From patchwork Thu Mar 2 15:45:02 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Patrick Bellasi X-Patchwork-Id: 94789 Delivered-To: patch@linaro.org Received: by 10.182.3.34 with SMTP id 2csp346452obz; Thu, 2 Mar 2017 07:49:26 -0800 (PST) X-Received: by 10.99.188.10 with SMTP id q10mr16314777pge.106.1488469765942; Thu, 02 Mar 2017 07:49:25 -0800 (PST) Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id j187si7750484pge.96.2017.03.02.07.49.25; Thu, 02 Mar 2017 07:49:25 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754639AbdCBPtU (ORCPT + 25 others); Thu, 2 Mar 2017 10:49:20 -0500 Received: from foss.arm.com ([217.140.101.70]:32872 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752735AbdCBPqj (ORCPT ); Thu, 2 Mar 2017 10:46:39 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 1BFE21424; Thu, 2 Mar 2017 07:45:27 -0800 (PST) Received: from e110439-lin.cambridge.arm.com (e110439-lin.cambridge.arm.com [10.1.210.68]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 2E80B3F220; Thu, 2 Mar 2017 07:45:24 -0800 (PST) From: Patrick Bellasi To: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org Cc: Patrick Bellasi , Viresh Kumar , Steven Rostedt , Vincent Guittot , John Stultz , Juri Lelli , Todd Kjos , Tim Murray , Andres Oportus , Joel Fernandes , Morten Rasmussen , Dietmar Eggemann , Chris Redpath , Ingo Molnar , Peter Zijlstra , "Rafael J . Wysocki" Subject: [PATCH 1/6] cpufreq: schedutil: reset sg_cpus's flags at IDLE enter Date: Thu, 2 Mar 2017 15:45:02 +0000 Message-Id: <1488469507-32463-2-git-send-email-patrick.bellasi@arm.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1488469507-32463-1-git-send-email-patrick.bellasi@arm.com> References: <1488469507-32463-1-git-send-email-patrick.bellasi@arm.com> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Currently, sg_cpu's flags are set to the value defined by the last call of the cpufreq_update_util()/cpufreq_update_this_cpu(); for RT/DL classes this corresponds to the SCHED_CPUFREQ_{RT/DL} flags always being set. When multiple CPU shares the same frequency domain it might happen that a CPU which executed an RT task, right before entering IDLE, has one of the SCHED_CPUFREQ_RT_DL flags set, permanently, until it exits IDLE. Thus, in sugov_next_freq_shared(), where utilisation and flags are aggregated across all the CPUs of a frequency domain, it turns out that all the CPUs of that domain will always run at the maximum OPP until another event happens in the idle CPU to eventually clear the SCHED_CPUFREQ_{RT/DL} flag. Such a behaviour can harm the energy efficiency of systems when RT workloads are not so frequent and other CPUs in the same frequency domain are running small utilisation workloads, which is a quite common scenario in mobile embedded systems. This patch proposes a solution which is aligned with the current principle to update the flags each time a scheduling event happens. The scheduling of the idle_task on a CPU is considered one of such meaningful events. That's why when the idle_task is selected for execution we poke the schedutil policy to reset the flags for that CPU. Moreover, no frequency transitions are activated at that point, which is fair in case the RT workload should come back in the future, but it allows other CPUs in the same frequency domain to scale down the frequency in case that should be needed. Signed-off-by: Patrick Bellasi Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org --- include/linux/sched.h | 1 + kernel/sched/cpufreq_schedutil.c | 7 +++++++ kernel/sched/idle_task.c | 4 ++++ 3 files changed, 12 insertions(+) -- 2.7.4 diff --git a/include/linux/sched.h b/include/linux/sched.h index e2ed46d..739b29d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -3653,6 +3653,7 @@ static inline unsigned long rlimit_max(unsigned int limit) #define SCHED_CPUFREQ_RT (1U << 0) #define SCHED_CPUFREQ_DL (1U << 1) #define SCHED_CPUFREQ_IOWAIT (1U << 2) +#define SCHED_CPUFREQ_IDLE (1U << 3) #define SCHED_CPUFREQ_RT_DL (SCHED_CPUFREQ_RT | SCHED_CPUFREQ_DL) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index fd46593..084a98b 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -281,6 +281,12 