2009-10-17 00:08:27 +00:00
perf-probe(1)
=============
NAME
----
perf-probe - Define new dynamic tracepoints
SYNOPSIS
--------
[verse]
2009-12-08 22:03:30 +00:00
'perf probe' [options] --add='PROBE' [...]
2009-11-04 00:12:13 +00:00
or
2009-12-08 22:03:30 +00:00
'perf probe' [options] PROBE
or
'perf probe' [options] --del='[GROUP:]EVENT' [...]
or
2015-04-24 09:47:50 +00:00
'perf probe' --list[=[GROUP:]EVENT]
2010-01-06 14:45:34 +00:00
or
2011-02-10 09:08:10 +00:00
'perf probe' [options] --line='LINE'
2010-10-21 10:13:23 +00:00
or
2010-10-21 10:13:41 +00:00
'perf probe' [options] --vars='PROBEPOINT'
2015-04-23 13:46:12 +00:00
or
'perf probe' [options] --funcs
2009-10-17 00:08:27 +00:00
DESCRIPTION
-----------
This command defines dynamic tracepoint events, by symbol and registers
without debuginfo, or by C expressions (C line numbers, C function names,
and C local variables) with debuginfo.
OPTIONS
-------
-k::
2009-11-04 00:12:13 +00:00
--vmlinux=PATH::
2009-10-17 00:08:27 +00:00
Specify vmlinux path which has debuginfo (Dwarf binary).
2010-10-21 10:13:41 +00:00
-m::
2011-06-27 07:27:51 +00:00
--module=MODNAME|PATH::
2010-10-21 10:13:41 +00:00
Specify module name in which perf-probe searches probe points
2011-06-27 07:27:51 +00:00
or lines. If a path of module file is passed, perf-probe
treat it as an offline module (this means you can add a probe on
a module which has not been loaded yet).
2010-10-21 10:13:41 +00:00
2010-06-14 19:26:30 +00:00
-s::
--source=PATH::
Specify path to kernel source.
2009-10-17 00:08:27 +00:00
-v::
--verbose::
Be more verbose (show parsed arguments, etc).
2015-01-30 09:37:46 +00:00
Can not use with -q.
-q::
--quiet::
Be quiet (do not show any messages including errors).
Can not use with -v.
2009-10-17 00:08:27 +00:00
2009-11-04 00:12:13 +00:00
-a::
2009-12-08 22:03:30 +00:00
--add=::
Define a probe event (see PROBE SYNTAX for detail).
-d::
--del=::
2010-02-25 13:35:19 +00:00
Delete probe events. This accepts glob wildcards('*', '?') and character
classes(e.g. [a-z], [!A-Z]).
2009-12-08 22:03:30 +00:00
-l::
2015-04-24 09:47:50 +00:00
--list[=[GROUP:]EVENT]::
List up current probe events. This can also accept filtering patterns of event names.
2009-10-17 00:08:27 +00:00
2010-01-06 14:45:34 +00:00
-L::
--line=::
Show source code lines which can be probed. This needs an argument
2010-02-25 13:35:19 +00:00
which specifies a range of the source code. (see LINE SYNTAX for detail)
2010-10-21 10:13:23 +00:00
-V::
--vars=::
Show available local variables at given probe point. The argument
syntax is same as PROBE SYNTAX, but NO ARGs.
2010-10-21 10:13:35 +00:00
--externs::
(Only for --vars) Show external defined variables in addition to local
variables.
2015-05-08 01:03:33 +00:00
--no-inlines::
(Only for --add) Search only for non-inlined functions. The functions
which do not have instances are ignored.
2011-01-13 12:46:11 +00:00
-F::
2015-05-05 02:29:50 +00:00
--funcs[=FILTER]::
2012-04-16 12:09:09 +00:00
Show available functions in given module or kernel. With -x/--exec,
can also list functions in a user space executable / shared library.
2015-05-05 02:29:50 +00:00
This also can accept a FILTER rule argument.
2011-01-13 12:46:11 +00:00
2011-01-20 14:15:39 +00:00
--filter=FILTER::
2011-01-20 14:15:45 +00:00
(Only for --vars and --funcs) Set filter. FILTER is a combination of glob
pattern, see FILTER PATTERN for detail.
Default FILTER is "!__k???tab_* & !__crc_*" for --vars, and "!_*"
for --funcs.
If several filters are specified, only the last filter is used.
2011-01-20 14:15:39 +00:00
2010-02-25 13:35:19 +00:00
-f::
--force::
Forcibly add events with existing name.
2010-01-06 14:45:34 +00:00
2010-03-16 22:06:05 +00:00
-n::
--dry-run::
Dry run. With this option, --add and --del doesn't execute actual
adding and removal operations.
2015-01-30 09:37:46 +00:00
--max-probes=NUM::
2010-04-21 19:56:40 +00:00
Set the maximum number of probe points for an event. Default is 128.
2012-04-16 12:09:09 +00:00
-x::
--exec=PATH::
Specify path to the executable or shared library file for user
space tracing. Can also be used with --funcs option.
