From patchwork Thu Oct 28 11:37:06 2010 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Thomas Renninger X-Patchwork-Id: 287382 Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by demeter1.kernel.org (8.14.4/8.14.3) with ESMTP id o9SBbDQT014154 for ; Thu, 28 Oct 2010 11:37:13 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758512Ab0J1LhL (ORCPT ); Thu, 28 Oct 2010 07:37:11 -0400 Received: from cantor2.suse.de ([195.135.220.15]:57763 "EHLO mx2.suse.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756727Ab0J1LhK (ORCPT ); Thu, 28 Oct 2010 07:37:10 -0400 Received: from relay2.suse.de (charybdis-ext.suse.de [195.135.221.2]) by mx2.suse.de (Postfix) with ESMTP id 9387794F51; Thu, 28 Oct 2010 13:37:08 +0200 (CEST) From: Thomas Renninger Organization: SUSE Products GmbH To: "Rafael J. Wysocki" Subject: [PATCH 2/3] PERF(kernel): Cleanup power events Date: Thu, 28 Oct 2010 13:37:06 +0200 User-Agent: KMail/1.13.3 (Linux/2.6.31.5-0.1-desktop; KDE/4.4.3; x86_64; ; ) Cc: linux-pm@lists.linux-foundation.org, jean.pihet@newoldbits.com, linux-trace-users@vger.kernel.org, linux-omap@vger.kernel.org, arjan@linux.intel.com, mingo@elte.hu References: <1288256579-22957-1-git-send-email-trenn@suse.de> <201010281317.55502.rjw@sisk.pl> <201010281331.19503.rjw@sisk.pl> In-Reply-To: <201010281331.19503.rjw@sisk.pl> MIME-Version: 1.0 Message-Id: <201010281337.07293.trenn@suse.de> Sender: linux-omap-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-omap@vger.kernel.org X-Greylist: IP, sender and recipient auto-whitelisted, not delayed by milter-greylist-4.2.3 (demeter1.kernel.org [140.211.167.41]); Thu, 28 Oct 2010 11:37:13 +0000 (UTC) diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 57d1868..155d975 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -374,6 +374,7 @@ void default_idle(void) { if (hlt_use_halt()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle(1, smp_processor_id()); current_thread_info()->status &= ~TS_POLLING; /* * TS_POLLING-cleared state must be visible before we @@ -444,6 +445,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { trace_power_start(POWER_CSTATE, (ax>>4)+1, smp_processor_id()); + trace_cpu_idle((ax>>4)+1, smp_processor_id()); if (!need_resched()) { if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -460,6 +462,7 @@ static void mwait_idle(void) { if (!need_resched()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); + trace_cpu_idle(1, smp_processor_id()); if (cpu_has(¤t_cpu_data, X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); @@ -481,10 +484,12 @@ static void mwait_idle(void) static void poll_idle(void) { trace_power_start(POWER_CSTATE, 0, smp_processor_id()); + trace_cpu_idle(0, smp_processor_id()); local_irq_enable(); while (!need_resched()) cpu_relax(); - trace_power_end(0); + trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } /* diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index 96586c3..4b9befa 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -113,8 +113,8 @@ void cpu_idle(void) stop_critical_timings(); pm_idle(); start_critical_timings(); - trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } tick_nohz_restart_sched_tick(); preempt_enable_no_resched(); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 3d9ea53..28153a9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -142,6 +142,8 @@ void cpu_idle(void) start_critical_timings(); trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, + smp_processor_id()); /* In many cases the interrupt that ended idle has already called exit_idle. But some idle diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 199dcb9..ed4919e 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -355,6 +355,7 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state) dprintk("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new, (unsigned long)freqs->cpu); trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu); + trace_cpu_frequency(freqs->new, freqs->cpu); srcu_notifier_call_chain(&cpufreq_transition_notifier_list, CPUFREQ_POSTCHANGE, freqs); if (likely(policy) && likely(policy->cpu == freqs->cpu)) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index a507108..08d5f05 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -107,6 +107,7 @@ static void cpuidle_idle_call(void) if (cpuidle_curr_governor->reflect) cpuidle_curr_governor->reflect(dev); trace_power_end(smp_processor_id()); + trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id()); } /** diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 21ac077..d3701bf 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -202,6 +202,7 @@ static int intel_idle(struct cpuidle_device *dev, struct cpuidle_state *state) stop_critical_timings(); trace_power_start(POWER_CSTATE, (eax >> 4) + 1, cpu); + trace_cpu_idle((eax >> 4) + 1, cpu); if (!need_resched()) { __monitor((void *)¤t_thread_info()->flags, 0, 0); diff --git a/include/trace/events/power.h b/include/trace/events/power.h index 35a2a6e..f10de41 100644 --- a/include/trace/events/power.h +++ b/include/trace/events/power.h @@ -7,6 +7,67 @@ #include #include +DECLARE_EVENT_CLASS(cpu, + + TP_PROTO(unsigned int state, unsigned int cpu_id), + + TP_ARGS(state, cpu_id), + + TP_STRUCT__entry( + __field( u32, state ) + __field( u32, cpu_id ) + ), + + TP_fast_assign( + __entry->state = state; + __entry->cpu_id = cpu_id; + ), + + TP_printk("state=%lu cpu_id=%lu", (unsigned long)__entry->state, + (unsigned long)__entry->cpu_id) +); + +DEFINE_EVENT(cpu, cpu_idle, + + TP_PROTO(unsigned int state, unsigned int cpu_id), + + TP_ARGS(state, cpu_id) +); + +/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */ +#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING +#define _PWR_EVENT_AVOID_DOUBLE_DEFINING + +#define PWR_EVENT_EXIT -1 + +#endif + +DEFINE_EVENT(cpu, cpu_frequency, + + TP_PROTO(unsigned int frequency, unsigned int cpu_id), + + TP_ARGS(frequency, cpu_id) +); + +TRACE_EVENT(machine_suspend, + + TP_PROTO(unsigned int state), + + TP_ARGS(state), + + TP_STRUCT__entry( + __field( u32, state ) + ), + + TP_fast_assign( + __entry->state = state; + ), + + TP_printk("state=%lu", (unsigned long)__entry->state) +); + +#ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED + #ifndef _TRACE_POWER_ENUM_ #define _TRACE_POWER_ENUM_ enum { @@ -69,8 +130,32 @@ TRACE_EVENT(power_end, TP_printk("cpu_id=%lu", (unsigned long)__entry->cpu_id) ); - +#endif /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */ #endif /* _TRACE_POWER_H */ +/* Deprecated dummy functions must be protected against multi- declartion */ +#ifndef EVENT_POWER_TRACING_DEPRECATED_PART_H +#define EVENT_POWER_TRACING_DEPRECATED_PART_H + +#ifndef CONFIG_EVENT_POWER_TRACING_DEPRECATED + +#ifndef _TRACE_POWER_ENUM_ +#define _TRACE_POWER_ENUM_ +enum { + POWER_NONE = 0, + POWER_CSTATE = 1, + POWER_PSTATE = 2, +}; +#endif + +static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {}; +static inline void trace_power_end(u64 cpuid) {}; +static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {}; +#endif /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */ + +#endif /* EVENT_POWER_TRACING_DEPRECATED_PART_H */ + + + /* This part must be outside protection */ #include diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig index 538501c..8ccbedd 100644 --- a/kernel/trace/Kconfig +++ b/kernel/trace/Kconfig @@ -64,6 +64,21 @@ config EVENT_TRACING select CONTEXT_SWITCH_TRACER bool +config EVENT_POWER_TRACING_DEPRECATED + depends on EVENT_TRACING + bool + default y + help + Provides old power event types: + C-state/idle accounting events: + power:power_start + power:power_end + and old cpufreq accounting event: + power:power_frequency + This is for userspace compatibility + and will vanish after 5 kernel iterations, + namely 2.6.41. + config CONTEXT_SWITCH_TRACER bool diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c index 0e0497d..f55fcf6 100644 --- a/kernel/trace/power-traces.c +++ b/kernel/trace/power-traces.c @@ -13,5 +13,8 @@ #define CREATE_TRACE_POINTS #include +#ifdef EVENT_POWER_TRACING_DEPRECATED EXPORT_TRACEPOINT_SYMBOL_GPL(power_start); +#endif +EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);