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, raw_spin_lock(&sg_policy->update_lock); + /* CPU is entering IDLE, reset flags without triggering an update */ + if (flags & SCHED_CPUFREQ_IDLE) { + sg_cpu->flags = 0; + goto done; + } + sg_cpu->util = util; sg_cpu->max = max; sg_cpu->flags = flags; @@ -293,6 +299,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, sugov_update_commit(sg_policy, time, next_f); } +done: raw_spin_unlock(&sg_policy->update_lock); } diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 0c00172..a844c91 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -29,6 +29,10 @@ pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf put_prev_task(rq, prev); update_idle_core(rq); schedstat_inc(rq->sched_goidle); + + /* kick cpufreq (see the comment in kernel/sched/sched.h). */ + cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IDLE); + return rq->idle; } From patchwork Thu Mar 2 15:45:03 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Patrick Bellasi X-Patchwork-Id: 94788 Delivered-To: patch@linaro.org Received: by 10.182.3.34 with SMTP id 2csp346448obz; Thu, 2 Mar 2017 07:49:25 -0800 (PST) X-Received: by 10.99.147.16 with SMTP id b16mr16335095pge.126.1488469765566; Thu, 02 Mar 2017 07:49:25 -0800 (PST) Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id j187si7750484pge.96.2017.03.02.07.49.25; Thu, 02 Mar 2017 07:49:25 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754629AbdCBPtP (ORCPT + 25 others); Thu, 2 Mar 2017 10:49:15 -0500 Received: from foss.arm.com ([217.140.101.70]:32890 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752746AbdCBPqj (ORCPT ); Thu, 2 Mar 2017 10:46:39 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 4DC3B1435; Thu, 2 Mar 2017 07:45:30 -0800 (PST) Received: from e110439-lin.cambridge.arm.com (e110439-lin.cambridge.arm.com [10.1.210.68]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id 5FE913F220; Thu, 2 Mar 2017 07:45:27 -0800 (PST) From: Patrick Bellasi To: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org Cc: Patrick Bellasi , Viresh Kumar , Steven Rostedt , Vincent Guittot , John Stultz , Juri Lelli , Todd Kjos , Tim Murray , Andres Oportus , Joel Fernandes , Morten Rasmussen , Dietmar Eggemann , Chris Redpath , Ingo Molnar , Peter Zijlstra , "Rafael J . Wysocki" Subject: [PATCH 2/6] cpufreq: schedutil: ignore the sugov kthread for frequencies selections Date: Thu, 2 Mar 2017 15:45:03 +0000 Message-Id: <1488469507-32463-3-git-send-email-patrick.bellasi@arm.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1488469507-32463-1-git-send-email-patrick.bellasi@arm.com> References: <1488469507-32463-1-git-send-email-patrick.bellasi@arm.com> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org In system where multiple CPUs shares the same frequency domain a small workload on a CPU can still be subject frequency spikes, generated by the activation of the sugov's kthread. Since the sugov kthread is a special RT task, which goal is just that to activate a frequency transition, it does not make sense for it to bias the schedutil's frequency selection. This patch exploits the information related to the current task to silently ignore cpufreq_update_this_cpu() calls, coming from the RT scheduler, while the sugov kthread is running. Signed-off-by: Patrick Bellasi Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org --- kernel/sched/cpufreq_schedutil.c | 6 ++++++ 1 file changed, 6 insertions(+) -- 2.7.4 diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 084a98b..a3fe5e4 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -274,6 +274,8 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, { struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util); struct sugov_policy *sg_policy = sg_cpu->sg_policy; + unsigned int cpu = smp_processor_id(); + struct task_struct *curr = cpu_curr(cpu); unsigned long util, max; unsigned int next_f; @@ -287,6 +289,10 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, goto done; } + /* Skip updates generated by sugov kthreads */ + if (curr == sg_policy->thread) + goto done; + sg_cpu->util = util; sg_cpu->max = max; sg_cpu->flags = flags; From patchwork Thu Mar 2 15:45:05 