2008-05-13 02:20:42 +07:00
|
|
|
#ifndef _LINUX_KERNEL_TRACE_H
|
|
|
|
#define _LINUX_KERNEL_TRACE_H
|
|
|
|
|
|
|
|
#include <linux/fs.h>
|
2011-07-27 06:09:06 +07:00
|
|
|
#include <linux/atomic.h>
|
2008-05-13 02:20:42 +07:00
|
|
|
#include <linux/sched.h>
|
|
|
|
#include <linux/clocksource.h>
|
2008-09-30 10:02:41 +07:00
|
|
|
#include <linux/ring_buffer.h>
|
ftrace: mmiotrace, updates
here is a patch that makes mmiotrace work almost well within the tracing
framework. The patch applies on top of my previous patch. I have my own
output formatting in place now.
Summary of changes:
- fix the NULL dereference that was due to not calling tracing_reset()
- add print_line() callback into struct tracer
- implement print_line() for mmiotrace, producing up-to-spec text
- add my output header, but that is not really called in the right place
- rewrote the main structs in mmiotrace
- added two new trace entry types: TRACE_MMIO_RW and TRACE_MMIO_MAP
- made some functions in trace.c non-static
- check current==NULL in tracing_generic_entry_update()
- fix(?) comparison in trace_seq_printf()
Things seem to work fine except a few issues. Markers (text lines injected
into mmiotrace log) are missing, I did not feel hacking them in before we
have variable length entries. My output header is printed only for 'trace'
file, but not 'trace_pipe'. For some reason, despite my quick fix,
iter->trace is NULL in print_trace_line() when called from 'trace_pipe'
file, which means I don't get proper output formatting.
I only tried by loading nouveau.ko, which just detects the card, and that
is traced fine. I didn't try further. Map, two reads and unmap. Works
perfectly.
I am missing the information about overflows, I'd prefer to have a
counter for lost events. I didn't try, but I guess currently there is no
way of knowning when it overflows?
So, not too far from being fully operational, it seems :-)
And looking at the diffstat, there also is some 700-900 lines of user space
code that just became obsolete.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 02:20:57 +07:00
|
|
|
#include <linux/mmiotrace.h>
|
2009-09-13 06:26:21 +07:00
|
|
|
#include <linux/tracepoint.h>
|
2008-09-23 17:32:08 +07:00
|
|
|
#include <linux/ftrace.h>
|
2009-09-10 00:22:48 +07:00
|
|
|
#include <linux/hw_breakpoint.h>
|
tracing: make trace_seq operations available for core kernel
In the process to make TRACE_EVENT macro work for modules, the trace_seq
operations must be available for core kernel code.
These operations are quite useful and can be used for other implementations.
The main idea is that we create a trace_seq handle that acts very much
like the seq_file handle.
struct trace_seq *s = kmalloc(sizeof(*s, GFP_KERNEL);
trace_seq_init(s);
trace_seq_printf(s, "some data %d\n", variable);
printk("%s", s->buffer);
The main use is to allow a top level function call several other functions
that may store printf like data into the buffer. Then at the end, the top
level function can process all the data with any method it would like to.
It could be passed to userspace, output via printk or even use seq_file:
trace_seq_to_user(s, ubuf, cnt);
seq_puts(m, s->buffer);
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-04-11 23:59:57 +07:00
|
|
|
#include <linux/trace_seq.h>
|
2009-04-13 22:20:49 +07:00
|
|
|
#include <linux/ftrace_event.h>
|
tracing: make trace_seq operations available for core kernel
In the process to make TRACE_EVENT macro work for modules, the trace_seq
operations must be available for core kernel code.
These operations are quite useful and can be used for other implementations.
The main idea is that we create a trace_seq handle that acts very much
like the seq_file handle.
struct trace_seq *s = kmalloc(sizeof(*s, GFP_KERNEL);
trace_seq_init(s);
trace_seq_printf(s, "some data %d\n", variable);
printk("%s", s->buffer);
The main use is to allow a top level function call several other functions
that may store printf like data into the buffer. Then at the end, the top
level function can process all the data with any method it would like to.
It could be passed to userspace, output via printk or even use seq_file:
trace_seq_to_user(s, ubuf, cnt);
seq_puts(m, s->buffer);
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-04-11 23:59:57 +07:00
|
|
|
|
2012-08-09 01:48:20 +07:00
|
|
|
#ifdef CONFIG_FTRACE_SYSCALLS
|
|
|
|
#include <asm/unistd.h> /* For NR_SYSCALLS */
|
|
|
|
#include <asm/syscall.h> /* some archs define it here */
|
|
|
|
#endif
|
|
|
|
|
2008-05-24 02:37:28 +07:00
|
|
|
enum trace_type {
|
|
|
|
__TRACE_FIRST_TYPE = 0,
|
|
|
|
|
|
|
|
TRACE_FN,
|
|
|
|
TRACE_CTX,
|
|
|
|
TRACE_WAKE,
|
|
|
|
TRACE_STACK,
|
2008-08-01 23:26:41 +07:00
|
|
|
TRACE_PRINT,
|
2009-03-13 00:24:49 +07:00
|
|
|
TRACE_BPRINT,
|
ftrace: mmiotrace, updates
here is a patch that makes mmiotrace work almost well within the tracing
framework. The patch applies on top of my previous patch. I have my own
output formatting in place now.
Summary of changes:
- fix the NULL dereference that was due to not calling tracing_reset()
- add print_line() callback into struct tracer
- implement print_line() for mmiotrace, producing up-to-spec text
- add my output header, but that is not really called in the right place
- rewrote the main structs in mmiotrace
- added two new trace entry types: TRACE_MMIO_RW and TRACE_MMIO_MAP
- made some functions in trace.c non-static
- check current==NULL in tracing_generic_entry_update()
- fix(?) comparison in trace_seq_printf()
Things seem to work fine except a few issues. Markers (text lines injected
into mmiotrace log) are missing, I did not feel hacking them in before we
have variable length entries. My output header is printed only for 'trace'
file, but not 'trace_pipe'. For some reason, despite my quick fix,
iter->trace is NULL in print_trace_line() when called from 'trace_pipe'
file, which means I don't get proper output formatting.
I only tried by loading nouveau.ko, which just detects the card, and that
is traced fine. I didn't try further. Map, two reads and unmap. Works
perfectly.
I am missing the information about overflows, I'd prefer to have a
counter for lost events. I didn't try, but I guess currently there is no
way of knowning when it overflows?
So, not too far from being fully operational, it seems :-)
And looking at the diffstat, there also is some 700-900 lines of user space
code that just became obsolete.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
2008-05-13 02:20:57 +07:00
|
|
|
TRACE_MMIO_RW,
|
|
|
|
TRACE_MMIO_MAP,
|
2008-11-13 03:24:24 +07:00
|
|
|
TRACE_BRANCH,
|
2008-11-26 06:57:25 +07:00
|
|
|
TRACE_GRAPH_RET,
|
|
|
|
TRACE_GRAPH_ENT,
|
2008-11-22 18:28:47 +07:00
|
|
|
TRACE_USER_STACK,
|
blktrace: add ftrace plugin
Impact: New way of using the blktrace infrastructure
This drops the requirement of userspace utilities to use the blktrace
facility.
Configuration is done thru sysfs, adding a "trace" directory to the
partition directory where blktrace can be enabled for the associated
request_queue.
The same filters present in the IOCTL interface are present as sysfs
device attributes.
The /sys/block/sdX/sdXN/trace/enable file allows tracing without any
filters.
The other files in this directory: pid, act_mask, start_lba and end_lba
can be used with the same meaning as with the IOCTL interface.
Using the sysfs interface will only setup the request_queue->blk_trace
fields, tracing will only take place when the "blk" tracer is selected
via the ftrace interface, as in the following example:
To see the trace, one can use the /d/tracing/trace file or the
/d/tracign/trace_pipe file, with semantics defined in the ftrace
documentation in Documentation/ftrace.txt.
[root@f10-1 ~]# cat /t/trace
kjournald-305 [000] 3046.491224: 8,1 A WBS 6367 + 8 <- (8,1) 6304
kjournald-305 [000] 3046.491227: 8,1 Q R 6367 + 8 [kjournald]
kjournald-305 [000] 3046.491236: 8,1 G RB 6367 + 8 [kjournald]
kjournald-305 [000] 3046.491239: 8,1 P NS [kjournald]
kjournald-305 [000] 3046.491242: 8,1 I RBS 6367 + 8 [kjournald]
kjournald-305 [000] 3046.491251: 8,1 D WB 6367 + 8 [kjournald]
kjournald-305 [000] 3046.491610: 8,1 U WS [kjournald] 1
<idle>-0 [000] 3046.511914: 8,1 C RS 6367 + 8 [6367]
[root@f10-1 ~]#
The default line context (prefix) format is the one described in the ftrace
documentation, with the blktrace specific bits using its existing format,
described in blkparse(8).
If one wants to have the classic blktrace formatting, this is possible by
using:
[root@f10-1 ~]# echo blk_classic > /t/trace_options
[root@f10-1 ~]# cat /t/trace
8,1 0 3046.491224 305 A WBS 6367 + 8 <- (8,1) 6304
8,1 0 3046.491227 305 Q R 6367 + 8 [kjournald]
8,1 0 3046.491236 305 G RB 6367 + 8 [kjournald]
8,1 0 3046.491239 305 P NS [kjournald]
8,1 0 3046.491242 305 I RBS 6367 + 8 [kjournald]
8,1 0 3046.491251 305 D WB 6367 + 8 [kjournald]
8,1 0 3046.491610 305 U WS [kjournald] 1
8,1 0 3046.511914 0 C RS 6367 + 8 [6367]
[root@f10-1 ~]#
Using the ftrace standard format allows more flexibility, such
as the ability of asking for backtraces via trace_options:
[root@f10-1 ~]# echo noblk_classic > /t/trace_options
[root@f10-1 ~]# echo stacktrace > /t/trace_options
[root@f10-1 ~]# cat /t/trace
kjournald-305 [000] 3318.826779: 8,1 A WBS 6375 + 8 <- (8,1) 6312
kjournald-305 [000] 3318.826782:
<= submit_bio
<= submit_bh
<= sync_dirty_buffer
<= journal_commit_transaction
<= kjournald
<= kthread
<= child_rip
kjournald-305 [000] 3318.826836: 8,1 Q R 6375 + 8 [kjournald]
kjournald-305 [000] 3318.826837:
<= generic_make_request
<= submit_bio
<= submit_bh
<= sync_dirty_buffer
<= journal_commit_transaction
<= kjournald
<= kthread
Please read the ftrace documentation to use aditional, standardized
tracing filters such as /d/tracing/trace_cpumask, etc.
See also /d/tracing/trace_mark to add comments in the trace stream,
that is equivalent to the /d/block/sdaN/msg interface.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-01-23 21:06:27 +07:00
|
|
|
TRACE_BLK,
|
2013-03-09 09:02:34 +07:00
|
|
|
TRACE_BPUTS,
|
2008-05-24 02:37:28 +07:00
|
|
|
|
2008-12-24 11:24:12 +07:00
|
|
|
__TRACE_LAST_TYPE,
|
2008-05-24 02:37:28 +07:00
|
|
|
};
|
|
|
|
|
2008-05-13 02:20:42 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef __field
|
|
|
|
#define __field(type, item) type item;
|
2008-05-13 02:20:51 +07:00
|
|
|
|
2009-09-13 06:22:23 +07:00
|
|
|
#undef __field_struct
|
|
|
|
#define __field_struct(type, item) __field(type, item)
|
2008-05-13 02:20:51 +07:00
|
|
|
|
2009-09-13 06:22:23 +07:00
|
|
|
#undef __field_desc
|
|
|
|
#define __field_desc(type, container, item)
|
2008-11-22 18:28:47 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef __array
|
|
|
|
#define __array(type, item, size) type item[size];
|
2009-03-06 23:21:47 +07:00
|
|
|
|
2009-09-13 06:22:23 +07:00
|
|
|
#undef __array_desc
|
|
|
|
#define __array_desc(type, container, item, size)
|
2008-09-30 10:02:42 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef __dynamic_array
|
|
|
|
#define __dynamic_array(type, item) type item[];
|
2008-09-30 10:02:42 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef F_STRUCT
|
|
|
|
#define F_STRUCT(args...) args
|
2008-11-12 05:24:42 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef FTRACE_ENTRY
|
2012-02-15 21:51:53 +07:00
|
|
|
#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
|
|
|
|
struct struct_name { \
|
|
|
|
struct trace_entry ent; \
|
|
|
|
tstruct \
|
2009-09-13 06:17:15 +07:00
|
|
|
}
|
2008-09-30 10:02:42 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef TP_ARGS
|
|
|
|
#define TP_ARGS(args...) args
|
2008-11-12 12:14:40 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#undef FTRACE_ENTRY_DUP
|
2012-02-15 21:51:53 +07:00
|
|
|
#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
|
2008-11-25 15:24:15 +07:00
|
|
|
|
2012-02-15 21:51:51 +07:00
|
|
|
#undef FTRACE_ENTRY_REG
|
2012-02-15 21:51:53 +07:00
|
|
|
#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
|
|
|
|
filter, regfn) \
|
|
|
|
FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
|
|
|
|
filter)
|
2012-02-15 21:51:51 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
#include "trace_entries.h"
|
2008-12-30 04:42:23 +07:00
|
|
|
|
2009-09-13 06:17:15 +07:00
|
|
|
/*
|
|
|
|
* syscalls are special, and need special handling, this is why
|
|
|
|
* they are not included in trace_entries.h
|
|
|
|
*/
|
2009-03-13 21:42:11 +07:00
|
|
|
struct syscall_trace_enter {
|
|
|
|
struct trace_entry ent;
|
|
|
|
int nr;
|
|
|
|
unsigned long args[];
|
|
|
|
};
|
|
|
|
|
|
|
|
struct syscall_trace_exit {
|
|
|
|
struct trace_entry ent;
|
|
|
|
int nr;
|
2009-11-25 14:14:59 +07:00
|
|
|
long ret;
|
2009-03-13 21:42:11 +07:00
|
|
|
};
|
|
|
|
|
tracing/kprobes: Support basic types on dynamic events
Support basic types of integer (u8, u16, u32, u64, s8, s16, s32, s64) in
kprobe tracer. With this patch, users can specify above basic types on
each arguments after ':'. If omitted, the argument type is set as
unsigned long (u32 or u64, arch-dependent).
