drm/i915/guc: Handle engine reset failure notification

GuC will notify the driver, via G2H, if it fails to
reset an engine. We recover by resorting to a full GPU
reset.

v2:
 (John Harrison):
  - s/drm_dbg/drm_err
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Fernando Pacheco <fernando.pacheco@intel.com>
Reviewed-by: John Harrison <John.C.Harrison@Intel.com>
Signed-off-by: John Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20210727002348.97202-14-matthew.brost@intel.com

drivers/gpu/drm/i915/gt/uc/intel_guc.h

@@ -271,6 +271,8 @@ int intel_guc_sched_done_process_msg(struct intel_guc *guc,
 				     const u32 *msg, u32 len);
 int intel_guc_context_reset_process_msg(struct intel_guc *guc,
 					const u32 *msg, u32 len);
+int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
+					 const u32 *msg, u32 len);
 
 void intel_guc_submission_reset_prepare(struct intel_guc *guc);
 void intel_guc_submission_reset(struct intel_guc *guc, bool stalled);

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

@@ -987,6 +987,9 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 	case INTEL_GUC_ACTION_CONTEXT_RESET_NOTIFICATION:
 		ret = intel_guc_context_reset_process_msg(guc, payload, len);
 		break;
+	case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION:
+		ret = intel_guc_engine_failure_process_msg(guc, payload, len);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;

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

@@ -2237,6 +2237,49 @@ int intel_guc_context_reset_process_msg(struct intel_guc *guc,
 	return 0;
 }
 
+static struct intel_engine_cs *
+guc_lookup_engine(struct intel_guc *guc, u8 guc_class, u8 instance)
+{
+	struct intel_gt *gt = guc_to_gt(guc);
+	u8 engine_class = guc_class_to_engine_class(guc_class);
+
+	/* Class index is checked in class converter */
+	GEM_BUG_ON(instance > MAX_ENGINE_INSTANCE);
+
+	return gt->engine_class[engine_class][instance];
+}
+
+int intel_guc_engine_failure_process_msg(struct intel_guc *guc,
+					 const u32 *msg, u32 len)
+{
+	struct intel_engine_cs *engine;
+	u8 guc_class, instance;
+	u32 reason;
+
+	if (unlikely(len != 3)) {
+		drm_err(&guc_to_gt(guc)->i915->drm, "Invalid length %u", len);
+		return -EPROTO;
+	}
+
+	guc_class = msg[0];
+	instance = msg[1];
+	reason = msg[2];
+
+	engine = guc_lookup_engine(guc, guc_class, instance);
+	if (unlikely(!engine)) {
+		drm_err(&guc_to_gt(guc)->i915->drm,
+			"Invalid engine %d:%d", guc_class, instance);
+		return -EPROTO;
+	}
+
+	intel_gt_handle_error(guc_to_gt(guc), engine->mask,
+			      I915_ERROR_CAPTURE,
+			      "GuC failed to reset %s (reason=0x%08x)\n",
+			      engine->name, reason);
+
+	return 0;
+}
+
 void intel_guc_submission_print_info(struct intel_guc *guc,
 				     struct drm_printer *p)
 {