Skip to content

RAS support for amdgpu

Alex Deucher amd-gfx 1 version New

Get series with b4
b4 am [email protected]

Versions newest first

  1. v1 Latest20 patches 0 repliesNew

Patches in v1 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/20drm/amdgpu: add ta ras fw info (v2)drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h drivers/gpu/drm/amd/amdgpu/psp_v11_0.c+11 -00 replies
2/20drm/amdgpu: export ta fw infodrivers/gpu/drm/amd/amdgpu/amdgpu_kms.c include/uapi/drm/amdgpu_drm.h+22 -00 replies
3/20drm/amdgpu: add module parameters for rasdrivers/gpu/drm/amd/amdgpu/amdgpu.h drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c+19 -00 replies
4/20drm/amdgpu: add ta_ras_if.hdrivers/gpu/drm/amd/amdgpu/ta_ras_if.h+108 -00 replies
5/20drm/amdgpu: add psp ras callback func and macrodrivers/gpu/drm/amd/amdgpu/amdgpu_psp.h+11 -00 replies
6/20drm/amdgpu: add psp ras subsystem infrastructure (v2)drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h+230 -00 replies
7/20drm/amdgpu: add psp v11 ras callbackdrivers/gpu/drm/amd/amdgpu/psp_v11_0.c+50 -00 replies
8/20drm/amdgpu: add psp cmd submit timeoutdrivers/gpu/drm/amd/amdgpu/amdgpu_psp.c+5 -10 replies
9/20drm/amdgpu: add amdgpu_ras.c to support ras (v2)drivers/gpu/drm/amd/amdgpu/Makefile drivers/gpu/drm/amd/amdgpu/amdgpu_device.c drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h +2 more+1475 -10 replies
10/20drm/amdgpu: add debugfs ctrl nodedrivers/gpu/drm/amd/amdgpu/amdgpu_ras.c drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h+121 -100 replies
11/20drm/amdgpu: reserve bad pages during recoverydrivers/gpu/drm/amd/amdgpu/amdgpu_device.c+5 -00 replies
12/20drm/amdgpu: enable ras on sdma4drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c+187 -10 replies
13/20drm/amdgpu: enable ras on gfx9 (v2)drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c+176 -00 replies
14/20drm/amdgpu: enable ras on gmc9drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c+278 -00 replies
15/20drm/amdgpu: Add a new flag to AMDGPU_CTX_OP_QUERY_STATE2drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h include/uapi/drm/amdgpu_drm.h+22 -00 replies
16/20drm/amdgpu: add ioctl query for enabled ras features (v2)drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c include/uapi/drm/amdgpu_drm.h+41 -00 replies
17/20drm/amdgpu: skip gpu reset when ras error occureddrivers/gpu/drm/amd/amdgpu/amdgpu_ras.h+3 -00 replies
18/20drm/amdgpu: add human readable debugfs control support (v2)drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c+102 -130 replies
19/20drm/amdkfd: add RAS capabilities in topology for Vega20 (v2)drivers/gpu/drm/amd/amdkfd/kfd_topology.c drivers/gpu/drm/amd/amdkfd/kfd_topology.h+20 -00 replies
20/20drm/amdkfd: add RAS ECC event support (v2)drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c +5 more+47 -20 replies

Reviews trailers per patch

All 20 patches have a Reviewed-by or Acked-by.

PatchAlex DeucherHawking ZhangFelix Kuehling
1/20R-b
2/20R-b
3/20R-b R-b
4/20R-b
5/20R-b A-b
6/20R-b
7/20R-b A-b
8/20R-b
9/20R-b
10/20R-b
11/20R-b
12/20R-b
13/20R-b
14/20R-b
15/20R-b
16/20R-b
17/20R-b
18/20R-b
19/20R-b R-b
20/20R-b R-b

Trailers given in replies are filled; those carried in the patches from earlier versions are outlined with dashes. Scroll the table sideways for all 3 reviewers.

Read the v1 thread

Cover letter [PATCH 00/20] RAS support for amdgpu

This patch set adds initial RAS (Reliability, Availability, Serviceability) support to amdgpu on supported boards. Features include SRAM and VRAM ECC, bad page tracking, and error containment.

Eric Huang (2):
drm/amdkfd: add RAS capabilities in topology for Vega20 (v2) drm/amdkfd: add RAS ECC event support (v2)

Feifei Xu (1):
drm/amdgpu: enable ras on gfx9 (v2)

xinhui pan (17):
drm/amdgpu: add ta ras fw info (v2)
drm/amdgpu: export ta fw info
drm/amdgpu: add module parameters for ras drm/amdgpu: add ta_ras_if.h
drm/amdgpu: add psp ras callback func and macro drm/amdgpu: add psp ras subsystem infrastructure (v2) drm/amdgpu: add psp v11 ras callback
drm/amdgpu: add psp cmd submit timeout drm/amdgpu: add amdgpu_ras.c to support ras (v2) drm/amdgpu: add debugfs ctrl node
drm/amdgpu: reserve bad pages during recovery drm/amdgpu: enable ras on sdma4
drm/amdgpu: enable ras on gmc9
drm/amdgpu: Add a new flag to AMDGPU_CTX_OP_QUERY_STATE2 drm/amdgpu: add ioctl query for enabled ras features (v2) drm/amdgpu: skip gpu reset when ras error occured drm/amdgpu: add human readable debugfs control support (v2)

 drivers/gpu/drm/amd/amdgpu/Makefile        |    2 +-
 drivers/gpu/drm/amd/amdgpu/amdgpu.h        |    2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.h |    1 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c    |   17 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.h    |    2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |   14 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c    |   17 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.h    |    3 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.h    |    2 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c    |   31 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c    |  220 ++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h    |   32 +
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c    | 1438 ++++++++++++++++++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h    |  229 ++++
 drivers/gpu/drm/amd/amdgpu/amdgpu_sdma.h   |    4 +
 drivers/gpu/drm/amd/amdgpu/gfx_v9_0.c      |  174 +++
 drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c      |  277 ++++
 drivers/gpu/drm/amd/amdgpu/psp_v11_0.c     |   57 +
 drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c     |  186 ++-
 drivers/gpu/drm/amd/amdgpu/ta_ras_if.h     |  108 ++
 drivers/gpu/drm/amd/amdkfd/kfd_device.c    |   11 +
 drivers/gpu/drm/amd/amdkfd/kfd_events.c    |   18 +-
 drivers/gpu/drm/amd/amdkfd/kfd_priv.h      |    3 +
 drivers/gpu/drm/amd/amdkfd/kfd_topology.c  |   16 +
 drivers/gpu/drm/amd/amdkfd/kfd_topology.h  |    4 +
 include/uapi/drm/amdgpu_drm.h              |   35 +
 include/uapi/linux/kfd_ioctl.h             |   12 +-
 27 files changed, 2910 insertions(+), 5 deletions(-)
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
 create mode 100644 drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
 create mode 100644 drivers/gpu/drm/amd/amdgpu/ta_ras_if.h
Signature · 6 lines
2.20.1

_______________________________________________
amd-gfx mailing list
[email protected]
https://lists.freedesktop.org/mailman/listinfo/amd-gfx