2015-08-28 15:02:37 +00:00
|
|
|
/*
|
|
|
|
* builtin-trace.c
|
|
|
|
*
|
|
|
|
* Builtin 'trace' command:
|
|
|
|
*
|
|
|
|
* Display a continuously updated trace of any workload, CPU, specific PID,
|
|
|
|
* system wide, etc. Default format is loosely strace like, but any other
|
|
|
|
* event may be specified using --event.
|
|
|
|
*
|
|
|
|
* Copyright (C) 2012, 2013, 2014, 2015 Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
|
|
|
|
*
|
|
|
|
* Initially based on the 'trace' prototype by Thomas Gleixner:
|
|
|
|
*
|
|
|
|
* http://lwn.net/Articles/415728/ ("Announcing a new utility: 'trace'")
|
|
|
|
*
|
|
|
|
* Released under the GPL v2. (and only v2, not any later version)
|
|
|
|
*/
|
|
|
|
|
2013-06-11 15:29:18 +00:00
|
|
|
#include <traceevent/event-parse.h>
|
2015-09-02 07:56:35 +00:00
|
|
|
#include <api/fs/tracing_path.h>
|
2012-09-26 23:05:56 +00:00
|
|
|
#include "builtin.h"
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
#include "util/color.h"
|
2013-08-22 19:49:54 +00:00
|
|
|
#include "util/debug.h"
|
2017-04-25 18:30:47 +00:00
|
|
|
#include "util/event.h"
|
2012-09-26 23:05:56 +00:00
|
|
|
#include "util/evlist.h"
|
2015-12-15 15:39:39 +00:00
|
|
|
#include <subcmd/exec-cmd.h>
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
#include "util/machine.h"
|
2017-04-18 14:33:48 +00:00
|
|
|
#include "util/path.h"
|
2013-08-29 04:29:52 +00:00
|
|
|
#include "util/session.h"
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
#include "util/thread.h"
|
2015-12-15 15:39:39 +00:00
|
|
|
#include <subcmd/parse-options.h>
|
2013-08-09 15:28:31 +00:00
|
|
|
#include "util/strlist.h"
|
2013-08-29 04:29:53 +00:00
|
|
|
#include "util/intlist.h"
|
2012-09-26 23:05:56 +00:00
|
|
|
#include "util/thread_map.h"
|
2013-10-09 03:26:53 +00:00
|
|
|
#include "util/stat.h"
|
perf trace: Beautify statx syscall 'flag' and 'mask' arguments
To test it, build samples/statx/test_statx, which I did as:
$ make headers_install
$ cc -I ~/git/linux/usr/include samples/statx/test-statx.c -o /tmp/statx
And then use perf trace on it:
# perf trace -e statx /tmp/statx /etc/passwd
statx(/etc/passwd) = 0
results=7ff
Size: 3496 Blocks: 8 IO Block: 4096 regular file
Device: fd:00 Inode: 280156 Links: 1
Access: (0644/-rw-r--r--) Uid: 0 Gid: 0
Access: 2017-03-29 16:01:01.650073438-0300
Modify: 2017-03-10 16:25:14.156479354-0300
Change: 2017-03-10 16:25:14.171479328-0300
0.000 ( 0.007 ms): statx/30648 statx(dfd: CWD, filename: 0x7ef503f4, flags: SYMLINK_NOFOLLOW, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7fff7ef4eb10) = 0
#
Using the test-stat.c options to change the mask:
# perf trace -e statx /tmp/statx -O /etc/passwd > /dev/null
0.000 ( 0.008 ms): statx/30745 statx(dfd: CWD, filename: 0x3a0753f4, flags: SYMLINK_NOFOLLOW, mask: BTIME, buffer: 0x7ffd3a0735c0) = 0
#
# perf trace -e statx /tmp/statx -A /etc/passwd > /dev/null
0.000 ( 0.010 ms): statx/30757 statx(dfd: CWD, filename: 0xa94e63f4, flags: SYMLINK_NOFOLLOW|NO_AUTOMOUNT, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffea94e49d0) = 0
#
# trace --no-inherit -e statx /tmp/statx -F /etc/passwd > /dev/null
0.000 ( 0.011 ms): statx(dfd: CWD, filename: 0x3b02d3f3, flags: SYMLINK_NOFOLLOW|STATX_FORCE_SYNC, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffd3b02c850) = 0
#
# trace --no-inherit -e statx /tmp/statx -F -L /etc/passwd > /dev/null
0.000 ( 0.008 ms): statx(dfd: CWD, filename: 0x15cff3f3, flags: STATX_FORCE_SYNC, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7fff15cfdda0) = 0
#
# trace --no-inherit -e statx /tmp/statx -D -O /etc/passwd > /dev/null
0.000 ( 0.009 ms): statx(dfd: CWD, filename: 0xfa37f3f3, flags: SYMLINK_NOFOLLOW|STATX_DONT_SYNC, mask: BTIME, buffer: 0x7ffffa37da20) = 0
#
Adding a probe to get the filename collected as well:
# perf probe 'vfs_getname=getname_flags:72 pathname=result->name:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=result->name:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
# trace --no-inherit -e statx /tmp/statx -D -O /etc/passwd > /dev/null
0.169 ( 0.007 ms): statx(dfd: CWD, filename: /etc/passwd, flags: SYMLINK_NOFOLLOW|STATX_DONT_SYNC, mask: BTIME, buffer: 0x7ffda9bf50f0) = 0
#
Same technique could be used to collect and beautify the result put in
the 'buffer' argument.
Finally do a system wide 'perf trace' session looking for any use of statx,
then run the test proggie with various flags:
# trace -e statx
16612.967 ( 0.028 ms): statx/4562 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffef195d660) = 0
33064.447 ( 0.011 ms): statx/4569 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW|STATX_FORCE_SYNC, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffc5484c790) = 0
36050.891 ( 0.023 ms): statx/4576 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW, mask: BTIME, buffer: 0x7ffeb18b66e0) = 0
38039.889 ( 0.023 ms): statx/4584 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7fff1db0ea90) = 0
^C#
This one also starts moving the beautifiers from files directly included
in builtin-trace.c to separate objects + a beauty.h header with
prototypes, so that we can add test cases in tools/perf/tests/ to fire
syscalls with various arguments and then get them intercepted as
syscalls:sys_enter_foo or raw_syscalls:sys_enter + sys_exit to then
format and check that the formatted output is the one we expect.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-xvzw8eynffvez5czyzidhrno@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-14 19:19:30 +00:00
|
|
|
#include "trace/beauty/beauty.h"
|
2013-12-03 13:09:24 +00:00
|
|
|
#include "trace-event.h"
|
2013-12-05 02:41:39 +00:00
|
|
|
#include "util/parse-events.h"
|
2016-02-26 09:31:54 +00:00
|
|
|
#include "util/bpf-loader.h"
|
2016-04-08 11:34:15 +00:00
|
|
|
#include "callchain.h"
|
2017-04-17 19:23:22 +00:00
|
|
|
#include "print_binary.h"
|
2017-04-17 19:51:59 +00:00
|
|
|
#include "string2.h"
|
2016-04-04 16:32:20 +00:00
|
|
|
#include "syscalltbl.h"
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
#include "rb_resort.h"
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2017-04-18 13:46:11 +00:00
|
|
|
#include <errno.h>
|
2017-04-17 18:23:08 +00:00
|
|
|
#include <inttypes.h>
|
2016-04-04 16:32:20 +00:00
|
|
|
#include <libaudit.h> /* FIXME: Still needed for audit_errno_to_name */
|
2017-04-19 22:06:30 +00:00
|
|
|
#include <poll.h>
|
2017-04-19 18:49:18 +00:00
|
|
|
#include <signal.h>
|
2012-09-26 23:05:56 +00:00
|
|
|
#include <stdlib.h>
|
2017-01-09 20:26:26 +00:00
|
|
|
#include <string.h>
|
2015-09-07 08:38:06 +00:00
|
|
|
#include <linux/err.h>
|
2016-03-30 22:43:32 +00:00
|
|
|
#include <linux/filter.h>
|
|
|
|
#include <linux/audit.h>
|
2017-04-17 14:39:06 +00:00
|
|
|
#include <linux/kernel.h>
|
perf trace: Pretty print getrandom() args
# trace -e getrandom
35622.560 ( 0.023 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35622.585 ( 0.006 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35622.594 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35627.395 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
35630.940 ( 0.013 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
35718.613 ( 0.015 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35718.629 ( 0.005 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35718.637 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35719.355 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
35721.042 ( 0.030 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41090.830 ( 0.012 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41090.845 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41090.851 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41091.750 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
41091.823 ( 0.006 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41122.078 ( 0.053 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41122.129 ( 0.009 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41122.139 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41124.492 ( 0.007 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
41124.470 ( 0.013 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41590.832 ( 0.014 ms): chrome/5957 getrandom(buf: 0x7fabac7b15b0, count: 16, flags: NONBLOCK ) = 16
41590.884 ( 0.004 ms): chrome/5957 getrandom(buf: 0x7fabac7b15c0, count: 16, flags: NONBLOCK ) = 16
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-gca0n1p3aca3depey703ph2q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 23:02:15 +00:00
|
|
|
#include <linux/random.h>
|
2016-04-14 21:29:08 +00:00
|
|
|
#include <linux/stringify.h>
|
2016-08-05 18:40:30 +00:00
|
|
|
#include <linux/time64.h>
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2017-04-17 19:10:49 +00:00
|
|
|
#include "sane_ctype.h"
|
|
|
|
|
2015-05-14 20:39:03 +00:00
|
|
|
#ifndef O_CLOEXEC
|
|
|
|
# define O_CLOEXEC 02000000
|
|
|
|
#endif
|
|
|
|
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
struct trace {
|
|
|
|
struct perf_tool tool;
|
2016-04-04 16:32:20 +00:00
|
|
|
struct syscalltbl *sctbl;
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
struct {
|
|
|
|
int max;
|
|
|
|
struct syscall *table;
|
|
|
|
struct {
|
|
|
|
struct perf_evsel *sys_enter,
|
|
|
|
*sys_exit;
|
|
|
|
} events;
|
|
|
|
} syscalls;
|
|
|
|
struct record_opts opts;
|
|
|
|
struct perf_evlist *evlist;
|
|
|
|
struct machine *host;
|
|
|
|
struct thread *current;
|
|
|
|
u64 base_time;
|
|
|
|
FILE *output;
|
|
|
|
unsigned long nr_events;
|
|
|
|
struct strlist *ev_qualifier;
|
|
|
|
struct {
|
|
|
|
size_t nr;
|
|
|
|
int *entries;
|
|
|
|
} ev_qualifier_ids;
|
|
|
|
struct {
|
|
|
|
size_t nr;
|
|
|
|
pid_t *entries;
|
|
|
|
} filter_pids;
|
|
|
|
double duration_filter;
|
|
|
|
double runtime_ms;
|
|
|
|
struct {
|
|
|
|
u64 vfs_getname,
|
|
|
|
proc_getname;
|
|
|
|
} stats;
|
2016-04-14 21:29:08 +00:00
|
|
|
unsigned int max_stack;
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
unsigned int min_stack;
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
bool not_ev_qualifier;
|
|
|
|
bool live;
|
|
|
|
bool full_time;
|
|
|
|
bool sched;
|
|
|
|
bool multiple_threads;
|
|
|
|
bool summary;
|
|
|
|
bool summary_only;
|
|
|
|
bool show_comm;
|
|
|
|
bool show_tool_stats;
|
|
|
|
bool trace_syscalls;
|
2016-04-11 18:49:11 +00:00
|
|
|
bool kernel_syscallchains;
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
bool force;
|
|
|
|
bool vfs_getname;
|
|
|
|
int trace_pgfaults;
|
2016-04-04 16:32:20 +00:00
|
|
|
int open_id;
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
};
|
trace: Beautify perf_event_open syscall
Syswide tracing and then running 'stat' and 'trace':
$ perf trace -e perf_event_open
1034.649 (0.019 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = -1 EINVAL Invalid argument
1034.670 (0.008 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.681 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.692 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
9986.983 (0.014 ms): trace/6139 perf_event_open(attr_uptr: 0x7ffd9c629320, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.026 (0.016 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.041 (0.008 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.489 (0.092 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.536 (0.044 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 4
9987.580 (0.041 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 5
9987.620 (0.037 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 7
9987.659 (0.035 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 8
9987.692 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 9
9987.727 (0.032 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 10
9987.761 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 11
Need to intercept perf_copy_attr() with a kprobe or with eBPF...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-njb105hab2i3t5dexym9lskl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-12 01:47:54 +00:00
|
|
|
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
struct tp_field {
|
|
|
|
int offset;
|
|
|
|
union {
|
|
|
|
u64 (*integer)(struct tp_field *field, struct perf_sample *sample);
|
|
|
|
void *(*pointer)(struct tp_field *field, struct perf_sample *sample);
|
|
|
|
};
|
|
|
|
};
|
|
|
|
|
|
|
|
#define TP_UINT_FIELD(bits) \
|
|
|
|
static u64 tp_field__u##bits(struct tp_field *field, struct perf_sample *sample) \
|
|
|
|
{ \
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
u##bits value; \
|
|
|
|
memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
|
|
|
|
return value; \
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
TP_UINT_FIELD(8);
|
|
|
|
TP_UINT_FIELD(16);
|
|
|
|
TP_UINT_FIELD(32);
|
|
|
|
TP_UINT_FIELD(64);
|
|
|
|
|
|
|
|
#define TP_UINT_FIELD__SWAPPED(bits) \
|
|
|
|
static u64 tp_field__swapped_u##bits(struct tp_field *field, struct perf_sample *sample) \
|
|
|
|
{ \
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
u##bits value; \
|
|
|
|
memcpy(&value, sample->raw_data + field->offset, sizeof(value)); \
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
return bswap_##bits(value);\
|
|
|
|
}
|
|
|
|
|
|
|
|
TP_UINT_FIELD__SWAPPED(16);
|
|
|
|
TP_UINT_FIELD__SWAPPED(32);
|
|
|
|
TP_UINT_FIELD__SWAPPED(64);
|
|
|
|
|
|
|
|
static int tp_field__init_uint(struct tp_field *field,
|
|
|
|
struct format_field *format_field,
|
|
|
|
bool needs_swap)
|
|
|
|
{
|
|
|
|
field->offset = format_field->offset;
|
|
|
|
|
|
|
|
switch (format_field->size) {
|
|
|
|
case 1:
|
|
|
|
field->integer = tp_field__u8;
|
|
|
|
break;
|
|
|
|
case 2:
|
|
|
|
field->integer = needs_swap ? tp_field__swapped_u16 : tp_field__u16;
|
|
|
|
break;
|
|
|
|
case 4:
|
|
|
|
field->integer = needs_swap ? tp_field__swapped_u32 : tp_field__u32;
|
|
|
|
break;
|
|
|
|
case 8:
|
|
|
|
field->integer = needs_swap ? tp_field__swapped_u64 : tp_field__u64;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
return sample->raw_data + field->offset;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int tp_field__init_ptr(struct tp_field *field, struct format_field *format_field)
|
|
|
|
{
|
|
|
|
field->offset = format_field->offset;
|
|
|
|
field->pointer = tp_field__ptr;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
struct syscall_tp {
|
|
|
|
struct tp_field id;
|
|
|
|
union {
|
|
|
|
struct tp_field args, ret;
|
|
|
|
};
|
|
|
|
};
|
|
|
|
|
|
|
|
static int perf_evsel__init_tp_uint_field(struct perf_evsel *evsel,
|
|
|
|
struct tp_field *field,
|
|
|
|
const char *name)
|
|
|
|
{
|
|
|
|
struct format_field *format_field = perf_evsel__field(evsel, name);
|
|
|
|
|
|
|
|
if (format_field == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return tp_field__init_uint(field, format_field, evsel->needs_swap);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define perf_evsel__init_sc_tp_uint_field(evsel, name) \
|
|
|
|
({ struct syscall_tp *sc = evsel->priv;\
|
|
|
|
perf_evsel__init_tp_uint_field(evsel, &sc->name, #name); })
|
|
|
|
|
|
|
|
static int perf_evsel__init_tp_ptr_field(struct perf_evsel *evsel,
|
|
|
|
struct tp_field *field,
|
|
|
|
const char *name)
|
|
|
|
{
|
|
|
|
struct format_field *format_field = perf_evsel__field(evsel, name);
|
|
|
|
|
|
|
|
if (format_field == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return tp_field__init_ptr(field, format_field);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define perf_evsel__init_sc_tp_ptr_field(evsel, name) \
|
|
|
|
({ struct syscall_tp *sc = evsel->priv;\
|
|
|
|
perf_evsel__init_tp_ptr_field(evsel, &sc->name, #name); })
|
|
|
|
|
|
|
|
static void perf_evsel__delete_priv(struct perf_evsel *evsel)
|
|
|
|
{
|
2013-12-26 20:41:15 +00:00
|
|
|
zfree(&evsel->priv);
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
perf_evsel__delete(evsel);
|
|
|
|
}
|
|
|
|
|
2013-11-12 11:51:45 +00:00
|
|
|
static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel, void *handler)
|
|
|
|
{
|
|
|
|
evsel->priv = malloc(sizeof(struct syscall_tp));
|
|
|
|
if (evsel->priv != NULL) {
|
|
|
|
if (perf_evsel__init_sc_tp_uint_field(evsel, id))
|
|
|
|
goto out_delete;
|
|
|
|
|
|
|
|
evsel->handler = handler;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
out_delete:
|
2013-12-26 20:41:15 +00:00
|
|
|
zfree(&evsel->priv);
|
2013-11-12 11:51:45 +00:00
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
2013-11-07 19:41:19 +00:00
|
|
|
static struct perf_evsel *perf_evsel__syscall_newtp(const char *direction, void *handler)
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
{
|
2013-11-07 19:41:19 +00:00
|
|
|
struct perf_evsel *evsel = perf_evsel__newtp("raw_syscalls", direction);
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
|
2013-12-05 02:41:39 +00:00
|
|
|
/* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
|
2015-09-07 08:38:06 +00:00
|
|
|
if (IS_ERR(evsel))
|
2013-12-05 02:41:39 +00:00
|
|
|
evsel = perf_evsel__newtp("syscalls", direction);
|
|
|
|
|
2015-09-07 08:38:06 +00:00
|
|
|
if (IS_ERR(evsel))
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (perf_evsel__init_syscall_tp(evsel, handler))
|
|
|
|
goto out_delete;
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
|
|
|
|
return evsel;
|
|
|
|
|
|
|
|
out_delete:
|
|
|
|
perf_evsel__delete_priv(evsel);
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define perf_evsel__sc_tp_uint(evsel, name, sample) \
|
|
|
|
({ struct syscall_tp *fields = evsel->priv; \
|
|
|
|
fields->name.integer(&fields->name, sample); })
|
|
|
|
|
|
|
|
#define perf_evsel__sc_tp_ptr(evsel, name, sample) \
|
|
|
|
({ struct syscall_tp *fields = evsel->priv; \
|
|
|
|
fields->name.pointer(&fields->name, sample); })
|
|
|
|
|
2013-09-03 18:50:28 +00:00
|
|
|
struct strarray {
|
2013-10-08 19:00:21 +00:00
|
|
|
int offset;
|
2013-09-03 18:50:28 +00:00
|
|
|
int nr_entries;
|
|
|
|
const char **entries;
|
|
|
|
};
|
|
|
|
|
|
|
|
#define DEFINE_STRARRAY(array) struct strarray strarray__##array = { \
|
|
|
|
.nr_entries = ARRAY_SIZE(array), \
|
|
|
|
.entries = array, \
|
|
|
|
}
|
|
|
|
|
2013-10-08 19:00:21 +00:00
|
|
|
#define DEFINE_STRARRAY_OFFSET(array, off) struct strarray strarray__##array = { \
|
|
|
|
.offset = off, \
|
|
|
|
.nr_entries = ARRAY_SIZE(array), \
|
|
|
|
.entries = array, \
|
|
|
|
}
|
|
|
|
|
2013-10-08 20:17:43 +00:00
|
|
|
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
|
|
|
|
const char *intfmt,
|
|
|
|
struct syscall_arg *arg)
|
2013-09-03 18:50:28 +00:00
|
|
|
{
|
|
|
|
struct strarray *sa = arg->parm;
|
2013-10-08 19:00:21 +00:00
|
|
|
int idx = arg->val - sa->offset;
|
2013-09-03 18:50:28 +00:00
|
|
|
|
|
|
|
if (idx < 0 || idx >= sa->nr_entries)
|
2013-10-08 20:17:43 +00:00
|
|
|
return scnprintf(bf, size, intfmt, arg->val);
|
2013-09-03 18:50:28 +00:00
|
|
|
|
|
|
|
return scnprintf(bf, size, "%s", sa->entries[idx]);
|
|
|
|
}
|
|
|
|
|
2013-10-08 20:17:43 +00:00
|
|
|
static size_t syscall_arg__scnprintf_strarray(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
return __syscall_arg__scnprintf_strarray(bf, size, "%d", arg);
|
|
|
|
}
|
|
|
|
|
2013-09-03 18:50:28 +00:00
|
|
|
#define SCA_STRARRAY syscall_arg__scnprintf_strarray
|
|
|
|
|
2014-02-10 17:09:48 +00:00
|
|
|
#if defined(__i386__) || defined(__x86_64__)
|
|
|
|
/*
|
|
|
|
* FIXME: Make this available to all arches as soon as the ioctl beautifier
|
|
|
|
* gets rewritten to support all arches.
|
|
|
|
*/
|
perf trace: Initial beautifier for ioctl's 'cmd' arg
[root@zoo linux]# trace -e ioctl | grep -v "cmd: 0x" | head -10
0.386 ( 0.001 ms): trace/1602 ioctl(fd: 1<pipe:[127057]>, cmd: TCGETS, arg: 0x7fff59fcb4d0 ) = -1 ENOTTY Inappropriate ioctl for device
1459.368 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.586 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.611 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
3740.526 ( 0.002 ms): awk/1612 ioctl(fd: 1<pipe:[128265]>, cmd: TCGETS, arg: 0x7fff4d166b90 ) = -1 ENOTTY Inappropriate ioctl for device
3740.704 ( 0.001 ms): awk/1612 ioctl(fd: 3</proc/meminfo>, cmd: TCGETS, arg: 0x7fff4d1669a0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.550 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.555 ( 0.003 ms): ps/1614 ioctl(fd: 2<socket:[19550]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.558 ( 0.002 ms): ps/1614 ioctl(cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.572 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TCGETS, arg: 0x7fff59176220 ) = -1 ENOTTY Inappropriate ioctl for device
[root@zoo linux]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-afajwap3mr60dfl4qpdl1pxn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-08 20:43:20 +00:00
|
|
|
static size_t syscall_arg__scnprintf_strhexarray(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
return __syscall_arg__scnprintf_strarray(bf, size, "%#x", arg);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define SCA_STRHEXARRAY syscall_arg__scnprintf_strhexarray
|
2014-02-10 17:09:48 +00:00
|
|
|
#endif /* defined(__i386__) || defined(__x86_64__) */
|
perf trace: Initial beautifier for ioctl's 'cmd' arg
[root@zoo linux]# trace -e ioctl | grep -v "cmd: 0x" | head -10
0.386 ( 0.001 ms): trace/1602 ioctl(fd: 1<pipe:[127057]>, cmd: TCGETS, arg: 0x7fff59fcb4d0 ) = -1 ENOTTY Inappropriate ioctl for device
1459.368 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.586 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.611 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
3740.526 ( 0.002 ms): awk/1612 ioctl(fd: 1<pipe:[128265]>, cmd: TCGETS, arg: 0x7fff4d166b90 ) = -1 ENOTTY Inappropriate ioctl for device
3740.704 ( 0.001 ms): awk/1612 ioctl(fd: 3</proc/meminfo>, cmd: TCGETS, arg: 0x7fff4d1669a0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.550 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.555 ( 0.003 ms): ps/1614 ioctl(fd: 2<socket:[19550]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.558 ( 0.002 ms): ps/1614 ioctl(cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.572 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TCGETS, arg: 0x7fff59176220 ) = -1 ENOTTY Inappropriate ioctl for device
[root@zoo linux]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-afajwap3mr60dfl4qpdl1pxn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-08 20:43:20 +00:00
|
|
|
|
2013-09-24 14:04:32 +00:00
|
|
|
static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg);
|
|
|
|
|
|
|
|
#define SCA_FD syscall_arg__scnprintf_fd
|
|
|
|
|
2016-07-05 17:43:27 +00:00
|
|
|
#ifndef AT_FDCWD
|
|
|
|
#define AT_FDCWD -100
|
|
|
|
#endif
|
|
|
|
|
2013-09-24 14:04:32 +00:00
|
|
|
static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
int fd = arg->val;
|
|
|
|
|
|
|
|
if (fd == AT_FDCWD)
|
|
|
|
return scnprintf(bf, size, "CWD");
|
|
|
|
|
|
|
|
return syscall_arg__scnprintf_fd(bf, size, arg);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define SCA_FDAT syscall_arg__scnprintf_fd_at
|
|
|
|
|
|
|
|
static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg);
|
|
|
|
|
|
|
|
#define SCA_CLOSE_FD syscall_arg__scnprintf_close_fd
|
|
|
|
|
2013-09-02 13:39:21 +00:00
|
|
|
static size_t syscall_arg__scnprintf_hex(char *bf, size_t size,
|
2013-09-03 15:20:12 +00:00
|
|
|
struct syscall_arg *arg)
|
2013-08-23 21:14:48 +00:00
|
|
|
{
|
2013-09-03 15:20:12 +00:00
|
|
|
return scnprintf(bf, size, "%#lx", arg->val);
|
2013-08-23 21:14:48 +00:00
|
|
|
}
|
|
|
|
|
2013-08-26 15:29:38 +00:00
|
|
|
#define SCA_HEX syscall_arg__scnprintf_hex
|
|
|
|
|
trace: Beautify perf_event_open syscall
Syswide tracing and then running 'stat' and 'trace':
$ perf trace -e perf_event_open
1034.649 (0.019 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = -1 EINVAL Invalid argument
1034.670 (0.008 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.681 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.692 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
9986.983 (0.014 ms): trace/6139 perf_event_open(attr_uptr: 0x7ffd9c629320, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.026 (0.016 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.041 (0.008 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.489 (0.092 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.536 (0.044 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 4
9987.580 (0.041 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 5
9987.620 (0.037 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 7
9987.659 (0.035 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 8
9987.692 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 9
9987.727 (0.032 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 10
9987.761 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 11
Need to intercept perf_copy_attr() with a kprobe or with eBPF...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-njb105hab2i3t5dexym9lskl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-12 01:47:54 +00:00
|
|
|
static size_t syscall_arg__scnprintf_int(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
return scnprintf(bf, size, "%d", arg->val);
|
|
|
|
}
|
|
|
|
|
|
|
|
#define SCA_INT syscall_arg__scnprintf_int
|
|
|
|
|
2015-10-29 14:48:18 +00:00
|
|
|
static const char *bpf_cmd[] = {
|
|
|
|
"MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
|
|
|
|
"MAP_GET_NEXT_KEY", "PROG_LOAD",
|
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(bpf_cmd);
|
|
|
|
|
2013-10-08 19:00:21 +00:00
|
|
|
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
|
|
|
|
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, 1);
|
perf trace: Beautify epoll_ctl 'op' arg
[root@sandy ~]# perf trace -e epoll_ctl
2.490 (0.003 ms): systemd-logind/586 epoll_ctl(epfd: 10, op: ADD, fd: 24, event: 0x7fff22314ef0) = 0
2.621 (0.003 ms): systemd-logind/586 epoll_ctl(epfd: 10, op: DEL, fd: 24 ) = 0
2.833 (0.010 ms): systemd-logind/586 epoll_ctl(epfd: 10, op: ADD, fd: 24, event: 0x7fff22314cd0) = 0
2.953 (0.002 ms): systemd-logind/586 epoll_ctl(epfd: 10, op: DEL, fd: 24 ) = 0
3.118 (0.002 ms): systemd-logind/586 epoll_ctl(epfd: 10, op: ADD, fd: 24, event: 0x7fff22314d20) = 0
4.762 (0.002 ms): systemd-logind/586 epoll_ctl(epfd: 10, op: DEL, fd: 24 ) = 0
^C[root@sandy ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-88xz9phc8cbicnxonud6if8h@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-20 14:27:32 +00:00
|
|
|
|
2013-09-03 18:50:28 +00:00
|
|
|
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
|
|
|
|
static DEFINE_STRARRAY(itimers);
|
|
|
|
|
perf trace: Beautify keyctl's option arg
8.697 (0.103 ms): pool/2343 keyctl(option: GET_PERSISTENT, arg2: 1000, arg3: 4294967294, arg4: 140703061514067, arg5: 140703692383680) = 1023192809
8.763 (0.049 ms): pool/2343 keyctl(option: SEARCH, arg2: 1023192809, arg3: 140703745767772, arg4: 140703745767832, arg5: 4294967294) = 140224497
8.789 (0.016 ms): pool/2343 keyctl(option: SEARCH, arg2: 140224497, arg3: 140703745767814, arg4: 140703745767900) = 512300257
8.807 (0.011 ms): pool/2343 keyctl(option: READ, arg2: 512300257 ) = 13
8.822 (0.008 ms): pool/2343 keyctl(option: READ, arg2: 512300257, arg3: 140703061514000, arg4: 13 ) = 13
8.837 (0.007 ms): pool/2343 keyctl(option: READ, arg2: 140224497 ) = 4
8.852 (0.009 ms): pool/2343 keyctl(option: READ, arg2: 140224497, arg3: 140703061514000, arg4: 4 ) = 4
8.869 (0.010 ms): pool/2343 keyctl(option: SEARCH, arg2: 140224497, arg3: 140703745767772, arg4: 140703061514032) = -1 ENOKEY Required key not available
8.892 (0.017 ms): pool/2343 keyctl(option: DESCRIBE, arg2: 512300257 ) = 43
8.910 (0.012 ms): pool/2343 keyctl(option: DESCRIBE, arg2: 512300257, arg3: 140703061544384, arg4: 43) = 43
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-013ab219irsxngyumrf5gp8s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 14:05:36 +00:00
|
|
|
static const char *keyctl_options[] = {
|
|
|
|
"GET_KEYRING_ID", "JOIN_SESSION_KEYRING", "UPDATE", "REVOKE", "CHOWN",
|
|
|
|
"SETPERM", "DESCRIBE", "CLEAR", "LINK", "UNLINK", "SEARCH", "READ",
|
|
|
|
"INSTANTIATE", "NEGATE", "SET_REQKEY_KEYRING", "SET_TIMEOUT",
|
|
|
|
"ASSUME_AUTHORITY", "GET_SECURITY", "SESSION_TO_PARENT", "REJECT",
|
|
|
|
"INSTANTIATE_IOV", "INVALIDATE", "GET_PERSISTENT",
|
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(keyctl_options);
|
|
|
|
|
2013-09-03 19:15:12 +00:00
|
|
|
static const char *whences[] = { "SET", "CUR", "END",
|
|
|
|
#ifdef SEEK_DATA
|
|
|
|
"DATA",
|
|
|
|
#endif
|
|
|
|
#ifdef SEEK_HOLE
|
|
|
|
"HOLE",
|
|
|
|
#endif
|
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(whences);
|
2013-09-02 16:46:44 +00:00
|
|
|
|
2013-09-03 19:28:58 +00:00
|
|
|
static const char *fcntl_cmds[] = {
|
|
|
|
"DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
|
|
|
|
"SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "F_GETLK64",
|
|
|
|
"F_SETLK64", "F_SETLKW64", "F_SETOWN_EX", "F_GETOWN_EX",
|
|
|
|
"F_GETOWNER_UIDS",
|
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(fcntl_cmds);
|
|
|
|
|
2013-09-04 14:52:33 +00:00
|
|
|
static const char *rlimit_resources[] = {
|
|
|
|
"CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
|
|
|
|
"MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
|
|
|
|
"RTTIME",
|
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(rlimit_resources);
|
|
|
|
|
2013-09-03 19:37:46 +00:00
|
|
|
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
|
|
|
|
static DEFINE_STRARRAY(sighow);
|
|
|
|
|
2013-09-23 01:45:00 +00:00
|
|
|
static const char *clockid[] = {
|
|
|
|
"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
|
2015-08-11 13:38:38 +00:00
|
|
|
"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE", "BOOTTIME",
|
|
|
|
"REALTIME_ALARM", "BOOTTIME_ALARM", "SGI_CYCLE", "TAI"
|
2013-09-23 01:45:00 +00:00
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(clockid);
|
|
|
|
|
2013-09-04 13:27:41 +00:00
|
|
|
static const char *socket_families[] = {
|
|
|
|
"UNSPEC", "LOCAL", "INET", "AX25", "IPX", "APPLETALK", "NETROM",
|
|
|
|
"BRIDGE", "ATMPVC", "X25", "INET6", "ROSE", "DECnet", "NETBEUI",
|
|
|
|
"SECURITY", "KEY", "NETLINK", "PACKET", "ASH", "ECONET", "ATMSVC",
|
|
|
|
"RDS", "SNA", "IRDA", "PPPOX", "WANPIPE", "LLC", "IB", "CAN", "TIPC",
|
|
|
|
"BLUETOOTH", "IUCV", "RXRPC", "ISDN", "PHONET", "IEEE802154", "CAIF",
|
|
|
|
"ALG", "NFC", "VSOCK",
|
|
|
|
};
|
|
|
|
static DEFINE_STRARRAY(socket_families);
|
|
|
|
|
2013-09-04 14:42:27 +00:00
|
|
|
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
size_t printed = 0;
|
|
|
|
int mode = arg->val;
|
|
|
|
|
|
|
|
if (mode == F_OK) /* 0 */
|
|
|
|
return scnprintf(bf, size, "F");
|
|
|
|
#define P_MODE(n) \
|
|
|
|
if (mode & n##_OK) { \
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s", #n); \
|
|
|
|
mode &= ~n##_OK; \
|
|
|
|
}
|
|
|
|
|
|
|
|
P_MODE(R);
|
|
|
|
P_MODE(W);
|
|
|
|
P_MODE(X);
|
|
|
|
#undef P_MODE
|
|
|
|
|
|
|
|
if (mode)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "|%#x", mode);
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define SCA_ACCMODE syscall_arg__scnprintf_access_mode
|
|
|
|
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg);
|
|
|
|
|
|
|
|
#define SCA_FILENAME syscall_arg__scnprintf_filename
|
|
|
|
|
2013-09-23 15:52:04 +00:00
|
|
|
static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
int printed = 0, flags = arg->val;
|
|
|
|
|
|
|
|
#define P_FLAG(n) \
|
|
|
|
if (flags & O_##n) { \
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
|
|
|
|
flags &= ~O_##n; \
|
|
|
|
}
|
|
|
|
|
|
|
|
P_FLAG(CLOEXEC);
|
|
|
|
P_FLAG(NONBLOCK);
|
|
|
|
#undef P_FLAG
|
|
|
|
|
|
|
|
if (flags)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define SCA_PIPE_FLAGS syscall_arg__scnprintf_pipe_flags
|
|
|
|
|
2014-02-10 17:09:48 +00:00
|
|
|
#if defined(__i386__) || defined(__x86_64__)
|
|
|
|
/*
|
|
|
|
* FIXME: Make this available to all arches.
