Unverified Commit 60439ac3 authored by Riana Tauro's avatar Riana Tauro Committed by Rodrigo Vivi
Browse files

drm/xe: Add a helper function to set recovery method 



Add a helper function to set recovery method. The recovery
method can be set before declaring the device wedged and sending the
drm wedged uevent. If no method is set, default unbind/re-bind method
will be set.

v2: fix documentation (Raag)

Signed-off-by: default avatarRiana Tauro <riana.tauro@intel.com>
Reviewed-by: default avatarRaag Jadav <raag.jadav@intel.com>
Link: https://lore.kernel.org/r/20250826063419.3022216-5-riana.tauro@intel.com


Signed-off-by: default avatarRodrigo Vivi <rodrigo.vivi@intel.com>
parent 90fdcf5f

drivers/gpu/drm/xe/xe_device.c

+21 −5
Original line number Diff line number Diff line
@@ -1176,13 +1176,26 @@ static void xe_device_wedged_fini(struct drm_device *drm, void *arg) 
 * is rebind/bus-reset.

 */



/**

 * xe_device_set_wedged_method - Set wedged recovery method

 * @xe: xe device instance

 * @method: recovery method to set

 *

 * Set wedged recovery method to be sent in drm wedged uevent.

 */

void xe_device_set_wedged_method(struct xe_device *xe, unsigned long method)

{

	xe->wedged.method = method;

}



/**

 * xe_device_declare_wedged - Declare device wedged

 * @xe: xe device instance

 *

 * This is a final state that can only be cleared with the recovery method

 * specified in the drm wedged uevent. The default recovery method is

 * re-probe (unbind + bind).

 * specified in the drm wedged uevent. The method can be set using

 * xe_device_set_wedged_method before declaring the device as wedged. If no method

 * is set, reprobe (unbind/re-bind) will be sent by default.

 *

 * In this state every IOCTL will be blocked so the GT cannot be used.

 * In general it will be called upon any critical error such as gt reset
@@ -1223,9 +1236,12 @@ void xe_device_declare_wedged(struct xe_device *xe) 
		xe_gt_declare_wedged(gt);



	if (xe_device_wedged(xe)) {

		/* If no wedge recovery method is set, use default */

		if (!xe->wedged.method)

			xe_device_set_wedged_method(xe, DRM_WEDGE_RECOVERY_REBIND |

						    DRM_WEDGE_RECOVERY_BUS_RESET);



		/* Notify userspace of wedged device */

		drm_dev_wedged_event(&xe->drm,

				     DRM_WEDGE_RECOVERY_REBIND | DRM_WEDGE_RECOVERY_BUS_RESET,

				     NULL);

		drm_dev_wedged_event(&xe->drm, xe->wedged.method, NULL);

	}

}

drivers/gpu/drm/xe/xe_device.h

+1 −0
Original line number Diff line number Diff line
@@ -187,6 +187,7 @@ static inline bool xe_device_wedged(struct xe_device *xe) 
	return atomic_read(&xe->wedged.flag);

}



void xe_device_set_wedged_method(struct xe_device *xe, unsigned long method);

void xe_device_declare_wedged(struct xe_device *xe);



struct xe_file *xe_file_get(struct xe_file *xef);

drivers/gpu/drm/xe/xe_device_types.h

+2 −0
Original line number Diff line number Diff line
@@ -541,6 +541,8 @@ struct xe_device { 
		atomic_t flag;

		/** @wedged.mode: Mode controlled by kernel parameter and debugfs */

		int mode;

		/** @wedged.method: Recovery method to be sent in the drm device wedged uevent */

		unsigned long method;

	} wedged;



	/** @bo_device: Struct to control async free of BOs */