2015-01-30 09:37:46 +00:00
--demangle::
Demangle application symbols. --no-demangle is also available
for disabling demangling.
2014-09-13 04:15:05 +00:00
--demangle-kernel::
2015-01-30 09:37:46 +00:00
Demangle kernel symbols. --no-demangle-kernel is also available
for disabling kernel demangling.
2014-09-13 04:15:05 +00:00
2012-04-16 12:09:25 +00:00
In absence of -m/-x options, perf probe checks if the first argument after
the options is an absolute path name. If its an absolute path, perf probe
uses it as a target module/target user space binary to probe.
2009-10-17 00:08:27 +00:00
PROBE SYNTAX
------------
Probe points are defined by following syntax.
2010-02-25 13:36:12 +00:00
1) Define event based on function name
[EVENT=]FUNC[@SRC][:RLN|+OFFS|%return|;PTN] [ARG ...]
2) Define event based on source file with line number
[EVENT=]SRC:ALN [ARG ...]
3) Define event based on source file with lazy pattern
[EVENT=]SRC;PTN [ARG ...]
2009-10-17 00:08:27 +00:00
2009-12-15 15:32:18 +00:00
'EVENT' specifies the name of new event, if omitted, it will be set the name of the probed function. Currently, event group name is set as 'probe'.
2010-02-25 13:36:12 +00:00
'FUNC' specifies a probed function name, and it may have one of the following options; '+OFFS' is the offset from function entry address in bytes, ':RLN' is the relative-line number from function entry line, and '%return' means that it probes function return. And ';PTN' means lazy matching pattern (see LAZY MATCHING). Note that ';PTN' must be the end of the probe point definition. In addition, '@SRC' specifies a source file which has that function.
It is also possible to specify a probe point by the source line number or lazy matching by using 'SRC:ALN' or 'SRC;PTN' syntax, where 'SRC' is the source file path, ':ALN' is the line number and ';PTN' is the lazy matching pattern.
2010-04-12 17:16:53 +00:00
'ARG' specifies the arguments of this probe point, (see PROBE ARGUMENT).
PROBE ARGUMENT
--------------
Each probe argument follows below syntax.
2010-04-12 17:17:22 +00:00
[NAME=]LOCALVAR|$retval|%REG|@SYMBOL[:TYPE]
2010-04-12 17:16:53 +00:00
2010-05-19 19:57:42 +00:00
'NAME' specifies the name of this argument (optional). You can use the name of local variable, local data structure member (e.g. var->field, var.field2), local array with fixed index (e.g. array[1], var->array[0], var->pointer[2]), or kprobe-tracer argument format (e.g. $retval, %ax, etc). Note that the name of this argument will be set as the last member name if you specify a local data structure member (e.g. field2 for 'var->field1.field2'.)
perf probe: Support $params special probe argument
$params is similar to $vars but matches only function parameters not
local variables.
Thus, this is useful for tracing function parameter changing or tracing
function call with parameters.
Testing it:
# perf probe tcp_sendmsg '$params'
Added new event:
probe:tcp_sendmsg (on tcp_sendmsg with $params)
You can now use it in all perf tools, such as:
perf record -e probe:tcp_sendmsg -aR sleep 1
# perf probe -l
probe:tcp_sendmsg (on tcp_sendmsg@acme/git/linux/net/ipv4/tcp.c with iocb sk msg size)
# perf record -a -e probe:*
press some random letters to generate TCP (sshd) traffic...
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.223 MB perf.data (6 samples) ]
# perf script
sshd 6385 [2] 3.907529: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24
sshd 6385 [2] 4.138973: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24
sshd 6385 [2] 4.378966: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24
sshd 6385 [2] 4.603681: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24
sshd 6385 [2] 4.818455: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24
sshd 6385 [2] 5.043603: probe:tcp_sendmsg: iocb=0xffff8800ac4cfe70 sk=0xffff88042196c140 msg=0xffff8800ac4cfda8 size=0x24
# cat /sys/kernel/debug/tracing/events/probe/tcp_sendmsg/format
name: tcp_sendmsg
ID: 1927
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned long __probe_ip; offset:8; size:8; signed:0;
field:u64 iocb; offset:16; size:8; signed:0;
field:u64 sk; offset:24; size:8; signed:0;
field:u64 msg; offset:32; size:8; signed:0;
field:u64 size; offset:40; size:8; signed:0;
print fmt: "(%lx) iocb=0x%Lx sk=0x%Lx msg=0x%Lx size=0x%Lx", REC->__probe_ip, REC->iocb, REC->sk, REC->msg, REC->size
#
Do some system wide tracing of this probe + write syscalls:
# perf trace -e write --ev probe:* --filter-pids 6385
462.612 (0.010 ms): bash/19153 write(fd: 1</dev/pts/1>, buf: 0x7f7556c78000, count: 29 ) = 29
462.701 (0.027 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ...
