drm/amdgpu,amdkfd: correct setting MES queue type

Browse source

MES ADD_QUEUE programs the firmware with the queue type from the driver
input, but MES REMOVE_QUEUE leaves queue_type at the zero-initialized
value.  Zero decodes as GFX in the MES REMOVE_QUEUE packet.

That means removing a KFD compute queue can be submitted to MES as a GFX
queue.  In a debug-trap suspend/remove sequence this can leave MES
looking for the doorbell in the wrong queue class and the REMOVE_QUEUE
command may never complete.  The observed failing packet removed
doorbell 0x1002 with queue_type=GFX even though the corresponding
ADD_QUEUE for the same doorbell was queue_type=COMPUTE.

Populate REMOVE_QUEUE.queue_type the same way ADD_QUEUE does.

Signed-off-by: Geoffrey McRae <geoffrey.mcrae@amd.com>
Reviewed-by: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

...

This commit is contained in:

Geoffrey McRae 2026-06-24 12:32:18 +10:00 • committed by Alex Deucher

parent 9d5f1c0db1

commit 89db46e455

6 changed files with 11 additions and 0 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

1

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

View file

1

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

View file

2

drivers/gpu/drm/amd/amdgpu/mes_v11_0.c

View file

2

drivers/gpu/drm/amd/amdgpu/mes_v12_0.c

View file

3

drivers/gpu/drm/amd/amdgpu/mes_v12_1.c

View file

2

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

View file