|
|
|
|
*/
|
perf trace: Initial beautifier for ioctl's 'cmd' arg
[root@zoo linux]# trace -e ioctl | grep -v "cmd: 0x" | head -10
0.386 ( 0.001 ms): trace/1602 ioctl(fd: 1<pipe:[127057]>, cmd: TCGETS, arg: 0x7fff59fcb4d0 ) = -1 ENOTTY Inappropriate ioctl for device
1459.368 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.586 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.611 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
3740.526 ( 0.002 ms): awk/1612 ioctl(fd: 1<pipe:[128265]>, cmd: TCGETS, arg: 0x7fff4d166b90 ) = -1 ENOTTY Inappropriate ioctl for device
3740.704 ( 0.001 ms): awk/1612 ioctl(fd: 3</proc/meminfo>, cmd: TCGETS, arg: 0x7fff4d1669a0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.550 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.555 ( 0.003 ms): ps/1614 ioctl(fd: 2<socket:[19550]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.558 ( 0.002 ms): ps/1614 ioctl(cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.572 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TCGETS, arg: 0x7fff59176220 ) = -1 ENOTTY Inappropriate ioctl for device
[root@zoo linux]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-afajwap3mr60dfl4qpdl1pxn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-08 20:43:20 +00:00
|
|
|
#define TCGETS 0x5401
|
|
|
|
|
|
|
|
static const char *tioctls[] = {
|
|
|
|
"TCGETS", "TCSETS", "TCSETSW", "TCSETSF", "TCGETA", "TCSETA", "TCSETAW",
|
|
|
|
"TCSETAF", "TCSBRK", "TCXONC", "TCFLSH", "TIOCEXCL", "TIOCNXCL",
|
|
|
|
"TIOCSCTTY", "TIOCGPGRP", "TIOCSPGRP", "TIOCOUTQ", "TIOCSTI",
|
|
|
|
"TIOCGWINSZ", "TIOCSWINSZ", "TIOCMGET", "TIOCMBIS", "TIOCMBIC",
|
|
|
|
"TIOCMSET", "TIOCGSOFTCAR", "TIOCSSOFTCAR", "FIONREAD", "TIOCLINUX",
|
|
|
|
"TIOCCONS", "TIOCGSERIAL", "TIOCSSERIAL", "TIOCPKT", "FIONBIO",
|
|
|
|
"TIOCNOTTY", "TIOCSETD", "TIOCGETD", "TCSBRKP", [0x27] = "TIOCSBRK",
|
|
|
|
"TIOCCBRK", "TIOCGSID", "TCGETS2", "TCSETS2", "TCSETSW2", "TCSETSF2",
|
|
|
|
"TIOCGRS485", "TIOCSRS485", "TIOCGPTN", "TIOCSPTLCK",
|
|
|
|
"TIOCGDEV||TCGETX", "TCSETX", "TCSETXF", "TCSETXW", "TIOCSIG",
|
|
|
|
"TIOCVHANGUP", "TIOCGPKT", "TIOCGPTLCK", "TIOCGEXCL",
|
|
|
|
[0x50] = "FIONCLEX", "FIOCLEX", "FIOASYNC", "TIOCSERCONFIG",
|
|
|
|
"TIOCSERGWILD", "TIOCSERSWILD", "TIOCGLCKTRMIOS", "TIOCSLCKTRMIOS",
|
|
|
|
"TIOCSERGSTRUCT", "TIOCSERGETLSR", "TIOCSERGETMULTI", "TIOCSERSETMULTI",
|
|
|
|
"TIOCMIWAIT", "TIOCGICOUNT", [0x60] = "FIOQSIZE",
|
|
|
|
};
|
|
|
|
|
|
|
|
static DEFINE_STRARRAY_OFFSET(tioctls, 0x5401);
|
2014-02-10 17:09:48 +00:00
|
|
|
#endif /* defined(__i386__) || defined(__x86_64__) */
|
perf trace: Initial beautifier for ioctl's 'cmd' arg
[root@zoo linux]# trace -e ioctl | grep -v "cmd: 0x" | head -10
0.386 ( 0.001 ms): trace/1602 ioctl(fd: 1<pipe:[127057]>, cmd: TCGETS, arg: 0x7fff59fcb4d0 ) = -1 ENOTTY Inappropriate ioctl for device
1459.368 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.586 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.611 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
3740.526 ( 0.002 ms): awk/1612 ioctl(fd: 1<pipe:[128265]>, cmd: TCGETS, arg: 0x7fff4d166b90 ) = -1 ENOTTY Inappropriate ioctl for device
3740.704 ( 0.001 ms): awk/1612 ioctl(fd: 3</proc/meminfo>, cmd: TCGETS, arg: 0x7fff4d1669a0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.550 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.555 ( 0.003 ms): ps/1614 ioctl(fd: 2<socket:[19550]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.558 ( 0.002 ms): ps/1614 ioctl(cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.572 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TCGETS, arg: 0x7fff59176220 ) = -1 ENOTTY Inappropriate ioctl for device
[root@zoo linux]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-afajwap3mr60dfl4qpdl1pxn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-08 20:43:20 +00:00
|
|
|
|
2016-04-13 14:55:18 +00:00
|
|
|
#ifndef GRND_NONBLOCK
|
|
|
|
#define GRND_NONBLOCK 0x0001
|
|
|
|
#endif
|
|
|
|
#ifndef GRND_RANDOM
|
|
|
|
#define GRND_RANDOM 0x0002
|
|
|
|
#endif
|
|
|
|
|
perf trace: Pretty print getrandom() args
# trace -e getrandom
35622.560 ( 0.023 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35622.585 ( 0.006 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35622.594 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35627.395 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
35630.940 ( 0.013 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
35718.613 ( 0.015 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35718.629 ( 0.005 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35718.637 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35719.355 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
35721.042 ( 0.030 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41090.830 ( 0.012 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41090.845 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41090.851 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41091.750 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
41091.823 ( 0.006 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41122.078 ( 0.053 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41122.129 ( 0.009 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41122.139 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41124.492 ( 0.007 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
41124.470 ( 0.013 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41590.832 ( 0.014 ms): chrome/5957 getrandom(buf: 0x7fabac7b15b0, count: 16, flags: NONBLOCK ) = 16
41590.884 ( 0.004 ms): chrome/5957 getrandom(buf: 0x7fabac7b15c0, count: 16, flags: NONBLOCK ) = 16
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-gca0n1p3aca3depey703ph2q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 23:02:15 +00:00
|
|
|
static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
int printed = 0, flags = arg->val;
|
|
|
|
|
|
|
|
#define P_FLAG(n) \
|
|
|
|
if (flags & GRND_##n) { \
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
|
|
|
|
flags &= ~GRND_##n; \
|
|
|
|
}
|
|
|
|
|
|
|
|
P_FLAG(RANDOM);
|
|
|
|
P_FLAG(NONBLOCK);
|
|
|
|
#undef P_FLAG
|
|
|
|
|
|
|
|
if (flags)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
|
|
|
#define SCA_GETRANDOM_FLAGS syscall_arg__scnprintf_getrandom_flags
|
|
|
|
|
2013-09-20 15:13:37 +00:00
|
|
|
#define STRARRAY(arg, name, array) \
|
|
|
|
.arg_scnprintf = { [arg] = SCA_STRARRAY, }, \
|
|
|
|
.arg_parm = { [arg] = &strarray__##array, }
|
|
|
|
|
2016-04-13 15:10:19 +00:00
|
|
|
#include "trace/beauty/eventfd.c"
|
2016-05-11 13:29:36 +00:00
|
|
|
#include "trace/beauty/flock.c"
|
2016-05-06 15:45:25 +00:00
|
|
|
#include "trace/beauty/futex_op.c"
|
2016-04-13 15:05:44 +00:00
|
|
|
#include "trace/beauty/mmap.c"
|
perf trace: Beautify mode_t arguments
When reading the syscall tracepoint /format file, look for arguments of type
"mode_t" and attach a beautifier:
[root@jouet ~]# cat ~/bin/tp_with_fields_of_type
#!/bin/bash
grep -w $1 /sys/kernel/tracing/events/syscalls/*/format | sed -r 's%.*sys_enter_(.*)/format.*%\1%g' | paste -d, -s
# tp_with_fields_of_type umode_t
chmod,creat,fchmodat,fchmod,mkdirat,mkdir,mknodat,mknod,mq_open,openat,open
#
Testing it:
#define S_ISUID 0004000
#define S_ISGID 0002000
#define S_ISVTX 0001000
#define S_IRWXU 0000700
#define S_IRUSR 0000400
#define S_IWUSR 0000200
#define S_IXUSR 0000100
#define S_IRWXG 0000070
#define S_IRGRP 0000040
#define S_IWGRP 0000020
#define S_IXGRP 0000010
#define S_IRWXO 0000007
#define S_IROTH 0000004
#define S_IWOTH 0000002
#define S_IXOTH 0000001
# for mode in 4000 2000 1000 700 400 200 100 70 40 20 10 7 4 2 1 ; do \
echo -n $mode '->' ; trace --no-inherit -e chmod,fchmodat,fchmod chmod $mode x; \
done
4000 -> 0.338 ( 0.012 ms): fchmodat(dfd: CWD, filename: x, mode: ISUID) = 0
2000 -> 0.438 ( 0.015 ms): fchmodat(dfd: CWD, filename: x, mode: ISGID) = 0
1000 -> 0.677 ( 0.040 ms): fchmodat(dfd: CWD, filename: x, mode: ISVTX) = 0
700 -> 0.394 ( 0.013 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXU) = 0
400 -> 0.337 ( 0.010 ms): fchmodat(dfd: CWD, filename: x, mode: IRUSR) = 0
200 -> 0.259 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IWUSR) = 0
100 -> 0.249 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IXUSR) = 0
70 -> 0.266 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXG) = 0
40 -> 0.329 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IRGRP) = 0
20 -> 0.250 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IWGRP) = 0
10 -> 0.259 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IXGRP) = 0
7 -> 0.249 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXO) = 0
4 -> 0.278 ( 0.011 ms): fchmodat(dfd: CWD, filename: x, mode: IROTH) = 0
2 -> 0.276 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IWOTH) = 0
1 -> 0.250 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IXOTH) = 0
#
# trace --no-inherit -e chmod,fchmodat,fchmod chmod 7777 x
0.258 ( 0.011 ms): fchmodat(dfd: CWD, filename: x, mode: IALLUGO) = 0
# trace --no-inherit -e chmod,fchmodat,fchmod chmod 7770 x
0.258 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: ISUID|ISGID|ISVTX|IRWXU|IRWXG) = 0
# trace --no-inherit -e chmod,fchmodat,fchmod chmod 777 x
0.293 ( 0.012 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXUGO
#
Now lets see if check by using the tracepoint for that specific syscall,
instead of raw_syscalls:sys_enter as 'trace' does for its strace fu:
# trace --no-inherit --ev syscalls:sys_enter_fchmodat -e fchmodat chmod 666 x
0.255 ( ): syscalls:sys_enter_fchmodat:dfd: 0xffffffffffffff9c, filename: 0x55db32a3f0f0, mode: 0x000001b6)
0.268 ( 0.012 ms): fchmodat(dfd: CWD, filename: x, mode: IRUGO|IWUGO ) = 0
#
Perfect, 0x1bc == 0666.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-18e8zfgbkj83xo87yoom43kd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-07 15:05:51 +00:00
|
|
|
#include "trace/beauty/mode_t.c"
|
2016-04-27 22:01:52 +00:00
|
|
|
#include "trace/beauty/msg_flags.c"
|
2016-05-06 13:02:32 +00:00
|
|
|
#include "trace/beauty/open_flags.c"
|
2016-04-26 14:03:03 +00:00
|
|
|
#include "trace/beauty/perf_event_open.c"
|
2016-05-06 15:45:25 +00:00
|
|
|
#include "trace/beauty/pid.c"
|
2016-04-06 15:51:33 +00:00
|
|
|
#include "trace/beauty/sched_policy.c"
|
2016-05-11 13:32:20 +00:00
|
|
|
#include "trace/beauty/seccomp.c"
|
2016-05-06 12:58:02 +00:00
|
|
|
#include "trace/beauty/signum.c"
|
2016-04-14 16:53:10 +00:00
|
|
|
#include "trace/beauty/socket_type.c"
|
2016-04-06 17:11:36 +00:00
|
|
|
#include "trace/beauty/waitid_options.c"
|
2016-04-06 15:51:33 +00:00
|
|
|
|
2012-09-26 23:05:56 +00:00
|
|
|
static struct syscall_fmt {
|
|
|
|
const char *name;
|
2012-09-27 16:16:00 +00:00
|
|
|
const char *alias;
|
2013-09-03 15:20:12 +00:00
|
|
|
size_t (*arg_scnprintf[6])(char *bf, size_t size, struct syscall_arg *arg);
|
2013-09-03 18:50:28 +00:00
|
|
|
void *arg_parm[6];
|
2012-09-26 23:05:56 +00:00
|
|
|
bool errmsg;
|
perf trace: Infrastructure to show COMM strings for syscalls returning PIDs
Starting with clone, waitid and wait4:
# trace -e waitid,wait4
1.385 ( 1.385 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) = 1210 (ls)
1.426 ( 0.002 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1150, options: NOHANG|UNTRACED|CONTINUED) = 0
3.293 ( 0.604 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee0560 ) = 1214 (sed)
3.342 ( 0.002 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee01d0, options: NOHANG ) = -1 ECHILD No child processes
3.576 ( 0.016 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee0550, options: NOHANG|UNTRACED|CONTINUED) = 1211 (bash)
^C# trace -e clone
0.027 ( 0.000 ms): systemd/1 ... [continued]: clone()) = 1227 (systemd)
0.050 ( 0.000 ms): systemd/1227 ... [continued]: clone()) = 0
^C[root@jouet ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lyf5d3y5j15wikjb6pe6ukoi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 17:33:07 +00:00
|
|
|
bool errpid;
|
2012-09-26 23:05:56 +00:00
|
|
|
bool timeout;
|
2013-08-26 14:36:30 +00:00
|
|
|
bool hexret;
|
2012-09-26 23:05:56 +00:00
|
|
|
} syscall_fmts[] = {
|
2013-09-04 14:42:27 +00:00
|
|
|
{ .name = "access", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [1] = SCA_ACCMODE, /* mode */ }, },
|
2012-09-27 16:16:00 +00:00
|
|
|
{ .name = "arch_prctl", .errmsg = true, .alias = "prctl", },
|
2015-10-29 14:48:18 +00:00
|
|
|
{ .name = "bpf", .errmsg = true, STRARRAY(0, cmd, bpf_cmd), },
|
2013-08-26 15:29:38 +00:00
|
|
|
{ .name = "brk", .hexret = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* brk */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "chdir", .errmsg = true, },
|
|
|
|
{ .name = "chmod", .errmsg = true, },
|
|
|
|
{ .name = "chroot", .errmsg = true, },
|
2013-09-23 01:45:00 +00:00
|
|
|
{ .name = "clock_gettime", .errmsg = true, STRARRAY(0, clk_id, clockid), },
|
perf trace: Infrastructure to show COMM strings for syscalls returning PIDs
Starting with clone, waitid and wait4:
# trace -e waitid,wait4
1.385 ( 1.385 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) = 1210 (ls)
1.426 ( 0.002 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1150, options: NOHANG|UNTRACED|CONTINUED) = 0
3.293 ( 0.604 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee0560 ) = 1214 (sed)
3.342 ( 0.002 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee01d0, options: NOHANG ) = -1 ECHILD No child processes
3.576 ( 0.016 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee0550, options: NOHANG|UNTRACED|CONTINUED) = 1211 (bash)
^C# trace -e clone
0.027 ( 0.000 ms): systemd/1 ... [continued]: clone()) = 1227 (systemd)
0.050 ( 0.000 ms): systemd/1227 ... [continued]: clone()) = 0
^C[root@jouet ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lyf5d3y5j15wikjb6pe6ukoi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 17:33:07 +00:00
|
|
|
{ .name = "clone", .errpid = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "close", .errmsg = true,
|
2014-12-17 20:24:45 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_CLOSE_FD, /* fd */ }, },
|
2013-07-30 19:38:23 +00:00
|
|
|
{ .name = "connect", .errmsg = true, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "creat", .errmsg = true, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "dup", .errmsg = true, },
|
|
|
|
{ .name = "dup2", .errmsg = true, },
|
|
|
|
{ .name = "dup3", .errmsg = true, },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "epoll_ctl", .errmsg = true, STRARRAY(1, op, epoll_ctl_ops), },
|
2013-09-12 15:18:56 +00:00
|
|
|
{ .name = "eventfd2", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_EFD_FLAGS, /* flags */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "faccessat", .errmsg = true, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "fadvise64", .errmsg = true, },
|
|
|
|
{ .name = "fallocate", .errmsg = true, },
|
|
|
|
{ .name = "fchdir", .errmsg = true, },
|
|
|
|
{ .name = "fchmod", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "fchmodat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "fchown", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "fchownat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "fcntl", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [1] = SCA_STRARRAY, /* cmd */ },
|
2013-09-24 14:04:32 +00:00
|
|
|
.arg_parm = { [1] = &strarray__fcntl_cmds, /* cmd */ }, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "fdatasync", .errmsg = true, },
|
2013-09-20 14:49:50 +00:00
|
|
|
{ .name = "flock", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [1] = SCA_FLOCK, /* cmd */ }, },
|
|
|
|
{ .name = "fsetxattr", .errmsg = true, },
|
|
|
|
{ .name = "fstat", .errmsg = true, .alias = "newfstat", },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "fstatat", .errmsg = true, .alias = "newfstatat", },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "fstatfs", .errmsg = true, },
|
|
|
|
{ .name = "fsync", .errmsg = true, },
|
|
|
|
{ .name = "ftruncate", .errmsg = true, },
|
2013-09-02 16:46:44 +00:00
|
|
|
{ .name = "futex", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_FUTEX_OP, /* op */ }, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "futimesat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "getdents", .errmsg = true, },
|
|
|
|
{ .name = "getdents64", .errmsg = true, },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "getitimer", .errmsg = true, STRARRAY(0, which, itimers), },
|
2016-04-06 17:55:18 +00:00
|
|
|
{ .name = "getpid", .errpid = true, },
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
{ .name = "getpgid", .errpid = true, },
|
2016-04-06 17:55:18 +00:00
|
|
|
{ .name = "getppid", .errpid = true, },
|
perf trace: Pretty print getrandom() args
# trace -e getrandom
35622.560 ( 0.023 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35622.585 ( 0.006 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35622.594 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35627.395 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
35630.940 ( 0.013 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
35718.613 ( 0.015 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35718.629 ( 0.005 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35718.637 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
35719.355 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
35721.042 ( 0.030 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41090.830 ( 0.012 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41090.845 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41090.851 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41091.750 ( 0.010 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
41091.823 ( 0.006 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41122.078 ( 0.053 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41122.129 ( 0.009 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41122.139 ( 0.004 ms): systemd-udevd/631 getrandom(buf: 0x55621e3c18f0, count: 16, flags: NONBLOCK) = 16
41124.492 ( 0.007 ms): libvirtd/1353 getrandom(buf: 0x7f7a1bfa35c0, count: 16, flags: NONBLOCK ) = 16
41124.470 ( 0.013 ms): fwupd/16120 getrandom(buf: 0x7f63243aa5c0, count: 16, flags: NONBLOCK ) = 16
41590.832 ( 0.014 ms): chrome/5957 getrandom(buf: 0x7fabac7b15b0, count: 16, flags: NONBLOCK ) = 16
41590.884 ( 0.004 ms): chrome/5957 getrandom(buf: 0x7fabac7b15c0, count: 16, flags: NONBLOCK ) = 16
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-gca0n1p3aca3depey703ph2q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-30 23:02:15 +00:00
|
|
|
{ .name = "getrandom", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [2] = SCA_GETRANDOM_FLAGS, /* flags */ }, },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "getrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "getxattr", .errmsg = true, },
|
|
|
|
{ .name = "inotify_add_watch", .errmsg = true, },
|
2013-08-26 15:29:38 +00:00
|
|
|
{ .name = "ioctl", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = {
|
2014-02-10 17:09:48 +00:00
|
|
|
#if defined(__i386__) || defined(__x86_64__)
|
|
|
|
/*
|
|
|
|
* FIXME: Make this available to all arches.
|
|
|
|
*/
|
perf trace: Initial beautifier for ioctl's 'cmd' arg
[root@zoo linux]# trace -e ioctl | grep -v "cmd: 0x" | head -10
0.386 ( 0.001 ms): trace/1602 ioctl(fd: 1<pipe:[127057]>, cmd: TCGETS, arg: 0x7fff59fcb4d0 ) = -1 ENOTTY Inappropriate ioctl for device
1459.368 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.586 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
1463.611 ( 0.002 ms): inotify_reader/10352 ioctl(fd: 18<anon_inode:inotify>, cmd: FIONREAD, arg: 0x7fb835228bcc ) = 0
3740.526 ( 0.002 ms): awk/1612 ioctl(fd: 1<pipe:[128265]>, cmd: TCGETS, arg: 0x7fff4d166b90 ) = -1 ENOTTY Inappropriate ioctl for device
3740.704 ( 0.001 ms): awk/1612 ioctl(fd: 3</proc/meminfo>, cmd: TCGETS, arg: 0x7fff4d1669a0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.550 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.555 ( 0.003 ms): ps/1614 ioctl(fd: 2<socket:[19550]>, cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.558 ( 0.002 ms): ps/1614 ioctl(cmd: TIOCGWINSZ, arg: 0x7fff591762b0 ) = -1 ENOTTY Inappropriate ioctl for device
3742.572 ( 0.002 ms): ps/1614 ioctl(fd: 1<pipe:[128266]>, cmd: TCGETS, arg: 0x7fff59176220 ) = -1 ENOTTY Inappropriate ioctl for device
[root@zoo linux]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-afajwap3mr60dfl4qpdl1pxn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-08 20:43:20 +00:00
|
|
|
[1] = SCA_STRHEXARRAY, /* cmd */
|
|
|
|
[2] = SCA_HEX, /* arg */ },
|
|
|
|
.arg_parm = { [1] = &strarray__tioctls, /* cmd */ }, },
|
2014-02-10 17:09:48 +00:00
|
|
|
#else
|
|
|
|
[2] = SCA_HEX, /* arg */ }, },
|
|
|
|
#endif
|
perf trace: Beautify keyctl's option arg
8.697 (0.103 ms): pool/2343 keyctl(option: GET_PERSISTENT, arg2: 1000, arg3: 4294967294, arg4: 140703061514067, arg5: 140703692383680) = 1023192809
8.763 (0.049 ms): pool/2343 keyctl(option: SEARCH, arg2: 1023192809, arg3: 140703745767772, arg4: 140703745767832, arg5: 4294967294) = 140224497
8.789 (0.016 ms): pool/2343 keyctl(option: SEARCH, arg2: 140224497, arg3: 140703745767814, arg4: 140703745767900) = 512300257
8.807 (0.011 ms): pool/2343 keyctl(option: READ, arg2: 512300257 ) = 13
8.822 (0.008 ms): pool/2343 keyctl(option: READ, arg2: 512300257, arg3: 140703061514000, arg4: 13 ) = 13
8.837 (0.007 ms): pool/2343 keyctl(option: READ, arg2: 140224497 ) = 4
8.852 (0.009 ms): pool/2343 keyctl(option: READ, arg2: 140224497, arg3: 140703061514000, arg4: 4 ) = 4
8.869 (0.010 ms): pool/2343 keyctl(option: SEARCH, arg2: 140224497, arg3: 140703745767772, arg4: 140703061514032) = -1 ENOKEY Required key not available
8.892 (0.017 ms): pool/2343 keyctl(option: DESCRIBE, arg2: 512300257 ) = 43
8.910 (0.012 ms): pool/2343 keyctl(option: DESCRIBE, arg2: 512300257, arg3: 140703061544384, arg4: 43) = 43
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-013ab219irsxngyumrf5gp8s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-11 14:05:36 +00:00
|
|
|
{ .name = "keyctl", .errmsg = true, STRARRAY(0, option, keyctl_options), },
|
2013-09-03 20:17:15 +00:00
|
|
|
{ .name = "kill", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "lchown", .errmsg = true, },
|
|
|
|
{ .name = "lgetxattr", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "linkat", .errmsg = true,
|
2014-12-17 20:24:45 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "listxattr", .errmsg = true, },
|
|
|
|
{ .name = "llistxattr", .errmsg = true, },
|
|
|
|
{ .name = "lremovexattr", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "lseek", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [2] = SCA_STRARRAY, /* whence */ },
|
2013-09-24 14:04:32 +00:00
|
|
|
.arg_parm = { [2] = &strarray__whences, /* whence */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "lsetxattr", .errmsg = true, },
|
|
|
|
{ .name = "lstat", .errmsg = true, .alias = "newlstat", },
|
|
|
|
{ .name = "lsxattr", .errmsg = true, },
|
2013-08-23 13:06:41 +00:00
|
|
|
{ .name = "madvise", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* start */
|
|
|
|
[2] = SCA_MADV_BHV, /* behavior */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "mkdir", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "mkdirat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
|
|
|
|
{ .name = "mknod", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "mknodat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* fd */ }, },
|
2013-09-24 03:09:38 +00:00
|
|
|
{ .name = "mlock", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
|
|
|
|
{ .name = "mlockall", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
|
2013-08-26 15:29:38 +00:00
|
|
|
{ .name = "mmap", .hexret = true,
|
2017-05-31 11:35:57 +00:00
|
|
|
/* The standard mmap maps to old_mmap on s390x */
|
|
|
|
#if defined(__s390x__)
|
|
|
|
.alias = "old_mmap",
|
|
|
|
#endif
|
perf trace: Add beautifier for mmap prot parm
[root@zoo ~]# perf trace -e mmap,mprotect sleep 1
0.984 ( 0.015 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd62ae000
1.114 ( 0.016 ms): mmap(addr: 0, len: 125100, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xd628f000
1.252 ( 0.020 ms): mmap(addr: 0x33c1600000, len: 3896312, prot: EXEC|READ, flags: 2050, fd: 3, off: 0) = 0xc1600000
1.282 ( 0.024 ms): mprotect(start: 0x33c17ad000, len: 2097152, prot: NONE ) = 0
1.315 ( 0.026 ms): mmap(addr: 0x33c19ad000, len: 24576, prot: READ|WRITE, flags: 2066, fd: 3, off: 1757184) = 0xc19ad000
1.352 ( 0.017 ms): mmap(addr: 0x33c19b3000, len: 17400, prot: READ|WRITE, flags: 50, fd: 4294967295, off: 0) = 0xc19b3000
1.415 ( 0.011 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628e000
1.440 ( 0.011 ms): mmap(addr: 0, len: 8192, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628c000
1.569 ( 0.019 ms): mprotect(start: 0x606000, len: 4096, prot: READ ) = 0
1.591 ( 0.017 ms): mprotect(start: 0x33c19ad000, len: 16384, prot: READ ) = 0
1.616 ( 0.016 ms): mprotect(start: 0x33c1420000, len: 4096, prot: READ ) = 0
2.105 ( 0.018 ms): mmap(addr: 0, len: 104789808, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xcfe9c000
[root@zoo ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-q1ubhdd9wigxneam616ggdsn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-20 20:44:42 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
|
perf trace: Add beautifier for mmap flags parm
[root@zoo ~]# perf trace -e mmap,mprotect sleep 1
0.992 ( 0.015 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: 4294967295, off: 0) = 0xa60be000
1.108 ( 0.012 ms): mmap(addr: 0, len: 125100, prot: READ, flags: PRIVATE, fd: 3, off: 0 ) = 0xa609f000
1.209 ( 0.014 ms): mmap(addr: 0x33c1600000, len: 3896312, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3, off: 0) = 0xc1600000
1.232 ( 0.018 ms): mprotect(start: 0x33c17ad000, len: 2097152, prot: NONE ) = 0
1.255 ( 0.018 ms): mmap(addr: 0x33c19ad000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1757184) = 0xc19ad000
1.281 ( 0.011 ms): mmap(addr: 0x33c19b3000, len: 17400, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED, fd: 4294967295, off: 0) = 0xc19b3000
1.328 ( 0.008 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: 4294967295, off: 0) = 0xa609e000
1.346 ( 0.008 ms): mmap(addr: 0, len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: 4294967295, off: 0) = 0xa609c000
1.443 ( 0.013 ms): mprotect(start: 0x606000, len: 4096, prot: READ ) = 0
1.459 ( 0.011 ms): mprotect(start: 0x33c19ad000, len: 16384, prot: READ ) = 0
1.477 ( 0.011 ms): mprotect(start: 0x33c1420000, len: 4096, prot: READ ) = 0
1.855 ( 0.013 ms): mmap(addr: 0, len: 104789808, prot: READ, flags: PRIVATE, fd: 3, off: 0) = 0x9fcac000
[root@zoo ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-q1ubhdd9wigxneam616ggdsn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-23 13:48:33 +00:00
|
|
|
[2] = SCA_MMAP_PROT, /* prot */
|
2016-05-23 15:59:53 +00:00
|
|
|
[3] = SCA_MMAP_FLAGS, /* flags */ }, },
|
2013-08-26 15:29:38 +00:00
|
|
|
{ .name = "mprotect", .errmsg = true,
|
perf trace: Add beautifier for mmap prot parm
[root@zoo ~]# perf trace -e mmap,mprotect sleep 1
0.984 ( 0.015 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd62ae000
1.114 ( 0.016 ms): mmap(addr: 0, len: 125100, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xd628f000
1.252 ( 0.020 ms): mmap(addr: 0x33c1600000, len: 3896312, prot: EXEC|READ, flags: 2050, fd: 3, off: 0) = 0xc1600000
1.282 ( 0.024 ms): mprotect(start: 0x33c17ad000, len: 2097152, prot: NONE ) = 0
1.315 ( 0.026 ms): mmap(addr: 0x33c19ad000, len: 24576, prot: READ|WRITE, flags: 2066, fd: 3, off: 1757184) = 0xc19ad000
1.352 ( 0.017 ms): mmap(addr: 0x33c19b3000, len: 17400, prot: READ|WRITE, flags: 50, fd: 4294967295, off: 0) = 0xc19b3000
1.415 ( 0.011 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628e000
1.440 ( 0.011 ms): mmap(addr: 0, len: 8192, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628c000
1.569 ( 0.019 ms): mprotect(start: 0x606000, len: 4096, prot: READ ) = 0
1.591 ( 0.017 ms): mprotect(start: 0x33c19ad000, len: 16384, prot: READ ) = 0
1.616 ( 0.016 ms): mprotect(start: 0x33c1420000, len: 4096, prot: READ ) = 0
2.105 ( 0.018 ms): mmap(addr: 0, len: 104789808, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xcfe9c000
[root@zoo ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-q1ubhdd9wigxneam616ggdsn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-20 20:44:42 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* start */
|
|
|
|
[2] = SCA_MMAP_PROT, /* prot */ }, },
|
2015-08-10 22:20:52 +00:00
|
|
|
{ .name = "mq_unlink", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_FILENAME, /* u_name */ }, },
|
perf trace: Add beautifier for mmap prot parm
[root@zoo ~]# perf trace -e mmap,mprotect sleep 1
0.984 ( 0.015 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd62ae000
1.114 ( 0.016 ms): mmap(addr: 0, len: 125100, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xd628f000
1.252 ( 0.020 ms): mmap(addr: 0x33c1600000, len: 3896312, prot: EXEC|READ, flags: 2050, fd: 3, off: 0) = 0xc1600000
1.282 ( 0.024 ms): mprotect(start: 0x33c17ad000, len: 2097152, prot: NONE ) = 0
1.315 ( 0.026 ms): mmap(addr: 0x33c19ad000, len: 24576, prot: READ|WRITE, flags: 2066, fd: 3, off: 1757184) = 0xc19ad000
1.352 ( 0.017 ms): mmap(addr: 0x33c19b3000, len: 17400, prot: READ|WRITE, flags: 50, fd: 4294967295, off: 0) = 0xc19b3000
1.415 ( 0.011 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628e000
1.440 ( 0.011 ms): mmap(addr: 0, len: 8192, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628c000
1.569 ( 0.019 ms): mprotect(start: 0x606000, len: 4096, prot: READ ) = 0
1.591 ( 0.017 ms): mprotect(start: 0x33c19ad000, len: 16384, prot: READ ) = 0
1.616 ( 0.016 ms): mprotect(start: 0x33c1420000, len: 4096, prot: READ ) = 0
2.105 ( 0.018 ms): mmap(addr: 0, len: 104789808, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xcfe9c000
[root@zoo ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-q1ubhdd9wigxneam616ggdsn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-20 20:44:42 +00:00
|
|
|
{ .name = "mremap", .hexret = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* addr */
|
perf trace: Add beautifier for mremap flags param
~/devel/kernel/tools/perf(branch:master*) » sudo ./perf trace ~/mremap_test
0.543 ( 0.003 ms): mprotect(start: 0x600000, len: 4096, prot: READ ) = 0
0.550 ( 0.003 ms): mprotect(start: 0x7f441260d000, len: 4096, prot: READ) = 0
0.561 ( 0.010 ms): munmap(addr: 0x7f44125e2000, len: 165572 ) = 0
0.595 ( 0.012 ms): mmap(len: 12288, prot: READ|WRITE, flags: SHARED|ANONYMOUS|LOCKED, fd: -1) = 0x12608000
0.603 ( 0.006 ms): mremap(addr: 0x7f4412608000, old_len: 4096, new_len: 4096, flags: MAYMOVE|FIXED, new_addr: 0x7f16da295000) = 0xda295000
0.608 ( 0.003 ms): mremap(addr: 0x7f441260a000, old_len: 4096, new_len: 4096, flags: MAYMOVE|FIXED, new_addr: 0x7f16da297000) = 0xda297000
0.612 ( 0.003 ms): mremap(addr: 0x7f4412609000, old_len: 4096, new_len: 4096, flags: MAYMOVE|FIXED, new_addr: 0x7f16da296000) = 0xda296000
0.619 ( 0.000 ms): exit_group(
Signed-off-by: Alex Snast <asnast@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1407944560-26924-1-git-send-email-asnast@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-08-13 15:42:40 +00:00
|
|
|
[3] = SCA_MREMAP_FLAGS, /* flags */
|
perf trace: Add beautifier for mmap prot parm
[root@zoo ~]# perf trace -e mmap,mprotect sleep 1
0.984 ( 0.015 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd62ae000
1.114 ( 0.016 ms): mmap(addr: 0, len: 125100, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xd628f000
1.252 ( 0.020 ms): mmap(addr: 0x33c1600000, len: 3896312, prot: EXEC|READ, flags: 2050, fd: 3, off: 0) = 0xc1600000
1.282 ( 0.024 ms): mprotect(start: 0x33c17ad000, len: 2097152, prot: NONE ) = 0
1.315 ( 0.026 ms): mmap(addr: 0x33c19ad000, len: 24576, prot: READ|WRITE, flags: 2066, fd: 3, off: 1757184) = 0xc19ad000
1.352 ( 0.017 ms): mmap(addr: 0x33c19b3000, len: 17400, prot: READ|WRITE, flags: 50, fd: 4294967295, off: 0) = 0xc19b3000
1.415 ( 0.011 ms): mmap(addr: 0, len: 4096, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628e000
1.440 ( 0.011 ms): mmap(addr: 0, len: 8192, prot: READ|WRITE, flags: 34, fd: 4294967295, off: 0) = 0xd628c000
1.569 ( 0.019 ms): mprotect(start: 0x606000, len: 4096, prot: READ ) = 0
1.591 ( 0.017 ms): mprotect(start: 0x33c19ad000, len: 16384, prot: READ ) = 0
1.616 ( 0.016 ms): mprotect(start: 0x33c1420000, len: 4096, prot: READ ) = 0
2.105 ( 0.018 ms): mmap(addr: 0, len: 104789808, prot: READ, flags: 2, fd: 3, off: 0 ) = 0xcfe9c000
[root@zoo ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-q1ubhdd9wigxneam616ggdsn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-20 20:44:42 +00:00
|
|
|
[4] = SCA_HEX, /* new_addr */ }, },
|
2013-09-24 03:09:38 +00:00
|
|
|
{ .name = "munlock", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
|
2013-08-26 15:29:38 +00:00
|
|
|
{ .name = "munmap", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_HEX, /* addr */ }, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "name_to_handle_at", .errmsg = true,
|
2014-12-17 20:24:45 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "newfstatat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
|
2013-09-02 19:22:31 +00:00
|
|
|
{ .name = "open", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [1] = SCA_OPEN_FLAGS, /* flags */ }, },
|
2013-09-02 19:40:40 +00:00
|
|
|
{ .name = "open_by_handle_at", .errmsg = true,
|
2013-09-24 14:04:32 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
|
|
|
|
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
|
2013-09-02 19:40:40 +00:00
|
|
|
{ .name = "openat", .errmsg = true,
|
2013-09-24 14:04:32 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */
|
|
|
|
[2] = SCA_OPEN_FLAGS, /* flags */ }, },
|
trace: Beautify perf_event_open syscall
Syswide tracing and then running 'stat' and 'trace':
$ perf trace -e perf_event_open
1034.649 (0.019 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = -1 EINVAL Invalid argument
1034.670 (0.008 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.681 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.692 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
9986.983 (0.014 ms): trace/6139 perf_event_open(attr_uptr: 0x7ffd9c629320, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.026 (0.016 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.041 (0.008 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.489 (0.092 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.536 (0.044 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 4
9987.580 (0.041 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 5
9987.620 (0.037 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 7
9987.659 (0.035 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 8
9987.692 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 9
9987.727 (0.032 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 10
9987.761 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 11
Need to intercept perf_copy_attr() with a kprobe or with eBPF...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-njb105hab2i3t5dexym9lskl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-12 01:47:54 +00:00
|
|
|
{ .name = "perf_event_open", .errmsg = true,
|
2016-04-26 14:40:17 +00:00
|
|
|
.arg_scnprintf = { [2] = SCA_INT, /* cpu */
|
trace: Beautify perf_event_open syscall
Syswide tracing and then running 'stat' and 'trace':
$ perf trace -e perf_event_open
1034.649 (0.019 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1, flags: FD_CLOEXEC) = -1 EINVAL Invalid argument
1034.670 (0.008 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.681 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
1034.692 (0.007 ms): perf/6133 perf_event_open(attr_uptr: 0x36f0360, pid: 16134, cpu: -1, group_fd: -1) = -1 EINVAL Invalid argument
9986.983 (0.014 ms): trace/6139 perf_event_open(attr_uptr: 0x7ffd9c629320, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.026 (0.016 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.041 (0.008 ms): trace/6139 perf_event_open(attr_uptr: 0x37c7e70, pid: -1, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.489 (0.092 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 3
9987.536 (0.044 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 4
9987.580 (0.041 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 5
9987.620 (0.037 ms): trace/6139 perf_event_open(attr_uptr: 0x3795ee0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 7
9987.659 (0.035 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, group_fd: -1, flags: FD_CLOEXEC) = 8
9987.692 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 1, group_fd: -1, flags: FD_CLOEXEC) = 9
9987.727 (0.032 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 2, group_fd: -1, flags: FD_CLOEXEC) = 10
9987.761 (0.031 ms): trace/6139 perf_event_open(attr_uptr: 0x37975d0, pid: 16140, cpu: 3, group_fd: -1, flags: FD_CLOEXEC) = 11
Need to intercept perf_copy_attr() with a kprobe or with eBPF...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-njb105hab2i3t5dexym9lskl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-12 01:47:54 +00:00
|
|
|
[3] = SCA_FD, /* group_fd */
|
|
|
|
[4] = SCA_PERF_FLAGS, /* flags */ }, },
|
2013-09-23 15:52:04 +00:00
|
|
|
{ .name = "pipe2", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_PIPE_FLAGS, /* flags */ }, },
|
2012-09-27 16:16:00 +00:00
|
|
|
{ .name = "poll", .errmsg = true, .timeout = true, },
|
|
|
|
{ .name = "ppoll", .errmsg = true, .timeout = true, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "pread", .errmsg = true, .alias = "pread64", },
|
|
|
|
{ .name = "preadv", .errmsg = true, .alias = "pread", },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "prlimit64", .errmsg = true, STRARRAY(1, resource, rlimit_resources), },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "pwrite", .errmsg = true, .alias = "pwrite64", },
|
|
|
|
{ .name = "pwritev", .errmsg = true, },
|
|
|
|
{ .name = "read", .errmsg = true, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "readlink", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "readlinkat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "readv", .errmsg = true, },
|
perf trace: Beautify send/recv syscall 'flags' arg
[root@sandy ~]# perf trace -a -e recvmmsg,recvmsg,recvfrom,sendto,sendmsg,sendmmsg
6.901 (0.002 ms): 589 recvmsg(fd: 51, msg: 0x7fff35673420, flags: CMSG_CLOEXEC) = -1 EAGAIN Resource temporarily unavailable
6.966 (0.008 ms): 589 sendmsg(fd: 50, msg: 0x7fff35673230, flags: NOSIGNAL ) = 961
6.984 (0.004 ms): 979 sendmsg(fd: 3, msg: 0x7fff5b484940, flags: NOSIGNAL ) = 945
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h25k5k50nac0ej5cl5iwgvae@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 14:54:48 +00:00
|
|
|
{ .name = "recvfrom", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
|
perf trace: Beautify send/recv syscall 'flags' arg
[root@sandy ~]# perf trace -a -e recvmmsg,recvmsg,recvfrom,sendto,sendmsg,sendmmsg
6.901 (0.002 ms): 589 recvmsg(fd: 51, msg: 0x7fff35673420, flags: CMSG_CLOEXEC) = -1 EAGAIN Resource temporarily unavailable
6.966 (0.008 ms): 589 sendmsg(fd: 50, msg: 0x7fff35673230, flags: NOSIGNAL ) = 961
6.984 (0.004 ms): 979 sendmsg(fd: 3, msg: 0x7fff5b484940, flags: NOSIGNAL ) = 945
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h25k5k50nac0ej5cl5iwgvae@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 14:54:48 +00:00
|
|
|
{ .name = "recvmmsg", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
|
perf trace: Beautify send/recv syscall 'flags' arg
[root@sandy ~]# perf trace -a -e recvmmsg,recvmsg,recvfrom,sendto,sendmsg,sendmmsg
6.901 (0.002 ms): 589 recvmsg(fd: 51, msg: 0x7fff35673420, flags: CMSG_CLOEXEC) = -1 EAGAIN Resource temporarily unavailable
6.966 (0.008 ms): 589 sendmsg(fd: 50, msg: 0x7fff35673230, flags: NOSIGNAL ) = 961
6.984 (0.004 ms): 979 sendmsg(fd: 3, msg: 0x7fff5b484940, flags: NOSIGNAL ) = 945
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h25k5k50nac0ej5cl5iwgvae@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 14:54:48 +00:00
|
|
|
{ .name = "recvmsg", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "removexattr", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "renameat", .errmsg = true,
|
2014-12-17 20:24:45 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "rmdir", .errmsg = true, },
|
2013-09-03 20:17:15 +00:00
|
|
|
{ .name = "rt_sigaction", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_SIGNUM, /* sig */ }, },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "rt_sigprocmask", .errmsg = true, STRARRAY(0, how, sighow), },
|
2013-09-03 20:17:15 +00:00
|
|
|
{ .name = "rt_sigqueueinfo", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
|
|
|
|
{ .name = "rt_tgsigqueueinfo", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
|
perf trace: Beautify sched_[gs]et_attr return value
Both return errno, show the string associated then.
