drm/i915/guc: Flag an error if an engine reset fails

If GuC encounters an error during engine reset, the i915 driver
promotes to full GT reset. This includes an info message about why the
reset is happening. However, that is not treated as a failure by any
of the CI systems because resets are an expected occurrance during
testing. This kind of failure is a major problem and should never
happen. So, complain more loudly and make sure CI notices.

Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20211211065859.2248188-4-John.C.Harrison@Intel.com

Author: johnharr-intel

drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c

@@ -4033,11 +4033,12 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 					 const u32 *msg, u32 len)
 {
 	struct intel_engine_cs *engine;
+	struct intel_gt *gt = guc_to_gt(guc);
 	u8 guc_class, instance;
 	u32 reason;
 
 	if (unlikely(len != 3)) {
-		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		drm_err(&gt->i915->drm, "Invalid length %u", len);
 		return -EPROTO;
 	}
 
@@ -4047,12 +4048,19 @@ int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
 
 	engine = guc_lookup_engine(guc, guc_class, instance);
 	if (unlikely(!engine)) {
-		drm_err(&guc_to_gt(guc)->i915->drm,
+		drm_err(&gt->i915->drm,
 			"Invalid engine %d:%d", guc_class, instance);
 		return -EPROTO;
 	}
 
-	intel_gt_handle_error(guc_to_gt(guc), engine->mask,
+	/*
+	 * This is an unexpected failure of a hardware feature. So, log a real
+	 * error message not just the informational that comes with the reset.
+	 */
+	drm_err(&gt->i915->drm, "GuC engine reset request failed on %d:%d (%s) because 0x%08X",
+		guc_class, instance, engine->name, reason);
+
+	intel_gt_handle_error(gt, engine->mask,
 			      I915_ERROR_CAPTURE,
 			      "GuC failed to reset %s (reason=0x%08x)\n",
 			      engine->name, reason);