tracing, perf: Convert the power tracer into an event tracer

This patch converts the existing power tracer into an event tracer, so that power events (C states and frequency changes) can be tracked via "perf". This also removes the perl script that was used to demo the tracer; its functionality is being replaced entirely with timechart. Signed-off-by: Arjan van de Ven <[email protected]> Acked-by: Peter Zijlstra <[email protected]> Cc: Paul Mackerras <[email protected]> Cc: Frederic Weisbecker <[email protected]> LKML-Reference: <[email protected]> Signed-off-by: Ingo Molnar <[email protected]>
mna · Sep 19, 2009 · 6161352 · 6161352
1 parent fd39e05
commit 6161352
Show file tree

Hide file tree

Showing 10 changed files with 113 additions and 388 deletions.
diff --git a/Documentation/trace/power.txt b/Documentation/trace/power.txt
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -33,7 +33,7 @@
 #include <linux/cpufreq.h>
 #include <linux/compiler.h>
 #include <linux/dmi.h>
-#include <trace/power.h>
+#include <trace/events/power.h>
 
 #include <linux/acpi.h>
 #include <linux/io.h>
@@ -72,8 +72,6 @@ static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
 
 static DEFINE_PER_CPU(struct aperfmperf, old_perf);
 
-DEFINE_TRACE(power_mark);
-
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance *acpi_perf_data;
 
@@ -332,7 +330,6 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	unsigned int i;
 	int result = 0;
-	struct power_trace it;
 
 	dprintk("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
 
@@ -364,7 +361,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		}
 	}
 
-	trace_power_mark(&it, POWER_PSTATE, next_perf_state);
+	trace_power_frequency(POWER_PSTATE, data->freq_table[next_state].frequency);
 
 	switch (data->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
@@ -9,7 +9,7 @@
 #include <linux/pm.h>
 #include <linux/clockchips.h>
 #include <linux/random.h>
-#include <trace/power.h>
+#include <trace/events/power.h>
 #include <asm/system.h>
 #include <asm/apic.h>
 #include <asm/syscalls.h>
@@ -25,9 +25,6 @@ EXPORT_SYMBOL(idle_nomwait);
 
 struct kmem_cache *task_xstate_cachep;
 
-DEFINE_TRACE(power_start);
-DEFINE_TRACE(power_end);
-
 int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 {
 	*dst = *src;
@@ -299,9 +296,7 @@ static inline int hlt_use_halt(void)
 void default_idle(void)
 {
 	if (hlt_use_halt()) {
-		struct power_trace it;
-
-		trace_power_start(&it, POWER_CSTATE, 1);
+		trace_power_start(POWER_CSTATE, 1);
 		current_thread_info()->status &= ~TS_POLLING;
 		/*
 		 * TS_POLLING-cleared state must be visible before we
@@ -314,7 +309,7 @@ void default_idle(void)
 		else
 			local_irq_enable();
 		current_thread_info()->status |= TS_POLLING;
-		trace_power_end(&it);
+		trace_power_end(0);
 	} else {
 		local_irq_enable();
 		/* loop is done by the caller */
@@ -372,9 +367,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait);
  */
 void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 {
-	struct power_trace it;
-
-	trace_power_start(&it, POWER_CSTATE, (ax>>4)+1);
+	trace_power_start(POWER_CSTATE, (ax>>4)+1);
 	if (!need_resched()) {
 		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
@@ -384,15 +377,14 @@ void mwait_idle_with_hints(unsigned long ax, unsigned long cx)
 		if (!need_resched())
 			__mwait(ax, cx);
 	}
-	trace_power_end(&it);
+	trace_power_end(0);
 }
 
 /* Default MONITOR/MWAIT with no hints, used for default C1 state */
 static void mwait_idle(void)
 {
-	struct power_trace it;
 	if (!need_resched()) {
-		trace_power_start(&it, POWER_CSTATE, 1);
+		trace_power_start(POWER_CSTATE, 1);
 		if (cpu_has(&current_cpu_data, X86_FEATURE_CLFLUSH_MONITOR))
 			clflush((void *)&current_thread_info()->flags);
 
@@ -402,7 +394,7 @@ static void mwait_idle(void)
 			__sti_mwait(0, 0);
 		else
 			local_irq_enable();
-		trace_power_end(&it);
+		trace_power_end(0);
 	} else
 		local_irq_enable();
 }
@@ -414,13 +406,11 @@ static void mwait_idle(void)
  */
 static void poll_idle(void)
 {
-	struct power_trace it;
-
-	trace_power_start(&it, POWER_CSTATE, 0);
+	trace_power_start(POWER_CSTATE, 0);
 	local_irq_enable();
 	while (!need_resched())
 		cpu_relax();
-	trace_power_end(&it);
+	trace_power_end(0);
 }
 
