RE: [PATCH] drm/amdgpu/userq: skip unmapped queues in amdgpu_userq_wait_for_signal

AMD General

A dereferenced queue may remain in the XArray. To avoid retrieving an unmapped queue, amdgpu_userq_destroy() should remove the queue from the process's queue XArray first. If there are any other paths that fail to remove dereferenced queues from the XArray, amdgpu_userq_wait_for_last_fence() should also skip those stale entries as a defensive safeguard.

Regards,
      Prike

> -----Original Message-----
> From: Jesse Zhang <[email protected]>
> Sent: Tuesday, August 18, 2026 3:29 PM
> To: [email protected]
> Cc: Deucher, Alexander <[email protected]>; Koenig, Christian
> <[email protected]>; Liang, Prike <[email protected]>; Khatri, Sunil
> <[email protected]>; Zhang, Jesse(Jie) <[email protected]>
> Subject: [PATCH] drm/amdgpu/userq: skip unmapped queues in
> amdgpu_userq_wait_for_signal
>
> amdgpu_userq_wait_for_signal() does an unbounded dma_fence_wait() on every
> queue's last_fence before eviction. A queue disabled via MODIFY with
> queue_percentage == 0 is unmapped but stays in the xarray, and its pending fence
> never signals because the work will not run while the queue is unmapped. Eviction
> then blocks forever, hanging the task and wedging the GPU on a forced reset.
>
> Only wait on fences of queues that are still mapped.
>
> Signed-off-by: Jesse Zhang <[email protected]>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c | 10 ++++++++++
>  1 file changed, 10 insertions(+)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> index feffebb210ea..cfbfecb05768 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_userq.c
> @@ -1302,6 +1302,16 @@ amdgpu_userq_wait_for_signal(struct
> amdgpu_userq_mgr *uq_mgr)
>               if (!f)
>                       continue;
>
> +             /*
> +              * Only a mapped queue can make progress on its fences. A queue
> +              * that has been unmapped (e.g. disabled through a MODIFY with
> +              * queue_percentage == 0) will never execute its pending work,
> +              * so its last_fence would never signal. Waiting on it here would
> +              * block the eviction path forever, so skip such queues.
> +              */
> +             if (queue->state != AMDGPU_USERQ_STATE_MAPPED)
> +                     continue;
> +
>               dma_fence_wait(f, false);
>       }
>  }
> --
> 2.49.0