Re: [PATCH v4 4/4] drm/amdgpu: Signal GPU_RESET EVENTFD notifications

["Christian König" <christian.koenig@amd.com>]

On 7/14/26 10:02, Srinivasan Shanmugam wrote:
> Signal GPU_RESET EVENTFD subscriptions after successful GPU reset
> completion.
> 
> GPU reset notifications allow userspace to observe that GPU recovery has
> completed and the device is operational again.
> 
> GPU_RESET is a device-scoped event, so no queue object is used. All
> processes that subscribed to GPU_RESET on the device are notified.
> 
> EVENTFD remains notification-only.
> 
> v2:
> - Move GPU_RESET EVENTFD signaling to the path that confirms a real
>   GPU hardware reset occurred.
> - Notify only after successful hardware reset completion.
> - Do not signal reset-skip or recovery-only paths.
> 
> Cc: Alex Deucher <alexander.deucher@amd.com>
> Cc: Christian König <christian.koenig@amd.com>
> Signed-off-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
> Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 51 +++++++++++++++++++++-
>  1 file changed, 49 insertions(+), 2 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index c924a55fd16f..15aaceae13d1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -5390,15 +5390,43 @@ static void amdgpu_device_halt_activities(struct amdgpu_device *adev,
>  	}
>  }
>  
> +/*
> + * Signal GPU_RESET EVENTFD subscriptions for all open DRM files.
> + *
> + * GPU reset is a device-wide event rather than being associated with a
> + * specific user queue. Notify every process that subscribed to the
> + * GPU_RESET event on this device.
> + */
> +static void amdgpu_device_eventfd_signal_gpu_reset(struct amdgpu_device *adev)
> +{
> +	struct drm_device *ddev = adev_to_drm(adev);
> +	struct drm_file *file;
> +
> +	mutex_lock(&ddev->filelist_mutex);
> +
> +	list_for_each_entry(file, &ddev->filelist, lhead) {

Is it allowed to grab the filelist_mutex in a device reset?

@Vitaly another one we need to handle in our lockdep checks. Lowest priority, but please put that on your TODO list.

Thanks,
Christian.

> +		struct amdgpu_fpriv *fpriv = file->driver_priv;
> +
> +		if (fpriv)
> +			amdgpu_eventfd_signal(&fpriv->eventfd_mgr,
> +					      DRM_AMDGPU_EVENT_TYPE_GPU_RESET,
> +					      NULL);
> +	}
> +
> +	mutex_unlock(&ddev->filelist_mutex);
> +}
> +
>  static int amdgpu_device_asic_reset(struct amdgpu_device *adev,
>  			      struct list_head *device_list,
>  			      struct amdgpu_reset_context *reset_context)
>  {
>  	struct amdgpu_device *tmp_adev = NULL;
> +	bool need_full_reset, skip_hw_reset;
>  	int retry_limit = AMDGPU_MAX_RETRY_LIMIT;
>  	int r = 0;
>  
> -retry:	/* Rest of adevs pre asic reset from XGMI hive. */
> +retry:
> +	/* Rest of adevs pre asic reset from XGMI hive. */
>  	list_for_each_entry(tmp_adev, device_list, reset_list) {
>  		r = amdgpu_device_pre_asic_reset(tmp_adev, reset_context);
>  		/*TODO Should we stop ?*/
> @@ -5430,10 +5458,30 @@ static int amdgpu_device_asic_reset(struct amdgpu_device *adev,
>  		}
>  		if (r)
>  			adev->asic_reset_res = r;
> +		else
> +			amdgpu_device_eventfd_signal_gpu_reset(adev);
>  	} else {
> +		/*
> +		 * Save the reset decision before amdgpu_do_asic_reset(),
> +		 * which may clear AMDGPU_NEED_FULL_RESET before returning.
> +		 */
> +		need_full_reset =
> +			test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
> +		skip_hw_reset =
> +			test_bit(AMDGPU_SKIP_HW_RESET, &reset_context->flags);
> +
>  		r = amdgpu_do_asic_reset(device_list, reset_context);
>  		if (r && r == -EAGAIN)
>  			goto retry;
> +
> +		/*
> +		 * Notify only after a real hardware reset completed.
> +		 * Do not notify recovery-only or reset-skip paths.
> +		 */
> +		if (!r && need_full_reset && !skip_hw_reset) {
> +			list_for_each_entry(tmp_adev, device_list, reset_list)
> +				amdgpu_device_eventfd_signal_gpu_reset(tmp_adev);
> +		}
>  	}
>  
>  	list_for_each_entry(tmp_adev, device_list, reset_list) {
> @@ -5530,7 +5578,6 @@ static void amdgpu_device_gpu_resume(struct amdgpu_device *adev,
>  	}
>  }
>  
> -
>  /**
>   * amdgpu_device_gpu_recover - reset the asic and recover scheduler
>   *