From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752781AbaBJRwu (ORCPT ); Mon, 10 Feb 2014 12:52:50 -0500 Received: from cdptpa-outbound-snat.email.rr.com ([107.14.166.225]:6944 "EHLO cdptpa-oedge-vip.email.rr.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1752279AbaBJRws (ORCPT ); Mon, 10 Feb 2014 12:52:48 -0500 Date: Mon, 10 Feb 2014 12:52:45 -0500 From: Steven Rostedt To: Nicholas Mc Guire Cc: linux-rt-users@vger.kernel.org, LKML , Sebastian Andrzej Siewior , Peter Zijlstra , Carsten Emde , Thomas Gleixner , Andreas Platschek Subject: Re: allow preemption in check_task_state Message-ID: <20140210125245.1afc834d@gandalf.local.home> In-Reply-To: <20140210171712.GA17517@opentech.at> References: <20140210153856.GD20017@opentech.at> <20140210111106.67438d1e@gandalf.local.home> <20140210171712.GA17517@opentech.at> X-Mailer: Claws Mail 3.9.3 (GTK+ 2.24.22; x86_64-pc-linux-gnu) MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-RR-Connecting-IP: 107.14.168.130:25 X-Cloudmark-Score: 0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 10 Feb 2014 18:17:12 +0100 Nicholas Mc Guire wrote: > > > > In rtmutex.c we have: > > > > pi_lock(&self->pi_lock); > > __set_current_state(self->saved_state); > > self->saved_state = TASK_RUNNING; > > pi_unlock(&self->pi_lock); > > > > As there is no wmb() here, it can be very possible that another CPU > > will see saved_state as TASK_RUNNING, and current state as > > TASK_RUNNING, and miss the update completely. > > > > I would not want to add a wmb() unless there is a real bug with the > > check state, as the above is in a very fast path and the check state is > > in a slower path. > > > maybe I'm missing/missunderstanding something here but > pi_unlock -> arch_spin_unlock is a full mb() > so once any task did an update of the state the loop should be catching > this update ? if the loop exits before the updat takes effect (pi_unlock) > would that be ncorrect ? Even if the spin locks were full memory barriers, it is still buggy. The fact that we set current_state to saved_state, and then saved_state to TASK_RUNNING without any memory barriers in between those two statements, means that the reader (even with a rmb()) can still see both as TASK_RUNNING. -- Steve