Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   "Merger, Edgar [AUTOSOL/MAS/AUGS]" <Edgar.Merger@emerson.com>
To:     Will Deacon <will@kernel.org>,
        "Deucher, Alexander" <Alexander.Deucher@amd.com>
CC:     "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "linux-pci@vger.kernel.org" <linux-pci@vger.kernel.org>,
        "iommu@lists.linux-foundation.org" <iommu@lists.linux-foundation.org>,
        Bjorn Helgaas <bhelgaas@google.com>,
        Joerg Roedel <jroedel@suse.de>,
        "Kuehling, Felix" <Felix.Kuehling@amd.com>
Subject: RE: [EXTERNAL] Re: [PATCH] PCI: Mark AMD Raven iGPU ATS as broken
Thread-Topic: [EXTERNAL] Re: [PATCH] PCI: Mark AMD Raven iGPU ATS as broken
Thread-Index: AQHWwdw3n5VLcueYHUSP0T6AMdoDgKnWTbwAgABu3qA=
Date:   Tue, 24 Nov 2020 05:32:12 +0000
Message-ID: <MWHPR10MB1310DE70BAC5A86892D5398B89FB0@MWHPR10MB1310.namprd10.prod.outlook.com>
References: <20201123134410.10648-1-will@kernel.org>
 <MN2PR12MB4488308D26DB50C18EA3BE0FF7FC0@MN2PR12MB4488.namprd12.prod.outlook.com>
 <20201123223356.GC12069@willie-the-truck>
In-Reply-To: <20201123223356.GC12069@willie-the-truck>
Accept-Language: de-DE, en-US
Content-Language: en-US
Content-Type: text/plain; charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-Network-Message-Id: 2734ff5f-f7fd-4cf1-9117-08d8903a4be5
X-MS-Exchange-CrossTenant-originalarrivaltime: 24 Nov 2020 05:32:12.6964
 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: eb06985d-06ca-4a17-81da-629ab99f6505
X-MS-Exchange-CrossTenant-mailboxtype: HOSTED
X-MS-Exchange-CrossTenant-userprincipalname: MPWT7WqPMLiJAhyM2YlKECuyXBmorS1f9S/10DozyGK+11lwF3XCM2wrY88sLChIGhKZMaTgXGWGlUBY4FogkO3C4DhiKvBItZU1DJzJCzo=
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CO1PR10MB4481
X-Proofpoint-Virus-Version: vendor=fsecure engine=2.50.10434:6.0.312,18.0.737
 definitions=2020-11-24_01:2020-11-24,2020-11-23 signatures=0
X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 bulkscore=0 adultscore=0
 mlxscore=0 mlxlogscore=999 phishscore=0 priorityscore=1501 clxscore=1011
 spamscore=0 malwarescore=0 impostorscore=0 suspectscore=0
 lowpriorityscore=0 classifier=spam adjust=0 reason=mlx scancount=1
 engine=8.12.0-2009150000 definitions=main-2011240032
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

This is a board developed by my company.
Subsystem-ID is ea50:0c19 or ea50:cc10 (depending on which particular carri=
er board the compute module is attached to), however we haven=B4t managed y=
et to enter this Subsystem-ID to every PCI-Device in the system, because of=
 missing means to do that by our UEFI-FW. This might will change if we upda=
te to latest AGESA version.=20

-----Original Message-----
From: Will Deacon <will@kernel.org>=20
Sent: Montag, 23. November 2020 23:34
To: Deucher, Alexander <Alexander.Deucher@amd.com>
Cc: linux-kernel@vger.kernel.org; linux-pci@vger.kernel.org; iommu@lists.li=
nux-foundation.org; Bjorn Helgaas <bhelgaas@google.com>; Merger, Edgar [AUT=
OSOL/MAS/AUGS] <Edgar.Merger@emerson.com>; Joerg Roedel <jroedel@suse.de>; =
Kuehling, Felix <Felix.Kuehling@amd.com>
Subject: [EXTERNAL] Re: [PATCH] PCI: Mark AMD Raven iGPU ATS as broken

