On Fri 13-01-12 16:41:31, Johannes Weiner wrote: > 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 the new page's, which might get slightly out of date until the next 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> Well spotted. Acked-by: Michal Hocko <mhocko@xxxxxxx> Thanks > --- > 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 > -- Michal Hocko SUSE Labs SUSE LINUX s.r.o. Lihovarska 1060/12 190 00 Praha 9 Czech Republic -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>