tracing: add "power-tracer": C/P state tracer to help power optimization

Impact: new "power-tracer" ftrace plugin

This patch adds a C/P-state ftrace plugin that will generate
detailed statistics about the C/P-states that are being used,
so that we can look at detailed decisions that the C/P-state
code is making, rather than the too high level "average"
that we have today.

An example way of using this is:

 mount -t debugfs none /sys/kernel/debug
 echo cstate > /sys/kernel/debug/tracing/current_tracer
 echo 1 > /sys/kernel/debug/tracing/tracing_enabled
 sleep 1
 echo 0 > /sys/kernel/debug/tracing/tracing_enabled
 cat /sys/kernel/debug/tracing/trace | perl scripts/trace/cstate.pl > out.svg

Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 198 insertions, 0 deletions

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 620feadff67a..d151aab48ed6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -217,6 +217,17 @@ config BRANCH_TRACER
 
 	  Say N if unsure.
 
+config POWER_TRACER
+	bool "Trace power consumption behavior"
+	depends on DEBUG_KERNEL
+	depends on X86
+	select TRACING
+	help
+	  This tracer helps developers to analyze and optimize the kernels
+	  power management decisions, specifically the C-state and P-state
+	  behavior.
+
+
 config STACK_TRACER
 	bool "Trace max stack"
 	depends on HAVE_FUNCTION_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index cef4bcb4e822..acaa06553eca 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -32,5 +32,6 @@ obj-$(CONFIG_BOOT_TRACER) += trace_boot.o
 obj-$(CONFIG_FUNCTION_RET_TRACER) += trace_functions_return.o
 obj-$(CONFIG_TRACE_BRANCH_PROFILING) += trace_branch.o
 obj-$(CONFIG_BTS_TRACER) += trace_bts.o
+obj-$(CONFIG_POWER_TRACER) += trace_power.o
 
 libftrace-y := ftrace.o
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 3abd645e8af2..4c453778a6ab 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -28,6 +28,7 @@ enum trace_type {
 	TRACE_FN_RET,
 	TRACE_USER_STACK,
 	TRACE_BTS,
+	TRACE_POWER,
 
 	__TRACE_LAST_TYPE
 };
@@ -160,6 +161,11 @@ struct bts_entry {
 	unsigned long		to;
 };
 
+struct trace_power {
+	struct trace_entry	ent;
+	struct power_trace	state_data;
+};
+
 /*
  * trace_flag_type is an enumeration that holds different
  * states when a trace occurs. These are:
@@ -266,6 +272,7 @@ extern void __ftrace_bad_type(void);
 		IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
 		IF_ASSIGN(var, ent, struct ftrace_ret_entry, TRACE_FN_RET);\
 		IF_ASSIGN(var, ent, struct bts_entry, TRACE_BTS);\
+ 		IF_ASSIGN(var, ent, struct trace_power, TRACE_POWER); \
 		__ftrace_bad_type();					\
 	} while (0)
 
