On Wed, Aug 20, 2025 at 4:28 AM Xuewen Yan <[email protected]> wrote:
>
> Add trace point to psi triggers. This is useful to
> observe the psi events in the kernel space.
>
> One use of this is to monitor memory pressure.
> When the pressure is too high, we can kill the process
> in the kernel space to prevent OOM.
>
> Signed-off-by: Xuewen Yan <[email protected]>
> ---
> v2:
> -fix compilation error;
> -export the tp;
> -add more commit message;
> ---
> include/trace/events/sched.h | 5 +++++
> kernel/sched/psi.c | 4 ++++
> 2 files changed, 9 insertions(+)
>
> diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
> index 7b2645b50e78..d54db5fcbca2 100644
> --- a/include/trace/events/sched.h
> +++ b/include/trace/events/sched.h
> @@ -896,6 +896,11 @@ DECLARE_TRACE(sched_set_need_resched,
> TP_PROTO(struct task_struct *tsk, int cpu, int tif),
> TP_ARGS(tsk, cpu, tif));
>
> +struct psi_trigger;
> +DECLARE_TRACE(psi_event,
DECLARE_TRACE will create a tracepoint but will not export it in the
tracefs. Why should we not have it in the tracefs?
> + TP_PROTO(struct psi_trigger *t),
> + TP_ARGS(t));
> +
> #endif /* _TRACE_SCHED_H */
>
> /* This part must be outside protection */
> diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> index 59fdb7ebbf22..f06eb91a1250 100644
> --- a/kernel/sched/psi.c
> +++ b/kernel/sched/psi.c
> @@ -141,6 +141,8 @@
> #include <linux/psi.h>
> #include "sched.h"
>
> +EXPORT_TRACEPOINT_SYMBOL_GPL(psi_event_tp);
So, are you planning to attach some handler to this trace event in your driver?
> +
> static int psi_bug __read_mostly;
>
> DEFINE_STATIC_KEY_FALSE(psi_disabled);
> @@ -509,6 +511,8 @@ static void update_triggers(struct psi_group *group, u64
> now,
> if (now < t->last_event_time + t->win.size)
> continue;
>
> + trace_psi_event_tp(t);
This should only be done if the below cmpxchg() check is true, right?
Otherwise it will not match with what userspace is receiving.
> +
> /* Generate an event */
> if (cmpxchg(&t->event, 0, 1) == 0) {
> if (t->of)
> --
> 2.25.1
>