e.g.
echo 'p account_system_time+0 hardirq_offset=%si:s32' > kprobe_events
adds a probe recording hardirq_offset in signed-32bits value on the
entry of account_system_time.
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20100412171708.3790.18599.stgit@localhost6.localdomain6>
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-04-13 00:17:08 +07:00
|
|
|
struct kprobe_trace_entry_head {
|
2009-08-14 03:35:11 +07:00
|
|
|
struct trace_entry ent;
|
|
|
|
unsigned long ip;
|
|
|
|
};
|
|
|
|
|
tracing/kprobes: Support basic types on dynamic events
Support basic types of integer (u8, u16, u32, u64, s8, s16, s32, s64) in
kprobe tracer. With this patch, users can specify above basic types on
each arguments after ':'. If omitted, the argument type is set as
unsigned long (u32 or u64, arch-dependent).
e.g.
echo 'p account_system_time+0 hardirq_offset=%si:s32' > kprobe_events
adds a probe recording hardirq_offset in signed-32bits value on the
entry of account_system_time.
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20100412171708.3790.18599.stgit@localhost6.localdomain6>
Signed-off-by: Masami Hiramatsu <mhiramat@redhat.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2010-04-13 00:17:08 +07:00
|
|
|
struct kretprobe_trace_entry_head {
|
2009-08-14 03:35:11 +07:00
|
|
|
struct trace_entry ent;
|
|
|
|
unsigned long func;
|
|
|
|
unsigned long ret_ip;
|
|
|
|
};
|
|
|
|
|
2008-09-17 02:02:27 +07:00
|
|
|
/*
|
|
|
|
* trace_flag_type is an enumeration that holds different
|
|
|
|
* states when a trace occurs. These are:
|
2008-10-24 20:42:59 +07:00
|
|
|
* IRQS_OFF - interrupts were disabled
|
2009-03-06 23:52:03 +07:00
|
|
|
* IRQS_NOSUPPORT - arch does not support irqs_disabled_flags
|
2009-09-10 08:34:19 +07:00
|
|
|
* NEED_RESCHED - reschedule is requested
|
2008-10-24 20:42:59 +07:00
|
|
|
* HARDIRQ - inside an interrupt handler
|
|
|
|
* SOFTIRQ - inside a softirq handler
|
2008-09-17 02:02:27 +07:00
|
|
|
*/
|
|
|
|
enum trace_flag_type {
|
|
|
|
TRACE_FLAG_IRQS_OFF = 0x01,
|
2008-10-24 20:42:59 +07:00
|
|
|
TRACE_FLAG_IRQS_NOSUPPORT = 0x02,
|
|
|
|
TRACE_FLAG_NEED_RESCHED = 0x04,
|
|
|
|
TRACE_FLAG_HARDIRQ = 0x08,
|
|
|
|
TRACE_FLAG_SOFTIRQ = 0x10,
|
2008-09-17 02:02:27 +07:00
|
|
|
};
|
|
|
|
|
2008-09-17 02:06:42 +07:00
|
|
|
#define TRACE_BUF_SIZE 1024
|
2008-05-13 02:20:42 +07:00
|
|
|
|
2012-05-12 00:29:49 +07:00
|
|
|
struct trace_array;
|
|
|
|
|
|
|
|
struct trace_cpu {
|
|
|
|
struct trace_array *tr;
|
|
|
|
struct dentry *dir;
|
|
|
|
int cpu;
|
|
|
|
};
|
|
|
|
|
2008-05-13 02:20:42 +07:00
|
|
|
/*
|
|
|
|
* The CPU trace array - it consists of thousands of trace entries
|
|
|
|
* plus some other descriptor data: (for example which task started
|
|
|
|
* the trace, etc.)
|
|
|
|
*/
|
|
|
|
struct trace_array_cpu {
|
2012-05-12 00:29:49 +07:00
|
|
|
struct trace_cpu trace_cpu;
|
2008-05-13 02:20:42 +07:00
|
|
|
atomic_t disabled;
|
2008-12-02 10:20:19 +07:00
|
|
|
void *buffer_page; /* ring buffer spare */
|
2008-05-13 02:20:45 +07:00
|
|
|
|
2012-02-03 03:00:41 +07:00
|
|
|
unsigned long entries;
|
2008-05-13 02:20:42 +07:00
|
|
|
unsigned long saved_latency;
|
|
|
|
unsigned long critical_start;
|
|
|
|
unsigned long critical_end;
|
|
|
|
unsigned long critical_sequence;
|
|
|
|
unsigned long nice;
|
|
|
|
unsigned long policy;
|
|
|
|
unsigned long rt_priority;
|
2009-09-01 22:06:29 +07:00
|
|
|
unsigned long skipped_entries;
|
2008-05-13 02:20:42 +07:00
|
|
|
cycle_t preempt_timestamp;
|
|
|
|
pid_t pid;
|
2012-03-14 06:02:19 +07:00
|
|
|
kuid_t uid;
|
2008-05-13 02:20:42 +07:00
|
|
|
char comm[TASK_COMM_LEN];
|
|
|
|
};
|
|
|
|
|
2012-05-12 00:29:49 +07:00
|
|
|
struct tracer;
|
|
|
|
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
struct trace_buffer {
|
|
|
|
struct trace_array *tr;
|
|
|
|
struct ring_buffer *buffer;
|
|
|
|
struct trace_array_cpu __percpu *data;
|
|
|
|
cycle_t time_start;
|
|
|
|
int cpu;
|
|
|
|
};
|
|
|
|
|
2008-05-13 02:20:42 +07:00
|
|
|
/*
|
|
|
|
* The trace array - an array of per-CPU trace arrays. This is the
|
|
|
|
* highest level data structure that individual tracers deal with.
|
|
|
|
* They have on/off state as well:
|
|
|
|
*/
|
|
|
|
struct trace_array {
|
2012-05-04 10:09:03 +07:00
|
|
|
struct list_head list;
|
2012-08-04 03:10:49 +07:00
|
|
|
char *name;
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
struct trace_buffer trace_buffer;
|
|
|
|
#ifdef CONFIG_TRACER_MAX_TRACE
|
|
|
|
/*
|
|
|
|
* The max_buffer is used to snapshot the trace when a maximum
|
|
|
|
* latency is reached, or when the user initiates a snapshot.
|
|
|
|
* Some tracers will use this to store a maximum trace while
|
|
|
|
* it continues examining live traces.
|
|
|
|
*
|
|
|
|
* The buffers for the max_buffer are set up the same as the trace_buffer
|
|
|
|
* When a snapshot is taken, the buffer of the max_buffer is swapped
|
|
|
|
* with the buffer of the trace_buffer and the buffers are reset for
|
|
|
|
* the trace_buffer so the tracing can continue.
|
|
|
|
*/
|
|
|
|
struct trace_buffer max_buffer;
|
2013-03-06 06:25:02 +07:00
|
|
|
bool allocated_snapshot;
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
#endif
|
2012-02-23 03:50:28 +07:00
|
|
|
int buffer_disabled;
|
2012-05-12 00:29:49 +07:00
|
|
|
struct trace_cpu trace_cpu; /* place holder */
|
2012-08-09 01:48:20 +07:00
|
|
|
#ifdef CONFIG_FTRACE_SYSCALLS
|
|
|
|
int sys_refcount_enter;
|
|
|
|
int sys_refcount_exit;
|
|
|
|
DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
|
|
|
|
DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
|
|
|
|
#endif
|
2012-05-12 00:29:49 +07:00
|
|
|
int stop_count;
|
|
|
|
int clock_id;
|
|
|
|
struct tracer *current_trace;
|
2012-05-04 10:09:03 +07:00
|
|
|
unsigned int flags;
|
2012-05-12 00:29:49 +07:00
|
|
|
raw_spinlock_t start_lock;
|
2012-05-04 10:09:03 +07:00
|
|
|
struct dentry *dir;
|
2012-05-12 00:29:49 +07:00
|
|
|
struct dentry *options;
|
|
|
|
struct dentry *percpu_dir;
|
2012-05-04 10:09:03 +07:00
|
|
|
struct dentry *event_dir;
|
|
|
|
struct list_head systems;
|
|
|
|
struct list_head events;
|
2008-05-13 02:20:46 +07:00
|
|
|
struct task_struct *waiter;
|
2013-03-07 03:27:24 +07:00
|
|
|
int ref;
|
2008-05-13 02:20:42 +07:00
|
|
|
};
|
|
|
|
|
2012-05-04 10:09:03 +07:00
|
|
|
enum {
|
|
|
|
TRACE_ARRAY_FL_GLOBAL = (1 << 0)
|
|
|
|
};
|
|
|
|
|
|
|
|
extern struct list_head ftrace_trace_arrays;
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The global tracer (top) should be the first trace array added,
|
|
|
|
* but we check the flag anyway.
|
|
|
|
*/
|
|
|
|
static inline struct trace_array *top_trace_array(void)
|
|
|
|
{
|
|
|
|
struct trace_array *tr;
|
|
|
|
|
|
|
|
tr = list_entry(ftrace_trace_arrays.prev,
|
|
|
|
typeof(*tr), list);
|
|
|
|
WARN_ON(!(tr->flags & TRACE_ARRAY_FL_GLOBAL));
|
|
|
|
return tr;
|
|
|
|
}
|
|
|
|
|
2008-10-01 21:52:51 +07:00
|
|
|
#define FTRACE_CMP_TYPE(var, type) \
|
|
|
|
__builtin_types_compatible_p(typeof(var), type *)
|
|
|
|
|
|
|
|
#undef IF_ASSIGN
|
|
|
|
#define IF_ASSIGN(var, entry, etype, id) \
|
|
|
|
if (FTRACE_CMP_TYPE(var, etype)) { \
|
|
|
|
var = (typeof(var))(entry); \
|
|
|
|
WARN_ON(id && (entry)->type != id); \
|
|
|
|
break; \
|
|
|
|
}
|
|
|
|
|
|
|
|
/* Will cause compile errors if type is not found. */
|
|
|
|
extern void __ftrace_bad_type(void);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The trace_assign_type is a verifier that the entry type is
|
|
|
|
* the same as the type being assigned. To add new types simply
|
|
|
|
* add a line with the following format:
|
|
|
|
*
|
|
|
|
* IF_ASSIGN(var, ent, type, id);
|
|
|
|
*
|
|
|
|
* Where "type" is the trace type that includes the trace_entry
|
|
|
|
* as the "ent" item. And "id" is the trace identifier that is
|
|
|
|
* used in the trace_type enum.
|
|
|
|
*
|
|
|
|
* If the type can have more than one id, then use zero.
