Re: [PATCH v2] sched: set TIF_NEED_RESCHED before calling __trace_set_need_resched()

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

Hello Gabriele,

On 6/30/2026 2:28 PM, Gabriele Monaco wrote:
> On Mon, 2026-06-29 at 23:05 +0530, K Prateek Nayak wrote:
>>> That said, we should indeed add the tracepoint to that path and probably
>>> adapt the monitor if that's making it fail indirectly.
>>
>> For the npr use-case, I think the current scheme is fine since
>> only SM_PREEMPt counts as a "schedule_entry_preempt" transition
>> and only that can transition the state machine out of the
>> "any_thread_running" state.
> 
> Right, the monitor can live without it, but I wonder if we need to put that
> tracepoint for correctness sake. After all, however unlikely, that's a
> need_resched too.
> 
> (then if the monitor really saw a need_resched after it's sched_entry, it would
> stay erroneously in rescheduling).
> 
> Anyway this all isn't related to the patch.

Ack! Would something like this work for completeness:

  (Lightly tested; Based on current tip:sched/core)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 96226707c2f6..934f540d0d3f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1049,9 +1049,16 @@ static inline void hrtick_schedule_exit(struct rq *rq) { }
  * this avoids any races wrt polling state changes and thereby avoids
  * spurious IPIs.
  */
-static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif)
+static inline bool set_nr_and_not_polling(struct rq *rq, int tif)
 {
-	return !(fetch_or(&ti->flags, 1 << tif) & _TIF_POLLING_NRFLAG);
+	struct task_struct *curr = rq->curr;
+	struct thread_info *ti = task_thread_info(curr);
+	unsigned long old_flags = fetch_or(&ti->flags, 1 << tif);
+
+	if (trace_sched_set_need_resched_tp_enabled() && !(old_flags & (1 << tif)))
+		trace_call__sched_set_need_resched_tp(curr, cpu_of(rq), tif);
+
+	return !(old_flags & _TIF_POLLING_NRFLAG);
 }
 
 /*
@@ -1076,8 +1083,11 @@ static bool set_nr_if_polling(struct task_struct *p)
 }
 
 #else
-static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif)
+static inline bool set_nr_and_not_polling(struct rq *rq, int tif)
 {
+	struct task_struct *curr = rq->curr;
+	struct thread_info *ti = task_thread_info(curr);
+
 	set_ti_thread_flag(ti, tif);
 	return true;
 }
@@ -1202,15 +1212,17 @@ static void __resched_curr(struct rq *rq, int tif)
 
 	cpu = cpu_of(rq);
 
-	trace_sched_set_need_resched_tp(curr, cpu, tif);
 	if (cpu == smp_processor_id()) {
-		set_ti_thread_flag(cti, tif);
+		int set = test_and_set_ti_thread_flag(cti, tif);
+
+		if (trace_sched_set_need_resched_tp_enabled() && !set)
+			trace_call__sched_set_need_resched_tp(curr, cpu, tif);
 		if (tif == TIF_NEED_RESCHED)
 			set_preempt_need_resched();
 		return;
 	}
 
-	if (set_nr_and_not_polling(cti, tif)) {
+	if (set_nr_and_not_polling(rq, tif)) {
 		if (tif == TIF_NEED_RESCHED)
 			smp_send_reschedule(cpu);
 	} else {
@@ -1350,7 +1362,7 @@ static void wake_up_idle_cpu(int cpu)
 	 * and testing of the above solutions didn't appear to report
 	 * much benefits.
 	 */
-	if (set_nr_and_not_polling(task_thread_info(rq->idle), TIF_NEED_RESCHED))
+	if (set_nr_and_not_polling(rq, TIF_NEED_RESCHED))
 		smp_send_reschedule(cpu);
 	else
 		trace_sched_wake_idle_without_ipi(cpu);
---

> 
> Thanks,
> Gabriele
> 

-- 
Thanks and Regards,
Prateek