From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756638AbXLKRGY (ORCPT ); Tue, 11 Dec 2007 12:06:24 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753313AbXLKRGO (ORCPT ); Tue, 11 Dec 2007 12:06:14 -0500 Received: from terminus.zytor.com ([198.137.202.10]:49226 "EHLO terminus.zytor.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753127AbXLKRGN (ORCPT ); Tue, 11 Dec 2007 12:06:13 -0500 Message-ID: <475EC342.8080901@zytor.com> Date: Tue, 11 Dec 2007 09:05:06 -0800 From: "H. Peter Anvin" User-Agent: Thunderbird 2.0.0.9 (X11/20071115) MIME-Version: 1.0 To: "David P. Reed" CC: Rene Herman , Paul Rolland , David Newall , Krzysztof Halasa , Pavel Machek , Andi Kleen , Alan Cox , linux-kernel@vger.kernel.org, Thomas Gleixner , Ingo Molnar , rol@witbe.net Subject: Re: RFC: outb 0x80 in inb_p, outb_p harmful on some modern AMD64 with MCP51 laptops References: <475879CD.9080006@reed.com> <20071207160439.71b7f46a@the-village.bc.nu> <20071209125458.GB4381@ucw.cz> <20071209165908.GA15910@one.firstfloor.org> <20071209212513.GC24284@elf.ucw.cz> <475CBDD7.5050602@keyaccess.nl> <475DE37F.20706@davidnewall.com> <475DE6F4.80702@zytor.com> <475DEB23.1000304@davidnewall.com> <20071211084059.3d03e11d@tux.DEF.witbe.net> <475E5D4B.8020101@keyaccess.nl> <475E7DC2.4060509@davidnewall.com> <475E8D91.20201@keyaccess.nl> <20071211143224.15900995@tux.DEF.witbe.net> <475E9B9B.2050709@keyaccess.nl> <475EACB8.7080608@keyaccess.nl> <20071211163706.2dc82275@tux.DEF.witbe.net> <475EB263.2050405@keyaccess.nl> <475EC1C0.2040000@reed.com> In-Reply-To: <475EC1C0.2040000@reed.com> Content-Type: text/plain; charset=ISO-8859-15; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org David P. Reed wrote: > I do remind all that 0x80 is a BIOS-specific standard, and is per BIOS - > other ports have been used in the history of the IBM PC family by some > vendors, and some machines have used it for DMA port mapping!! Correction: ALL machines use it for DMA port mapping. The port is assigned to the legacy DMA controller, but performs no operation. That's what makes it safe to write (NOT read!) -hpa