|
|
|
|
*/
|
|
|
|
#define trace_assign_type(var, ent) \
|
|
|
|
do { \
|
|
|
|
IF_ASSIGN(var, ent, struct ftrace_entry, TRACE_FN); \
|
|
|
|
IF_ASSIGN(var, ent, struct ctx_switch_entry, 0); \
|
|
|
|
IF_ASSIGN(var, ent, struct stack_entry, TRACE_STACK); \
|
2008-11-22 18:28:47 +07:00
|
|
|
IF_ASSIGN(var, ent, struct userstack_entry, TRACE_USER_STACK);\
|
2008-10-01 21:52:51 +07:00
|
|
|
IF_ASSIGN(var, ent, struct print_entry, TRACE_PRINT); \
|
2009-03-13 00:24:49 +07:00
|
|
|
IF_ASSIGN(var, ent, struct bprint_entry, TRACE_BPRINT); \
|
2013-03-09 09:02:34 +07:00
|
|
|
IF_ASSIGN(var, ent, struct bputs_entry, TRACE_BPUTS); \
|
2008-10-01 21:52:51 +07:00
|
|
|
IF_ASSIGN(var, ent, struct trace_mmiotrace_rw, \
|
|
|
|
TRACE_MMIO_RW); \
|
|
|
|
IF_ASSIGN(var, ent, struct trace_mmiotrace_map, \
|
|
|
|
TRACE_MMIO_MAP); \
|
2008-11-13 03:24:24 +07:00
|
|
|
IF_ASSIGN(var, ent, struct trace_branch, TRACE_BRANCH); \
|
2008-11-26 06:57:25 +07:00
|
|
|
IF_ASSIGN(var, ent, struct ftrace_graph_ent_entry, \
|
|
|
|
TRACE_GRAPH_ENT); \
|
|
|
|
IF_ASSIGN(var, ent, struct ftrace_graph_ret_entry, \
|
|
|
|
TRACE_GRAPH_RET); \
|
2008-10-01 21:52:51 +07:00
|
|
|
__ftrace_bad_type(); \
|
|
|
|
} while (0)
|
2008-09-30 01:18:34 +07:00
|
|
|
|
2008-11-18 01:23:42 +07:00
|
|
|
/*
|
|
|
|
* An option specific to a tracer. This is a boolean value.
|
|
|
|
* The bit is the bit index that sets its value on the
|
|
|
|
* flags value in struct tracer_flags.
|
|
|
|
*/
|
|
|
|
struct tracer_opt {
|
2009-03-06 23:52:03 +07:00
|
|
|
const char *name; /* Will appear on the trace_options file */
|
|
|
|
u32 bit; /* Mask assigned in val field in tracer_flags */
|
2008-11-18 01:23:42 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
/*
|
|
|
|
* The set of specific options for a tracer. Your tracer
|
|
|
|
* have to set the initial value of the flags val.
|
|
|
|
*/
|
|
|
|
struct tracer_flags {
|
|
|
|
u32 val;
|
2009-03-06 23:52:03 +07:00
|
|
|
struct tracer_opt *opts;
|
2008-11-18 01:23:42 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
/* Makes more easy to define a tracer opt */
|
|
|
|
#define TRACER_OPT(s, b) .name = #s, .bit = b
|
|
|
|
|
2009-01-09 01:03:56 +07:00
|
|
|
|
2009-02-11 08:25:00 +07:00
|
|
|
/**
|
|
|
|
* struct tracer - a specific tracer and its callbacks to interact with debugfs
|
|
|
|
* @name: the name chosen to select it on the available_tracers file
|
|
|
|
* @init: called when one switches to this tracer (echo name > current_tracer)
|
|
|
|
* @reset: called when one switches to another tracer
|
|
|
|
* @start: called when tracing is unpaused (echo 1 > tracing_enabled)
|
|
|
|
* @stop: called when tracing is paused (echo 0 > tracing_enabled)
|
|
|
|
* @open: called when the trace file is opened
|
|
|
|
* @pipe_open: called when the trace_pipe file is opened
|
|
|
|
* @wait_pipe: override how the user waits for traces on trace_pipe
|
|
|
|
* @close: called when the trace file is released
|
2009-12-07 21:06:24 +07:00
|
|
|
* @pipe_close: called when the trace_pipe file is released
|
2009-02-11 08:25:00 +07:00
|
|
|
* @read: override the default read callback on trace_pipe
|
|
|
|
* @splice_read: override the default splice_read callback on trace_pipe
|
|
|
|
* @selftest: selftest to run on boot (see trace_selftest.c)
|
|
|
|
* @print_headers: override the first lines that describe your columns
|
|
|
|
* @print_line: callback that prints a trace
|
|
|
|
* @set_flag: signals one of your private flags changed (trace_options file)
|
|
|
|
* @flags: your private flags
|
2008-05-13 02:20:42 +07:00
|
|
|
*/
|
|
|
|
struct tracer {
|
|
|
|
const char *name;
|
2008-11-16 11:57:26 +07:00
|
|
|
int (*init)(struct trace_array *tr);
|
2008-05-13 02:20:42 +07:00
|
|
|
void (*reset)(struct trace_array *tr);
|
ftrace: restructure tracing start/stop infrastructure
Impact: change where tracing is started up and stopped
Currently, when a new tracer is selected via echo'ing a tracer name into
the current_tracer file, the startup is only done if tracing_enabled is
set to one. If tracing_enabled is changed to zero (by echo'ing 0 into
the tracing_enabled file) a full shutdown is performed.
The full startup and shutdown of a tracer can be expensive and the
user can lose out traces when echo'ing in 0 to the tracing_enabled file,
because the process takes too long. There can also be places that
the user would like to start and stop the tracer several times and
doing the full startup and shutdown of a tracer might be too expensive.
This patch performs the full startup and shutdown when a tracer is
selected. It also adds a way to do a quick start or stop of a tracer.
The quick version is just a flag that prevents the tracing from
taking place, but the overhead of the code is still there.
For example, the startup of a tracer may enable tracepoints, or enable
the function tracer. The stop and start will just set a flag to
have the tracer ignore the calls when the tracepoint or function trace
is called. The overhead of the tracer may still be present when
the tracer is stopped, but no tracing will occur. Setting the tracer
to the 'nop' tracer (or any other tracer) will perform the shutdown
of the tracer which will disable the tracepoint or disable the
function tracer.
The tracing_enabled file will simply start or stop tracing.
This change is all internal. The end result for the user should be the same
as before. If tracing_enabled is not set, no trace will happen.
If tracing_enabled is set, then the trace will happen. The tracing_enabled
variable is static between tracers. Enabling tracing_enabled and
going to another tracer will keep tracing_enabled enabled. Same
is true with disabling tracing_enabled.
This patch will now provide a fast start/stop method to the users
for enabling or disabling tracing.
Note: There were two methods to the struct tracer that were never
used: The methods start and stop. These were to be used as a hook
to the reading of the trace output, but ended up not being
necessary. These two methods are now used to enable the start
and stop of each tracer, in case the tracer needs to do more than
just not write into the buffer. For example, the irqsoff tracer
must stop recording max latencies when tracing is stopped.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-06 04:05:44 +07:00
|
|
|
void (*start)(struct trace_array *tr);
|
|
|
|
void (*stop)(struct trace_array *tr);
|
2008-05-13 02:20:42 +07:00
|
|
|
void (*open)(struct trace_iterator *iter);
|
2008-05-13 02:21:01 +07:00
|
|
|
void (*pipe_open)(struct trace_iterator *iter);
|
2009-02-11 08:25:00 +07:00
|
|
|
void (*wait_pipe)(struct trace_iterator *iter);
|
2008-05-13 02:20:42 +07:00
|
|
|
void (*close)(struct trace_iterator *iter);
|
2009-12-07 21:06:24 +07:00
|
|
|
void (*pipe_close)(struct trace_iterator *iter);
|
2008-05-13 02:21:01 +07:00
|
|
|
ssize_t (*read)(struct trace_iterator *iter,
|
|
|
|
struct file *filp, char __user *ubuf,
|
|
|
|
size_t cnt, loff_t *ppos);
|
2009-02-09 13:15:56 +07:00
|
|
|
ssize_t (*splice_read)(struct trace_iterator *iter,
|
|
|
|
struct file *filp,
|
|
|
|
loff_t *ppos,
|
|
|
|
struct pipe_inode_info *pipe,
|
|
|
|
size_t len,
|
|
|
|
unsigned int flags);
|
2008-05-13 02:20:44 +07:00
|
|
|
#ifdef CONFIG_FTRACE_STARTUP_TEST
|
|
|
|
int (*selftest)(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
#endif
|
2008-11-25 15:12:31 +07:00
|
|
|
void (*print_header)(struct seq_file *m);
|
2008-09-30 01:18:34 +07:00
|
|
|
enum print_line_t (*print_line)(struct trace_iterator *iter);
|
2008-11-18 01:23:42 +07:00
|
|
|
/* If you handled the flag setting, return 0 */
|
|
|
|
int (*set_flag)(u32 old_flags, u32 bit, int set);
|
2013-03-15 02:03:53 +07:00
|
|
|
/* Return 0 if OK with change, else return non-zero */
|
|
|
|
int (*flag_changed)(struct tracer *tracer,
|
|
|
|
u32 mask, int set);
|
2008-05-13 02:20:42 +07:00
|
|
|
struct tracer *next;
|
2009-03-06 23:52:03 +07:00
|
|
|
struct tracer_flags *flags;
|
2012-10-02 15:27:10 +07:00
|
|
|
bool print_max;
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
bool enabled;
|
|
|
|
#ifdef CONFIG_TRACER_MAX_TRACE
|
2012-10-02 15:27:10 +07:00
|
|
|
bool use_max_tr;
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
#endif
|
2008-05-13 02:20:42 +07:00
|
|
|
};
|
|
|
|
|
2009-03-03 02:04:40 +07:00
|
|
|
|
2011-06-15 06:02:29 +07:00
|
|
|
/* Only current can touch trace_recursion */
|
|
|
|
|
2012-11-03 04:47:21 +07:00
|
|
|
/*
|
|
|
|
* For function tracing recursion:
|
|
|
|
* The order of these bits are important.
|
|
|
|
*
|
|
|
|
* When function tracing occurs, the following steps are made:
|
|
|
|
* If arch does not support a ftrace feature:
|
|
|
|
* call internal function (uses INTERNAL bits) which calls...
|
|
|
|
* If callback is registered to the "global" list, the list
|
|
|
|
* function is called and recursion checks the GLOBAL bits.
|
|
|
|
* then this function calls...
|
|
|
|
* The function callback, which can use the FTRACE bits to
|
|
|
|
* check for recursion.
|
|
|
|
*
|
|
|
|
* Now if the arch does not suppport a feature, and it calls
|
|
|
|
* the global list function which calls the ftrace callback
|
|
|
|
* all three of these steps will do a recursion protection.
|
|
|
|
* There's no reason to do one if the previous caller already
|
|
|
|
* did. The recursion that we are protecting against will
|
|
|
|
* go through the same steps again.
|
|
|
|
*
|
|
|
|
* To prevent the multiple recursion checks, if a recursion
|
|
|
|
* bit is set that is higher than the MAX bit of the current
|
|
|
|
* check, then we know that the check was made by the previous
|
|
|
|
* caller, and we can skip the current check.
|
|
|
|
*/
|
2012-11-03 04:32:25 +07:00
|
|
|
enum {
|
2012-11-03 05:33:05 +07:00
|
|
|
TRACE_BUFFER_BIT,
|
|
|
|
TRACE_BUFFER_NMI_BIT,
|
|
|
|
TRACE_BUFFER_IRQ_BIT,
|
|
|
|
TRACE_BUFFER_SIRQ_BIT,
|
|
|
|
|
|
|
|
/* Start of function recursion bits */
|
|
|
|
TRACE_FTRACE_BIT,
|
2012-11-03 04:47:21 +07:00
|
|
|
TRACE_FTRACE_NMI_BIT,
|
|
|
|
TRACE_FTRACE_IRQ_BIT,
|
|
|
|
TRACE_FTRACE_SIRQ_BIT,
|
2012-11-03 04:32:25 +07:00
|
|
|
|
2012-11-03 04:47:21 +07:00
|
|
|
/* GLOBAL_BITs must be greater than FTRACE_BITs */
|
2012-11-03 04:32:25 +07:00
|
|
|
TRACE_GLOBAL_BIT,
|
|
|
|
TRACE_GLOBAL_NMI_BIT,
|
|
|
|
TRACE_GLOBAL_IRQ_BIT,
|
|
|
|
TRACE_GLOBAL_SIRQ_BIT,
|
|
|
|
|
2012-11-03 04:47:21 +07:00
|
|
|
/* INTERNAL_BITs must be greater than GLOBAL_BITs */
|
|
|
|
TRACE_INTERNAL_BIT,
|
|
|
|
TRACE_INTERNAL_NMI_BIT,
|
|
|
|
TRACE_INTERNAL_IRQ_BIT,
|
|
|
|
TRACE_INTERNAL_SIRQ_BIT,
|
|
|
|
|
2012-11-03 04:32:25 +07:00
|
|
|
TRACE_CONTROL_BIT,
|
2012-02-15 21:51:48 +07:00
|
|
|
|
2011-06-15 06:02:29 +07:00
|
|
|
/*
|
|
|
|
* Abuse of the trace_recursion.
