From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751419AbaJFGik (ORCPT ); Mon, 6 Oct 2014 02:38:40 -0400 Received: from mx2.parallels.com ([199.115.105.18]:48089 "EHLO mx2.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750888AbaJFGii (ORCPT ); Mon, 6 Oct 2014 02:38:38 -0400 Date: Mon, 6 Oct 2014 10:38:29 +0400 From: Vladimir Davydov To: Michal Hocko CC: Johannes Weiner , , Greg Thelen , Dave Hansen , , Subject: Re: [patch 1/3] mm: memcontrol: lockless page counters Message-ID: <20141006063829.GB1162@esperanza> References: <1411573390-9601-1-git-send-email-hannes@cmpxchg.org> <1411573390-9601-2-git-send-email-hannes@cmpxchg.org> <20140926103104.GE29445@esperanza> <20141002120748.GA1359@cmpxchg.org> <20141003153623.GA1162@esperanza> <20141003154134.GG4816@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Disposition: inline In-Reply-To: <20141003154134.GG4816@dhcp22.suse.cz> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Fri, Oct 03, 2014 at 05:41:34PM +0200, Michal Hocko wrote: > On Fri 03-10-14 19:36:23, Vladimir Davydov wrote: > > On Thu, Oct 02, 2014 at 08:07:48AM -0400, Johannes Weiner wrote: > [...] > > > The barriers are implied in change-return atomics, which is why there > > > is an xchg. But it's clear that this needs to be documented. This?: > > > > With the comments it looks correct to me, but I wonder if we can always > > rely on implicit memory barriers issued by atomic ops. Are there any > > archs where it doesn't hold? > > xchg is explcitly mentioned in Documentation/memory-barriers.txt so it > is expected to be barrier on all archs. Besides that not all atomic ops > imply memory barriers. Only those that "modifies some state in memory > and returns information about the state" do. Thank you for the info, now it's clear to me. Thanks, Vladimir