[RFC v2 5/6] drm/i915/uc: Use -EIO code for GuC initialization failures
Michal Wajdeczko
michal.wajdeczko at intel.com
Fri Jan 11 10:02:34 UTC 2019
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 | 17 ++++++++++-------
drivers/gpu/drm/i915/intel_uc.c | 12 +++---------
2 files changed, 13 insertions(+), 16 deletions(-)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index bb67d144d5a3..6893a69add2e 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -5443,8 +5443,10 @@ 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)
@@ -5497,7 +5499,8 @@ 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);
@@ -5514,17 +5517,17 @@ 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)
+ if (ret != -EIO) {
+ intel_uc_fini_misc(dev_priv);
i915_gem_cleanup_userptr(dev_priv);
+ }
if (ret == -EIO) {
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 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_uc.c b/drivers/gpu/drm/i915/intel_uc.c
index 3eea146b11b7..dc613aaf39c1 100644
--- a/drivers/gpu/drm/i915/intel_uc.c
+++ b/drivers/gpu/drm/i915/intel_uc.c
@@ -433,16 +433,10 @@ int intel_uc_init_hw(struct drm_i915_private *i915)
guc_capture_load_err_log(guc);
err_out:
__uc_sanitize(i915);
-
- /*
- * 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;
+
+ /* We want to disable GPU but keep KMS alive */
+ return -EIO;
}
void intel_uc_fini_hw(struct drm_i915_private *i915)
--
2.19.2
More information about the Intel-gfx-trybot
mailing list