More work needed to capture the sched_attr arg to beautify it in turn,
probably using BPF.
Before:
0.210 ( 0.001 ms): sched_setattr(uattr: 0x7ffc684f02b0) = -22
After the patch, for this sched_attr, all other parms are zero, so not
shown:
struct sched_attr attr = {
.size = sizeof(attr),
.sched_policy = SCHED_DEADLINE,
.sched_runtime = 10 * USECS_PER_SEC,
.sched_period = 30 * USECS_PER_SEC,
.sched_deadline = attr.sched_period,
};
0.321 ( 0.002 ms): sched_setattr(uattr: 0x7ffc44116da0) = -1 EINVAL Invalid argument
[root@jouet c]# perf trace -e sched_setattr ./sched_deadline
Couldn't negotiate deadline: Invalid argument
0.229 ( 0.003 ms): sched_setattr(uattr: 0x7ffd8dcd8df0) = -1 EINVAL Invalid argument
[root@jouet c]#
Now to figure out the reason for this EINVAL.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Clark Williams <williams@redhat.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-tyot2n7e48zm8pdw8tbcm3sl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-09-28 16:45:38 +00:00
|
|
|
{ .name = "sched_getattr", .errmsg = true, },
|
|
|
|
{ .name = "sched_setattr", .errmsg = true, },
|
2016-04-06 15:51:33 +00:00
|
|
|
{ .name = "sched_setscheduler", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_SCHED_POLICY, /* policy */ }, },
|
2016-03-30 22:43:32 +00:00
|
|
|
{ .name = "seccomp", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_SECCOMP_OP, /* op */
|
|
|
|
[1] = SCA_SECCOMP_FLAGS, /* flags */ }, },
|
2012-09-27 16:16:00 +00:00
|
|
|
{ .name = "select", .errmsg = true, .timeout = true, },
|
perf trace: Beautify send/recv syscall 'flags' arg
[root@sandy ~]# perf trace -a -e recvmmsg,recvmsg,recvfrom,sendto,sendmsg,sendmmsg
6.901 (0.002 ms): 589 recvmsg(fd: 51, msg: 0x7fff35673420, flags: CMSG_CLOEXEC) = -1 EAGAIN Resource temporarily unavailable
6.966 (0.008 ms): 589 sendmsg(fd: 50, msg: 0x7fff35673230, flags: NOSIGNAL ) = 961
6.984 (0.004 ms): 979 sendmsg(fd: 3, msg: 0x7fff5b484940, flags: NOSIGNAL ) = 945
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h25k5k50nac0ej5cl5iwgvae@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 14:54:48 +00:00
|
|
|
{ .name = "sendmmsg", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
|
perf trace: Beautify send/recv syscall 'flags' arg
[root@sandy ~]# perf trace -a -e recvmmsg,recvmsg,recvfrom,sendto,sendmsg,sendmmsg
6.901 (0.002 ms): 589 recvmsg(fd: 51, msg: 0x7fff35673420, flags: CMSG_CLOEXEC) = -1 EAGAIN Resource temporarily unavailable
6.966 (0.008 ms): 589 sendmsg(fd: 50, msg: 0x7fff35673230, flags: NOSIGNAL ) = 961
6.984 (0.004 ms): 979 sendmsg(fd: 3, msg: 0x7fff5b484940, flags: NOSIGNAL ) = 945
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h25k5k50nac0ej5cl5iwgvae@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 14:54:48 +00:00
|
|
|
{ .name = "sendmsg", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [2] = SCA_MSG_FLAGS, /* flags */ }, },
|
perf trace: Beautify send/recv syscall 'flags' arg
[root@sandy ~]# perf trace -a -e recvmmsg,recvmsg,recvfrom,sendto,sendmsg,sendmmsg
6.901 (0.002 ms): 589 recvmsg(fd: 51, msg: 0x7fff35673420, flags: CMSG_CLOEXEC) = -1 EAGAIN Resource temporarily unavailable
6.966 (0.008 ms): 589 sendmsg(fd: 50, msg: 0x7fff35673230, flags: NOSIGNAL ) = 961
6.984 (0.004 ms): 979 sendmsg(fd: 3, msg: 0x7fff5b484940, flags: NOSIGNAL ) = 945
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-h25k5k50nac0ej5cl5iwgvae@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 14:54:48 +00:00
|
|
|
{ .name = "sendto", .errmsg = true,
|
2016-05-23 15:59:53 +00:00
|
|
|
.arg_scnprintf = { [3] = SCA_MSG_FLAGS, /* flags */ }, },
|
2016-04-06 17:55:18 +00:00
|
|
|
{ .name = "set_tid_address", .errpid = true, },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "setitimer", .errmsg = true, STRARRAY(0, which, itimers), },
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
{ .name = "setpgid", .errmsg = true, },
|
2013-09-20 15:13:37 +00:00
|
|
|
{ .name = "setrlimit", .errmsg = true, STRARRAY(0, resource, rlimit_resources), },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "setxattr", .errmsg = true, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "shutdown", .errmsg = true, },
|
2013-09-04 13:27:41 +00:00
|
|
|
{ .name = "socket", .errmsg = true,
|
2013-09-04 14:00:44 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
|
|
|
|
[1] = SCA_SK_TYPE, /* type */ },
|
2013-09-20 15:24:20 +00:00
|
|
|
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
|
|
|
|
{ .name = "socketpair", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_STRARRAY, /* family */
|
|
|
|
[1] = SCA_SK_TYPE, /* type */ },
|
2013-09-04 13:27:41 +00:00
|
|
|
.arg_parm = { [0] = &strarray__socket_families, /* family */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "stat", .errmsg = true, .alias = "newstat", },
|
|
|
|
{ .name = "statfs", .errmsg = true, },
|
perf trace: Beautify statx syscall 'flag' and 'mask' arguments
To test it, build samples/statx/test_statx, which I did as:
$ make headers_install
$ cc -I ~/git/linux/usr/include samples/statx/test-statx.c -o /tmp/statx
And then use perf trace on it:
# perf trace -e statx /tmp/statx /etc/passwd
statx(/etc/passwd) = 0
results=7ff
Size: 3496 Blocks: 8 IO Block: 4096 regular file
Device: fd:00 Inode: 280156 Links: 1
Access: (0644/-rw-r--r--) Uid: 0 Gid: 0
Access: 2017-03-29 16:01:01.650073438-0300
Modify: 2017-03-10 16:25:14.156479354-0300
Change: 2017-03-10 16:25:14.171479328-0300
0.000 ( 0.007 ms): statx/30648 statx(dfd: CWD, filename: 0x7ef503f4, flags: SYMLINK_NOFOLLOW, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7fff7ef4eb10) = 0
#
Using the test-stat.c options to change the mask:
# perf trace -e statx /tmp/statx -O /etc/passwd > /dev/null
0.000 ( 0.008 ms): statx/30745 statx(dfd: CWD, filename: 0x3a0753f4, flags: SYMLINK_NOFOLLOW, mask: BTIME, buffer: 0x7ffd3a0735c0) = 0
#
# perf trace -e statx /tmp/statx -A /etc/passwd > /dev/null
0.000 ( 0.010 ms): statx/30757 statx(dfd: CWD, filename: 0xa94e63f4, flags: SYMLINK_NOFOLLOW|NO_AUTOMOUNT, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffea94e49d0) = 0
#
# trace --no-inherit -e statx /tmp/statx -F /etc/passwd > /dev/null
0.000 ( 0.011 ms): statx(dfd: CWD, filename: 0x3b02d3f3, flags: SYMLINK_NOFOLLOW|STATX_FORCE_SYNC, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffd3b02c850) = 0
#
# trace --no-inherit -e statx /tmp/statx -F -L /etc/passwd > /dev/null
0.000 ( 0.008 ms): statx(dfd: CWD, filename: 0x15cff3f3, flags: STATX_FORCE_SYNC, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7fff15cfdda0) = 0
#
# trace --no-inherit -e statx /tmp/statx -D -O /etc/passwd > /dev/null
0.000 ( 0.009 ms): statx(dfd: CWD, filename: 0xfa37f3f3, flags: SYMLINK_NOFOLLOW|STATX_DONT_SYNC, mask: BTIME, buffer: 0x7ffffa37da20) = 0
#
Adding a probe to get the filename collected as well:
# perf probe 'vfs_getname=getname_flags:72 pathname=result->name:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=result->name:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
# trace --no-inherit -e statx /tmp/statx -D -O /etc/passwd > /dev/null
0.169 ( 0.007 ms): statx(dfd: CWD, filename: /etc/passwd, flags: SYMLINK_NOFOLLOW|STATX_DONT_SYNC, mask: BTIME, buffer: 0x7ffda9bf50f0) = 0
#
Same technique could be used to collect and beautify the result put in
the 'buffer' argument.
Finally do a system wide 'perf trace' session looking for any use of statx,
then run the test proggie with various flags:
# trace -e statx
16612.967 ( 0.028 ms): statx/4562 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffef195d660) = 0
33064.447 ( 0.011 ms): statx/4569 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW|STATX_FORCE_SYNC, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7ffc5484c790) = 0
36050.891 ( 0.023 ms): statx/4576 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW, mask: BTIME, buffer: 0x7ffeb18b66e0) = 0
38039.889 ( 0.023 ms): statx/4584 statx(dfd: CWD, filename: /tmp/statx, flags: SYMLINK_NOFOLLOW, mask: TYPE|MODE|NLINK|UID|GID|ATIME|MTIME|CTIME|INO|SIZE|BLOCKS|BTIME, buffer: 0x7fff1db0ea90) = 0
^C#
This one also starts moving the beautifiers from files directly included
in builtin-trace.c to separate objects + a beauty.h header with
prototypes, so that we can add test cases in tools/perf/tests/ to fire
syscalls with various arguments and then get them intercepted as
syscalls:sys_enter_foo or raw_syscalls:sys_enter + sys_exit to then
format and check that the formatted output is the one we expect.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David Ahern <dsahern@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-xvzw8eynffvez5czyzidhrno@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-14 19:19:30 +00:00
|
|
|
{ .name = "statx", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* flags */
|
|
|
|
[2] = SCA_STATX_FLAGS, /* flags */
|
|
|
|
[3] = SCA_STATX_MASK, /* mask */ }, },
|
perf trace: Use vfs_getname syscall arg beautifier in more syscalls
Those were covered and tested in this cset:
access, chdir, chmod, chown, chroot, creat, getxattr,
inotify_add_watch, lchown, lgetxattr, listxattr,
lsetxattr, mkdir, mkdirat, mknod, rmdir, faccessat,
newfstatat, openat, readlink, readlinkat, removexattr,
setxattr, statfs, swapon, swapoff, truncate, unlinkat,
utime, utimes, utimensat.
E.g.:
# trace -e statfs,access,mkdir mkdir /tmp/bla
0.285 (0.020 ms): mkdir/2799 access(filename: /etc/ld.so.preload, mode: R ) = -1 ENOENT No such file or directory
1.070 (0.032 ms): mkdir/2799 statfs(pathname: /sys/fs/selinux, buf: 0x7ffeafbdc930) = 0
1.087 (0.013 ms): mkdir/2799 statfs(pathname: /sys/fs/selinux, buf: 0x7ffeafbdc820) = 0
1.189 (0.014 ms): mkdir/2799 access(filename: /etc/selinux/config ) = 0
1.905 (0.610 ms): mkdir/2799 mkdir(pathname: /tmp/bla, mode: 511 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-wbqtnlktquun3wtpjdz3okul@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
and an empty message aborts the commit.
2015-08-05 02:31:25 +00:00
|
|
|
{ .name = "swapoff", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
|
|
|
|
{ .name = "swapon", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [0] = SCA_FILENAME, /* specialfile */ }, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "symlinkat", .errmsg = true,
|
2014-12-17 20:24:45 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
|
2013-09-03 20:17:15 +00:00
|
|
|
{ .name = "tgkill", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [2] = SCA_SIGNUM, /* sig */ }, },
|
|
|
|
{ .name = "tkill", .errmsg = true,
|
|
|
|
.arg_scnprintf = { [1] = SCA_SIGNUM, /* sig */ }, },
|
2016-05-23 19:37:55 +00:00
|
|
|
{ .name = "truncate", .errmsg = true, },
|
2013-08-26 15:21:41 +00:00
|
|
|
{ .name = "uname", .errmsg = true, .alias = "newuname", },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "unlinkat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dfd */ }, },
|
|
|
|
{ .name = "utime", .errmsg = true, },
|
2013-09-24 14:04:32 +00:00
|
|
|
{ .name = "utimensat", .errmsg = true,
|
2016-05-23 19:37:55 +00:00
|
|
|
.arg_scnprintf = { [0] = SCA_FDAT, /* dirfd */ }, },
|
|
|
|
{ .name = "utimes", .errmsg = true, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "vmsplice", .errmsg = true, },
|
perf trace: Infrastructure to show COMM strings for syscalls returning PIDs
Starting with clone, waitid and wait4:
# trace -e waitid,wait4
1.385 ( 1.385 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) = 1210 (ls)
1.426 ( 0.002 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1150, options: NOHANG|UNTRACED|CONTINUED) = 0
3.293 ( 0.604 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee0560 ) = 1214 (sed)
3.342 ( 0.002 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee01d0, options: NOHANG ) = -1 ECHILD No child processes
3.576 ( 0.016 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee0550, options: NOHANG|UNTRACED|CONTINUED) = 1211 (bash)
^C# trace -e clone
0.027 ( 0.000 ms): systemd/1 ... [continued]: clone()) = 1227 (systemd)
0.050 ( 0.000 ms): systemd/1227 ... [continued]: clone()) = 0
^C[root@jouet ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lyf5d3y5j15wikjb6pe6ukoi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 17:33:07 +00:00
|
|
|
{ .name = "wait4", .errpid = true,
|
2016-04-06 17:11:36 +00:00
|
|
|
.arg_scnprintf = { [2] = SCA_WAITID_OPTIONS, /* options */ }, },
|
perf trace: Infrastructure to show COMM strings for syscalls returning PIDs
Starting with clone, waitid and wait4:
# trace -e waitid,wait4
1.385 ( 1.385 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) = 1210 (ls)
1.426 ( 0.002 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1150, options: NOHANG|UNTRACED|CONTINUED) = 0
3.293 ( 0.604 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee0560 ) = 1214 (sed)
3.342 ( 0.002 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee01d0, options: NOHANG ) = -1 ECHILD No child processes
3.576 ( 0.016 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee0550, options: NOHANG|UNTRACED|CONTINUED) = 1211 (bash)
^C# trace -e clone
0.027 ( 0.000 ms): systemd/1 ... [continued]: clone()) = 1227 (systemd)
0.050 ( 0.000 ms): systemd/1227 ... [continued]: clone()) = 0
^C[root@jouet ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lyf5d3y5j15wikjb6pe6ukoi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 17:33:07 +00:00
|
|
|
{ .name = "waitid", .errpid = true,
|
2016-04-06 17:11:36 +00:00
|
|
|
.arg_scnprintf = { [3] = SCA_WAITID_OPTIONS, /* options */ }, },
|
2016-05-23 15:59:53 +00:00
|
|
|
{ .name = "write", .errmsg = true, },
|
|
|
|
{ .name = "writev", .errmsg = true, },
|
2012-09-26 23:05:56 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
static int syscall_fmt__cmp(const void *name, const void *fmtp)
|
|
|
|
{
|
|
|
|
const struct syscall_fmt *fmt = fmtp;
|
|
|
|
return strcmp(name, fmt->name);
|
|
|
|
}
|
|
|
|
|
|
|
|
static struct syscall_fmt *syscall_fmt__find(const char *name)
|
|
|
|
{
|
|
|
|
const int nmemb = ARRAY_SIZE(syscall_fmts);
|
|
|
|
return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
|
|
|
|
}
|
|
|
|
|
|
|
|
struct syscall {
|
|
|
|
struct event_format *tp_format;
|
2015-03-20 20:46:53 +00:00
|
|
|
int nr_args;
|
|
|
|
struct format_field *args;
|
2012-09-26 23:05:56 +00:00
|
|
|
const char *name;
|
2014-06-17 17:29:24 +00:00
|
|
|
bool is_exit;
|
2012-09-26 23:05:56 +00:00
|
|
|
struct syscall_fmt *fmt;
|
2013-09-03 15:20:12 +00:00
|
|
|
size_t (**arg_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
|
2013-09-03 18:50:28 +00:00
|
|
|
void **arg_parm;
|
2012-09-26 23:05:56 +00:00
|
|
|
};
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
/*
|
|
|
|
* We need to have this 'calculated' boolean because in some cases we really
|
|
|
|
* don't know what is the duration of a syscall, for instance, when we start
|
|
|
|
* a session and some threads are waiting for a syscall to finish, say 'poll',
|
|
|
|
* in which case all we can do is to print "( ? ) for duration and for the
|
|
|
|
* start timestamp.
|
|
|
|
*/
|
|
|
|
static size_t fprintf_duration(unsigned long t, bool calculated, FILE *fp)
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
{
|
|
|
|
double duration = (double)t / NSEC_PER_MSEC;
|
|
|
|
size_t printed = fprintf(fp, "(");
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
if (!calculated)
|
|
|
|
printed += fprintf(fp, " ? ");
|
|
|
|
else if (duration >= 1.0)
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
printed += color_fprintf(fp, PERF_COLOR_RED, "%6.3f ms", duration);
|
|
|
|
else if (duration >= 0.01)
|
|
|
|
printed += color_fprintf(fp, PERF_COLOR_YELLOW, "%6.3f ms", duration);
|
|
|
|
else
|
|
|
|
printed += color_fprintf(fp, PERF_COLOR_NORMAL, "%6.3f ms", duration);
|
2013-08-19 15:01:10 +00:00
|
|
|
return printed + fprintf(fp, "): ");
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
/**
|
|
|
|
* filename.ptr: The filename char pointer that will be vfs_getname'd
|
|
|
|
* filename.entry_str_pos: Where to insert the string translated from
|
|
|
|
* filename.ptr by the vfs_getname tracepoint/kprobe.
|
|
|
|
*/
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
struct thread_trace {
|
|
|
|
u64 entry_time;
|
|
|
|
bool entry_pending;
|
2012-10-17 20:09:46 +00:00
|
|
|
unsigned long nr_events;
|
2014-07-08 18:05:16 +00:00
|
|
|
unsigned long pfmaj, pfmin;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
char *entry_str;
|
2012-10-17 20:13:12 +00:00
|
|
|
double runtime_ms;
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
struct {
|
|
|
|
unsigned long ptr;
|
2015-08-14 16:16:27 +00:00
|
|
|
short int entry_str_pos;
|
|
|
|
bool pending_open;
|
|
|
|
unsigned int namelen;
|
|
|
|
char *name;
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
} filename;
|
2013-09-24 14:04:32 +00:00
|
|
|
struct {
|
|
|
|
int max;
|
|
|
|
char **table;
|
|
|
|
} paths;
|
2013-10-09 03:26:53 +00:00
|
|
|
|
|
|
|
struct intlist *syscall_stats;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
};
|
|
|
|
|
|
|
|
static struct thread_trace *thread_trace__new(void)
|
|
|
|
{
|
2013-09-24 14:04:32 +00:00
|
|
|
struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace));
|
|
|
|
|
|
|
|
if (ttrace)
|
|
|
|
ttrace->paths.max = -1;
|
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
ttrace->syscall_stats = intlist__new(NULL);
|
|
|
|
|
2013-09-24 14:04:32 +00:00
|
|
|
return ttrace;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
}
|
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
static struct thread_trace *thread__trace(struct thread *thread, FILE *fp)
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
{
|
2012-10-17 20:09:46 +00:00
|
|
|
struct thread_trace *ttrace;
|
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
if (thread == NULL)
|
|
|
|
goto fail;
|
|
|
|
|
2014-10-06 00:46:03 +00:00
|
|
|
if (thread__priv(thread) == NULL)
|
|
|
|
thread__set_priv(thread, thread_trace__new());
|
2014-12-17 20:24:45 +00:00
|
|
|
|
2014-10-06 00:46:03 +00:00
|
|
|
if (thread__priv(thread) == NULL)
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
goto fail;
|
|
|
|
|
2014-10-06 00:46:03 +00:00
|
|
|
ttrace = thread__priv(thread);
|
2012-10-17 20:09:46 +00:00
|
|
|
++ttrace->nr_events;
|
|
|
|
|
|
|
|
return ttrace;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
fail:
|
2013-08-19 15:01:10 +00:00
|
|
|
color_fprintf(fp, PERF_COLOR_RED,
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
"WARNING: not enough memory, dropping samples!\n");
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2014-06-26 16:14:25 +00:00
|
|
|
#define TRACE_PFMAJ (1 << 0)
|
|
|
|
#define TRACE_PFMIN (1 << 1)
|
|
|
|
|
2015-08-05 01:17:29 +00:00
|
|
|
static const size_t trace__entry_str_size = 2048;
|
|
|
|
|
2013-09-27 20:34:10 +00:00
|
|
|
static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
|
2013-09-24 14:04:32 +00:00
|
|
|
{
|
2014-10-06 00:46:03 +00:00
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
2013-09-24 14:04:32 +00:00
|
|
|
|
|
|
|
if (fd > ttrace->paths.max) {
|
|
|
|
char **npath = realloc(ttrace->paths.table, (fd + 1) * sizeof(char *));
|
|
|
|
|
|
|
|
if (npath == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (ttrace->paths.max != -1) {
|
|
|
|
memset(npath + ttrace->paths.max + 1, 0,
|
|
|
|
(fd - ttrace->paths.max) * sizeof(char *));
|
|
|
|
} else {
|
|
|
|
memset(npath, 0, (fd + 1) * sizeof(char *));
|
|
|
|
}
|
|
|
|
|
|
|
|
ttrace->paths.table = npath;
|
|
|
|
ttrace->paths.max = fd;
|
|
|
|
}
|
|
|
|
|
|
|
|
ttrace->paths.table[fd] = strdup(pathname);
|
|
|
|
|
|
|
|
return ttrace->paths.table[fd] != NULL ? 0 : -1;
|
|
|
|
}
|
|
|
|
|
2013-09-27 20:34:10 +00:00
|
|
|
static int thread__read_fd_path(struct thread *thread, int fd)
|
|
|
|
{
|
|
|
|
char linkname[PATH_MAX], pathname[PATH_MAX];
|
|
|
|
struct stat st;
|
|
|
|
int ret;
|
|
|
|
|
|
|
|
if (thread->pid_ == thread->tid) {
|
|
|
|
scnprintf(linkname, sizeof(linkname),
|
|
|
|
"/proc/%d/fd/%d", thread->pid_, fd);
|
|
|
|
} else {
|
|
|
|
scnprintf(linkname, sizeof(linkname),
|
|
|
|
"/proc/%d/task/%d/fd/%d", thread->pid_, thread->tid, fd);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (lstat(linkname, &st) < 0 || st.st_size + 1 > (off_t)sizeof(pathname))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
ret = readlink(linkname, pathname, sizeof(pathname));
|
|
|
|
|
|
|
|
if (ret < 0 || ret > st.st_size)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
pathname[ret] = '\0';
|
|
|
|
return trace__set_fd_pathname(thread, fd, pathname);
|
|
|
|
}
|
|
|
|
|
2013-09-27 21:06:19 +00:00
|
|
|
static const char *thread__fd_path(struct thread *thread, int fd,
|
|
|
|
struct trace *trace)
|
2013-09-24 14:04:32 +00:00
|
|
|
{
|
2014-10-06 00:46:03 +00:00
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
2013-09-24 14:04:32 +00:00
|
|
|
|
|
|
|
if (ttrace == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (fd < 0)
|
|
|
|
return NULL;
|
|
|
|
|
perf trace: Fix up fd -> pathname resolution
There was a brown paper bag bug in the patch that introduced a reference
implementation on using 'perf probe' made wannabe tracepoints that broke fd ->
pathname resolution, fix it:
[root@zoo ~]# perf probe 'vfs_getname=getname_flags:65 pathname=result->name:string'
Added new event:
probe:vfs_getname (on getname_flags:65 with pathname=result->name:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
[root@zoo ~]
Before:
[acme@zoo linux]$ trace touch -e open,fstat /tmp/b
1.159 ( 0.007 ms): open(filename: 0x7fd73f2fe088, flags: CLOEXEC ) = 3
1.163 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fff1b25e610 ) = 0
1.192 ( 0.009 ms): open(filename: 0x7fd73f4fedb8, flags: CLOEXEC ) = 3
1.201 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fff1b25e660 ) = 0
1.501 ( 0.013 ms): open(filename: 0x7fd73f0a1610, flags: CLOEXEC ) = 3
1.505 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fd73f2ddb60 ) = 0
1.581 ( 0.011 ms): open(filename: 0x7fff1b2603da, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
[acme@zoo linux]$
After:
[acme@zoo linux]$ trace touch -e open,fstat,dup2,mmap,close /tmp/b
1.105 ( 0.004 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1 ) = 0x2fbf000
1.136 ( 0.008 ms): open(filename: 0x7f8902dbc088, flags: CLOEXEC ) = 3
1.140 ( 0.002 ms): fstat(fd: 3</etc/ld.so.cache>, statbuf: 0x7fff19889ef0 ) = 0
1.146 ( 0.004 ms): mmap(len: 86079, prot: READ, flags: PRIVATE, fd: 3</etc/ld.so.cache> ) = 0x2fa9000
1.149 ( 0.001 ms): close(fd: 3</etc/ld.so.cache> ) = 0
1.170 ( 0.010 ms): open(filename: 0x7f8902fbcdb8, flags: CLOEXEC ) = 3
1.178 ( 0.002 ms): fstat(fd: 3</lib64/libc.so.6>, statbuf: 0x7fff19889f40 ) = 0
1.188 ( 0.006 ms): mmap(len: 3924576, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3</lib64/libc.so.6>) = 0x29e2000
1.207 ( 0.007 ms): mmap(addr: 0x7f8902d96000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3</lib64/libc.so.6>, off: 1785856) = 0x2d96000
1.217 ( 0.004 ms): mmap(addr: 0x7f8902d9c000, len: 16992, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED, fd: -1) = 0x2d9c000
1.228 ( 0.002 ms): close(fd: 3</lib64/libc.so.6> ) = 0
1.243 ( 0.003 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1 ) = 0x2fa8000
1.250 ( 0.003 ms): mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1 ) = 0x2fa6000
1.452 ( 0.010 ms): open(filename: 0x7f8902b5f610, flags: CLOEXEC ) = 3
1.455 ( 0.002 ms): fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7f8902d9bb60 ) = 0
1.461 ( 0.004 ms): mmap(len: 106070960, prot: READ, flags: PRIVATE, fd: 3</usr/lib/locale/locale-archive>) = 0xfc4b9000
1.469 ( 0.002 ms): close(fd: 3</usr/lib/locale/locale-archive> ) = 0
1.528 ( 0.010 ms): open(filename: 0x7fff1988c3da, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
1.532 ( 0.002 ms): dup2(oldfd: 3</tmp/b> ) = 0
1.535 ( 0.001 ms): close(fd: 3</tmp/b> ) = 0
1.544 ( 0.001 ms): close( ) = 0
1.555 ( 0.001 ms): close(fd: 1 ) = 0
1.558 ( 0.001 ms): close(fd: 2 ) = 0
[acme@zoo linux]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-vcm22xpjxc3j4hbyuzjzf7ik@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-06-10 19:00:18 +00:00
|
|
|
if ((fd > ttrace->paths.max || ttrace->paths.table[fd] == NULL)) {
|
2013-09-27 21:06:19 +00:00
|
|
|
if (!trace->live)
|
|
|
|
return NULL;
|
|
|
|
++trace->stats.proc_getname;
|
perf trace: Fix up fd -> pathname resolution
There was a brown paper bag bug in the patch that introduced a reference
implementation on using 'perf probe' made wannabe tracepoints that broke fd ->
pathname resolution, fix it:
[root@zoo ~]# perf probe 'vfs_getname=getname_flags:65 pathname=result->name:string'
Added new event:
probe:vfs_getname (on getname_flags:65 with pathname=result->name:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
[root@zoo ~]
Before:
[acme@zoo linux]$ trace touch -e open,fstat /tmp/b
1.159 ( 0.007 ms): open(filename: 0x7fd73f2fe088, flags: CLOEXEC ) = 3
1.163 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fff1b25e610 ) = 0
1.192 ( 0.009 ms): open(filename: 0x7fd73f4fedb8, flags: CLOEXEC ) = 3
1.201 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fff1b25e660 ) = 0
1.501 ( 0.013 ms): open(filename: 0x7fd73f0a1610, flags: CLOEXEC ) = 3
1.505 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fd73f2ddb60 ) = 0
1.581 ( 0.011 ms): open(filename: 0x7fff1b2603da, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
[acme@zoo linux]$
After:
[acme@zoo linux]$ trace touch -e open,fstat,dup2,mmap,close /tmp/b
1.105 ( 0.004 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1 ) = 0x2fbf000
1.136 ( 0.008 ms): open(filename: 0x7f8902dbc088, flags: CLOEXEC ) = 3
1.140 ( 0.002 ms): fstat(fd: 3</etc/ld.so.cache>, statbuf: 0x7fff19889ef0 ) = 0
1.146 ( 0.004 ms): mmap(len: 86079, prot: READ, flags: PRIVATE, fd: 3</etc/ld.so.cache> ) = 0x2fa9000
1.149 ( 0.001 ms): close(fd: 3</etc/ld.so.cache> ) = 0
1.170 ( 0.010 ms): open(filename: 0x7f8902fbcdb8, flags: CLOEXEC ) = 3
1.178 ( 0.002 ms): fstat(fd: 3</lib64/libc.so.6>, statbuf: 0x7fff19889f40 ) = 0
1.188 ( 0.006 ms): mmap(len: 3924576, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3</lib64/libc.so.6>) = 0x29e2000
1.207 ( 0.007 ms): mmap(addr: 0x7f8902d96000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3</lib64/libc.so.6>, off: 1785856) = 0x2d96000
1.217 ( 0.004 ms): mmap(addr: 0x7f8902d9c000, len: 16992, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED, fd: -1) = 0x2d9c000
1.228 ( 0.002 ms): close(fd: 3</lib64/libc.so.6> ) = 0
1.243 ( 0.003 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1 ) = 0x2fa8000
1.250 ( 0.003 ms): mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1 ) = 0x2fa6000
1.452 ( 0.010 ms): open(filename: 0x7f8902b5f610, flags: CLOEXEC ) = 3
1.455 ( 0.002 ms): fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7f8902d9bb60 ) = 0
1.461 ( 0.004 ms): mmap(len: 106070960, prot: READ, flags: PRIVATE, fd: 3</usr/lib/locale/locale-archive>) = 0xfc4b9000
1.469 ( 0.002 ms): close(fd: 3</usr/lib/locale/locale-archive> ) = 0
1.528 ( 0.010 ms): open(filename: 0x7fff1988c3da, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
1.532 ( 0.002 ms): dup2(oldfd: 3</tmp/b> ) = 0
1.535 ( 0.001 ms): close(fd: 3</tmp/b> ) = 0
1.544 ( 0.001 ms): close( ) = 0
1.555 ( 0.001 ms): close(fd: 1 ) = 0
1.558 ( 0.001 ms): close(fd: 2 ) = 0
[acme@zoo linux]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-vcm22xpjxc3j4hbyuzjzf7ik@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-06-10 19:00:18 +00:00
|
|
|
if (thread__read_fd_path(thread, fd))
|
2013-09-27 21:06:19 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
2013-09-24 14:04:32 +00:00
|
|
|
|
|
|
|
return ttrace->paths.table[fd];
|
|
|
|
}
|
|
|
|
|
|
|
|
static size_t syscall_arg__scnprintf_fd(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
int fd = arg->val;
|
|
|
|
size_t printed = scnprintf(bf, size, "%d", fd);
|
2013-09-27 21:06:19 +00:00
|
|
|
const char *path = thread__fd_path(arg->thread, fd, arg->trace);
|
2013-09-24 14:04:32 +00:00
|
|
|
|
|
|
|
if (path)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "<%s>", path);
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
|
|
|
static size_t syscall_arg__scnprintf_close_fd(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
int fd = arg->val;
|
|
|
|
size_t printed = syscall_arg__scnprintf_fd(bf, size, arg);
|
2014-10-06 00:46:03 +00:00
|
|
|
struct thread_trace *ttrace = thread__priv(arg->thread);
|
2013-09-24 14:04:32 +00:00
|
|
|
|
2013-12-26 20:41:15 +00:00
|
|
|
if (ttrace && fd >= 0 && fd <= ttrace->paths.max)
|
|
|
|
zfree(&ttrace->paths.table[fd]);
|
2013-09-24 14:04:32 +00:00
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
static void thread__set_filename_pos(struct thread *thread, const char *bf,
|
|
|
|
unsigned long ptr)
|
|
|
|
{
|
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
|
|
|
|
|
|
|
ttrace->filename.ptr = ptr;
|
|
|
|
ttrace->filename.entry_str_pos = bf - ttrace->entry_str;
|
|
|
|
}
|
|
|
|
|
|
|
|
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
unsigned long ptr = arg->val;
|
|
|
|
|
|
|
|
if (!arg->trace->vfs_getname)
|
|
|
|
return scnprintf(bf, size, "%#x", ptr);
|
|
|
|
|
|
|
|
thread__set_filename_pos(arg->thread, bf, ptr);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
static bool trace__filter_duration(struct trace *trace, double t)
|
|
|
|
{
|
|
|
|
return t < (trace->duration_filter * NSEC_PER_MSEC);
|
|
|
|
}
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
static size_t __trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
{
|
|
|
|
double ts = (double)(tstamp - trace->base_time) / NSEC_PER_MSEC;
|
|
|
|
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
return fprintf(fp, "%10.3f ", ts);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
}
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
/*
|
|
|
|
* We're handling tstamp=0 as an undefined tstamp, i.e. like when we are
|
|
|
|
* using ttrace->entry_time for a thread that receives a sys_exit without
|
|
|
|
* first having received a sys_enter ("poll" issued before tracing session
|
|
|
|
* starts, lost sys_enter exit due to ring buffer overflow).
