aha/include/linux/tracepoint.h
Steven Rostedt da4d03020c tracing: new format for specialized trace points
Impact: clean up and enhancement

The TRACE_EVENT_FORMAT macro looks quite ugly and is limited in its
ability to save data as well as to print the record out. Working with
Ingo Molnar, we came up with a new format that is much more pleasing to
the eye of C developers. This new macro is more C style than the old
macro, and is more obvious to what it does.

Here's the example. The only updated macro in this patch is the
sched_switch trace point.

The old method looked like this:

 TRACE_EVENT_FORMAT(sched_switch,
        TP_PROTO(struct rq *rq, struct task_struct *prev,
                struct task_struct *next),
        TP_ARGS(rq, prev, next),
        TP_FMT("task %s:%d ==> %s:%d",
              prev->comm, prev->pid, next->comm, next->pid),
        TRACE_STRUCT(
                TRACE_FIELD(pid_t, prev_pid, prev->pid)
                TRACE_FIELD(int, prev_prio, prev->prio)
                TRACE_FIELD_SPECIAL(char next_comm[TASK_COMM_LEN],
                                    next_comm,
                                    TP_CMD(memcpy(TRACE_ENTRY->next_comm,
                                                 next->comm,
                                                 TASK_COMM_LEN)))
                TRACE_FIELD(pid_t, next_pid, next->pid)
                TRACE_FIELD(int, next_prio, next->prio)
        ),
        TP_RAW_FMT("prev %d:%d ==> next %s:%d:%d")
        );

The above method is hard to read and requires two format fields.

The new method:

 /*
  * Tracepoint for task switches, performed by the scheduler:
  *
  * (NOTE: the 'rq' argument is not used by generic trace events,
  *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_switch,

	TP_PROTO(struct rq *rq, struct task_struct *prev,
		 struct task_struct *next),

	TP_ARGS(rq, prev, next),

	TP_STRUCT__entry(
		__array(	char,	prev_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	prev_pid			)
		__field(	int,	prev_prio			)
		__array(	char,	next_comm,	TASK_COMM_LEN	)
		__field(	pid_t,	next_pid			)
		__field(	int,	next_prio			)
	),

	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
		__entry->next_comm, __entry->next_pid, __entry->next_prio),

	TP_fast_assign(
		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
		__entry->prev_pid	= prev->pid;
		__entry->prev_prio	= prev->prio;
		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
		__entry->next_pid	= next->pid;
		__entry->next_prio	= next->prio;
	)
 );

This macro is called TRACE_EVENT, it is broken up into 5 parts:

 TP_PROTO:        the proto type of the trace point
 TP_ARGS:         the arguments of the trace point
 TP_STRUCT_entry: the structure layout of the entry in the ring buffer
 TP_printk:       the printk format
 TP_fast_assign:  the method used to write the entry into the ring buffer

The structure is the definition of how the event will be saved in the
ring buffer. The printk is used by the internal tracing in case of
an oops, and the kernel needs to print out the format of the record
to the console. This the TP_printk gives a means to show the records
in a human readable format. It is also used to print out the data
from the trace file.

The TP_fast_assign is executed directly. It is basically like a C function,
where the __entry is the handle to the record.

