From 7ce22039be2570828a8758545303247c0a57b0c5 Mon Sep 17 00:00:00 2001
From: John Harrison <John.C.Harrison@Intel.com>
Date: Fri, 10 Dec 2021 22:58:58 -0800
Subject: drm/i915/guc: Flag an error if an engine reset fails
Git-commit: fb3965f9ae28b83290e5b5431a77aace66071ca1
Patch-mainline: v5.17-rc1
References: jsc#PED-1166 jsc#PED-1168 jsc#PED-1170 jsc#PED-1218 jsc#PED-1220 jsc#PED-1222 jsc#PED-1223 jsc#PED-1225

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
Acked-by: Patrik Jakobsson <pjakobsson@suse.de>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

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 30933d59287c..e7517206af82 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/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);
-- 
2.38.1