2015-08-28 22:02:37 +07:00
|
|
|
/*
|
|
|
|
* 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 22:29:18 +07:00
|
|
|
#include <traceevent/event-parse.h>
|
2015-09-02 14:56:35 +07:00
|
|
|
#include <api/fs/tracing_path.h>
|
2018-11-07 20:04:51 +07:00
|
|
|
#include <bpf/bpf.h>
|
perf trace: Allow dumping a BPF map after setting up BPF events
Initial use case:
Dumping the maps setup by tools/perf/examples/bpf/augmented_raw_syscalls.c,
which so far are just booleans, showing just non-zeroed entries:
# cat ~/.perfconfig
[llvm]
dump-obj = true
clang-opt = -g
[trace]
#add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
add_events = /wb/augmented_raw_syscalls.o
$ date
Tue Feb 19 16:29:33 -03 2019
$ ls -la /wb/augmented_raw_syscalls.o
-rwxr-xr-x. 1 root root 14048 Jan 24 12:09 /wb/augmented_raw_syscalls.o
$ file /wb/augmented_raw_syscalls.o
/wb/augmented_raw_syscalls.o: ELF 64-bit LSB relocatable, eBPF, version 1 (SYSV), with debug_info, not stripped
$
# trace -e recvmmsg,sendmmsg --map-dump foobar
ERROR: BPF map "foobar" not found
# trace -e recvmmsg,sendmmsg --map-dump filtered_pids
ERROR: BPF map "filtered_pids" not found
# trace -e recvmmsg,sendmmsg --map-dump pids_filtered
[2583] = 1,
[2267] = 1,
^Z
[1]+ Stopped trace -e recvmmsg,sendmmsg --map-dump pids_filtered
# pidof trace
2267
# ps ax|grep gnome-terminal|grep -v grep
2583 ? Ssl 58:33 /usr/libexec/gnome-terminal-server
^C
# trace -e recvmmsg,sendmmsg --map-dump syscalls
[299] = 1,
[307] = 1,
^C
# grep x64_recvmmsg arch/x86/entry/syscalls/syscall_64.tbl
299 64 recvmmsg __x64_sys_recvmmsg
# grep x64_sendmmsg arch/x86/entry/syscalls/syscall_64.tbl
307 64 sendmmsg __x64_sys_sendmmsg
#
Next step probably will be something like 'perf stat's --interval-print and
--interval-clear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-ztxj25rtx37ixo9cfajt8ocy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-20 02:17:33 +07:00
|
|
|
#include "util/bpf_map.h"
|
2012-09-27 06:05:56 +07:00
|
|
|
#include "builtin.h"
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
#include "util/cgroup.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>
2012-10-07 04:43:19 +07:00
|
|
|
#include "util/color.h"
|
perf trace: Allow specifying a set of events to add in perfconfig
To add augmented_raw_syscalls to the events speficied by the user, or be
the only one if no events were specified by the user, one can add this
to perfconfig:
# cat ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
#
I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it
always load, this way:
# perf trace -e open* cat /etc/passwd > /dev/null
0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 03:30:20 +07:00
|
|
|
#include "util/config.h"
|
2013-08-23 02:49:54 +07:00
|
|
|
#include "util/debug.h"
|
2018-01-19 15:56:16 +07:00
|
|
|
#include "util/env.h"
|
2017-04-26 01:30:47 +07:00
|
|
|
#include "util/event.h"
|
2012-09-27 06:05:56 +07:00
|
|
|
#include "util/evlist.h"
|
2015-12-15 22:39:39 +07:00
|
|
|
#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>
2012-10-07 04:43:19 +07:00
|
|
|
#include "util/machine.h"
|
2019-01-27 19:42:37 +07:00
|
|
|
#include "util/map.h"
|
2019-01-28 06:03:34 +07:00
|
|
|
#include "util/symbol.h"
|
2017-04-18 21:33:48 +07:00
|
|
|
#include "util/path.h"
|
2013-08-29 11:29:52 +07:00
|
|
|
#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>
2012-10-07 04:43:19 +07:00
|
|
|
#include "util/thread.h"
|
2015-12-15 22:39:39 +07:00
|
|
|
#include <subcmd/parse-options.h>
|
2013-08-09 22:28:31 +07:00
|
|
|
#include "util/strlist.h"
|
2013-08-29 11:29:53 +07:00
|
|
|
#include "util/intlist.h"
|
2012-09-27 06:05:56 +07:00
|
|
|
#include "util/thread_map.h"
|
2013-10-09 10:26:53 +07:00
|
|
|
#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>
2017-03-15 02:19:30 +07:00
|
|
|
#include "trace/beauty/beauty.h"
|
2013-12-03 20:09:24 +07:00
|
|
|
#include "trace-event.h"
|
2013-12-05 09:41:39 +07:00
|
|
|
#include "util/parse-events.h"
|
2016-02-26 16:31:54 +07:00
|
|
|
#include "util/bpf-loader.h"
