1
linux/kernel/trace/trace_sched_switch.c
Steven Rostedt 38516ab59f tracing: Let tracepoints have data passed to tracepoint callbacks
This patch adds data to be passed to tracepoint callbacks.

The created functions from DECLARE_TRACE() now need a mandatory data
parameter. For example:

DECLARE_TRACE(mytracepoint, int value, value)

Will create the register function:

int register_trace_mytracepoint((void(*)(void *data, int value))probe,
                                void *data);

As the first argument, all callbacks (probes) must take a (void *data)
parameter. So a callback for the above tracepoint will look like:

void myprobe(void *data, int value)
{
}

The callback may choose to ignore the data parameter.

This change allows callbacks to register a private data pointer along
with the function probe.

	void mycallback(void *data, int value);

	register_trace_mytracepoint(mycallback, mydata);

Then the mycallback() will receive the "mydata" as the first parameter
before the args.

A more detailed example:

  DECLARE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status));

  /* In the C file */

  DEFINE_TRACE(mytracepoint, TP_PROTO(int status), TP_ARGS(status));

  [...]

       trace_mytracepoint(status);

  /* In a file registering this tracepoint */

  int my_callback(void *data, int status)
  {
	struct my_struct my_data = data;
	[...]
  }

  [...]
	my_data = kmalloc(sizeof(*my_data), GFP_KERNEL);
	init_my_data(my_data);
	register_trace_mytracepoint(my_callback, my_data);

The same callback can also be registered to the same tracepoint as long
as the data registered is different. Note, the data must also be used
to unregister the callback:

	unregister_trace_mytracepoint(my_callback, my_data);

Because of the data parameter, tracepoints declared this way can not have
no args. That is:

  DECLARE_TRACE(mytracepoint, TP_PROTO(void), TP_ARGS());

will cause an error.

If no arguments are needed, a new macro can be used instead:

  DECLARE_TRACE_NOARGS(mytracepoint);

Since there are no arguments, the proto and args fields are left out.

This is part of a series to make the tracepoint footprint smaller:

   text	   data	    bss	    dec	    hex	filename
4913961	1088356	 861512	6863829	 68bbd5	vmlinux.orig
4914025	1088868	 861512	6864405	 68be15	vmlinux.class
4918492	1084612	 861512	6864616	 68bee8	vmlinux.tracepoint

Again, this patch also increases the size of the kernel, but
lays the ground work for decreasing it.

 v5: Fixed net/core/drop_monitor.c to handle these updates.

 v4: Moved the DECLARE_TRACE() DECLARE_TRACE_NOARGS out of the
     #ifdef CONFIG_TRACE_POINTS, since the two are the same in both
     cases. The __DECLARE_TRACE() is what changes.
     Thanks to Frederic Weisbecker for pointing this out.

 v3: Made all register_* functions require data to be passed and
     all callbacks to take a void * parameter as its first argument.
     This makes the calling functions comply with C standards.

     Also added more comments to the modifications of DECLARE_TRACE().

 v2: Made the DECLARE_TRACE() have the ability to pass arguments
     and added a new DECLARE_TRACE_NOARGS() for tracepoints that
     do not need any arguments.

Acked-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Neil Horman <nhorman@tuxdriver.com>
Cc: David S. Miller <davem@davemloft.net>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2010-05-14 09:50:34 -04:00

