From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932248AbWFUQhp (ORCPT ); Wed, 21 Jun 2006 12:37:45 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932249AbWFUQhp (ORCPT ); Wed, 21 Jun 2006 12:37:45 -0400 Received: from ns.suse.de ([195.135.220.2]:13716 "EHLO mx1.suse.de") by vger.kernel.org with ESMTP id S932248AbWFUQho (ORCPT ); Wed, 21 Jun 2006 12:37:44 -0400 From: Andi Kleen To: Dave Olson Subject: Re: [discuss] Re: [RFC] Whitelist chipsets supporting MSI and check Hyper-transport capabilitiesKJ Date: Wed, 21 Jun 2006 18:37:30 +0200 User-Agent: KMail/1.9.3 Cc: Allen Martin , discuss@x86-64.org, Brice Goglin , linux-kernel@vger.kernel.org, Greg Lindahl References: In-Reply-To: MIME-Version: 1.0 Content-Disposition: inline Message-Id: <200606211837.30056.ak@suse.de> Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org On Wednesday 21 June 2006 18:21, Dave Olson wrote: > On Wed, 21 Jun 2006, Andi Kleen wrote: > > | "Allen Martin" writes: > | > | > > > | > > NForce4 PCI Express is an unknown - we'll see how that works. > | > > > | > > | > MSI is not officially supported on nForce4 and hasn't been fully tested. > | > | Ok thanks for the information. We should definitely disable it by default > | then, maybe with an boot option so that the speed-over-stability crowd > | can enable it (+ possibly an oops taint bit) > > Why disable it, when it's clearly working? Because I don't think normal Linux users should be in the hardware validation business. If the vendor says it's not tested we shouldn't enable it by default. -Andi