|
2016-04-08 18:34:15 +07:00
|
|
|
#include "callchain.h"
|
2017-04-18 02:23:22 +07:00
|
|
|
#include "print_binary.h"
|
2017-04-18 02:51:59 +07:00
|
|
|
#include "string2.h"
|
2016-04-04 23:32:20 +07:00
|
|
|
#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 22:47:16 +07:00
|
|
|
#include "rb_resort.h"
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2017-04-18 20:46:11 +07:00
|
|
|
#include <errno.h>
|
2017-04-18 01:23:08 +07:00
|
|
|
#include <inttypes.h>
|
2017-04-20 05:06:30 +07:00
|
|
|
#include <poll.h>
|
2017-04-20 01:49:18 +07:00
|
|
|
#include <signal.h>
|
2012-09-27 06:05:56 +07:00
|
|
|
#include <stdlib.h>
|
2017-01-10 03:26:26 +07:00
|
|
|
#include <string.h>
|
2015-09-07 15:38:06 +07:00
|
|
|
#include <linux/err.h>
|
2016-03-31 05:43:32 +07:00
|
|
|
#include <linux/filter.h>
|
2017-04-17 21:39:06 +07:00
|
|
|
#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>
2016-03-31 06:02:15 +07:00
|
|
|
#include <linux/random.h>
|
2016-04-15 04:29:08 +07:00
|
|
|
#include <linux/stringify.h>
|
2016-08-06 01:40:30 +07:00
|
|
|
#include <linux/time64.h>
|
2018-01-23 02:42:16 +07:00
|
|
|
#include <fcntl.h>
|
2018-12-27 23:32:59 +07:00
|
|
|
#include <sys/sysmacros.h>
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2017-04-18 02:10:49 +07:00
|
|
|
#include "sane_ctype.h"
|
|
|
|
|
2015-05-15 03:39:03 +07:00
|
|
|
#ifndef O_CLOEXEC
|
|
|
|
# define O_CLOEXEC 02000000
|
|
|
|
#endif
|
|
|
|
|
2017-07-14 03:14:11 +07:00
|
|
|
#ifndef F_LINUX_SPECIFIC_BASE
|
|
|
|
# define F_LINUX_SPECIFIC_BASE 1024
|
|
|
|
#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>
2016-04-07 04:02:41 +07:00
|
|
|
struct trace {
|
|
|
|
struct perf_tool tool;
|
2016-04-04 23:32:20 +07:00
|
|
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
struct {
|
|
|
|
int max;
|
|
|
|
struct syscall *table;
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
struct bpf_map *map;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
struct {
|
|
|
|
struct perf_evsel *sys_enter,
|
2018-08-08 02:21:44 +07:00
|
|
|
*sys_exit,
|
|
|
|
*augmented;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
} events;
|
|
|
|
} syscalls;
|
perf trace: Allow dumping a BPF map after setting up BPF events
Initial use case:
Dumping the maps setup by tools/perf/examples/bpf/augmented_raw_syscalls.c,
which so far are just booleans, showing just non-zeroed entries:
# cat ~/.perfconfig
[llvm]
dump-obj = true
clang-opt = -g
[trace]
#add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
add_events = /wb/augmented_raw_syscalls.o
$ date
Tue Feb 19 16:29:33 -03 2019
$ ls -la /wb/augmented_raw_syscalls.o
-rwxr-xr-x. 1 root root 14048 Jan 24 12:09 /wb/augmented_raw_syscalls.o
$ file /wb/augmented_raw_syscalls.o
/wb/augmented_raw_syscalls.o: ELF 64-bit LSB relocatable, eBPF, version 1 (SYSV), with debug_info, not stripped
$
# trace -e recvmmsg,sendmmsg --map-dump foobar
ERROR: BPF map "foobar" not found
# trace -e recvmmsg,sendmmsg --map-dump filtered_pids
ERROR: BPF map "filtered_pids" not found
# trace -e recvmmsg,sendmmsg --map-dump pids_filtered
[2583] = 1,
[2267] = 1,
^Z
[1]+ Stopped trace -e recvmmsg,sendmmsg --map-dump pids_filtered
# pidof trace
2267
# ps ax|grep gnome-terminal|grep -v grep
2583 ? Ssl 58:33 /usr/libexec/gnome-terminal-server
^C
# trace -e recvmmsg,sendmmsg --map-dump syscalls
[299] = 1,
[307] = 1,
^C
# grep x64_recvmmsg arch/x86/entry/syscalls/syscall_64.tbl
299 64 recvmmsg __x64_sys_recvmmsg
# grep x64_sendmmsg arch/x86/entry/syscalls/syscall_64.tbl
307 64 sendmmsg __x64_sys_sendmmsg
#
Next step probably will be something like 'perf stat's --interval-print and
--interval-clear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-ztxj25rtx37ixo9cfajt8ocy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-20 02:17:33 +07:00
|
|
|
struct {
|
|
|
|
struct bpf_map *map;
|
|
|
|
} dump;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
struct record_opts opts;
|
|
|
|
struct perf_evlist *evlist;
|
|
|
|
struct machine *host;
|
|
|
|
struct thread *current;
