On 15/08/16 15:49, akash.goel@xxxxxxxxx wrote:
From: Sagar Arun Kamble <sagar.a.kamble@xxxxxxxxx>
Before capturing the GuC logs as a part of error state, there should be a
force log buffer flush action sent to GuC before proceeding with GPU reset
and re-initializing GUC. There could be some data in the log buffer which
is yet to be captured and those logs would be particularly useful to
understand that why the GPU reset was initiated.
v2:
- Avoid the wait via flush_work, to serialize against an ongoing log
buffer flush, from the error state capture path. (Chris)
- Rebase.
Signed-off-by: Sagar Arun Kamble <sagar.a.kamble@xxxxxxxxx>
Signed-off-by: Akash Goel <akash.goel@xxxxxxxxx>
---
drivers/gpu/drm/i915/i915_gpu_error.c | 2 ++
drivers/gpu/drm/i915/i915_guc_submission.c | 30 ++++++++++++++++++++++++++++++
drivers/gpu/drm/i915/intel_guc.h | 1 +
3 files changed, 33 insertions(+)
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 94297aa..b73c671 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1301,6 +1301,8 @@ static void i915_gem_capture_guc_log_buffer(struct drm_i915_private *dev_priv,
if (!dev_priv->guc.log.vma || (i915.guc_log_level < 0))
return;
+ i915_guc_flush_logs(dev_priv, false);
+
error->guc_log = i915_error_object_create(dev_priv,
dev_priv->guc.log.vma);
}
diff --git a/drivers/gpu/drm/i915/i915_guc_submission.c b/drivers/gpu/drm/i915/i915_guc_submission.c
index b8d6313..85df2f3 100644
--- a/drivers/gpu/drm/i915/i915_guc_submission.c
+++ b/drivers/gpu/drm/i915/i915_guc_submission.c
@@ -185,6 +185,16 @@ static int host2guc_logbuffer_flush_complete(struct intel_guc *guc)
return host2guc_action(guc, data, 1);
}
+static int host2guc_force_logbuffer_flush(struct intel_guc *guc)
+{
+ u32 data[2];
+
+ data[0] = HOST2GUC_ACTION_FORCE_LOG_BUFFER_FLUSH;
+ data[1] = 0;
+
+ return host2guc_action(guc, data, 2);
+}
+
/*
* Initialise, update, or clear doorbell data shared with the GuC
*
@@ -1536,6 +1546,26 @@ void i915_guc_capture_logs(struct drm_i915_private *dev_priv)
intel_runtime_pm_put(dev_priv);
}
+void i915_guc_flush_logs(struct drm_i915_private *dev_priv, bool can_wait)
+{
+ if (!i915.enable_guc_submission || (i915.guc_log_level < 0))
+ return;
+
+ /* First disable the interrupts, will be renabled afterwards */
+ gen9_disable_guc_interrupts(dev_priv);
+
+ /* Before initiating the forceful flush, wait for any pending/ongoing
+ * flush to complete otherwise forceful flush may not happen, but wait
+ * can't be done for some paths like error state capture in which case
+ * take a chance & directly attempt the forceful flush.
+ */
+ if (can_wait)
+ flush_work(&dev_priv->guc.log.flush_work);
+
+ /* Ask GuC to update the log buffer state */
+ host2guc_force_logbuffer_flush(&dev_priv->guc);
Should you just call i915_guc_capture_logs from here? Error capture
could also potentially benefit from it and you could remove it from the
debugfs patch then.
+}
+
void i915_guc_unregister(struct drm_i915_private *dev_priv)
{
if (!i915.enable_guc_submission)
diff --git a/drivers/gpu/drm/i915/intel_guc.h b/drivers/gpu/drm/i915/intel_guc.h
index 8598f38..d7eda42 100644
--- a/drivers/gpu/drm/i915/intel_guc.h
+++ b/drivers/gpu/drm/i915/intel_guc.h
@@ -182,6 +182,7 @@ int i915_guc_wq_check_space(struct drm_i915_gem_request *rq);
void i915_guc_submission_disable(struct drm_i915_private *dev_priv);
void i915_guc_submission_fini(struct drm_i915_private *dev_priv);
void i915_guc_capture_logs(struct drm_i915_private *dev_priv);
+void i915_guc_flush_logs(struct drm_i915_private *dev_priv, bool can_wait);
void i915_guc_register(struct drm_i915_private *dev_priv);
void i915_guc_unregister(struct drm_i915_private *dev_priv);
Regards,
Tvrtko
_______________________________________________
Intel-gfx mailing list
Intel-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/intel-gfx