|
|
|
|
*/
|
|
|
|
static size_t trace__fprintf_tstamp(struct trace *trace, u64 tstamp, FILE *fp)
|
|
|
|
{
|
|
|
|
if (tstamp > 0)
|
|
|
|
return __trace__fprintf_tstamp(trace, tstamp, fp);
|
|
|
|
|
|
|
|
return fprintf(fp, " ? ");
|
|
|
|
}
|
|
|
|
|
2012-10-05 05:02:16 +00:00
|
|
|
static bool done = false;
|
2013-10-16 14:57:33 +00:00
|
|
|
static bool interrupted = false;
|
2012-10-05 05:02:16 +00:00
|
|
|
|
2013-10-16 14:57:33 +00:00
|
|
|
static void sig_handler(int sig)
|
2012-10-05 05:02:16 +00:00
|
|
|
{
|
|
|
|
done = true;
|
2013-10-16 14:57:33 +00:00
|
|
|
interrupted = sig == SIGINT;
|
2012-10-05 05:02:16 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
|
2017-03-29 19:37:51 +00:00
|
|
|
u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
{
|
|
|
|
size_t printed = trace__fprintf_tstamp(trace, tstamp, fp);
|
2017-03-29 19:37:51 +00:00
|
|
|
printed += fprintf_duration(duration, duration_calculated, fp);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
perf trace: Add option to show process COMM
Enabled by default, disable with --no-comm, e.g.:
181.821 (0.001 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: PEEK|TRUNC|CMSG_CLOEXEC ) = 20
181.824 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.825 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.834 (0.002 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: CMSG_CLOEXEC ) = 20
181.836 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.838 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.705 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 1256
181.710 (0.002 ms): evolution-addr/10924 geteuid( ) = 1000
181.712 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.727 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 1256
181.731 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.734 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.908 (0.002 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 20
181.913 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.915 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.930 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 20
181.934 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.937 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
220.718 (0.010 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.741 (0.000 ms): dbus-daemon/10711 ... [continued]: epoll_wait()) = 1
220.759 (0.004 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.780 (0.002 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.788 (0.001 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = -1 EAGAIN Resource temporarily unavailable
220.760 (0.004 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.771 (0.023 ms): perf/26347 open(filename: 0xf2e780, mode: 15918976 ) = 19
220.850 (0.002 ms): perf/26347 close(fd: 19 ) = 0
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6be5jvnkdzjptdrebfn5263n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 15:35:21 +00:00
|
|
|
if (trace->multiple_threads) {
|
|
|
|
if (trace->show_comm)
|
2013-09-11 14:56:44 +00:00
|
|
|
printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
|
2013-07-04 13:20:31 +00:00
|
|
|
printed += fprintf(fp, "%d ", thread->tid);
|
perf trace: Add option to show process COMM
Enabled by default, disable with --no-comm, e.g.:
181.821 (0.001 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: PEEK|TRUNC|CMSG_CLOEXEC ) = 20
181.824 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.825 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.834 (0.002 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: CMSG_CLOEXEC ) = 20
181.836 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.838 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.705 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 1256
181.710 (0.002 ms): evolution-addr/10924 geteuid( ) = 1000
181.712 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.727 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 1256
181.731 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.734 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.908 (0.002 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 20
181.913 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.915 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.930 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 20
181.934 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.937 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
220.718 (0.010 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.741 (0.000 ms): dbus-daemon/10711 ... [continued]: epoll_wait()) = 1
220.759 (0.004 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.780 (0.002 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.788 (0.001 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = -1 EAGAIN Resource temporarily unavailable
220.760 (0.004 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.771 (0.023 ms): perf/26347 open(filename: 0xf2e780, mode: 15918976 ) = 19
220.850 (0.002 ms): perf/26347 close(fd: 19 ) = 0
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6be5jvnkdzjptdrebfn5263n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 15:35:21 +00:00
|
|
|
}
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
static int trace__process_event(struct trace *trace, struct machine *machine,
|
2013-09-11 14:18:24 +00:00
|
|
|
union perf_event *event, struct perf_sample *sample)
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
switch (event->header.type) {
|
|
|
|
case PERF_RECORD_LOST:
|
2013-08-19 15:01:10 +00:00
|
|
|
color_fprintf(trace->output, PERF_COLOR_RED,
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
"LOST %" PRIu64 " events!\n", event->lost.lost);
|
2013-09-11 14:18:24 +00:00
|
|
|
ret = machine__process_lost_event(machine, event, sample);
|
2016-03-30 19:51:17 +00:00
|
|
|
break;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
default:
|
2013-09-11 14:18:24 +00:00
|
|
|
ret = machine__process_event(machine, event, sample);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
static int trace__tool_process(struct perf_tool *tool,
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
union perf_event *event,
|
2013-09-11 14:18:24 +00:00
|
|
|
struct perf_sample *sample,
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
struct machine *machine)
|
|
|
|
{
|
2013-08-19 15:01:10 +00:00
|
|
|
struct trace *trace = container_of(tool, struct trace, tool);
|
2013-09-11 14:18:24 +00:00
|
|
|
return trace__process_event(trace, machine, event, sample);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
}
|
|
|
|
|
2016-05-17 14:56:24 +00:00
|
|
|
static char *trace__machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, char **modp)
|
|
|
|
{
|
|
|
|
struct machine *machine = vmachine;
|
|
|
|
|
|
|
|
if (machine->kptr_restrict_warned)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (symbol_conf.kptr_restrict) {
|
|
|
|
pr_warning("Kernel address maps (/proc/{kallsyms,modules}) are restricted.\n\n"
|
|
|
|
"Check /proc/sys/kernel/kptr_restrict.\n\n"
|
|
|
|
"Kernel samples will not be resolved.\n");
|
|
|
|
machine->kptr_restrict_warned = true;
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
return machine__resolve_kernel_addr(vmachine, addrp, modp);
|
|
|
|
}
|
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
|
|
|
|
{
|
2014-08-12 06:40:45 +00:00
|
|
|
int err = symbol__init(NULL);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
2013-09-28 19:13:00 +00:00
|
|
|
trace->host = machine__new_host();
|
|
|
|
if (trace->host == NULL)
|
|
|
|
return -ENOMEM;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
2016-05-17 14:56:24 +00:00
|
|
|
if (trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr) < 0)
|
2015-07-22 19:16:16 +00:00
|
|
|
return -errno;
|
|
|
|
|
2013-11-11 14:36:12 +00:00
|
|
|
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
|
2015-06-17 13:51:11 +00:00
|
|
|
evlist->threads, trace__tool_process, false,
|
|
|
|
trace->opts.proc_map_timeout);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
if (err)
|
|
|
|
symbol__exit();
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2013-08-23 21:14:48 +00:00
|
|
|
static int syscall__set_arg_fmts(struct syscall *sc)
|
|
|
|
{
|
|
|
|
struct format_field *field;
|
2016-05-23 15:59:53 +00:00
|
|
|
int idx = 0, len;
|
2013-08-23 21:14:48 +00:00
|
|
|
|
2015-03-20 20:46:53 +00:00
|
|
|
sc->arg_scnprintf = calloc(sc->nr_args, sizeof(void *));
|
2013-08-23 21:14:48 +00:00
|
|
|
if (sc->arg_scnprintf == NULL)
|
|
|
|
return -1;
|
|
|
|
|
2013-09-03 18:50:28 +00:00
|
|
|
if (sc->fmt)
|
|
|
|
sc->arg_parm = sc->fmt->arg_parm;
|
|
|
|
|
2015-03-20 20:46:53 +00:00
|
|
|
for (field = sc->args; field; field = field->next) {
|
2013-08-26 15:29:38 +00:00
|
|
|
if (sc->fmt && sc->fmt->arg_scnprintf[idx])
|
|
|
|
sc->arg_scnprintf[idx] = sc->fmt->arg_scnprintf[idx];
|
2016-05-23 19:37:55 +00:00
|
|
|
else if (strcmp(field->type, "const char *") == 0 &&
|
|
|
|
(strcmp(field->name, "filename") == 0 ||
|
|
|
|
strcmp(field->name, "path") == 0 ||
|
|
|
|
strcmp(field->name, "pathname") == 0))
|
|
|
|
sc->arg_scnprintf[idx] = SCA_FILENAME;
|
2013-08-26 15:29:38 +00:00
|
|
|
else if (field->flags & FIELD_IS_POINTER)
|
2013-08-23 21:14:48 +00:00
|
|
|
sc->arg_scnprintf[idx] = syscall_arg__scnprintf_hex;
|
perf trace: Beautify pid_t arguments
When reading the syscall tracepoint /format file, look for arguments
of type "pid_t" and attach the PID beautifier, that will do a lookup
on the threads it knows, i.e. the ones that came from PERF_RECORD_COMM
events and add the COMM after the pid in such args:
Excerpt of a system wide trace for syscalls with pid_t args:
55602.977 ( 0.006 ms): bash/12122 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55603.024 ( 0.004 ms): bash/24347 setpgid(pid: 24347 (bash), pgid: 24347 (bash)) = 0
55691.527 (88.397 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) ...
55692.479 ( 0.952 ms): git/24347 wait4(upid: 24368, stat_addr: 0x7ffe030d5724) ...
55694.549 ( 2.070 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4fc10) = 24369 (pre-commit)
55694.575 ( 0.002 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f650, options: NOHANG) = -1 ECHILD No child processes
55695.934 ( 0.010 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = 24370 (git)
55695.937 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f2d0, options: NOHANG) = -1 ECHILD No child processes
55717.963 ( 0.000 ms): pre-commit/24371 ... [continued]: wait4()) = 24372
55717.978 (21.468 ms): :24371/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) ...
55718.087 ( 0.109 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24373 (tr)
55718.187 ( 0.096 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4f230) = 24374 (wc)
55718.218 ( 0.002 ms): pre-commit/24371 wait4(upid: -1, stat_addr: 0x7ffc94f4eed0, options: NOHANG) = -1 ECHILD No child processes
55718.367 ( 0.005 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = 24371 (pre-commit)
55718.369 ( 0.001 ms): pre-commit/24368 wait4(upid: -1, stat_addr: 0x7ffc94f4f1d0, options: NOHANG) = -1 ECHILD No child processes
55741.021 (49.494 ms): git/24347 ... [continued]: wait4()) = 24368 (pre-commit)
74146.427 (18319.601 ms): git/24347 wait4(upid: 24375 (git), stat_addr: 0x7ffe030d6824) ...
74149.036 ( 0.891 ms): bash/24391 wait4(upid: -1, stat_addr: 0x7ffe0cee0560) = 24393 (sed)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-75yl9hzjhb020iadc81gdj8t@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 21:02:41 +00:00
|
|
|
else if (strcmp(field->type, "pid_t") == 0)
|
|
|
|
sc->arg_scnprintf[idx] = SCA_PID;
|
perf trace: Beautify mode_t arguments
When reading the syscall tracepoint /format file, look for arguments of type
"mode_t" and attach a beautifier:
[root@jouet ~]# cat ~/bin/tp_with_fields_of_type
#!/bin/bash
grep -w $1 /sys/kernel/tracing/events/syscalls/*/format | sed -r 's%.*sys_enter_(.*)/format.*%\1%g' | paste -d, -s
# tp_with_fields_of_type umode_t
chmod,creat,fchmodat,fchmod,mkdirat,mkdir,mknodat,mknod,mq_open,openat,open
#
Testing it:
#define S_ISUID 0004000
#define S_ISGID 0002000
#define S_ISVTX 0001000
#define S_IRWXU 0000700
#define S_IRUSR 0000400
#define S_IWUSR 0000200
#define S_IXUSR 0000100
#define S_IRWXG 0000070
#define S_IRGRP 0000040
#define S_IWGRP 0000020
#define S_IXGRP 0000010
#define S_IRWXO 0000007
#define S_IROTH 0000004
#define S_IWOTH 0000002
#define S_IXOTH 0000001
# for mode in 4000 2000 1000 700 400 200 100 70 40 20 10 7 4 2 1 ; do \
echo -n $mode '->' ; trace --no-inherit -e chmod,fchmodat,fchmod chmod $mode x; \
done
4000 -> 0.338 ( 0.012 ms): fchmodat(dfd: CWD, filename: x, mode: ISUID) = 0
2000 -> 0.438 ( 0.015 ms): fchmodat(dfd: CWD, filename: x, mode: ISGID) = 0
1000 -> 0.677 ( 0.040 ms): fchmodat(dfd: CWD, filename: x, mode: ISVTX) = 0
700 -> 0.394 ( 0.013 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXU) = 0
400 -> 0.337 ( 0.010 ms): fchmodat(dfd: CWD, filename: x, mode: IRUSR) = 0
200 -> 0.259 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IWUSR) = 0
100 -> 0.249 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IXUSR) = 0
70 -> 0.266 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXG) = 0
40 -> 0.329 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IRGRP) = 0
20 -> 0.250 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IWGRP) = 0
10 -> 0.259 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IXGRP) = 0
7 -> 0.249 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXO) = 0
4 -> 0.278 ( 0.011 ms): fchmodat(dfd: CWD, filename: x, mode: IROTH) = 0
2 -> 0.276 ( 0.009 ms): fchmodat(dfd: CWD, filename: x, mode: IWOTH) = 0
1 -> 0.250 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: IXOTH) = 0
#
# trace --no-inherit -e chmod,fchmodat,fchmod chmod 7777 x
0.258 ( 0.011 ms): fchmodat(dfd: CWD, filename: x, mode: IALLUGO) = 0
# trace --no-inherit -e chmod,fchmodat,fchmod chmod 7770 x
0.258 ( 0.008 ms): fchmodat(dfd: CWD, filename: x, mode: ISUID|ISGID|ISVTX|IRWXU|IRWXG) = 0
# trace --no-inherit -e chmod,fchmodat,fchmod chmod 777 x
0.293 ( 0.012 ms): fchmodat(dfd: CWD, filename: x, mode: IRWXUGO
#
Now lets see if check by using the tracepoint for that specific syscall,
instead of raw_syscalls:sys_enter as 'trace' does for its strace fu:
# trace --no-inherit --ev syscalls:sys_enter_fchmodat -e fchmodat chmod 666 x
0.255 ( ): syscalls:sys_enter_fchmodat:dfd: 0xffffffffffffff9c, filename: 0x55db32a3f0f0, mode: 0x000001b6)
0.268 ( 0.012 ms): fchmodat(dfd: CWD, filename: x, mode: IRUGO|IWUGO ) = 0
#
Perfect, 0x1bc == 0666.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-18e8zfgbkj83xo87yoom43kd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-07 15:05:51 +00:00
|
|
|
else if (strcmp(field->type, "umode_t") == 0)
|
|
|
|
sc->arg_scnprintf[idx] = SCA_MODE_T;
|
2016-05-23 15:59:53 +00:00
|
|
|
else if ((strcmp(field->type, "int") == 0 ||
|
|
|
|
strcmp(field->type, "unsigned int") == 0 ||
|
|
|
|
strcmp(field->type, "long") == 0) &&
|
|
|
|
(len = strlen(field->name)) >= 2 &&
|
|
|
|
strcmp(field->name + len - 2, "fd") == 0) {
|
|
|
|
/*
|
|
|
|
* /sys/kernel/tracing/events/syscalls/sys_enter*
|
|
|
|
* egrep 'field:.*fd;' .../format|sed -r 's/.*field:([a-z ]+) [a-z_]*fd.+/\1/g'|sort|uniq -c
|
|
|
|
* 65 int
|
|
|
|
* 23 unsigned int
|
|
|
|
* 7 unsigned long
|
|
|
|
*/
|
|
|
|
sc->arg_scnprintf[idx] = SCA_FD;
|
|
|
|
}
|
2013-08-23 21:14:48 +00:00
|
|
|
++idx;
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-09-26 23:05:56 +00:00
|
|
|
static int trace__read_syscall_info(struct trace *trace, int id)
|
|
|
|
{
|
|
|
|
char tp_name[128];
|
|
|
|
struct syscall *sc;
|
2016-04-04 16:32:20 +00:00
|
|
|
const char *name = syscalltbl__name(trace->sctbl, id);
|
2012-10-20 15:39:03 +00:00
|
|
|
|
|
|
|
if (name == NULL)
|
|
|
|
return -1;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
|
|
|
if (id > trace->syscalls.max) {
|
|
|
|
struct syscall *nsyscalls = realloc(trace->syscalls.table, (id + 1) * sizeof(*sc));
|
|
|
|
|
|
|
|
if (nsyscalls == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (trace->syscalls.max != -1) {
|
|
|
|
memset(nsyscalls + trace->syscalls.max + 1, 0,
|
|
|
|
(id - trace->syscalls.max) * sizeof(*sc));
|
|
|
|
} else {
|
|
|
|
memset(nsyscalls, 0, (id + 1) * sizeof(*sc));
|
|
|
|
}
|
|
|
|
|
|
|
|
trace->syscalls.table = nsyscalls;
|
|
|
|
trace->syscalls.max = id;
|
|
|
|
}
|
|
|
|
|
|
|
|
sc = trace->syscalls.table + id;
|
2012-10-20 15:39:03 +00:00
|
|
|
sc->name = name;
|
2013-08-09 15:28:31 +00:00
|
|
|
|
2012-10-20 15:39:03 +00:00
|
|
|
sc->fmt = syscall_fmt__find(sc->name);
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2012-09-27 16:16:00 +00:00
|
|
|
snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
|
2013-12-03 13:09:24 +00:00
|
|
|
sc->tp_format = trace_event__tp_format("syscalls", tp_name);
|
2012-09-27 16:16:00 +00:00
|
|
|
|
2015-09-07 08:38:06 +00:00
|
|
|
if (IS_ERR(sc->tp_format) && sc->fmt && sc->fmt->alias) {
|
2012-09-27 16:16:00 +00:00
|
|
|
snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
|
2013-12-03 13:09:24 +00:00
|
|
|
sc->tp_format = trace_event__tp_format("syscalls", tp_name);
|
2012-09-27 16:16:00 +00:00
|
|
|
}
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2015-09-07 08:38:06 +00:00
|
|
|
if (IS_ERR(sc->tp_format))
|
2013-08-23 21:14:48 +00:00
|
|
|
return -1;
|
|
|
|
|
2015-03-20 20:46:53 +00:00
|
|
|
sc->args = sc->tp_format->format.fields;
|
|
|
|
sc->nr_args = sc->tp_format->format.nr_fields;
|
2016-02-26 13:14:25 +00:00
|
|
|
/*
|
|
|
|
* We need to check and discard the first variable '__syscall_nr'
|
|
|
|
* or 'nr' that mean the syscall number. It is needless here.
|
|
|
|
* So drop '__syscall_nr' or 'nr' field but does not exist on older kernels.
|
|
|
|
*/
|
|
|
|
if (sc->args && (!strcmp(sc->args->name, "__syscall_nr") || !strcmp(sc->args->name, "nr"))) {
|
2015-03-20 20:46:53 +00:00
|
|
|
sc->args = sc->args->next;
|
|
|
|
--sc->nr_args;
|
|
|
|
}
|
|
|
|
|
2014-06-17 17:29:24 +00:00
|
|
|
sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
|
|
|
|
|
2013-08-23 21:14:48 +00:00
|
|
|
return syscall__set_arg_fmts(sc);
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
static int trace__validate_ev_qualifier(struct trace *trace)
|
|
|
|
{
|
2015-07-02 21:28:11 +00:00
|
|
|
int err = 0, i;
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
struct str_node *pos;
|
|
|
|
|
2015-07-02 21:28:11 +00:00
|
|
|
trace->ev_qualifier_ids.nr = strlist__nr_entries(trace->ev_qualifier);
|
|
|
|
trace->ev_qualifier_ids.entries = malloc(trace->ev_qualifier_ids.nr *
|
|
|
|
sizeof(trace->ev_qualifier_ids.entries[0]));
|
|
|
|
|
|
|
|
if (trace->ev_qualifier_ids.entries == NULL) {
|
|
|
|
fputs("Error:\tNot enough memory for allocating events qualifier ids\n",
|
|
|
|
trace->output);
|
|
|
|
err = -EINVAL;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
i = 0;
|
|
|
|
|
2016-06-23 14:31:20 +00:00
|
|
|
strlist__for_each_entry(pos, trace->ev_qualifier) {
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
const char *sc = pos->s;
|
2016-04-04 16:32:20 +00:00
|
|
|
int id = syscalltbl__id(trace->sctbl, sc);
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
|
2015-07-02 21:28:11 +00:00
|
|
|
if (id < 0) {
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
if (err == 0) {
|
|
|
|
fputs("Error:\tInvalid syscall ", trace->output);
|
|
|
|
err = -EINVAL;
|
|
|
|
} else {
|
|
|
|
fputs(", ", trace->output);
|
|
|
|
}
|
|
|
|
|
|
|
|
fputs(sc, trace->output);
|
|
|
|
}
|
2015-07-02 21:28:11 +00:00
|
|
|
|
|
|
|
trace->ev_qualifier_ids.entries[i++] = id;
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
if (err < 0) {
|
|
|
|
fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
|
|
|
|
"\nHint:\tand: 'man syscalls'\n", trace->output);
|
2015-07-02 21:28:11 +00:00
|
|
|
zfree(&trace->ev_qualifier_ids.entries);
|
|
|
|
trace->ev_qualifier_ids.nr = 0;
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
}
|
2015-07-02 21:28:11 +00:00
|
|
|
out:
|
perf trace: Validate syscall list passed via -e argument
The 'trace' tool was accepting any names passed and just looking if
syscalls returned via the raw_syscalls:* tracepoints were in that list,
leading to it accepting perf events and then never finding any, as those
are not valid syscall names, confusing users.
Fix it by checking each entry in the list using audit_name_to_syscall,
telling the user which entries are invalid and suggesting where to look
for valid syscall names.
E.g:
[root@zoo ~]# trace -e open,foo,bar,close,baz
Error: Invalid syscall bar, baz, foo
Hint: try 'perf list syscalls:sys_enter_*'
Hint: and: 'man syscalls'
[root@zoo ~]#
Reported-by: Flavio Leitner <fbl@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-4g1i3m1z6fzsrznn2umi02wa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-25 22:32:33 +00:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
/*
|
|
|
|
* args is to be interpreted as a series of longs but we need to handle
|
|
|
|
* 8-byte unaligned accesses. args points to raw_data within the event
|
|
|
|
* and raw_data is guaranteed to be 8-byte unaligned because it is
|
|
|
|
* preceded by raw_size which is a u32. So we need to copy args to a temp
|
|
|
|
* variable to read it. Most notably this avoids extended load instructions
|
|
|
|
* on unaligned addresses
|
|
|
|
*/
|
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
unsigned char *args, struct trace *trace,
|
2013-09-24 14:04:32 +00:00
|
|
|
struct thread *thread)
|
2012-09-26 23:05:56 +00:00
|
|
|
{
|
|
|
|
size_t printed = 0;
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
unsigned char *p;
|
|
|
|
unsigned long val;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2015-03-20 20:46:53 +00:00
|
|
|
if (sc->args != NULL) {
|
2012-09-26 23:05:56 +00:00
|
|
|
struct format_field *field;
|
2013-09-03 15:20:12 +00:00
|
|
|
u8 bit = 1;
|
|
|
|
struct syscall_arg arg = {
|
2013-09-24 14:04:32 +00:00
|
|
|
.idx = 0,
|
|
|
|
.mask = 0,
|
|
|
|
.trace = trace,
|
|
|
|
.thread = thread,
|
2013-09-03 15:20:12 +00:00
|
|
|
};
|
2013-09-02 13:39:21 +00:00
|
|
|
|
2015-03-20 20:46:53 +00:00
|
|
|
for (field = sc->args; field;
|
2013-09-03 15:20:12 +00:00
|
|
|
field = field->next, ++arg.idx, bit <<= 1) {
|
|
|
|
if (arg.mask & bit)
|
2013-09-02 13:39:21 +00:00
|
|
|
continue;
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
|
|
|
|
/* special care for unaligned accesses */
|
|
|
|
p = args + sizeof(unsigned long) * arg.idx;
|
|
|
|
memcpy(&val, p, sizeof(val));
|
|
|
|
|
2013-09-20 15:19:41 +00:00
|
|
|
/*
|
|
|
|
* Suppress this argument if its value is zero and
|
|
|
|
* and we don't have a string associated in an
|
|
|
|
* strarray for it.
|
|
|
|
*/
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
if (val == 0 &&
|
2013-09-20 15:19:41 +00:00
|
|
|
!(sc->arg_scnprintf &&
|
|
|
|
sc->arg_scnprintf[arg.idx] == SCA_STRARRAY &&
|
|
|
|
sc->arg_parm[arg.idx]))
|
2013-09-12 14:27:34 +00:00
|
|
|
continue;
|
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
printed += scnprintf(bf + printed, size - printed,
|
2013-08-23 21:14:48 +00:00
|
|
|
"%s%s: ", printed ? ", " : "", field->name);
|
2013-09-03 15:20:12 +00:00
|
|
|
if (sc->arg_scnprintf && sc->arg_scnprintf[arg.idx]) {
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
arg.val = val;
|
2013-09-03 18:50:28 +00:00
|
|
|
if (sc->arg_parm)
|
|
|
|
arg.parm = sc->arg_parm[arg.idx];
|
2013-09-03 15:20:12 +00:00
|
|
|
printed += sc->arg_scnprintf[arg.idx](bf + printed,
|
|
|
|
size - printed, &arg);
|
2013-09-02 13:39:21 +00:00
|
|
|
} else {
|
2013-08-23 21:14:48 +00:00
|
|
|
printed += scnprintf(bf + printed, size - printed,
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
"%ld", val);
|
2013-09-02 13:39:21 +00:00
|
|
|
}
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|
2016-05-06 02:38:05 +00:00
|
|
|
} else if (IS_ERR(sc->tp_format)) {
|
|
|
|
/*
|
|
|
|
* If we managed to read the tracepoint /format file, then we
|
|
|
|
* may end up not having any args, like with gettid(), so only
|
|
|
|
* print the raw args when we didn't manage to read it.
|
|
|
|
*/
|
2013-09-03 15:20:12 +00:00
|
|
|
int i = 0;
|
|
|
|
|
2012-09-26 23:05:56 +00:00
|
|
|
while (i < 6) {
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
/* special care for unaligned accesses */
|
|
|
|
p = args + sizeof(unsigned long) * i;
|
|
|
|
memcpy(&val, p, sizeof(val));
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
printed += scnprintf(bf + printed, size - printed,
|
|
|
|
"%sarg%d: %ld",
|
perf trace: Fix SIGBUS failures due to misaligned accesses
On Sparc64 perf-trace is failing in many spots due to extended load
instructions being used on misaligned accesses.
(gdb) run trace ls
Starting program: /tmp/perf/perf trace ls
[Thread debugging using libthread_db enabled]
Detaching after fork from child process 169460.
<ls output removed>
Program received signal SIGBUS, Bus error.
0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
warning: Source file is more recent than executable.
61 TP_UINT_FIELD(64);
(gdb) bt
0 0x000000000014f4dc in tp_field__u64 (field=0x4cc700, sample=0x7feffffa098) at builtin-trace.c:61
1 0x0000000000156ad4 in trace__sys_exit (trace=0x7feffffc268, evsel=0x4cc580, event=0xfffffc0104912000,
sample=0x7feffffa098) at builtin-trace.c:1701
2 0x0000000000158c14 in trace__run (trace=0x7feffffc268, argc=1, argv=0x7fefffff360) at builtin-trace.c:2160
3 0x000000000015b78c in cmd_trace (argc=1, argv=0x7fefffff360, prefix=0x0) at builtin-trace.c:2609
4 0x0000000000107d94 in run_builtin (p=0x4549c8, argc=2, argv=0x7fefffff360) at perf.c:341
5 0x0000000000108140 in handle_internal_command (argc=2, argv=0x7fefffff360) at perf.c:400
6 0x0000000000108308 in run_argv (argcp=0x7feffffef2c, argv=0x7feffffef20) at perf.c:444
7 0x0000000000108728 in main (argc=2, argv=0x7fefffff360) at perf.c:559
(gdb) p *sample
$1 = {ip = 4391276, pid = 169472, tid = 169472, time = 6303014583281250, addr = 0, id = 72082,
stream_id = 18446744073709551615, period = 1, weight = 0, transaction = 0, cpu = 73, raw_size = 36,
data_src = 84410401, flags = 0, insn_len = 0, raw_data = 0xfffffc010491203c, callchain = 0x0,
branch_stack = 0x0, user_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0},
intr_regs = {abi = 0, mask = 0, regs = 0x0, cache_regs = 0x7feffffa098, cache_mask = 0}, user_stack = {
offset = 0, size = 0, data = 0x0}, read = {time_enabled = 0, time_running = 0, {group = {nr = 0,
values = 0x0}, one = {value = 0, id = 0}}}}
(gdb) p *field
$2 = {offset = 16, {integer = 0x14f4a8 <tp_field__u64>, pointer = 0x14f4a8 <tp_field__u64>}}
sample->raw_data is guaranteed to not be 8-byte aligned because it is preceded
by the size as a u3. So accessing raw data with an extended load instruction causes
the SIGBUS. Resolve by using memcpy to a temporary variable of appropriate size.
Signed-off-by: David Ahern <david.ahern@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1424376022-140608-1-git-send-email-david.ahern@oracle.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-19 20:00:22 +00:00
|
|
|
printed ? ", " : "", i, val);
|
2012-09-26 23:05:56 +00:00
|
|
|
++i;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2012-09-28 20:58:36 +00:00
|
|
|
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 16:14:24 +00:00
|
|
|
union perf_event *event,
|
2012-09-28 20:58:36 +00:00
|
|
|
struct perf_sample *sample);
|
|
|
|
|
|
|
|
static struct syscall *trace__syscall_info(struct trace *trace,
|
2013-10-09 03:26:53 +00:00
|
|
|
struct perf_evsel *evsel, int id)
|
2012-09-28 20:58:36 +00:00
|
|
|
{
|
|
|
|
|
|
|
|
if (id < 0) {
|
2013-08-22 20:55:25 +00:00
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX: Noticed on x86_64, reproduced as far back as 3.0.36, haven't tried
|
|
|
|
* before that, leaving at a higher verbosity level till that is
|
|
|
|
* explained. Reproduced with plain ftrace with:
|
|
|
|
*
|
|
|
|
* echo 1 > /t/events/raw_syscalls/sys_exit/enable
|
|
|
|
* grep "NR -1 " /t/trace_pipe
|
|
|
|
*
|
|
|
|
* After generating some load on the machine.
|
|
|
|
*/
|
|
|
|
if (verbose > 1) {
|
|
|
|
static u64 n;
|
|
|
|
fprintf(trace->output, "Invalid syscall %d id, skipping (%s, %" PRIu64 ") ...\n",
|
|
|
|
id, perf_evsel__name(evsel), ++n);
|
|
|
|
}
|
2012-09-28 20:58:36 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL) &&
|
|
|
|
trace__read_syscall_info(trace, id))
|
|
|
|
goto out_cant_read;
|
|
|
|
|
|
|
|
if ((id > trace->syscalls.max || trace->syscalls.table[id].name == NULL))
|
|
|
|
goto out_cant_read;
|
|
|
|
|
|
|
|
return &trace->syscalls.table[id];
|
|
|
|
|
|
|
|
out_cant_read:
|
2017-02-17 08:17:38 +00:00
|
|
|
if (verbose > 0) {
|
2013-08-22 19:49:54 +00:00
|
|
|
fprintf(trace->output, "Problems reading syscall %d", id);
|
|
|
|
if (id <= trace->syscalls.max && trace->syscalls.table[id].name != NULL)
|
|
|
|
fprintf(trace->output, "(%s)", trace->syscalls.table[id].name);
|
|
|
|
fputs(" information\n", trace->output);
|
|
|
|
}
|
2012-09-28 20:58:36 +00:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
static void thread__update_stats(struct thread_trace *ttrace,
|
|
|
|
int id, struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
struct int_node *inode;
|
|
|
|
struct stats *stats;
|
|
|
|
u64 duration = 0;
|
|
|
|
|
|
|
|
inode = intlist__findnew(ttrace->syscall_stats, id);
|
|
|
|
if (inode == NULL)
|
|
|
|
return;
|
|
|
|
|
|
|
|
stats = inode->priv;
|
|
|
|
if (stats == NULL) {
|
|
|
|
stats = malloc(sizeof(struct stats));
|
|
|
|
if (stats == NULL)
|
|
|
|
return;
|
|
|
|
init_stats(stats);
|
|
|
|
inode->priv = stats;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ttrace->entry_time && sample->time > ttrace->entry_time)
|
|
|
|
duration = sample->time - ttrace->entry_time;
|
|
|
|
|
|
|
|
update_stats(stats, duration);
|
|
|
|
}
|
|
|
|
|
perf trace: Handle multiple threads better wrt syscalls being intermixed
$ trace time taskset -c 0 usleep 1
0.845 ( 0.021 ms): time/16722 wait4(upid: 4294967295, stat_addr: 0x7fff17f443d4, ru: 0x7fff17f44438 ) ...
0.865 ( 0.008 ms): time/16723 execve(arg0: 140733595272004, arg1: 140733595272720, arg2: 140733595272768, arg3: 139755107218496, arg4: 7307199665339051828, arg5: 3) = -2
2.395 ( 1.523 ms): taskset/16723 execve(arg0: 140733595272013, arg1: 140733595272720, arg2: 140733595272768, arg3: 139755107218496, arg4: 7307199665339051828, arg5: 3) = 0
2.411 ( 0.002 ms): taskset/16723 brk( ) = 0x1915000
3.300 ( 0.058 ms): usleep/16723 nanosleep(rqtp: 0x7ffff4ada190 ) = 0
<SNIP>
3.305 ( 0.000 ms): usleep/16723 exit_group(
3.363 ( 2.539 ms): time/16722 ... [continued]: wait4()) = 16723
3.366 ( 0.001 ms): time/16722 rt_sigaction(sig: INT, act: 0x7fff17f44160, oact: 0x7fff17f44200, sigsetsize: 8) = 0
We we're not seeing this line:
0.845 ( 0.021 ms): time/16722 wait4(upid: 4294967295, stat_addr: 0x7fff17f443d4, ru: 0x7fff17f44438 ) ...
just the one when it finishes:
3.363 ( 2.539 ms): time/16722 ... [continued]: wait4()) = 16723
Still some issues left till we move to ordered_samples when multiple
CPUs/threads are involved...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-zq9x30a1ky3djqewqn2v3ja3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-13 16:22:21 +00:00
|
|
|
static int trace__printf_interrupted_entry(struct trace *trace, struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
struct thread_trace *ttrace;
|
|
|
|
u64 duration;
|
|
|
|
size_t printed;
|
|
|
|
|
|
|
|
if (trace->current == NULL)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ttrace = thread__priv(trace->current);
|
|
|
|
|
|
|
|
if (!ttrace->entry_pending)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
duration = sample->time - ttrace->entry_time;
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
printed = trace__fprintf_entry_head(trace, trace->current, duration, true, ttrace->entry_time, trace->output);
|
perf trace: Handle multiple threads better wrt syscalls being intermixed
$ trace time taskset -c 0 usleep 1
0.845 ( 0.021 ms): time/16722 wait4(upid: 4294967295, stat_addr: 0x7fff17f443d4, ru: 0x7fff17f44438 ) ...
0.865 ( 0.008 ms): time/16723 execve(arg0: 140733595272004, arg1: 140733595272720, arg2: 140733595272768, arg3: 139755107218496, arg4: 7307199665339051828, arg5: 3) = -2
2.395 ( 1.523 ms): taskset/16723 execve(arg0: 140733595272013, arg1: 140733595272720, arg2: 140733595272768, arg3: 139755107218496, arg4: 7307199665339051828, arg5: 3) = 0
2.411 ( 0.002 ms): taskset/16723 brk( ) = 0x1915000
3.300 ( 0.058 ms): usleep/16723 nanosleep(rqtp: 0x7ffff4ada190 ) = 0
<SNIP>
3.305 ( 0.000 ms): usleep/16723 exit_group(
3.363 ( 2.539 ms): time/16722 ... [continued]: wait4()) = 16723
3.366 ( 0.001 ms): time/16722 rt_sigaction(sig: INT, act: 0x7fff17f44160, oact: 0x7fff17f44200, sigsetsize: 8) = 0
We we're not seeing this line:
0.845 ( 0.021 ms): time/16722 wait4(upid: 4294967295, stat_addr: 0x7fff17f443d4, ru: 0x7fff17f44438 ) ...
just the one when it finishes:
3.363 ( 2.539 ms): time/16722 ... [continued]: wait4()) = 16723
Still some issues left till we move to ordered_samples when multiple
CPUs/threads are involved...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-zq9x30a1ky3djqewqn2v3ja3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-13 16:22:21 +00:00
|
|
|
printed += fprintf(trace->output, "%-70s) ...\n", ttrace->entry_str);
|
|
|
|
ttrace->entry_pending = false;
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2012-09-28 20:58:36 +00:00
|
|
|
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 16:14:24 +00:00
|
|
|
union perf_event *event __maybe_unused,
|
2012-09-28 20:58:36 +00:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
char *msg;
|
2012-09-28 20:58:36 +00:00
|
|
|
void *args;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
size_t printed = 0;
|
2013-08-09 15:28:31 +00:00
|
|
|
struct thread *thread;
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
|
2013-10-09 03:26:53 +00:00
|
|
|
struct syscall *sc = trace__syscall_info(trace, evsel, id);
|
2013-08-09 15:28:31 +00:00
|
|
|
struct thread_trace *ttrace;
|
|
|
|
|
|
|
|
if (sc == NULL)
|
|
|
|
return -1;
|
2012-09-28 20:58:36 +00:00
|
|
|
|
2013-09-28 19:13:00 +00:00
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2013-08-19 15:01:10 +00:00
|
|
|
ttrace = thread__trace(thread, trace->output);
|
2013-08-09 15:28:31 +00:00
|
|
|
if (ttrace == NULL)
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
goto out_put;
|
2012-09-28 20:58:36 +00:00
|
|
|
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
|
|
|
if (ttrace->entry_str == NULL) {
|
2015-08-05 01:17:29 +00:00
|
|
|
ttrace->entry_str = malloc(trace__entry_str_size);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
if (!ttrace->entry_str)
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
goto out_put;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
|
2015-03-25 21:01:15 +00:00
|
|
|
trace__printf_interrupted_entry(trace, sample);
|
perf trace: Handle multiple threads better wrt syscalls being intermixed
$ trace time taskset -c 0 usleep 1
0.845 ( 0.021 ms): time/16722 wait4(upid: 4294967295, stat_addr: 0x7fff17f443d4, ru: 0x7fff17f44438 ) ...
