2009-03-06 10:35:29 +08:00
|
|
|
/*
|
|
|
|
|
* trace_export.c - export basic ftrace utilities to user space
|
|
|
|
|
*
|
|
|
|
|
* Copyright (C) 2009 Steven Rostedt <srostedt@redhat.com>
|
|
|
|
|
*/
|
|
|
|
|
#include <linux/stringify.h>
|
|
|
|
|
#include <linux/kallsyms.h>
|
|
|
|
|
#include <linux/seq_file.h>
|
|
|
|
|
#include <linux/debugfs.h>
|
|
|
|
|
#include <linux/uaccess.h>
|
|
|
|
|
#include <linux/ftrace.h>
|
|
|
|
|
#include <linux/module.h>
|
|
|
|
|
#include <linux/init.h>
|
|
|
|
|
#include <linux/fs.h>
|
|
|
|
|
|
|
|
|
|
#include "trace_output.h"
|
|
|
|
|
|
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 05:14:30 +08:00
|
|
|
|
|
|
|
|
#undef TRACE_STRUCT
|
|
|
|
|
#define TRACE_STRUCT(args...) args
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD
|
|
|
|
|
#define TRACE_FIELD(type, item, assign) \
|
|
|
|
|
ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t" \
|
|
|
|
|
"offset:%u;\tsize:%u;\n", \
|
|
|
|
|
(unsigned int)offsetof(typeof(field), item), \
|
|
|
|
|
(unsigned int)sizeof(field.item)); \
|
|
|
|
|
if (!ret) \
|
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD_SPECIAL
|
2009-03-31 13:48:49 +08:00
|
|
|
#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
|
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 05:14:30 +08:00
|
|
|
ret = trace_seq_printf(s, "\tfield special:" #type_item ";\t" \
|
|
|
|
|
"offset:%u;\tsize:%u;\n", \
|
|
|
|
|
(unsigned int)offsetof(typeof(field), item), \
|
|
|
|
|
(unsigned int)sizeof(field.item)); \
|
|
|
|
|
if (!ret) \
|
|
|
|
|
return 0;
|
2009-03-06 10:35:29 +08:00
|
|
|
|
|
|
|
|
#undef TRACE_FIELD_ZERO_CHAR
|
2009-03-06 23:50:53 +08:00
|
|
|
#define TRACE_FIELD_ZERO_CHAR(item) \
|
2009-04-03 18:24:46 +08:00
|
|
|
ret = trace_seq_printf(s, "\tfield:char " #item ";\t" \
|
2009-03-06 23:50:53 +08:00
|
|
|
"offset:%u;\tsize:0;\n", \
|
|
|
|
|
(unsigned int)offsetof(typeof(field), item)); \
|
|
|
|
|
if (!ret) \
|
2009-03-06 10:35:29 +08:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
|
|
|
2009-03-10 03:47:18 +08:00
|
|
|
#undef TP_RAW_FMT
|
|
|
|
|
#define TP_RAW_FMT(args...) args
|
2009-03-06 10:35:29 +08:00
|
|
|
|
|
|
|
|
#undef TRACE_EVENT_FORMAT
|
|
|
|
|
#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
|
|
|
|
|
static int \
|
|
|
|
|
ftrace_format_##call(struct trace_seq *s) \
|
|
|
|
|
{ \
|
|
|
|
|
struct args field; \
|
|
|
|
|
int ret; \
|
|
|
|
|
\
|
|
|
|
|
tstruct; \
|
|
|
|
|
\
|
|
|
|
|
trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \
|
|
|
|
|
\
|
|
|
|
|
return ret; \
|
|
|
|
|
}
|
|
|
|
|
|
2009-03-31 13:49:16 +08:00
|
|
|
#undef TRACE_EVENT_FORMAT_NOFILTER
|
|
|
|
|
#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
|
|
|
|
|
tpfmt) \
|
|
|
|
|
static int \
|
|
|
|
|
ftrace_format_##call(struct trace_seq *s) \
|
|
|
|
|
{ \
|
|
|
|
|
struct args field; \
|
|
|
|
|
int ret; \
|
|
|
|
|
\
|
|
|
|
|
tstruct; \
|
|
|
|
|
\
|
|
|
|
|
trace_seq_printf(s, "\nprint fmt: \"%s\"\n", tpfmt); \
|
|
|
|
|
\
|
|
|
|
|
return ret; \
|
|
|
|
|
}
|
|
|
|
|
|
2009-03-06 10:35:29 +08:00
|
|
|
#include "trace_event_types.h"
|
|
|
|
|
|
|
|
|
|
#undef TRACE_ZERO_CHAR
|
|
|
|
|
#define TRACE_ZERO_CHAR(arg)
