kernel-fxtec-pro1x/kernel/trace/trace_export.c

170 lines
4.2 KiB
C
Raw Normal View History

/*
* 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"
#undef TRACE_SYSTEM
#define TRACE_SYSTEM ftrace
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>
2009-03-09 15:14:30 -06:00
/* not needed for this file */
#undef __field_struct
#define __field_struct(type, item)
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>
2009-03-09 15:14:30 -06:00
#undef __field
#define __field(type, item) type item;
#undef __field_desc
#define __field_desc(type, container, item) type item;
#undef __array
#define __array(type, item, size) type item[size];
#undef __array_desc
#define __array_desc(type, container, item, size) type item[size];
#undef __dynamic_array
#define __dynamic_array(type, item) type item[];
#undef F_STRUCT
#define F_STRUCT(args...) args
#undef F_printk
#define F_printk(fmt, args...) fmt, args
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
struct ____ftrace_##name { \
tstruct \
}; \
static void __always_unused ____ftrace_check_##name(void) \
{ \
struct ____ftrace_##name *__entry = NULL; \
\
/* force compile-time check on F_printk() */ \
printk(print); \
}
#undef FTRACE_ENTRY_DUP
#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
#include "trace_entries.h"
#undef __field
#define __field(type, item) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
if (ret) \
return ret;
#undef __field_desc
#define __field_desc(type, container, item) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), \
container.item), \
sizeof(field.container.item), \
is_signed_type(type), FILTER_OTHER); \
if (ret) \
return ret;
#undef __array
#define __array(type, item, len) \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
ret = trace_define_field(event_call, #type "[" #len "]", #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
if (ret) \
return ret;
#undef __array_desc
#define __array_desc(type, container, item, len) \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
ret = trace_define_field(event_call, #type "[" #len "]", #item, \
offsetof(typeof(field), \
container.item), \
sizeof(field.container.item), \
is_signed_type(type), FILTER_OTHER); \
if (ret) \
return ret;
#undef __dynamic_array
#define __dynamic_array(type, item) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
0, is_signed_type(type), FILTER_OTHER);\
if (ret) \
return ret;
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
int \
ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
{ \
struct struct_name field; \
int ret; \
\
tstruct; \
\
return ret; \
}
#include "trace_entries.h"
static int ftrace_raw_init_event(struct ftrace_event_call *call)
{
INIT_LIST_HEAD(&call->fields);
return 0;
}
#undef __entry
#define __entry REC
#undef __field
#define __field(type, item)
#undef __field_desc
#define __field_desc(type, container, item)
#undef __array
#define __array(type, item, len)
#undef __array_desc
#define __array_desc(type, container, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item)
#undef F_printk
#define F_printk(fmt, args...) #fmt ", " __stringify(args)
#undef FTRACE_ENTRY
#define FTRACE_ENTRY(call, struct_name, type, tstruct, print) \
\
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>
2009-03-30 23:48:49 -06:00
struct ftrace_event_call __used \
__attribute__((__aligned__(4))) \
__attribute__((section("_ftrace_events"))) event_##call = { \
.name = #call, \
.id = type, \
.system = __stringify(TRACE_SYSTEM), \
.raw_init = ftrace_raw_init_event, \
.print_fmt = print, \
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>
2009-03-30 23:48:49 -06:00
.define_fields = ftrace_define_fields_##call, \
}; \
#include "trace_entries.h"