From patchwork Thu May 14 23:55:48 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Ruchi Kandoi X-Patchwork-Id: 6410511 Return-Path: X-Original-To: patchwork-linux-pm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id DA1839F1C1 for ; Thu, 14 May 2015 23:56:37 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id D8D5320498 for ; Thu, 14 May 2015 23:56:36 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id BA991203DA for ; Thu, 14 May 2015 23:56:35 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1423051AbbENX4e (ORCPT ); Thu, 14 May 2015 19:56:34 -0400 Received: from mail-ig0-f176.google.com ([209.85.213.176]:35328 "EHLO mail-ig0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1423047AbbENX4O (ORCPT ); Thu, 14 May 2015 19:56:14 -0400 Received: by igbyr2 with SMTP id yr2so182363875igb.0 for ; Thu, 14 May 2015 16:56:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=20120113; h=from:to:subject:date:message-id:in-reply-to:references; bh=0RUlpsjOC3XQHwuJGExvxJYlv9ifw5dF9s65/BdGdYM=; b=XueWLUAOZaRyIRFmfmmp8uksxEGGSqNzqHn74uxu7orWpjNPykOH/Uhy76609vz8LO rJ+afyeDr83w9nA88zk2mRtBOO62aKPBHu5RB/17mhDLGB3f03NVo1V0/vA7wEIySC2g euioc15iPHwNblaVEUso9/szi2eUqK35CxpTCM0UA3Iu1MnXppnsFA/j9DZvb3+O7UnA r8UEdb5a+tmi00mKEvw2m6/g3wOqASz61dmVAsMBoYMSJ04/CnQg61T55G3nREqTL3y7 23yWktYkBWcTCs7R/qnyCdcrGs/iMujFb8oBMKItp155QU4FVte5FcnBmnei9aABE6sc Pv7A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:subject:date:message-id:in-reply-to :references; bh=0RUlpsjOC3XQHwuJGExvxJYlv9ifw5dF9s65/BdGdYM=; b=icgucxzB9sFkHUpsfyygop597wIWUNUXR+AAZ22+titpJzXnrJIeoHzQM+8LBGNsUa OhBmRTlW2yEiGT7Udi1LYtNO1raWSKiWknILBaaR91B/3LtLt2p7fs5Do8oGq1I6mzpI 8xfMnyr5WmSlXFogpK6FPJu79NH2PyMQrufr5Ef0DFzZga5ZXOtNseYlu3yrYSmgaGVZ Vnmdfrevdc43e1KqDLPXrvZ5MXFEHL9VqC+108rozOVvv7JbfpyTga6V+N4OxU74TNWd SfYB0Gs7BQxJpqCRk5fvDPGqCvk3UPpcgpkjEev6Kfe20RvxiFmSIPzCMNO8rqYrrgeo 0DSQ== X-Gm-Message-State: ALoCoQkgczaOfAaxZT2IucYJaaBjPb1dbtsstKGfSXqyIGOK8T4BjTAj6yEZ2KNBIDIHZlUhbnK3 X-Received: by 10.50.4.67 with SMTP id i3mr4685216igi.47.1431647773721; Thu, 14 May 2015 16:56:13 -0700 (PDT) Received: from kandoiruchi.mtv.corp.google.com ([172.22.121.97]) by mx.google.com with ESMTPSA id r4sm360433igh.9.2015.05.14.16.56.12 (version=TLSv1.2 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Thu, 14 May 2015 16:56:13 -0700 (PDT) From: Ruchi Kandoi To: kandoiruchi@google.com, "Rafael J. Wysocki" , Viresh Kumar , Ingo Molnar , Peter Zijlstra , Andrew Morton , Oleg Nesterov , "Kirill A. Shutemov" , Vladimir Davydov , Heinrich Schuchardt , Thomas Gleixner , Kees Cook , Konstantin Khlebnikov , Davidlohr Bueso , linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH 2/2] sched: cpufreq: Adds a field cpu_power in the task_struct Date: Thu, 14 May 2015 16:55:48 -0700 Message-Id: <1431647748-13221-3-git-send-email-kandoiruchi@google.com> X-Mailer: git-send-email 2.2.0.rc0.207.ga3a616c In-Reply-To: <1431647748-13221-1-git-send-email-kandoiruchi@google.com> References: <1431647748-13221-1-git-send-email-kandoiruchi@google.com> Sender: linux-pm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pm@vger.kernel.org X-Spam-Status: No, score=-6.8 required=5.0 tests=BAYES_00, DKIM_ADSP_CUSTOM_MED, DKIM_SIGNED,RCVD_IN_DNSWL_HI,T_DKIM_INVALID,T_RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP cpu_power has been added to keep track of amount of power each task is consuming. cpu_power is updated whenever stime and utime are updated for a task. power is computed by taking into account the frequency at which the current core was running and the current for cpu actively running at hat frequency. Signed-off-by: Ruchi Kandoi --- drivers/cpufreq/cpufreq_stats.c | 23 +++++++++++++++++++++++ include/linux/cpufreq.h | 8 ++++++++ include/linux/sched.h | 2 ++ kernel/fork.c | 1 + kernel/sched/cputime.c | 7 +++++++ 5 files changed, 41 insertions(+) diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c index 6f0b562..4a0bd9a 100644 --- a/drivers/cpufreq/cpufreq_stats.c +++ b/drivers/cpufreq/cpufreq_stats.c @@ -14,6 +14,7 @@ #include #include #include +#include static spinlock_t cpufreq_stats_lock; @@ -83,6 +84,28 @@ static void store_current_value(struct cpufreq_power_stats *powerstats, } } +void acct_update_power(struct task_struct *task, cputime_t cputime) +{ + struct cpufreq_power_stats *powerstats; + struct cpufreq_stats *stats; + struct cpufreq_policy *policy; + unsigned int cpu_num, curr; + + if (!task) + return; + cpu_num = task_cpu(task); + powerstats = per_cpu(cpufreq_power_stats, cpu_num); + policy = cpufreq_cpu_get(cpu_num); + if (!powerstats || !policy || !(policy->stats)) + return; + + stats = policy->stats; + curr = powerstats->curr[stats->last_index]; + task->cpu_power += curr * cputime_to_usecs(cputime); + cpufreq_cpu_put(cpu_num); +} +EXPORT_SYMBOL_GPL(acct_update_power); + static ssize_t store_current_in_state(struct cpufreq_policy *policy, const char *buf, size_t len) { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 2ee4888..86826c8 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -18,6 +18,7 @@ #include #include #include +#include /********************************************************************* * CPUFREQ INTERFACE * @@ -601,4 +602,11 @@ unsigned int cpufreq_generic_get(unsigned int cpu); int cpufreq_generic_init(struct cpufreq_policy *policy, struct cpufreq_frequency_table *table, unsigned int transition_latency); + +/********************************************************************* + * CPUFREQ STATS * + *********************************************************************/ + +void acct_update_power(struct task_struct *p, cputime_t cputime); + #endif /* _LINUX_CPUFREQ_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 26a2e61..1f2400a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1429,6 +1429,7 @@ struct task_struct { int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ cputime_t utime, stime, utimescaled, stimescaled; + unsigned long long cpu_power; cputime_t gtime; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE struct cputime prev_cputime; @@ -1441,6 +1442,7 @@ struct task_struct { VTIME_USER, VTIME_SYS, } vtime_snap_whence; + #endif unsigned long nvcsw, nivcsw; /* context switch counts */ u64 start_time; /* monotonic time in nsec */ diff --git a/kernel/fork.c b/kernel/fork.c index 03c1eaa..2ca0e9e 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1341,6 +1341,7 @@ static struct task_struct *copy_process(unsigned long clone_flags, p->utime = p->stime = p->gtime = 0; p->utimescaled = p->stimescaled = 0; + p->cpu_power = 0; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE p->prev_cputime.utime = p->prev_cputime.stime = 0; #endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 8394b1e..53a79d5 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -4,6 +4,7 @@ #include #include #include +#include #include "sched.h" @@ -149,6 +150,9 @@ void account_user_time(struct task_struct *p, cputime_t cputime, /* Account for user time used */ acct_account_cputime(p); + + /* Account power usage for user time */ + acct_update_power(p, cputime); } /* @@ -199,6 +203,9 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, /* Account for system time used */ acct_account_cputime(p); + + /* Account power usage for system time */ + acct_update_power(p, cputime); } /*