From: Thomas Renninger <trenn@suse.de>
To: mingo@elte.hu
Cc: trenn@suse.de, rjw@sisk.pl, linux-kernel@vger.kernel.org,
arjan@linux.intel.com, jean.pihet@newoldbits.com
Subject: [PATCH 2/3] PERF(kernel): Cleanup power events
Date: Thu, 11 Nov 2010 19:03:14 +0100 [thread overview]
Message-ID: <1289498595-25806-3-git-send-email-trenn@suse.de> (raw)
In-Reply-To: <1289498595-25806-1-git-send-email-trenn@suse.de>
Recent changes:
- Enable EVENT_POWER_TRACING_DEPRECATED by default
New power trace events:
power:cpu_idle
power:cpu_frequency
power:machine_suspend
C-state/idle accounting events:
power:power_start
power:power_end
are replaced with:
power:cpu_idle
and
power:power_frequency
is replaced with:
power:cpu_frequency
power:machine_suspend
is newly introduced.
Jean Pihet has a patch integrated into the generic layer
(kernel/power/suspend.c) which will make use of it.
the type= field got removed from both, it was never
used and the type is differed by the event type itself.
perf timechart
userspace tool gets adjusted in a separate patch.
Signed-off-by: Thomas Renninger <trenn@suse.de>
Acked-by: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: Jean Pihet <jean.pihet@newoldbits.com>
CC: Arjan van de Ven <arjan@linux.intel.com>
CC: Ingo Molnar <mingo@elte.hu>
CC: rjw@sisk.pl
CC: linux-kernel@vger.kernel.org
---
arch/x86/kernel/process.c | 7 +++-
arch/x86/kernel/process_32.c | 2 +-
arch/x86/kernel/process_64.c | 2 +
drivers/cpufreq/cpufreq.c | 1 +
drivers/cpuidle/cpuidle.c | 1 +
drivers/idle/intel_idle.c | 1 +
include/trace/events/power.h | 87 +++++++++++++++++++++++++++++++++++++++++-
kernel/trace/Kconfig | 15 +++++++
kernel/trace/power-traces.c | 3 +
9 files changed, 116 insertions(+), 3 deletions(-)
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 b3d7a3a..4c818a7 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 c63a438..1109f68 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 3c95325..ba5134f 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -221,6 +221,7 @@ 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 286784d..ab26d8e 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -7,6 +7,67 @@
#include <linux/ktime.h>
#include <linux/tracepoint.h>
+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 {
@@ -153,8 +214,32 @@ DEFINE_EVENT(power_domain, power_domain_target,
TP_ARGS(name, state, 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 <trace/define_trace.h>
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bc..0be2e7f 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -69,6 +69,21 @@ 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 <trace/events/power.h>
+#ifdef EVENT_POWER_TRACING_DEPRECATED
EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
--
1.6.3
next prev parent reply other threads:[~2010-11-11 18:03 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
2010-11-11 18:03 [RESEND] Power trace event cleanup by still providing old interface for some time Thomas Renninger
2010-11-11 18:03 ` [PATCH 1/3] PERF: Do not export power_frequency, but power_start event Thomas Renninger
2010-11-15 15:50 ` Jean Pihet
2010-11-11 18:03 ` Thomas Renninger [this message]
2010-11-12 14:20 ` [PATCH 2/3] PERF(kernel): Cleanup power events Jean Pihet
2010-11-12 18:17 ` Thomas Renninger
2010-11-12 21:50 ` Jean Pihet
2010-11-14 13:34 ` Thomas Renninger
2010-11-18 8:01 ` Ingo Molnar
2010-11-18 9:27 ` Thomas Renninger
2010-11-18 9:36 ` Ingo Molnar
2010-11-18 9:44 ` Jean Pihet
2010-11-18 10:52 ` Ingo Molnar
2010-11-18 16:34 ` Jean Pihet
2010-11-19 0:14 ` Thomas Renninger
2010-11-14 13:22 ` Thomas Renninger
2010-11-15 15:49 ` Jean Pihet
2010-11-11 18:03 ` [PATCH 3/3] PERF(userspace): Adjust perf timechart to the new " Thomas Renninger
2010-11-18 13:01 Power trace event cleanup by still providing old interface for some time Thomas Renninger
2010-11-18 13:01 ` [PATCH 2/3] PERF(kernel): Cleanup power events Thomas Renninger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1289498595-25806-3-git-send-email-trenn@suse.de \
--to=trenn@suse.de \
--cc=arjan@linux.intel.com \
--cc=jean.pihet@newoldbits.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=rjw@sisk.pl \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).