linux-next.git/drivers/gpu/drm/amd/amdgpu/mes_userqueue.c, branch master

drm/amdgpu,amdkfd: correct setting MES queue type

2026-07-01T15:42:37+00:00

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 Reviewed-by: Sunil Khatri Signed-off-by: Alex Deucher

drm/amdgpu: implement per-process MES context

2026-06-17T20:20:37+00:00

MES process context is a process-level page where process specific context is saved for MES scheduler. However, current user-queue code path assigns fw_obj of a queue to MES process_context_addr when adding the queue to MES. This means every new queue from the same process would replace the previous process context address with that queue's fw_obj address. What's worse is, when user space frees a queue, its fw_obj will be freed as well, causing MES working on a NULL page pointer. This issue leads to inconsistency and crash in the scheduler. This commit allocates a process-level page for MES process contexts for a process other than queue-level Signed-off-by: Zhu Lingshan Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu: use a single entry point for mes compute reset

2026-06-17T19:51:35+00:00

When we reset MES queues we need to coordinate across KGD and KFD. Use a single function to handle the queue resets across KFD and KGD. v2: squash in fixes for userqs Co-developed-by: Jesse Zhang Co-developed-by: Amber Lin Signed-off-by: Amber Lin Signed-off-by: Jesse Zhang Reviewed-by: Jesse Zhang Signed-off-by: Alex Deucher

drm/amdgpu/userq: add MES userq reset helper

2026-06-17T19:51:35+00:00

Will be used by the common compute queue reset handler. Reviewed-by: Jesse Zhang Signed-off-by: Alex Deucher

drm/amdgpu/userq: drop detect_and_reset callback

2026-06-17T19:51:34+00:00

No longer needed. Reviewed-by: Jesse Zhang Reviewed-by: Prike Liang Signed-off-by: Alex Deucher

drm/amdgpu/userq: add mes userq reset callback

2026-06-17T19:51:34+00:00

Enable per queue reset for MES managed queues. Reviewed-by: Jesse Zhang Reviewed-by: Prike Liang Signed-off-by: Alex Deucher

drm/amdgpu/userq: move wptr_obj cleanup in mqd_destroy

2026-06-03T17:58:51+00:00

In case when queue_create fails and mqd has already been allocated and hence wptr_obj is not cleaned up. So moving that cleanup part to mqd_destroy so it takes care of all the cases of clean up and during tear down of the queue. Signed-off-by: Sunil Khatri Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu/userq: use array instead of list for userq_vas

2026-05-27T14:50:02+00:00

Use arrays instead of list for userq_vas since we have fixed no of bos. Also, we dont have to worry to free that memory later since this array would be free along with queue only. Signed-off-by: Sunil Khatri Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu/userq: remove amdgpu_userq_create/destroy_object wrapper

2026-05-27T14:48:34+00:00

Remove the amdgpu_userq_create/destroy_object wrappers and use directly the kernel bo allocation function which does all the things which are done in wrapper. Signed-off-by: Sunil Khatri Suggested-by: Christian König Reviewed-by: Christian König Signed-off-by: Alex Deucher

drm/amdgpu/userq: add amdgpu_bo_unpin when amdgpu_ttm_alloc_gart fails

2026-05-27T14:39:20+00:00

Unpin the wptr_obj->obj when amdgpu_ttm_alloc_gart fails. Signed-off-by: Sunil Khatri Reviewed-by: Christian König Signed-off-by: Alex Deucher