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
struct cgroup *cgroup;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
u64 base_time;
|
|
|
|
FILE *output;
|
|
|
|
unsigned long nr_events;
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
unsigned long nr_events_printed;
|
|
|
|
unsigned long max_events;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
struct strlist *ev_qualifier;
|
|
|
|
struct {
|
|
|
|
size_t nr;
|
|
|
|
int *entries;
|
|
|
|
} ev_qualifier_ids;
|
|
|
|
struct {
|
|
|
|
size_t nr;
|
|
|
|
pid_t *entries;
|
2018-11-07 20:04:51 +07:00
|
|
|
struct bpf_map *map;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
} filter_pids;
|
|
|
|
double duration_filter;
|
|
|
|
double runtime_ms;
|
|
|
|
struct {
|
|
|
|
u64 vfs_getname,
|
|
|
|
proc_getname;
|
|
|
|
} stats;
|
2016-04-15 04:29:08 +07:00
|
|
|
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 21:10:31 +07:00
|
|
|
unsigned int min_stack;
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
int raw_augmented_syscalls_args_size;
|
2018-11-03 18:19:56 +07:00
|
|
|
bool raw_augmented_syscalls;
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
bool sort_events;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
bool not_ev_qualifier;
|
|
|
|
bool live;
|
|
|
|
bool full_time;
|
|
|
|
bool sched;
|
|
|
|
bool multiple_threads;
|
|
|
|
bool summary;
|
|
|
|
bool summary_only;
|
perf trace: Show only failing syscalls
For instance:
# 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
# perf trace --failure sleep 1
0.043 ( 0.010 ms): sleep/10978 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
For reference, here are all the syscalls in this case:
# perf trace sleep 1
? ( ): sleep/10976 ... [continued]: execve()) = 0
0.027 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.044 ( 0.010 ms): sleep/10976 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
0.057 ( 0.006 ms): sleep/10976 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.064 ( 0.002 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b370) = 0
0.067 ( 0.003 ms): sleep/10976 mmap(len: 111457, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec8615000
0.071 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.080 ( 0.007 ms): sleep/10976 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.088 ( 0.002 ms): sleep/10976 read(fd: 3, buf: 0x7fffac22b538, count: 832) = 832
0.092 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b3d0) = 0
0.094 ( 0.002 ms): sleep/10976 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7feec8613000
0.099 ( 0.004 ms): sleep/10976 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7feec8057000
0.104 ( 0.007 ms): sleep/10976 mprotect(start: 0x7feec8203000, len: 2097152) = 0
0.112 ( 0.005 ms): sleep/10976 mmap(addr: 0x7feec8403000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1753088) = 0x7feec8403000
0.120 ( 0.003 ms): sleep/10976 mmap(addr: 0x7feec8409000, len: 14976, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED) = 0x7feec8409000
0.128 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.139 ( 0.001 ms): sleep/10976 arch_prctl(option: 4098, arg2: 140663540761856) = 0
0.186 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8403000, len: 16384, prot: READ) = 0
0.204 ( 0.003 ms): sleep/10976 mprotect(start: 0x55bdc0ec3000, len: 4096, prot: READ) = 0
0.209 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8631000, len: 4096, prot: READ) = 0
0.214 ( 0.010 ms): sleep/10976 munmap(addr: 0x7feec8615000, len: 111457) = 0
0.269 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.271 ( 0.002 ms): sleep/10976 brk(brk: 0x55bdc2d25000) = 0x55bdc2d25000
0.274 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d25000
0.278 ( 0.007 ms): sleep/10976 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.288 ( 0.001 ms): sleep/10976 fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7feec8408aa0) = 0
0.290 ( 0.003 ms): sleep/10976 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec1488000
