kernel/linux.git/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c, branch v5.16.1Linux kernel stable tree (mirror)https://git.radix-linux.su/kernel/linux.git/atom?h=v5.16.12021-10-13T18:14:48+00:00drm/amdgpu: Fix RAS page retirement with mode2 reset on Aldebaran2021-10-13T18:14:48+00:00Mukul Joshimukul.joshi@amd.com2021-09-21T00:48:23+00:00urn:sha1:91a1a52d03aa0f1f2b51c7df8a7bf437e906e29f
During mode2 reset, the GPU is temporarily removed from the
mgpu_info list. As a result, page retirement fails because it
cannot find the GPU in the GPU list.
To fix this, create our own list of GPUs that support MCE notifier
based page retirement and use that list to check if the UMC error
occurred on a GPU that supports MCE notifier based page retirement.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Tao Zhou <tao.zhou1@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Register MCE notifier for Aldebaran RAS2021-10-06T19:53:38+00:00Mukul Joshimukul.joshi@amd.com2021-09-22T18:49:43+00:00urn:sha1:12b2cab79017ebe598c74493ac1cfc5934d3ccc2
On Aldebaran, GPU driver will handle bad page retirement
for GPU memory even though UMC is host managed. As a result,
register a bad page retirement handler on the mce notifier
chain to retire bad pages on Aldebaran.
Signed-off-by: Mukul Joshi <mukul.joshi@amd.com>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: resolve RAS query bug2021-10-04T19:22:57+00:00John Clementsjohn.clements@amd.com2021-09-29T07:06:21+00:00urn:sha1:eb601e61d3492d809cb82a19560a6c31c36fd48a
clear error count when persistant harvesting is not enabled
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: skip umc ras irq handling in poison mode (v2)2021-09-28T13:30:07+00:00Tao Zhoutao.zhou1@amd.com2021-09-17T10:40:57+00:00urn:sha1:f524dd54a78924b59acd8f251788889129b3a2e9
In ras poison mode, umc uncorrectable error will be ignored until
the corrupted data consumed by another ras module (such as gfx, sdma).
v2: update the debug message and replace dev_warn with dev_info.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: set poison supported flag for RAS (v2)2021-09-28T13:30:07+00:00Tao Zhoutao.zhou1@amd.com2021-09-17T10:24:09+00:00urn:sha1:e43488493cbb46e862f83c66887f3e6cb854c6f0
Add RAS poison supported flag and tell PSP RAS TA about the info.
v2: rename poison mode to poison supported, we can also disable poison
mode even we support it.
print value of poison supported if ras feature enablement fails.
Signed-off-by: Tao Zhou <tao.zhou1@amd.com>
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Remove all code paths under the EAGAIN path in RAS late init2021-09-23T20:35:13+00:00Candice Licandice.li@amd.com2021-09-15T07:14:18+00:00urn:sha1:9080a18fc554cea0858fae6692a7003c5f0365fc
All code paths under the EAGAIN path in RAS late init are unused.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Updated RAS infrastructure2021-09-23T20:34:43+00:00John Clementsjohn.clements@amd.com2021-09-22T06:04:52+00:00urn:sha1:640ae42efb828be69a9ee6ac88fb3d5a3e678ddf
Update RAS infrastructure to support RAS query for MCA subblocks
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amdgpu: Update RAS trigger error block support2021-09-14T19:37:48+00:00John Clementsjohn.clements@amd.com2021-09-09T08:05:12+00:00urn:sha1:3771449bc80fa494c15f366ce1fa9e3168332b6a
Added trigger error support for MP0/MP1/MPIO blocks
Reviewed-by: Hawking Zhang <Hawking.Zhang@amd.com>
Signed-off-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/amdgpu: add mpio to ras block2021-09-01T20:55:11+00:00Candice Licandice.li@amd.com2021-08-27T11:14:36+00:00urn:sha1:a0a2f7bb220945e369de77ea004d96236e9463a6
Add MPIO to RAS block
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
drm/amd/amdgpu: remove unnecessary RAS context field2021-08-16T19:35:55+00:00Candice Licandice.li@amd.com2021-08-13T11:06:33+00:00urn:sha1:893cf382c0403d7c4581f0f01f6d06c76485123d
Delete ras_if->name in the RAS ctx structure and remove related lines.
Signed-off-by: Candice Li <candice.li@amd.com>
Reviewed-by: John Clements <john.clements@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>