From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758027AbYEHNkB (ORCPT ); Thu, 8 May 2008 09:40:01 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752925AbYEHNjx (ORCPT ); Thu, 8 May 2008 09:39:53 -0400 Received: from one.firstfloor.org ([213.235.205.2]:50225 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752117AbYEHNjw (ORCPT ); Thu, 8 May 2008 09:39:52 -0400 Message-ID: <482302A3.3010405@firstfloor.org> Date: Thu, 08 May 2008 15:39:47 +0200 From: Andi Kleen User-Agent: Thunderbird 1.5.0.12 (X11/20060911) MIME-Version: 1.0 To: Rene Herman CC: Linus Torvalds , "H. Peter Anvin" , Thomas Gleixner , Adrian Bunk , Yinghai Lu , Ingo Molnar , Linux Kernel , akpm@linux-foundation.org, Pavel Machek Subject: Re: [PATCH] x86: introduce a new Linux defined feature flag for PAT support References: <48210A71.1060409@keyaccess.nl> <86802c440805061939q39ff5500h3c9e229ecbc6b2e6@mail.gmail.com> <20080507124650.GD29935@cs181133002.pp.htv.fi> <48221AE3.6020602@keyaccess.nl> <482233F0.7040000@zytor.com> <48224318.8020209@keyaccess.nl> <48224361.5080102@zytor.com> <48224507.8010102@keyaccess.nl> <48224930.9030901@keyaccess.nl> <48225DEC.2030502@keyaccess.nl> <878wylayiw.fsf@basil.nowhere.org> <4822F4A1.2030602@keyaccess.nl> In-Reply-To: <4822F4A1.2030602@keyaccess.nl> Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Rene Herman wrote: > On 08-05-08 12:19, Andi Kleen wrote: > >>> Use a new Linux defined X86_FEATURE_PAT_GOOD feature flag to >> >> Better would be PAT_TESTED or PAT_RANDOMLY_APPROVED. Most of these >> CPUs without PAT_GOOD have actually perfectly good PAT, as Windows >> proves every day. >> >> The main flaw in all of this of course is that there is no procedure >> to test CPUs which do not have the flag set yet. > > Quite. And hiding the fact that the CPU _should_ have perfectly good > PAT doesn't help any at all. The discussion turned into a mini-flame > war enough that now noone would even consider backing down, but this > current PAT setup just sucks plain and simple. For old CPUs it is actually ok (after all they worked for years without PAT), I just don't like it for new CPUs. It's a bad idea there and in the x86 world it is a reasonable expectation that CPU features generally work. That said I am not aware of that many PAT erratas even on old CPUs. There are a few, but they are known and well understood and could well be black listed. -Andi