|
|
|
|
* As we need a way to maintain state if we are tracing the function
|
|
|
|
* graph in irq because we want to trace a particular function that
|
|
|
|
* was called in irq context but we have irq tracing off. Since this
|
|
|
|
* can only be modified by current, we can reuse trace_recursion.
|
|
|
|
*/
|
2012-11-03 04:32:25 +07:00
|
|
|
TRACE_IRQ_BIT,
|
|
|
|
};
|
2011-06-15 06:02:29 +07:00
|
|
|
|
2012-11-03 04:32:25 +07:00
|
|
|
#define trace_recursion_set(bit) do { (current)->trace_recursion |= (1<<(bit)); } while (0)
|
|
|
|
#define trace_recursion_clear(bit) do { (current)->trace_recursion &= ~(1<<(bit)); } while (0)
|
|
|
|
#define trace_recursion_test(bit) ((current)->trace_recursion & (1<<(bit)))
|
2011-06-15 06:02:29 +07:00
|
|
|
|
2012-11-03 04:47:21 +07:00
|
|
|
#define TRACE_CONTEXT_BITS 4
|
|
|
|
|
|
|
|
#define TRACE_FTRACE_START TRACE_FTRACE_BIT
|
|
|
|
#define TRACE_FTRACE_MAX ((1 << (TRACE_FTRACE_START + TRACE_CONTEXT_BITS)) - 1)
|
|
|
|
|
|
|
|
#define TRACE_GLOBAL_START TRACE_GLOBAL_BIT
|
|
|
|
#define TRACE_GLOBAL_MAX ((1 << (TRACE_GLOBAL_START + TRACE_CONTEXT_BITS)) - 1)
|
|
|
|
|
|
|
|
#define TRACE_LIST_START TRACE_INTERNAL_BIT
|
|
|
|
#define TRACE_LIST_MAX ((1 << (TRACE_LIST_START + TRACE_CONTEXT_BITS)) - 1)
|
|
|
|
|
|
|
|
#define TRACE_CONTEXT_MASK TRACE_LIST_MAX
|
|
|
|
|
|
|
|
static __always_inline int trace_get_context_bit(void)
|
|
|
|
{
|
|
|
|
int bit;
|
|
|
|
|
|
|
|
if (in_interrupt()) {
|
|
|
|
if (in_nmi())
|
|
|
|
bit = 0;
|
|
|
|
|
|
|
|
else if (in_irq())
|
|
|
|
bit = 1;
|
|
|
|
else
|
|
|
|
bit = 2;
|
|
|
|
} else
|
|
|
|
bit = 3;
|
|
|
|
|
|
|
|
return bit;
|
|
|
|
}
|
|
|
|
|
|
|
|
static __always_inline int trace_test_and_set_recursion(int start, int max)
|
|
|
|
{
|
|
|
|
unsigned int val = current->trace_recursion;
|
|
|
|
int bit;
|
|
|
|
|
|
|
|
/* A previous recursion check was made */
|
|
|
|
if ((val & TRACE_CONTEXT_MASK) > max)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
bit = trace_get_context_bit() + start;
|
|
|
|
if (unlikely(val & (1 << bit)))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
val |= 1 << bit;
|
|
|
|
current->trace_recursion = val;
|
|
|
|
barrier();
|
|
|
|
|
|
|
|
return bit;
|
|
|
|
}
|
|
|
|
|
|
|
|
static __always_inline void trace_clear_recursion(int bit)
|
|
|
|
{
|
|
|
|
unsigned int val = current->trace_recursion;
|
|
|
|
|
|
|
|
if (!bit)
|
|
|
|
return;
|
|
|
|
|
|
|
|
bit = 1 << bit;
|
|
|
|
val &= ~bit;
|
|
|
|
|
|
|
|
barrier();
|
|
|
|
current->trace_recursion = val;
|
|
|
|
}
|
|
|
|
|
2012-06-28 07:46:14 +07:00
|
|
|
static inline struct ring_buffer_iter *
|
|
|
|
trace_buffer_iter(struct trace_iterator *iter, int cpu)
|
|
|
|
{
|
|
|
|
if (iter->buffer_iter && iter->buffer_iter[cpu])
|
|
|
|
return iter->buffer_iter[cpu];
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2009-02-06 03:02:00 +07:00
|
|
|
int tracer_init(struct tracer *t, struct trace_array *tr);
|
ftrace: restructure tracing start/stop infrastructure
Impact: change where tracing is started up and stopped
Currently, when a new tracer is selected via echo'ing a tracer name into
the current_tracer file, the startup is only done if tracing_enabled is
set to one. If tracing_enabled is changed to zero (by echo'ing 0 into
the tracing_enabled file) a full shutdown is performed.
The full startup and shutdown of a tracer can be expensive and the
user can lose out traces when echo'ing in 0 to the tracing_enabled file,
because the process takes too long. There can also be places that
the user would like to start and stop the tracer several times and
doing the full startup and shutdown of a tracer might be too expensive.
This patch performs the full startup and shutdown when a tracer is
selected. It also adds a way to do a quick start or stop of a tracer.
The quick version is just a flag that prevents the tracing from
taking place, but the overhead of the code is still there.
For example, the startup of a tracer may enable tracepoints, or enable
the function tracer. The stop and start will just set a flag to
have the tracer ignore the calls when the tracepoint or function trace
is called. The overhead of the tracer may still be present when
the tracer is stopped, but no tracing will occur. Setting the tracer
to the 'nop' tracer (or any other tracer) will perform the shutdown
of the tracer which will disable the tracepoint or disable the
function tracer.
The tracing_enabled file will simply start or stop tracing.
This change is all internal. The end result for the user should be the same
as before. If tracing_enabled is not set, no trace will happen.
If tracing_enabled is set, then the trace will happen. The tracing_enabled
variable is static between tracers. Enabling tracing_enabled and
going to another tracer will keep tracing_enabled enabled. Same
is true with disabling tracing_enabled.
This patch will now provide a fast start/stop method to the users
for enabling or disabling tracing.
Note: There were two methods to the struct tracer that were never
used: The methods start and stop. These were to be used as a hook
to the reading of the trace output, but ended up not being
necessary. These two methods are now used to enable the start
and stop of each tracer, in case the tracer needs to do more than
just not write into the buffer. For example, the irqsoff tracer
must stop recording max latencies when tracing is stopped.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2008-11-06 04:05:44 +07:00
|
|
|
int tracing_is_enabled(void);
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
void tracing_reset(struct trace_buffer *buf, int cpu);
|
|
|
|
void tracing_reset_online_cpus(struct trace_buffer *buf);
|
2009-05-07 08:54:09 +07:00
|
|
|
void tracing_reset_current(int cpu);
|
2013-03-05 11:26:06 +07:00
|
|
|
void tracing_reset_all_online_cpus(void);
|
2008-05-13 02:20:42 +07:00
|
|
|
int tracing_open_generic(struct inode *inode, struct file *filp);
|
2009-03-27 06:25:38 +07:00
|
|
|
struct dentry *trace_create_file(const char *name,
|
2011-07-24 15:33:43 +07:00
|
|
|
umode_t mode,
|
2009-03-27 06:25:38 +07:00
|
|
|
struct dentry *parent,
|
|
|
|
void *data,
|
|
|
|
const struct file_operations *fops);
|
|
|
|
|
2012-05-12 00:29:49 +07:00
|
|
|
struct dentry *tracing_init_dentry_tr(struct trace_array *tr);
|
2008-05-13 02:20:42 +07:00
|
|
|
struct dentry *tracing_init_dentry(void);
|
2008-05-13 02:20:49 +07:00
|
|
|
|
tracing: Introduce trace_buffer_{lock_reserve,unlock_commit}
Impact: new API
These new functions do what previously was being open coded, reducing
the number of details ftrace plugin writers have to worry about.
It also standardizes the handling of stacktrace, userstacktrace and
other trace options we may introduce in the future.
With this patch, for instance, the blk tracer (and some others already
in the tree) can use the "userstacktrace" /d/tracing/trace_options
facility.
$ codiff /tmp/vmlinux.before /tmp/vmlinux.after
linux-2.6-tip/kernel/trace/trace.c:
trace_vprintk | -5
trace_graph_return | -22
trace_graph_entry | -26
trace_function | -45
__ftrace_trace_stack | -27
ftrace_trace_userstack | -29
tracing_sched_switch_trace | -66
tracing_stop | +1
trace_seq_to_user | -1
ftrace_trace_special | -63
ftrace_special | +1
tracing_sched_wakeup_trace | -70
tracing_reset_online_cpus | -1
13 functions changed, 2 bytes added, 355 bytes removed, diff: -353
linux-2.6-tip/block/blktrace.c:
__blk_add_trace | -58
1 function changed, 58 bytes removed, diff: -58
linux-2.6-tip/kernel/trace/trace.c:
trace_buffer_lock_reserve | +88
trace_buffer_unlock_commit | +86
2 functions changed, 174 bytes added, diff: +174
/tmp/vmlinux.after:
16 functions changed, 176 bytes added, 413 bytes removed, diff: -237
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Frédéric Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-06 01:14:13 +07:00
|
|
|
struct ring_buffer_event;
|
|
|
|
|
2009-09-03 01:17:06 +07:00
|
|
|
struct ring_buffer_event *
|
|
|
|
trace_buffer_lock_reserve(struct ring_buffer *buffer,
|
|
|
|
int type,
|
|
|
|
unsigned long len,
|
|
|
|
unsigned long flags,
|
|
|
|
int pc);
|
tracing: Introduce trace_buffer_{lock_reserve,unlock_commit}
Impact: new API
These new functions do what previously was being open coded, reducing
the number of details ftrace plugin writers have to worry about.
It also standardizes the handling of stacktrace, userstacktrace and
other trace options we may introduce in the future.
With this patch, for instance, the blk tracer (and some others already
in the tree) can use the "userstacktrace" /d/tracing/trace_options
facility.
