Re: [PATCH] sched/stats: Fix run_delay over-count for proxy-migrated blocked donors

[K Prateek Nayak <kprateek.nayak@amd.com>]

On 10/25/2026 6:37 PM, albin_yang@163.com wrote:
> diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
> index dc626f99ffd9..ef52fbe86bba 100644
> --- a/kernel/sched/stats.h
> +++ b/kernel/sched/stats.h
> @@ -290,7 +290,7 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t)
>   */
>  static inline void sched_info_enqueue(struct rq *rq, struct task_struct *t)
>  {
> -	if (!t->sched_info.last_queued && !t->se.sched_delayed)
> +	if (!t->sched_info.last_queued && !t->se.sched_delayed && !task_is_blocked(t))

I think the sched info bits should be adapted to use the p->is_blocked
indicator instead of adding these endless exceptions.

Could you see if something like below works:

  (Only build tested; Prepared on top of sched-core-2026-10-18)

diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index ebe0a7765f98..bd8c5cdfd12a 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -233,16 +233,13 @@ static inline void psi_account_irqtime(struct rq *rq, struct task_struct *curr,
 /*
  * We are interested in knowing how long it was from the *first* time a
  * task was queued to the time that it finally hit a CPU, we call this routine
- * from dequeue_task() to account for possible rq->clock skew across CPUs. The
- * delta taken on each CPU would annul the skew.
+ * from dequeue_task() / __schedule() to account for possible rq->clock skew
+ * across CPUs. The delta taken on each CPU would annul the skew.
  */
-static inline void sched_info_dequeue(struct rq *rq, struct task_struct *t)
+static inline void __sched_info_dequeue(struct rq *rq, struct task_struct *t)
 {
 	unsigned long long delta = 0;
 
-	if (!t->sched_info.last_queued)
-		return;
-
 	delta = rq_clock(rq) - t->sched_info.last_queued;
 	t->sched_info.last_queued = 0;
 	t->sched_info.run_delay += delta;
@@ -255,6 +252,15 @@ static inline void sched_info_dequeue(struct rq *rq, struct task_struct *t)
 	rq_sched_info_dequeue(rq, delta);
 }
 
+static inline void sched_info_dequeue(struct rq *rq, struct task_struct *t)
+{
+	/* blocked tasks are handled at sched_info_depart() */
+	if (t->is_blocked)
+		return;
+
+	__sched_info_dequeue(rq, t);
+}
+
 /*
  * Called when a task finally hits the CPU.  We can now calculate how
  * long it was waiting to run.  We also note when it began so that we
@@ -290,7 +296,7 @@ static void sched_info_arrive(struct rq *rq, struct task_struct *t)
  */
 static inline void sched_info_enqueue(struct rq *rq, struct task_struct *t)
 {
-	if (!t->sched_info.last_queued)
+	if (t->is_blocked)
 		t->sched_info.last_queued = rq_clock(rq);
 }
 
@@ -310,6 +316,9 @@ static inline void sched_info_depart(struct rq *rq, struct task_struct *t)
 
 	if (task_is_running(t))
 		sched_info_enqueue(rq, t);
+
+	if (t->is_blocked)
+		__sched_info_dequeue(rq, t);
 }
 
 /*
---

It is similar to how we handle PSI signals.

>  		t->sched_info.last_queued = rq_clock(rq);
>  }
>  

-- 
Thanks and Regards,
Prateek