Re: [PATCH] cpufreq: x86: Make scaling_cur_freq behave more as expected

From: Rafael J. Wysocki
Date: Fri Jul 28 2017 - 08:35:05 EST


On Thursday, July 27, 2017 11:01:39 PM Doug Smythies wrote:
> On 2017.07.27 17:13 Rafael J. Wysocki wrote:
>
> > From: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> >
> > After commit f8475cef9008 "x86: use common aperfmperf_khz_on_cpu() to
> > calculate KHz using APERF/MPERF" the scaling_cur_freq policy attribute
> > in sysfs only behaves as expected on x86 with APERF/MPERF registers
> > available when it is read from at least twice in a row.
> >
> > The value returned by the first read may not be meaningful, because
> > the computations in there use cached values from the previous
> > aperfmperf_snapshot_khz() call which may be stale. However, the
> > interface is expected to return meaningful values on every read,
> > including the first one.
> >
> > To address this problem modify arch_freq_get_on_cpu() to call
> > aperfmperf_snapshot_khz() twice, with a short delay between
> > these calls, if the previous invocation of aperfmperf_snapshot_khz()
> > was too far back in the past (specifically, more that 1s ago) and
> > adjust aperfmperf_snapshot_khz() for that.
> >
> > Fixes: f8475cef9008 "x86: use common aperfmperf_khz_on_cpu() to calculate KHz using APERF/MPERF"
> > Reported-by: Doug Smythies <dsmythies@xxxxxxxxx>
> > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
> > ---
> > arch/x86/kernel/cpu/aperfmperf.c | 36 +++++++++++++++++++++++++++++-------
> > 1 file changed, 29 insertions(+), 7 deletions(-)
> >
> > Index: linux-pm/arch/x86/kernel/cpu/aperfmperf.c
>
> ...[deleted the rest]...
>
> This proposed patch would be good. However, I can only try it maybe by Sunday.
> I think the maximum time span means that this code:
>
> /*
> * if (cpu_khz * aperf_delta) fits into ULLONG_MAX, then
> * khz = (cpu_khz * aperf_delta) / mperf_delta
> */
> if (div64_u64(ULLONG_MAX, cpu_khz) > aperf_delta)
> s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
> else /* khz = aperf_delta / (mperf_delta / cpu_khz) */
> s->khz = div64_u64(aperf_delta,
> div64_u64(mperf_delta, cpu_khz));
>
> Could be reduced to this:
>
> s->khz = div64_u64((cpu_khz * aperf_delta), mperf_delta);
>
> Because it could never overflow anymore.

Right, that's a good point.

I'll send a v2 with this change included shortly.

Thanks,
Rafael