[Intel-gfx] [PATCH v8 09/12] drm/i915/uc: Use correct error code for GuC initialization failure

[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.

v2: don't allow -EIO from uc_init
    don't call uc_fini[_misc] on -EIO
    mark guc fw as failed on hw init failure
    prepare uc_fini_hw to run after earlier -EIO

v3: update comments (Sagar)
    use sanitize functions on failure in init_hw (Michal)
    and also sanitize guc/huc fw in fini_hw (Michal)

v4: rebase
v5: rebase

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: Sagar Arun Kamble <sagar.a.kamble at intel.com>
Reviewed-by: Sagar Arun Kamble <sagar.a.kamble at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c    | 17 ++++++++++-------
 drivers/gpu/drm/i915/intel_guc.h   |  5 +++++
 drivers/gpu/drm/i915/intel_uc.c    | 15 +++++++++++----
 drivers/gpu/drm/i915/intel_uc_fw.h |  5 +++++
 4 files changed, 31 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index decda1a..532246a 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5444,8 +5444,10 @@ 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)
@@ -5492,7 +5494,8 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	i915_gem_contexts_lost(dev_priv);
 	i915_gem_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);
@@ -5506,15 +5509,15 @@ int i915_gem_init(struct drm_i915_private *dev_priv)
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 	mutex_unlock(&dev_priv->drm.struct_mutex);
 
-	intel_uc_fini_misc(dev_priv);
-
-	if (ret != -EIO)
+	if (ret != -EIO) {
+		intel_uc_fini_misc(dev_priv);
 		i915_gem_cleanup_userptr(dev_priv);
+	}
 
 	if (ret == -EIO) {
 		/*
-		 * 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 initialization 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_terminally_wedged(&dev_priv->gpu_error)) {
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index f1265e1..c587068 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -176,6 +176,11 @@ static inline int intel_guc_sanitize(struct intel_guc *guc)
 	return 0;
 }
 
+static inline bool intel_guc_is_loaded(struct intel_guc *guc)
+{
+	return intel_uc_fw_is_loaded(&guc->fw);
+}
+
 static inline void intel_guc_enable_msg(struct intel_guc *guc, u32 mask)
 {
 	spin_lock_irq(&guc->irq_lock);
diff --git a/drivers/gpu/drm/i915/intel_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 0439966..7862731 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -332,6 +332,8 @@ static void __uc_sanitize(struct drm_i915_private *i915)
 	intel_huc_sanitize(huc);
 	intel_guc_sanitize(guc);
 
+	GEM_BUG_ON(intel_guc_is_loaded(guc));
+
 	__intel_uc_reset_hw(i915);
 }
 
@@ -420,11 +422,13 @@ int intel_uc_init_hw(struct drm_i915_private *dev_priv)
 	 * 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(dev_priv->drm.dev, "GuC initialization failed %d\n", ret);
-	return ret;
+
+	/* Sanitize GuC/HuC to avoid clean-up on wedged */
+	__uc_sanitize(dev_priv);
+
+	/* We want to disable GPU submission but keep KMS alive */
+	return -EIO;
 }
 
 void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
@@ -436,6 +440,9 @@ void intel_uc_fini_hw(struct drm_i915_private *dev_priv)
 
 	GEM_BUG_ON(!HAS_GUC(dev_priv));
 
+	if (!intel_guc_is_loaded(guc))
+		return;
+
 	if (USES_GUC_SUBMISSION(dev_priv))
 		intel_guc_submission_disable(guc);
 
diff --git a/drivers/gpu/drm/i915/intel_uc_fw.h b/drivers/gpu/drm/i915/intel_uc_fw.h
index dc33b12..77ad2aa 100644
--- a/drivers/gpu/drm/i915/intel_uc_fw.h
+++ b/drivers/gpu/drm/i915/intel_uc_fw.h
@@ -121,6 +121,11 @@ static inline void intel_uc_fw_sanitize(struct intel_uc_fw *uc_fw)
 		uc_fw->load_status = INTEL_UC_FIRMWARE_PENDING;
 }
 
+static inline bool intel_uc_fw_is_loaded(struct intel_uc_fw *uc_fw)
+{
+	return uc_fw->load_status == INTEL_UC_FIRMWARE_SUCCESS;
+}
+
 /**
  * intel_uc_fw_get_upload_size() - Get size of firmware needed to be uploaded.
  * @uc_fw: uC firmware.
-- 
1.9.1