int srcu, ret;
/*
+ * Ideally the busyness worker should take a gt pm wakeref because the
+ * worker only needs to be active while gt is awake. However, the
+ * gt_park path cancels the worker synchronously and this complicates
+ * the flow if the worker is also running at the same time. The cancel
+ * waits for the worker and when the worker releases the wakeref, that
+ * would call gt_park and would lead to a deadlock.
+ *
+ * The resolution is to take the global pm wakeref if runtime pm is
+ * already active. If not, we don't need to update the busyness stats as
+ * the stats would already be updated when the gt was parked.
+ *
+ * Note:
+ * - We do not requeue the worker if we cannot take a reference to runtime
+ * pm since intel_guc_busyness_unpark would requeue the worker in the
+ * resume path.
+ *
+ * - If the gt was parked longer than time taken for GT timestamp to roll
+ * over, we ignore those rollovers since we don't care about tracking
+ * the exact GT time. We only care about roll overs when the gt is
+ * active and running workloads.
+ *
+ * - There is a window of time between gt_park and runtime suspend,
+ * where the worker may run. This is acceptable since the worker will
+ * not find any new data to update busyness.
+ */
+ wakeref = intel_runtime_pm_get_if_active(>->i915->runtime_pm);
+ if (!wakeref)
+ return;
+
+ /*
* Synchronize with gt reset to make sure the worker does not
* corrupt the engine/guc stats. NB: can't actually block waiting
* for a reset to complete as the reset requires flushing out
*/
ret = intel_gt_reset_trylock(gt, &srcu);
if (ret)
- return;
+ goto err_trylock;
- with_intel_runtime_pm(>->i915->runtime_pm, wakeref)
- __update_guc_busyness_stats(guc);
+ __update_guc_busyness_stats(guc);
/* adjust context stats for overflow */
xa_for_each(&guc->context_lookup, index, ce)
intel_gt_reset_unlock(gt, srcu);
guc_enable_busyness_worker(guc);
+
+err_trylock:
+ intel_runtime_pm_put(>->i915->runtime_pm, wakeref);
}
static int guc_action_enable_usage_stats(struct intel_guc *guc)