462.701 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44)
462.710 (0.035 ms): sshd/19152 ... [continued]: write()) = 68
462.787 (0.009 ms): bash/19153 write(fd: 2</dev/pts/1>, buf: 0x7f7556c77000, count: 22 ) = 22
462.865 (0.002 ms): sshd/19152 write(fd: 3<socket:[63117]>, buf: 0x7f78dd12e160, count: 68 ) ...
462.865 ( ): probe:tcp_sendmsg:(ffffffff8163db30) iocb=0xffff8803ebec7e70 sk=0xffff88042196ab80 msg=0xffff8803ebec7da8 size=0x44)
462.873 (0.010 ms): sshd/19152 ... [continued]: write()) = 68
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hemant Kumar <hemant@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150506124653.4961.59806.stgit@localhost.localdomain
[ Add some examples to the changelog message showing how to use it ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-05-06 12:46:53 +00:00
'$vars' and '$params' special arguments are also available for NAME, '$vars' is expanded to the local variables (including function parameters) which can access at given probe point. '$params' is expanded to only the function parameters.
2010-05-19 19:57:35 +00:00
'TYPE' casts the type of this argument (optional). If omitted, perf probe automatically set the type based on debuginfo. You can specify 'string' type only for the local variable or structure member which is an array of or a pointer to 'char' or 'unsigned char' type.
2009-10-17 00:08:27 +00:00
2014-02-28 14:02:15 +00:00
On x86 systems %REG is always the short form of the register: for example %AX. %RAX or %EAX is not valid.
2010-01-06 14:45:34 +00:00
LINE SYNTAX
-----------
2010-12-01 01:57:15 +00:00
Line range is described by following syntax.
2010-01-06 14:45:34 +00:00
2011-02-10 09:08:10 +00:00
"FUNC[@SRC][:RLN[+NUM|-RLN2]]|SRC[:ALN[+NUM|-ALN2]]"
2010-01-06 14:45:34 +00:00
FUNC specifies the function name of showing lines. 'RLN' is the start line
number from function entry line, and 'RLN2' is the end line number. As same as
probe syntax, 'SRC' means the source file path, 'ALN' is start line number,
and 'ALN2' is end line number in the file. It is also possible to specify how
2011-02-10 09:08:10 +00:00
many lines to show by using 'NUM'. Moreover, 'FUNC@SRC' combination is good
for searching a specific function when several functions share same name.
2010-01-06 14:45:34 +00:00
So, "source.c:100-120" shows lines between 100th to l20th in source.c file. And "func:10+20" shows 20 lines from 10th line of func function.
2010-02-25 13:36:12 +00:00
LAZY MATCHING
-------------
The lazy line matching is similar to glob matching but ignoring spaces in both of pattern and target. So this accepts wildcards('*', '?') and character classes(e.g. [a-z], [!A-Z]).
e.g.
'a=*' can matches 'a=b', 'a = b', 'a == b' and so on.
This provides some sort of flexibility and robustness to probe point definitions against minor code changes. For example, actual 10th line of schedule() can be moved easily by modifying schedule(), but the same line matching 'rq=cpu_rq*' may still exist in the function.)
2011-01-20 14:15:39 +00:00
FILTER PATTERN
--------------
The filter pattern is a glob matching pattern(s) to filter variables.
In addition, you can use "!" for specifying filter-out rule. You also can give several rules combined with "&" or "|", and fold those rules as one rule by using "(" ")".
e.g.
With --filter "foo* | bar*", perf probe -V shows variables which start with "foo" or "bar".
With --filter "!foo* & *bar", perf probe -V shows variables which don't start with "foo" and end with "bar", like "fizzbar". But "foobar" is filtered out.
2010-02-25 13:36:12 +00:00
2010-02-25 13:35:19 +00:00
EXAMPLES
--------
Display which lines in schedule() can be probed:
./perf probe --line schedule
Add a probe on schedule() function 12th line with recording cpu local variable:
./perf probe schedule:12 cpu
or
./perf probe --add='schedule:12 cpu'
this will add one or more probes which has the name start with "schedule".
2010-02-25 13:36:12 +00:00
Add probes on lines in schedule() function which calls update_rq_clock().
./perf probe 'schedule;update_rq_clock*'
or
./perf probe --add='schedule;update_rq_clock*'
2010-02-25 13:35:19 +00:00
Delete all probes on schedule().
./perf probe --del='schedule*'
2012-04-16 12:09:09 +00:00
Add probes at zfree() function on /bin/zsh
2012-04-16 12:09:25 +00:00
./perf probe -x /bin/zsh zfree or ./perf probe /bin/zsh zfree
2012-04-16 12:09:09 +00:00
Add probes at malloc() function on libc
2012-04-16 12:09:25 +00:00
./perf probe -x /lib/libc.so.6 malloc or ./perf probe /lib/libc.so.6 malloc
2010-02-25 13:35:19 +00:00
2009-10-17 00:08:27 +00:00
SEE ALSO
--------
linkperf:perf-trace[1], linkperf:perf-record[1]