0.297 ( 0.001 ms): sleep/10976 close(fd: 3</usr/lib/locale/locale-archive>) = 0
0.325 (1000.193 ms): sleep/10976 nanosleep(rqtp: 0x7fffac22c0b0) = 0
1000.560 ( 0.006 ms): sleep/10976 close(fd: 1) = 0
1000.573 ( 0.005 ms): sleep/10976 close(fd: 2) = 0
1000.596 ( ): sleep/10976 exit_group()
#
And can be done systemwide, etc, with backtraces:
# perf trace --max-stack=16 --failure sleep 1
0.048 ( 0.015 ms): sleep/11092 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
__access (inlined)
dl_main (/usr/lib64/ld-2.26.so)
#
Or for some specific syscalls:
# perf trace --max-stack=16 -e openat --failure cat /tmp/rien
cat: /tmp/rien: No such file or directory
0.251 ( 0.012 ms): cat/11106 openat(dfd: CWD, filename: /tmp/rien) = -1 ENOENT No such file or directory
__libc_open64 (inlined)
main (/usr/bin/cat)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/cat)
#
Look for inotify* syscalls that fail, system wide, for 2 seconds, with backtraces:
# perf trace -a --max-stack=16 --failure -e inotify* sleep 2
819.165 ( 0.058 ms): gmain/1724 inotify_add_watch(fd: 8<anon_inode:inotify>, pathname: /home/acme/~, mask: 16789454) = -1 ENOENT No such file or directory
__GI_inotify_add_watch (inlined)
_ik_watch (/usr/lib64/libgio-2.0.so.0.5400.3)
_ip_start_watching (/usr/lib64/libgio-2.0.so.0.5400.3)
im_scan_missing (/usr/lib64/libgio-2.0.so.0.5400.3)
g_timeout_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iterate.isra.23 (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iteration (/usr/lib64/libglib-2.0.so.0.5400.3)
glib_worker_main (/usr/lib64/libglib-2.0.so.0.5400.3)
g_thread_proxy (/usr/lib64/libglib-2.0.so.0.5400.3)
start_thread (/usr/lib64/libpthread-2.26.so)
__GI___clone (inlined)
#
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: https://lkml.kernel.org/n/tip-8f7d3mngaxvi7tlzloz3n7cs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-29 22:22:59 +07:00
|
|
|
bool failure_only;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
bool show_comm;
|
2018-01-22 21:38:54 +07:00
|
|
|
bool print_sample;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
bool show_tool_stats;
|
|
|
|
bool trace_syscalls;
|
2016-04-12 01:49:11 +07:00
|
|
|
bool kernel_syscallchains;
|
perf trace: Make the alignment of the syscall args be configurable
Since the start 'perf trace' aligns the parens enclosing the list of
syscall args to align the syscall results, allow this to be
configurable, keeping the default of 70. Using:
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC) = 3
close(3) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC) = 3
close(3) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC) = 3
close(3) = 0
nanosleep(0x7ffc00de66f0, 0) = 0
close(1) = 0
close(2) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-r8cbhoz1lr5npq9tutpvoigr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 23:40:49 +07:00
|
|
|
s16 args_alignment;
|
perf trace: Allow configuring if the syscall start timestamp should be printed
# trace -e open*,close,*sleep sleep 1
0.000 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
0.016 close(fd: 3 ) = 0
0.024 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
0.074 close(fd: 3 ) = 0
0.235 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.251 close(fd: 3 ) = 0
0.285 nanosleep(rqtp: 0x7ffd68e6d620, rmtp: 0 ) = 0
1000.386 close(fd: 1 ) = 0
1000.395 close(fd: 2 ) = 0
#
# perf config trace.show_timestamp=no
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: , flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7fffa79c38e0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mjjnicy48367jah6ls4k0nk8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:17:19 +07:00
|
|
|
bool show_tstamp;
|
2018-12-14 20:22:18 +07:00
|
|
|
bool show_duration;
|
2018-12-14 20:12:09 +07:00
|
|
|
bool show_zeros;
|
perf trace: Allow suppressing the syscall argument names
To show just the values:
Default:
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Remove it:
# perf config trace.show_arg_names=no
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3
