Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755023Ab1EDPi3 (ORCPT ); Wed, 4 May 2011 11:38:29 -0400 Received: from smtp1.linux-foundation.org ([140.211.169.13]:54255 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754986Ab1EDPi2 (ORCPT ); Wed, 4 May 2011 11:38:28 -0400 MIME-Version: 1.0 In-Reply-To: References: <20110504083559.GB25724@elte.hu> <20110504101932.GA3392@elte.hu> <20110504112746.GE8007@htj.dyndns.org> <20110504132022.GA17294@htj.dyndns.org> <20110504142532.GC17294@htj.dyndns.org> From: Linus Torvalds Date: Wed, 4 May 2011 08:37:33 -0700 Message-ID: Subject: Re: [block IO crash] Re: 2.6.39-rc5-git2 boot crashs To: Christoph Lameter Cc: Thomas Gleixner , Tejun Heo , Pekka Enberg , Ingo Molnar , Jens Axboe , Andrew Morton , werner , "H. Peter Anvin" , Linux Kernel Mailing List Content-Type: text/plain; charset=ISO-8859-1 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 626 Lines: 17 On Wed, May 4, 2011 at 8:28 AM, Christoph Lameter wrote: > > There are no memory barriers used. The barrier() here is a compiler hint > to not keep data across it. Go back and read my email, please. The lack of memory barriers is exactly what I worry about. Look at the initialization path. The "tid" thing is _not_ purely cpu-local. Linus -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/