Re: [PATCH v2 1/3] drm: Create an app info option for wedge events

[Rodrigo Vivi <rodrigo.vivi@intel.com>]

On Sun, May 11, 2025 at 07:47:43PM -0300, André Almeida wrote:
> When a device get wedged, it might be caused by a guilty application.
> For userspace, knowing which app was the cause can be useful for some
> situations, like for implementing a policy, logs or for giving a chance
> for the compositor to let the user know what app caused the problem.
> This is an optional argument, when `PID=-1` there's no information about
> the app caused the problem, or if any app was involved during the hang.
> 
> Sometimes just the PID isn't enough giving that the app might be already
> dead by the time userspace will try to check what was this PID's name,
> so to make the life easier also notify what's the app's name in the user
> event.
> 
> Signed-off-by: André Almeida <andrealmeid@igalia.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_device.c |  2 +-
>  drivers/gpu/drm/amd/amdgpu/amdgpu_job.c    |  2 +-
>  drivers/gpu/drm/drm_drv.c                  | 16 +++++++++++++---
>  drivers/gpu/drm/i915/gt/intel_reset.c      |  3 ++-
>  drivers/gpu/drm/xe/xe_device.c             |  3 ++-
>  include/drm/drm_device.h                   |  8 ++++++++
>  include/drm/drm_drv.h                      |  3 ++-
>  7 files changed, 29 insertions(+), 8 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> index 7f354cd532dc..c8a51418d0e7 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
> @@ -6216,7 +6216,7 @@ 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);
> +		drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
>  
>  	return r;
>  }
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index acb21fc8b3ce..a47b2eb301e5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -166,7 +166,7 @@ static enum drm_gpu_sched_stat amdgpu_job_timedout(struct drm_sched_job *s_job)
>  			if (amdgpu_ring_sched_ready(ring))
>  				drm_sched_start(&ring->sched, 0);
>  			dev_err(adev->dev, "Ring %s reset succeeded\n", ring->sched.name);
> -			drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE);
> +			drm_dev_wedged_event(adev_to_drm(adev), DRM_WEDGE_RECOVERY_NONE, NULL);
>  			goto exit;
>  		}
>  		dev_err(adev->dev, "Ring %s reset failure\n", ring->sched.name);
> diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
> index 3dc7acd56b1d..1816ef4251e7 100644
> --- a/drivers/gpu/drm/drm_drv.c
> +++ b/drivers/gpu/drm/drm_drv.c
> @@ -542,6 +542,7 @@ static const char *drm_get_wedge_recovery(unsigned int opt)
>   * drm_dev_wedged_event - generate a device wedged uevent
>   * @dev: DRM device
>   * @method: method(s) to be used for recovery
> + * @info: optional information about the guilty app
>   *
>   * This generates a device wedged uevent for the DRM device specified by @dev.
>   * Recovery @method\(s) of choice will be sent in the uevent environment as
> @@ -554,13 +555,14 @@ static const char *drm_get_wedge_recovery(unsigned int opt)
>   *
>   * Returns: 0 on success, negative error code otherwise.
>   */
> -int drm_dev_wedged_event(struct drm_device *dev, unsigned long method)
> +int drm_dev_wedged_event(struct drm_device *dev, unsigned long method,
> +			 struct drm_wedge_app_info *info)
>  {
>  	const char *recovery = NULL;
>  	unsigned int len, opt;
>  	/* Event string length up to 28+ characters with available methods */
> -	char event_string[32];
> -	char *envp[] = { event_string, NULL };
> +	char event_string[32], pid_string[15], comm_string[TASK_COMM_LEN];
> +	char *envp[] = { event_string, pid_string, comm_string, NULL };
>  
>  	len = scnprintf(event_string, sizeof(event_string), "%s", "WEDGED=");
>  
> @@ -582,6 +584,14 @@ int drm_dev_wedged_event(struct drm_device *dev, unsigned long method)
>  	drm_info(dev, "device wedged, %s\n", method == DRM_WEDGE_RECOVERY_NONE ?
>  		 "but recovered through reset" : "needs recovery");
>  
> +	if (info) {
> +		snprintf(pid_string, sizeof(pid_string), "PID=%u", info->pid);
> +		snprintf(comm_string, sizeof(comm_string), "APP=%s", info->comm);
> +	} else {
> +		snprintf(pid_string, sizeof(pid_string), "%s", "PID=-1");
> +		snprintf(comm_string, sizeof(comm_string), "%s", "APP=none");
> +	}
> +
>  	return kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, envp);
>  }
>  EXPORT_SYMBOL(drm_dev_wedged_event);
> diff --git a/drivers/gpu/drm/i915/gt/intel_reset.c b/drivers/gpu/drm/i915/gt/intel_reset.c
> index dbdcfe130ad4..ba1d8fdc3c7b 100644
> --- a/drivers/gpu/drm/i915/gt/intel_reset.c
> +++ b/drivers/gpu/drm/i915/gt/intel_reset.c
> @@ -1448,7 +1448,8 @@ static void intel_gt_reset_global(struct intel_gt *gt,
>  		kobject_uevent_env(kobj, KOBJ_CHANGE, reset_done_event);
>  	else
>  		drm_dev_wedged_event(&gt->i915->drm,
> -				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET);
> +				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET,
> +				     NULL);

