From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754945Ab0EDHEr (ORCPT ); Tue, 4 May 2010 03:04:47 -0400 Received: from hera.kernel.org ([140.211.167.34]:46066 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751217Ab0EDHEq (ORCPT ); Tue, 4 May 2010 03:04:46 -0400 Message-ID: <4BDFC6C0.7020009@kernel.org> Date: Tue, 04 May 2010 09:03:28 +0200 From: Tejun Heo User-Agent: Mozilla/5.0 (X11; U; Linux i686 (x86_64); en-US; rv:1.9.1.9) Gecko/20100317 Thunderbird/3.0.4 MIME-Version: 1.0 To: Peter Zijlstra CC: mingo@elte.hu, linux-kernel@vger.kernel.org, x86@kernel.org, oleg@redhat.com, rusty@rustcorp.com.au, sivanich@sgi.com, heiko.carstens@de.ibm.com, dipankar@in.ibm.com, josh@freedesktop.org, paulmck@linux.vnet.ibm.com, akpm@linux-foundation.org, arjan@linux.intel.com, torvalds@linux-foundation.org Subject: Re: [PATCH 1/4] cpu_stop: implement stop_cpu[s]() References: <1271952554-22368-1-git-send-email-tj@kernel.org> <1271952554-22368-2-git-send-email-tj@kernel.org> <1272893189.5605.119.camel@twins> <4BDFC06B.4020805@kernel.org> In-Reply-To: <4BDFC06B.4020805@kernel.org> X-Enigmail-Version: 1.0.1 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.2.3 (hera.kernel.org [127.0.0.1]); Tue, 04 May 2010 07:03:30 +0000 (UTC) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 05/04/2010 08:36 AM, Tejun Heo wrote: > On 05/03/2010 03:26 PM, Peter Zijlstra wrote: >> On Thu, 2010-04-22 at 18:09 +0200, Tejun Heo wrote: >>> +static int cpu_stopper_thread(void *data) >>> +{ >>> + struct cpu_stopper *stopper = data; >> >> BUG_ON(stopper != __get_cpu_var(cpu_stopper)); ? > > Added. Now that I think more about it, there's a subtle race condition with the above BUG_ON(). Stoppers are prepared by CPU_UP_PREPARE and started by CPU_ONLINE but brought down by CPU_DEAD. IOW, they're allowed to run detached from their designated CPUs between CPU_DYING and CPU_DEAD (the reponsibility of guaranteeing target cpus's onliness is on the callers). So, the above BUG_ON() might trigger spuriously if a cpu goes down after brought online before its cpu_stopper had a chance to pass through the BUG_ON() test. Thanks. -- tejun