Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752548AbbLNPIK (ORCPT ); Mon, 14 Dec 2015 10:08:10 -0500 Received: from 8bytes.org ([81.169.241.247]:44438 "EHLO theia.8bytes.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751830AbbLNPII (ORCPT ); Mon, 14 Dec 2015 10:08:08 -0500 Date: Mon, 14 Dec 2015 16:08:05 +0100 From: Joerg Roedel To: Suravee Suthikulpanit Cc: linux-kernel@vger.kernel.org, iommu@lists.linux-foundation.org Subject: Re: [PATCH] iommu/amd: Assign default IOMMU when there is only one IOMMU Message-ID: <20151214150805.GE11292@8bytes.org> References: <1449874478-31770-1-git-send-email-Suravee.Suthikulpanit@amd.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1449874478-31770-1-git-send-email-Suravee.Suthikulpanit@amd.com> User-Agent: Mutt/1.5.21 (2010-09-15) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 845 Lines: 22 On Fri, Dec 11, 2015 at 04:54:38PM -0600, Suravee Suthikulpanit wrote: > Current driver makes assumption that device with devid zero is always > included in the range of devices to be managed by IOMMU. However, > certain FW does not include devid zero in IVRS table. > This has caused IOMMU perf driver to fail to initialize. Hmm, this is a firmware bug. Is this bug seen in any systems that are for sale? > This patch implements a workaround for this case by always assign > devid zero to be handled by the first IOMMU. Otherwise its better to fix the firmware than to add workarounds. Joerg -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/