From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751740Ab2APFuU (ORCPT ); Mon, 16 Jan 2012 00:50:20 -0500 Received: from fgwmail5.fujitsu.co.jp ([192.51.44.35]:58526 "EHLO fgwmail5.fujitsu.co.jp" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750715Ab2APFuS (ORCPT ); Mon, 16 Jan 2012 00:50:18 -0500 X-SecurityPolicyCheck-FJ: OK by FujitsuOutboundMailChecker v1.3.1 Date: Mon, 16 Jan 2012 14:48:37 +0900 From: KAMEZAWA Hiroyuki To: Johannes Weiner Cc: Andrew Morton , Hugh Dickins , Michal Hocko , linux-mm@kvack.org, linux-kernel@vger.kernel.org Subject: Re: [patch] mm: memcg: update the correct soft limit tree during migration Message-Id: <20120116144837.eaedf4d3.kamezawa.hiroyu@jp.fujitsu.com> In-Reply-To: <1326469291-5642-1-git-send-email-hannes@cmpxchg.org> References: <1326469291-5642-1-git-send-email-hannes@cmpxchg.org> Organization: FUJITSU Co. LTD. X-Mailer: Sylpheed 3.1.1 (GTK+ 2.10.14; i686-pc-mingw32) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, 13 Jan 2012 16:41:31 +0100 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 the new page's, which might get slightly out of date until the next 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 > Signed-off-by: Johannes Weiner > --- > 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; > } > Nice Catch. Acked-by: KAMEZAWA Hiroyuki