close(3 ) = 0
nanosleep(0x7ffced3a8c40, 0 ) = 0
close(1 ) = 0
close(2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:32:02 +07:00
|
|
|
bool show_arg_names;
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
bool show_string_prefix;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
bool force;
|
|
|
|
bool vfs_getname;
|
|
|
|
int trace_pgfaults;
|
2018-12-05 23:05:09 +07:00
|
|
|
struct {
|
|
|
|
struct ordered_events data;
|
|
|
|
u64 last;
|
|
|
|
} oe;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
};
|
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 08:47:54 +07:00
|
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
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>
2015-02-20 03:00:22 +07:00
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
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>
2015-02-20 03:00:22 +07:00
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
return bswap_##bits(value);\
|
|
|
|
}
|
|
|
|
|
|
|
|
TP_UINT_FIELD__SWAPPED(16);
|
|
|
|
TP_UINT_FIELD__SWAPPED(32);
|
|
|
|
TP_UINT_FIELD__SWAPPED(64);
|
|
|
|
|
2018-08-03 01:03:02 +07:00
|
|
|
static int __tp_field__init_uint(struct tp_field *field, int size, int offset, bool needs_swap)
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
{
|
2018-08-03 01:03:02 +07:00
|
|
|
field->offset = offset;
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
|
2018-08-03 01:03:02 +07:00
|
|
|
switch (size) {
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2018-09-20 01:56:45 +07:00
|
|
|
static int tp_field__init_uint(struct tp_field *field, struct tep_format_field *format_field, bool needs_swap)
|
2018-08-03 01:03:02 +07:00
|
|
|
{
|
|
|
|
return __tp_field__init_uint(field, format_field->size, format_field->offset, needs_swap);
|
|
|
|
}
|
|
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
static void *tp_field__ptr(struct tp_field *field, struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
return sample->raw_data + field->offset;
|
|
|
|
}
|
|
|
|
|
2018-08-03 01:03:02 +07:00
|
|
|
static int __tp_field__init_ptr(struct tp_field *field, int offset)
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
{
|
2018-08-03 01:03:02 +07:00
|
|
|
field->offset = offset;
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
field->pointer = tp_field__ptr;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-09-20 01:56:45 +07:00
|
|
|
static int tp_field__init_ptr(struct tp_field *field, struct tep_format_field *format_field)
|
2018-08-03 01:03:02 +07:00
|
|
|
{
|
|
|
|
return __tp_field__init_ptr(field, format_field->offset);
|
|
|
|
}
|
|
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
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)
|
|
|
|
{
|
2018-09-20 01:56:45 +07:00
|
|
|
struct tep_format_field *format_field = perf_evsel__field(evsel, name);
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
2018-09-20 01:56:45 +07:00
|
|
|
struct tep_format_field *format_field = perf_evsel__field(evsel, name);
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
|
|
|
|
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)
|
|
|
|
{
|
2013-12-27 03:41:15 +07:00
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
perf_evsel__delete(evsel);
|
|
|
|
}
|
|
|
|
|
2018-08-03 01:09:24 +07:00
|
|
|
static int perf_evsel__init_syscall_tp(struct perf_evsel *evsel)
|
|
|
|
{
|
|
|
|
struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
|
|
|
|
|
|
|
|
if (evsel->priv != NULL) {
|
2018-12-05 23:08:11 +07:00
|
|
|
if (perf_evsel__init_tp_uint_field(evsel, &sc->id, "__syscall_nr") &&
|
|
|
|
perf_evsel__init_tp_uint_field(evsel, &sc->id, "nr"))
|
2018-08-03 01:09:24 +07:00
|
|
|
goto out_delete;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
return -ENOMEM;
|
|
|
|
out_delete:
|
|
|
|
zfree(&evsel->priv);
|
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
static int perf_evsel__init_augmented_syscall_tp(struct perf_evsel *evsel, struct perf_evsel *tp)
|
2018-08-08 02:21:44 +07:00
|
|
|
{
|
|
|
