From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andreas Hartmann Subject: Re: [dm-devel] AMD-Vi IO_PAGE_FAULTs and ata3.00: failed command: READ FPDMA QUEUED errors since Linux 4.0 Date: Wed, 30 Sep 2015 16:52:47 +0200 Message-ID: <560BF73F.8000008@maya.org> References: <55B7BEA2.30205@01019freenet.de> <20150728175054.GB24782@redhat.com> <55B7D054.4070308@maya.org> <20150728192908.GA25264@redhat.com> <55BCD5A7.2080708@maya.org> <55BE1D5E.6020709@maya.org> <55FE5740.2060701@maya.org> <20150929152100.GL3036@8bytes.org> <20150929162042.GR3036@8bytes.org> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <20150929162042.GR3036-zLv9SwRftAIdnm+yROfE0A@public.gmane.org> List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org Errors-To: iommu-bounces-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org To: Joerg Roedel , Mikulas Patocka Cc: device-mapper development , linux-pci , iommu-cunTk1MwBs9QetFLy7KEm3xJsTq8ys+cHZ5vskTnxNA@public.gmane.org, Jens Axboe , Andreas Hartmann , Linus Torvalds , Christoph Hellwig , Milan Broz List-Id: dm-devel.ids On 09/29/2015 at 06:20 PM, Joerg Roedel wrote: > On Tue, Sep 29, 2015 at 11:58:10AM -0400, Mikulas Patocka wrote: >> On Tue, 29 Sep 2015, Joerg Roedel wrote: >> There was a patch (34b48db66e08ca1c1bc07cf305d672ac940268dc) that >> increased default block request size. That patch triggers AMD-Vi page >> faults. The bug may be in ATA driver, in ATA controller on in AMD-Vi >> driver or hardware. I didn't see anything in that thread that proves that >> the bug in not in AMD-Vi IOMMU. >> >> The bug probably existed even before kernel 3.19, but it was masked by the >> fact that I/O request size was artifically capped. Bisecting probably >> won't find it, as it may have existed since ever. > > Okay, I see. But as long as the request-size is not bigger than 128MB > (the biggest chunk the AMD IOMMU driver can map at once), I don't see > how the IOMMU driver could be at fault. > > Which ATA driver is in use when this happens and are there instructions > on how to reproduce the issue? > > Alternativly someone who can reproduce it should trace the calls to > __map_single and __unmap_single in the AMD IOMMU driver to find out > whether the addresses which the faults happen on are really mapped, or > at least requested from the AMD IOMMU driver. How can I trace it? Thanks, Andreas From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout1.freenet.de ([195.4.92.91]:57088 "EHLO mout1.freenet.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750768AbbI3Ozu (ORCPT ); Wed, 30 Sep 2015 10:55:50 -0400 Subject: Re: [dm-devel] AMD-Vi IO_PAGE_FAULTs and ata3.00: failed command: READ FPDMA QUEUED errors since Linux 4.0 To: Joerg Roedel , Mikulas Patocka References: <55B7BEA2.30205@01019freenet.de> <20150728175054.GB24782@redhat.com> <55B7D054.4070308@maya.org> <20150728192908.GA25264@redhat.com> <55BCD5A7.2080708@maya.org> <55BE1D5E.6020709@maya.org> <55FE5740.2060701@maya.org> <20150929152100.GL3036@8bytes.org> <20150929162042.GR3036@8bytes.org> Cc: Andreas Hartmann , iommu@lists.linux-foundation.org, Leo Duran , Christoph Hellwig , device-mapper development , Milan Broz , Jens Axboe , linux-pci , Linus Torvalds From: Andreas Hartmann Message-ID: <560BF73F.8000008@maya.org> Date: Wed, 30 Sep 2015 16:52:47 +0200 MIME-Version: 1.0 In-Reply-To: <20150929162042.GR3036@8bytes.org> Content-Type: text/plain; charset=windows-1252 Sender: linux-pci-owner@vger.kernel.org List-ID: On 09/29/2015 at 06:20 PM, Joerg Roedel wrote: > On Tue, Sep 29, 2015 at 11:58:10AM -0400, Mikulas Patocka wrote: >> On Tue, 29 Sep 2015, Joerg Roedel wrote: >> There was a patch (34b48db66e08ca1c1bc07cf305d672ac940268dc) that >> increased default block request size. That patch triggers AMD-Vi page >> faults. The bug may be in ATA driver, in ATA controller on in AMD-Vi >> driver or hardware. I didn't see anything in that thread that proves that >> the bug in not in AMD-Vi IOMMU. >> >> The bug probably existed even before kernel 3.19, but it was masked by the >> fact that I/O request size was artifically capped. Bisecting probably >> won't find it, as it may have existed since ever. > > Okay, I see. But as long as the request-size is not bigger than 128MB > (the biggest chunk the AMD IOMMU driver can map at once), I don't see > how the IOMMU driver could be at fault. > > Which ATA driver is in use when this happens and are there instructions > on how to reproduce the issue? > > Alternativly someone who can reproduce it should trace the calls to > __map_single and __unmap_single in the AMD IOMMU driver to find out > whether the addresses which the faults happen on are really mapped, or > at least requested from the AMD IOMMU driver. How can I trace it? Thanks, Andreas