drm/xe: Notify Userspace when gt reset fails

Send uevent in case of gt reset failure. This intimation can be used by
userspace monitoring tool to do the device level reset/reboot
when GT reset fails. udevadm can be used to monitor the uevents.

v2:
- Support only gt failure notification (Rodrigo)

v3
- Rectify the comments in header file.

v4
- Use pci kobj instead of drm kobj for notification.(Rodrigo)
- Cleanup (Badal)

v5
- Add tile id and gt id as additional info provided by uevent.
- Provide code documentation for the uevent. (Rodrigo)

Cc: Aravind Iddamsetty <aravind.iddamsetty@intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay@intel.com>
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Badal Nilawar <badal.nilawar@intel.com>
Signed-off-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

drivers/gpu/drm/xe/xe_gt.c

@@ -8,6 +8,7 @@
 #include <linux/minmax.h>
 
 #include <drm/drm_managed.h>
+#include <drm/xe_drm.h>
 
 #include "regs/xe_gt_regs.h"
 #include "xe_bb.h"
@@ -499,6 +500,20 @@ static int do_gt_restart(struct xe_gt *gt)
 	return 0;
 }
 
+static void xe_uevent_gt_reset_failure(struct pci_dev *pdev, u8 tile_id, u8 gt_id)
+{
+	char *reset_event[4];
+
+	reset_event[0] = XE_RESET_FAILED_UEVENT "=NEEDS_RESET";
+	reset_event[1] = kasprintf(GFP_KERNEL, "TILE_ID=%d", tile_id);
+	reset_event[2] = kasprintf(GFP_KERNEL, "GT_ID=%d", gt_id);
+	reset_event[3] = NULL;
+	kobject_uevent_env(&pdev->dev.kobj, KOBJ_CHANGE, reset_event);
+
+	kfree(reset_event[1]);
+	kfree(reset_event[2]);
+}
+
 static int gt_reset(struct xe_gt *gt)
 {
 	int err;
@@ -549,6 +564,10 @@ static int gt_reset(struct xe_gt *gt)
 	xe_device_mem_access_put(gt_to_xe(gt));
 	xe_gt_err(gt, "reset failed (%pe)\n", ERR_PTR(err));
 
+	/* Notify userspace about gt reset failure */
+	xe_uevent_gt_reset_failure(to_pci_dev(gt_to_xe(gt)->drm.dev),
+				   gt_to_tile(gt)->id, gt->info.id);
+
 	return err;
 }
 

include/uapi/drm/xe_drm.h

@@ -16,6 +16,16 @@ extern "C" {
  * subject to backwards-compatibility constraints.
  */
 
+/**
+ * DOC: uevent generated by xe on it's pci node.
+ *
+ * XE_RESET_FAILED_UEVENT - Event is generated when attempt to reset gt
+ * fails. The value supplied with the event is always "NEEDS_RESET".
+ * Additional information supplied is tile id and gt id of the gt unit for
+ * which reset has failed.
+ */
+#define XE_RESET_FAILED_UEVENT "DEVICE_STATUS"
+
 /**
  * struct xe_user_extension - Base class for defining a chain of extensions
  *