[PATCH v2 1/2] drm/i915/uc: Use -EIO code for GuC initialization failures

[Michal Wajdeczko]

Since commit 6ca9a2beb54a ("drm/i915: Unwind i915_gem_init() failure")
we believed that we correctly handle all errors encountered during
GuC initialization, including special one that indicates request to
run driver with disabled GPU submission (-EIO).

Unfortunately since commit 121981fafe69 ("drm/i915/guc: Combine
enable_guc_loading|submission modparams") we stopped using that
error code to avoid unwanted fallback to execlist submission mode.

In result any GuC initialization failure was treated as non-recoverable
error leading to driver load abort, so we could not even read related
GuC error log to investigate cause of the problem.

Fix that by always returning -EIO on uC hardware related failure.

Signed-off-by: Michal Wajdeczko <michal.wajdeczko at intel.com>
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Michal Winiarski <michal.winiarski at intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio at intel.com>
Cc: Sujaritha Sundaresan <sujaritha.sundaresan at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 14 ++++++++------
 drivers/gpu/drm/i915/intel_uc.c | 11 +++--------
 2 files changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 1a684b7e8c09..9086dd58305c 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -4845,8 +4845,10 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	intel_init_gt_powersave(dev_priv);
 
 	ret = intel_uc_init(dev_priv);
-	if (ret)
+	if (ret) {
+		GEM_BUG_ON(ret == -EIO);
 		goto err_pm;
+	}
 
 	ret = i915_gem_init_hw(dev_priv);
 	if (ret)
@@ -4899,7 +4901,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	mutex_lock(&dev_priv->drm.struct_mutex);
 	intel_uc_fini_hw(dev_priv);
 err_uc_init:
-	intel_uc_fini(dev_priv);
+	if (ret != -EIO)
+		intel_uc_fini(dev_priv);
 err_pm:
 	if (ret != -EIO) {
 		intel_cleanup_gt_powersave(dev_priv);
@@ -4916,9 +4919,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
 err_uc_misc:
-	intel_uc_fini_misc(dev_priv);
-
 	if (ret != -EIO) {
+		intel_uc_fini_misc(dev_priv);
 		i915_gem_cleanup_userptr(dev_priv);
 		i915_timelines_fini(dev_priv);
 	}
@@ -4927,8 +4929,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 		mutex_lock(&dev_priv->drm.struct_mutex);
 
 		/*
-		 * Allow engine initialisation to fail by marking the GPU as
-		 * wedged. But we only want to do this where the GPU is angry,
+		 * Allow engines or uC initialisation to fail by marking the GPU
+		 * as wedged. But we only want to do this when the GPU is angry,
 		 * for all other failure, such as an allocation failure, bail.
 		 */
 		if (!i915_reset_failed(dev_priv)) {
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 2d360d53757f..0d35e9afd745 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -423,15 +423,10 @@ int intel_uc_init_hw(struct drm_i915_private *i915)
 err_log_capture:
 	guc_capture_load_err_log(guc);
 err_out:
-	/*
-	 * Note that there is no fallback as either user explicitly asked for
-	 * the GuC or driver default option was to run with the GuC enabled.
-	 */
-	if (GEM_WARN_ON(ret == -EIO))
-		ret = -EINVAL;
-
 	dev_err(i915->drm.dev, "GuC initialization failed %d\n", ret);
-	return ret;
+
+	/* Mark GPU as wedged, but keep KMS alive. */
+	return -EIO;
 }
 
 void intel_uc_fini_hw(struct drm_i915_private *i915)
-- 
2.19.2