From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755844AbZDYITi (ORCPT ); Sat, 25 Apr 2009 04:19:38 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751516AbZDYITW (ORCPT ); Sat, 25 Apr 2009 04:19:22 -0400 Received: from atrey.karlin.mff.cuni.cz ([195.113.26.193]:50157 "EHLO atrey.karlin.mff.cuni.cz" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751734AbZDYITV (ORCPT ); Sat, 25 Apr 2009 04:19:21 -0400 Date: Sat, 25 Apr 2009 10:19:14 +0200 From: Pavel Machek To: Mathieu Desnoyers Cc: akpm@linux-foundation.org, Ingo Molnar , linux-kernel@vger.kernel.org, mark.langsdorf@amd.com, arekm@maven.pl, "H. Peter Anvin" , Andi Kleen , Avi Kivity Subject: Re: [patch 2/2] x86 amd fix cmpxchg read acquire barrier Message-ID: <20090425081914.GD2428@ucw.cz> References: <20090422201852.092307236@polymtl.ca> <20090422202453.829846363@polymtl.ca> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20090422202453.829846363@polymtl.ca> User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed 2009-04-22 16:18:54, Mathieu Desnoyers wrote: > http://google-perftools.googlecode.com/svn-history/r48/trunk/src/base/atomicops-internals-x86.cc > > says > > " // Opteron Rev E has a bug in which on very rare occasions a locked > // instruction doesn't act as a read-acquire barrier if followed by a > // non-locked read-modify-write instruction. Rev F has this bug in > // pre-release versions, but not in versions released to customers, > // so we test only for Rev E, which is family 15, model 32..63 inclusive. Could we be more careful here and catch the F pre-release versions, too? Stepping should help there... -- (english) http://www.livejournal.com/~pavelmachek (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html