linux_dsm_epyc7002/kernel/trace/trace_power.c

215 lines
5.0 KiB
C
Raw Normal View History

/*
* 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 <trace/power.h>
#include <linux/kallsyms.h>
#include <linux/module.h>
#include "trace.h"
#include "trace_output.h"
static struct trace_array *power_trace;
static int __read_mostly trace_power_enabled;
static void probe_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();
}
static void probe_power_end(struct power_trace *it)
{
tracing/filters: add run-time field descriptions to TRACE_EVENT_FORMAT events This patch adds run-time field descriptions to all the event formats exported using TRACE_EVENT_FORMAT. It also hooks up all the tracers that use them (i.e. the tracers in the 'ftrace subsystem') so they can also have their output filtered by the event-filtering mechanism. When I was testing this, there were a couple of things that fooled me into thinking the filters weren't working, when actually they were - I'll mention them here so others don't make the same mistakes (and file bug reports. ;-) One is that some of the tracers trace multiple events e.g. the sched_switch tracer uses the context_switch and wakeup events, and if you don't set filters on all of the traced events, the unfiltered output from the events without filters on them can make it look like the filtering as a whole isn't working properly, when actually it is doing what it was asked to do - it just wasn't asked to do the right thing. The other is that for the really high-volume tracers e.g. the function tracer, the volume of filtered events can be so high that it pushes the unfiltered events out of the ring buffer before they can be read so e.g. cat'ing the trace file repeatedly shows either no output, or once in awhile some output but that isn't there the next time you read the trace, which isn't what you normally expect when reading the trace file. If you read from the trace_pipe file though, you can catch them before they disappear. Changes from v1: As suggested by Frederic Weisbecker: - get rid of externs in functions - added unlikely() to filter_check_discard() Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-31 12:48:49 +07:00
struct ftrace_event_call *call = &event_power;
struct ring_buffer_event *event;
struct trace_power *entry;
struct trace_array_cpu *data;
struct trace_array *tr = power_trace;
if (!trace_power_enabled)
return;
preempt_disable();
it->end = ktime_get();
data = tr->data[smp_processor_id()];
event = trace_buffer_lock_reserve(tr, TRACE_POWER,
sizeof(*entry), 0, 0);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
entry->state_data = *it;
if (!filter_check_discard(call, entry, tr->buffer, event))
trace_buffer_unlock_commit(tr, event, 0, 0);
out:
preempt_enable();
}
static void probe_power_mark(struct power_trace *it, unsigned int type,
unsigned int level)
{
tracing/filters: add run-time field descriptions to TRACE_EVENT_FORMAT events This patch adds run-time field descriptions to all the event formats exported using TRACE_EVENT_FORMAT. It also hooks up all the tracers that use them (i.e. the tracers in the 'ftrace subsystem') so they can also have their output filtered by the event-filtering mechanism. When I was testing this, there were a couple of things that fooled me into thinking the filters weren't working, when actually they were - I'll mention them here so others don't make the same mistakes (and file bug reports. ;-) One is that some of the tracers trace multiple events e.g. the sched_switch tracer uses the context_switch and wakeup events, and if you don't set filters on all of the traced events, the unfiltered output from the events without filters on them can make it look like the filtering as a whole isn't working properly, when actually it is doing what it was asked to do - it just wasn't asked to do the right thing. The other is that for the really high-volume tracers e.g. the function tracer, the volume of filtered events can be so high that it pushes the unfiltered events out of the ring buffer before they can be read so e.g. cat'ing the trace file repeatedly shows either no output, or once in awhile some output but that isn't there the next time you read the trace, which isn't what you normally expect when reading the trace file. If you read from the trace_pipe file though, you can catch them before they disappear. Changes from v1: As suggested by Frederic Weisbecker: - get rid of externs in functions - added unlikely() to filter_check_discard() Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Signed-off-by: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-31 12:48:49 +07:00
struct ftrace_event_call *call = &event_power;
struct ring_buffer_event *event;
struct trace_power *entry;
struct trace_array_cpu *data;
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 = trace_buffer_lock_reserve(tr, TRACE_POWER,
sizeof(*entry), 0, 0);
if (!event)
goto out;
entry = ring_buffer_event_data(event);
entry->state_data = *it;
if (!filter_check_discard(call, entry, tr->buffer, event))
trace_buffer_unlock_commit(tr, event, 0, 0);
out:
preempt_enable();
}
static int tracing_power_register(void)
{
int ret;
ret = register_trace_power_start(probe_power_start);
if (ret) {
pr_info("power trace: Couldn't activate tracepoint"
" probe to trace_power_start\n");
return ret;
}
ret = register_trace_power_end(probe_power_end);
if (ret) {
pr_info("power trace: Couldn't activate tracepoint"
" probe to trace_power_end\n");
goto fail_start;
}
ret = register_trace_power_mark(probe_power_mark);
if (ret) {
pr_info("power trace: Couldn't activate tracepoint"
" probe to trace_power_mark\n");
goto fail_end;
}
return ret;
fail_end:
unregister_trace_power_end(probe_power_end);
fail_start:
unregister_trace_power_start(probe_power_start);
return ret;
}
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 void power_trace_reset(struct trace_array *tr)
{
trace_power_enabled = 0;
unregister_trace_power_start(probe_power_start);
unregister_trace_power_end(probe_power_end);
unregister_trace_power_mark(probe_power_mark);
}
static int power_trace_init(struct trace_array *tr)
{
int cpu;
power_trace = tr;
trace_power_enabled = 1;
tracing_power_register();
for_each_cpu(cpu, cpu_possible_mask)
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 void power_print_header(struct seq_file *s)
{
seq_puts(s, "# TIMESTAMP STATE EVENT\n");
seq_puts(s, "# | | |\n");
}
static struct tracer power_tracer __read_mostly =
{
.name = "power",
.init = power_trace_init,
.start = start_power_trace,
.stop = stop_power_trace,
.reset = power_trace_reset,
.print_line = power_print_line,
.print_header = power_print_header,
};
static int init_power_trace(void)
{
return register_tracer(&power_tracer);
}
device_initcall(init_power_trace);