Re: [PATCH v3] sched: set TIF_NEED_RESCHED before calling __trace_set_need_resched()

[Gabriele Monaco <gmonaco@redhat.com>]

Hi Andrea,

On Mon, 2026-09-28 at 19:19 +0200, Andrea Righi wrote:
> This leaves the race Prateek described in the v2 discussion: a remote CPU sets
> TIF_NEED_RESCHED under rq->lock, but the target CPU can emit sched_entry_tp()
> before acquiring that lock, ahead of the need-resched tracepoint.
> 
> I reproduced it with this applied to tip/master. With the RV nrp monitor
> enabled, 300 runs of "perf bench sched messaging -g 20 -l 100" produced:
> 
>   rv: monitor nrp does not allow event schedule_entry_preempt on state
> any_thread_running
> 
> Applying the following on top fixed the ordering, the same 300-run test then
> completed without an RV violation. If it makes sense, could you fold this
> change into v4?
> 
> Thanks,
> -Andrea

thanks for looking into this. Is this change required for anything else besides
fixing the nrp monitor after changing the order with need_resched?

I believe this would break the sts monitor which expects sched_entry before
disabling interrupts.

Both monitors could be adapted to either case, but if your change is just for
the sake of nrp, I think it's easier to just allow this race, since nrp is
already allowing the race with interrupts.
I haven't tested yet, but something like allowing a sched_entry_preempt without
need_resched set but provided it's going to be set before sched_exit would
probably do (it'd allow also independent need_resched there, but those will then
need their own preemption too).

I'd say if you don't need to move sched_entry for other reasons we can wait to
apply this change until I see what's better for the models.

Thanks,
Gabriele

> 
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 639b5df7cf130..91a15a4234280 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -7143,9 +7143,6 @@ static void __sched notrace __schedule(int sched_mode)
>  	struct rq *rq;
>  	int cpu;
>  
> -	/* Trace preemptions consistently with task switches */
> -	trace_sched_entry_tp(sched_mode == SM_PREEMPT);
> -
>  	cpu = smp_processor_id();
>  	rq = cpu_rq(cpu);
>  	prev = rq->curr;
> @@ -7178,6 +7175,9 @@ static void __sched notrace __schedule(int sched_mode)
>  	rq_lock(rq, &rf);
>  	smp_mb__after_spinlock();
>  
> +	/* Trace preemptions consistently with task switches */
> +	trace_sched_entry_tp(sched_mode == SM_PREEMPT);
> +
>  	hrtick_schedule_enter(rq);
>  
>  	/* Promote REQ to ACT */
> 
> 
> > 
> > Fixes: adcc3bfa8806 ("sched: Adapt sched tracepoints for RV task model")
> > Signed-off-by: Sechang Lim <rhkrqnwk98@gmail.com>
> > ---
> > v3:
> >  - reorder need_ipi variable. (K Prateek Nayak)
> > 
> > v2:
> >  - https://lore.kernel.org/all/20260627081657.499781-1-rhkrqnwk98@gmail.com/
> > 
> > v1:
> >  - https://lore.kernel.org/all/20260625065656.392182-1-rhkrqnwk98@gmail.com/
> > 
> >  include/linux/sched.h | 5 ++---
> >  kernel/sched/core.c   | 7 +++++--
> >  2 files changed, 7 insertions(+), 5 deletions(-)
> > 
> > diff --git a/include/linux/sched.h b/include/linux/sched.h
> > index ee06cba5c6f5..c9efd08dae92 100644
> > --- a/include/linux/sched.h
> > +++ b/include/linux/sched.h
> > @@ -2071,10 +2071,9 @@ static inline int test_tsk_thread_flag(struct
> > task_struct *tsk, int flag)
> >  
> >  static inline void set_tsk_need_resched(struct task_struct *tsk)
> >  {
> > -	if (tracepoint_enabled(sched_set_need_resched_tp) &&
> > -	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
> > +	if (!test_and_set_tsk_thread_flag(tsk, TIF_NEED_RESCHED) &&
> > +	    tracepoint_enabled(sched_set_need_resched_tp))
> >  		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
> > -	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
> >  }
> >  
> >  static inline void clear_tsk_need_resched(struct task_struct *tsk)
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index b8871449d3c6..19de28f0d85a 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -1171,6 +1171,7 @@ static void __resched_curr(struct rq *rq, int tif)
> >  {
> >  	struct task_struct *curr = rq->curr;
> >  	struct thread_info *cti = task_thread_info(curr);
> > +	bool need_ipi;
> >  	int cpu;
> >  
> >  	lockdep_assert_rq_held(rq);
> > @@ -1187,15 +1188,17 @@ 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);
> >  		if (tif == TIF_NEED_RESCHED)
> >  			set_preempt_need_resched();
> > +		trace_sched_set_need_resched_tp(curr, cpu, tif);
> >  		return;
> >  	}
> >  
> > -	if (set_nr_and_not_polling(cti, tif)) {
> > +	need_ipi = set_nr_and_not_polling(cti, tif);
> > +	trace_sched_set_need_resched_tp(curr, cpu, tif);
> > +	if (need_ipi) {
> >  		if (tif == TIF_NEED_RESCHED)
> >  			smp_send_reschedule(cpu);
> >  	} else {
> > -- 
> > 2.43.0
> >