drm/i915/uc: Inject probe errors into intel_uc_init_hw

Inject probe errors into intel_uc_init_hw to make sure we
correctly handle any uC initialization failure.

To avoid complains from CI about injected errors use
i915_probe_error to lower message level.

v4: rebased after moving hot fixes moved to separate patches

Signed-off-by: Michal Wajdeczko <michal.wajdeczko@intel.com>
Cc: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Chris Wilson <chris@chris-wilson.co.uk> #v1
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20190802184055.31988-6-michal.wajdeczko@intel.com

5 files changed, 35 insertions, 11 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 b4b508f19a1c..412892096daa 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1123,6 +1123,10 @@ int intel_guc_submission_enable(struct intel_guc *guc)
 	enum intel_engine_id id;
 	int err;
 
+	err = i915_inject_load_error(gt->i915, -ENXIO);
+	if (err)
+		return err;
+
 	/*
 	 * We're using GuC work items for submitting work through GuC. Since
 	 * we're coalescing multiple requests from a single context into a
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_huc.c b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
index d642b167a389..ef54053c5ef9 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_huc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_huc.c
@@ -139,6 +139,10 @@ int intel_huc_auth(struct intel_huc *huc)
 	GEM_BUG_ON(!intel_uc_fw_is_loaded(&huc->fw));
 	GEM_BUG_ON(intel_huc_is_authenticated(huc));
 
+	ret = i915_inject_load_error(gt->i915, -ENXIO);
+	if (ret)
+		goto fail;
+
 	ret = intel_guc_auth_huc(guc,
 				 intel_guc_ggtt_offset(guc, huc->rsa_data));
 	if (ret) {
@@ -158,13 +162,11 @@ int intel_huc_auth(struct intel_huc *huc)
 	}
 
 	huc->fw.status = INTEL_UC_FIRMWARE_RUNNING;
-
 	return 0;
 
 fail:
+	i915_probe_error(gt->i915, "HuC: Authentication failed %d\n", ret);
 	huc->fw.status = INTEL_UC_FIRMWARE_FAIL;
-
-	DRM_ERROR("HuC: Authentication failed %d\n", ret);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
index e5421c0b9a25..66d6e0775c23 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc.c
@@ -39,6 +39,10 @@ static int __intel_uc_reset_hw(struct intel_uc *uc)
 	int ret;
 	u32 guc_status;
 
+	ret = i915_inject_load_error(gt->i915, -ENXIO);
+	if (ret)
+		return ret;
+
 	ret = intel_reset_guc(gt);
 	if (ret) {
 		DRM_ERROR("Failed to reset GuC, ret = %d\n", ret);
@@ -205,6 +209,10 @@ static int guc_enable_communication(struct intel_guc *guc)
 
 	GEM_BUG_ON(guc_communication_enabled(guc));
 
+	ret = i915_inject_load_error(i915, -ENXIO);
+	if (ret)
+		return ret;
+
 	ret = intel_guc_ct_enable(&guc->ct);
 	if (ret)
 		return ret;
@@ -376,6 +384,10 @@ static int uc_init_wopcm(struct intel_uc *uc)
 	GEM_BUG_ON(!(size & GUC_WOPCM_SIZE_MASK));
 	GEM_BUG_ON(size & ~GUC_WOPCM_SIZE_MASK);
 
+	err = i915_inject_load_error(gt->i915, -ENXIO);
+	if (err)
+		return err;
+
 	mask = GUC_WOPCM_SIZE_MASK | GUC_WOPCM_SIZE_LOCKED;
 	err = intel_uncore_write_and_verify(uncore, GUC_WOPCM_SIZE, size, mask,
 					    size | GUC_WOPCM_SIZE_LOCKED);
@@ -502,7 +514,7 @@ err_out:
 	if (GEM_WARN_ON(ret == -EIO))
 		ret = -EINVAL;
 
-	dev_err(i915->drm.dev, "GuC initialization failed %d\n", ret);
+	i915_probe_error(i915, "GuC initialization failed %d\n", ret);
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
index 650ad6037b74..a3a22a26016c 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.c
@@ -383,6 +383,10 @@ static int uc_fw_xfer(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	u64 offset;
 	int ret;
 
+	ret = i915_inject_load_error(gt->i915, -ETIMEDOUT);
+	if (ret)
+		return ret;
+
 	intel_uncore_forcewake_get(uncore, FORCEWAKE_ALL);
 
 	/* Set the source address for the uCode */
@@ -443,8 +447,13 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	/* make sure the status was cleared the last time we reset the uc */
 	GEM_BUG_ON(intel_uc_fw_is_loaded(uc_fw));
 
+	err = i915_inject_load_error(gt->i915, -ENOEXEC);
+	if (err)
+		return err;
+
 	if (!intel_uc_fw_is_available(uc_fw))
 		return -ENOEXEC;
+
 	/* Call custom loader */
 	intel_uc_fw_ggtt_bind(uc_fw, gt);
 	err = uc_fw_xfer(uc_fw, gt, wopcm_offset, dma_flags);
@@ -464,13 +473,10 @@ int intel_uc_fw_upload(struct intel_uc_fw *uc_fw, struct intel_gt *gt,
 	return 0;
 
 fail:
+	i915_probe_error(gt->i915, "Failed to load %s firmware %s (%d)\n",
+			 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path,
+			 err);
 	uc_fw->status = INTEL_UC_FIRMWARE_FAIL;
-	DRM_DEBUG_DRIVER("%s fw load failed\n",
-			 intel_uc_fw_type_repr(uc_fw->type));
-
-	DRM_WARN("%s: Failed to load firmware %s (error %d)\n",
-		 intel_uc_fw_type_repr(uc_fw->type), uc_fw->path, err);
-
 	return err;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 5e87acc4b770..2436cd598e6e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1243,7 +1243,7 @@ int i915_gem_init_hw(struct drm_i915_private *i915)
 	/* We can't enable contexts until all firmware is loaded */
 	ret = intel_uc_init_hw(&gt->uc);
 	if (ret) {
-		DRM_ERROR("Enabling uc failed (%d)\n", ret);
+		i915_probe_error(i915, "Enabling uc failed (%d)\n", ret);
 		goto out;
 	}