(For future) I believe we can later modify the gt_reset handles here
to get ctx->id when we are coming from reset paths with context and
NULL when we don't have pid.

Perhaps one possibility could be strings to make this flexible
'pid:%d'

'path:debugfs'

But just a brainstorm kind of idea... not a strong feeling or need.

>  }
>  
>  /**
> diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
> index c02c4c4e9412..f329613e061f 100644
> --- a/drivers/gpu/drm/xe/xe_device.c
> +++ b/drivers/gpu/drm/xe/xe_device.c
> @@ -1168,7 +1168,8 @@ void xe_device_declare_wedged(struct xe_device *xe)
>  
>  		/* Notify userspace of wedged device */
>  		drm_dev_wedged_event(&xe->drm,
> -				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET);
> +				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET,
> +				     NULL);

similarly here, for the paths where we come to the wedge declaration from
exeq_queue, we could get q->vm->xef->pid...

But again, no blocker from my side. For both i915 and Xe:

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

>  	}
>  
>  	for_each_gt(gt, xe, id)
> diff --git a/include/drm/drm_device.h b/include/drm/drm_device.h
> index e2f894f1b90a..b87401d5079e 100644
> --- a/include/drm/drm_device.h
> +++ b/include/drm/drm_device.h
> @@ -30,6 +30,14 @@ struct pci_controller;
>  #define DRM_WEDGE_RECOVERY_REBIND	BIT(1)	/* unbind + bind driver */
>  #define DRM_WEDGE_RECOVERY_BUS_RESET	BIT(2)	/* unbind + reset bus device + bind */
>  
> +/**
> + * struct drm_wedge_app_info - information about the guilty app of a wedge dev
> + */
> +struct drm_wedge_app_info {
> +	pid_t pid;
> +	char *comm;
> +};
> +
>  /**
>   * enum switch_power_state - power state of drm device
>   */
> diff --git a/include/drm/drm_drv.h b/include/drm/drm_drv.h
> index a43d707b5f36..8fc6412a6345 100644
> --- a/include/drm/drm_drv.h
> +++ b/include/drm/drm_drv.h
> @@ -482,7 +482,8 @@ void drm_put_dev(struct drm_device *dev);
>  bool drm_dev_enter(struct drm_device *dev, int *idx);
>  void drm_dev_exit(int idx);
>  void drm_dev_unplug(struct drm_device *dev);
> -int drm_dev_wedged_event(struct drm_device *dev, unsigned long method);
> +int drm_dev_wedged_event(struct drm_device *dev, unsigned long method,
> +			 struct drm_wedge_app_info *info);
>  
>  /**
>   * drm_dev_is_unplugged - is a DRM device unplugged
> -- 
> 2.49.0
>