drm: Create a task info option for wedge events

When a device get wedged, it might be caused by a guilty application.
For userspace, knowing which task was involved 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 task was involved in the
problem.  This is an optional argument, when the task info is not
available, the PID and TASK string won't appear in the event string.

Sometimes just the PID isn't enough giving that the task 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 task's name in the user
event.

Acked-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Krzysztof Karas <krzysztof.karas@intel.com>
Reviewed-by: Raag Jadav <raag.jadav@intel.com>
Acked-by: Christian König <christian.koenig@amd.com>
Link: https://lore.kernel.org/r/20250617124949.2151549-4-andrealmeid@igalia.com
Signed-off-by: André Almeida <andrealmeid@igalia.com>

drivers/gpu/drm/amd/amdgpu/amdgpu_device.c

@@ -6364,7 +6364,7 @@ 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;
 }

drivers/gpu/drm/amd/amdgpu/amdgpu_job.c

@@ -164,7 +164,7 @@ 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);

drivers/gpu/drm/drm_drv.c

@@ -35,6 +35,7 @@
 #include <linux/moduleparam.h>
 #include <linux/mount.h>
 #include <linux/pseudo_fs.h>
+#include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/sprintf.h>
 #include <linux/srcu.h>
@@ -539,10 +540,15 @@ static const char *drm_get_wedge_recovery(unsigned int opt)
 	}
 }
 
+#define WEDGE_STR_LEN	32
+#define PID_STR_LEN	15
+#define COMM_STR_LEN	(TASK_COMM_LEN + 5)
+
 /**
  * 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 task
  *
  * 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
@@ -555,13 +561,13 @@ 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_task_info *info)
 {
+	char event_string[WEDGE_STR_LEN], pid_string[PID_STR_LEN], comm_string[COMM_STR_LEN];
+	char *envp[] = { event_string, NULL, NULL, NULL };
 	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 };
 
 	len = scnprintf(event_string, sizeof(event_string), "%s", "WEDGED=");
 
@@ -583,6 +589,13 @@ 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 && (info->comm[0] != '\0') && (info->pid >= 0)) {
+		snprintf(pid_string, sizeof(pid_string), "PID=%u", info->pid);
+		snprintf(comm_string, sizeof(comm_string), "TASK=%s", info->comm);
+		envp[1] = pid_string;
+		envp[2] = comm_string;
+	}
+
 	return kobject_uevent_env(&dev->primary->kdev->kobj, KOBJ_CHANGE, envp);
 }
 EXPORT_SYMBOL(drm_dev_wedged_event);

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);
 }
 
 /**

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);
 	}
 
 	for_each_gt(gt, xe, id)

include/drm/drm_device.h

@@ -5,6 +5,7 @@
 #include <linux/kref.h>
 #include <linux/mutex.h>
 #include <linux/idr.h>
+#include <linux/sched.h>
 
 #include <drm/drm_mode_config.h>
 
@@ -30,6 +31,14 @@ 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_task_info - information about the guilty task of a wedge dev
+ */
+struct drm_wedge_task_info {
+	pid_t pid;
+	char comm[TASK_COMM_LEN];
+};
+
 /**
  * enum switch_power_state - power state of drm device
  */

include/drm/drm_drv.h

@@ -487,7 +487,8 @@ 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_task_info *info);
 
 /**
  * drm_dev_is_unplugged - is a DRM device unplugged