$ codiff /tmp/vmlinux.before /tmp/vmlinux.after
linux-2.6-tip/kernel/trace/trace.c:
trace_vprintk | -5
trace_graph_return | -22
trace_graph_entry | -26
trace_function | -45
__ftrace_trace_stack | -27
ftrace_trace_userstack | -29
tracing_sched_switch_trace | -66
tracing_stop | +1
trace_seq_to_user | -1
ftrace_trace_special | -63
ftrace_special | +1
tracing_sched_wakeup_trace | -70
tracing_reset_online_cpus | -1
13 functions changed, 2 bytes added, 355 bytes removed, diff: -353
linux-2.6-tip/block/blktrace.c:
__blk_add_trace | -58
1 function changed, 58 bytes removed, diff: -58
linux-2.6-tip/kernel/trace/trace.c:
trace_buffer_lock_reserve | +88
trace_buffer_unlock_commit | +86
2 functions changed, 174 bytes added, diff: +174
/tmp/vmlinux.after:
16 functions changed, 176 bytes added, 413 bytes removed, diff: -237
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Frédéric Weisbecker <fweisbec@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-02-06 01:14:13 +07:00
|
|
|
|
2008-09-17 01:56:41 +07:00
|
|
|
struct trace_entry *tracing_get_trace_entry(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data);
|
2009-02-03 05:29:21 +07:00
|
|
|
|
|
|
|
struct trace_entry *trace_find_next_entry(struct trace_iterator *iter,
|
|
|
|
int *ent_cpu, u64 *ent_ts);
|
|
|
|
|
2012-10-11 23:14:25 +07:00
|
|
|
void __buffer_unlock_commit(struct ring_buffer *buffer,
|
|
|
|
struct ring_buffer_event *event);
|
|
|
|
|
2010-08-05 21:22:23 +07:00
|
|
|
int trace_empty(struct trace_iterator *iter);
|
|
|
|
|
|
|
|
void *trace_find_next_entry_inc(struct trace_iterator *iter);
|
|
|
|
|
|
|
|
void trace_init_global_iter(struct trace_iterator *iter);
|
|
|
|
|
|
|
|
void tracing_iter_reset(struct trace_iterator *iter, int cpu);
|
|
|
|
|
2009-02-11 08:25:00 +07:00
|
|
|
void poll_wait_pipe(struct trace_iterator *iter);
|
|
|
|
|
2008-05-13 02:20:42 +07:00
|
|
|
void ftrace(struct trace_array *tr,
|
|
|
|
struct trace_array_cpu *data,
|
|
|
|
unsigned long ip,
|
|
|
|
unsigned long parent_ip,
|
2008-10-02 00:14:09 +07:00
|
|
|
unsigned long flags, int pc);
|
2008-05-13 02:20:42 +07:00
|
|
|
void tracing_sched_switch_trace(struct trace_array *tr,
|
|
|
|
struct task_struct *prev,
|
|
|
|
struct task_struct *next,
|
2008-10-02 00:14:09 +07:00
|
|
|
unsigned long flags, int pc);
|
2008-05-13 02:20:51 +07:00
|
|
|
|
|
|
|
void tracing_sched_wakeup_trace(struct trace_array *tr,
|
|
|
|
struct task_struct *wakee,
|
|
|
|
struct task_struct *cur,
|
2008-10-02 00:14:09 +07:00
|
|
|
unsigned long flags, int pc);
|
2008-05-13 02:20:49 +07:00
|
|
|
void trace_function(struct trace_array *tr,
|
|
|
|
unsigned long ip,
|
|
|
|
unsigned long parent_ip,
|
2008-10-02 00:14:09 +07:00
|
|
|
unsigned long flags, int pc);
|
2010-09-23 19:00:52 +07:00
|
|
|
void trace_graph_function(struct trace_array *tr,
|
|
|
|
unsigned long ip,
|
|
|
|
unsigned long parent_ip,
|
|
|
|
unsigned long flags, int pc);
|
tracing/latency: Fix header output for latency tracers
In case the the graph tracer (CONFIG_FUNCTION_GRAPH_TRACER) or even the
function tracer (CONFIG_FUNCTION_TRACER) are not set, the latency tracers
do not display proper latency header.
The involved/fixed latency tracers are:
wakeup_rt
wakeup
preemptirqsoff
preemptoff
irqsoff
The patch adds proper handling of tracer configuration options for latency
tracers, and displaying correct header info accordingly.
* The current output (for wakeup tracer) with both graph and function
tracers disabled is:
# tracer: wakeup
#
<idle>-0 0d.h5 1us+: 0:120:R + [000] 7: 0:R watchdog/0
<idle>-0 0d.h5 3us+: ttwu_do_activate.clone.1 <-try_to_wake_up
...
* The fixed output is:
# tracer: wakeup
#
# wakeup latency trace v1.1.5 on 3.1.0-tip+
# --------------------------------------------------------------------
# latency: 55 us, #4/4, CPU#0 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
# -----------------
# | task: migration/0-6 (uid:0 nice:0 policy:1 rt_prio:99)
# -----------------
#
# _------=> CPU#
# / _-----=> irqs-off
# | / _----=> need-resched
# || / _---=> hardirq/softirq
# ||| / _--=> preempt-depth
# |||| / delay
# cmd pid ||||| time | caller
# \ / ||||| \ | /
cat-1129 0d..4 1us : 1129:120:R + [000] 6: 0:R migration/0
cat-1129 0d..4 2us+: ttwu_do_activate.clone.1 <-try_to_wake_up
* The current output (for wakeup tracer) with only function
tracer enabled is:
# tracer: wakeup
#
cat-1140 0d..4 1us+: 1140:120:R + [000] 6: 0:R migration/0
cat-1140 0d..4 2us : ttwu_do_activate.clone.1 <-try_to_wake_up
* The fixed output is:
# tracer: wakeup
#
# wakeup latency trace v1.1.5 on 3.1.0-tip+
# --------------------------------------------------------------------
# latency: 207 us, #109/109, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:2)
# -----------------
# | task: watchdog/1-12 (uid:0 nice:0 policy:1 rt_prio:99)
# -----------------
#
# _------=> CPU#
# / _-----=> irqs-off
# | / _----=> need-resched
# || / _---=> hardirq/softirq
# ||| / _--=> preempt-depth
# |||| / delay
# cmd pid ||||| time | caller
# \ / ||||| \ | /
<idle>-0 1d.h5 1us+: 0:120:R + [001] 12: 0:R watchdog/1
<idle>-0 1d.h5 3us : ttwu_do_activate.clone.1 <-try_to_wake_up
Link: http://lkml.kernel.org/r/20111107150849.GE1807@m.brq.redhat.com
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-11-07 22:08:49 +07:00
|
|
|
void trace_latency_header(struct seq_file *m);
|
2010-04-03 00:01:22 +07:00
|
|
|
void trace_default_header(struct seq_file *m);
|
|
|
|
void print_trace_header(struct seq_file *m, struct trace_iterator *iter);
|
|
|
|
int trace_empty(struct trace_iterator *iter);
|
2008-05-13 02:20:42 +07:00
|
|
|
|
2008-11-26 06:57:25 +07:00
|
|
|
void trace_graph_return(struct ftrace_graph_ret *trace);
|
2008-12-03 11:50:05 +07:00
|
|
|
int trace_graph_entry(struct ftrace_graph_ent *trace);
|
2009-07-29 23:59:58 +07:00
|
|
|
void set_graph_array(struct trace_array *tr);
|
2008-11-25 15:24:15 +07:00
|
|
|
|
2008-05-22 22:49:22 +07:00
|
|
|
void tracing_start_cmdline_record(void);
|
|
|
|
void tracing_stop_cmdline_record(void);
|
2008-11-08 10:36:02 +07:00
|
|
|
void tracing_sched_switch_assign_trace(struct trace_array *tr);
|
|
|
|
void tracing_stop_sched_switch_record(void);
|
|
|
|
void tracing_start_sched_switch_record(void);
|
2008-05-13 02:20:42 +07:00
|
|
|
int register_tracer(struct tracer *type);
|
2009-09-13 06:43:07 +07:00
|
|
|
int is_tracing_stopped(void);
|
2010-08-05 21:22:23 +07:00
|
|
|
|
|
|
|
extern cpumask_var_t __read_mostly tracing_buffer_mask;
|
|
|
|
|
|
|
|
#define for_each_tracing_cpu(cpu) \
|
|
|
|
for_each_cpu(cpu, tracing_buffer_mask)
|
2008-05-13 02:20:42 +07:00
|
|
|
|
|
|
|
extern unsigned long nsecs_to_usecs(unsigned long nsecs);
|
|
|
|
|
2010-02-26 06:36:43 +07:00
|
|
|
extern unsigned long tracing_thresh;
|
|
|
|
|
2009-08-28 03:52:21 +07:00
|
|
|
#ifdef CONFIG_TRACER_MAX_TRACE
|
2008-05-13 02:20:42 +07:00
|
|
|
extern unsigned long tracing_max_latency;
|
|
|
|
|
|
|
|
void update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu);
|
|
|
|
void update_max_tr_single(struct trace_array *tr,
|
|
|
|
struct task_struct *tsk, int cpu);
|
2009-08-28 03:52:21 +07:00
|
|
|
#endif /* CONFIG_TRACER_MAX_TRACE */
|
2008-05-13 02:20:42 +07:00
|
|
|
|
2009-07-29 22:51:13 +07:00
|
|
|
#ifdef CONFIG_STACKTRACE
|
2009-09-03 01:17:06 +07:00
|
|
|
void ftrace_trace_stack(struct ring_buffer *buffer, unsigned long flags,
|
2009-07-29 22:51:13 +07:00
|
|
|
int skip, int pc);
|
|
|
|
|
2011-06-08 14:09:34 +07:00
|
|
|
void ftrace_trace_stack_regs(struct ring_buffer *buffer, unsigned long flags,
|
|
|
|
int skip, int pc, struct pt_regs *regs);
|
|
|
|
|
2009-09-03 01:17:06 +07:00
|
|
|
void ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags,
|
2009-07-29 22:51:13 +07:00
|
|
|
int pc);
|
|
|
|
|
|
|
|
void __trace_stack(struct trace_array *tr, unsigned long flags, int skip,
|
|
|
|
int pc);
|
|
|
|
#else
|
2010-05-10 10:23:00 +07:00
|
|
|
static inline void ftrace_trace_stack(struct ring_buffer *buffer,
|
2009-07-29 22:51:13 +07:00
|
|
|
unsigned long flags, int skip, int pc)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2011-06-08 14:09:34 +07:00
|
|
|
static inline void ftrace_trace_stack_regs(struct ring_buffer *buffer,
|
|
|
|
unsigned long flags, int skip,
|
|
|
|
int pc, struct pt_regs *regs)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
2010-05-10 10:23:00 +07:00
|
|
|
static inline void ftrace_trace_userstack(struct ring_buffer *buffer,
|
2009-07-29 22:51:13 +07:00
|
|
|
unsigned long flags, int pc)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void __trace_stack(struct trace_array *tr, unsigned long flags,
|
|
|
|
int skip, int pc)
|
|
|
|
{
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_STACKTRACE */
|
2009-01-16 07:12:40 +07:00
|
|
|
|
2008-05-13 02:20:51 +07:00
|
|
|
extern cycle_t ftrace_now(int cpu);
|
2008-05-13 02:20:42 +07:00
|
|
|
|
2009-03-17 06:20:15 +07:00
|
|
|
extern void trace_find_cmdline(int pid, char comm[]);
|
2008-12-29 19:02:17 +07:00
|
|
|
|
2008-05-13 02:20:42 +07:00
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
|
|
extern unsigned long ftrace_update_tot_cnt;
|
2012-07-21 00:45:59 +07:00
|
|
|
#endif
|
2008-05-13 02:20:54 +07:00
|
|
|
#define DYN_FTRACE_TEST_NAME trace_selftest_dynamic_test_func
|
|
|
|
extern int DYN_FTRACE_TEST_NAME(void);
|
2011-05-06 11:08:51 +07:00
|
|
|
#define DYN_FTRACE_TEST_NAME2 trace_selftest_dynamic_test_func2
|
|
|
|
extern int DYN_FTRACE_TEST_NAME2(void);
|
2008-05-13 02:20:42 +07:00
|
|
|
|
2013-03-08 10:48:09 +07:00
|
|
|
extern bool ring_buffer_expanded;
|
2009-07-01 09:47:05 +07:00
|
|
|
extern bool tracing_selftest_disabled;
|
2009-10-08 06:17:45 +07:00
|
|
|
DECLARE_PER_CPU(int, ftrace_cpu_disabled);
|
2009-07-01 09:47:05 +07:00
|
|
|
|
2008-05-13 02:20:44 +07:00
|
|
|
#ifdef CONFIG_FTRACE_STARTUP_TEST
|
|
|
|
extern int trace_selftest_startup_function(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2009-02-08 03:33:57 +07:00
|
|
|
extern int trace_selftest_startup_function_graph(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-05-13 02:20:44 +07:00
|
|
|
extern int trace_selftest_startup_irqsoff(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_preemptoff(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_preemptirqsoff(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
|
|
|
extern int trace_selftest_startup_wakeup(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-09-19 17:06:43 +07:00
|
|
|
extern int trace_selftest_startup_nop(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-05-13 02:20:44 +07:00
|
|
|
extern int trace_selftest_startup_sched_switch(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-11-13 03:24:24 +07:00
|
|
|
extern int trace_selftest_startup_branch(struct tracer *trace,
|
|
|
|
struct trace_array *tr);
|
2008-05-13 02:20:44 +07:00
|
|
|
#endif /* CONFIG_FTRACE_STARTUP_TEST */
|
|
|
|
|
2008-05-13 02:20:45 +07:00
|
|
|
extern void *head_page(struct trace_array_cpu *data);
|
2009-03-30 12:48:00 +07:00
|
|
|
extern unsigned long long ns2usecs(cycle_t nsec);
|
2008-12-04 05:45:11 +07:00
|
|
|
extern int
|
2009-03-20 01:03:53 +07:00
|
|
|
trace_vbprintk(unsigned long ip, const char *fmt, va_list args);
|
2009-03-13 00:24:49 +07:00
|
|
|
extern int
|
2009-03-20 01:03:53 +07:00
|
|
|
trace_vprintk(unsigned long ip, const char *fmt, va_list args);
|
2009-09-04 06:11:07 +07:00
|
|
|
extern int
|
|
|
|
trace_array_vprintk(struct trace_array *tr,
|
|
|
|
unsigned long ip, const char *fmt, va_list args);
|
|
|
|
int trace_array_printk(struct trace_array *tr,
|
|
|
|
unsigned long ip, const char *fmt, ...);
|
tracing: Consolidate max_tr into main trace_array structure
Currently, the way the latency tracers and snapshot feature works
is to have a separate trace_array called "max_tr" that holds the
snapshot buffer. For latency tracers, this snapshot buffer is used
to swap the running buffer with this buffer to save the current max
latency.
