Re: [PATCH 1/4] sched/psi: rearrange polling code in preparation

[Suren Baghdasaryan]

On Thu, Mar 9, 2023 at 9:08 AM Domenico Cerasuolo
<cerasuolodomenico@xxxxxxxxx> wrote:
>
> Move a few functions up in the file to avoid forward declaration needed
> in the patch implementing unprivileged PSI triggers.
>
> Suggested-by: Johannes Weiner <hannes@xxxxxxxxxxx>
> Signed-off-by: Domenico Cerasuolo <cerasuolodomenico@xxxxxxxxx>

LGTM. Will Ack when we finalize the rest of the patchset.

> ---
>  kernel/sched/psi.c | 196 ++++++++++++++++++++++-----------------------
>  1 file changed, 98 insertions(+), 98 deletions(-)
>
> diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
> index 02e011cabe91..fe9269f1d2a4 100644
> --- a/kernel/sched/psi.c
> +++ b/kernel/sched/psi.c
> @@ -384,92 +384,6 @@ static void collect_percpu_times(struct psi_group *group,
>                 *pchanged_states = changed_states;
>  }
>
> -static u64 update_averages(struct psi_group *group, u64 now)
> -{
> -       unsigned long missed_periods = 0;
> -       u64 expires, period;
> -       u64 avg_next_update;
> -       int s;
> -
> -       /* avgX= */
> -       expires = group->avg_next_update;
> -       if (now - expires >= psi_period)
> -               missed_periods = div_u64(now - expires, psi_period);
> -
> -       /*
> -        * The periodic clock tick can get delayed for various
> -        * reasons, especially on loaded systems. To avoid clock
> -        * drift, we schedule the clock in fixed psi_period intervals.
> -        * But the deltas we sample out of the per-cpu buckets above
> -        * are based on the actual time elapsing between clock ticks.
> -        */
> -       avg_next_update = expires + ((1 + missed_periods) * psi_period);
> -       period = now - (group->avg_last_update + (missed_periods * psi_period));
> -       group->avg_last_update = now;
> -
> -       for (s = 0; s < NR_PSI_STATES - 1; s++) {
> -               u32 sample;
> -
> -               sample = group->total[PSI_AVGS][s] - group->avg_total[s];
> -               /*
> -                * Due to the lockless sampling of the time buckets,
> -                * recorded time deltas can slip into the next period,
> -                * which under full pressure can result in samples in
> -                * excess of the period length.
> -                *
> -                * We don't want to report non-sensical pressures in
> -                * excess of 100%, nor do we want to drop such events
> -                * on the floor. Instead we punt any overage into the
> -                * future until pressure subsides. By doing this we
> -                * don't underreport the occurring pressure curve, we
> -                * just report it delayed by one period length.
> -                *
> -                * The error isn't cumulative. As soon as another
> -                * delta slips from a period P to P+1, by definition
> -                * it frees up its time T in P.
> -                */
> -               if (sample > period)
> -                       sample = period;
> -               group->avg_total[s] += sample;
> -               calc_avgs(group->avg[s], missed_periods, sample, period);
> -       }
> -
> -       return avg_next_update;
> -}
> -
> -static void psi_avgs_work(struct work_struct *work)
> -{
> -       struct delayed_work *dwork;
> -       struct psi_group *group;
> -       u32 changed_states;
> -       u64 now;
> -
> -       dwork = to_delayed_work(work);
> -       group = container_of(dwork, struct psi_group, avgs_work);
> -
> -       mutex_lock(&group->avgs_lock);
> -
> -       now = sched_clock();
> -
> -       collect_percpu_times(group, PSI_AVGS, &changed_states);
> -       /*
> -        * If there is task activity, periodically fold the per-cpu
> -        * times and feed samples into the running averages. If things
> -        * are idle and there is no data to process, stop the clock.
> -        * Once restarted, we'll catch up the running averages in one
> -        * go - see calc_avgs() and missed_periods.
> -        */
> -       if (now >= group->avg_next_update)
> -               group->avg_next_update = update_averages(group, now);
> -
> -       if (changed_states & PSI_STATE_RESCHEDULE) {
> -               schedule_delayed_work(dwork, nsecs_to_jiffies(
> -                               group->avg_next_update - now) + 1);
> -       }
> -
> -       mutex_unlock(&group->avgs_lock);
> -}
> -
>  /* Trigger tracking window manipulations */
>  static void window_reset(struct psi_window *win, u64 now, u64 value,
>                          u64 prev_growth)
> @@ -516,18 +430,6 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
>         return growth;
>  }
>
> -static void init_triggers(struct psi_group *group, u64 now)
> -{
> -       struct psi_trigger *t;
