From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1763682AbXLTWss (ORCPT ); Thu, 20 Dec 2007 17:48:48 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754211AbXLTWsj (ORCPT ); Thu, 20 Dec 2007 17:48:39 -0500 Received: from ebiederm.dsl.xmission.com ([166.70.28.69]:59814 "EHLO ebiederm.dsl.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750918AbXLTWsi (ORCPT ); Thu, 20 Dec 2007 17:48:38 -0500 From: ebiederm@xmission.com (Eric W. Biederman) To: "Peer Chen" Cc: "peerchen" , "linux-kernel" , "akpm" , "Andy Currid" Subject: Re: [PATCH] msi: set 'En' bit of MSI Mapping Capability References: <200712182300373901202@gmail.com> <15F501D1A78BD343BE8F4D8DB854566B1F24C119@hkemmail01.nvidia.com> Date: Thu, 20 Dec 2007 15:48:08 -0700 In-Reply-To: <15F501D1A78BD343BE8F4D8DB854566B1F24C119@hkemmail01.nvidia.com> (Peer Chen's message of "Thu, 20 Dec 2007 21:43:00 +0800") Message-ID: User-Agent: Gnus/5.110006 (No Gnus v0.6) Emacs/21.4 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org "Peer Chen" writes: > The quirk is for our Intel platform, we don't want HT MSI mapping > enabled in any of our devices. Why is this a problem? I seem to recall a real hypertransport bus downstream of the Intel cpu. If there is a real hypertransport bus in the middle then what happens if someone puts a tunnel that uses hypertransport between the two chips? I feel very dense right now. I don't understand why enabling the mapping on an Intel based system is a problem. I am afraid there is some important gap in my understanding in which case we may need to rethink enabling the hypertransport capability by default. If disabling the hypertransport bus is simply an optimization, or it is to deal with an issue that appears exclusive to Nvidia chips I have no problem with your quirk. Eric