Re: [PATCH v3 1/3] idle: add support for tasks that inject idle

[Rafael J. Wysocki]

On Thu, Nov 24, 2016 at 12:04 PM, Ingo Molnar <mingo@xxxxxxxxxx> wrote:
>
> * Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
>> On Wed, Nov 23, 2016 at 12:13:08PM -0800, Jacob Pan wrote:
>> > @@ -280,6 +272,58 @@ bool cpu_in_idle(unsigned long pc)
>> >             pc < (unsigned long)__cpuidle_text_end;
>> >  }
>> >
>> > +static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *hrtimer)
>> > +{
>> > +   set_tsk_need_resched(current);
>> > +   return HRTIMER_NORESTART;
>> > +}
>> > +
>> > +void play_idle(unsigned long duration_ms)
>> > +{
>> > +   struct hrtimer timer;
>> > +   unsigned long end_time;
>> > +
>> > +   /*
>> > +    * Only FIFO tasks can disable the tick since they don't need the forced
>> > +    * preemption.
>> > +    */
>> > +   WARN_ON_ONCE(current->policy != SCHED_FIFO);
>> > +   WARN_ON_ONCE(current->nr_cpus_allowed != 1);
>> > +   WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
>> > +   WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
>> > +
>> > +   rcu_sleep_check();
>> > +   preempt_disable();
>> > +   current->flags |= PF_IDLE;
>> > +   cpuidle_use_deepest_state(true);
>> > +
>> > +   /*
>> > +    * If duration is 0, we will return after a natural wake event occurs. If
>> > +    * duration is none zero, we will go back to sleep if we were woken up earlier.
>> > +    * We also set up a timer to make sure we don't oversleep in deep idle.
>> > +    */
>> > +   if (!duration_ms)
>> > +           do_idle();
>>
>> OK, so that doesn't make any sense, you should not be calling this
>> without a timeout.
>>
>> > +   else {
>> > +           hrtimer_init_on_stack(&timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
>> > +           timer.function = idle_inject_timer_fn;
>> > +           hrtimer_start(&timer, ms_to_ktime(duration_ms),
>> > +                   HRTIMER_MODE_REL_PINNED);
>> > +           end_time = jiffies + msecs_to_jiffies(duration_ms);
>> > +
>> > +           while (time_after(end_time, jiffies))
>> > +                   do_idle();
>> > +   }
>> > +   hrtimer_cancel(&timer);
>> > +
>> > +   cpuidle_use_deepest_state(false);
>> > +   current->flags &= ~PF_IDLE;
>> > +
>> > +   preempt_fold_need_resched();
>> > +   preempt_enable();
>> > +}
>> > +EXPORT_SYMBOL_GPL(play_idle);
>>
>>
>> How about something like so... (since I had to edit, I fixed up most
>> things Ingo complained about as well).
>>
>> Note that it doesn't build because of a distinct lack of
>> cpuidle_use_deepest_state() in my kernel tree.
>
> Ok, I really like this one, it so much cleaner!
>
> If the patch builds & works:
>
>   Acked-by: Ingo Molnar <mingo@xxxxxxxxxx>

OK, thanks!

Jacob, can you please test this one along with the rest of the series?

Thanks,
Rafael