From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753520AbYIVOqc (ORCPT ); Mon, 22 Sep 2008 10:46:32 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753272AbYIVOqQ (ORCPT ); Mon, 22 Sep 2008 10:46:16 -0400 Received: from mx2.mail.elte.hu ([157.181.151.9]:39553 "EHLO mx2.mail.elte.hu" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753241AbYIVOqP (ORCPT ); Mon, 22 Sep 2008 10:46:15 -0400 Date: Mon, 22 Sep 2008 16:46:01 +0200 From: Ingo Molnar To: Joerg Roedel Cc: FUJITA Tomonori , linux-kernel@vger.kernel.org Subject: Re: [PATCH] AMD IOMMU: revert "x86, AMD IOMMU: honor iommu=off instead of amd_iommu=off" Message-ID: <20080922144601.GA27956@elte.hu> References: <20080922223457W.fujita.tomonori@lab.ntt.co.jp> <20080922140749.GY24392@amd.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20080922140749.GY24392@amd.com> User-Agent: Mutt/1.5.18 (2008-05-17) X-ELTE-VirusStatus: clean X-ELTE-SpamScore: -1.5 X-ELTE-SpamLevel: X-ELTE-SpamCheck: no X-ELTE-SpamVersion: ELTE 2.0 X-ELTE-SpamCheck-Details: score=-1.5 required=5.9 tests=BAYES_00 autolearn=no SpamAssassin version=3.2.3 -1.5 BAYES_00 BODY: Bayesian spam probability is 0 to 1% [score: 0.0000] Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org * Joerg Roedel wrote: > > x86, AMD IOMMU: honor iommu=off instead of amd_iommu=off > > > > This patch removes the amd_iommu=off kernel parameter and honors > > the generic > > > > iommu=off parameter for the same purpose. > > > > > > The above commit is wrong. > > It isn't. The user normally don't care about the type of IOMMU in the > system. So disabling it with iommu=off is the right way. To achieve > what you want its better to add iommu=gart and iommu=amd to the option > parser. This will be consistent with Calgary and SWIOTLB too. well, what matters in the end is to have a consistent set of exclusion options: gart_iommu=off # disable the GART (and only that one) intel_iommu=off # disable the Intel IOMMU (and only that one) amd_iommu=off # disable AMD-IOMMU (and only that one) then there's the all-off option: iommu=off # wildcard: disable all IOMMUs [ whether iommu=off also disables the swiotlb is a detail. ] and we could also do the inclusive options in addition: iommu=gart # use the GART as the primary IOMMU [if available] iommu=amd # use the AMD-IOMMU as the primary IOMMU [if available] iommu=intel # use the Intel IOMMU [if available] so could we please first agree on such a specific list of generic options, and then implement them consistently, while keeping legacies (the ones that matter) intact as well? Ingo