On 6/13/2025 8:02 PM, [email protected] wrote:
From: John Harrison <[email protected]>
There is a sporadic failure to enable CTs ocurring in CI on one
specific machine that can't be reproduced locally. The driver already
supports dumping out a whole bunch of GuC related debug info on such a
failure but only when the verbose GuC debug config option is enabled.
It would be preferable to not enable all the verbose debug output. So
just bump the CT_DEAD code to regular I915 debug level rather than GUC
debug level, at least temporarily for CI.
To prevent excessive spam in other parts of CI, also add a check
against doing a CT_DEAD dump during an error injection test. No point
in dumping large amounts of 'why did this fail' info when the fail is
deliberately induced.
v2: Revert accidentally enabling some other verbose debug output.
Signed-off-by: John Harrison <[email protected]>
Reviewed-by: Daniele Ceraolo Spurio <[email protected]>
Daniele
---
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c | 11 +++++++----
drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h | 2 +-
2 files changed, 8 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
index 0d5197c0824a9..380a11c92d632 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.c
@@ -13,7 +13,7 @@
#include "intel_guc_ct.h"
#include "intel_guc_print.h"
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
enum {
CT_DEAD_ALIVE = 0,
CT_DEAD_SETUP,
@@ -144,7 +144,7 @@ void intel_guc_ct_init_early(struct intel_guc_ct *ct)
spin_lock_init(&ct->requests.lock);
INIT_LIST_HEAD(&ct->requests.pending);
INIT_LIST_HEAD(&ct->requests.incoming);
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
INIT_WORK(&ct->dead_ct_worker, ct_dead_ct_worker_func);
#endif
INIT_WORK(&ct->requests.worker, ct_incoming_request_worker_func);
@@ -373,7 +373,7 @@ int intel_guc_ct_enable(struct intel_guc_ct *ct)
ct->enabled = true;
ct->stall_time = KTIME_MAX;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
ct->dead_ct_reported = false;
ct->dead_ct_reason = CT_DEAD_ALIVE;
#endif
@@ -1377,7 +1377,7 @@ void intel_guc_ct_print_info(struct intel_guc_ct *ct,
ct->ctbs.recv.desc->tail);
}
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
static void ct_dead_ct_worker_func(struct work_struct *w)
{
struct intel_guc_ct *ct = container_of(w, struct intel_guc_ct,
dead_ct_worker);
@@ -1386,6 +1386,9 @@ static void ct_dead_ct_worker_func(struct work_struct *w)
if (ct->dead_ct_reported)
return;
+ if (i915_error_injected())
+ return;
+
ct->dead_ct_reported = true;
guc_info(guc, "CTB is dead - reason=0x%X\n", ct->dead_ct_reason);
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
index 2c4bb9a941be6..e9a6ec4e6d387 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_ct.h
@@ -97,7 +97,7 @@ struct intel_guc_ct {
/** @stall_time: time of first time a CTB submission is stalled */
ktime_t stall_time;
-#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_GUC)
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG)
int dead_ct_reason;
bool dead_ct_reported;
struct work_struct dead_ct_worker;