0.865 ( 0.008 ms): time/16723 execve(arg0: 140733595272004, arg1: 140733595272720, arg2: 140733595272768, arg3: 139755107218496, arg4: 7307199665339051828, arg5: 3) = -2
2.395 ( 1.523 ms): taskset/16723 execve(arg0: 140733595272013, arg1: 140733595272720, arg2: 140733595272768, arg3: 139755107218496, arg4: 7307199665339051828, arg5: 3) = 0
2.411 ( 0.002 ms): taskset/16723 brk( ) = 0x1915000
3.300 ( 0.058 ms): usleep/16723 nanosleep(rqtp: 0x7ffff4ada190 ) = 0
<SNIP>
3.305 ( 0.000 ms): usleep/16723 exit_group(
3.363 ( 2.539 ms): time/16722 ... [continued]: wait4()) = 16723
3.366 ( 0.001 ms): time/16722 rt_sigaction(sig: INT, act: 0x7fff17f44160, oact: 0x7fff17f44200, sigsetsize: 8) = 0
We we're not seeing this line:
0.845 ( 0.021 ms): time/16722 wait4(upid: 4294967295, stat_addr: 0x7fff17f443d4, ru: 0x7fff17f44438 ) ...
just the one when it finishes:
3.363 ( 2.539 ms): time/16722 ... [continued]: wait4()) = 16723
Still some issues left till we move to ordered_samples when multiple
CPUs/threads are involved...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-zq9x30a1ky3djqewqn2v3ja3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-13 16:22:21 +00:00
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
ttrace->entry_time = sample->time;
|
|
|
|
msg = ttrace->entry_str;
|
2015-08-05 01:17:29 +00:00
|
|
|
printed += scnprintf(msg + printed, trace__entry_str_size - printed, "%s(", sc->name);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
2015-08-05 01:17:29 +00:00
|
|
|
printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
|
2013-09-24 14:04:32 +00:00
|
|
|
args, trace, thread);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
2014-06-17 17:29:24 +00:00
|
|
|
if (sc->is_exit) {
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
if (!(trace->duration_filter || trace->summary_only || trace->min_stack)) {
|
2017-03-29 19:37:51 +00:00
|
|
|
trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
|
2016-05-17 15:13:54 +00:00
|
|
|
fprintf(trace->output, "%-70s)\n", ttrace->entry_str);
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
}
|
2015-08-14 16:16:27 +00:00
|
|
|
} else {
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
ttrace->entry_pending = true;
|
2015-08-14 16:16:27 +00:00
|
|
|
/* See trace__vfs_getname & trace__sys_exit */
|
|
|
|
ttrace->filename.pending_open = false;
|
|
|
|
}
|
2012-09-28 20:58:36 +00:00
|
|
|
|
2015-03-03 01:21:35 +00:00
|
|
|
if (trace->current != thread) {
|
|
|
|
thread__put(trace->current);
|
|
|
|
trace->current = thread__get(thread);
|
|
|
|
}
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
2012-09-28 20:58:36 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
static int trace__resolve_callchain(struct trace *trace, struct perf_evsel *evsel,
|
|
|
|
struct perf_sample *sample,
|
|
|
|
struct callchain_cursor *cursor)
|
perf trace: Support callchains for --event too
We already were able to ask for callchains for a specific event:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
This would enable tracing just the "nanosleep" syscall, with callchains
at syscall exit and would ask the kernel for frame pointer callchains to
be enabled for the "sched:sched_switch" tracepoint event, its just that
we were not resolving the callchain and printing it in 'perf trace', do
it:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
0.425 ( 0.013 ms): usleep/6718 nanosleep(rqtp: 0x7ffcc1d16e20) ...
0.425 ( ): sched:sched_switch:usleep:6718 [120] S ==> swapper/2:0 [120])
__schedule+0xfe200402 ([kernel.kallsyms])
schedule+0xfe200035 ([kernel.kallsyms])
do_nanosleep+0xfe20006f ([kernel.kallsyms])
hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
sys_nanosleep+0xfe20007a ([kernel.kallsyms])
do_syscall_64+0xfe200062 ([kernel.kallsyms])
return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
__nanosleep+0xffff008b8cbe2010 (/usr/lib64/libc-2.22.so)
0.486 ( 0.073 ms): usleep/6718 ... [continued]: nanosleep()) = 0
__nanosleep+0x10 (/usr/lib64/libc-2.22.so)
usleep+0x34 (/usr/lib64/libc-2.22.so)
main+0x1eb (/usr/bin/usleep)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
_start+0x29 (/usr/bin/usleep)
#
Pretty compact, huh? DWARF callchains for raw_syscalls:sys_exit + frame
pointer callchains for a tracepoint, if your hardware supports LBR, go
wild with /call-graph=lbr/, guess the next step is to lift this from
'perf script':
-F, --fields <str> comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw.
Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,period,iregs,brstack,brstacksym,flags
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2e7yiv5hqdm8jywlmfivvx2v@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-12 13:11:07 +00:00
|
|
|
{
|
|
|
|
struct addr_location al;
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
|
|
|
|
if (machine__resolve(trace->host, &al, sample) < 0 ||
|
|
|
|
thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, trace->max_stack))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int trace__fprintf_callchain(struct trace *trace, struct perf_sample *sample)
|
|
|
|
{
|
perf trace: Support callchains for --event too
We already were able to ask for callchains for a specific event:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
This would enable tracing just the "nanosleep" syscall, with callchains
at syscall exit and would ask the kernel for frame pointer callchains to
be enabled for the "sched:sched_switch" tracepoint event, its just that
we were not resolving the callchain and printing it in 'perf trace', do
it:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
0.425 ( 0.013 ms): usleep/6718 nanosleep(rqtp: 0x7ffcc1d16e20) ...
0.425 ( ): sched:sched_switch:usleep:6718 [120] S ==> swapper/2:0 [120])
__schedule+0xfe200402 ([kernel.kallsyms])
schedule+0xfe200035 ([kernel.kallsyms])
do_nanosleep+0xfe20006f ([kernel.kallsyms])
hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
sys_nanosleep+0xfe20007a ([kernel.kallsyms])
do_syscall_64+0xfe200062 ([kernel.kallsyms])
return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
__nanosleep+0xffff008b8cbe2010 (/usr/lib64/libc-2.22.so)
0.486 ( 0.073 ms): usleep/6718 ... [continued]: nanosleep()) = 0
__nanosleep+0x10 (/usr/lib64/libc-2.22.so)
usleep+0x34 (/usr/lib64/libc-2.22.so)
main+0x1eb (/usr/bin/usleep)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
_start+0x29 (/usr/bin/usleep)
#
Pretty compact, huh? DWARF callchains for raw_syscalls:sys_exit + frame
pointer callchains for a tracepoint, if your hardware supports LBR, go
wild with /call-graph=lbr/, guess the next step is to lift this from
'perf script':
-F, --fields <str> comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw.
Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,period,iregs,brstack,brstacksym,flags
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2e7yiv5hqdm8jywlmfivvx2v@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-12 13:11:07 +00:00
|
|
|
/* TODO: user-configurable print_opts */
|
2016-04-12 18:16:15 +00:00
|
|
|
const unsigned int print_opts = EVSEL__PRINT_SYM |
|
|
|
|
EVSEL__PRINT_DSO |
|
|
|
|
EVSEL__PRINT_UNKNOWN_AS_ADDR;
|
perf trace: Support callchains for --event too
We already were able to ask for callchains for a specific event:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
This would enable tracing just the "nanosleep" syscall, with callchains
at syscall exit and would ask the kernel for frame pointer callchains to
be enabled for the "sched:sched_switch" tracepoint event, its just that
we were not resolving the callchain and printing it in 'perf trace', do
it:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
0.425 ( 0.013 ms): usleep/6718 nanosleep(rqtp: 0x7ffcc1d16e20) ...
0.425 ( ): sched:sched_switch:usleep:6718 [120] S ==> swapper/2:0 [120])
__schedule+0xfe200402 ([kernel.kallsyms])
schedule+0xfe200035 ([kernel.kallsyms])
do_nanosleep+0xfe20006f ([kernel.kallsyms])
hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
sys_nanosleep+0xfe20007a ([kernel.kallsyms])
do_syscall_64+0xfe200062 ([kernel.kallsyms])
return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
__nanosleep+0xffff008b8cbe2010 (/usr/lib64/libc-2.22.so)
0.486 ( 0.073 ms): usleep/6718 ... [continued]: nanosleep()) = 0
__nanosleep+0x10 (/usr/lib64/libc-2.22.so)
usleep+0x34 (/usr/lib64/libc-2.22.so)
main+0x1eb (/usr/bin/usleep)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
_start+0x29 (/usr/bin/usleep)
#
Pretty compact, huh? DWARF callchains for raw_syscalls:sys_exit + frame
pointer callchains for a tracepoint, if your hardware supports LBR, go
wild with /call-graph=lbr/, guess the next step is to lift this from
'perf script':
-F, --fields <str> comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw.
Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,period,iregs,brstack,brstacksym,flags
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2e7yiv5hqdm8jywlmfivvx2v@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-12 13:11:07 +00:00
|
|
|
|
2016-04-14 20:53:49 +00:00
|
|
|
return sample__fprintf_callchain(sample, 38, print_opts, &callchain_cursor, trace->output);
|
perf trace: Support callchains for --event too
We already were able to ask for callchains for a specific event:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
This would enable tracing just the "nanosleep" syscall, with callchains
at syscall exit and would ask the kernel for frame pointer callchains to
be enabled for the "sched:sched_switch" tracepoint event, its just that
we were not resolving the callchain and printing it in 'perf trace', do
it:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
0.425 ( 0.013 ms): usleep/6718 nanosleep(rqtp: 0x7ffcc1d16e20) ...
0.425 ( ): sched:sched_switch:usleep:6718 [120] S ==> swapper/2:0 [120])
__schedule+0xfe200402 ([kernel.kallsyms])
schedule+0xfe200035 ([kernel.kallsyms])
do_nanosleep+0xfe20006f ([kernel.kallsyms])
hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
sys_nanosleep+0xfe20007a ([kernel.kallsyms])
do_syscall_64+0xfe200062 ([kernel.kallsyms])
return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
__nanosleep+0xffff008b8cbe2010 (/usr/lib64/libc-2.22.so)
0.486 ( 0.073 ms): usleep/6718 ... [continued]: nanosleep()) = 0
__nanosleep+0x10 (/usr/lib64/libc-2.22.so)
usleep+0x34 (/usr/lib64/libc-2.22.so)
main+0x1eb (/usr/bin/usleep)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
_start+0x29 (/usr/bin/usleep)
#
Pretty compact, huh? DWARF callchains for raw_syscalls:sys_exit + frame
pointer callchains for a tracepoint, if your hardware supports LBR, go
wild with /call-graph=lbr/, guess the next step is to lift this from
'perf script':
-F, --fields <str> comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw.
Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,period,iregs,brstack,brstacksym,flags
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2e7yiv5hqdm8jywlmfivvx2v@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-12 13:11:07 +00:00
|
|
|
}
|
|
|
|
|
2012-09-28 20:58:36 +00:00
|
|
|
static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 16:14:24 +00:00
|
|
|
union perf_event *event __maybe_unused,
|
2012-09-28 20:58:36 +00:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
2014-09-26 12:54:01 +00:00
|
|
|
long ret;
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
u64 duration = 0;
|
2017-03-29 19:37:51 +00:00
|
|
|
bool duration_calculated = false;
|
2013-08-09 15:28:31 +00:00
|
|
|
struct thread *thread;
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0;
|
2013-10-09 03:26:53 +00:00
|
|
|
struct syscall *sc = trace__syscall_info(trace, evsel, id);
|
2013-08-09 15:28:31 +00:00
|
|
|
struct thread_trace *ttrace;
|
|
|
|
|
|
|
|
if (sc == NULL)
|
|
|
|
return -1;
|
2012-09-28 20:58:36 +00:00
|
|
|
|
2013-09-28 19:13:00 +00:00
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2013-08-19 15:01:10 +00:00
|
|
|
ttrace = thread__trace(thread, trace->output);
|
2013-08-09 15:28:31 +00:00
|
|
|
if (ttrace == NULL)
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
goto out_put;
|
2012-09-28 20:58:36 +00:00
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
if (trace->summary)
|
|
|
|
thread__update_stats(ttrace, id, sample);
|
|
|
|
|
perf trace: Don't relookup fields by name in each sample
Instead do the lookups just when creating the tracepoints, initially for
the most common, raw_syscalls:sys_{enter,exit}.
It works by having evsel->priv have a per tracepoint structure with
entries for the fields, for direct access, with the offset and a
function to get the value from the sample, doing the swap if needed.
Using a simple workload that does M millions write syscalls, we go from:
# perf stat -i -e cycles /tmp/oldperf trace ./sc_hello 100 > /dev/null
Performance counter stats for '/tmp/oldperf trace ./sc_hello 100':
8,366,771,459 cycles
2.668025928 seconds time elapsed
# perf stat -i -e cycles perf trace ./sc_hello 100 > /dev/null
Performance counter stats for 'perf trace ./sc_hello 100':
8,345,187,650 cycles
2.631748425 seconds time elapsed
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-eyfhvoo510a5i10b27dnvm88@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-11-06 19:35:57 +00:00
|
|
|
ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
|
2012-09-28 20:58:36 +00:00
|
|
|
|
2016-04-04 16:32:20 +00:00
|
|
|
if (id == trace->open_id && ret >= 0 && ttrace->filename.pending_open) {
|
2015-08-14 16:16:27 +00:00
|
|
|
trace__set_fd_pathname(thread, ret, ttrace->filename.name);
|
|
|
|
ttrace->filename.pending_open = false;
|
2013-09-27 21:06:19 +00:00
|
|
|
++trace->stats.vfs_getname;
|
|
|
|
}
|
|
|
|
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
if (ttrace->entry_time) {
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
duration = sample->time - ttrace->entry_time;
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
if (trace__filter_duration(trace, duration))
|
|
|
|
goto out;
|
2017-03-29 19:37:51 +00:00
|
|
|
duration_calculated = true;
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
} else if (trace->duration_filter)
|
|
|
|
goto out;
|
perf trace: Add an event duration column
# perf trace usleep 1 | tail -10
0.453 ( 0.002 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763342848
0.456 ( 0.001 ms): mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -763346944
0.459 ( 0.001 ms): arch_prctl(option: 4098, arg2: 140126839658240, arg3: 140126839652352, arg4: 34, arg5: 4294967295) = 0
0.473 ( 0.003 ms): mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
0.477 ( 0.003 ms): mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
0.483 ( 0.004 ms): munmap(addr: 140126839664640, len: 91882 ) = 0
0.540 ( 0.001 ms): brk(brk: 0 ) = 31928320
0.542 ( 0.002 ms): brk(brk: 32063488 ) = 32063488
1.456 ( 0.901 ms): nanosleep(rqtp: 140735472817168, rmtp: 0 ) = 0
1.462 ( 0.000 ms): exit_group(error_code: 0
#
This also comes from the tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-g9akh5hjw2kvjerpo9xror6f@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-24 19:24:47 +00:00
|
|
|
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
if (sample->callchain) {
|
|
|
|
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
|
|
|
|
if (callchain_ret == 0) {
|
|
|
|
if (callchain_cursor.nr < trace->min_stack)
|
|
|
|
goto out;
|
|
|
|
callchain_ret = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-11-12 16:31:15 +00:00
|
|
|
if (trace->summary_only)
|
|
|
|
goto out;
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
trace__fprintf_entry_head(trace, thread, duration, duration_calculated, ttrace->entry_time, trace->output);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
|
|
|
|
if (ttrace->entry_pending) {
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, "%-70s", ttrace->entry_str);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
} else {
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, " ... [");
|
|
|
|
color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
|
|
|
|
fprintf(trace->output, "]: %s()", sc->name);
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
}
|
|
|
|
|
2013-08-26 14:28:34 +00:00
|
|
|
if (sc->fmt == NULL) {
|
|
|
|
signed_print:
|
2014-09-26 12:54:01 +00:00
|
|
|
fprintf(trace->output, ") = %ld", ret);
|
perf trace: Infrastructure to show COMM strings for syscalls returning PIDs
Starting with clone, waitid and wait4:
# trace -e waitid,wait4
1.385 ( 1.385 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) = 1210 (ls)
1.426 ( 0.002 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1150, options: NOHANG|UNTRACED|CONTINUED) = 0
3.293 ( 0.604 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee0560 ) = 1214 (sed)
3.342 ( 0.002 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee01d0, options: NOHANG ) = -1 ECHILD No child processes
3.576 ( 0.016 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee0550, options: NOHANG|UNTRACED|CONTINUED) = 1211 (bash)
^C# trace -e clone
0.027 ( 0.000 ms): systemd/1 ... [continued]: clone()) = 1227 (systemd)
0.050 ( 0.000 ms): systemd/1227 ... [continued]: clone()) = 0
^C[root@jouet ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lyf5d3y5j15wikjb6pe6ukoi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 17:33:07 +00:00
|
|
|
} else if (ret < 0 && (sc->fmt->errmsg || sc->fmt->errpid)) {
|
2014-08-14 02:22:41 +00:00
|
|
|
char bf[STRERR_BUFSIZE];
|
tools: Introduce str_error_r()
The tools so far have been using the strerror_r() GNU variant, that
returns a string, be it the buffer passed or something else.
But that, besides being tricky in cases where we expect that the
function using strerror_r() returns the error formatted in a provided
buffer (we have to check if it returned something else and copy that
instead), breaks the build on systems not using glibc, like Alpine
Linux, where musl libc is used.
So, introduce yet another wrapper, str_error_r(), that has the GNU
interface, but uses the portable XSI variant of strerror_r(), so that
users rest asured that the provided buffer is used and it is what is
returned.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-d4t42fnf48ytlk8rjxs822tf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-06 14:56:20 +00:00
|
|
|
const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
|
2012-09-28 20:58:36 +00:00
|
|
|
*e = audit_errno_to_name(-ret);
|
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, ") = -1 %s %s", e, emsg);
|
2013-08-26 14:28:34 +00:00
|
|
|
} else if (ret == 0 && sc->fmt->timeout)
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, ") = 0 Timeout");
|
2013-08-26 14:36:30 +00:00
|
|
|
else if (sc->fmt->hexret)
|
2014-09-26 12:54:01 +00:00
|
|
|
fprintf(trace->output, ") = %#lx", ret);
|
perf trace: Infrastructure to show COMM strings for syscalls returning PIDs
Starting with clone, waitid and wait4:
# trace -e waitid,wait4
1.385 ( 1.385 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1720, options: UNTRACED|CONTINUED) = 1210 (ls)
1.426 ( 0.002 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee1150, options: NOHANG|UNTRACED|CONTINUED) = 0
3.293 ( 0.604 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee0560 ) = 1214 (sed)
3.342 ( 0.002 ms): bash/1211 wait4(upid: -1, stat_addr: 0x7ffe0cee01d0, options: NOHANG ) = -1 ECHILD No child processes
3.576 ( 0.016 ms): bash/12122 wait4(upid: -1, stat_addr: 0x7ffe0cee0550, options: NOHANG|UNTRACED|CONTINUED) = 1211 (bash)
^C# trace -e clone
0.027 ( 0.000 ms): systemd/1 ... [continued]: clone()) = 1227 (systemd)
0.050 ( 0.000 ms): systemd/1227 ... [continued]: clone()) = 0
^C[root@jouet ~]#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-lyf5d3y5j15wikjb6pe6ukoi@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-06 17:33:07 +00:00
|
|
|
else if (sc->fmt->errpid) {
|
|
|
|
struct thread *child = machine__find_thread(trace->host, ret, ret);
|
|
|
|
|
|
|
|
if (child != NULL) {
|
|
|
|
fprintf(trace->output, ") = %ld", ret);
|
|
|
|
if (child->comm_set)
|
|
|
|
fprintf(trace->output, " (%s)", thread__comm_str(child));
|
|
|
|
thread__put(child);
|
|
|
|
}
|
|
|
|
} else
|
2013-08-26 14:28:34 +00:00
|
|
|
goto signed_print;
|
2012-09-28 20:58:36 +00:00
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
fputc('\n', trace->output);
|
2016-04-08 11:34:15 +00:00
|
|
|
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
if (callchain_ret > 0)
|
|
|
|
trace__fprintf_callchain(trace, sample);
|
|
|
|
else if (callchain_ret < 0)
|
|
|
|
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
out:
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
ttrace->entry_pending = false;
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
2012-09-28 20:58:36 +00:00
|
|
|
}
|
|
|
|
|
2013-09-27 21:06:19 +00:00
|
|
|
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 16:14:24 +00:00
|
|
|
union perf_event *event __maybe_unused,
|
2013-09-27 21:06:19 +00:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
struct thread *thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
|
|
|
struct thread_trace *ttrace;
|
|
|
|
size_t filename_len, entry_str_len, to_move;
|
|
|
|
ssize_t remaining_space;
|
|
|
|
char *pos;
|
2015-08-14 16:16:27 +00:00
|
|
|
const char *filename = perf_evsel__rawptr(evsel, sample, "pathname");
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
|
|
|
|
if (!thread)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ttrace = thread__priv(thread);
|
|
|
|
if (!ttrace)
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out_put;
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
|
2015-08-14 16:16:27 +00:00
|
|
|
filename_len = strlen(filename);
|
2017-03-24 17:51:28 +00:00
|
|
|
if (filename_len == 0)
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out_put;
|
2015-08-14 16:16:27 +00:00
|
|
|
|
|
|
|
if (ttrace->filename.namelen < filename_len) {
|
|
|
|
char *f = realloc(ttrace->filename.name, filename_len + 1);
|
|
|
|
|
|
|
|
if (f == NULL)
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out_put;
|
2015-08-14 16:16:27 +00:00
|
|
|
|
|
|
|
ttrace->filename.namelen = filename_len;
|
|
|
|
ttrace->filename.name = f;
|
|
|
|
}
|
|
|
|
|
|
|
|
strcpy(ttrace->filename.name, filename);
|
|
|
|
ttrace->filename.pending_open = true;
|
|
|
|
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
if (!ttrace->filename.ptr)
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out_put;
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
|
|
|
|
entry_str_len = strlen(ttrace->entry_str);
|
|
|
|
remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
|
|
|
|
if (remaining_space <= 0)
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out_put;
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
|
|
|
|
if (filename_len > (size_t)remaining_space) {
|
|
|
|
filename += filename_len - remaining_space;
|
|
|
|
filename_len = remaining_space;
|
|
|
|
}
|
|
|
|
|
|
|
|
to_move = entry_str_len - ttrace->filename.entry_str_pos + 1; /* \0 */
|
|
|
|
pos = ttrace->entry_str + ttrace->filename.entry_str_pos;
|
|
|
|
memmove(pos + filename_len, pos, to_move);
|
|
|
|
memcpy(pos, filename, filename_len);
|
|
|
|
|
|
|
|
ttrace->filename.ptr = 0;
|
|
|
|
ttrace->filename.entry_str_pos = 0;
|
2017-03-24 18:03:19 +00:00
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
perf trace: Deref sys_enter pointer args with contents from probe:vfs_getname
To work like strace and dereference syscall pointer args we need to
insert probes (or tracepoints) right after we copy those bytes from
userspace.
Since we're formatting the syscall args at raw_syscalls:sys_enter time,
we need to have a formatter that just stores the position where, later,
when we get the probe:vfs_getname, we can insert the pointer contents.
Now, if a probe:vfs_getname with this format is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:72@/home/git/linux/fs/namei.c with pathname)
That was, in this case, put in place with:
# perf probe 'vfs_getname=getname_flags:72 pathname=filename:string'
Added new event:
probe:vfs_getname (on getname_flags:72 with pathname=filename:string)
You can now use it in all perf tools, such as:
perf record -e probe:vfs_getname -aR sleep 1
#
Then 'perf trace' will notice that and do the pointer -> contents
expansion:
# trace -e open touch /tmp/bla
0.165 (0.010 ms): touch/17752 open(filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.195 (0.011 ms): touch/17752 open(filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.512 (0.012 ms): touch/17752 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.582 (0.012 ms): touch/17752 open(filename: /tmp/bla, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: 438) = 3
#
Roughly equivalent to strace's output:
# strace -rT -e open touch /tmp/bla
0.000000 open("/etc/ld.so.cache", O_RDONLY|O_CLOEXEC) = 3 <0.000039>
0.000317 open("/lib64/libc.so.6", O_RDONLY|O_CLOEXEC) = 3 <0.000102>
0.001461 open("/usr/lib/locale/locale-archive", O_RDONLY|O_CLOEXEC) = 3 <0.000072>
0.000405 open("/tmp/bla", O_WRONLY|O_CREAT|O_NOCTTY|O_NONBLOCK, 0666) = 3 <0.000055>
0.000641 +++ exited with 0 +++
#
Now we need to either look for at all syscalls that are marked as
pointers and have some well known names ("filename", "pathname", etc)
and set the arg formatter to the one used for the "open" syscall in this
patch.
This implementation works for syscalls with just a string being copied
from userspace, for matching syscalls with more than one string being
copied via the same probe/trace point (vfs_getname) we need to extend
the vfs_getname probe spec to include the pointer too, but there are
some problems with that in 'perf probe' or the kernel kprobes code, need
to investigate before considering supporting multiple strings per
syscall.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Milian Wolff <mail@milianw.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-xvuwx6nuj8cf389kf9s2ue2s@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-08-05 01:30:09 +00:00
|
|
|
out:
|
2013-09-27 21:06:19 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-10-17 20:13:12 +00:00
|
|
|
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 16:14:24 +00:00
|
|
|
union perf_event *event __maybe_unused,
|
2012-10-17 20:13:12 +00:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
|
|
|
|
double runtime_ms = (double)runtime / NSEC_PER_MSEC;
|
2013-09-28 19:13:00 +00:00
|
|
|
struct thread *thread = machine__findnew_thread(trace->host,
|
2013-08-27 08:23:03 +00:00
|
|
|
sample->pid,
|
|
|
|
sample->tid);
|
2013-08-19 15:01:10 +00:00
|
|
|
struct thread_trace *ttrace = thread__trace(thread, trace->output);
|
2012-10-17 20:13:12 +00:00
|
|
|
|
|
|
|
if (ttrace == NULL)
|
|
|
|
goto out_dump;
|
|
|
|
|
|
|
|
ttrace->runtime_ms += runtime_ms;
|
|
|
|
trace->runtime_ms += runtime_ms;
|
2017-03-24 18:03:19 +00:00
|
|
|
out_put:
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
thread__put(thread);
|
2012-10-17 20:13:12 +00:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_dump:
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
|
2012-10-17 20:13:12 +00:00
|
|
|
evsel->name,
|
|
|
|
perf_evsel__strval(evsel, sample, "comm"),
|
|
|
|
(pid_t)perf_evsel__intval(evsel, sample, "pid"),
|
|
|
|
runtime,
|
|
|
|
perf_evsel__intval(evsel, sample, "vruntime"));
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out_put;
|
2012-10-17 20:13:12 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Print content of bpf-output event
With this patch the contend of BPF output event is printed by
'perf trace'. For example:
# ./perf trace -a --ev bpf-output/no-inherit,name=evt/ \
--ev ./test_bpf_trace.c/map:channel.event=evt/ \
usleep 100000
...
1.787 ( 0.004 ms): usleep/3832 nanosleep(rqtp: 0x7ffc78b18980 ) ...
1.787 ( ): evt:Raise a BPF event!..)
1.788 ( ): perf_bpf_probe:func_begin:(ffffffff810e97d0))
...
101.866 (87.038 ms): gmain/1654 poll(ufds: 0x7f57a80008c0, nfds: 2, timeout_msecs: 1000 ) ...
101.866 ( ): evt:Raise a BPF event!..)
101.867 ( ): perf_bpf_probe:func_end:(ffffffff810e97d0 <- ffffffff81796173))
101.869 (100.087 ms): usleep/3832 ... [continued]: nanosleep()) = 0
...
(There is an extra ')' at the end of several lines. However, it is
another problem, unrelated to this commit.)
Where test_bpf_trace.c is:
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
#define SEC(NAME) __attribute__((section(NAME), used))
static u64 (*ktime_get_ns)(void) =
(void *)BPF_FUNC_ktime_get_ns;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
static int (*get_smp_processor_id)(void) =
(void *)BPF_FUNC_get_smp_processor_id;
static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
(void *)BPF_FUNC_perf_event_output;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
static inline int __attribute__((always_inline))
func(void *ctx, int type)
{
char output_str[] = "Raise a BPF event!";
char err_str[] = "BAD %d\n";
int err;
err = perf_event_output(ctx, &channel, get_smp_processor_id(),
&output_str, sizeof(output_str));
if (err)
trace_printk(err_str, sizeof(err_str), err);
return 1;
}
SEC("func_begin=sys_nanosleep")
int func_begin(void *ctx) {return func(ctx, 1);}
SEC("func_end=sys_nanosleep%return")
int func_end(void *ctx) { return func(ctx, 2);}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456479154-136027-8-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-26 09:31:55 +00:00
|
|
|
static void bpf_output__printer(enum binary_printer_ops op,
|
|
|
|
unsigned int val, void *extra)
|
|
|
|
{
|
|
|
|
FILE *output = extra;
|
|
|
|
unsigned char ch = (unsigned char)val;
|
|
|
|
|
|
|
|
switch (op) {
|
|
|
|
case BINARY_PRINT_CHAR_DATA:
|
|
|
|
fprintf(output, "%c", isprint(ch) ? ch : '.');
|
|
|
|
break;
|
|
|
|
case BINARY_PRINT_DATA_BEGIN:
|
|
|
|
case BINARY_PRINT_LINE_BEGIN:
|
|
|
|
case BINARY_PRINT_ADDR:
|
|
|
|
case BINARY_PRINT_NUM_DATA:
|
|
|
|
case BINARY_PRINT_NUM_PAD:
|
|
|
|
case BINARY_PRINT_SEP:
|
|
|
|
case BINARY_PRINT_CHAR_PAD:
|
|
|
|
case BINARY_PRINT_LINE_END:
|
|
|
|
case BINARY_PRINT_DATA_END:
|
|
|
|
default:
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void bpf_output__fprintf(struct trace *trace,
|
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
print_binary(sample->raw_data, sample->raw_size, 8,
|
|
|
|
bpf_output__printer, trace->output);
|
|
|
|
}
|
|
|
|
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
|
|
|
|
union perf_event *event __maybe_unused,
|
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
2016-04-20 22:55:48 +00:00
|
|
|
int callchain_ret = 0;
|
|
|
|
|
|
|
|
if (sample->callchain) {
|
|
|
|
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
|
|
|
|
if (callchain_ret == 0) {
|
|
|
|
if (callchain_cursor.nr < trace->min_stack)
|
|
|
|
goto out;
|
|
|
|
callchain_ret = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
trace__printf_interrupted_entry(trace, sample);
|
|
|
|
trace__fprintf_tstamp(trace, sample->time, trace->output);
|
2015-02-20 05:51:50 +00:00
|
|
|
|
|
|
|
if (trace->trace_syscalls)
|
|
|
|
fprintf(trace->output, "( ): ");
|
|
|
|
|
|
|
|
fprintf(trace->output, "%s:", evsel->name);
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
|
perf trace: Print content of bpf-output event
With this patch the contend of BPF output event is printed by
'perf trace'. For example:
# ./perf trace -a --ev bpf-output/no-inherit,name=evt/ \
--ev ./test_bpf_trace.c/map:channel.event=evt/ \
usleep 100000
...
1.787 ( 0.004 ms): usleep/3832 nanosleep(rqtp: 0x7ffc78b18980 ) ...
1.787 ( ): evt:Raise a BPF event!..)
1.788 ( ): perf_bpf_probe:func_begin:(ffffffff810e97d0))
...
101.866 (87.038 ms): gmain/1654 poll(ufds: 0x7f57a80008c0, nfds: 2, timeout_msecs: 1000 ) ...
101.866 ( ): evt:Raise a BPF event!..)
101.867 ( ): perf_bpf_probe:func_end:(ffffffff810e97d0 <- ffffffff81796173))
101.869 (100.087 ms): usleep/3832 ... [continued]: nanosleep()) = 0
...
(There is an extra ')' at the end of several lines. However, it is
another problem, unrelated to this commit.)
Where test_bpf_trace.c is:
/************************ BEGIN **************************/
#include <uapi/linux/bpf.h>
struct bpf_map_def {
unsigned int type;
unsigned int key_size;
unsigned int value_size;
unsigned int max_entries;
};
#define SEC(NAME) __attribute__((section(NAME), used))
static u64 (*ktime_get_ns)(void) =
(void *)BPF_FUNC_ktime_get_ns;
static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
(void *)BPF_FUNC_trace_printk;
static int (*get_smp_processor_id)(void) =
(void *)BPF_FUNC_get_smp_processor_id;
static int (*perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
(void *)BPF_FUNC_perf_event_output;
struct bpf_map_def SEC("maps") channel = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
static inline int __attribute__((always_inline))
func(void *ctx, int type)
{
char output_str[] = "Raise a BPF event!";
char err_str[] = "BAD %d\n";
int err;
err = perf_event_output(ctx, &channel, get_smp_processor_id(),
&output_str, sizeof(output_str));
if (err)
trace_printk(err_str, sizeof(err_str), err);
return 1;
}
SEC("func_begin=sys_nanosleep")
int func_begin(void *ctx) {return func(ctx, 1);}
SEC("func_end=sys_nanosleep%return")
int func_end(void *ctx) { return func(ctx, 2);}
char _license[] SEC("license") = "GPL";
int _version SEC("version") = LINUX_VERSION_CODE;
/************************* END ***************************/
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456479154-136027-8-git-send-email-wangnan0@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-26 09:31:55 +00:00
|
|
|
if (perf_evsel__is_bpf_output(evsel)) {
|
|
|
|
bpf_output__fprintf(trace, sample);
|
|
|
|
} else if (evsel->tp_format) {
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
event_format__fprintf(evsel->tp_format, sample->cpu,
|
|
|
|
sample->raw_data, sample->raw_size,
|
|
|
|
trace->output);
|
|
|
|
}
|
|
|
|
|
|
|
|
fprintf(trace->output, ")\n");
|
perf trace: Support callchains for --event too
We already were able to ask for callchains for a specific event:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
This would enable tracing just the "nanosleep" syscall, with callchains
at syscall exit and would ask the kernel for frame pointer callchains to
be enabled for the "sched:sched_switch" tracepoint event, its just that
we were not resolving the callchain and printing it in 'perf trace', do
it:
# trace -e nanosleep --call dwarf --event sched:sched_switch/call-graph=fp/ usleep 1
0.425 ( 0.013 ms): usleep/6718 nanosleep(rqtp: 0x7ffcc1d16e20) ...
0.425 ( ): sched:sched_switch:usleep:6718 [120] S ==> swapper/2:0 [120])
__schedule+0xfe200402 ([kernel.kallsyms])
schedule+0xfe200035 ([kernel.kallsyms])
do_nanosleep+0xfe20006f ([kernel.kallsyms])
hrtimer_nanosleep+0xfe2000dc ([kernel.kallsyms])
sys_nanosleep+0xfe20007a ([kernel.kallsyms])
do_syscall_64+0xfe200062 ([kernel.kallsyms])
return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms])
__nanosleep+0xffff008b8cbe2010 (/usr/lib64/libc-2.22.so)
0.486 ( 0.073 ms): usleep/6718 ... [continued]: nanosleep()) = 0
__nanosleep+0x10 (/usr/lib64/libc-2.22.so)
usleep+0x34 (/usr/lib64/libc-2.22.so)
main+0x1eb (/usr/bin/usleep)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
_start+0x29 (/usr/bin/usleep)
#
Pretty compact, huh? DWARF callchains for raw_syscalls:sys_exit + frame
pointer callchains for a tracepoint, if your hardware supports LBR, go
wild with /call-graph=lbr/, guess the next step is to lift this from
'perf script':
-F, --fields <str> comma separated output fields prepend with 'type:'. Valid types: hw,sw,trace,raw.
Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,addr,symoff,period,iregs,brstack,brstacksym,flags
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-2e7yiv5hqdm8jywlmfivvx2v@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-12 13:11:07 +00:00
|
|
|
|
2016-04-20 22:55:48 +00:00
|
|
|
if (callchain_ret > 0)
|
|
|
|
trace__fprintf_callchain(trace, sample);
|
|
|
|
else if (callchain_ret < 0)
|
|
|
|
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
|
|
|
|
out:
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-06-26 16:14:25 +00:00
|
|
|
static void print_location(FILE *f, struct perf_sample *sample,
|
|
|
|
struct addr_location *al,
|
|
|
|
bool print_dso, bool print_sym)
|
|
|
|
{
|
|
|
|
|
2017-02-17 08:17:38 +00:00
|
|
|
if ((verbose > 0 || print_dso) && al->map)
|
2014-06-26 16:14:25 +00:00
|
|
|
fprintf(f, "%s@", al->map->dso->long_name);
|
|
|
|
|
2017-02-17 08:17:38 +00:00
|
|
|
if ((verbose > 0 || print_sym) && al->sym)
|
2014-07-08 18:39:21 +00:00
|
|
|
fprintf(f, "%s+0x%" PRIx64, al->sym->name,
|
2014-06-26 16:14:25 +00:00
|
|
|
al->addr - al->sym->start);
|
|
|
|
else if (al->map)
|
2014-07-08 18:39:21 +00:00
|
|
|
fprintf(f, "0x%" PRIx64, al->addr);
|
2014-06-26 16:14:25 +00:00
|
|
|
else
|
2014-07-08 18:39:21 +00:00
|
|
|
fprintf(f, "0x%" PRIx64, sample->addr);
|
2014-06-26 16:14:25 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static int trace__pgfault(struct trace *trace,
|
|
|
|
struct perf_evsel *evsel,
|
2016-03-22 21:23:43 +00:00
|
|
|
union perf_event *event __maybe_unused,
|
2014-06-26 16:14:25 +00:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
struct thread *thread;
|
|
|
|
struct addr_location al;
|
|
|
|
char map_type = 'd';
|
2014-07-08 18:05:16 +00:00
|
|
|
struct thread_trace *ttrace;
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
int err = -1;
|
2016-04-20 23:06:02 +00:00
|
|
|
int callchain_ret = 0;
|
2014-06-26 16:14:25 +00:00
|
|
|
|
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2016-04-20 23:06:02 +00:00
|
|
|
|
|
|
|
if (sample->callchain) {
|
|
|
|
callchain_ret = trace__resolve_callchain(trace, evsel, sample, &callchain_cursor);
|
|
|
|
if (callchain_ret == 0) {
|
|
|
|
if (callchain_cursor.nr < trace->min_stack)
|
|
|
|
goto out_put;
|
|
|
|
callchain_ret = 1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-07-08 18:05:16 +00:00
|
|
|
ttrace = thread__trace(thread, trace->output);
|
|
|
|
if (ttrace == NULL)
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
goto out_put;
|
2014-07-08 18:05:16 +00:00
|
|
|
|
|
|
|
if (evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ)
|
|
|
|
ttrace->pfmaj++;
|
|
|
|
else
|
|
|
|
ttrace->pfmin++;
|
|
|
|
|
|
|
|
if (trace->summary_only)
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
goto out;
|
2014-06-26 16:14:25 +00:00
|
|
|
|
2016-03-22 21:23:43 +00:00
|
|
|
thread__find_addr_location(thread, sample->cpumode, MAP__FUNCTION,
|
2014-06-26 16:14:25 +00:00
|
|
|
sample->ip, &al);
|
|
|
|
|
2017-03-29 19:37:51 +00:00
|
|
|
trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
|
2014-06-26 16:14:25 +00:00
|
|
|
|
|
|
|
fprintf(trace->output, "%sfault [",
|
|
|
|
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ?
|
|
|
|
"maj" : "min");
|
|
|
|
|
|
|
|
print_location(trace->output, sample, &al, false, true);
|
|
|
|
|
|
|
|
fprintf(trace->output, "] => ");
|
|
|
|
|
2016-03-22 21:23:43 +00:00
|
|
|
thread__find_addr_location(thread, sample->cpumode, MAP__VARIABLE,
|
2014-06-26 16:14:25 +00:00
|
|
|
sample->addr, &al);
|
|
|
|
|
|
|
|
if (!al.map) {
|
2016-03-22 21:23:43 +00:00
|
|
|
thread__find_addr_location(thread, sample->cpumode,
|
2014-06-26 16:14:25 +00:00
|
|
|
MAP__FUNCTION, sample->addr, &al);
|
|
|
|
|
|
|
|
if (al.map)
|
|
|
|
map_type = 'x';
|
|
|
|
else
|
|
|
|
map_type = '?';
|
|
|
|
}
|
|
|
|
|
|
|
|
print_location(trace->output, sample, &al, true, false);
|
|
|
|
|
|
|
|
fprintf(trace->output, " (%c%c)\n", map_type, al.level);
|
2016-04-19 19:31:12 +00:00
|
|
|
|
2016-04-20 23:06:02 +00:00
|
|
|
if (callchain_ret > 0)
|
|
|
|
trace__fprintf_callchain(trace, sample);
|
|
|
|
else if (callchain_ret < 0)
|
|
|
|
pr_err("Problem processing %s callchain, skipping...\n", perf_evsel__name(evsel));
|
perf machine: Protect the machine->threads with a rwlock
In addition to using refcounts for the struct thread lifetime
management, we need to protect access to machine->threads from
concurrent access.
That happens in 'perf top', where a thread processes events, inserting
and deleting entries from that rb_tree while another thread decays
hist_entries, that end up dropping references and ultimately deleting
threads from the rb_tree and releasing its resources when no further
hist_entry (or other data structures, like in 'perf sched') references
it.
So the rule is the same for refcounts + protected trees in the kernel,
get the tree lock, find object, bump the refcount, drop the tree lock,
return, use object, drop the refcount if no more use of it is needed,
keep it if storing it in some other data structure, drop when releasing
that data structure.
I.e. pair "t = machine__find(new)_thread()" with a "thread__put(t)", and
"perf_event__preprocess_sample(&al)" with "addr_location__put(&al)".
The addr_location__put() one is because as we return references to
several data structures, we may end up adding more reference counting
for the other data structures and then we'll drop it at
addr_location__put() time.
Acked-by: David Ahern <dsahern@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-bs9rt4n0jw3hi9f3zxyy3xln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-06 23:43:22 +00:00
|
|
|
out:
|
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
2014-06-26 16:14:25 +00:00
|
|
|
}
|
|
|
|
|
2016-03-31 18:16:28 +00:00
|
|
|
static void trace__set_base_time(struct trace *trace,
|
perf trace: Don't set the base timestamp using events without PERF_SAMPLE_TIME
This was causing bogus values to be shown at the timestamp column:
Before:
# trace --ev bpf-output/no-inherit,name=evt/ --ev /home/acme/bpf/test_bpf_trace.c/map:channel.event=evt/ usleep 10
94631143.385 ( 0.001 ms): brk( ) = 0x555555757000
94631143.398 ( 0.003 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1) = 0x7ffff7ff6000
94631143.406 ( 0.004 ms): access(filename: 0xf7df9e10, mode: R ) = -1 ENOENT No such file or directory
94631143.412 ( 0.004 ms): open(filename: 0xf7df8761, flags: CLOEXEC) = 3
94631143.415 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fffffffd6b0 ) = 0
94631143.419 ( 0.003 ms): mmap(len: 106798, prot: READ, flags: PRIVATE, fd: 3) = 0x7ffff7fdb000
94631143.420 ( 0.001 ms): close(fd: 3 ) = 0
94631143.432 ( 0.004 ms): open(filename: 0xf7ff6640, flags: CLOEXEC) = 3
<SNIP>
After:
# trace --ev bpf-output/no-inherit,name=evt/ --ev /home/acme/bpf/test_bpf_trace.c/map:channel.event=evt/ usleep 10
0.022 ( 0.001 ms): brk( ) = 0x55d7668a6000
0.037 ( 0.003 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1) = 0x7f8fbeb97000
0.123 ( 0.083 ms): access(filename: 0xbe995e10, mode: R ) = -1 ENOENT No such file or directory
0.130 ( 0.004 ms): open(filename: 0xbe994761, flags: CLOEXEC) = 3
0.133 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fff6487a890 ) = 0
0.138 ( 0.003 ms): mmap(len: 106798, prot: READ, flags: PRIVATE, fd: 3) = 0x7f8fbeb7c000
0.140 ( 0.001 ms): close(fd: 3 ) = 0
0.151 ( 0.004 ms): open(filename: 0xbeb97640, flags: CLOEXEC) = 3
<SNIP>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-p7m8llv81iv55ekxexdp5n57@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-31 18:19:39 +00:00
|
|
|
struct perf_evsel *evsel,
|
2016-03-31 18:16:28 +00:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
perf trace: Don't set the base timestamp using events without PERF_SAMPLE_TIME
This was causing bogus values to be shown at the timestamp column:
Before:
# trace --ev bpf-output/no-inherit,name=evt/ --ev /home/acme/bpf/test_bpf_trace.c/map:channel.event=evt/ usleep 10
94631143.385 ( 0.001 ms): brk( ) = 0x555555757000
94631143.398 ( 0.003 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1) = 0x7ffff7ff6000
94631143.406 ( 0.004 ms): access(filename: 0xf7df9e10, mode: R ) = -1 ENOENT No such file or directory
94631143.412 ( 0.004 ms): open(filename: 0xf7df8761, flags: CLOEXEC) = 3
94631143.415 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fffffffd6b0 ) = 0
94631143.419 ( 0.003 ms): mmap(len: 106798, prot: READ, flags: PRIVATE, fd: 3) = 0x7ffff7fdb000
94631143.420 ( 0.001 ms): close(fd: 3 ) = 0
94631143.432 ( 0.004 ms): open(filename: 0xf7ff6640, flags: CLOEXEC) = 3
<SNIP>
After:
# trace --ev bpf-output/no-inherit,name=evt/ --ev /home/acme/bpf/test_bpf_trace.c/map:channel.event=evt/ usleep 10
0.022 ( 0.001 ms): brk( ) = 0x55d7668a6000
0.037 ( 0.003 ms): mmap(len: 4096, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS, fd: -1) = 0x7f8fbeb97000
0.123 ( 0.083 ms): access(filename: 0xbe995e10, mode: R ) = -1 ENOENT No such file or directory
0.130 ( 0.004 ms): open(filename: 0xbe994761, flags: CLOEXEC) = 3
0.133 ( 0.002 ms): fstat(fd: 3, statbuf: 0x7fff6487a890 ) = 0
0.138 ( 0.003 ms): mmap(len: 106798, prot: READ, flags: PRIVATE, fd: 3) = 0x7f8fbeb7c000
0.140 ( 0.001 ms): close(fd: 3 ) = 0
0.151 ( 0.004 ms): open(filename: 0xbeb97640, flags: CLOEXEC) = 3
<SNIP>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-p7m8llv81iv55ekxexdp5n57@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-03-31 18:19:39 +00:00
|
|
|
/*
|
|
|
|
* BPF events were not setting PERF_SAMPLE_TIME, so be more robust
|
|
|
|
* and don't use sample->time unconditionally, we may end up having
|
|
|
|
* some other event in the future without PERF_SAMPLE_TIME for good
|
|
|
|
* reason, i.e. we may not be interested in its timestamps, just in
|
|
|
|
* it taking place, picking some piece of information when it
|
|
|
|
* appears in our event stream (vfs_getname comes to mind).
|
|
|
|
*/
|
|
|
|
if (trace->base_time == 0 && !trace->full_time &&
|
|
|
|
(evsel->attr.sample_type & PERF_SAMPLE_TIME))
|
2016-03-31 18:16:28 +00:00
|
|
|
trace->base_time = sample->time;
|
|
|
|
}
|
|
|
|
|
2013-08-29 04:29:52 +00:00
|
|
|
static int trace__process_sample(struct perf_tool *tool,
|
2014-06-26 16:14:24 +00:00
|
|
|
union perf_event *event,
|
2013-08-29 04:29:52 +00:00
|
|
|
struct perf_sample *sample,
|
|
|
|
struct perf_evsel *evsel,
|
|
|
|
struct machine *machine __maybe_unused)
|
|
|
|
{
|
|
|
|
struct trace *trace = container_of(tool, struct trace, tool);
|
2016-11-25 16:29:52 +00:00
|
|
|
struct thread *thread;
|
2013-08-29 04:29:52 +00:00
|
|
|
int err = 0;
|
|
|
|
|
2013-11-06 13:17:38 +00:00
|
|
|
tracepoint_handler handler = evsel->handler;
|
2013-08-29 04:29:52 +00:00
|
|
|
|
2016-11-25 16:29:52 +00:00
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
|
|
|
if (thread && thread__is_filtered(thread))
|
2017-03-24 18:03:19 +00:00
|
|
|
goto out;
|
2013-08-29 04:29:53 +00:00
|
|
|
|
2016-03-31 18:16:28 +00:00
|
|
|
trace__set_base_time(trace, evsel, sample);
|
2013-08-29 04:29:52 +00:00
|
|
|
|
2013-12-05 02:41:41 +00:00
|
|
|
if (handler) {
|
|
|
|
++trace->nr_events;
|
2014-06-26 16:14:24 +00:00
|
|
|
handler(trace, evsel, event, sample);
|
2013-12-05 02:41:41 +00:00
|
|
|
}
|
2017-03-24 18:03:19 +00:00
|
|
|
out:
|
|
|
|
thread__put(thread);
|
2013-08-29 04:29:52 +00:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2014-06-26 16:14:26 +00:00
|
|
|
static int trace__record(struct trace *trace, int argc, const char **argv)
|
2013-09-28 19:13:01 +00:00
|
|
|
{
|
|
|
|
unsigned int rec_argc, i, j;
|
|
|
|
const char **rec_argv;
|
|
|
|
const char * const record_args[] = {
|
|
|
|
"record",
|
|
|
|
"-R",
|
|
|
|
"-m", "1024",
|
|
|
|
"-c", "1",
|
|
|
|
};
|
|
|
|
|
2014-06-26 16:14:26 +00:00
|
|
|
const char * const sc_args[] = { "-e", };
|
|
|
|
unsigned int sc_args_nr = ARRAY_SIZE(sc_args);
|
|
|
|
const char * const majpf_args[] = { "-e", "major-faults" };
|
|
|
|
unsigned int majpf_args_nr = ARRAY_SIZE(majpf_args);
|
|
|
|
const char * const minpf_args[] = { "-e", "minor-faults" };
|
|
|
|
unsigned int minpf_args_nr = ARRAY_SIZE(minpf_args);
|
|
|
|
|
2013-12-05 02:41:39 +00:00
|
|
|
/* +1 is for the event string below */
|
2014-06-26 16:14:26 +00:00
|
|
|
rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
|
|
|
|
majpf_args_nr + minpf_args_nr + argc;
|
2013-09-28 19:13:01 +00:00
|
|
|
rec_argv = calloc(rec_argc + 1, sizeof(char *));
|
|
|
|
|
|
|
|
if (rec_argv == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2014-06-26 16:14:26 +00:00
|
|
|
j = 0;
|
2013-09-28 19:13:01 +00:00
|
|
|
for (i = 0; i < ARRAY_SIZE(record_args); i++)
|
2014-06-26 16:14:26 +00:00
|
|
|
rec_argv[j++] = record_args[i];
|
|
|
|
|
2014-06-26 16:14:28 +00:00
|
|
|
if (trace->trace_syscalls) {
|
|
|
|
for (i = 0; i < sc_args_nr; i++)
|
|
|
|
rec_argv[j++] = sc_args[i];
|
|
|
|
|
|
|
|
/* event string may be different for older kernels - e.g., RHEL6 */
|
|
|
|
if (is_valid_tracepoint("raw_syscalls:sys_enter"))
|
|
|
|
rec_argv[j++] = "raw_syscalls:sys_enter,raw_syscalls:sys_exit";
|
|
|
|
else if (is_valid_tracepoint("syscalls:sys_enter"))
|
|
|
|
rec_argv[j++] = "syscalls:sys_enter,syscalls:sys_exit";
|
|
|
|
else {
|
|
|
|
pr_err("Neither raw_syscalls nor syscalls events exist.\n");
|
|
|
|
return -1;
|
|
|
|
}
|
2013-12-05 02:41:39 +00:00
|
|
|
}
|
|
|
|
|
2014-06-26 16:14:26 +00:00
|
|
|
if (trace->trace_pgfaults & TRACE_PFMAJ)
|
|
|
|
for (i = 0; i < majpf_args_nr; i++)
|
|
|
|
rec_argv[j++] = majpf_args[i];
|
|
|
|
|
|
|
|
if (trace->trace_pgfaults & TRACE_PFMIN)
|
|
|
|
for (i = 0; i < minpf_args_nr; i++)
|
|
|
|
rec_argv[j++] = minpf_args[i];
|
|
|
|
|
|
|
|
for (i = 0; i < (unsigned int)argc; i++)
|
|
|
|
rec_argv[j++] = argv[i];
|
2013-09-28 19:13:01 +00:00
|
|
|
|
2017-03-27 14:47:20 +00:00
|
|
|
return cmd_record(j, rec_argv);
|
2013-09-28 19:13:01 +00:00
|
|
|
}
|
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
|
|
|
|
|
2015-08-04 20:01:04 +00:00
|
|
|
static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
|
2013-09-27 21:06:19 +00:00
|
|
|
{
|
2013-11-07 19:41:19 +00:00
|
|
|
struct perf_evsel *evsel = perf_evsel__newtp("probe", "vfs_getname");
|
2015-09-07 08:38:06 +00:00
|
|
|
|
|
|
|
if (IS_ERR(evsel))
|
2015-08-04 20:01:04 +00:00
|
|
|
return false;
|
2013-09-27 21:06:19 +00:00
|
|
|
|
|
|
|
if (perf_evsel__field(evsel, "pathname") == NULL) {
|
|
|
|
perf_evsel__delete(evsel);
|
2015-08-04 20:01:04 +00:00
|
|
|
return false;
|
2013-09-27 21:06:19 +00:00
|
|
|
}
|
|
|
|
|
2013-11-06 13:17:38 +00:00
|
|
|
evsel->handler = trace__vfs_getname;
|
2013-09-27 21:06:19 +00:00
|
|
|
perf_evlist__add(evlist, evsel);
|
2015-08-04 20:01:04 +00:00
|
|
|
return true;
|
2013-09-27 21:06:19 +00:00
|
|
|
}
|
|
|
|
|
2016-04-19 19:00:01 +00:00
|
|
|
static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
|
2014-06-26 16:14:25 +00:00
|
|
|
{
|
|
|
|
struct perf_evsel *evsel;
|
|
|
|
struct perf_event_attr attr = {
|
|
|
|
.type = PERF_TYPE_SOFTWARE,
|
|
|
|
.mmap_data = 1,
|
|
|
|
};
|
|
|
|
|
|
|
|
attr.config = config;
|
2014-07-23 21:15:09 +00:00
|
|
|
attr.sample_period = 1;
|
2014-06-26 16:14:25 +00:00
|
|
|
|
|
|
|
event_attr_init(&attr);
|
|
|
|
|
|
|
|
evsel = perf_evsel__new(&attr);
|
2016-04-19 19:00:01 +00:00
|
|
|
if (evsel)
|
|
|
|
evsel->handler = trace__pgfault;
|
2014-06-26 16:14:25 +00:00
|
|
|
|
2016-04-19 19:00:01 +00:00
|
|
|
return evsel;
|
2014-06-26 16:14:25 +00:00
|
|
|
}
|
|
|
|
|
2015-02-21 20:10:29 +00:00
|
|
|
static void trace__handle_event(struct trace *trace, union perf_event *event, struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
const u32 type = event->header.type;
|
|
|
|
struct perf_evsel *evsel;
|
|
|
|
|
|
|
|
if (type != PERF_RECORD_SAMPLE) {
|
|
|
|
trace__process_event(trace, trace->host, event, sample);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
evsel = perf_evlist__id2evsel(trace->evlist, sample->id);
|
|
|
|
if (evsel == NULL) {
|
|
|
|
fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample->id);
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2016-03-31 18:16:28 +00:00
|
|
|
trace__set_base_time(trace, evsel, sample);
|
|
|
|
|
2015-02-21 20:10:29 +00:00
|
|
|
if (evsel->attr.type == PERF_TYPE_TRACEPOINT &&
|
|
|
|
sample->raw_data == NULL) {
|
|
|
|
fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
|
|
|
|
perf_evsel__name(evsel), sample->tid,
|
|
|
|
sample->cpu, sample->raw_size);
|
|
|
|
} else {
|
|
|
|
tracepoint_handler handler = evsel->handler;
|
|
|
|
handler(trace, evsel, event, sample);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-07-02 21:24:51 +00:00
|
|
|
static int trace__add_syscall_newtp(struct trace *trace)
|
|
|
|
{
|
|
|
|
int ret = -1;
|
|
|
|
struct perf_evlist *evlist = trace->evlist;
|
|
|
|
struct perf_evsel *sys_enter, *sys_exit;
|
|
|
|
|
|
|
|
sys_enter = perf_evsel__syscall_newtp("sys_enter", trace__sys_enter);
|
|
|
|
if (sys_enter == NULL)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
|
|
|
|
goto out_delete_sys_enter;
|
|
|
|
|
|
|
|
sys_exit = perf_evsel__syscall_newtp("sys_exit", trace__sys_exit);
|
|
|
|
if (sys_exit == NULL)
|
|
|
|
goto out_delete_sys_enter;
|
|
|
|
|
|
|
|
if (perf_evsel__init_sc_tp_uint_field(sys_exit, ret))
|
|
|
|
goto out_delete_sys_exit;
|
|
|
|
|
|
|
|
perf_evlist__add(evlist, sys_enter);
|
|
|
|
perf_evlist__add(evlist, sys_exit);
|
|
|
|
|
2016-04-18 15:09:08 +00:00
|
|
|
if (callchain_param.enabled && !trace->kernel_syscallchains) {
|
2016-04-11 18:49:11 +00:00
|
|
|
/*
|
|
|
|
* We're interested only in the user space callchain
|
|
|
|
* leading to the syscall, allow overriding that for
|
|
|
|
* debugging reasons using --kernel_syscall_callchains
|
|
|
|
*/
|
|
|
|
sys_exit->attr.exclude_callchain_kernel = 1;
|
|
|
|
}
|
|
|
|
|
2015-07-02 21:28:11 +00:00
|
|
|
trace->syscalls.events.sys_enter = sys_enter;
|
|
|
|
trace->syscalls.events.sys_exit = sys_exit;
|
2015-07-02 21:24:51 +00:00
|
|
|
|
|
|
|
ret = 0;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
|
|
|
|
out_delete_sys_exit:
|
|
|
|
perf_evsel__delete_priv(sys_exit);
|
|
|
|
out_delete_sys_enter:
|
|
|
|
perf_evsel__delete_priv(sys_enter);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
perf trace: Use event filters for the event qualifier list
We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.
Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.
If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:
# trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
(common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 15:44:59 +00:00
|
|
|
static int trace__set_ev_qualifier_filter(struct trace *trace)
|
|
|
|
{
|
|
|
|
int err = -1;
|
2016-09-16 14:44:03 +00:00
|
|
|
struct perf_evsel *sys_exit;
|
perf trace: Use event filters for the event qualifier list
We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.
Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.
If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:
# trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
(common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 15:44:59 +00:00
|
|
|
char *filter = asprintf_expr_inout_ints("id", !trace->not_ev_qualifier,
|
|
|
|
trace->ev_qualifier_ids.nr,
|
|
|
|
trace->ev_qualifier_ids.entries);
|
|
|
|
|
|
|
|
if (filter == NULL)
|
|
|
|
goto out_enomem;
|
|
|
|
|
2016-09-16 14:44:04 +00:00
|
|
|
if (!perf_evsel__append_tp_filter(trace->syscalls.events.sys_enter,
|
|
|
|
filter)) {
|
2016-09-16 14:44:03 +00:00
|
|
|
sys_exit = trace->syscalls.events.sys_exit;
|
2016-09-16 14:44:04 +00:00
|
|
|
err = perf_evsel__append_tp_filter(sys_exit, filter);
|
2016-09-16 14:44:03 +00:00
|
|
|
}
|
perf trace: Use event filters for the event qualifier list
We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.
Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.
If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:
# trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
(common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 15:44:59 +00:00
|
|
|
|
|
|
|
free(filter);
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
out_enomem:
|
|
|
|
errno = ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
2015-07-02 21:24:51 +00:00
|
|
|
|
2012-10-05 05:02:16 +00:00
|
|
|
static int trace__run(struct trace *trace, int argc, const char **argv)
|
2012-09-26 23:05:56 +00:00
|
|
|
{
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
struct perf_evlist *evlist = trace->evlist;
|
2016-04-19 19:00:01 +00:00
|
|
|
struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL;
|
2012-10-17 20:09:46 +00:00
|
|
|
int err = -1, i;
|
|
|
|
unsigned long before;
|
2012-10-05 05:02:16 +00:00
|
|
|
const bool forks = argc > 0;
|
2014-09-22 17:39:48 +00:00
|
|
|
bool draining = false;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2013-09-24 14:04:32 +00:00
|
|
|
trace->live = true;
|
|
|
|
|
2015-07-02 21:24:51 +00:00
|
|
|
if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
|
2015-01-22 13:52:55 +00:00
|
|
|
goto out_error_raw_syscalls;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2014-06-26 16:14:28 +00:00
|
|
|
if (trace->trace_syscalls)
|
2015-08-04 20:01:04 +00:00
|
|
|
trace->vfs_getname = perf_evlist__add_vfs_getname(evlist);
|
2013-09-27 21:06:19 +00:00
|
|
|
|
2016-04-19 19:00:01 +00:00
|
|
|
if ((trace->trace_pgfaults & TRACE_PFMAJ)) {
|
|
|
|
pgfault_maj = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MAJ);
|
|
|
|
if (pgfault_maj == NULL)
|
|
|
|
goto out_error_mem;
|
|
|
|
perf_evlist__add(evlist, pgfault_maj);
|
2015-01-22 13:34:22 +00:00
|
|
|
}
|
2014-06-26 16:14:25 +00:00
|
|
|
|
2016-04-19 19:00:01 +00:00
|
|
|
if ((trace->trace_pgfaults & TRACE_PFMIN)) {
|
|
|
|
pgfault_min = perf_evsel__new_pgfault(PERF_COUNT_SW_PAGE_FAULTS_MIN);
|
|
|
|
if (pgfault_min == NULL)
|
|
|
|
goto out_error_mem;
|
|
|
|
perf_evlist__add(evlist, pgfault_min);
|
|
|
|
}
|
2014-06-26 16:14:25 +00:00
|
|
|
|
2012-10-17 20:13:12 +00:00
|
|
|
if (trace->sched &&
|
2015-01-22 14:13:43 +00:00
|
|
|
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
|
|
|
|
trace__sched_stat_runtime))
|
|
|
|
goto out_error_sched_stat_runtime;
|
2012-10-17 20:13:12 +00:00
|
|
|
|
2012-09-26 23:05:56 +00:00
|
|
|
err = perf_evlist__create_maps(evlist, &trace->opts.target);
|
|
|
|
if (err < 0) {
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
|
2012-09-26 23:05:56 +00:00
|
|
|
goto out_delete_evlist;
|
|
|
|
}
|
|
|
|
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
err = trace__symbols_init(trace, evlist);
|
|
|
|
if (err < 0) {
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, "Problems initializing symbol libraries!\n");
|
2014-01-03 18:56:06 +00:00
|
|
|
goto out_delete_evlist;
|
perf trace: Support interrupted syscalls
Using the same strategies as in the tmp.perf/trace2, i.e. the 'trace'
tool implemented by tglx, just updated to the current codebase.
Example:
[root@sandy linux]# perf trace usleep 1 | tail
2.003: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128396288
2.017: mmap(addr: 0, len: 4096, prot: 3, flags: 34, fd: 4294967295, off: 0 ) = -2128400384
2.029: arch_prctl(option: 4098, arg2: 140146949441280, arg3: 140146949435392, arg4: 34, arg5: 4294967295) = 0
2.084: mprotect(start: 208741634048, len: 16384, prot: 1 ) = 0
2.098: mprotect(start: 208735956992, len: 4096, prot: 1 ) = 0
2.122: munmap(addr: 140146949447680, len: 91882 ) = 0
2.359: brk(brk: 0 ) = 28987392
2.371: brk(brk: 29122560 ) = 29122560
2.490: nanosleep(rqtp: 140735694241504, rmtp: 0 ) = 0
2.507: exit_group(error_code: 0
[root@sandy linux]#
For now the timestamp and duration are always on, will be selectable.
Also if multiple threads are being monitored, its tid will appear.
The ret output continues to be interpreted a la strace.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ly9ulroru4my5isn0xe9gr0m@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-06 21:43:19 +00:00
|
|
|
}
|
|
|
|
|
2016-04-11 21:42:37 +00:00
|
|
|
perf_evlist__config(evlist, &trace->opts, NULL);
|
|
|
|
|
2016-04-19 19:31:12 +00:00
|
|
|
if (callchain_param.enabled) {
|
|
|
|
bool use_identifier = false;
|
|
|
|
|
|
|
|
if (trace->syscalls.events.sys_exit) {
|
|
|
|
perf_evsel__config_callchain(trace->syscalls.events.sys_exit,
|
|
|
|
&trace->opts, &callchain_param);
|
|
|
|
use_identifier = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (pgfault_maj) {
|
|
|
|
perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
|
|
|
|
use_identifier = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (pgfault_min) {
|
|
|
|
perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
|
|
|
|
use_identifier = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (use_identifier) {
|
|
|
|
/*
|
|
|
|
* Now we have evsels with different sample_ids, use
|
|
|
|
* PERF_SAMPLE_IDENTIFIER to map from sample to evsel
|
|
|
|
* from a fixed position in each ring buffer record.
|
|
|
|
*
|
|
|
|
* As of this the changeset introducing this comment, this
|
|
|
|
* isn't strictly needed, as the fields that can come before
|
|
|
|
* PERF_SAMPLE_ID are all used, but we'll probably disable
|
|
|
|
* some of those for things like copying the payload of
|
|
|
|
* pointer syscall arguments, and for vfs_getname we don't
|
|
|
|
* need PERF_SAMPLE_ADDR and PERF_SAMPLE_IP, so do this
|
|
|
|
* here as a warning we need to use PERF_SAMPLE_IDENTIFIER.
|
|
|
|
*/
|
|
|
|
perf_evlist__set_sample_bit(evlist, IDENTIFIER);
|
|
|
|
perf_evlist__reset_sample_bit(evlist, ID);
|
|
|
|
}
|
2016-04-11 21:42:37 +00:00
|
|
|
}
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2012-10-05 05:02:16 +00:00
|
|
|
signal(SIGCHLD, sig_handler);
|
|
|
|
signal(SIGINT, sig_handler);
|
|
|
|
|
|
|
|
if (forks) {
|
2013-03-11 07:43:15 +00:00
|
|
|
err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
|
2014-01-03 17:56:49 +00:00
|
|
|
argv, false, NULL);
|
2012-10-05 05:02:16 +00:00
|
|
|
if (err < 0) {
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, "Couldn't run the workload!\n");
|
2014-01-03 18:56:06 +00:00
|
|
|
goto out_delete_evlist;
|
2012-10-05 05:02:16 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-09-26 23:05:56 +00:00
|
|
|
err = perf_evlist__open(evlist);
|
perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid
kernel/events/core.c has:
/*
* perf event paranoia level:
* -1 - not paranoid at all
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
*/
int sysctl_perf_event_paranoid __read_mostly = 1;
So, with the default being 1, a non-root user can trace his stuff:
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
1
[acme@zoo ~]$ yes > /dev/null &
[1] 15338
[acme@zoo ~]$ trace -p 15338 | head -5
0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
[acme@zoo ~]$
[acme@zoo ~]$ trace --duration 1 sleep 1
1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250 ) = 0
[acme@zoo ~]$
[acme@zoo ~]$ trace -- usleep 1 | tail -5
0.905 ( 0.002 ms): brk( ) = 0x1c82000
0.910 ( 0.003 ms): brk(brk: 0x1ca3000 ) = 0x1ca3000
0.913 ( 0.001 ms): brk( ) = 0x1ca3000
0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280 ) = 0
0.995 ( 0.000 ms): exit_group(
[acme@zoo ~]$
But can't do system wide tracing:
[acme@zoo ~]$ trace
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 0
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:
[acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
2
[acme@zoo ~]$
[acme@zoo ~]$ trace usleep 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
If the user manages to get what he/she wants, convincing root not
to be paranoid at all...
[root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
[root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
-1
[root@zoo ~]#
[acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
root 729 Xorg
[acme@zoo ~]$
[acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg | head -5
23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = 8
23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = -1 EAGAIN Resource temporarily unavailable
23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
[acme@zoo ~]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-17 20:38:29 +00:00
|
|
|
if (err < 0)
|
|
|
|
goto out_error_open;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2016-02-26 09:31:54 +00:00
|
|
|
err = bpf__apply_obj_config();
|
|
|
|
if (err) {
|
|
|
|
char errbuf[BUFSIZ];
|
|
|
|
|
|
|
|
bpf__strerror_apply_obj_config(err, errbuf, sizeof(errbuf));
|
|
|
|
pr_err("ERROR: Apply config to BPF failed: %s\n",
|
|
|
|
errbuf);
|
|
|
|
goto out_error_open;
|
|
|
|
}
|
|
|
|
|
2015-02-21 18:15:21 +00:00
|
|
|
/*
|
|
|
|
* Better not use !target__has_task() here because we need to cover the
|
|
|
|
* case where no threads were specified in the command line, but a
|
|
|
|
* workload was, and in that case we will fill in the thread_map when
|
|
|
|
* we fork the workload in perf_evlist__prepare_workload.
|
|
|
|
*/
|
perf trace: Introduce --filter-pids
When tracing in X we get event loops due to the tracing activity, i.e.
updates to a gnome-terminal that generate syscalls for X.org, etc.
To get a more useful view of what is happening, syscall wise, system
wide, we need to filter those, like in:
# ps ax|egrep '981|2296|1519' | grep -v egrep
981 tty1 Ss+ 5:40 /usr/bin/Xorg :0 -background none ...
1519 ? Sl 2:22 /usr/bin/gnome-shell
2296 ? Sl 4:16 /usr/libexec/gnome-terminal-server
#
# trace -e write --filter-pids 981,2296,1519
0.385 ( 0.021 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
0.922 ( 0.014 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
5006.525 ( 0.029 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
5007.235 ( 0.023 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
5177.646 ( 0.018 ms): rtkit-daemon/782 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7f7eea70be88, count: 8) = 8
8314.497 ( 0.004 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af7b0, count: 8) = 8
8314.518 ( 0.002 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af0e0, count: 8) = 8
^C#
When this option is used the tracer pid is also filtered.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f5qmiyy7c0uxdm21ncatpeek@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-21 19:36:52 +00:00
|
|
|
if (trace->filter_pids.nr > 0)
|
|
|
|
err = perf_evlist__set_filter_pids(evlist, trace->filter_pids.nr, trace->filter_pids.entries);
|
2015-06-22 22:36:02 +00:00
|
|
|
else if (thread_map__pid(evlist->threads, 0) == -1)
|
perf trace: Introduce --filter-pids
When tracing in X we get event loops due to the tracing activity, i.e.
updates to a gnome-terminal that generate syscalls for X.org, etc.
To get a more useful view of what is happening, syscall wise, system
wide, we need to filter those, like in:
# ps ax|egrep '981|2296|1519' | grep -v egrep
981 tty1 Ss+ 5:40 /usr/bin/Xorg :0 -background none ...
1519 ? Sl 2:22 /usr/bin/gnome-shell
2296 ? Sl 4:16 /usr/libexec/gnome-terminal-server
#
# trace -e write --filter-pids 981,2296,1519
0.385 ( 0.021 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
0.922 ( 0.014 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
5006.525 ( 0.029 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
5007.235 ( 0.023 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
5177.646 ( 0.018 ms): rtkit-daemon/782 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7f7eea70be88, count: 8) = 8
8314.497 ( 0.004 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af7b0, count: 8) = 8
8314.518 ( 0.002 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af0e0, count: 8) = 8
^C#
When this option is used the tracer pid is also filtered.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f5qmiyy7c0uxdm21ncatpeek@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-21 19:36:52 +00:00
|
|
|
err = perf_evlist__set_filter_pid(evlist, getpid());
|
|
|
|
|
perf evlist: Make perf_evlist__set_filter use perf_evsel__set_filter
Instead of calling perf_evsel__apply_filter straight away, so that
we can, in the next patches, expand the filter with more conditions
before actually calling the ioctl to pass the end result filter to
the kernel.
Now we need to call perf_evlist__apply_filters() after the filter
is completely setup, i.e. do the ioctl calls.
The perf_evlist__apply_filters() method was already in place, because
that is the model for the other tools that receives filters in the
command line: go on setting then in the evsel->filter and only at
the end, after parsing the whole command line, apply them.
We get, as a bonus, a more expressive message that states which
event, if any, failed to have the filter applied to, with an
error message stating what happened.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f429pgz75ryz7tpe6v74etre@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-03 20:42:03 +00:00
|
|
|
if (err < 0)
|
|
|
|
goto out_error_mem;
|
|
|
|
|
perf trace: Use event filters for the event qualifier list
We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.
Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.
If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:
# trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
(common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 15:44:59 +00:00
|
|
|
if (trace->ev_qualifier_ids.nr > 0) {
|
|
|
|
err = trace__set_ev_qualifier_filter(trace);
|
|
|
|
if (err < 0)
|
|
|
|
goto out_errno;
|
|
|
|
|
2015-08-03 20:12:29 +00:00
|
|
|
pr_debug("event qualifier tracepoint filter: %s\n",
|
|
|
|
trace->syscalls.events.sys_exit->filter);
|
|
|
|
}
|
perf trace: Use event filters for the event qualifier list
We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.
Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.
If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:
# trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
(common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 15:44:59 +00:00
|
|
|
|
perf evlist: Make perf_evlist__set_filter use perf_evsel__set_filter
Instead of calling perf_evsel__apply_filter straight away, so that
we can, in the next patches, expand the filter with more conditions
before actually calling the ioctl to pass the end result filter to
the kernel.
Now we need to call perf_evlist__apply_filters() after the filter
is completely setup, i.e. do the ioctl calls.