The only items needed for the max_tr is really just a copy of the buffer
itself, the per_cpu data pointers, the time_start timestamp that states
when the max latency was triggered, and the cpu that the max latency
was triggered on. All other fields in trace_array are unused by the
max_tr, making the max_tr mostly bloat.
This change removes the max_tr completely, and adds a new structure
called trace_buffer, that holds the buffer pointer, the per_cpu data
pointers, the time_start timestamp, and the cpu where the latency occurred.
The trace_array, now has two trace_buffers, one for the normal trace and
one for the max trace or snapshot. By doing this, not only do we remove
the bloat from the max_trace but the instances of traces can now use
their own snapshot feature and not have just the top level global_trace have
the snapshot feature and latency tracers for itself.
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-03-05 21:24:35 +07:00
|
|
|
int trace_array_printk_buf(struct ring_buffer *buffer,
|
|
|
|
unsigned long ip, const char *fmt, ...);
|
2010-08-05 21:22:23 +07:00
|
|
|
void trace_printk_seq(struct trace_seq *s);
|
|
|
|
enum print_line_t print_trace_line(struct trace_iterator *iter);
|
2008-05-13 02:20:45 +07:00
|
|
|
|
2008-05-13 02:20:52 +07:00
|
|
|
extern unsigned long trace_flags;
|
|
|
|
|
2009-08-25 15:12:56 +07:00
|
|
|
extern int trace_clock_id;
|
|
|
|
|
2008-11-11 13:14:25 +07:00
|
|
|
/* Standard output formatting function used for function return traces */
|
2008-11-26 03:07:04 +07:00
|
|
|
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
|
2010-04-03 00:01:22 +07:00
|
|
|
|
|
|
|
/* Flag options */
|
|
|
|
#define TRACE_GRAPH_PRINT_OVERRUN 0x1
|
|
|
|
#define TRACE_GRAPH_PRINT_CPU 0x2
|
|
|
|
#define TRACE_GRAPH_PRINT_OVERHEAD 0x4
|
|
|
|
#define TRACE_GRAPH_PRINT_PROC 0x8
|
|
|
|
#define TRACE_GRAPH_PRINT_DURATION 0x10
|
|
|
|
#define TRACE_GRAPH_PRINT_ABS_TIME 0x20
|
|
|
|
|
2010-04-03 00:01:21 +07:00
|
|
|
extern enum print_line_t
|
|
|
|
print_graph_function_flags(struct trace_iterator *iter, u32 flags);
|
|
|
|
extern void print_graph_headers_flags(struct seq_file *s, u32 flags);
|
2009-03-24 10:12:58 +07:00
|
|
|
extern enum print_line_t
|
|
|
|
trace_print_graph_duration(unsigned long long duration, struct trace_seq *s);
|
2010-04-03 00:01:22 +07:00
|
|
|
extern void graph_trace_open(struct trace_iterator *iter);
|
|
|
|
extern void graph_trace_close(struct trace_iterator *iter);
|
|
|
|
extern int __trace_graph_entry(struct trace_array *tr,
|
|
|
|
struct ftrace_graph_ent *trace,
|
|
|
|
unsigned long flags, int pc);
|
|
|
|
extern void __trace_graph_return(struct trace_array *tr,
|
|
|
|
struct ftrace_graph_ret *trace,
|
|
|
|
unsigned long flags, int pc);
|
|
|
|
|
2008-12-04 03:36:57 +07:00
|
|
|
|
|
|
|
#ifdef CONFIG_DYNAMIC_FTRACE
|
|
|
|
/* TODO: make this variable */
|
|
|
|
#define FTRACE_GRAPH_MAX_FUNCS 32
|
2010-02-10 14:43:04 +07:00
|
|
|
extern int ftrace_graph_filter_enabled;
|
2008-12-04 03:36:57 +07:00
|
|
|
extern int ftrace_graph_count;
|
|
|
|
extern unsigned long ftrace_graph_funcs[FTRACE_GRAPH_MAX_FUNCS];
|
|
|
|
|
|
|
|
static inline int ftrace_graph_addr(unsigned long addr)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2010-02-10 14:43:04 +07:00
|
|
|
if (!ftrace_graph_filter_enabled)
|
2008-12-04 03:36:57 +07:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
for (i = 0; i < ftrace_graph_count; i++) {
|
2011-06-15 06:02:29 +07:00
|
|
|
if (addr == ftrace_graph_funcs[i]) {
|
|
|
|
/*
|
|
|
|
* If no irqs are to be traced, but a set_graph_function
|
|
|
|
* is set, and called by an interrupt handler, we still
|
|
|
|
* want to trace it.
|
|
|
|
*/
|
|
|
|
if (in_irq())
|
|
|
|
trace_recursion_set(TRACE_IRQ_BIT);
|
|
|
|
else
|
|
|
|
trace_recursion_clear(TRACE_IRQ_BIT);
|
2008-12-04 03:36:57 +07:00
|
|
|
return 1;
|
2011-06-15 06:02:29 +07:00
|
|
|
}
|
2008-12-04 03:36:57 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2008-11-11 13:14:25 +07:00
|
|
|
#else
|
2008-12-04 15:18:28 +07:00
|
|
|
static inline int ftrace_graph_addr(unsigned long addr)
|
|
|
|
{
|
|
|
|
return 1;
|
2008-12-04 03:36:57 +07:00
|
|
|
}
|
|
|
|
#endif /* CONFIG_DYNAMIC_FTRACE */
|
|
|
|
#else /* CONFIG_FUNCTION_GRAPH_TRACER */
|
2008-11-11 13:14:25 +07:00
|
|
|
static inline enum print_line_t
|
2010-04-03 00:01:21 +07:00
|
|
|
print_graph_function_flags(struct trace_iterator *iter, u32 flags)
|
2008-11-11 13:14:25 +07:00
|
|
|
{
|
|
|
|
return TRACE_TYPE_UNHANDLED;
|
|
|
|
}
|
2008-12-04 03:36:57 +07:00
|
|
|
#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
|
2008-11-11 13:14:25 +07:00
|
|
|
|
2009-10-14 03:33:52 +07:00
|
|
|
extern struct list_head ftrace_pids;
|
2008-12-04 03:36:59 +07:00
|
|
|
|
2009-06-25 12:30:12 +07:00
|
|
|
#ifdef CONFIG_FUNCTION_TRACER
|
2008-12-04 03:36:59 +07:00
|
|
|
static inline int ftrace_trace_task(struct task_struct *task)
|
|
|
|
{
|
2009-10-14 03:33:52 +07:00
|
|
|
if (list_empty(&ftrace_pids))
|
2008-12-04 03:36:59 +07:00
|
|
|
return 1;
|
|
|
|
|
|
|
|
return test_tsk_trace_trace(task);
|
|
|
|
}
|
2011-09-30 08:26:16 +07:00
|
|
|
extern int ftrace_is_dead(void);
|
2009-06-25 12:30:12 +07:00
|
|
|
#else
|
|
|
|
static inline int ftrace_trace_task(struct task_struct *task)
|
|
|
|
{
|
|
|
|
return 1;
|
|
|
|
}
|
2011-09-30 08:26:16 +07:00
|
|
|
static inline int ftrace_is_dead(void) { return 0; }
|
2009-06-25 12:30:12 +07:00
|
|
|
#endif
|
2008-12-04 03:36:59 +07:00
|
|
|
|
2012-02-15 21:51:52 +07:00
|
|
|
int ftrace_event_is_function(struct ftrace_event_call *call);
|
|
|
|
|
2009-09-11 22:29:27 +07:00
|
|
|
/*
|
|
|
|
* struct trace_parser - servers for reading the user input separated by spaces
|
|
|
|
* @cont: set if the input is not complete - no final space char was found
|
|
|
|
* @buffer: holds the parsed user input
|
2010-01-29 14:57:49 +07:00
|
|
|
* @idx: user input length
|
2009-09-11 22:29:27 +07:00
|
|
|
* @size: buffer size
|
|
|
|
*/
|
|
|
|
struct trace_parser {
|
|
|
|
bool cont;
|
|
|
|
char *buffer;
|
|
|
|
unsigned idx;
|
|
|
|
unsigned size;
|
|
|
|
};
|
|
|
|
|
|
|
|
static inline bool trace_parser_loaded(struct trace_parser *parser)
|
|
|
|
{
|
|
|
|
return (parser->idx != 0);
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline bool trace_parser_cont(struct trace_parser *parser)
|
|
|
|
{
|
|
|
|
return parser->cont;
|
|
|
|
}
|
|
|
|
|
|
|
|
static inline void trace_parser_clear(struct trace_parser *parser)
|
|
|
|
{
|
|
|
|
parser->cont = false;
|
|
|
|
parser->idx = 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
extern int trace_parser_get_init(struct trace_parser *parser, int size);
|
|
|
|
extern void trace_parser_put(struct trace_parser *parser);
|
|
|
|
extern int trace_get_user(struct trace_parser *parser, const char __user *ubuf,
|
|
|
|
size_t cnt, loff_t *ppos);
|
|
|
|
|
2008-05-13 02:21:00 +07:00
|
|
|
/*
|
|
|
|
* trace_iterator_flags is an enumeration that defines bit
|
|
|
|
* positions into trace_flags that controls the output.
|
|
|
|
*
|
|
|
|
* NOTE: These bits must match the trace_options array in
|
|
|
|
* trace.c.
|
|
|
|
*/
|
2008-05-13 02:20:52 +07:00
|
|
|
enum trace_iterator_flags {
|
|
|
|
TRACE_ITER_PRINT_PARENT = 0x01,
|
|
|
|
TRACE_ITER_SYM_OFFSET = 0x02,
|
|
|
|
TRACE_ITER_SYM_ADDR = 0x04,
|
|
|
|
TRACE_ITER_VERBOSE = 0x08,
|
|
|
|
TRACE_ITER_RAW = 0x10,
|
|
|
|
TRACE_ITER_HEX = 0x20,
|
|
|
|
TRACE_ITER_BIN = 0x40,
|
|
|
|
TRACE_ITER_BLOCK = 0x80,
|
|
|
|
TRACE_ITER_STACKTRACE = 0x100,
|
2009-12-08 10:16:26 +07:00
|
|
|
TRACE_ITER_PRINTK = 0x200,
|
|
|
|
TRACE_ITER_PREEMPTONLY = 0x400,
|
|
|
|
TRACE_ITER_BRANCH = 0x800,
|
|
|
|
TRACE_ITER_ANNOTATE = 0x1000,
|
|
|
|
TRACE_ITER_USERSTACKTRACE = 0x2000,
|
|
|
|
TRACE_ITER_SYM_USEROBJ = 0x4000,
|
|
|
|
TRACE_ITER_PRINTK_MSGONLY = 0x8000,
|
|
|
|
TRACE_ITER_CONTEXT_INFO = 0x10000, /* Print pid/cpu/time */
|
|
|
|
TRACE_ITER_LATENCY_FMT = 0x20000,
|
|
|
|
TRACE_ITER_SLEEP_TIME = 0x40000,
|
|
|
|
TRACE_ITER_GRAPH_TIME = 0x80000,
|
2010-07-02 10:07:32 +07:00
|
|
|
TRACE_ITER_RECORD_CMD = 0x100000,
|
2010-12-09 04:46:47 +07:00
|
|
|
TRACE_ITER_OVERWRITE = 0x200000,
|
2011-06-15 09:44:07 +07:00
|
|
|
TRACE_ITER_STOP_ON_FREE = 0x400000,
|
tracing: Add irq, preempt-count and need resched info to default trace output
People keep asking how to get the preempt count, irq, and need resched info
and we keep telling them to enable the latency format. Some developers think
that traces without this info is completely useless, and for a lot of tasks
it is useless.
The first option was to enable the latency trace as the default format, but
the header for the latency format is pretty useless for most tracers and
it also does the timestamp in straight microseconds from the time the trace
started. This is sometimes more difficult to read as the default trace is
seconds from the start of boot up.
