From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758985AbZKZJff (ORCPT ); Thu, 26 Nov 2009 04:35:35 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754500AbZKZJfe (ORCPT ); Thu, 26 Nov 2009 04:35:34 -0500 Received: from bombadil.infradead.org ([18.85.46.34]:54981 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752960AbZKZJfd convert rfc822-to-8bit (ORCPT ); Thu, 26 Nov 2009 04:35:33 -0500 Subject: Re: [patch] sched: fix set_task_cpu() and provide an unlocked runqueue variant From: Peter Zijlstra To: Mike Galbraith Cc: Ingo Molnar , LKML In-Reply-To: <1259199068.6186.33.camel@marge.simson.net> References: <1258891781.14325.34.camel@marge.simson.net> <1259173672.4027.732.camel@laptop> <1259197270.6186.17.camel@marge.simson.net> <1259199068.6186.33.camel@marge.simson.net> Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: 8BIT Date: Thu, 26 Nov 2009 10:35:39 +0100 Message-ID: <1259228139.4273.6.camel@twins> Mime-Version: 1.0 X-Mailer: Evolution 2.28.1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2009-11-26 at 02:31 +0100, Mike Galbraith wrote: > On Thu, 2009-11-26 at 02:01 +0100, Mike Galbraith wrote: > > On Wed, 2009-11-25 at 19:27 +0100, Peter Zijlstra wrote: > > > > I've got to ask, what's that barrier for? > > > > It's a leftover from frustrated bug hunting. > > To be more specific, I put it there to ensure that min_vruntimes are > stable. min_vruntime should only ever be poked at when holding the respective rq->lock, even with a barrier a 64bit read on a 32bit machine can go all funny. > I figured that if try_to_wake_up() needs a barrier to look at > task->state, I had better do the same for the runqueues. Ah, ttwu() has that barrier for another reason. The wmb in ttwu() is to ensure the wakee sees the state of the waker at the time of waking. That is, its about ordering things like: A B my_cond = true; wake_process(my_friend); while (!my_cond) schedule(); So that you can actually observe my_cond being true once you wakeup (schedule acts as a mb() when it actually schedules).