298 lines
6.8 KiB
C

/*
* trace context switch
*
* Copyright (C) 2007 Steven Rostedt <srostedt@redhat.com>
*
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/debugfs.h>
#include <linux/kallsyms.h>
#include <linux/uaccess.h>
#include <linux/ftrace.h>
#include <trace/events/sched.h>
#include "trace.h"
static struct trace_array *ctx_trace;
static int __read_mostly tracer_enabled;
static int sched_ref;
static DEFINE_MUTEX(sched_register_mutex);
static int sched_stopped;
void
tracing_sched_switch_trace(struct trace_array *tr,
struct task_struct *prev,
struct task_struct *next,
unsigned long flags, int pc)
{
struct ftrace_event_call *call = &event_context_switch;
struct ring_buffer *buffer = tr->buffer;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
event = trace_buffer_lock_reserve(buffer, TRACE_CTX,
sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->prev_pid = prev->pid;
entry->prev_prio = prev->prio;
entry->prev_state = prev->state;
entry->next_pid = next->pid;
entry->next_prio = next->prio;
entry->next_state = next->state;
entry->next_cpu = task_cpu(next);
if (!filter_check_discard(call, entry, buffer, event))
trace_buffer_unlock_commit(buffer, event, flags, pc);
}
static void
probe_sched_switch(void *ignore, struct task_struct *prev, struct task_struct *next)
{
struct trace_array_cpu *data;
unsigned long flags;
int cpu;
int pc;
if (unlikely(!sched_ref))
return;
tracing_record_cmdline(prev);
tracing_record_cmdline(next);
if (!tracer_enabled || sched_stopped)
return;
pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = ctx_trace->data[cpu];
if (likely(!atomic_read(&data->disabled)))
tracing_sched_switch_trace(ctx_trace, prev, next, flags, pc);
local_irq_restore(flags);
}
void
tracing_sched_wakeup_trace(struct trace_array *tr,
struct task_struct *wakee,
struct task_struct *curr,
unsigned long flags, int pc)
{
struct ftrace_event_call *call = &event_wakeup;
struct ring_buffer_event *event;
struct ctx_switch_entry *entry;
struct ring_buffer *buffer = tr->buffer;
event = trace_buffer_lock_reserve(buffer, TRACE_WAKE,
sizeof(*entry), flags, pc);
if (!event)
return;
entry = ring_buffer_event_data(event);
entry->prev_pid = curr->pid;
entry->prev_prio = curr->prio;
entry->prev_state = curr->state;
entry->next_pid = wakee->pid;
entry->next_prio = wakee->prio;
entry->next_state = wakee->state;
entry->next_cpu = task_cpu(wakee);
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
ftrace_trace_stack(tr->buffer, flags, 6, pc);
ftrace_trace_userstack(tr->buffer, flags, pc);
}
static void
probe_sched_wakeup(void *ignore, struct task_struct *wakee, int success)
{
struct trace_array_cpu *data;
unsigned long flags;
int cpu, pc;
if (unlikely(!sched_ref))
return;
tracing_record_cmdline(current);
if (!tracer_enabled || sched_stopped)
return;
pc = preempt_count();
local_irq_save(flags);
cpu = raw_smp_processor_id();
data = ctx_trace->data[cpu];
if (likely(!atomic_read(&data->disabled)))
tracing_sched_wakeup_trace(ctx_trace, wakee, current,
flags, pc);
local_irq_restore(flags);
}
static int tracing_sched_register(void)
{
int ret;
ret = register_trace_sched_wakeup(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup\n");
return ret;
}
ret = register_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
if (ret) {
pr_info("wakeup trace: Couldn't activate tracepoint"
" probe to kernel_sched_wakeup_new\n");
goto fail_deprobe;
}
ret = register_trace_sched_switch(probe_sched_switch, NULL);
if (ret) {
pr_info("sched trace: Couldn't activate tracepoint"
" probe to kernel_sched_switch\n");
goto fail_deprobe_wake_new;
}
return ret;
fail_deprobe_wake_new:
unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
fail_deprobe:
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
return ret;
}
static void tracing_sched_unregister(void)
{
unregister_trace_sched_switch(probe_sched_switch, NULL);
unregister_trace_sched_wakeup_new(probe_sched_wakeup, NULL);
unregister_trace_sched_wakeup(probe_sched_wakeup, NULL);
}
static void tracing_start_sched_switch(void)
{
mutex_lock(&sched_register_mutex);
if (!(sched_ref++))
tracing_sched_register();
mutex_unlock(&sched_register_mutex);
}
static void tracing_stop_sched_switch(void)
{
mutex_lock(&sched_register_mutex);
if (!(--sched_ref))
tracing_sched_unregister();
mutex_unlock(&sched_register_mutex);
}
void tracing_start_cmdline_record(void)
{
tracing_start_sched_switch();
}
void tracing_stop_cmdline_record(void)
{
tracing_stop_sched_switch();
}
/**
* tracing_start_sched_switch_record - start tracing context switches
*
* Turns on context switch tracing for a tracer.
*/
void tracing_start_sched_switch_record(void)
{
if (unlikely(!ctx_trace)) {
WARN_ON(1);
return;
}
tracing_start_sched_switch();
mutex_lock(&sched_register_mutex);
tracer_enabled++;
mutex_unlock(&sched_register_mutex);
}
/**
* tracing_stop_sched_switch_record - start tracing context switches
*
* Turns off context switch tracing for a tracer.
*/
void tracing_stop_sched_switch_record(void)
{
mutex_lock(&sched_register_mutex);
tracer_enabled--;
WARN_ON(tracer_enabled < 0);
mutex_unlock(&sched_register_mutex);
tracing_stop_sched_switch();
}
/**
* tracing_sched_switch_assign_trace - assign a trace array for ctx switch
* @tr: trace array pointer to assign
*
* Some tracers might want to record the context switches in their
* trace. This function lets those tracers assign the trace array
* to use.
*/
void tracing_sched_switch_assign_trace(struct trace_array *tr)
{
ctx_trace = tr;
}
static void stop_sched_trace(struct trace_array *tr)
{
tracing_stop_sched_switch_record();
}
static int sched_switch_trace_init(struct trace_array *tr)
{
ctx_trace = tr;
tracing_reset_online_cpus(tr);
tracing_start_sched_switch_record();
return 0;
}
static void sched_switch_trace_reset(struct trace_array *tr)
{
if (sched_ref)
stop_sched_trace(tr);
}
static void sched_switch_trace_start(struct trace_array *tr)
{
sched_stopped = 0;
}
static void sched_switch_trace_stop(struct trace_array *tr)
{
sched_stopped = 1;
}
static struct tracer sched_switch_trace __read_mostly =
{
.name = "sched_switch",
.init = sched_switch_trace_init,
.reset = sched_switch_trace_reset,
.start = sched_switch_trace_start,
.stop = sched_switch_trace_stop,
.wait_pipe = poll_wait_pipe,
#ifdef CONFIG_FTRACE_SELFTEST
.selftest = trace_selftest_startup_sched_switch,
#endif
};
__init static int init_sched_switch_trace(void)
{
return register_tracer(&sched_switch_trace);
}
device_initcall(init_sched_switch_trace);