The perf_evlist__apply_filters() method was already in place, because
that is the model for the other tools that receives filters in the
command line: go on setting then in the evsel->filter and only at
the end, after parsing the whole command line, apply them.
We get, as a bonus, a more expressive message that states which
event, if any, failed to have the filter applied to, with an
error message stating what happened.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f429pgz75ryz7tpe6v74etre@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-03 20:42:03 +00:00
|
|
|
err = perf_evlist__apply_filters(evlist, &evsel);
|
|
|
|
if (err < 0)
|
|
|
|
goto out_error_apply_filters;
|
2015-02-21 18:15:21 +00:00
|
|
|
|
2013-11-28 16:57:22 +00:00
|
|
|
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages, false);
|
2014-12-11 21:04:10 +00:00
|
|
|
if (err < 0)
|
|
|
|
goto out_error_mmap;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
perf trace: Implement --delay
In the perf wiki todo-list[1], there is an entry regarding initial-delay
and 'perf trace'; the following small patch tries to fulfill this point.
It has been generated against the branch tip/perf/core.
It has only been implemented in the "trace__run" case.
Ex.:
$ sudo strace -- ./perf trace --delay 5 sleep 1 2>&1
...
fcntl(7, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
ioctl(7, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
ioctl(11, PERF_EVENT_IOC_SET_OUTPUT, 0x7) = 0
fcntl(11, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
ioctl(11, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
write(6, "\0", 1) = 1
close(6) = 0
nanosleep({0, 5000000}, NULL) = 0 # DELAY OF 5 MS BEFORE ENABLING THE EVENTS
ioctl(3, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(4, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(5, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(7, PERF_EVENT_IOC_ENABLE, 0) = 0
...
[1]: https://perf.wiki.kernel.org/index.php/Todo
Signed-off-by: Alexis Berlemont <alexis.berlemont@gmail.com>
Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20161010054328.4028-2-alexis.berlemont@gmail.com
[ Add entry to the manpage, cut'n'pasted from stat's and record's ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-10 05:43:28 +00:00
|
|
|
if (!target__none(&trace->opts.target) && !trace->opts.initial_delay)
|
2015-04-22 13:04:23 +00:00
|
|
|
perf_evlist__enable(evlist);
|
|
|
|
|
2012-10-05 05:02:16 +00:00
|
|
|
if (forks)
|
|
|
|
perf_evlist__start_workload(evlist);
|
|
|
|
|
perf trace: Implement --delay
In the perf wiki todo-list[1], there is an entry regarding initial-delay
and 'perf trace'; the following small patch tries to fulfill this point.
It has been generated against the branch tip/perf/core.
It has only been implemented in the "trace__run" case.
Ex.:
$ sudo strace -- ./perf trace --delay 5 sleep 1 2>&1
...
fcntl(7, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
ioctl(7, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
ioctl(11, PERF_EVENT_IOC_SET_OUTPUT, 0x7) = 0
fcntl(11, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
ioctl(11, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
write(6, "\0", 1) = 1
close(6) = 0
nanosleep({0, 5000000}, NULL) = 0 # DELAY OF 5 MS BEFORE ENABLING THE EVENTS
ioctl(3, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(4, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(5, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(7, PERF_EVENT_IOC_ENABLE, 0) = 0
...
[1]: https://perf.wiki.kernel.org/index.php/Todo
Signed-off-by: Alexis Berlemont <alexis.berlemont@gmail.com>
Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20161010054328.4028-2-alexis.berlemont@gmail.com
[ Add entry to the manpage, cut'n'pasted from stat's and record's ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-10 05:43:28 +00:00
|
|
|
if (trace->opts.initial_delay) {
|
|
|
|
usleep(trace->opts.initial_delay * 1000);
|
|
|
|
perf_evlist__enable(evlist);
|
|
|
|
}
|
|
|
|
|
2015-06-22 22:36:02 +00:00
|
|
|
trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
|
2015-02-13 15:32:45 +00:00
|
|
|
evlist->threads->nr > 1 ||
|
|
|
|
perf_evlist__first(evlist)->attr.inherit;
|
2012-09-26 23:05:56 +00:00
|
|
|
again:
|
2012-10-17 20:09:46 +00:00
|
|
|
before = trace->nr_events;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
|
|
|
for (i = 0; i < evlist->nr_mmaps; i++) {
|
|
|
|
union perf_event *event;
|
|
|
|
|
|
|
|
while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
|
|
|
|
struct perf_sample sample;
|
|
|
|
|
2012-10-17 20:09:46 +00:00
|
|
|
++trace->nr_events;
|
2012-09-26 23:05:56 +00:00
|
|
|
|
|
|
|
err = perf_evlist__parse_sample(evlist, event, &sample);
|
|
|
|
if (err) {
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
|
2013-10-24 07:43:33 +00:00
|
|
|
goto next_event;
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|
|
|
|
|
2015-02-21 20:10:29 +00:00
|
|
|
trace__handle_event(trace, event, &sample);
|
2013-10-24 07:43:33 +00:00
|
|
|
next_event:
|
|
|
|
perf_evlist__mmap_consume(evlist, i);
|
2013-09-03 14:55:07 +00:00
|
|
|
|
2013-10-16 14:57:33 +00:00
|
|
|
if (interrupted)
|
|
|
|
goto out_disable;
|
perf trace: Disable events and drain events when forked workload ends
We were not checking in the inner event processing loop if the forked workload
had finished, which, on a busy system, may make it take a long time trying to
drain events, entering a seemingly neverending loop, waiting for the system to
get idle enough to make it drain the buffers.
Fix it by disabling the events when 'done' is true, in the inner loop, to start
draining what is in the buffers.
Now:
[root@ssdandy ~]# time trace --filter-pids 14003 -a sleep 1 | tail
996.748 ( 0.002 ms): sh/30296 rt_sigprocmask(how: SETMASK, nset: 0x7ffc83418160, sigsetsize: 8) = 0
996.751 ( 0.002 ms): sh/30296 rt_sigprocmask(how: BLOCK, nset: 0x7ffc834181f0, oset: 0x7ffc83418270, sigsetsize: 8) = 0
996.755 ( 0.002 ms): sh/30296 rt_sigaction(sig: INT, act: 0x7ffc83417f50, oact: 0x7ffc83417ff0, sigsetsize: 8) = 0
1004.543 ( 0.362 ms): tail/30198 ... [continued]: read()) = 4096
1004.548 ( 7.791 ms): sh/30296 wait4(upid: -1, stat_addr: 0x7ffc834181a0) ...
1004.975 ( 0.427 ms): tail/30198 read(buf: 0x7633f0, count: 8192) = 4096
1005.390 ( 0.410 ms): tail/30198 read(buf: 0x765410, count: 8192) = 4096
1005.743 ( 0.348 ms): tail/30198 read(buf: 0x7633f0, count: 8192) = 4096
1006.197 ( 0.449 ms): tail/30198 read(buf: 0x765410, count: 8192) = 4096
1006.492 ( 0.290 ms): tail/30198 read(buf: 0x7633f0, count: 8192) = 4096
real 0m1.219s
user 0m0.704s
sys 0m0.331s
[root@ssdandy ~]#
Reported-by: Michael Petlan <mpetlan@redhat.com>
Suggested-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-p6kpn1b26qcbe47pufpw0tex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-22 14:11:57 +00:00
|
|
|
|
|
|
|
if (done && !draining) {
|
|
|
|
perf_evlist__disable(evlist);
|
|
|
|
draining = true;
|
|
|
|
}
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-10-17 20:09:46 +00:00
|
|
|
if (trace->nr_events == before) {
|
2013-10-16 14:57:33 +00:00
|
|
|
int timeout = done ? 100 : -1;
|
2012-10-05 05:02:16 +00:00
|
|
|
|
2014-09-22 17:39:48 +00:00
|
|
|
if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
|
|
|
|
if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP) == 0)
|
|
|
|
draining = true;
|
|
|
|
|
2013-10-16 14:57:33 +00:00
|
|
|
goto again;
|
2014-09-22 17:39:48 +00:00
|
|
|
}
|
2013-10-16 14:57:33 +00:00
|
|
|
} else {
|
|
|
|
goto again;
|
2012-10-05 05:02:16 +00:00
|
|
|
}
|
|
|
|
|
2013-10-16 14:57:33 +00:00
|
|
|
out_disable:
|
2015-03-03 01:21:35 +00:00
|
|
|
thread__zput(trace->current);
|
|
|
|
|
2013-10-16 14:57:33 +00:00
|
|
|
perf_evlist__disable(evlist);
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2013-09-27 21:06:19 +00:00
|
|
|
if (!err) {
|
|
|
|
if (trace->summary)
|
|
|
|
trace__fprintf_thread_summary(trace, trace->output);
|
|
|
|
|
|
|
|
if (trace->show_tool_stats) {
|
|
|
|
fprintf(trace->output, "Stats:\n "
|
|
|
|
" vfs_getname : %" PRIu64 "\n"
|
|
|
|
" proc_getname: %" PRIu64 "\n",
|
|
|
|
trace->stats.vfs_getname,
|
|
|
|
trace->stats.proc_getname);
|
|
|
|
}
|
|
|
|
}
|
2013-10-09 03:26:53 +00:00
|
|
|
|
2012-09-26 23:05:56 +00:00
|
|
|
out_delete_evlist:
|
|
|
|
perf_evlist__delete(evlist);
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
trace->evlist = NULL;
|
2013-09-24 14:04:32 +00:00
|
|
|
trace->live = false;
|
2012-09-26 23:05:56 +00:00
|
|
|
return err;
|
2013-10-17 15:07:58 +00:00
|
|
|
{
|
|
|
|
char errbuf[BUFSIZ];
|
perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid
kernel/events/core.c has:
/*
* perf event paranoia level:
* -1 - not paranoid at all
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
*/
int sysctl_perf_event_paranoid __read_mostly = 1;
So, with the default being 1, a non-root user can trace his stuff:
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
1
[acme@zoo ~]$ yes > /dev/null &
[1] 15338
[acme@zoo ~]$ trace -p 15338 | head -5
0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
[acme@zoo ~]$
[acme@zoo ~]$ trace --duration 1 sleep 1
1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250 ) = 0
[acme@zoo ~]$
[acme@zoo ~]$ trace -- usleep 1 | tail -5
0.905 ( 0.002 ms): brk( ) = 0x1c82000
0.910 ( 0.003 ms): brk(brk: 0x1ca3000 ) = 0x1ca3000
0.913 ( 0.001 ms): brk( ) = 0x1ca3000
0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280 ) = 0
0.995 ( 0.000 ms): exit_group(
[acme@zoo ~]$
But can't do system wide tracing:
[acme@zoo ~]$ trace
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 0
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:
[acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
2
[acme@zoo ~]$
[acme@zoo ~]$ trace usleep 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
If the user manages to get what he/she wants, convincing root not
to be paranoid at all...
[root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
[root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
-1
[root@zoo ~]#
[acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
root 729 Xorg
[acme@zoo ~]$
[acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg | head -5
23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = 8
23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = -1 EAGAIN Resource temporarily unavailable
23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
[acme@zoo ~]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-17 20:38:29 +00:00
|
|
|
|
2015-01-22 14:13:43 +00:00
|
|
|
out_error_sched_stat_runtime:
|
2015-09-02 07:56:35 +00:00
|
|
|
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime");
|
2015-01-22 14:13:43 +00:00
|
|
|
goto out_error;
|
|
|
|
|
2015-01-22 13:52:55 +00:00
|
|
|
out_error_raw_syscalls:
|
2015-09-02 07:56:35 +00:00
|
|
|
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "raw_syscalls", "sys_(enter|exit)");
|
perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid
kernel/events/core.c has:
/*
* perf event paranoia level:
* -1 - not paranoid at all
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
*/
int sysctl_perf_event_paranoid __read_mostly = 1;
So, with the default being 1, a non-root user can trace his stuff:
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
1
[acme@zoo ~]$ yes > /dev/null &
[1] 15338
[acme@zoo ~]$ trace -p 15338 | head -5
0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
[acme@zoo ~]$
[acme@zoo ~]$ trace --duration 1 sleep 1
1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250 ) = 0
[acme@zoo ~]$
[acme@zoo ~]$ trace -- usleep 1 | tail -5
0.905 ( 0.002 ms): brk( ) = 0x1c82000
0.910 ( 0.003 ms): brk(brk: 0x1ca3000 ) = 0x1ca3000
0.913 ( 0.001 ms): brk( ) = 0x1ca3000
0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280 ) = 0
0.995 ( 0.000 ms): exit_group(
[acme@zoo ~]$
But can't do system wide tracing:
[acme@zoo ~]$ trace
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 0
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:
[acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
2
[acme@zoo ~]$
[acme@zoo ~]$ trace usleep 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
If the user manages to get what he/she wants, convincing root not
to be paranoid at all...
[root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
[root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
-1
[root@zoo ~]#
[acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
root 729 Xorg
[acme@zoo ~]$
[acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg | head -5
23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = 8
23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = -1 EAGAIN Resource temporarily unavailable
23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
[acme@zoo ~]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-17 20:38:29 +00:00
|
|
|
goto out_error;
|
|
|
|
|
2014-12-11 21:04:10 +00:00
|
|
|
out_error_mmap:
|
|
|
|
perf_evlist__strerror_mmap(evlist, errno, errbuf, sizeof(errbuf));
|
|
|
|
goto out_error;
|
|
|
|
|
perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid
kernel/events/core.c has:
/*
* perf event paranoia level:
* -1 - not paranoid at all
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
*/
int sysctl_perf_event_paranoid __read_mostly = 1;
So, with the default being 1, a non-root user can trace his stuff:
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
1
[acme@zoo ~]$ yes > /dev/null &
[1] 15338
[acme@zoo ~]$ trace -p 15338 | head -5
0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
[acme@zoo ~]$
[acme@zoo ~]$ trace --duration 1 sleep 1
1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250 ) = 0
[acme@zoo ~]$
[acme@zoo ~]$ trace -- usleep 1 | tail -5
0.905 ( 0.002 ms): brk( ) = 0x1c82000
0.910 ( 0.003 ms): brk(brk: 0x1ca3000 ) = 0x1ca3000
0.913 ( 0.001 ms): brk( ) = 0x1ca3000
0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280 ) = 0
0.995 ( 0.000 ms): exit_group(
[acme@zoo ~]$
But can't do system wide tracing:
[acme@zoo ~]$ trace
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 0
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:
[acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
2
[acme@zoo ~]$
[acme@zoo ~]$ trace usleep 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
If the user manages to get what he/she wants, convincing root not
to be paranoid at all...
[root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
[root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
-1
[root@zoo ~]#
[acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
root 729 Xorg
[acme@zoo ~]$
[acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg | head -5
23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = 8
23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = -1 EAGAIN Resource temporarily unavailable
23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
[acme@zoo ~]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-17 20:38:29 +00:00
|
|
|
out_error_open:
|
|
|
|
perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
|
|
|
|
|
|
|
|
out_error:
|
2013-10-17 15:07:58 +00:00
|
|
|
fprintf(trace->output, "%s\n", errbuf);
|
2013-10-04 05:17:31 +00:00
|
|
|
goto out_delete_evlist;
|
perf evlist: Make perf_evlist__set_filter use perf_evsel__set_filter
Instead of calling perf_evsel__apply_filter straight away, so that
we can, in the next patches, expand the filter with more conditions
before actually calling the ioctl to pass the end result filter to
the kernel.
Now we need to call perf_evlist__apply_filters() after the filter
is completely setup, i.e. do the ioctl calls.
The perf_evlist__apply_filters() method was already in place, because
that is the model for the other tools that receives filters in the
command line: go on setting then in the evsel->filter and only at
the end, after parsing the whole command line, apply them.
We get, as a bonus, a more expressive message that states which
event, if any, failed to have the filter applied to, with an
error message stating what happened.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f429pgz75ryz7tpe6v74etre@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-03 20:42:03 +00:00
|
|
|
|
|
|
|
out_error_apply_filters:
|
|
|
|
fprintf(trace->output,
|
|
|
|
"Failed to set filter \"%s\" on event %s with %d (%s)\n",
|
|
|
|
evsel->filter, perf_evsel__name(evsel), errno,
|
tools: Introduce str_error_r()
The tools so far have been using the strerror_r() GNU variant, that
returns a string, be it the buffer passed or something else.
But that, besides being tricky in cases where we expect that the
function using strerror_r() returns the error formatted in a provided
buffer (we have to check if it returned something else and copy that
instead), breaks the build on systems not using glibc, like Alpine
Linux, where musl libc is used.
So, introduce yet another wrapper, str_error_r(), that has the GNU
interface, but uses the portable XSI variant of strerror_r(), so that
users rest asured that the provided buffer is used and it is what is
returned.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-d4t42fnf48ytlk8rjxs822tf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-06 14:56:20 +00:00
|
|
|
str_error_r(errno, errbuf, sizeof(errbuf)));
|
perf evlist: Make perf_evlist__set_filter use perf_evsel__set_filter
Instead of calling perf_evsel__apply_filter straight away, so that
we can, in the next patches, expand the filter with more conditions
before actually calling the ioctl to pass the end result filter to
the kernel.
Now we need to call perf_evlist__apply_filters() after the filter
is completely setup, i.e. do the ioctl calls.
The perf_evlist__apply_filters() method was already in place, because
that is the model for the other tools that receives filters in the
command line: go on setting then in the evsel->filter and only at
the end, after parsing the whole command line, apply them.
We get, as a bonus, a more expressive message that states which
event, if any, failed to have the filter applied to, with an
error message stating what happened.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f429pgz75ryz7tpe6v74etre@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-03 20:42:03 +00:00
|
|
|
goto out_delete_evlist;
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|
2015-01-22 14:08:04 +00:00
|
|
|
out_error_mem:
|
|
|
|
fprintf(trace->output, "Not enough memory to run!\n");
|
|
|
|
goto out_delete_evlist;
|
perf trace: Use event filters for the event qualifier list
We use raw_syscalls:sys_{enter,exit} events to show the syscalls, but were
using a rather lazy/inneficient way to implement our 'strace -e' equivalent:
filter out after reading the events in the ring buffer.
Deflect more work to the kernel by appending a filter expression for that,
that, together with the pid list, that is always present, if only to filter the
tracer itself, reduces pressure on the ring buffer and otherwise use
infrastructure already in place in the kernel to do early filtering.
If we use it with -v we can see the filter passed to the kernel,
for instance, for this contrieved case:
# trace -v -e \!open,close,write,poll,recvfrom,select,recvmsg,writev,sendmsg,read,futex,epoll_wait,ioctl,eventfd --filter-pids 2189,2566,1398,2692,4475,4532
<SNIP>
(common_pid != 2514 && common_pid != 1398 && common_pid != 2189 && common_pid != 2566 && common_pid != 2692 && common_pid != 4475 && common_pid != 4532) && (id != 3 && id != 232 && id != 284 && id != 202 && id != 16 && id != 2 && id != 7 && id != 0 && id != 45 && id != 47 && id != 23 && id != 46 && id != 1 && id != 20)
0.011 (0.011 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
16.946 (0.019 ms): caribou/2295 eventfd2(flags: CLOEXEC|NONBLOCK) = 18
38.598 (0.167 ms): chronyd/794 socket(family: INET, type: DGRAM ) = 4
38.603 (0.002 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: GETFD) = 0
38.605 (0.001 ms): chronyd/794 fcntl(fd: 4<socket:[239307]>, cmd: SETFD, arg: 1) = 0
^C
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-ti2tg18atproqpguc2moinp6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-07-04 15:44:59 +00:00
|
|
|
|
|
|
|
out_errno:
|
|
|
|
fprintf(trace->output, "errno=%d,%s\n", errno, strerror(errno));
|
|
|
|
goto out_delete_evlist;
|
perf trace: Improve messages related to /proc/sys/kernel/perf_event_paranoid
kernel/events/core.c has:
/*
* perf event paranoia level:
* -1 - not paranoid at all
* 0 - disallow raw tracepoint access for unpriv
* 1 - disallow cpu events for unpriv
* 2 - disallow kernel profiling for unpriv
*/
int sysctl_perf_event_paranoid __read_mostly = 1;
So, with the default being 1, a non-root user can trace his stuff:
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
1
[acme@zoo ~]$ yes > /dev/null &
[1] 15338
[acme@zoo ~]$ trace -p 15338 | head -5
0.005 ( 0.005 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.045 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.085 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.125 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
0.165 ( 0.001 ms): write(fd: 1</dev/null>, buf: 0x7fe6db765000, count: 4096 ) = 4096
[acme@zoo ~]$
[acme@zoo ~]$ trace --duration 1 sleep 1
1002.148 (1001.218 ms): nanosleep(rqtp: 0x7fff46c79250 ) = 0
[acme@zoo ~]$
[acme@zoo ~]$ trace -- usleep 1 | tail -5
0.905 ( 0.002 ms): brk( ) = 0x1c82000
0.910 ( 0.003 ms): brk(brk: 0x1ca3000 ) = 0x1ca3000
0.913 ( 0.001 ms): brk( ) = 0x1ca3000
0.990 ( 0.059 ms): nanosleep(rqtp: 0x7fffe31a3280 ) = 0
0.995 ( 0.000 ms): exit_group(
[acme@zoo ~]$
But can't do system wide tracing:
[acme@zoo ~]$ trace
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 0
Error: Operation not permitted.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 1.
[acme@zoo ~]$
If the paranoid level is >= 2, i.e. turn this perf stuff off for !root users:
[acme@zoo ~]$ sudo sh -c 'echo 2 > /proc/sys/kernel/perf_event_paranoid'
[acme@zoo ~]$ cat /proc/sys/kernel/perf_event_paranoid
2
[acme@zoo ~]$
[acme@zoo ~]$ trace usleep 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
[acme@zoo ~]$ trace --cpu 1
Error: Permission denied.
Hint: Check /proc/sys/kernel/perf_event_paranoid setting.
Hint: For your workloads it needs to be <= 1
Hint: For system wide tracing it needs to be set to -1.
Hint: The current value is 2.
[acme@zoo ~]$
If the user manages to get what he/she wants, convincing root not
to be paranoid at all...
[root@zoo ~]# echo -1 > /proc/sys/kernel/perf_event_paranoid
[root@zoo ~]# cat /proc/sys/kernel/perf_event_paranoid
-1
[root@zoo ~]#
[acme@zoo ~]$ ps -eo user,pid,comm | grep Xorg
root 729 Xorg
[acme@zoo ~]$
[acme@zoo ~]$ trace -a --duration 0.001 -e \!select,ioctl,writev | grep Xorg | head -5
23.143 ( 0.003 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.152 ( 0.004 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = 8
23.161 ( 0.002 ms): Xorg/729 read(fd: 31, buf: 0x2544af0, count: 4096 ) = -1 EAGAIN Resource temporarily unavailable
23.175 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
23.235 ( 0.002 ms): Xorg/729 setitimer(which: REAL, value: 0x7fffaadf16e0 ) = 0
[acme@zoo ~]$
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-di28olfwd28rvkox7v3hqhu1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-10-17 20:38:29 +00:00
|
|
|
}
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2013-08-29 04:29:52 +00:00
|
|
|
static int trace__replay(struct trace *trace)
|
|
|
|
{
|
|
|
|
const struct perf_evsel_str_handler handlers[] = {
|
2013-09-27 21:06:19 +00:00
|
|
|
{ "probe:vfs_getname", trace__vfs_getname, },
|
2013-08-29 04:29:52 +00:00
|
|
|
};
|
2013-10-15 14:27:32 +00:00
|
|
|
struct perf_data_file file = {
|
|
|
|
.path = input_name,
|
|
|
|
.mode = PERF_DATA_MODE_READ,
|
perf trace: Support using -f to override perf.data file ownership
Enable perf trace to use perf.data when it is not owned by current user
or root.
Example:
# perf trace record ls
# chown Yunlong.Song:Yunlong.Song perf.data
# ls -al perf.data
-rw------- 1 Yunlong.Song Yunlong.Song 4153101 Apr 2 15:28 perf.data
# id
uid=0(root) gid=0(root) groups=0(root),64(pkcs11)
Before this patch:
# perf trace -i perf.data
File perf.data not owned by current user or root (use -f to override)
# perf trace -i perf.data -f
Error: unknown switch `f'
usage: perf trace [<options>] [<command>]
or: perf trace [<options>] -- <command> [<options>]
or: perf trace record [<options>] [<command>]
or: perf trace record [<options>] -- <command> [<options>]
--event <event> event selector. use 'perf list' to list
available events
--comm show the thread COMM next to its id
--tool_stats show tool stats
-e, --expr <expr> list of events to trace
-o, --output <file> output file name
-i, --input <file> Analyze events in file
-p, --pid <pid> trace events on existing process id
-t, --tid <tid> trace events on existing thread id
--filter-pids <float>
...
As shown above, the -f option does not work at all.
After this patch:
# perf trace -i perf.data
File perf.data not owned by current user or root (use -f to override)
# perf trace -i perf.data -f
0.056 ( 0.002 ms): ls/47325 brk( ...
0.108 ( 0.018 ms): ls/47325 mmap(len: 4096, prot: READ|WRITE, ...
0.145 ( 0.013 ms): ls/47325 access(filename: 0x7f31259a0eb0, ...
0.172 ( 0.008 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.180 ( 0.004 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.185 ( 0.004 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.189 ( 0.003 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.195 ( 0.004 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.199 ( 0.002 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.205 ( 0.004 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.211 ( 0.004 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.220 ( 0.007 ms): ls/47325 open(filename: 0x7f312599e8ff, ...
...
...
As shown above, the -f option really works now.
Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1427982439-27388-10-git-send-email-yunlong.song@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 13:47:18 +00:00
|
|
|
.force = trace->force,
|
2013-10-15 14:27:32 +00:00
|
|
|
};
|
2013-08-29 04:29:52 +00:00
|
|
|
struct perf_session *session;
|
2013-11-12 06:25:00 +00:00
|
|
|
struct perf_evsel *evsel;
|
2013-08-29 04:29:52 +00:00
|
|
|
int err = -1;
|
|
|
|
|
|
|
|
trace->tool.sample = trace__process_sample;
|
|
|
|
trace->tool.mmap = perf_event__process_mmap;
|
2013-09-23 01:44:58 +00:00
|
|
|
trace->tool.mmap2 = perf_event__process_mmap2;
|
2013-08-29 04:29:52 +00:00
|
|
|
trace->tool.comm = perf_event__process_comm;
|
|
|
|
trace->tool.exit = perf_event__process_exit;
|
|
|
|
trace->tool.fork = perf_event__process_fork;
|
|
|
|
trace->tool.attr = perf_event__process_attr;
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-07 20:41:43 +00:00
|
|
|
trace->tool.tracing_data = perf_event__process_tracing_data;
|
2013-08-29 04:29:52 +00:00
|
|
|
trace->tool.build_id = perf_event__process_build_id;
|
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info
Introduce a new option to record PERF_RECORD_NAMESPACES events emitted
by the kernel when fork, clone, setns or unshare are invoked. And update
perf-record documentation with the new option to record namespace
events.
Committer notes:
Combined it with a later patch to allow printing it via 'perf report -D'
and be able to test the feature introduced in this patch. Had to move
here also perf_ns__name(), that was introduced in another later patch.
Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt:
util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=]
ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx
^
Testing it:
# perf record --namespaces -a
^C[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ]
#
# perf report -D
<SNIP>
3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7
[0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc,
4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb]
0x1151e0 [0x30]: event: 9
.
. ... raw event: size 48 bytes
. 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h....
. 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c....
. 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................
<SNIP>
NAMESPACES events: 1
<SNIP>
#
Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@fb.com>
Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com>
Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Eric Biederman <ebiederm@xmission.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sargun Dhillon <sargun@sargun.me>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-07 20:41:43 +00:00
|
|
|
trace->tool.namespaces = perf_event__process_namespaces;
|
2013-08-29 04:29:52 +00:00
|
|
|
|
2014-07-06 12:18:21 +00:00
|
|
|
trace->tool.ordered_events = true;
|
2013-08-29 04:29:52 +00:00
|
|
|
trace->tool.ordering_requires_timestamps = true;
|
|
|
|
|
|
|
|
/* add tid to output */
|
|
|
|
trace->multiple_threads = true;
|
|
|
|
|
2013-10-15 14:27:32 +00:00
|
|
|
session = perf_session__new(&file, false, &trace->tool);
|
2013-08-29 04:29:52 +00:00
|
|
|
if (session == NULL)
|
2014-09-24 01:33:37 +00:00
|
|
|
return -1;
|
2013-08-29 04:29:52 +00:00
|
|
|
|
2016-11-25 16:29:52 +00:00
|
|
|
if (trace->opts.target.pid)
|
|
|
|
symbol_conf.pid_list_str = strdup(trace->opts.target.pid);
|
|
|
|
|
|
|
|
if (trace->opts.target.tid)
|
|
|
|
symbol_conf.tid_list_str = strdup(trace->opts.target.tid);
|
|
|
|
|
2014-08-12 06:40:45 +00:00
|
|
|
if (symbol__init(&session->header.env) < 0)
|
2014-08-12 06:40:44 +00:00
|
|
|
goto out;
|
|
|
|
|
2013-09-28 19:13:00 +00:00
|
|
|
trace->host = &session->machines.host;
|
|
|
|
|
2013-08-29 04:29:52 +00:00
|
|
|
err = perf_session__set_tracepoints_handlers(session, handlers);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
2013-11-12 06:25:00 +00:00
|
|
|
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
|
|
|
|
"raw_syscalls:sys_enter");
|
2013-12-05 02:41:39 +00:00
|
|
|
/* older kernels have syscalls tp versus raw_syscalls */
|
|
|
|
if (evsel == NULL)
|
|
|
|
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
|
|
|
|
"syscalls:sys_enter");
|
2013-11-12 06:25:00 +00:00
|
|
|
|
2014-06-26 16:14:28 +00:00
|
|
|
if (evsel &&
|
|
|
|
(perf_evsel__init_syscall_tp(evsel, trace__sys_enter) < 0 ||
|
|
|
|
perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
|
2013-11-12 06:25:00 +00:00
|
|
|
pr_err("Error during initialize raw_syscalls:sys_enter event\n");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
|
|
|
|
"raw_syscalls:sys_exit");
|
2013-12-05 02:41:39 +00:00
|
|
|
if (evsel == NULL)
|
|
|
|
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
|
|
|
|
"syscalls:sys_exit");
|
2014-06-26 16:14:28 +00:00
|
|
|
if (evsel &&
|
|
|
|
(perf_evsel__init_syscall_tp(evsel, trace__sys_exit) < 0 ||
|
|
|
|
perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
|
2013-11-12 06:25:00 +00:00
|
|
|
pr_err("Error during initialize raw_syscalls:sys_exit event\n");
|
2013-08-29 04:29:52 +00:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2016-06-23 14:26:15 +00:00
|
|
|
evlist__for_each_entry(session->evlist, evsel) {
|
2014-06-26 16:14:26 +00:00
|
|
|
if (evsel->attr.type == PERF_TYPE_SOFTWARE &&
|
|
|
|
(evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MAJ ||
|
|
|
|
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS_MIN ||
|
|
|
|
evsel->attr.config == PERF_COUNT_SW_PAGE_FAULTS))
|
|
|
|
evsel->handler = trace__pgfault;
|
|
|
|
}
|
|
|
|
|
2013-08-29 04:29:52 +00:00
|
|
|
setup_pager();
|
|
|
|
|
2015-03-03 14:58:45 +00:00
|
|
|
err = perf_session__process_events(session);
|
2013-08-29 04:29:52 +00:00
|
|
|
if (err)
|
|
|
|
pr_err("Failed to process events, error %d", err);
|
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
else if (trace->summary)
|
|
|
|
trace__fprintf_thread_summary(trace, trace->output);
|
|
|
|
|
2013-08-29 04:29:52 +00:00
|
|
|
out:
|
|
|
|
perf_session__delete(session);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2012-10-17 20:13:12 +00:00
|
|
|
static size_t trace__fprintf_threads_header(FILE *fp)
|
|
|
|
{
|
|
|
|
size_t printed;
|
|
|
|
|
2013-11-12 14:42:14 +00:00
|
|
|
printed = fprintf(fp, "\n Summary of events:\n\n");
|
2013-10-09 03:26:53 +00:00
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2016-05-04 19:06:26 +00:00
|
|
|
DEFINE_RESORT_RB(syscall_stats, a->msecs > b->msecs,
|
|
|
|
struct stats *stats;
|
|
|
|
double msecs;
|
|
|
|
int syscall;
|
|
|
|
)
|
|
|
|
{
|
|
|
|
struct int_node *source = rb_entry(nd, struct int_node, rb_node);
|
|
|
|
struct stats *stats = source->priv;
|
|
|
|
|
|
|
|
entry->syscall = source->i;
|
|
|
|
entry->stats = stats;
|
|
|
|
entry->msecs = stats ? (u64)stats->n * (avg_stats(stats) / NSEC_PER_MSEC) : 0;
|
|
|
|
}
|
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
static size_t thread__dump_stats(struct thread_trace *ttrace,
|
|
|
|
struct trace *trace, FILE *fp)
|
|
|
|
{
|
|
|
|
size_t printed = 0;
|
|
|
|
struct syscall *sc;
|
2016-05-04 19:06:26 +00:00
|
|
|
struct rb_node *nd;
|
|
|
|
DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
|
2013-10-09 03:26:53 +00:00
|
|
|
|
2016-05-04 19:06:26 +00:00
|
|
|
if (syscall_stats == NULL)
|
2013-10-09 03:26:53 +00:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
printed += fprintf(fp, "\n");
|
|
|
|
|
2015-08-06 09:24:29 +00:00
|
|
|
printed += fprintf(fp, " syscall calls total min avg max stddev\n");
|
|
|
|
printed += fprintf(fp, " (msec) (msec) (msec) (msec) (%%)\n");
|
|
|
|
printed += fprintf(fp, " --------------- -------- --------- --------- --------- --------- ------\n");
|
2013-11-12 14:42:14 +00:00
|
|
|
|
2016-06-23 14:34:10 +00:00
|
|
|
resort_rb__for_each_entry(nd, syscall_stats) {
|
2016-05-04 19:06:26 +00:00
|
|
|
struct stats *stats = syscall_stats_entry->stats;
|
2013-10-09 03:26:53 +00:00
|
|
|
if (stats) {
|
|
|
|
double min = (double)(stats->min) / NSEC_PER_MSEC;
|
|
|
|
double max = (double)(stats->max) / NSEC_PER_MSEC;
|
|
|
|
double avg = avg_stats(stats);
|
|
|
|
double pct;
|
|
|
|
u64 n = (u64) stats->n;
|
|
|
|
|
|
|
|
pct = avg ? 100.0 * stddev_stats(stats)/avg : 0.0;
|
|
|
|
avg /= NSEC_PER_MSEC;
|
|
|
|
|
2016-05-04 19:06:26 +00:00
|
|
|
sc = &trace->syscalls.table[syscall_stats_entry->syscall];
|
2013-11-12 14:42:14 +00:00
|
|
|
printed += fprintf(fp, " %-15s", sc->name);
|
2015-08-06 09:24:29 +00:00
|
|
|
printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
|
2016-05-04 19:06:26 +00:00
|
|
|
n, syscall_stats_entry->msecs, min, avg);
|
2013-11-13 12:21:48 +00:00
|
|
|
printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
|
2013-10-09 03:26:53 +00:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-05-04 19:06:26 +00:00
|
|
|
resort_rb__delete(syscall_stats);
|
2013-10-09 03:26:53 +00:00
|
|
|
printed += fprintf(fp, "\n\n");
|
2012-10-17 20:13:12 +00:00
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
|
2013-09-28 19:12:59 +00:00
|
|
|
{
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
size_t printed = 0;
|
2014-10-06 00:46:03 +00:00
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
2013-09-28 19:12:59 +00:00
|
|
|
double ratio;
|
|
|
|
|
|
|
|
if (ttrace == NULL)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
|
|
|
|
|
2013-11-14 16:43:30 +00:00
|
|
|
printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
|
2013-11-12 14:42:14 +00:00
|
|
|
printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
|
2013-11-14 16:43:30 +00:00
|
|
|
printed += fprintf(fp, "%.1f%%", ratio);
|
2014-07-08 18:05:16 +00:00
|
|
|
if (ttrace->pfmaj)
|
|
|
|
printed += fprintf(fp, ", %lu majfaults", ttrace->pfmaj);
|
|
|
|
if (ttrace->pfmin)
|
|
|
|
printed += fprintf(fp, ", %lu minfaults", ttrace->pfmin);
|
perf trace: Do not show the runtime_ms for a thread when not collecting it
That field is only updated when we use the "sched:sched_stat_runtime"
tracepoint, and that is only done so far when we use the '--stat' command line
option, without it we get just zeros, confusing the users:
Without this patch:
# trace -a -s sleep 1
<SNIP>
qemu-system-x86 (9931), 468 events, 9.6%, 0.000 msec
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
---------- ------ --------- --------- --------- --------- ------
ppoll 98 982.374 0.000 10.024 29.983 12.65%
write 34 0.401 0.005 0.012 0.027 5.49%
ioctl 102 0.347 0.002 0.003 0.007 3.08%
firefox (10871), 1856 events, 38.2%, 0.000 msec
(msec) (msec) (msec) (msec) (%)
---------- ------ --------- --------- --------- --------- ------
poll 395 934.873 0.000 2.367 17.120 11.51%
recvmsg 395 0.988 0.001 0.003 0.021 4.20%
read 106 0.460 0.002 0.004 0.007 3.17%
futex 24 0.108 0.001 0.004 0.010 10.05%
mmap 2 0.041 0.016 0.021 0.026 23.92%
write 6 0.027 0.004 0.004 0.005 2.52%
After this patch that ', 0.000 msecs' gets suppressed when --stat is not
in use.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-p7emqrsw7900tdkg43v9l1e1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-05 18:46:50 +00:00
|
|
|
if (trace->sched)
|
|
|
|
printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
|
|
|
|
else if (fputc('\n', fp) != EOF)
|
|
|
|
++printed;
|
|
|
|
|
2013-10-09 03:26:53 +00:00
|
|
|
printed += thread__dump_stats(ttrace, trace, fp);
|
2013-09-28 19:12:59 +00:00
|
|
|
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
return printed;
|
|
|
|
}
|
2013-09-28 19:12:59 +00:00
|
|
|
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
static unsigned long thread__nr_events(struct thread_trace *ttrace)
|
|
|
|
{
|
|
|
|
return ttrace ? ttrace->nr_events : 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
DEFINE_RESORT_RB(threads, (thread__nr_events(a->thread->priv) < thread__nr_events(b->thread->priv)),
|
|
|
|
struct thread *thread;
|
|
|
|
)
|
|
|
|
{
|
|
|
|
entry->thread = rb_entry(nd, struct thread, rb_node);
|
2013-09-28 19:12:59 +00:00
|
|
|
}
|
|
|
|
|
2012-10-17 20:13:12 +00:00
|
|
|
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp)
|
|
|
|
{
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host);
|
|
|
|
size_t printed = trace__fprintf_threads_header(fp);
|
|
|
|
struct rb_node *nd;
|
2012-10-17 20:13:12 +00:00
|
|
|
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
if (threads == NULL) {
|
|
|
|
fprintf(fp, "%s", "Error sorting output by nr_events!\n");
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2016-06-23 14:34:10 +00:00
|
|
|
resort_rb__for_each_entry(nd, threads)
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
|
2013-09-28 19:12:59 +00:00
|
|
|
|
perf trace: Sort summary output by number of events
# trace -a -s sleep 1 |& grep events | tail
gmain (1733), 34 events, 1.0%, 0.000 msec
hexchat (9765), 46 events, 1.4%, 0.000 msec
ssh (11109), 80 events, 2.4%, 0.000 msec
sleep (32631), 81 events, 2.4%, 0.000 msec
qemu-system-x86 (10021), 272 events, 8.2%, 0.000 msec
Xorg (1965), 322 events, 9.7%, 0.000 msec
SoftwareVsyncTh (10922), 366 events, 11.1%, 0.000 msec
gnome-shell (2231), 446 events, 13.5%, 0.000 msec
qemu-system-x86 (9931), 468 events, 14.1%, 0.000 msec
firefox (10871), 1098 events, 33.2%, 0.000 msec
[root@jouet ~]#
Suggested-by: Milian Wolff <milian.wolff@kdab.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-ye4cnprhfeiq32ar4lt60dqs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-05-04 15:47:16 +00:00
|
|
|
resort_rb__delete(threads);
|
|
|
|
|
|
|
|
return printed;
|
2012-10-17 20:13:12 +00:00
|
|
|
}
|
|
|
|
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
static int trace__set_duration(const struct option *opt, const char *str,
|
|
|
|
int unset __maybe_unused)
|
|
|
|
{
|
|
|
|
struct trace *trace = opt->value;
|
|
|
|
|
|
|
|
trace->duration_filter = atof(str);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf trace: Introduce --filter-pids
When tracing in X we get event loops due to the tracing activity, i.e.
updates to a gnome-terminal that generate syscalls for X.org, etc.
