android_kernel_xiaomi_sm8350/kernel/trace/trace_events.c

923 lines
18 KiB
C
Raw Normal View History

/*
* event tracer
*
* Copyright (C) 2008 Red Hat Inc, Steven Rostedt <srostedt@redhat.com>
*
* - Added format output of fields of the trace point.
* This was based off of work by Tom Zanussi <tzanussi@gmail.com>.
*
*/
#include <linux/debugfs.h>
#include <linux/uaccess.h>
#include <linux/module.h>
#include <linux/ctype.h>
#include "trace_output.h"
#define TRACE_SYSTEM "TRACE_SYSTEM"
static DEFINE_MUTEX(event_mutex);
LIST_HEAD(ftrace_events);
int trace_define_field(struct ftrace_event_call *call, char *type,
char *name, int offset, int size)
{
struct ftrace_event_field *field;
field = kzalloc(sizeof(*field), GFP_KERNEL);
if (!field)
goto err;
field->name = kstrdup(name, GFP_KERNEL);
if (!field->name)
goto err;
field->type = kstrdup(type, GFP_KERNEL);
if (!field->type)
goto err;
field->offset = offset;
field->size = size;
list_add(&field->link, &call->fields);
return 0;
err:
if (field) {
kfree(field->name);
kfree(field->type);
}
kfree(field);
return -ENOMEM;
}
EXPORT_SYMBOL_GPL(trace_define_field);
static void ftrace_clear_events(void)
{
struct ftrace_event_call *call;
list_for_each_entry(call, &ftrace_events, list) {
if (call->enabled) {
call->enabled = 0;
call->unregfunc();
}
}
}
static void ftrace_event_enable_disable(struct ftrace_event_call *call,
int enable)
{
switch (enable) {
case 0:
if (call->enabled) {
call->enabled = 0;
call->unregfunc();
}
break;
case 1:
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 17:14:30 -04:00
if (!call->enabled) {
call->enabled = 1;
call->regfunc();
}
break;
}
}
static int ftrace_set_clr_event(char *buf, int set)
{
struct ftrace_event_call *call;
char *event = NULL, *sub = NULL, *match;
int ret = -EINVAL;
/*
* The buf format can be <subsystem>:<event-name>
* *:<event-name> means any event by that name.
* :<event-name> is the same.
*
* <subsystem>:* means all events in that subsystem
* <subsystem>: means the same.
*
* <name> (no ':') means all events in a subsystem with
* the name <name> or any event that matches <name>
*/
match = strsep(&buf, ":");
if (buf) {
sub = match;
event = buf;
match = NULL;
if (!strlen(sub) || strcmp(sub, "*") == 0)
sub = NULL;
if (!strlen(event) || strcmp(event, "*") == 0)
event = NULL;
}
mutex_lock(&event_mutex);
list_for_each_entry(call, &ftrace_events, list) {
if (!call->name || !call->regfunc)
continue;
if (match &&
strcmp(match, call->name) != 0 &&
strcmp(match, call->system) != 0)
continue;
if (sub && strcmp(sub, call->system) != 0)
continue;
if (event && strcmp(event, call->name) != 0)
continue;
ftrace_event_enable_disable(call, set);
ret = 0;
}
mutex_unlock(&event_mutex);
return ret;
}
/* 128 should be much more than enough */
#define EVENT_BUF_SIZE 127
static ssize_t
ftrace_event_write(struct file *file, const char __user *ubuf,
size_t cnt, loff_t *ppos)
{
size_t read = 0;
int i, set = 1;
ssize_t ret;
char *buf;
char ch;
if (!cnt || cnt < 0)
return 0;
ret = tracing_update_buffers();
if (ret < 0)
return ret;
ret = get_user(ch, ubuf++);
if (ret)
return ret;
read++;
cnt--;
/* skip white space */
while (cnt && isspace(ch)) {
ret = get_user(ch, ubuf++);
if (ret)
return ret;
read++;
cnt--;
}
/* Only white space found? */
if (isspace(ch)) {
file->f_pos += read;
ret = read;
return ret;
}
buf = kmalloc(EVENT_BUF_SIZE+1, GFP_KERNEL);
if (!buf)
return -ENOMEM;
if (cnt > EVENT_BUF_SIZE)
cnt = EVENT_BUF_SIZE;
i = 0;
while (cnt && !isspace(ch)) {
if (!i && ch == '!')
