Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753152AbdDJW0j (ORCPT ); Mon, 10 Apr 2017 18:26:39 -0400 Received: from cloudserver094114.home.net.pl ([79.96.170.134]:50541 "EHLO cloudserver094114.home.net.pl" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751275AbdDJW0h (ORCPT ); Mon, 10 Apr 2017 18:26:37 -0400 From: "Rafael J. Wysocki" To: Linux PM Cc: Juri Lelli , LKML , Peter Zijlstra , Srinivas Pandruvada , Viresh Kumar , Vincent Guittot , Patrick Bellasi , Joel Fernandes , Morten Rasmussen , Brendan Jackman Subject: [RFC/RFT][PATCH 1/2] cpufreq: schedutil: Use policy-dependent transition delays Date: Tue, 11 Apr 2017 00:20:41 +0200 Message-ID: <71055380.gdY33coAtF@aspire.rjw.lan> User-Agent: KMail/4.14.10 (Linux/4.11.0-rc4+; KDE/4.14.9; x86_64; ; ) In-Reply-To: <2407280.n9qVSLCrF5@aspire.rjw.lan> References: <3498238.liCqOyIkGA@aspire.rjw.lan> <2407280.n9qVSLCrF5@aspire.rjw.lan> MIME-Version: 1.0 Content-Transfer-Encoding: 7Bit Content-Type: text/plain; charset="us-ascii" Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 3300 Lines: 94 From: Rafael J. Wysocki Make the schedutil governor take the initial (default) value of the rate_limit_us sysfs attribute from the (new) transition_delay_us policy parameter (to be set by the scaling driver). That will allow scaling drivers to make schedutil use smaller default values of rate_limit_us and reduce the default average time interval between consecutive frequency changes. Make intel_pstate set transition_delay_us to 500. Signed-off-by: Rafael J. Wysocki --- This is a replacement for https://patchwork.kernel.org/patch/9671831/ --- drivers/cpufreq/intel_pstate.c | 2 ++ include/linux/cpufreq.h | 7 +++++++ kernel/sched/cpufreq_schedutil.c | 15 ++++++++++----- 3 files changed, 19 insertions(+), 5 deletions(-) Index: linux-pm/include/linux/cpufreq.h =================================================================== --- linux-pm.orig/include/linux/cpufreq.h +++ linux-pm/include/linux/cpufreq.h @@ -120,6 +120,13 @@ struct cpufreq_policy { bool fast_switch_possible; bool fast_switch_enabled; + /* + * Preferred average time interval between consecutive invocations of + * the driver to set the frequency for this policy. To be set by the + * scaling driver (0, which is the default, means no preference). + */ + unsigned int transition_delay_us; + /* Cached frequency lookup from cpufreq_driver_resolve_freq. */ unsigned int cached_target_freq; int cached_resolved_idx; Index: linux-pm/kernel/sched/cpufreq_schedutil.c =================================================================== --- linux-pm.orig/kernel/sched/cpufreq_schedutil.c +++ linux-pm/kernel/sched/cpufreq_schedutil.c @@ -491,7 +491,6 @@ static int sugov_init(struct cpufreq_pol { struct sugov_policy *sg_policy; struct sugov_tunables *tunables; - unsigned int lat; int ret = 0; /* State should be equivalent to EXIT */ @@ -530,10 +529,16 @@ static int sugov_init(struct cpufreq_pol goto stop_kthread; } - tunables->rate_limit_us = LATENCY_MULTIPLIER; - lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC; - if (lat) - tunables->rate_limit_us *= lat; + if (policy->transition_delay_us) { + tunables->rate_limit_us = policy->transition_delay_us; + } else { + unsigned int lat; + + tunables->rate_limit_us = LATENCY_MULTIPLIER; + lat = policy->cpuinfo.transition_latency / NSEC_PER_USEC; + if (lat) + tunables->rate_limit_us *= lat; + } policy->governor_data = sg_policy; sg_policy->tunables = tunables; Index: linux-pm/drivers/cpufreq/intel_pstate.c =================================================================== --- linux-pm.orig/drivers/cpufreq/intel_pstate.c +++ linux-pm/drivers/cpufreq/intel_pstate.c @@ -41,6 +41,7 @@ #define INTEL_PSTATE_HWP_SAMPLING_INTERVAL (50 * NSEC_PER_MSEC) #define INTEL_CPUFREQ_TRANSITION_LATENCY 20000 +#define INTEL_CPUFREQ_TRANSITION_DELAY 500 #ifdef CONFIG_ACPI #include @@ -2237,6 +2238,7 @@ static int intel_cpufreq_cpu_init(struct return ret; policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY; + policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY; /* This reflects the intel_pstate_get_cpu_pstates() setting. */ policy->cur = policy->cpuinfo.min_freq;