To get a more useful view of what is happening, syscall wise, system
wide, we need to filter those, like in:
# ps ax|egrep '981|2296|1519' | grep -v egrep
981 tty1 Ss+ 5:40 /usr/bin/Xorg :0 -background none ...
1519 ? Sl 2:22 /usr/bin/gnome-shell
2296 ? Sl 4:16 /usr/libexec/gnome-terminal-server
#
# trace -e write --filter-pids 981,2296,1519
0.385 ( 0.021 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
0.922 ( 0.014 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
5006.525 ( 0.029 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 136) = 136
5007.235 ( 0.023 ms): goa-daemon/2061 write(fd: 1</dev/null>, buf: 0x7fbeb017b000, count: 140) = 140
5177.646 ( 0.018 ms): rtkit-daemon/782 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7f7eea70be88, count: 8) = 8
8314.497 ( 0.004 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af7b0, count: 8) = 8
8314.518 ( 0.002 ms): gsd-locate-poi/2084 write(fd: 5<anon_inode:[eventfd]>, buf: 0x7fffe96af0e0, count: 8) = 8
^C#
When this option is used the tracer pid is also filtered.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-f5qmiyy7c0uxdm21ncatpeek@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-21 19:36:52 +00:00
|
|
|
static int trace__set_filter_pids(const struct option *opt, const char *str,
|
|
|
|
int unset __maybe_unused)
|
|
|
|
{
|
|
|
|
int ret = -1;
|
|
|
|
size_t i;
|
|
|
|
struct trace *trace = opt->value;
|
|
|
|
/*
|
|
|
|
* FIXME: introduce a intarray class, plain parse csv and create a
|
|
|
|
* { int nr, int entries[] } struct...
|
|
|
|
*/
|
|
|
|
struct intlist *list = intlist__new(str);
|
|
|
|
|
|
|
|
if (list == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
i = trace->filter_pids.nr = intlist__nr_entries(list) + 1;
|
|
|
|
trace->filter_pids.entries = calloc(i, sizeof(pid_t));
|
|
|
|
|
|
|
|
if (trace->filter_pids.entries == NULL)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
trace->filter_pids.entries[0] = getpid();
|
|
|
|
|
|
|
|
for (i = 1; i < trace->filter_pids.nr; ++i)
|
|
|
|
trace->filter_pids.entries[i] = intlist__entry(list, i - 1)->i;
|
|
|
|
|
|
|
|
intlist__delete(list);
|
|
|
|
ret = 0;
|
|
|
|
out:
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
static int trace__open_output(struct trace *trace, const char *filename)
|
|
|
|
{
|
|
|
|
struct stat st;
|
|
|
|
|
|
|
|
if (!stat(filename, &st) && st.st_size) {
|
|
|
|
char oldname[PATH_MAX];
|
|
|
|
|
|
|
|
scnprintf(oldname, sizeof(oldname), "%s.old", filename);
|
|
|
|
unlink(oldname);
|
|
|
|
rename(filename, oldname);
|
|
|
|
}
|
|
|
|
|
|
|
|
trace->output = fopen(filename, "w");
|
|
|
|
|
|
|
|
return trace->output == NULL ? -errno : 0;
|
|
|
|
}
|
|
|
|
|
2014-06-26 16:14:25 +00:00
|
|
|
static int parse_pagefaults(const struct option *opt, const char *str,
|
|
|
|
int unset __maybe_unused)
|
|
|
|
{
|
|
|
|
int *trace_pgfaults = opt->value;
|
|
|
|
|
|
|
|
if (strcmp(str, "all") == 0)
|
|
|
|
*trace_pgfaults |= TRACE_PFMAJ | TRACE_PFMIN;
|
|
|
|
else if (strcmp(str, "maj") == 0)
|
|
|
|
*trace_pgfaults |= TRACE_PFMAJ;
|
|
|
|
else if (strcmp(str, "min") == 0)
|
|
|
|
*trace_pgfaults |= TRACE_PFMIN;
|
|
|
|
else
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
|
|
|
|
{
|
|
|
|
struct perf_evsel *evsel;
|
|
|
|
|
2016-06-23 14:26:15 +00:00
|
|
|
evlist__for_each_entry(evlist, evsel)
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
evsel->handler = handler;
|
|
|
|
}
|
|
|
|
|
2017-01-09 20:26:26 +00:00
|
|
|
/*
|
|
|
|
* XXX: Hackish, just splitting the combined -e+--event (syscalls
|
|
|
|
* (raw_syscalls:{sys_{enter,exit}} + events (tracepoints, HW, SW, etc) to use
|
|
|
|
* existing facilities unchanged (trace->ev_qualifier + parse_options()).
|
|
|
|
*
|
|
|
|
* It'd be better to introduce a parse_options() variant that would return a
|
|
|
|
* list with the terms it didn't match to an event...
|
|
|
|
*/
|
|
|
|
static int trace__parse_events_option(const struct option *opt, const char *str,
|
|
|
|
int unset __maybe_unused)
|
|
|
|
{
|
|
|
|
struct trace *trace = (struct trace *)opt->value;
|
|
|
|
const char *s = str;
|
|
|
|
char *sep = NULL, *lists[2] = { NULL, NULL, };
|
|
|
|
int len = strlen(str), err = -1, list;
|
|
|
|
char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
|
|
|
|
char group_name[PATH_MAX];
|
|
|
|
|
|
|
|
if (strace_groups_dir == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (*s == '!') {
|
|
|
|
++s;
|
|
|
|
trace->not_ev_qualifier = true;
|
|
|
|
}
|
|
|
|
|
|
|
|
while (1) {
|
|
|
|
if ((sep = strchr(s, ',')) != NULL)
|
|
|
|
*sep = '\0';
|
|
|
|
|
|
|
|
list = 0;
|
|
|
|
if (syscalltbl__id(trace->sctbl, s) >= 0) {
|
|
|
|
list = 1;
|
|
|
|
} else {
|
|
|
|
path__join(group_name, sizeof(group_name), strace_groups_dir, s);
|
|
|
|
if (access(group_name, R_OK) == 0)
|
|
|
|
list = 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (lists[list]) {
|
|
|
|
sprintf(lists[list] + strlen(lists[list]), ",%s", s);
|
|
|
|
} else {
|
|
|
|
lists[list] = malloc(len);
|
|
|
|
if (lists[list] == NULL)
|
|
|
|
goto out;
|
|
|
|
strcpy(lists[list], s);
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!sep)
|
|
|
|
break;
|
|
|
|
|
|
|
|
*sep = ',';
|
|
|
|
s = sep + 1;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (lists[1] != NULL) {
|
|
|
|
struct strlist_config slist_config = {
|
|
|
|
.dirname = strace_groups_dir,
|
|
|
|
};
|
|
|
|
|
|
|
|
trace->ev_qualifier = strlist__new(lists[1], &slist_config);
|
|
|
|
if (trace->ev_qualifier == NULL) {
|
|
|
|
fputs("Not enough memory to parse event qualifier", trace->output);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (trace__validate_ev_qualifier(trace))
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
err = 0;
|
|
|
|
|
|
|
|
if (lists[0]) {
|
|
|
|
struct option o = OPT_CALLBACK('e', "event", &trace->evlist, "event",
|
|
|
|
"event selector. use 'perf list' to list available events",
|
|
|
|
parse_events_option);
|
|
|
|
err = parse_events_option(&o, lists[0], 0);
|
|
|
|
}
|
|
|
|
out:
|
|
|
|
if (sep)
|
|
|
|
*sep = ',';
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2017-03-27 14:47:20 +00:00
|
|
|
int cmd_trace(int argc, const char **argv)
|
2012-09-26 23:05:56 +00:00
|
|
|
{
|
2015-03-18 13:35:57 +00:00
|
|
|
const char *trace_usage[] = {
|
2012-10-05 05:02:16 +00:00
|
|
|
"perf trace [<options>] [<command>]",
|
|
|
|
"perf trace [<options>] -- <command> [<options>]",
|
2013-09-28 19:13:01 +00:00
|
|
|
"perf trace record [<options>] [<command>]",
|
|
|
|
"perf trace record [<options>] -- <command> [<options>]",
|
2012-09-26 23:05:56 +00:00
|
|
|
NULL
|
|
|
|
};
|
|
|
|
struct trace trace = {
|
|
|
|
.syscalls = {
|
|
|
|
. max = -1,
|
|
|
|
},
|
|
|
|
.opts = {
|
|
|
|
.target = {
|
|
|
|
.uid = UINT_MAX,
|
|
|
|
.uses_mmap = true,
|
|
|
|
},
|
|
|
|
.user_freq = UINT_MAX,
|
|
|
|
.user_interval = ULLONG_MAX,
|
2014-01-14 20:52:14 +00:00
|
|
|
.no_buffering = true,
|
2014-12-12 20:28:32 +00:00
|
|
|
.mmap_pages = UINT_MAX,
|
2015-06-17 13:51:11 +00:00
|
|
|
.proc_map_timeout = 500,
|
2012-09-26 23:05:56 +00:00
|
|
|
},
|
2015-08-05 19:52:23 +00:00
|
|
|
.output = stderr,
|
perf trace: Add option to show process COMM
Enabled by default, disable with --no-comm, e.g.:
181.821 (0.001 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: PEEK|TRUNC|CMSG_CLOEXEC ) = 20
181.824 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.825 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.834 (0.002 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: CMSG_CLOEXEC ) = 20
181.836 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.838 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.705 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 1256
181.710 (0.002 ms): evolution-addr/10924 geteuid( ) = 1000
181.712 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.727 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 1256
181.731 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.734 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.908 (0.002 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 20
181.913 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.915 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.930 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 20
181.934 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.937 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
220.718 (0.010 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.741 (0.000 ms): dbus-daemon/10711 ... [continued]: epoll_wait()) = 1
220.759 (0.004 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.780 (0.002 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.788 (0.001 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = -1 EAGAIN Resource temporarily unavailable
220.760 (0.004 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.771 (0.023 ms): perf/26347 open(filename: 0xf2e780, mode: 15918976 ) = 19
220.850 (0.002 ms): perf/26347 close(fd: 19 ) = 0
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6be5jvnkdzjptdrebfn5263n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 15:35:21 +00:00
|
|
|
.show_comm = true,
|
2014-06-26 16:14:28 +00:00
|
|
|
.trace_syscalls = true,
|
2016-04-11 18:49:11 +00:00
|
|
|
.kernel_syscallchains = false,
|
2016-04-15 19:41:19 +00:00
|
|
|
.max_stack = UINT_MAX,
|
2012-09-26 23:05:56 +00:00
|
|
|
};
|
2013-08-19 15:01:10 +00:00
|
|
|
const char *output_name = NULL;
|
2012-09-26 23:05:56 +00:00
|
|
|
const struct option trace_options[] = {
|
2017-01-09 20:26:26 +00:00
|
|
|
OPT_CALLBACK('e', "event", &trace, "event",
|
|
|
|
"event/syscall selector. use 'perf list' to list available events",
|
|
|
|
trace__parse_events_option),
|
perf trace: Add option to show process COMM
Enabled by default, disable with --no-comm, e.g.:
181.821 (0.001 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: PEEK|TRUNC|CMSG_CLOEXEC ) = 20
181.824 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.825 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.834 (0.002 ms): deja-dup-monit/10784 recvmsg(fd: 8, msg: 0x7fff4342baf0, flags: CMSG_CLOEXEC ) = 20
181.836 (0.001 ms): deja-dup-monit/10784 geteuid( ) = 1000
181.838 (0.001 ms): deja-dup-monit/10784 getegid( ) = 1000
181.705 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 1256
181.710 (0.002 ms): evolution-addr/10924 geteuid( ) = 1000
181.712 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.727 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 1256
181.731 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.734 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.908 (0.002 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: PEEK|TRUNC|CMSG_CLOEXEC) = 20
181.913 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.915 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
181.930 (0.003 ms): evolution-addr/10924 recvmsg(fd: 10, msg: 0x7fff17dc6990, flags: CMSG_CLOEXEC ) = 20
181.934 (0.001 ms): evolution-addr/10924 geteuid( ) = 1000
181.937 (0.001 ms): evolution-addr/10924 getegid( ) = 1000
220.718 (0.010 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.741 (0.000 ms): dbus-daemon/10711 ... [continued]: epoll_wait()) = 1
220.759 (0.004 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.780 (0.002 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = 200
220.788 (0.001 ms): dbus-daemon/10711 recvmsg(fd: 11, msg: 0x7ffff94594d0, flags: CMSG_CLOEXEC ) = -1 EAGAIN Resource temporarily unavailable
220.760 (0.004 ms): at-spi2-regist/10715 sendmsg(fd: 3, msg: 0x7fffdb8756c0, flags: NOSIGNAL ) = 200
220.771 (0.023 ms): perf/26347 open(filename: 0xf2e780, mode: 15918976 ) = 19
220.850 (0.002 ms): perf/26347 close(fd: 19 ) = 0
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-6be5jvnkdzjptdrebfn5263n@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-09-12 15:35:21 +00:00
|
|
|
OPT_BOOLEAN(0, "comm", &trace.show_comm,
|
|
|
|
"show the thread COMM next to its id"),
|
2013-09-27 21:06:19 +00:00
|
|
|
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
|
2017-01-09 20:26:26 +00:00
|
|
|
OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
|
|
|
|
trace__parse_events_option),
|
2013-08-19 15:01:10 +00:00
|
|
|
OPT_STRING('o', "output", &output_name, "file", "output file name"),
|
2013-08-29 04:29:52 +00:00
|
|
|
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
|
2012-09-26 23:05:56 +00:00
|
|
|
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
|
|
|
|
"trace events on existing process id"),
|
2013-08-20 17:15:45 +00:00
|
|
|
OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
|
2012-09-26 23:05:56 +00:00
|
|
|
"trace events on existing thread id"),
|
2015-04-23 14:59:20 +00:00
|
|
|
OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
|
|
|
|
"pids to filter (by the kernel)", trace__set_filter_pids),
|
2013-08-20 17:15:45 +00:00
|
|
|
OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
|
2012-09-26 23:05:56 +00:00
|
|
|
"system-wide collection from all CPUs"),
|
2013-08-20 17:15:45 +00:00
|
|
|
OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
|
2012-09-26 23:05:56 +00:00
|
|
|
"list of cpus to monitor"),
|
2013-08-29 04:29:52 +00:00
|
|
|
OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
|
2012-09-26 23:05:56 +00:00
|
|
|
"child tasks do not inherit counters"),
|
2013-09-01 10:36:12 +00:00
|
|
|
OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
|
|
|
|
"number of mmap data pages",
|
|
|
|
perf_evlist__parse_mmap_pages),
|
2013-08-20 17:15:45 +00:00
|
|
|
OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
|
2012-09-26 23:05:56 +00:00
|
|
|
"user to profile"),
|
perf trace: Add duration filter
Example:
[acme@sandy linux]$ perf trace --duration 0.025 usleep 1
2.221 ( 0.958 ms): 6724 execve(arg0: 140733557168278, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = -2
3.690 ( 1.443 ms): 6724 execve(arg0: 140733557168295, arg1: 140733557178768, arg2: 16134304, arg3: 140733557167840, arg4: 7955998171588342573, arg5: 6723) = 0
3.979 ( 0.048 ms): 6724 open(filename: 208733843841, flags: 0, mode: 1 ) = 3
4.071 ( 0.075 ms): 6724 open(filename: 139744419925673, flags: 0, mode: 0 ) = 3
4.318 ( 0.056 ms): 6724 nanosleep(rqtp: 140734030404608, rmtp: 0 ) = 0
[acme@sandy linux]$ perf trace --duration 0.100 usleep 1
1.143 ( 1.021 ms): 6726 execve(arg0: 140736323962279, arg1: 140736323972752, arg2: 34926752, arg3: 140736323961824, arg4: 7955998171588342573, arg5: 6725) = 0
[acme@sandy linux]$
Cherry picked from tmp.perf/trace2 branch.
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-oslw2j2958we9qf0ctra4whd@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-10-08 12:56:00 +00:00
|
|
|
OPT_CALLBACK(0, "duration", &trace, "float",
|
|
|
|
"show only events with duration > N.M ms",
|
|
|
|
trace__set_duration),
|
2012-10-17 20:13:12 +00:00
|
|
|
OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
|
2013-08-22 19:49:54 +00:00
|
|
|
OPT_INCR('v', "verbose", &verbose, "be more verbose"),
|
2013-09-04 18:37:43 +00:00
|
|
|
OPT_BOOLEAN('T', "time", &trace.full_time,
|
|
|
|
"Show full timestamp, not time relative to first start"),
|
2013-11-12 16:31:15 +00:00
|
|
|
OPT_BOOLEAN('s', "summary", &trace.summary_only,
|
|
|
|
"Show only syscall summary with statistics"),
|
|
|
|
OPT_BOOLEAN('S', "with-summary", &trace.summary,
|
|
|
|
"Show all syscalls and summary with statistics"),
|
2014-06-26 16:14:25 +00:00
|
|
|
OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
|
|
|
|
"Trace pagefaults", parse_pagefaults, "maj"),
|
2014-06-26 16:14:28 +00:00
|
|
|
OPT_BOOLEAN(0, "syscalls", &trace.trace_syscalls, "Trace syscalls"),
|
perf trace: Support using -f to override perf.data file ownership
Enable perf trace to use perf.data when it is not owned by current user
or root.
Example:
# perf trace record ls
# chown Yunlong.Song:Yunlong.Song perf.data
# ls -al perf.data
-rw------- 1 Yunlong.Song Yunlong.Song 4153101 Apr 2 15:28 perf.data
# id
uid=0(root) gid=0(root) groups=0(root),64(pkcs11)
Before this patch:
# perf trace -i perf.data
File perf.data not owned by current user or root (use -f to override)
# perf trace -i perf.data -f
Error: unknown switch `f'
usage: perf trace [<options>] [<command>]
or: perf trace [<options>] -- <command> [<options>]
or: perf trace record [<options>] [<command>]
or: perf trace record [<options>] -- <command> [<options>]
--event <event> event selector. use 'perf list' to list
available events
--comm show the thread COMM next to its id
--tool_stats show tool stats
-e, --expr <expr> list of events to trace
-o, --output <file> output file name
-i, --input <file> Analyze events in file
-p, --pid <pid> trace events on existing process id
-t, --tid <tid> trace events on existing thread id
--filter-pids <float>
...
As shown above, the -f option does not work at all.
After this patch:
# perf trace -i perf.data
File perf.data not owned by current user or root (use -f to override)
# perf trace -i perf.data -f
0.056 ( 0.002 ms): ls/47325 brk( ...
0.108 ( 0.018 ms): ls/47325 mmap(len: 4096, prot: READ|WRITE, ...
0.145 ( 0.013 ms): ls/47325 access(filename: 0x7f31259a0eb0, ...
0.172 ( 0.008 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.180 ( 0.004 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.185 ( 0.004 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.189 ( 0.003 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.195 ( 0.004 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.199 ( 0.002 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.205 ( 0.004 ms): ls/47325 open(filename: 0x7fffeb9a0d00, ...
0.211 ( 0.004 ms): ls/47325 stat(filename: 0x7fffeb9a0d00, ...
0.220 ( 0.007 ms): ls/47325 open(filename: 0x7f312599e8ff, ...
...
...
As shown above, the -f option really works now.
Signed-off-by: Yunlong Song <yunlong.song@huawei.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1427982439-27388-10-git-send-email-yunlong.song@huawei.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-04-02 13:47:18 +00:00
|
|
|
OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
|
2016-04-08 11:34:15 +00:00
|
|
|
OPT_CALLBACK(0, "call-graph", &trace.opts,
|
|
|
|
"record_mode[,record_size]", record_callchain_help,
|
|
|
|
&record_parse_callchain_opt),
|
2016-04-11 18:49:11 +00:00
|
|
|
OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
|
|
|
|
"Show the kernel callchains on the syscall exit path"),
|
perf trace: Introduce --min-stack filter
Counterpart to --max-stack, to help focusing on deeply nested calls. Can
be combined with --duration, etc.
E.g.:
System wide syscall tracing looking for call stacks longer than 66:
# trace --mmap-pages 32768 --filter-pid 2711 --call-graph dwarf,16384 --min-stack 66
Or more compactly:
# trace -m 32768 --filt 2711 --call dwarf,16384 --min-st 66
363.027 ( 0.002 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24230, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.038 ( 0.006 ms): gnome-shell/2287 writev(fd: 5<socket:[32540]>, vec: 0x7ffc5ea243a0, vlen: 3 ) = 4
__GI___writev+0x2d (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x359 (/usr/lib64/libxcb.so.1.1.0)
_xcb_out_send+0x4d (/usr/lib64/libxcb.so.1.1.0)
xcb_writev+0x45 (/usr/lib64/libxcb.so.1.1.0)
_XSend+0x19e (/usr/lib64/libX11.so.6.3.0)
_XReply+0x82 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
363.086 ( 0.042 ms): gnome-shell/2287 poll(ufds: 0x7ffc5ea24250, nfds: 1, timeout_msecs: 4294967295 ) = 1
[0xf6fdd] (/usr/lib64/libc-2.22.so)
_xcb_conn_wait+0x92 (/usr/lib64/libxcb.so.1.1.0)
wait_for_reply+0xb7 (/usr/lib64/libxcb.so.1.1.0)
xcb_wait_for_reply+0x61 (/usr/lib64/libxcb.so.1.1.0)
_XReply+0x127 (/usr/lib64/libX11.so.6.3.0)
XSync+0x4d (/usr/lib64/libX11.so.6.3.0)
dri3_bind_tex_image+0x42 (/usr/lib64/libGL.so.1.2.0)
_cogl_winsys_texture_pixmap_x11_update+0x117 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_update+0x67 (/usr/lib64/libcogl.so.20.4.1)
_cogl_texture_pixmap_x11_pre_paint+0x13 (/usr/lib64/libcogl.so.20.4.1)
_cogl_pipeline_layer_pre_paint+0x5e (/usr/lib64/libcogl.so.20.4.1)
_cogl_rectangles_validate_layer_cb+0x1b (/usr/lib64/libcogl.so.20.4.1)
cogl_pipeline_foreach_layer+0xbe (/usr/lib64/libcogl.so.20.4.1)
_cogl_framebuffer_draw_multitextured_rectangles+0x77 (/usr/lib64/libcogl.so.20.4.1)
cogl_framebuffer_draw_multitextured_rectangle+0x51 (/usr/lib64/libcogl.so.20.4.1)
paint_clipped_rectangle+0xb6 (/usr/lib64/libmutter.so.0.0.0)
meta_shaped_texture_paint+0x3e3 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_actor_paint+0x14b (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_real_paint+0x20 (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_window_group_paint+0x19f (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
[0x3d970] (/usr/lib64/gnome-shell/libgnome-shell.so)
_g_closure_invoke_va+0xb2 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_paint+0x3a (/usr/lib64/libclutter-1.0.so.0.2400.2)
meta_stage_paint+0x45 (/usr/lib64/libmutter.so.0.0.0)
_g_closure_invoke_va+0x164 (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit_valist+0xc0d (/usr/lib64/libgobject-2.0.so.0.4600.2)
g_signal_emit+0x8f (/usr/lib64/libgobject-2.0.so.0.4600.2)
clutter_actor_continue_paint+0x2bb (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_actor_paint.part.41+0x47b (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_paint+0x17b (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_stage_cogl_redraw+0x496 (/usr/lib64/libclutter-1.0.so.0.2400.2)
_clutter_stage_do_update+0x117 (/usr/lib64/libclutter-1.0.so.0.2400.2)
clutter_clock_dispatch+0x169 (/usr/lib64/libclutter-1.0.so.0.2400.2)
g_main_context_dispatch+0x15a (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_context_iterate.isra.29+0x1e0 (/usr/lib64/libglib-2.0.so.0.4600.2)
g_main_loop_run+0xc2 (/usr/lib64/libglib-2.0.so.0.4600.2)
meta_run+0x2c (/usr/lib64/libmutter.so.0.0.0)
main+0x3f7 (/usr/bin/gnome-shell)
__libc_start_main+0xf0 (/usr/lib64/libc-2.22.so)
[0x2909] (/usr/bin/gnome-shell)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-jncuxju9fibq2rl6olhqwjw6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-15 14:10:31 +00:00
|
|
|
OPT_UINTEGER(0, "min-stack", &trace.min_stack,
|
|
|
|
"Set the minimum stack depth when parsing the callchain, "
|
|
|
|
"anything below the specified depth will be ignored."),
|
2016-04-14 21:29:08 +00:00
|
|
|
OPT_UINTEGER(0, "max-stack", &trace.max_stack,
|
|
|
|
"Set the maximum stack depth when parsing the callchain, "
|
|
|
|
"anything beyond the specified depth will be ignored. "
|
2016-04-27 13:16:24 +00:00
|
|
|
"Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
|
2015-06-17 13:51:11 +00:00
|
|
|
OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
|
|
|
|
"per thread proc mmap processing timeout in ms"),
|
perf trace: Implement --delay
In the perf wiki todo-list[1], there is an entry regarding initial-delay
and 'perf trace'; the following small patch tries to fulfill this point.
It has been generated against the branch tip/perf/core.
It has only been implemented in the "trace__run" case.
Ex.:
$ sudo strace -- ./perf trace --delay 5 sleep 1 2>&1
...
fcntl(7, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
ioctl(7, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
ioctl(11, PERF_EVENT_IOC_SET_OUTPUT, 0x7) = 0
fcntl(11, F_SETFL, O_RDONLY|O_NONBLOCK) = 0
ioctl(11, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0
write(6, "\0", 1) = 1
close(6) = 0
nanosleep({0, 5000000}, NULL) = 0 # DELAY OF 5 MS BEFORE ENABLING THE EVENTS
ioctl(3, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(4, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(5, PERF_EVENT_IOC_ENABLE, 0) = 0
ioctl(7, PERF_EVENT_IOC_ENABLE, 0) = 0
...
[1]: https://perf.wiki.kernel.org/index.php/Todo
Signed-off-by: Alexis Berlemont <alexis.berlemont@gmail.com>
Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20161010054328.4028-2-alexis.berlemont@gmail.com
[ Add entry to the manpage, cut'n'pasted from stat's and record's ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-10-10 05:43:28 +00:00
|
|
|
OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
|
|
|
|
"ms to wait before starting measurement after program "
|
|
|
|
"start"),
|
2012-09-26 23:05:56 +00:00
|
|
|
OPT_END()
|
|
|
|
};
|
2016-04-16 12:36:32 +00:00
|
|
|
bool __maybe_unused max_stack_user_set = true;
|
2016-04-15 20:52:34 +00:00
|
|
|
bool mmap_pages_user_set = true;
|
2015-03-18 13:35:57 +00:00
|
|
|
const char * const trace_subcommands[] = { "record", NULL };
|
2012-09-26 23:05:56 +00:00
|
|
|
int err;
|
2012-10-05 05:02:13 +00:00
|
|
|
char bf[BUFSIZ];
|
2012-09-26 23:05:56 +00:00
|
|
|
|
2015-02-24 18:35:55 +00:00
|
|
|
signal(SIGSEGV, sighandler_dump_stack);
|
|
|
|
signal(SIGFPE, sighandler_dump_stack);
|
|
|
|
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
trace.evlist = perf_evlist__new();
|
2016-04-04 16:32:20 +00:00
|
|
|
trace.sctbl = syscalltbl__new();
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
|
2016-04-04 16:32:20 +00:00
|
|
|
if (trace.evlist == NULL || trace.sctbl == NULL) {
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
pr_err("Not enough memory to run!\n");
|
2015-05-11 12:28:36 +00:00
|
|
|
err = -ENOMEM;
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2015-03-18 13:35:57 +00:00
|
|
|
argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
|
|
|
|
trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
|
2013-11-12 16:31:15 +00:00
|
|
|
|
2016-04-08 15:07:24 +00:00
|
|
|
err = bpf__setup_stdout(trace.evlist);
|
|
|
|
if (err) {
|
|
|
|
bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
|
|
|
|
pr_err("ERROR: Setup BPF stdout failed: %s\n", bf);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2016-04-12 19:05:02 +00:00
|
|
|
err = -1;
|
|
|
|
|
2014-06-26 16:14:25 +00:00
|
|
|
if (trace.trace_pgfaults) {
|
|
|
|
trace.opts.sample_address = true;
|
|
|
|
trace.opts.sample_time = true;
|
|
|
|
}
|
|
|
|
|
2016-04-15 20:52:34 +00:00
|
|
|
if (trace.opts.mmap_pages == UINT_MAX)
|
|
|
|
mmap_pages_user_set = false;
|
|
|
|
|
2016-04-15 19:41:19 +00:00
|
|
|
if (trace.max_stack == UINT_MAX) {
|
2016-05-19 14:34:06 +00:00
|
|
|
trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl_perf_event_max_stack;
|
2016-04-15 19:41:19 +00:00
|
|
|
max_stack_user_set = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef HAVE_DWARF_UNWIND_SUPPORT
|
2016-05-19 22:00:27 +00:00
|
|
|
if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled && trace.trace_syscalls)
|
2016-04-15 19:41:19 +00:00
|
|
|
record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
|
|
|
|
#endif
|
|
|
|
|
2016-04-18 15:09:08 +00:00
|
|
|
if (callchain_param.enabled) {
|
2016-04-15 20:52:34 +00:00
|
|
|
if (!mmap_pages_user_set && geteuid() == 0)
|
|
|
|
trace.opts.mmap_pages = perf_event_mlock_kb_in_pages() * 4;
|
|
|
|
|
2016-04-08 11:34:15 +00:00
|
|
|
symbol_conf.use_callchain = true;
|
2016-04-15 20:52:34 +00:00
|
|
|
}
|
2016-04-08 11:34:15 +00:00
|
|
|
|
perf trace: Allow mixing with other events
Basically adopting 'perf record' --event command line argument syntax:
# trace -e \!mprotect,mmap,munmap,open,close,read,fstat,access,arch_prctl --event sched:*switch,sched:*exec,sched:*exit usleep 1
0.048 ( ): sched:sched_process_exec:filename=/bin/usleep pid=24732 old_pid=24732)
0.078 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.430 (0.002 ms): usleep/24732 brk( ) = 0x78f000
0.434 (0.003 ms): usleep/24732 brk(brk: 0x7b0000 ) = 0x7b0000
0.438 (0.001 ms): usleep/24732 brk( ) = 0x7b0000
0.460 (0.004 ms): usleep/24732 nanosleep(rqtp: 0x7ffff3696a40) ...
0.460 ( ): sched:sched_switch:prev_comm=usleep prev_pid=24732 prev_prio=120 prev_state=S ==> next_comm=swapper/1 next_pid=0 next_prio=120)
0.515 (0.058 ms): usleep/24732 ... [continued]: nanosleep()) = 0
0.520 (0.000 ms): usleep/24732 exit_group(
0.550 ( ): sched:sched_process_exit:comm=usleep pid=24732 prio=120)
#
Next steps, probably in this order:
1) Use ordered_events code, the logic in trace needs the events to be
time ordered when needed, i.e. when multiple CPUs are involved.
2) Callchains!
3) Automatically account for interruptions when saying how long things
took.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: David Ahern <dsahern@gmail.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/n/tip-gpst8mph575yb4wgf91qibyb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-03 15:58:57 +00:00
|
|
|
if (trace.evlist->nr_entries > 0)
|
|
|
|
evlist__set_evsel_handler(trace.evlist, trace__event_handler);
|
|
|
|
|
2014-06-26 16:14:26 +00:00
|
|
|
if ((argc >= 1) && (strcmp(argv[0], "record") == 0))
|
|
|
|
return trace__record(&trace, argc-1, &argv[1]);
|
|
|
|
|
|
|
|
/* summary_only implies summary option, but don't overwrite summary if set */
|
|
|
|
if (trace.summary_only)
|
|
|
|
trace.summary = trace.summary_only;
|
|
|
|
|
2015-02-06 09:16:45 +00:00
|
|
|
if (!trace.trace_syscalls && !trace.trace_pgfaults &&
|
|
|
|
trace.evlist->nr_entries == 0 /* Was --events used? */) {
|
2014-06-26 16:14:28 +00:00
|
|
|
pr_err("Please specify something to trace.\n");
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2017-01-09 20:26:26 +00:00
|
|
|
if (!trace.trace_syscalls && trace.ev_qualifier) {
|
2016-04-12 19:05:02 +00:00
|
|
|
pr_err("The -e option can't be used with --no-syscalls.\n");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
if (output_name != NULL) {
|
|
|
|
err = trace__open_output(&trace, output_name);
|
|
|
|
if (err < 0) {
|
|
|
|
perror("failed to create output file");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-04-04 16:32:20 +00:00
|
|
|
trace.open_id = syscalltbl__id(trace.sctbl, "open");
|
|
|
|
|
2013-11-12 19:46:16 +00:00
|
|
|
err = target__validate(&trace.opts.target);
|
2012-10-05 05:02:13 +00:00
|
|
|
if (err) {
|
2013-11-12 19:46:16 +00:00
|
|
|
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace.output, "%s", bf);
|
|
|
|
goto out_close;
|
2012-10-05 05:02:13 +00:00
|
|
|
}
|
|
|
|
|
2013-11-12 19:46:16 +00:00
|
|
|
err = target__parse_uid(&trace.opts.target);
|
2012-09-26 23:05:56 +00:00
|
|
|
if (err) {
|
2013-11-12 19:46:16 +00:00
|
|
|
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
|
2013-08-19 15:01:10 +00:00
|
|
|
fprintf(trace.output, "%s", bf);
|
|
|
|
goto out_close;
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|
|
|
|
|
2013-11-12 19:46:16 +00:00
|
|
|
if (!argc && target__none(&trace.opts.target))
|
2012-10-05 05:02:14 +00:00
|
|
|
trace.opts.target.system_wide = true;
|
|
|
|
|
2013-08-29 04:29:52 +00:00
|
|
|
if (input_name)
|
|
|
|
err = trace__replay(&trace);
|
|
|
|
else
|
|
|
|
err = trace__run(&trace, argc, argv);
|
2012-10-17 20:13:12 +00:00
|
|
|
|
2013-08-19 15:01:10 +00:00
|
|
|
out_close:
|
|
|
|
if (output_name != NULL)
|
|
|
|
fclose(trace.output);
|
|
|
|
out:
|
2012-10-17 20:13:12 +00:00
|
|
|
return err;
|
2012-09-26 23:05:56 +00:00
|
|
|
}
|