From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Rafael J. Wysocki" Subject: Re: [PATCH linux-pm] cpufreq: governors: Fix calculation of wall time in get_cpu_idle_time Date: Fri, 22 Mar 2013 14:24:11 +0100 Message-ID: <1799487.FNztk3vCxS@vostro.rjw.lan> References: <514C0555.1010806@semaphore.gr> Mime-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: 7Bit Return-path: Received: from hydra.sisk.pl ([212.160.235.94]:33603 "EHLO hydra.sisk.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753876Ab3CVNQv (ORCPT ); Fri, 22 Mar 2013 09:16:51 -0400 In-Reply-To: <514C0555.1010806@semaphore.gr> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Stratos Karafotis Cc: cpufreq@vger.kernel.org, linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org On Friday, March 22, 2013 09:16:37 AM Stratos Karafotis wrote: > With commit 8755a8ae31ba213db196324011a0da2a85807f25 the wall in > get_cpu_idle_time is not calculated, when we use ondemand with > io_is_busy = 1, preventing the CPU to increase to max frequency. > > Properly, calculate wall time when we use io_is_busy. > > Signed-off-by: Stratos Karafotis I folded the change below into the original patch. Thanks, Rafael > --- > drivers/cpufreq/cpufreq_governor.c | 2 +- > 1 file changed, 1 insertion(+), 1 deletion(-) > > diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c > index b49d45d..41e5e56 100644 > --- a/drivers/cpufreq/cpufreq_governor.c > +++ b/drivers/cpufreq/cpufreq_governor.c > @@ -53,7 +53,7 @@ static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall) > > u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy) > { > - u64 idle_time = get_cpu_idle_time_us(cpu, NULL); > + u64 idle_time = get_cpu_idle_time_us(cpu, io_busy ? wall : NULL); > > if (idle_time == -1ULL) > return get_cpu_idle_time_jiffy(cpu, wall); > -- I speak only for myself. Rafael J. Wysocki, Intel Open Source Technology Center.