drm/amdkfd: Fix TCP XNACK scoreboard reset race

Browse source

Fix a hardware RTL bug in the TCP XNACK scoreboard reset path where a wave
receiving a no-retry FAULT from UTC and subsequently terminating may leave
its scoreboard entry uncleared when reset events arrive back-to-back.

This can cause a later, unrelated wave using the same slot to incorrectly
inherit the XNACK error state, resulting in its VMEM operations being
dropped even though the wave never faulted.

Signed-off-by: Gang Ba <Gang.Ba@amd.com>
Reviewed-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

...

This commit is contained in:

Gang Ba 2026-09-10 17:12:03 -04:00 • committed by Alex Deucher

parent aee05c455a

commit a6332b8471

9 changed files with 184 additions and 3 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

3

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_aldebaran.c

View file

10

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.c

View file

1

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gfx_v9.h

View file

83

drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.c

View file

1

drivers/gpu/drm/amd/amdgpu/gfx_v9_4_2.h

View file

63

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c

View file

2

drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.h

View file

23

drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c

View file

1

drivers/gpu/drm/amd/include/kgd_kfd_interface.h

View file