On Mon, Nov 23, 2020 at 09:04:14PM +0000, Deucher, Alexander wrote:
> [AMD Public Use]
>=20
> > -----Original Message-----
> > From: Will Deacon <will@kernel.org>
> > Sent: Monday, November 23, 2020 8:44 AM
> > To: linux-kernel@vger.kernel.org
> > Cc: linux-pci@vger.kernel.org; iommu@lists.linux-foundation.org;=20
> > Will Deacon <will@kernel.org>; Bjorn Helgaas <bhelgaas@google.com>;=20
> > Deucher, Alexander <Alexander.Deucher@amd.com>; Edgar Merger=20
> > <Edgar.Merger@emerson.com>; Joerg Roedel <jroedel@suse.de>
> > Subject: [PATCH] PCI: Mark AMD Raven iGPU ATS as broken
> >=20
> > Edgar Merger reports that the AMD Raven GPU does not work reliably=20
> > on his system when the IOMMU is enabled:
> >=20
> >   | [drm:amdgpu_job_timedout [amdgpu]] *ERROR* ring gfx timeout,=20
> > signaled seq=3D1, emitted seq=3D3
> >   | [...]
> >   | amdgpu 0000:0b:00.0: GPU reset begin!
> >   | AMD-Vi: Completion-Wait loop timed out
> >   | iommu ivhd0: AMD-Vi: Event logged [IOTLB_INV_TIMEOUT
> > device=3D0b:00.0 address=3D0x38edc0970]
> >=20
> > This is indicative of a hardware/platform configuration issue so,=20
> > since disabling ATS has been shown to resolve the problem, add a=20
> > quirk to match this particular device while Edgar follows-up with AMD f=
or more information.
> >=20
> > Cc: Bjorn Helgaas <bhelgaas@google.com>
> > Cc: Alex Deucher <alexander.deucher@amd.com>
> > Reported-by: Edgar Merger <Edgar.Merger@emerson.com>
> > Suggested-by: Joerg Roedel <jroedel@suse.de>
> > Link:
> > https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__nam11.safelinks.=
protection.outlook.com_-3Furl-3Dhttps-253A-252F-252Flore&d=3DDwIBAg&c=3DjOU=
RTkCZzT8tVB5xPEYIm3YJGoxoTaQsQPzPKJGaWbo&r=3DBJxhacqqa4K1PJGm6_-862rdSP13_P=
6LVp7j_9l1xmg&m=3DWjiRGepDgI7voSyaAJcvnvZb6gsvZ1fvcnR2tm6bGXg&s=3DO1nU-RafB=
XMAS7Mao5Gtu6o1Xkuj8fg4oHQs74TssuA&e=3D .
> > kernel.org%2Flinux-
> > iommu%2FMWHPR10MB1310F042A30661D4158520B589FC0%40MWHPR10M
> > B1310.namprd10.prod.outlook.com&amp;data=3D04%7C01%7Calexander.deuc
> > her%40amd.com%7C1a883fe14d0c408e7d9508d88fb5df4e%7C3dd8961fe488
> > 4e608e11a82d994e183d%7C0%7C0%7C637417358593629699%7CUnknown%7
> > CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwi
> > LCJXVCI6Mn0%3D%7C1000&amp;sdata=3DTMgKldWzsX8XZ0l7q3%2BszDWXQJJ
> > LOUfX5oGaoLN8n%2B8%3D&amp;reserved=3D0
> > Signed-off-by: Will Deacon <will@kernel.org>
> > ---
> >=20
> > Hi all,
> >=20
> > Since Joerg is away at the moment, I'm posting this to try to make=20
> > some progress with the thread in the Link: tag.
>=20
> + Felix
>=20
> What system is this?  Can you provide more details?  Does a sbios=20
> update fix this?  Disabling ATS for all Ravens will break GPU compute=20
> for a lot of people.  I'd prefer to just black list this particular=20
> system (e.g., just SSIDs or revision) if possible.

Cheers, Alex. I'll have to defer to Edgar for the details, as my understand=
ing from the original thread over at:

https://urldefense.proofpoint.com/v2/url?u=3Dhttps-3A__lore.kernel.org_linu=
x-2Diommu_MWHPR10MB1310CDB6829DDCF5EA84A14689150-40MWHPR10MB1310.namprd10.p=
rod.outlook.com_&d=3DDwIBAg&c=3DjOURTkCZzT8tVB5xPEYIm3YJGoxoTaQsQPzPKJGaWbo=
&r=3DBJxhacqqa4K1PJGm6_-862rdSP13_P6LVp7j_9l1xmg&m=3DWjiRGepDgI7voSyaAJcvnv=
Zb6gsvZ1fvcnR2tm6bGXg&s=3D9qyuCqHeOGaY1sKjkzNN5A6ks6PNF7V2M2PPckHyFKk&e=3D=
=20

is that this is a board developed by his company.

Edgar -- please can you answer Alex's questions?

Will