Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753376AbaBDAGy (ORCPT ); Mon, 3 Feb 2014 19:06:54 -0500 Received: from mail-pa0-f52.google.com ([209.85.220.52]:57733 "EHLO mail-pa0-f52.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751322AbaBDAGx (ORCPT ); Mon, 3 Feb 2014 19:06:53 -0500 Date: Mon, 3 Feb 2014 16:06:51 -0800 (PST) From: David Rientjes X-X-Sender: rientjes@chino.kir.corp.google.com To: Vlastimil Babka cc: Michal Hocko , Holger Kiehl , linux-kernel , Mel Gorman , linux-mm@kvack.org Subject: Re: Need help in bug in isolate_migratepages_range In-Reply-To: <52EFC93D.3030106@suse.cz> Message-ID: References: <20140203122052.GC2495@dhcp22.suse.cz> <20140203162036.GJ2495@dhcp22.suse.cz> <52EFC93D.3030106@suse.cz> User-Agent: Alpine 2.02 (DEB 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 3 Feb 2014, Vlastimil Babka wrote: > It seems to come from balloon_page_movable() and its test page_count(page) == > 1. > Hmm, I think it might be because compound_head() == NULL here. Holger, this looks like a race condition when allocating a compound page, did you only see it once or is it actually reproducible? I think this happens when a new compound page is allocated and PageBuddy is cleared before prep_compound_page() and then we see PageTail(p) set but p->first_page is not yet initialized. Is there any way to avoid memory barriers in compound_page()? -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/