Re: [PATCH v7 08/15] sched: Add task enqueue/dequeue trace points

[gmonaco]

Hi Peter,

On Tue, 2026-03-10 at 11:56 +0100, Gabriele Monaco wrote:
> From: Nam Cao <namcao@xxxxxxxxxxxxx>
> 
> Add trace points into enqueue_task() and dequeue_task().
> 
> Signed-off-by: Nam Cao <namcao@xxxxxxxxxxxxx>
> Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> Reviewed-by: K Prateek Nayak <kprateek.nayak@xxxxxxx>
> Co-developed-by: Gabriele Monaco <gmonaco@xxxxxxxxxx>
> Signed-off-by: Gabriele Monaco <gmonaco@xxxxxxxxxx>
> ---

Could I get an Ack for this?

Thanks,
Gabriele

> 
> Notes:
>     V7:
>     * Use cpu_of(rq) helper in tracepoint calls
>     V5:
>     * Do not fire enqueue tracepoint for delayed enqueues
> 
>  include/trace/events/sched.h |  8 ++++++++
>  kernel/sched/core.c          | 12 +++++++++++-
>  kernel/sched/sched.h         |  2 ++
>  3 files changed, 21 insertions(+), 1 deletion(-)
> 
> diff --git a/include/trace/events/sched.h
> b/include/trace/events/sched.h
> index 7b2645b50e78..5844147ec5fd 100644
> --- a/include/trace/events/sched.h
> +++ b/include/trace/events/sched.h
> @@ -896,6 +896,14 @@ DECLARE_TRACE(sched_set_need_resched,
>  	TP_PROTO(struct task_struct *tsk, int cpu, int tif),
>  	TP_ARGS(tsk, cpu, tif));
>  
> +DECLARE_TRACE(sched_enqueue,
> +	TP_PROTO(struct task_struct *tsk, int cpu),
> +	TP_ARGS(tsk, cpu));
> +
> +DECLARE_TRACE(sched_dequeue,
> +	TP_PROTO(struct task_struct *tsk, int cpu),
> +	TP_ARGS(tsk, cpu));
> +
>  #endif /* _TRACE_SCHED_H */
>  
>  /* This part must be outside protection */
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index b7f77c165a6e..c9ca1e048612 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -122,6 +122,8 @@
> EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(sched_entry_tp);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(sched_exit_tp);
>  EXPORT_TRACEPOINT_SYMBOL_GPL(sched_set_need_resched_tp);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_enqueue_tp);
> +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_dequeue_tp);
>  
>  DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
>  DEFINE_PER_CPU(struct rnd_state, sched_rnd_state);
> @@ -2094,6 +2096,9 @@ unsigned long get_wchan(struct task_struct *p)
>  
>  void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
>  {
> +	if (trace_sched_enqueue_tp_enabled() && !(flags &
> ENQUEUE_DELAYED))
> +		trace_sched_enqueue_tp(p, cpu_of(rq));
> +
>  	if (!(flags & ENQUEUE_NOCLOCK))
>  		update_rq_clock(rq);
>  
> @@ -2120,6 +2125,8 @@ void enqueue_task(struct rq *rq, struct
> task_struct *p, int flags)
>   */
>  inline bool dequeue_task(struct rq *rq, struct task_struct *p, int
> flags)
>  {
> +	bool ret;
> +
>  	if (sched_core_enabled(rq))
>  		sched_core_dequeue(rq, p, flags);
>  
> @@ -2136,7 +2143,10 @@ inline bool dequeue_task(struct rq *rq, struct
> task_struct *p, int flags)
>  	 * and mark the task ->sched_delayed.
>  	 */
>  	uclamp_rq_dec(rq, p);
> -	return p->sched_class->dequeue_task(rq, p, flags);
> +	ret = p->sched_class->dequeue_task(rq, p, flags);
> +	if (trace_sched_dequeue_tp_enabled() && !(flags &
> DEQUEUE_SLEEP))
> +		trace_sched_dequeue_tp(p, cpu_of(rq));
> +	return ret;
>  }
>  
>  void activate_task(struct rq *rq, struct task_struct *p, int flags)
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 43bbf0693cca..d7ab0aa58a70 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -2955,6 +2955,8 @@ static inline void sub_nr_running(struct rq
> *rq, unsigned count)
>  
>  static inline void __block_task(struct rq *rq, struct task_struct
> *p)
>  {
> +	trace_sched_dequeue_tp(p, cpu_of(rq));
> +
>  	if (p->sched_contributes_to_load)
>  		rq->nr_uninterruptible++;
>