[Intel-gfx] [RFC PATCH 69/97] drm/i915/guc: Handle engine reset failure notification

[Matthew Brost]

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

Signed-off-by: Matthew Brost <matthew.brost at intel.com>
Signed-off-by: Fernando Pacheco <fernando.pacheco at intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc.h        |  2 +
 drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c     |  6 +++
 .../gpu/drm/i915/gt/uc/intel_guc_submission.c | 43 +++++++++++++++++++
 3 files changed, 51 insertions(+)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index a2abe1c422e3..e118d8217e77 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -265,6 +265,8 @@ 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);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 9c84b2ba63a8..d5b326d4e250 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -947,6 +947,12 @@ static int ct_process_request(struct intel_guc_ct *ct, struct ct_incoming_msg *r
 			CT_ERROR(ct, "context reset notification failed %x %*ph\n",
 				  action, 4 * len, payload);
 		break;
+	case INTEL_GUC_ACTION_ENGINE_FAILURE_NOTIFICATION:
+		ret = intel_guc_engine_failure_process_msg(guc, payload, len);
+		if (unlikely(ret))
+			CT_ERROR(ct, "engine failure handler failed %x %*ph\n",
+				  action, 4 * len, payload);
+		break;
 	default:
 		ret = -EOPNOTSUPP;
 		break;
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 940017495731..22f17a055b21 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -2227,6 +2227,49 @@ 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_dbg(&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_dbg(&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_log_submission_info(struct intel_guc *guc,
 				   struct drm_printer *p)
 {
-- 
2.28.0