From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754620Ab2APMmt (ORCPT ); Mon, 16 Jan 2012 07:42:49 -0500 Received: from static.213.204.9.176.clients.your-server.de ([176.9.204.213]:40800 "EHLO shutemov.name" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754470Ab2APMms convert rfc822-to-8bit (ORCPT ); Mon, 16 Jan 2012 07:42:48 -0500 Date: Mon, 16 Jan 2012 14:43:08 +0200 From: "Kirill A. Shutemov" To: Johannes Weiner Cc: Andrew Morton , Hugh Dickins , KAMEZAWA Hiroyuki , 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: <20120116124308.GA25981@shutemov.name> References: <1326469291-5642-1-git-send-email-hannes@cmpxchg.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: 8BIT In-Reply-To: <1326469291-5642-1-git-send-email-hannes@cmpxchg.org> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Jan 13, 2012 at 04:41:31PM +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 the new page's, which might get slightly out of date until the next 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 Acked-by: Kirill A. Shutemov -- Kirill A. Shutemov