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Patrick Bellasi X-Patchwork-Id: 94787 Delivered-To: patch@linaro.org Received: by 10.182.3.34 with SMTP id 2csp346376obz; Thu, 2 Mar 2017 07:49:13 -0800 (PST) X-Received: by 10.84.239.8 with SMTP id w8mr19528418plk.73.1488469753430; Thu, 02 Mar 2017 07:49:13 -0800 (PST) Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id 33si5131220plk.81.2017.03.02.07.49.13; Thu, 02 Mar 2017 07:49:13 -0800 (PST) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754600AbdCBPtK (ORCPT + 25 others); Thu, 2 Mar 2017 10:49:10 -0500 Received: from foss.arm.com ([217.140.101.70]:32926 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752794AbdCBPqj (ORCPT ); Thu, 2 Mar 2017 10:46:39 -0500 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id B58FD147A; Thu, 2 Mar 2017 07:45:36 -0800 (PST) Received: from e110439-lin.cambridge.arm.com (e110439-lin.cambridge.arm.com [10.1.210.68]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPA id C60553F220; Thu, 2 Mar 2017 07:45:33 -0800 (PST) From: Patrick Bellasi To: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org Cc: Patrick Bellasi , Viresh Kumar , Steven Rostedt , Vincent Guittot , John Stultz , Juri Lelli , Todd Kjos , Tim Murray , Andres Oportus , Joel Fernandes , Morten Rasmussen , Dietmar Eggemann , Chris Redpath , Ingo Molnar , Peter Zijlstra , "Rafael J . Wysocki" Subject: [PATCH 4/6] cpufreq: schedutil: relax rate-limiting while running RT/DL tasks Date: Thu, 2 Mar 2017 15:45:05 +0000 Message-Id: <1488469507-32463-5-git-send-email-patrick.bellasi@arm.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: <1488469507-32463-1-git-send-email-patrick.bellasi@arm.com> References: <1488469507-32463-1-git-send-email-patrick.bellasi@arm.com> Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org The policy in use for RT/DL tasks sets the maximum frequency when a task in these classes calls for a cpufreq_update_this_cpu(). However, the current implementation is still enforcing a frequency switch rate limiting when these tasks are running. This is potentially working against the goal to switch to the maximum OPP when RT tasks are running. In certain unfortunate cases it can also happen that a RT task almost complete its activation at a lower OPP. This patch overrides on purpose the rate limiting configuration to better serve RT/DL tasks. As long as a frequency scaling operation is not in progress, a frequency switch is always authorized when running in "rt_mode", i.e. the current task in a CPU belongs to the RT/DL class. Signed-off-by: Patrick Bellasi Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Rafael J. Wysocki Cc: Viresh Kumar Cc: linux-kernel@vger.kernel.org Cc: linux-pm@vger.kernel.org --- kernel/sched/cpufreq_schedutil.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) -- 2.7.4 diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index b98a167..44bff37 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -66,7 +66,8 @@ static DEFINE_PER_CPU(struct sugov_cpu, sugov_cpu); /************************ Governor internals ***********************/ -static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) +static bool sugov_should_update_freq(struct sugov_policy *sg_policy, + u64 time, bool rt_mode) { s64 delta_ns; @@ -83,6 +84,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time) return true; } + /* Always update if a RT/DL task is running */ + if (rt_mode) + return true; + delta_ns = time - sg_policy->last_freq_update_time; return delta_ns >= sg_policy->freq_update_delay_ns; } @@ -215,7 +220,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, sugov_set_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; - if (!sugov_should_update_freq(sg_policy, time)) + if (!sugov_should_update_freq(sg_policy, time, rt_mode)) return; if (rt_mode) { @@ -324,7 +329,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, sugov_set_iowait_boost(sg_cpu, time, flags); sg_cpu->last_update = time; - if (sugov_should_update_freq(sg_policy, time)) { + if (sugov_should_update_freq(sg_policy, time, rt_mode)) { next_f = sg_policy->policy->cpuinfo.max_freq; if (!rt_mode) next_f = sugov_next_freq_shared(sg_cpu, util, max, flags);