get_rc6() has the same runqueue lock deadlock as guc_engine_busyness():
it is reached from the PMU callbacks, which perf can invoke from the
scheduler with the runqueue lock held, and intel_gt_pm_put_async() there
can wake a workqueue worker via try_to_wake_up().
Use intel_gt_pm_put_delay() so the deferred put arms a timer instead.
The remaining async puts in atomic contexts (hrtimer, tasklet, irq_work,
G2H handlers) cannot run with the runqueue lock held and are left alone.
Fixes: 07779a76ee1f ("drm/i915: Mark up the calling context for
intel_wakeref_put()")
Signed-off-by: Umesh Nerlige Ramappa <[email protected]>
Assisted-by: Claude:claude-opus-5
---
drivers/gpu/drm/i915/i915_pmu.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 1c3bafda9c70..4598d9b5678a 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -229,7 +229,12 @@ static u64 get_rc6(struct intel_gt *gt)
wakeref = intel_gt_pm_get_if_awake(gt);
if (wakeref) {
val = __get_rc6(gt);
- intel_gt_pm_put_async(gt, wakeref);
+ /*
+ * We are reached from the perf callbacks, which perf may invoke
+ * from the scheduler with the runqueue lock held. Defer the put
+ * on a timer so that it can never wake a task from here.
+ */
+ intel_gt_pm_put_delay(gt, wakeref, 1);
}
spin_lock_irqsave(&pmu->lock, flags);
--
2.55.0
