From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752780AbcLGInd (ORCPT ); Wed, 7 Dec 2016 03:43:33 -0500 Received: from mail-wj0-f196.google.com ([209.85.210.196]:34412 "EHLO mail-wj0-f196.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752418AbcLGIn3 (ORCPT ); Wed, 7 Dec 2016 03:43:29 -0500 Date: Wed, 7 Dec 2016 09:43:05 +0100 From: Michal Hocko To: Xishi Qiu Cc: Andrew Morton , Mel Gorman , Yaowei Bai , Christian Borntraeger , Linux MM , LKML , Yisheng Xie Subject: Re: [RFC PATCH v3] mm: use READ_ONCE in page_cpupid_xchg_last() Message-ID: <20161207084305.GA20350@dhcp22.suse.cz> References: <584523E4.9030600@huawei.com> <58461A0A.3070504@huawei.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <58461A0A.3070504@huawei.com> User-Agent: Mutt/1.6.0 (2016-04-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue 06-12-16 09:53:14, Xishi Qiu wrote: > A compiler could re-read "old_flags" from the memory location after reading > and calculation "flags" and passes a newer value into the cmpxchg making > the comparison succeed while it should actually fail. > > Signed-off-by: Xishi Qiu > Suggested-by: Christian Borntraeger > --- > mm/mmzone.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/mm/mmzone.c b/mm/mmzone.c > index 5652be8..e0b698e 100644 > --- a/mm/mmzone.c > +++ b/mm/mmzone.c > @@ -102,7 +102,7 @@ int page_cpupid_xchg_last(struct page *page, int cpupid) > int last_cpupid; > > do { > - old_flags = flags = page->flags; > + old_flags = flags = READ_ONCE(page->flags); > last_cpupid = page_cpupid_last(page); what prevents compiler from doing? old_flags = READ_ONCE(page->flags); flags = READ_ONCE(page->flags); Or this doesn't matter? > > flags &= ~(LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT); > -- > 1.8.3.1 > -- Michal Hocko SUSE Labs