Re: [PATCH v4 14/16] timer: Implement the hierarchical pull model

[Anna-Maria Behnsen]

On Tue, 8 Nov 2022, Frederic Weisbecker wrote:

> On Fri, Nov 04, 2022 at 03:57:35PM +0100, Anna-Maria Behnsen wrote:
> > @@ -1859,6 +1863,36 @@ void forward_and_idle_timer_bases(unsigned long basej, u64 basem,
> >  	 */
> >  	is_idle = time_after(nextevt, basej + 1);
> >  
> > +	if (is_idle) {
> > +		u64 next_tmigr;
> > +
> > +		next_tmigr = tmigr_cpu_deactivate(tevt->global);
> > +
> > +		tevt->global = KTIME_MAX;
> > +
> > +		/*
> > +		 * If CPU is the last going idle in timer migration
> > +		 * hierarchy, make sure CPU will wake up in time to handle
> > +		 * remote timers. next_tmigr == KTIME_MAX if other CPUs are
> > +		 * still active.
> > +		 */
> > +		if (next_tmigr < tevt->local) {
> > +			u64 tmp;
> > +
> > +			/* If we missed a tick already, force 0 delta */
> > +			if (next_tmigr < basem)
> > +				next_tmigr = basem;
> > +
> > +			tmp = div_u64(next_tmigr - basem, TICK_NSEC);
> > +
> > +			nextevt = basej + (unsigned long)tmp;
> > +			tevt->local = next_tmigr;
> > +			is_idle = time_after(nextevt, basej + 1);
> 
> So after that, tevt->global shouldn't matter anymore for tick_nohz_next_event(),
> right? If so then probably that line can go away (with a comment specifying why we can
> ignore the global part)?:
> 
>        tevt.local = min_t(u64, tevt.local, tevt.global);
> 

tevt->global is set to KTIME_MAX anyway. So the whole tevt information is
also no longer required in tick_nohz_next_event(). I need to rework the
patch where this was introduced. Then the forward_and_idle_timer_bases()
could still simply return the next timer and then there is no longer a
point against using your idea with naming of the functions.