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD
|
|
|
|
|
#define TRACE_FIELD(type, item, assign)\
|
|
|
|
|
entry->item = assign;
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD
|
|
|
|
|
#define TRACE_FIELD(type, item, assign)\
|
|
|
|
|
entry->item = assign;
|
|
|
|
|
|
2009-03-10 03:47:18 +08:00
|
|
|
#undef TP_CMD
|
|
|
|
|
#define TP_CMD(cmd...) cmd
|
2009-03-06 10:35:29 +08:00
|
|
|
|
|
|
|
|
#undef TRACE_ENTRY
|
|
|
|
|
#define TRACE_ENTRY entry
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD_SPECIAL
|
2009-03-31 13:48:49 +08:00
|
|
|
#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd) \
|
2009-03-06 10:35:29 +08:00
|
|
|
cmd;
|
|
|
|
|
|
|
|
|
|
#undef TRACE_EVENT_FORMAT
|
|
|
|
|
#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
|
2009-03-31 13:48:49 +08:00
|
|
|
int ftrace_define_fields_##call(void); \
|
|
|
|
|
static int ftrace_raw_init_event_##call(void); \
|
2009-03-06 10:35:29 +08:00
|
|
|
\
|
2009-03-31 13:48:49 +08:00
|
|
|
struct ftrace_event_call __used \
|
2009-03-06 10:35:29 +08:00
|
|
|
__attribute__((__aligned__(4))) \
|
|
|
|
|
__attribute__((section("_ftrace_events"))) event_##call = { \
|
2009-03-11 02:10:56 +08:00
|
|
|
.name = #call, \
|
2009-03-06 10:35:29 +08:00
|
|
|
.id = proto, \
|
|
|
|
|
.system = __stringify(TRACE_SYSTEM), \
|
2009-03-31 13:48:49 +08:00
|
|
|
.raw_init = ftrace_raw_init_event_##call, \
|
2009-03-06 10:35:29 +08:00
|
|
|
.show_format = ftrace_format_##call, \
|
2009-03-31 13:48:49 +08:00
|
|
|
.define_fields = ftrace_define_fields_##call, \
|
|
|
|
|
}; \
|
|
|
|
|
static int ftrace_raw_init_event_##call(void) \
|
|
|
|
|
{ \
|
|
|
|
|
INIT_LIST_HEAD(&event_##call.fields); \
|
tracing/filters: allow on-the-fly filter switching
This patch allows event filters to be safely removed or switched
on-the-fly while avoiding the use of rcu or the suspension of tracing of
previous versions.
It does it by adding a new filter_pred_none() predicate function which
does nothing and by never deallocating either the predicates or any of
the filter_pred members used in matching; the predicate lists are
allocated and initialized during ftrace_event_calls initialization.
Whenever a filter is removed or replaced, the filter_pred_* functions
currently in use by the affected ftrace_event_call are immediately
switched over to to the filter_pred_none() function, while the rest of
the filter_pred members are left intact, allowing any currently
executing filter_pred_* functions to finish up, using the values they're
currently using.
In the case of filter replacement, the new predicate values are copied
into the old predicates after the above step, and the filter_pred_none()
functions are replaced by the filter_pred_* functions for the new
filter. In this case, it is possible though very unlikely that a
previous filter_pred_* is still running even after the
filter_pred_none() switch and the switch to the new filter_pred_*. In
that case, however, because nothing has been deallocated in the
filter_pred, the worst that can happen is that the old filter_pred_*
function sees the new values and as a result produces either a false
positive or a false negative, depending on the values it finds.