> -
> -       list_for_each_entry(t, &group->triggers, node)
> -               window_reset(&t->win, now,
> -                               group->total[PSI_POLL][t->state], 0);
> -       memcpy(group->polling_total, group->total[PSI_POLL],
> -                  sizeof(group->polling_total));
> -       group->polling_next_update = now + group->poll_min_period;
> -}
> -
>  static u64 update_triggers(struct psi_group *group, u64 now)
>  {
>         struct psi_trigger *t;
> @@ -590,6 +492,104 @@ static u64 update_triggers(struct psi_group *group, u64 now)
>         return now + group->poll_min_period;
>  }
>
> +static u64 update_averages(struct psi_group *group, u64 now)
> +{
> +       unsigned long missed_periods = 0;
> +       u64 expires, period;
> +       u64 avg_next_update;
> +       int s;
> +
> +       /* avgX= */
> +       expires = group->avg_next_update;
> +       if (now - expires >= psi_period)
> +               missed_periods = div_u64(now - expires, psi_period);
> +
> +       /*
> +        * The periodic clock tick can get delayed for various
> +        * reasons, especially on loaded systems. To avoid clock
> +        * drift, we schedule the clock in fixed psi_period intervals.
> +        * But the deltas we sample out of the per-cpu buckets above
> +        * are based on the actual time elapsing between clock ticks.
> +        */
> +       avg_next_update = expires + ((1 + missed_periods) * psi_period);
> +       period = now - (group->avg_last_update + (missed_periods * psi_period));
> +       group->avg_last_update = now;
> +
> +       for (s = 0; s < NR_PSI_STATES - 1; s++) {
> +               u32 sample;
> +
> +               sample = group->total[PSI_AVGS][s] - group->avg_total[s];
> +               /*
> +                * Due to the lockless sampling of the time buckets,
> +                * recorded time deltas can slip into the next period,
> +                * which under full pressure can result in samples in
> +                * excess of the period length.
> +                *
> +                * We don't want to report non-sensical pressures in
> +                * excess of 100%, nor do we want to drop such events
> +                * on the floor. Instead we punt any overage into the
> +                * future until pressure subsides. By doing this we
> +                * don't underreport the occurring pressure curve, we
> +                * just report it delayed by one period length.
> +                *
> +                * The error isn't cumulative. As soon as another
> +                * delta slips from a period P to P+1, by definition
> +                * it frees up its time T in P.
> +                */
> +               if (sample > period)
> +                       sample = period;
> +               group->avg_total[s] += sample;
> +               calc_avgs(group->avg[s], missed_periods, sample, period);
> +       }
> +
> +       return avg_next_update;
> +}
> +
> +static void psi_avgs_work(struct work_struct *work)
> +{
> +       struct delayed_work *dwork;
> +       struct psi_group *group;
> +       u32 changed_states;
> +       u64 now;
> +
> +       dwork = to_delayed_work(work);
> +       group = container_of(dwork, struct psi_group, avgs_work);
> +
> +       mutex_lock(&group->avgs_lock);
> +
> +       now = sched_clock();
> +
> +       collect_percpu_times(group, PSI_AVGS, &changed_states);
> +       /*
> +        * If there is task activity, periodically fold the per-cpu
> +        * times and feed samples into the running averages. If things
> +        * are idle and there is no data to process, stop the clock.
> +        * Once restarted, we'll catch up the running averages in one
> +        * go - see calc_avgs() and missed_periods.
> +        */
> +       if (now >= group->avg_next_update)
> +               group->avg_next_update = update_averages(group, now);
> +
> +       if (changed_states & PSI_STATE_RESCHEDULE) {
> +               schedule_delayed_work(dwork, nsecs_to_jiffies(
> +                               group->avg_next_update - now) + 1);
> +       }
> +
> +       mutex_unlock(&group->avgs_lock);
> +}
> +
> +static void init_triggers(struct psi_group *group, u64 now)
> +{
> +       struct psi_trigger *t;
> +
> +       list_for_each_entry(t, &group->triggers, node)
> +               window_reset(&t->win, now,
> +                               group->total[PSI_POLL][t->state], 0);
> +       memcpy(group->polling_total, group->total[PSI_POLL],
> +                  sizeof(group->polling_total));
> +       group->polling_next_update = now + group->poll_min_period;
> +}
> +
>  /* Schedule polling if it's not already scheduled or forced. */
>  static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay,
>                                    bool force)
> --
> 2.34.1
>