 /*

diff --git a/include/trace/events/power.h b/include/trace/events/power.h
@@ -0,0 +1,81 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM power
+
+#if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWER_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+
+#ifndef _TRACE_POWER_ENUM_
+#define _TRACE_POWER_ENUM_
+enum {
+	POWER_NONE = 0,
+	POWER_CSTATE = 1,
+	POWER_PSTATE = 2,
+};
+#endif
+
+
+
+TRACE_EVENT(power_start,
+
+	TP_PROTO(unsigned int type, unsigned int state),
+
+	TP_ARGS(type, state),
+
+	TP_STRUCT__entry(
+		__field(	u64,		type		)
+		__field(	u64,		state		)
+	),
+
+	TP_fast_assign(
+		__entry->type = type;
+		__entry->state = state;
+	),
+
+	TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long)__entry->state)
+);
+
+TRACE_EVENT(power_end,
+
+	TP_PROTO(int dummy),
+
+	TP_ARGS(dummy),
+
+	TP_STRUCT__entry(
+		__field(	u64,		dummy		)
+	),
+
+	TP_fast_assign(
+		__entry->dummy = 0xffff;
+	),
+
+	TP_printk("dummy=%lu", (unsigned long)__entry->dummy)
+
+);
+
+
+TRACE_EVENT(power_frequency,
+
+	TP_PROTO(unsigned int type, unsigned int state),
+
+	TP_ARGS(type, state),
+
+	TP_STRUCT__entry(
+		__field(	u64,		type		)
+		__field(	u64,		state		)
+	),
+
+	TP_fast_assign(
+		__entry->type = type;
+		__entry->state = state;
+	),
+
+	TP_printk("type=%lu state=%lu", (unsigned long)__entry->type, (unsigned long) __entry->state)
+);
+
+#endif /* _TRACE_POWER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
@@ -42,7 +42,6 @@ obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += trace_functions_graph.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_HW_BRANCH_TRACER) += trace_hw_branches.o
-obj-$(CONFIG_POWER_TRACER) += trace_power.o
 obj-$(CONFIG_KMEMTRACE) += kmemtrace.o
 obj-$(CONFIG_WORKQUEUE_TRACER) += trace_workqueue.o
 obj-$(CONFIG_BLK_DEV_IO_TRACE) += blktrace.o
@@ -54,5 +53,6 @@ obj-$(CONFIG_EVENT_TRACING) += trace_export.o
 obj-$(CONFIG_FTRACE_SYSCALLS) += trace_syscalls.o
 obj-$(CONFIG_EVENT_PROFILE) += trace_event_profile.o
 obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
+obj-$(CONFIG_EVENT_TRACING) += power-traces.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
@@ -0,0 +1,20 @@
+/*
+ * Power trace points
+ *
+ * Copyright (C) 2009 Arjan van de Ven <[email protected]>
+ */
+
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/power.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_end);
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
@@ -11,7 +11,6 @@
 #include <linux/ftrace.h>
 #include <trace/boot.h>
 #include <linux/kmemtrace.h>
-#include <trace/power.h>
 
 #include <linux/trace_seq.h>
 #include <linux/ftrace_event.h>
@@ -37,7 +36,6 @@ enum trace_type {
 	TRACE_HW_BRANCHES,
 	TRACE_KMEM_ALLOC,
 	TRACE_KMEM_FREE,
-	TRACE_POWER,
 	TRACE_BLK,
 
 	__TRACE_LAST_TYPE,
@@ -207,7 +205,6 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry,	\
 			  TRACE_GRAPH_RET);		\
 		IF_ASSIGN(var, ent, struct hw_branch_entry, TRACE_HW_BRANCHES);\
-		IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
 		IF_ASSIGN(var, ent, struct kmemtrace_alloc_entry,	\
 			  TRACE_KMEM_ALLOC);	\
 		IF_ASSIGN(var, ent, struct kmemtrace_free_entry,	\

diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
@@ -330,23 +330,6 @@ FTRACE_ENTRY(hw_branch, hw_branch_entry,
 	F_printk("from: %llx to: %llx", __entry->from, __entry->to)
 );
 
-FTRACE_ENTRY(power, trace_power,
-
-	TRACE_POWER,
-
-	F_STRUCT(
-		__field_struct(	struct power_trace,	state_data	)
-		__field_desc(	s64,	state_data,	stamp		)
-		__field_desc(	s64,	state_data,	end		)
-		__field_desc(	int,	state_data,	type		)
-		__field_desc(	int,	state_data,	state		)
-	),
-
-	F_printk("%llx->%llx type:%u state:%u",
-		 __entry->stamp, __entry->end,
-		 __entry->type, __entry->state)
-);
-
 FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
 
 	TRACE_KMEM_ALLOC,