[PATCH 3/3] drm/amdgpu: Trigger a wedged event for every type of reset

[Christian König]

Am 19.02.25 um 22:35 schrieb André Almeida:
> Instead of only triggering a wedged event for complete GPU resets,
> trigger for all types, like soft resets and ring resets. Regardless of
> the reset, it's useful for userspace to know that it happened because
> the kernel will reject further submissions from that app.
>
> Signed-off-by: André Almeida <andrealmeid at igalia.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  3 ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    | 16 +++++++++-------
>  2 files changed, 9 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 24ba52d76045..36738c1a5b59 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -6123,9 +6123,6 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
>  
>  	atomic_set(&adev->reset_domain->reset_res, r);
>  
> -	if (!r)
> -		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
> -

Feel free to add my rb to patch #1 and #2, but this here is a bad idea.

We have resets which are not triggered by a submission timeout, but rather because of RAS (for example) and those would now not be raised any more.

Regards,
Christian.

>  	return r;
>  }
>  
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index 698e5799e542..1082b957e7b1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -91,8 +91,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>  	struct amdgpu_job *job = to_amdgpu_job(s_job);
>  	struct amdgpu_task_info *ti;
>  	struct amdgpu_device *adev = ring->adev;
> -	int idx;
> -	int r;
> +	int idx, ret = 0;
>  
>  	if (!drm_dev_enter(adev_to_drm(adev), &idx)) {
>  		dev_info(adev->dev, "%s - device unplugged skipping recovery on scheduler:%s",
> @@ -141,8 +140,8 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>  		 * we'll fall back to full GPU reset.
>  		 */
>  		drm_sched_wqueue_stop(&ring->sched);
> -		r = amdgpu_ring_reset(ring, job->vmid);
> -		if (!r) {
> +		ret = amdgpu_ring_reset(ring, job->vmid);
> +		if (!ret) {
>  			if (amdgpu_ring_sched_ready(ring))
>  				drm_sched_stop(&ring->sched, s_job);
>  			atomic_inc(&ring->adev->gpu_reset_counter);
> @@ -170,9 +169,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>  		 */
>  		set_bit(AMDGPU_SKIP_COREDUMP, &reset_context.flags);
>  
> -		r = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);
> -		if (r)
> -			dev_err(adev->dev, "GPU Recovery Failed: %d\n", r);
> +		ret = amdgpu_device_gpu_recover(ring->adev, job, &reset_context);
> +		if (ret)
> +			dev_err(adev->dev, "GPU Recovery Failed: %d\n", ret);
>  	} else {
>  		drm_sched_suspend_timeout(&ring->sched);
>  		if (amdgpu_sriov_vf(adev))
> @@ -180,6 +179,9 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>  	}
>  
>  exit:
> +	if (!ret)
> +		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
> +
>  	drm_dev_exit(idx);
>  	return DRM_GPU_SCHED_STAT_NOMINAL;
>  }