Re: [patch] mm: memcg: update the correct soft limit tree duringmigration

[Michal Hocko]

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 the new page's, which might get slightly out of date until the next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 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/