Signed-off-by: Steven Rostedt <srostedt@redhat.com>
2009-03-10 00:35:07 -04:00

166 lines
4.9 KiB
C

#ifndef _LINUX_TRACEPOINT_H
#define _LINUX_TRACEPOINT_H
/*
* Kernel Tracepoint API.
*
* See Documentation/tracepoint.txt.
*
* (C) Copyright 2008 Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca>
*
* Heavily inspired from the Linux Kernel Markers.
*
* This file is released under the GPLv2.
* See the file COPYING for more details.
*/
#include <linux/types.h>
#include <linux/rcupdate.h>
struct module;
struct tracepoint;
struct tracepoint {
const char *name; /* Tracepoint name */
int state; /* State. */
void **funcs;
} __attribute__((aligned(32))); /*
* Aligned on 32 bytes because it is
* globally visible and gcc happily
* align these on the structure size.
* Keep in sync with vmlinux.lds.h.
*/
#define TP_PROTO(args...) args
#define TP_ARGS(args...) args
#ifdef CONFIG_TRACEPOINTS
/*
* it_func[0] is never NULL because there is at least one element in the array
* when the array itself is non NULL.
*/
#define __DO_TRACE(tp, proto, args) \
do { \
void **it_func; \
\
rcu_read_lock_sched_notrace(); \
it_func = rcu_dereference((tp)->funcs); \
if (it_func) { \
do { \
((void(*)(proto))(*it_func))(args); \
} while (*(++it_func)); \
} \
rcu_read_unlock_sched_notrace(); \
} while (0)
/*
* Make sure the alignment of the structure in the __tracepoints section will
* not add unwanted padding between the beginning of the section and the
* structure. Force alignment to the same alignment as the section start.
*/
#define DECLARE_TRACE(name, proto, args) \
extern struct tracepoint __tracepoint_##name; \
static inline void trace_##name(proto) \
{ \
if (unlikely(__tracepoint_##name.state)) \
__DO_TRACE(&__tracepoint_##name, \
TP_PROTO(proto), TP_ARGS(args)); \
} \
static inline int register_trace_##name(void (*probe)(proto)) \
{ \
return tracepoint_probe_register(#name, (void *)probe); \
} \
static inline int unregister_trace_##name(void (*probe)(proto)) \
{ \
return tracepoint_probe_unregister(#name, (void *)probe);\
}
#define DEFINE_TRACE(name) \
static const char __tpstrtab_##name[] \
__attribute__((section("__tracepoints_strings"))) = #name; \
struct tracepoint __tracepoint_##name \
__attribute__((section("__tracepoints"), aligned(32))) = \
{ __tpstrtab_##name, 0, NULL }
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name) \
EXPORT_SYMBOL_GPL(__tracepoint_##name)
#define EXPORT_TRACEPOINT_SYMBOL(name) \
EXPORT_SYMBOL(__tracepoint_##name)
extern void tracepoint_update_probe_range(struct tracepoint *begin,
struct tracepoint *end);
#else /* !CONFIG_TRACEPOINTS */
#define DECLARE_TRACE(name, proto, args) \
static inline void _do_trace_##name(struct tracepoint *tp, proto) \
{ } \
static inline void trace_##name(proto) \
{ } \
static inline int register_trace_##name(void (*probe)(proto)) \
{ \
return -ENOSYS; \
} \
static inline int unregister_trace_##name(void (*probe)(proto)) \
{ \
return -ENOSYS; \
}
#define DEFINE_TRACE(name)
#define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
#define EXPORT_TRACEPOINT_SYMBOL(name)
static inline void tracepoint_update_probe_range(struct tracepoint *begin,
struct tracepoint *end)
{ }
#endif /* CONFIG_TRACEPOINTS */
/*
* Connect a probe to a tracepoint.
* Internal API, should not be used directly.
*/
extern int tracepoint_probe_register(const char *name, void *probe);
/*
* Disconnect a probe from a tracepoint.
* Internal API, should not be used directly.
*/
extern int tracepoint_probe_unregister(const char *name, void *probe);
extern int tracepoint_probe_register_noupdate(const char *name, void *probe);
extern int tracepoint_probe_unregister_noupdate(const char *name, void *probe);
extern void tracepoint_probe_update_all(void);
struct tracepoint_iter {
struct module *module;
struct tracepoint *tracepoint;
};
extern void tracepoint_iter_start(struct tracepoint_iter *iter);
extern void tracepoint_iter_next(struct tracepoint_iter *iter);
extern void tracepoint_iter_stop(struct tracepoint_iter *iter);
extern void tracepoint_iter_reset(struct tracepoint_iter *iter);
extern int tracepoint_get_iter_range(struct tracepoint **tracepoint,
struct tracepoint *begin, struct tracepoint *end);
/*
* tracepoint_synchronize_unregister must be called between the last tracepoint
* probe unregistration and the end of module exit to make sure there is no
* caller executing a probe when it is freed.
*/
static inline void tracepoint_synchronize_unregister(void)
{
synchronize_sched();
}
#define PARAMS(args...) args
#define TRACE_FORMAT(name, proto, args, fmt) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
#define TRACE_EVENT_FORMAT(name, proto, args, fmt, struct, tpfmt) \
TRACE_FORMAT(name, PARAMS(proto), PARAMS(args), PARAMS(fmt))
#define TRACE_EVENT(name, proto, args, struct, print, assign) \
DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
#endif