set = 0;
else
buf[i++] = ch;
ret = get_user(ch, ubuf++);
if (ret)
goto out_free;
read++;
cnt--;
}
buf[i] = 0;
file->f_pos += read;
ret = ftrace_set_clr_event(buf, set);
if (ret)
goto out_free;
ret = read;
out_free:
kfree(buf);
return ret;
}
static void *
t_next(struct seq_file *m, void *v, loff_t *pos)
{
struct list_head *list = m->private;
struct ftrace_event_call *call;
(*pos)++;
for (;;) {
if (list == &ftrace_events)
return NULL;
call = list_entry(list, struct ftrace_event_call, list);
/*
* The ftrace subsystem is for showing formats only.
* They can not be enabled or disabled via the event files.
*/
if (call->regfunc)
break;
list = list->next;
}
m->private = list->next;
return call;
}
static void *t_start(struct seq_file *m, loff_t *pos)
{
return t_next(m, NULL, pos);
}
static void *
s_next(struct seq_file *m, void *v, loff_t *pos)
{
struct list_head *list = m->private;
struct ftrace_event_call *call;
(*pos)++;
retry:
if (list == &ftrace_events)
return NULL;
call = list_entry(list, struct ftrace_event_call, list);
if (!call->enabled) {
list = list->next;
goto retry;
}
m->private = list->next;
return call;
}
static void *s_start(struct seq_file *m, loff_t *pos)
{
return s_next(m, NULL, pos);
}
static int t_show(struct seq_file *m, void *v)
{
struct ftrace_event_call *call = v;
if (strcmp(call->system, TRACE_SYSTEM) != 0)
seq_printf(m, "%s:", call->system);
seq_printf(m, "%s\n", call->name);
return 0;
}
static void t_stop(struct seq_file *m, void *p)
{
}
static int
ftrace_event_seq_open(struct inode *inode, struct file *file)
{
int ret;
const struct seq_operations *seq_ops;
if ((file->f_mode & FMODE_WRITE) &&
!(file->f_flags & O_APPEND))
ftrace_clear_events();
seq_ops = inode->i_private;
ret = seq_open(file, seq_ops);
if (!ret) {
struct seq_file *m = file->private_data;
m->private = ftrace_events.next;
}
return ret;
}
static ssize_t
event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
char *buf;
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 17:14:30 -04:00
if (call->enabled)
buf = "1\n";
else
buf = "0\n";
return simple_read_from_buffer(ubuf, cnt, ppos, buf, 2);
}
static ssize_t
event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
char buf[64];
unsigned long val;
int ret;
if (cnt >= sizeof(buf))
return -EINVAL;
if (copy_from_user(&buf, ubuf, cnt))
return -EFAULT;
buf[cnt] = 0;
ret = strict_strtoul(buf, 10, &val);
if (ret < 0)
return ret;
ret = tracing_update_buffers();
if (ret < 0)
return ret;
switch (val) {
case 0:
case 1:
mutex_lock(&event_mutex);
ftrace_event_enable_disable(call, val);
mutex_unlock(&event_mutex);
break;
default:
return -EINVAL;
}
*ppos += cnt;
return cnt;
}
#undef FIELD
#define FIELD(type, name) \
#type, "common_" #name, offsetof(typeof(field), name), \
sizeof(field.name)
static int trace_write_header(struct trace_seq *s)
{
struct trace_entry field;
/* struct trace_entry */
return trace_seq_printf(s,
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\tfield:%s %s;\toffset:%zu;\tsize:%zu;\n"
"\n",
FIELD(unsigned char, type),
FIELD(unsigned char, flags),
FIELD(unsigned char, preempt_count),
FIELD(int, pid),
FIELD(int, tgid));
}
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 17:14:30 -04:00
static ssize_t
event_format_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
struct trace_seq *s;
char *buf;
int r;
if (*ppos)
return 0;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
trace_seq_init(s);
/* If any of the first writes fail, so will the show_format. */
trace_seq_printf(s, "name: %s\n", call->name);
trace_seq_printf(s, "ID: %d\n", call->id);
trace_seq_printf(s, "format:\n");
trace_write_header(s);
r = call->show_format(s);
if (!r) {
/*
* ug! The format output is bigger than a PAGE!!