Latency format:
# tracer: nop
#
# nop latency trace v1.1.5 on 3.2.0-rc1-test+
# --------------------------------------------------------------------
# latency: 0 us, #159771/64234230, CPU#1 | (M:preempt VP:0, KP:0, SP:0 HP:0 #P:4)
# -----------------
# | task: -0 (uid:0 nice:0 policy:0 rt_prio:0)
# -----------------
#
# _------=> CPU#
# / _-----=> irqs-off
# | / _----=> need-resched
# || / _---=> hardirq/softirq
# ||| / _--=> preempt-depth
# |||| / delay
# cmd pid ||||| time | caller
# \ / ||||| \ | /
migratio-6 0...2 41778231us+: rcu_note_context_switch <-__schedule
migratio-6 0...2 41778233us : trace_rcu_utilization <-rcu_note_context_switch
migratio-6 0...2 41778235us+: rcu_sched_qs <-rcu_note_context_switch
migratio-6 0d..2 41778236us+: rcu_preempt_qs <-rcu_note_context_switch
migratio-6 0...2 41778238us : trace_rcu_utilization <-rcu_note_context_switch
migratio-6 0...2 41778239us+: debug_lockdep_rcu_enabled <-__schedule
default format:
# tracer: nop
#
# TASK-PID CPU# TIMESTAMP FUNCTION
# | | | | |
migration/0-6 [000] 50.025810: rcu_note_context_switch <-__schedule
migration/0-6 [000] 50.025812: trace_rcu_utilization <-rcu_note_context_switch
migration/0-6 [000] 50.025813: rcu_sched_qs <-rcu_note_context_switch
migration/0-6 [000] 50.025815: rcu_preempt_qs <-rcu_note_context_switch
migration/0-6 [000] 50.025817: trace_rcu_utilization <-rcu_note_context_switch
migration/0-6 [000] 50.025818: debug_lockdep_rcu_enabled <-__schedule
migration/0-6 [000] 50.025820: debug_lockdep_rcu_enabled <-__schedule
The latency format header has latency information that is pretty meaningless
for most tracers. Although some of the header is useful, and we can add that
later to the default format as well.
What is really useful with the latency format is the irqs-off, need-resched
hard/softirq context and the preempt count.
This commit adds the option irq-info which is on by default that adds this
information:
# tracer: nop
#
# _-----=> irqs-off
# / _----=> need-resched
# | / _---=> hardirq/softirq
# || / _--=> preempt-depth
# ||| / delay
# TASK-PID CPU# |||| TIMESTAMP FUNCTION
# | | | |||| | |
<idle>-0 [000] d..2 49.309305: cpuidle_get_driver <-cpuidle_idle_call
<idle>-0 [000] d..2 49.309307: mwait_idle <-cpu_idle
<idle>-0 [000] d..2 49.309309: need_resched <-mwait_idle
<idle>-0 [000] d..2 49.309310: test_ti_thread_flag <-need_resched
<idle>-0 [000] d..2 49.309312: trace_power_start.constprop.13 <-mwait_idle
<idle>-0 [000] d..2 49.309313: trace_cpu_idle <-mwait_idle
<idle>-0 [000] d..2 49.309315: need_resched <-mwait_idle
If a user wants the old format, they can disable the 'irq-info' option:
# tracer: nop
#
# TASK-PID CPU# TIMESTAMP FUNCTION
# | | | | |
<idle>-0 [000] 49.309305: cpuidle_get_driver <-cpuidle_idle_call
<idle>-0 [000] 49.309307: mwait_idle <-cpu_idle
<idle>-0 [000] 49.309309: need_resched <-mwait_idle
<idle>-0 [000] 49.309310: test_ti_thread_flag <-need_resched
<idle>-0 [000] 49.309312: trace_power_start.constprop.13 <-mwait_idle
<idle>-0 [000] 49.309313: trace_cpu_idle <-mwait_idle
<idle>-0 [000] 49.309315: need_resched <-mwait_idle
Requested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-11-17 21:34:33 +07:00
|
|
|
TRACE_ITER_IRQ_INFO = 0x800000,
|
2012-09-08 08:12:19 +07:00
|
|
|
TRACE_ITER_MARKERS = 0x1000000,
|
2013-03-14 23:10:40 +07:00
|
|
|
TRACE_ITER_FUNCTION = 0x2000000,
|
2008-05-13 02:20:52 +07:00
|
|
|
};
|
|
|
|
|
2008-11-11 13:14:25 +07:00
|
|
|
/*
|
|
|
|
* TRACE_ITER_SYM_MASK masks the options in trace_flags that
|
|
|
|
* control the output of kernel symbols.
|
|
|
|
*/
|
|
|
|
#define TRACE_ITER_SYM_MASK \
|
|
|
|
(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
|
|
|
|
|
2008-09-22 01:16:30 +07:00
|
|
|
extern struct tracer nop_trace;
|
|
|
|
|
2008-11-13 03:24:24 +07:00
|
|
|
#ifdef CONFIG_BRANCH_TRACER
|
2008-11-13 03:24:24 +07:00
|
|
|
extern int enable_branch_tracing(struct trace_array *tr);
|
|
|
|
extern void disable_branch_tracing(void);
|
|
|
|
static inline int trace_branch_enable(struct trace_array *tr)
|
2008-11-12 12:14:40 +07:00
|
|
|
{
|
2008-11-13 03:24:24 +07:00
|
|
|
if (trace_flags & TRACE_ITER_BRANCH)
|
|
|
|
return enable_branch_tracing(tr);
|
2008-11-12 12:14:40 +07:00
|
|
|
return 0;
|
|
|
|
}
|
2008-11-13 03:24:24 +07:00
|
|
|
static inline void trace_branch_disable(void)
|
2008-11-12 12:14:40 +07:00
|
|
|
{
|
|
|
|
/* due to races, always disable */
|
2008-11-13 03:24:24 +07:00
|
|
|
disable_branch_tracing();
|
2008-11-12 12:14:40 +07:00
|
|
|
}
|
|
|
|
#else
|
2008-11-13 03:24:24 +07:00
|
|
|
static inline int trace_branch_enable(struct trace_array *tr)
|
2008-11-12 12:14:40 +07:00
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
2008-11-13 03:24:24 +07:00
|
|
|
static inline void trace_branch_disable(void)
|
2008-11-12 12:14:40 +07:00
|
|
|
{
|
|
|
|
}
|
2008-11-13 03:24:24 +07:00
|
|
|
#endif /* CONFIG_BRANCH_TRACER */
|
2008-11-12 12:14:40 +07:00
|
|
|
|
2009-03-12 01:33:00 +07:00
|
|
|
/* set ring buffers to default size if not already done so */
|
|
|
|
int tracing_update_buffers(void);
|
|
|
|
|
2009-02-28 14:41:25 +07:00
|
|
|
/* trace event type bit fields, not numeric */
|
|
|
|
enum {
|
|
|
|
TRACE_EVENT_TYPE_PRINTF = 1,
|
|
|
|
TRACE_EVENT_TYPE_RAW = 2,
|
|
|
|
};
|
|
|
|
|
2009-03-22 15:30:39 +07:00
|
|
|
struct ftrace_event_field {
|
|
|
|
struct list_head link;
|
2013-02-28 08:41:37 +07:00
|
|
|
const char *name;
|
|
|
|
const char *type;
|
2009-08-07 09:33:02 +07:00
|
|
|
int filter_type;
|
2009-03-22 15:30:39 +07:00
|
|
|
int offset;
|
|
|
|
int size;
|
2009-04-28 15:04:53 +07:00
|
|
|
int is_signed;
|
2009-03-22 15:30:39 +07:00
|
|
|
};
|
|
|
|
|
2009-04-28 15:04:47 +07:00
|
|
|
struct event_filter {
|
2011-01-28 10:42:43 +07:00
|
|
|
int n_preds; /* Number assigned */
|
|
|
|
int a_preds; /* allocated */
|
2011-01-28 10:49:48 +07:00
|
|
|
struct filter_pred *preds;
|
2011-01-28 10:54:33 +07:00
|
|
|
struct filter_pred *root;
|
tracing/filters: a better event parser
Replace the current event parser hack with a better one. Filters are
no longer specified predicate by predicate, but all at once and can
use parens and any of the following operators:
numeric fields:
==, !=, <, <=, >, >=
string fields:
==, !=
predicates can be combined with the logical operators:
&&, ||
examples:
"common_preempt_count > 4" > filter
"((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter
If there was an error, the erroneous string along with an error
message can be seen by looking at the filter e.g.:
((sig >= 10 && sig < 15) || dsig == 17) && comm != bash
^
parse_error: Field not found
Currently the caret for an error always appears at the beginning of
the filter; a real position should be used, but the error message
should be useful even without it.
To clear a filter, '0' can be written to the filter file.
Filters can also be set or cleared for a complete subsystem by writing
the same filter as would be written to an individual event to the
filter file at the root of the subsytem. Note however, that if any
event in the subsystem lacks a field specified in the filter being
set, the set will fail and all filters in the subsytem are
automatically cleared. This change from the previous version was made
because using only the fields that happen to exist for a given event
would most likely result in a meaningless filter.
Because the logical operators are now implemented as predicates, the
maximum number of predicates in a filter was increased from 8 to 16.
[ Impact: add new, extended trace-filter implementation ]
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905899.6416.121.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-28 15:04:59 +07:00
|
|
|
char *filter_string;
|
2009-04-28 15:04:47 +07:00
|
|
|
};
|
|
|
|
|
2009-03-22 15:31:17 +07:00
|
|
|
struct event_subsystem {
|
|
|
|
struct list_head list;
|
|
|
|
const char *name;
|
2009-07-20 09:20:53 +07:00
|
|
|
struct event_filter *filter;
|
2011-07-05 22:36:06 +07:00
|
|
|
int ref_count;
|
2009-03-22 15:31:17 +07:00
|
|
|
};
|
|
|
|
|
2012-05-04 10:09:03 +07:00
|
|
|
struct ftrace_subsystem_dir {
|
|
|
|
struct list_head list;
|
|
|
|
struct event_subsystem *subsystem;
|
|
|
|
struct trace_array *tr;
|
|
|
|
struct dentry *entry;
|
|
|
|
int ref_count;
|
|
|
|
int nr_events;
|
|
|
|
};
|
|
|
|
|
2011-01-28 10:54:33 +07:00
|
|
|
#define FILTER_PRED_INVALID ((unsigned short)-1)
|
|
|
|
#define FILTER_PRED_IS_RIGHT (1 << 15)
|
2011-01-28 11:16:51 +07:00
|
|
|
#define FILTER_PRED_FOLD (1 << 15)
|
2011-01-28 10:54:33 +07:00
|
|
|
|
2011-01-28 11:21:34 +07:00
|
|
|
/*
|
|
|
|
* The max preds is the size of unsigned short with
|
|
|
|
* two flags at the MSBs. One bit is used for both the IS_RIGHT
|
|
|
|
* and FOLD flags. The other is reserved.
|
|
|
|
*
|
|
|
|
* 2^14 preds is way more than enough.
|
|
|
|
*/
|
|
|
|
#define MAX_FILTER_PRED 16384
|
2011-01-28 11:19:49 +07:00
|
|
|
|
2009-03-22 15:31:04 +07:00
|
|
|
struct filter_pred;
|
2009-09-25 02:10:44 +07:00
|
|
|
struct regex;
|
2009-03-22 15:31:04 +07:00
|
|
|
|
2011-01-28 10:37:09 +07:00
|
|
|
typedef int (*filter_pred_fn_t) (struct filter_pred *pred, void *event);
|
2009-03-22 15:31:04 +07:00
|
|
|
|
2009-09-25 02:10:44 +07:00
|
|
|
typedef int (*regex_match_func)(char *str, struct regex *r, int len);
|
|
|
|
|
2009-09-25 02:31:51 +07:00
|
|
|
enum regex_type {
|
2009-10-15 10:21:12 +07:00
|
|
|
MATCH_FULL = 0,
|
2009-09-25 02:31:51 +07:00
|
|
|
MATCH_FRONT_ONLY,
|
|
|
|
MATCH_MIDDLE_ONLY,
|
|
|
|
MATCH_END_ONLY,
|
|
|
|
};
|
|
|
|
|
2009-09-25 02:10:44 +07:00
|
|
|
struct regex {
|
|
|
|
char pattern[MAX_FILTER_STR_VAL];
|
|
|
|
int len;
|
|
|
|
int field_len;
|
|
|
|
regex_match_func match;
|
|
|
|
};
|
|
|
|
|
2009-03-22 15:31:04 +07:00
|
|
|
struct filter_pred {
|
2009-09-25 02:10:44 +07:00
|
|
|
filter_pred_fn_t fn;
|
|
|
|
u64 val;
|
|
|
|
struct regex regex;
|
2011-08-11 21:25:47 +07:00
|
|
|
unsigned short *ops;
|
2011-08-11 21:25:54 +07:00
|
|
|
struct ftrace_event_field *field;
|
2009-09-25 02:10:44 +07:00
|
|
|
int offset;
|
|
|
|
int not;
|
|
|
|
int op;
|
2011-01-28 10:54:33 +07:00
|
|
|
unsigned short index;
|
|
|
|
unsigned short parent;
|
|
|
|
unsigned short left;
|
|
|
|
unsigned short right;
|
2009-03-22 15:31:04 +07:00
|
|
|
};
|
|
|
|
|
2009-09-25 02:31:51 +07:00
|
|
|
extern enum regex_type
|
|
|
|
filter_parse_regex(char *buff, int len, char **search, int *not);
|
tracing/filters: a better event parser
Replace the current event parser hack with a better one. Filters are
no longer specified predicate by predicate, but all at once and can
use parens and any of the following operators:
numeric fields:
==, !=, <, <=, >, >=
string fields:
==, !=
predicates can be combined with the logical operators:
&&, ||
examples:
"common_preempt_count > 4" > filter
"((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter
If there was an error, the erroneous string along with an error
message can be seen by looking at the filter e.g.:
((sig >= 10 && sig < 15) || dsig == 17) && comm != bash
^
parse_error: Field not found
Currently the caret for an error always appears at the beginning of
the filter; a real position should be used, but the error message
should be useful even without it.
