Re: [PATCH V2 2/2] cpufreq: Optimize cpufreq_frequency_table_target()

[Steve Muckle]

On Thu, Jun 02, 2016 at 06:59:04AM +0530, Viresh Kumar wrote:
> On 01-06-16, 12:46, Steve Muckle wrote:
> > >  	/*
> > >  	 * Find the closest frequency above target_freq.
> > > -	 *
> > > -	 * The table is sorted in the reverse order with respect to the
> > > -	 * frequency and all of the entries are valid (see the initialization).
> > >  	 */
> > > -	entry = policy->freq_table;
> > > -	do {
> > > -		entry++;
> > > -		freq = entry->frequency;
> > > -	} while (freq >= target_freq && freq != CPUFREQ_TABLE_END);
> > > -	entry--;
> > > +	index = cpufreq_frequency_table_target(policy, target_freq,
> > > +					       CPUFREQ_RELATION_L);
> > 
> > This adds a function call to the fast path...
> 
> I understand that, but I am not sure how far should we go to avoid
> that. Open coding routines to save on that isn't a good idea surely.
> 
> I have at least kept this routine in cpufreq.h to avoid a call, but
> eventually we will have at least a call somewhere within it. :(

Shouldn't we be able to avoid extra function calls through the use of
macros/inlines? Otherwise this is making things slower for schedutil
than it is today. 

Actually cpufreq_driver_resolve_freq() shouldn't require any calls from
schedutil when a freq_table is available - the whole thing could be run
inline.