So one downside to this method is that rarely, it can produce a bad
match during the filter switch, but it should be possible to live with
that, IMHO.
The other downside is that at least in this patch the predicate lists
are always pre-allocated, taking up memory from the start. They could
probably be allocated on first-use, and de-allocated when tracing is
completely stopped - if this patch makes sense, I could create another
one to do that later on.
Oh, and it also places a restriction on the size of __arrays in events,
currently set to 128, since they can't be larger than the now embedded
str_val arrays in the filter_pred struct.
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: paulmck@linux.vnet.ibm.com
LKML-Reference: <1239610670.6660.49.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-13 16:17:50 +08:00
|
|
|
init_preds(&event_##call); \
|
2009-03-31 13:48:49 +08:00
|
|
|
return 0; \
|
|
|
|
|
} \
|
|
|
|
|
|
2009-03-31 13:49:16 +08:00
|
|
|
#undef TRACE_EVENT_FORMAT_NOFILTER
|
|
|
|
|
#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
|
|
|
|
|
tpfmt) \
|
|
|
|
|
\
|
|
|
|
|
struct ftrace_event_call __used \
|
|
|
|
|
__attribute__((__aligned__(4))) \
|
|
|
|
|
__attribute__((section("_ftrace_events"))) event_##call = { \
|
|
|
|
|
.name = #call, \
|
|
|
|
|
.id = proto, \
|
|
|
|
|
.system = __stringify(TRACE_SYSTEM), \
|
|
|
|
|
.show_format = ftrace_format_##call, \
|
|
|
|
|
};
|
|
|
|
|
|
2009-03-31 13:48:49 +08:00
|
|
|
#include "trace_event_types.h"
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD
|
|
|
|
|
#define TRACE_FIELD(type, item, assign) \
|
|
|
|
|
ret = trace_define_field(event_call, #type, #item, \
|
|
|
|
|
offsetof(typeof(field), item), \
|
|
|
|
|
sizeof(field.item)); \
|
|
|
|
|
if (ret) \
|
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD_SPECIAL
|
|
|
|
|
#define TRACE_FIELD_SPECIAL(type, item, len, cmd) \
|
|
|
|
|
ret = trace_define_field(event_call, #type "[" #len "]", #item, \
|
|
|
|
|
offsetof(typeof(field), item), \
|
|
|
|
|
sizeof(field.item)); \
|
|
|
|
|
if (ret) \
|
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
|
|
#undef TRACE_FIELD_ZERO_CHAR
|
|
|
|
|
#define TRACE_FIELD_ZERO_CHAR(item)
|
|
|
|
|
|
|
|
|
|
#undef TRACE_EVENT_FORMAT
|
|
|
|
|
#define TRACE_EVENT_FORMAT(call, proto, args, fmt, tstruct, tpfmt) \
|
|
|
|
|
int \
|
|
|
|
|
ftrace_define_fields_##call(void) \
|
|
|
|
|
{ \
|
|
|
|
|
struct ftrace_event_call *event_call = &event_##call; \
|
|
|
|
|
struct args field; \
|
|
|
|
|
int ret; \
|
|
|
|
|
\
|
|
|
|
|
__common_field(unsigned char, type); \
|
|
|
|
|
__common_field(unsigned char, flags); \
|
|
|
|
|
__common_field(unsigned char, preempt_count); \
|
|
|
|
|
__common_field(int, pid); \
|
|
|
|
|
__common_field(int, tgid); \
|
|
|
|
|
\
|
|
|
|
|
tstruct; \
|
|
|
|
|
\
|
|
|
|
|
return ret; \
|
2009-03-06 10:35:29 +08:00
|
|
|
}
|
2009-03-31 13:48:49 +08:00
|
|
|
|
2009-03-31 13:49:16 +08:00
|
|
|
#undef TRACE_EVENT_FORMAT_NOFILTER
|
|
|
|
|
#define TRACE_EVENT_FORMAT_NOFILTER(call, proto, args, fmt, tstruct, \
|
|
|
|
|
tpfmt)
|
|
|
|
|
|
2009-03-06 10:35:29 +08:00
|
|
|
#include "trace_event_types.h"
|