From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755304Ab0EOCZt (ORCPT ); Fri, 14 May 2010 22:25:49 -0400 Received: from relay3.sgi.com ([192.48.152.1]:39924 "EHLO relay.sgi.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1753272Ab0EOCZr (ORCPT ); Fri, 14 May 2010 22:25:47 -0400 Message-ID: <4BEE0623.9010801@sgi.com> Date: Fri, 14 May 2010 19:25:39 -0700 From: Mike Travis User-Agent: Thunderbird 2.0.0.24 (X11/20100411) MIME-Version: 1.0 To: "H. Peter Anvin" CC: Jesse Barnes , Bjorn Helgaas , Mike Habeck , Ingo Molnar , Thomas Gleixner , x86@kernel.org, Jacob Pan , Tejun Heo , LKML , Yinghai , "linux-pci@vger.kernel.org" , Myron Stowe Subject: Re: [Patch 1/1] x86 pci: Add option to not assign BAR's if not already assigned References: <4BEAF008.9030805@sgi.com> <201005131256.17997.bjorn.helgaas@hp.com> <4BEC5530.1000008@sgi.com> <201005131402.30759.bjorn.helgaas@hp.com> <20100514152509.3aeb37b4@virtuousgeek.org> <4BEDCFD9.7020202@sgi.com> <4BEDD03B.30106@zytor.com> <4BEDD14A.1030400@sgi.com> In-Reply-To: <4BEDD14A.1030400@sgi.com> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org ... We're somewhat fortunate in that our Legacy I/O > devices are confined to those on the first blade, and all of these > other devices are on other blades (PCI segments 1+). By "somewhat" I meant we'd be way more fortunate without the legacy I/O devices at all! But hpa is right, 4 lines of assembler is way better than (900?) lines of C. My feeling is that if a CPU needs legacy i/o it should be built into the chip. HAH! ;-) The BIOS should just list the machine resources, in a "non-BIOS" way, (oh wait, that's ACPI! :*) Cheers!