*/
buf = "FORMAT TOO BIG\n";
r = simple_read_from_buffer(ubuf, cnt, ppos,
buf, strlen(buf));
goto out;
}
r = simple_read_from_buffer(ubuf, cnt, ppos,
s->buffer, s->len);
out:
kfree(s);
return r;
}
static ssize_t
event_id_read(struct file *filp, char __user *ubuf, size_t cnt, loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
struct trace_seq *s;
int r;
if (*ppos)
return 0;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
trace_seq_init(s);
trace_seq_printf(s, "%d\n", call->id);
r = simple_read_from_buffer(ubuf, cnt, ppos,
s->buffer, s->len);
kfree(s);
return r;
}
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
static ssize_t
event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
struct trace_seq *s;
int r;
if (*ppos)
return 0;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
trace_seq_init(s);
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 04:17:50 -04:00
filter_print_preds(call->preds, call->n_preds, s);
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
kfree(s);
return r;
}
static ssize_t
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct ftrace_event_call *call = filp->private_data;
char buf[64], *pbuf = buf;
struct filter_pred *pred;
int err;
if (cnt >= sizeof(buf))
return -EINVAL;
if (copy_from_user(&buf, ubuf, cnt))
return -EFAULT;
buf[cnt] = '\0';
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
pred = kzalloc(sizeof(*pred), GFP_KERNEL);
if (!pred)
return -ENOMEM;
err = filter_parse(&pbuf, pred);
if (err < 0) {
filter_free_pred(pred);
return err;
}
if (pred->clear) {
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 04:17:50 -04:00
filter_disable_preds(call);
filter_free_pred(pred);
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
return cnt;
}
err = filter_add_pred(call, pred);
if (err < 0) {
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
filter_free_pred(pred);
return err;
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
}
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 04:17:50 -04:00
filter_free_pred(pred);
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
*ppos += cnt;
return cnt;
}
static ssize_t
subsystem_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct event_subsystem *system = filp->private_data;
struct trace_seq *s;
int r;
if (*ppos)
return 0;
s = kmalloc(sizeof(*s), GFP_KERNEL);
if (!s)
return -ENOMEM;
trace_seq_init(s);
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 04:17:50 -04:00
filter_print_preds(system->preds, system->n_preds, s);
r = simple_read_from_buffer(ubuf, cnt, ppos, s->buffer, s->len);
kfree(s);
return r;
}
static ssize_t
subsystem_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
{
struct event_subsystem *system = filp->private_data;
char buf[64], *pbuf = buf;
struct filter_pred *pred;
int err;
if (cnt >= sizeof(buf))
return -EINVAL;
if (copy_from_user(&buf, ubuf, cnt))
return -EFAULT;
buf[cnt] = '\0';
pred = kzalloc(sizeof(*pred), GFP_KERNEL);
if (!pred)
return -ENOMEM;
err = filter_parse(&pbuf, pred);
if (err < 0) {
filter_free_pred(pred);
return err;
}
if (pred->clear) {
filter_free_subsystem_preds(system);
filter_free_pred(pred);
return cnt;
}
err = filter_add_subsystem_pred(system, pred);
if (err < 0) {
filter_free_subsystem_preds(system);
filter_free_pred(pred);
return err;
}
*ppos += cnt;
return cnt;
}
static const struct seq_operations show_event_seq_ops = {
.start = t_start,
.next = t_next,
.show = t_show,
.stop = t_stop,
};
static const struct seq_operations show_set_event_seq_ops = {
.start = s_start,
.next = s_next,
.show = t_show,
.stop = t_stop,
};
static const struct file_operations ftrace_avail_fops = {
.open = ftrace_event_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
static const struct file_operations ftrace_set_event_fops = {
.open = ftrace_event_seq_open,
.read = seq_read,
.write = ftrace_event_write,
.llseek = seq_lseek,
.release = seq_release,
};
static const struct file_operations ftrace_enable_fops = {
.open = tracing_open_generic,
.read = event_enable_read,
.write = event_enable_write,
};
static const struct file_operations ftrace_event_format_fops = {
.open = tracing_open_generic,
.read = event_format_read,
};
static const struct file_operations ftrace_event_id_fops = {
.open = tracing_open_generic,