diff --git a/kernel/trace/trace_power.c b/kernel/trace/trace_power.c
new file mode 100644
index 000000000000..a7172a352f62
--- /dev/null
+++ b/kernel/trace/trace_power.c
@@ -0,0 +1,179 @@
+/*
+ * ring buffer based C-state tracer
+ *
+ * Arjan van de Ven <arjan@linux.intel.com>
+ * Copyright (C) 2008 Intel Corporation
+ *
+ * Much is borrowed from trace_boot.c which is
+ * Copyright (C) 2008 Frederic Weisbecker <fweisbec@gmail.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <linux/ftrace.h>
+#include <linux/kallsyms.h>
+#include <linux/module.h>
+
+#include "trace.h"
+
+static struct trace_array *power_trace;
+static int __read_mostly trace_power_enabled;
+
+
+static void start_power_trace(struct trace_array *tr)
+{
+	trace_power_enabled = 1;
+}
+
+static void stop_power_trace(struct trace_array *tr)
+{
+	trace_power_enabled = 0;
+}
+
+
+static int power_trace_init(struct trace_array *tr)
+{
+	int cpu;
+	power_trace = tr;
+
+	trace_power_enabled = 1;
+
+	for_each_cpu_mask(cpu, cpu_possible_map)
+		tracing_reset(tr, cpu);
+	return 0;
+}
+
+static enum print_line_t power_print_line(struct trace_iterator *iter)
+{
+	int ret = 0;
+	struct trace_entry *entry = iter->ent;
+	struct trace_power *field ;
+	struct power_trace *it;
+	struct trace_seq *s = &iter->seq;
+	struct timespec stamp;
+	struct timespec duration;
+
+	trace_assign_type(field, entry);
+	it = &field->state_data;
+	stamp = ktime_to_timespec(it->stamp);
+	duration = ktime_to_timespec(ktime_sub(it->end, it->stamp));
+
+	if (entry->type == TRACE_POWER) {
+		if (it->type == POWER_CSTATE)
+			ret = trace_seq_printf(s, "[%5ld.%09ld] CSTATE: Going to C%i on cpu %i for %ld.%09ld\n",
+					  stamp.tv_sec,
+					  stamp.tv_nsec,
+					  it->state, iter->cpu,
+					  duration.tv_sec,
+					  duration.tv_nsec);
+		if (it->type == POWER_PSTATE)
+			ret = trace_seq_printf(s, "[%5ld.%09ld] PSTATE: Going to P%i on cpu %i\n",
+					  stamp.tv_sec,
+					  stamp.tv_nsec,
+					  it->state, iter->cpu);
+		if (!ret)
+			return TRACE_TYPE_PARTIAL_LINE;
+		return TRACE_TYPE_HANDLED;
+	}
+	return TRACE_TYPE_UNHANDLED;
+}
+
+static struct tracer power_tracer __read_mostly =
+{
+	.name		= "power",
+	.init		= power_trace_init,
+	.start		= start_power_trace,
+	.stop		= stop_power_trace,
+	.reset		= stop_power_trace,
+	.print_line	= power_print_line,
+};
+
+static int init_power_trace(void)
+{
+	return register_tracer(&power_tracer);
+}
+device_initcall(init_power_trace);
+
+void trace_power_start(struct power_trace *it, unsigned int type,
+			 unsigned int level)
+{
+	if (!trace_power_enabled)
+		return;
+
+	memset(it, 0, sizeof(struct power_trace));
+	it->state = level;
+	it->type = type;
+	it->stamp = ktime_get();
+}
+EXPORT_SYMBOL_GPL(trace_power_start);
+
+
+void trace_power_end(struct power_trace *it)
+{
+	struct ring_buffer_event *event;
+	struct trace_power *entry;
+	struct trace_array_cpu *data;
+	unsigned long irq_flags;
+	struct trace_array *tr = power_trace;
+
+	if (!trace_power_enabled)
+		return;
+
+	preempt_disable();
+	it->end = ktime_get();
+	data = tr->data[smp_processor_id()];
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+	entry->ent.type = TRACE_POWER;
+	entry->state_data = *it;
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+
+ out:
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(trace_power_end);
+
+void trace_power_mark(struct power_trace *it, unsigned int type,
+			 unsigned int level)
+{
+	struct ring_buffer_event *event;
+	struct trace_power *entry;
+	struct trace_array_cpu *data;
+	unsigned long irq_flags;
+	struct trace_array *tr = power_trace;
+
+	if (!trace_power_enabled)
+		return;
+
+	memset(it, 0, sizeof(struct power_trace));
+	it->state = level;
+	it->type = type;
+	it->stamp = ktime_get();
+	preempt_disable();
+	it->end = it->stamp;
+	data = tr->data[smp_processor_id()];
+
+	event = ring_buffer_lock_reserve(tr->buffer, sizeof(*entry),
+					 &irq_flags);
+	if (!event)
+		goto out;
+	entry	= ring_buffer_event_data(event);
+	tracing_generic_entry_update(&entry->ent, 0, 0);
+	entry->ent.type = TRACE_POWER;
+	entry->state_data = *it;
+	ring_buffer_unlock_commit(tr->buffer, event, irq_flags);
+
+	trace_wake_up();
+
+ out:
+	preempt_enable();
+}
+EXPORT_SYMBOL_GPL(trace_power_mark);