To clear a filter, '0' can be written to the filter file.
Filters can also be set or cleared for a complete subsystem by writing
the same filter as would be written to an individual event to the
filter file at the root of the subsytem. Note however, that if any
event in the subsystem lacks a field specified in the filter being
set, the set will fail and all filters in the subsytem are
automatically cleared. This change from the previous version was made
because using only the fields that happen to exist for a given event
would most likely result in a meaningless filter.
Because the logical operators are now implemented as predicates, the
maximum number of predicates in a filter was increased from 8 to 16.
[ Impact: add new, extended trace-filter implementation ]
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905899.6416.121.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-28 15:04:59 +07:00
|
|
|
extern void print_event_filter(struct ftrace_event_call *call,
|
2009-03-24 14:14:31 +07:00
|
|
|
struct trace_seq *s);
|
tracing/filters: a better event parser
Replace the current event parser hack with a better one. Filters are
no longer specified predicate by predicate, but all at once and can
use parens and any of the following operators:
numeric fields:
==, !=, <, <=, >, >=
string fields:
==, !=
predicates can be combined with the logical operators:
&&, ||
examples:
"common_preempt_count > 4" > filter
"((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter
If there was an error, the erroneous string along with an error
message can be seen by looking at the filter e.g.:
((sig >= 10 && sig < 15) || dsig == 17) && comm != bash
^
parse_error: Field not found
Currently the caret for an error always appears at the beginning of
the filter; a real position should be used, but the error message
should be useful even without it.
To clear a filter, '0' can be written to the filter file.
Filters can also be set or cleared for a complete subsystem by writing
the same filter as would be written to an individual event to the
filter file at the root of the subsytem. Note however, that if any
event in the subsystem lacks a field specified in the filter being
set, the set will fail and all filters in the subsytem are
automatically cleared. This change from the previous version was made
because using only the fields that happen to exist for a given event
would most likely result in a meaningless filter.
Because the logical operators are now implemented as predicates, the
maximum number of predicates in a filter was increased from 8 to 16.
[ Impact: add new, extended trace-filter implementation ]
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905899.6416.121.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-28 15:04:59 +07:00
|
|
|
extern int apply_event_filter(struct ftrace_event_call *call,
|
|
|
|
char *filter_string);
|
2012-05-04 10:09:03 +07:00
|
|
|
extern int apply_subsystem_event_filter(struct ftrace_subsystem_dir *dir,
|
tracing/filters: a better event parser
Replace the current event parser hack with a better one. Filters are
no longer specified predicate by predicate, but all at once and can
use parens and any of the following operators:
numeric fields:
==, !=, <, <=, >, >=
string fields:
==, !=
predicates can be combined with the logical operators:
&&, ||
examples:
"common_preempt_count > 4" > filter
"((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter
If there was an error, the erroneous string along with an error
message can be seen by looking at the filter e.g.:
((sig >= 10 && sig < 15) || dsig == 17) && comm != bash
^
parse_error: Field not found
Currently the caret for an error always appears at the beginning of
the filter; a real position should be used, but the error message
should be useful even without it.
To clear a filter, '0' can be written to the filter file.
Filters can also be set or cleared for a complete subsystem by writing
the same filter as would be written to an individual event to the
filter file at the root of the subsytem. Note however, that if any
event in the subsystem lacks a field specified in the filter being
set, the set will fail and all filters in the subsytem are
automatically cleared. This change from the previous version was made
because using only the fields that happen to exist for a given event
would most likely result in a meaningless filter.
Because the logical operators are now implemented as predicates, the
maximum number of predicates in a filter was increased from 8 to 16.
[ Impact: add new, extended trace-filter implementation ]
Signed-off-by: Tom Zanussi <tzanussi@gmail.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: fweisbec@gmail.com
Cc: Li Zefan <lizf@cn.fujitsu.com>
LKML-Reference: <1240905899.6416.121.camel@tropicana>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-04-28 15:04:59 +07:00
|
|
|
char *filter_string);
|
|
|
|
extern void print_subsystem_event_filter(struct event_subsystem *system,
|
2009-04-17 12:27:08 +07:00
|
|
|
struct trace_seq *s);
|
2009-08-07 09:33:02 +07:00
|
|
|
extern int filter_assign_type(const char *type);
|
2009-03-22 15:31:04 +07:00
|
|
|
|
2013-03-11 14:13:42 +07:00
|
|
|
struct ftrace_event_field *
|
|
|
|
trace_find_event_field(struct ftrace_event_call *call, char *name);
|
2010-04-22 21:35:55 +07:00
|
|
|
|
2009-04-08 15:15:54 +07:00
|
|
|
static inline int
|
2009-03-31 12:48:49 +07:00
|
|
|
filter_check_discard(struct ftrace_event_call *call, void *rec,
|
2009-04-08 15:15:54 +07:00
|
|
|
struct ring_buffer *buffer,
|
2009-03-31 12:48:49 +07:00
|
|
|
struct ring_buffer_event *event)
|
|
|
|
{
|
2010-04-23 22:12:36 +07:00
|
|
|
if (unlikely(call->flags & TRACE_EVENT_FL_FILTERED) &&
|
2009-10-15 10:21:42 +07:00
|
|
|
!filter_match_preds(call->filter, rec)) {
|
2009-04-08 15:15:54 +07:00
|
|
|
ring_buffer_discard_commit(buffer, event);
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
2009-03-31 12:48:49 +07:00
|
|
|
}
|
|
|
|
|
2010-07-02 10:07:32 +07:00
|
|
|
extern void trace_event_enable_cmd_record(bool enable);
|
2012-08-04 03:10:49 +07:00
|
|
|
extern int event_trace_add_tracer(struct dentry *parent, struct trace_array *tr);
|
2012-08-08 03:14:16 +07:00
|
|
|
extern int event_trace_del_tracer(struct trace_array *tr);
|
2010-07-02 10:07:32 +07:00
|
|
|
|
2009-05-06 09:33:45 +07:00
|
|
|
extern struct mutex event_mutex;
|
2009-04-11 00:52:20 +07:00
|
|
|
extern struct list_head ftrace_events;
|
2009-03-20 02:26:15 +07:00
|
|
|
|
2009-03-13 01:19:25 +07:00
|
|
|
extern const char *__start___trace_bprintk_fmt[];
|
|
|
|
extern const char *__stop___trace_bprintk_fmt[];
|
|
|
|
|
tracing: Add percpu buffers for trace_printk()
Currently, trace_printk() uses a single buffer to write into
to calculate the size and format needed to save the trace. To
do this safely in an SMP environment, a spin_lock() is taken
to only allow one writer at a time to the buffer. But this could
also affect what is being traced, and add synchronization that
would not be there otherwise.
Ideally, using percpu buffers would be useful, but since trace_printk()
is only used in development, having per cpu buffers for something
never used is a waste of space. Thus, the use of the trace_bprintk()
format section is changed to be used for static fmts as well as dynamic ones.
Then at boot up, we can check if the section that holds the trace_printk
formats is non-empty, and if it does contain something, then we
know a trace_printk() has been added to the kernel. At this time
the trace_printk per cpu buffers are allocated. A check is also
done at module load time in case a module is added that contains a
trace_printk().
Once the buffers are allocated, they are never freed. If you use
a trace_printk() then you should know what you are doing.
A buffer is made for each type of context:
normal
softirq
irq
nmi
The context is checked and the appropriate buffer is used.
This allows for totally lockless usage of trace_printk(),
and they no longer even disable interrupts.
Requested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-09-23 01:01:55 +07:00
|
|
|
void trace_printk_init_buffers(void);
|
2012-10-11 21:15:05 +07:00
|
|
|
void trace_printk_start_comm(void);
|
2013-03-15 02:03:53 +07:00
|
|
|
int trace_keep_overwrite(struct tracer *tracer, u32 mask, int set);
|
2012-05-12 00:29:49 +07:00
|
|
|
int set_tracer_flag(struct trace_array *tr, unsigned int mask, int enabled);
|
tracing: Add percpu buffers for trace_printk()
Currently, trace_printk() uses a single buffer to write into
to calculate the size and format needed to save the trace. To
do this safely in an SMP environment, a spin_lock() is taken
to only allow one writer at a time to the buffer. But this could
also affect what is being traced, and add synchronization that
would not be there otherwise.
Ideally, using percpu buffers would be useful, but since trace_printk()
is only used in development, having per cpu buffers for something
never used is a waste of space. Thus, the use of the trace_bprintk()
format section is changed to be used for static fmts as well as dynamic ones.
Then at boot up, we can check if the section that holds the trace_printk
formats is non-empty, and if it does contain something, then we
know a trace_printk() has been added to the kernel. At this time
the trace_printk per cpu buffers are allocated. A check is also
done at module load time in case a module is added that contains a
trace_printk().
Once the buffers are allocated, they are never freed. If you use
a trace_printk() then you should know what you are doing.
A buffer is made for each type of context:
normal
softirq
irq
nmi
The context is checked and the appropriate buffer is used.
This allows for totally lockless usage of trace_printk(),
and they no longer even disable interrupts.
Requested-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2011-09-23 01:01:55 +07:00
|
|
|
|
2013-03-09 12:40:58 +07:00
|
|
|
/*
|
|
|
|
* Normal trace_printk() and friends allocates special buffers
|
|
|
|
* to do the manipulation, as well as saves the print formats
|
|
|
|
* into sections to display. But the trace infrastructure wants
|
|
|
|
* to use these without the added overhead at the price of being
|
|
|
|
* a bit slower (used mainly for warnings, where we don't care
|
|
|
|
* about performance). The internal_trace_puts() is for such
|
|
|
|
* a purpose.
|
|
|
|
*/
|
|
|
|
#define internal_trace_puts(str) __trace_puts(_THIS_IP_, str, strlen(str))
|
|
|
|
|
2009-09-13 06:26:21 +07:00
|
|
|
#undef FTRACE_ENTRY
|
2012-02-15 21:51:53 +07:00
|
|
|
#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \
|
2010-02-25 01:59:23 +07:00
|
|
|
extern struct ftrace_event_call \
|
|
|
|
__attribute__((__aligned__(4))) event_##call;
|
2009-09-13 06:26:21 +07:00
|
|
|
#undef FTRACE_ENTRY_DUP
|
2012-02-15 21:51:53 +07:00
|
|
|
#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \
|
|
|
|
FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
|
|
|
|
filter)
|
2009-09-13 06:26:21 +07:00
|
|
|
#include "trace_entries.h"
|
2009-03-31 12:48:49 +07:00
|
|
|
|
2012-04-13 15:52:59 +07:00
|
|
|
#if defined(CONFIG_PERF_EVENTS) && defined(CONFIG_FUNCTION_TRACER)
|
2012-02-15 21:51:52 +07:00
|
|
|
int perf_ftrace_event_register(struct ftrace_event_call *call,
|
|
|
|
enum trace_reg type, void *data);
|
|
|
|
#else
|
|
|
|
#define perf_ftrace_event_register NULL
|
2012-04-13 15:52:59 +07:00
|
|
|
#endif
|
2012-02-15 21:51:52 +07:00
|
|
|
|
2008-05-13 02:20:42 +07:00
|
|
|
#endif /* _LINUX_KERNEL_TRACE_H */
|