign enough (to
my knowledge) that we probably don't want this for stable.

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 602207b..7a292a5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3247,7 +3247,7 @@ int mem_cgroup_prepare_migration(struct page *page,
 		ctype = MEM_CGROUP_CHARGE_TYPE_CACHE;
 	else
 		ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM;
-	__mem_cgroup_commit_charge(memcg, page, 1, pc, ctype);
+	__mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype);
 	return ret;
 }
 
-- 
1.7.7.5

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/