.read = event_id_read,
};
tracing: add per-event filtering This patch adds per-event filtering to the event tracing subsystem. It adds a 'filter' debugfs file to each event directory. This file can be written to to set filters; reading from it will display the current set of filters set for that event. Basically, any field listed in the 'format' file for an event can be filtered on (including strings, but not yet other array types) using either matching ('==') or non-matching ('!=') 'predicates'. A 'predicate' can be either a single expression: # echo pid != 0 > filter # cat filter pid != 0 or a compound expression of up to 8 sub-expressions combined using '&&' or '||': # echo comm == Xorg > filter # echo "&& sig != 29" > filter # cat filter comm == Xorg && sig != 29 Only events having field values matching an expression will be available in the trace output; non-matching events are discarded. Note that a compound expression is built up by echoing each sub-expression separately - it's not the most efficient way to do things, but it keeps the parser simple and assumes that compound expressions will be relatively uncommon. In any case, a subsequent patch introducing a way to set filters for entire subsystems should mitigate any need to do this for lots of events. Setting a filter without an '&&' or '||' clears the previous filter completely and sets the filter to the new expression: # cat filter comm == Xorg && sig != 29 # echo comm != Xorg # cat filter comm != Xorg To clear a filter, echo 0 to the filter file: # echo 0 > filter # cat filter none The limit of 8 predicates for a compound expression is arbitrary - for efficiency, it's implemented as an array of pointers to predicates, and 8 seemed more than enough for any filter... Signed-off-by: Tom Zanussi <tzanussi@gmail.com> Acked-by: Frederic Weisbecker <fweisbec@gmail.com> LKML-Reference: <1237710665.7703.48.camel@charm-linux> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-03-22 04:31:04 -04:00
static const struct file_operations ftrace_event_filter_fops = {
.open = tracing_open_generic,
.read = event_filter_read,
.write = event_filter_write,
};
static const struct file_operations ftrace_subsystem_filter_fops = {
.open = tracing_open_generic,
.read = subsystem_filter_read,
.write = subsystem_filter_write,
};
static struct dentry *event_trace_events_dir(void)
{
static struct dentry *d_tracer;
static struct dentry *d_events;
if (d_events)
return d_events;
d_tracer = tracing_init_dentry();
if (!d_tracer)
return NULL;
d_events = debugfs_create_dir("events", d_tracer);
if (!d_events)
pr_warning("Could not create debugfs "
"'events' directory\n");
return d_events;
}
static LIST_HEAD(event_subsystems);
static struct dentry *
event_subsystem_dir(const char *name, struct dentry *d_events)
{
struct event_subsystem *system;
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 01:48:49 -04:00
struct dentry *entry;
/* First see if we did not already create this dir */
list_for_each_entry(system, &event_subsystems, list) {
if (strcmp(system->name, name) == 0)
return system->entry;
}
/* need to create new entry */
system = kmalloc(sizeof(*system), GFP_KERNEL);
if (!system) {
pr_warning("No memory to create event subsystem %s\n",
name);
return d_events;
}
system->entry = debugfs_create_dir(name, d_events);
if (!system->entry) {
pr_warning("Could not create event subsystem %s\n",
name);
kfree(system);
return d_events;
}
system->name = kstrdup(name, GFP_KERNEL);
if (!system->name) {
debugfs_remove(system->entry);
kfree(system);
return d_events;
}
list_add(&system->list, &event_subsystems);
system->preds = NULL;
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 04:17:50 -04:00
system->n_preds = 0;
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 01:48:49 -04:00
entry = debugfs_create_file("filter", 0644, system->entry, system,
&ftrace_subsystem_filter_fops);
if (!entry)
pr_warning("Could not create debugfs "
"'%s/filter' entry\n", name);
return system->entry;
}
static int
event_create_dir(struct ftrace_event_call *call, struct dentry *d_events)
{
struct dentry *entry;
int ret;
/*
* If the trace point header did not define TRACE_SYSTEM
* then the system would be called "TRACE_SYSTEM".
