Arun,
On Mon, 6 Apr 2009, Arun R Bharadwaj wrote:
>
> +ktime_t clockevents_get_next_event(int cpu)
> +{
> + struct tick_device *td;
> + struct clock_event_device *dev;
> +
> + td = &per_cpu(tick_cpu_device, cpu);
> + dev = td->evtdev;
> +
> + return dev->next_event;
> +}
> +
Preferrably this function should be in the clock events code and a
stub inline function which returns KTIME_MAX for non clock events
archs is probably necessary as well.
> /*
> * Switch the timer base to the current CPU when possible.
> */
> @@ -198,8 +211,17 @@ switch_hrtimer_base(struct hrtimer *time
> {
> struct hrtimer_clock_base *new_base;
> struct hrtimer_cpu_base *new_cpu_base;
> + int cpu, preferred_cpu = -1;
> +
> + cpu = smp_processor_id();
> + if (get_sysctl_timer_migration() && !pinned && idle_cpu(cpu)) {
> + preferred_cpu = get_nohz_load_balancer();
> + if (preferred_cpu >= 0)
> + cpu = preferred_cpu;
> + }
>
> - new_cpu_base = &__get_cpu_var(hrtimer_bases);
> +again:
> + new_cpu_base = &per_cpu(hrtimer_bases, cpu);
> new_base = &new_cpu_base->clock_base[base->index];
>
> if (base != new_base) {
> @@ -220,6 +242,32 @@ switch_hrtimer_base(struct hrtimer *time
> spin_unlock(&base->cpu_base->lock);
> spin_lock(&new_base->cpu_base->lock);
> timer->base = new_base;
> +
> + if (cpu == preferred_cpu) {
> + /* Calculate clock monotonic expiry time */
> + ktime_t expires = ktime_sub(hrtimer_get_expires(timer),
> + new_base->offset);
> +
> + /*
> + * Get the next event on target cpu from the
> + * clock events layer.
> + * This covers the highres=off nohz=on case as well.
> + */
> + ktime_t next = clockevents_get_next_event(cpu);
> +
> + ktime_t delta = ktime_sub(expires, next);
> +
> + /*
> + * We do not migrate the timer when it is expiring
> + * before the next event on the target cpu because
> + * we cannot reprogram the target cpu hardware and
> + * we would cause it to fire late.
> + */
> + if (delta.tv64 < 0) {
> + cpu = smp_processor_id();
You are missing a small but fatal detail here: You hold
new_base->cpu_base->lock. So you need to do:
spin_unlock(&new_base->cpu_base->lock);
spin_lock(&base->cpu_base->lock);
> + goto again;
> + }
Also you need to move
> timer->base = new_base;
here to avoid a stale timer->base setting.
> + }
> }
> return new_base;
> }
Thanks,
tglx
_______________________________________________
linux-pm mailing list
linux-pm@xxxxxxxxxxxxxxxxxxxxxxxxxx
https://lists.linux-foundation.org/mailman/listinfo/linux-pm
