[Intel-xe] [PATCH v3 1/2] drm/xe: Notify Userspace when engine reset fails

Himal Prasad Ghimiray himal.prasad.ghimiray at intel.com
Tue Jul 18 12:03:21 UTC 2023


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:
-Add NULL check for xe_gt_hw_engine return(Aravind)
-Arrange variables in Christmas tree order(Tejas)
-Check GUC_GSC_OTHER_CLASS(Tejas)

v3:
- Rebase
- Remove notification for engine reset failure (Rodrigo)

Cc: Aravind Iddamsetty <aravind.iddamsetty at intel.com>
Cc: Tejas Upadhyay <tejas.upadhyay at iddntel.com>
Cc: Rodrigo Vivi <rodrigo.vivi at intel.com>
Reviewed-by: Badal Nilawar <badal.nilawar at intel.com>
Signed-off-by: Himal Prasad Ghimiray<himal.prasad.ghimiray at intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c | 18 ++++++++++++++++++
 include/uapi/drm/xe_drm.h  |  8 ++++++++
 2 files changed, 26 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index a21d44bfe9e8..1db4d610f2fd 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/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"
@@ -500,6 +501,20 @@ static int do_gt_restart(struct xe_gt *gt)
 	return 0;
 }
 
+static void xe_uevent_gt_reset_failure(struct xe_device *xe, u8 id)
+{
+	char *reset_event[5];
+
+	reset_event[0] = XE_RESET_FAILED_UEVENT "=1";
+	reset_event[1] = "RESET_ENABLED=1";
+	reset_event[2] = "RESET_UNIT=gt";
+	reset_event[3] = kasprintf(GFP_KERNEL, "RESET_ID=%d", id);
+	reset_event[4] = NULL;
+	kobject_uevent_env(&xe->drm.primary->kdev->kobj, KOBJ_CHANGE, reset_event);
+
+	kfree(reset_event[3]);
+}
+
 static int gt_reset(struct xe_gt *gt)
 {
 	int err;
@@ -549,6 +564,9 @@ 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(gt_to_xe(gt), gt->info.id);
+
 	return err;
 }
 
diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 347351a8f618..0865601352b2 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -16,6 +16,14 @@ extern "C" {
  * subject to backwards-compatibility constraints.
  */
 
+/*
+ * Uevents generated by xe on it's device node.
+ *
+ * XE_RESET_FAILED_UEVENT - Event is generated when attempt to reset engine
+ *	or gt fails. The value supplied with the event is always 1.
+ */
+#define XE_RESET_FAILED_UEVENT "RESET_FAILED"
+
 /**
  * struct xe_user_extension - Base class for defining a chain of extensions
  *
-- 
2.25.1



More information about the Intel-xe mailing list