*/
if (strcmp(call->system, TRACE_SYSTEM) != 0)
d_events = event_subsystem_dir(call->system, d_events);
if (call->raw_init) {
ret = call->raw_init();
if (ret < 0) {
pr_warning("Could not initialize trace point"
" events/%s\n", call->name);
return ret;
}
}
call->dir = debugfs_create_dir(call->name, d_events);
if (!call->dir) {
pr_warning("Could not create debugfs "
"'%s' directory\n", call->name);
return -1;
}
if (call->regfunc)
entry = trace_create_file("enable", 0644, call->dir, call,
&ftrace_enable_fops);
if (call->id)
entry = trace_create_file("id", 0444, call->dir, call,
&ftrace_event_id_fops);
if (call->define_fields) {
ret = call->define_fields();
if (ret < 0) {
pr_warning("Could not initialize trace point"
" events/%s\n", call->name);
return ret;
}
entry = trace_create_file("filter", 0644, call->dir, call,
&ftrace_event_filter_fops);
}
/* A trace may not want to export its format */
if (!call->show_format)
return 0;
entry = trace_create_file("format", 0444, call->dir, call,
&ftrace_event_format_fops);
return 0;
}
#define for_each_event(event, start, end) \
for (event = start; \
(unsigned long)event < (unsigned long)end; \
event++)
#ifdef CONFIG_MODULES
static void trace_module_add_events(struct module *mod)
{
struct ftrace_event_call *call, *start, *end;
struct dentry *d_events;
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
if (start == end)
return;
d_events = event_trace_events_dir();
if (!d_events)
return;
for_each_event(call, start, end) {
/* The linker may leave blanks */
if (!call->name)
continue;
call->mod = mod;
list_add(&call->list, &ftrace_events);
event_create_dir(call, d_events);
}
}
static void trace_module_remove_events(struct module *mod)
{
struct ftrace_event_call *call, *p;
list_for_each_entry_safe(call, p, &ftrace_events, list) {
if (call->mod == mod) {
if (call->enabled) {
call->enabled = 0;
call->unregfunc();
}
if (call->event)
unregister_ftrace_event(call->event);
debugfs_remove_recursive(call->dir);
list_del(&call->list);
}
}
}
static int trace_module_notify(struct notifier_block *self,
unsigned long val, void *data)
{
struct module *mod = data;
mutex_lock(&event_mutex);
switch (val) {
case MODULE_STATE_COMING:
trace_module_add_events(mod);
break;
case MODULE_STATE_GOING:
trace_module_remove_events(mod);
break;
}
mutex_unlock(&event_mutex);
return 0;
}
#else
static int trace_module_notify(struct notifier_block *self,
unsigned long val, void *data)
{
return 0;
}
#endif /* CONFIG_MODULES */
struct notifier_block trace_module_nb = {
.notifier_call = trace_module_notify,
.priority = 0,
};
extern struct ftrace_event_call __start_ftrace_events[];
extern struct ftrace_event_call __stop_ftrace_events[];
static __init int event_trace_init(void)
{
struct ftrace_event_call *call;
struct dentry *d_tracer;
struct dentry *entry;
struct dentry *d_events;
int ret;
d_tracer = tracing_init_dentry();
if (!d_tracer)
return 0;
entry = debugfs_create_file("available_events", 0444, d_tracer,
(void *)&show_event_seq_ops,
&ftrace_avail_fops);
if (!entry)
pr_warning("Could not create debugfs "
"'available_events' entry\n");
entry = debugfs_create_file("set_event", 0644, d_tracer,
(void *)&show_set_event_seq_ops,
&ftrace_set_event_fops);
if (!entry)
pr_warning("Could not create debugfs "
"'set_event' entry\n");
d_events = event_trace_events_dir();
if (!d_events)
return 0;
for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
/* The linker may leave blanks */
if (!call->name)
continue;
list_add(&call->list, &ftrace_events);
event_create_dir(call, d_events);
}
ret = register_module_notifier(&trace_module_nb);
if (!ret)
pr_warning("Failed to register trace events module notifier\n");
return 0;
}
fs_initcall(event_trace_init);