|
struct syscall_tp *sc = evsel->priv = malloc(sizeof(struct syscall_tp));
|
|
|
|
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
if (evsel->priv != NULL) {
|
|
|
|
struct tep_format_field *syscall_id = perf_evsel__field(tp, "id");
|
|
|
|
if (syscall_id == NULL)
|
|
|
|
syscall_id = perf_evsel__field(tp, "__syscall_nr");
|
|
|
|
if (syscall_id == NULL)
|
|
|
|
goto out_delete;
|
|
|
|
if (__tp_field__init_uint(&sc->id, syscall_id->size, syscall_id->offset, evsel->needs_swap))
|
2018-08-08 02:21:44 +07:00
|
|
|
goto out_delete;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
return -ENOMEM;
|
|
|
|
out_delete:
|
|
|
|
zfree(&evsel->priv);
|
|
|
|
return -EINVAL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int perf_evsel__init_augmented_syscall_tp_args(struct perf_evsel *evsel)
|
|
|
|
{
|
|
|
|
struct syscall_tp *sc = evsel->priv;
|
|
|
|
|
|
|
|
return __tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64));
|
|
|
|
}
|
|
|
|
|
perf trace: Use the raw_syscalls:sys_enter for the augmented syscalls
Now we combine what comes from the "bpf-output" event, i.e. what is
added in the augmented_syscalls.c BPF program via the
__augmented_syscalls__ BPF map, i.e. the payload we get with
raw_syscalls:sys_enter tracepoints plus the pointer contents, right
after that payload, with the raw_syscall:sys_exit also added, without
augmentation, in the augmented_syscalls.c program.
The end result is that for the hooked syscalls, we get strace like
output with pointer expansion, something that wasn't possible before
with just raw_syscalls:sys_enter + raw_syscalls:sys_exit.
E.g.:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c ping -c 2 ::1
0.000 ( 0.008 ms): ping/19573 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.036 ( 0.006 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
0.070 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
0.095 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
0.127 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
0.156 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
0.181 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.212 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
0.242 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
0.266 ( 0.003 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
0.709 ( 0.006 ms): ping/19573 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
PING ::1(::1) 56 data bytes
1.133 ( 0.011 ms): ping/19573 connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.033 ms
1.234 ( 0.036 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
64 bytes from ::1: icmp_seq=2 ttl=64 time=0.120 ms
--- ::1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.033/0.076/0.120/0.044 ms
1002.060 ( 0.129 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, flags: CONFIRM, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
#
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat tools/perf/examples/bpf/hello.c
#include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
0.000 ( 0.008 ms): cat/20054 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.020 ( 0.005 ms): cat/20054 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.176 ( 0.011 ms): cat/20054 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.243 ( 0.006 ms): cat/20054 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c) = 3
#
Now to think how to hook on all syscalls, fallbacking to the non-augmented
raw_syscalls:sys_enter payload.
Probably the best way is to use a BPF_MAP_TYPE_PROG_ARRAY just like
samples/bpf/tracex5_kern.c does.
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: https://lkml.kernel.org/n/tip-nlt60y69o26xi59z5vtpdrj5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-09-04 02:29:39 +07:00
|
|
|
static int perf_evsel__init_augmented_syscall_tp_ret(struct perf_evsel *evsel)
|
|
|
|
{
|
|
|
|
struct syscall_tp *sc = evsel->priv;
|
|
|
|
|
|
|
|
return __tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap);
|
|
|
|
}
|
|
|
|
|
2018-08-03 00:27:09 +07:00
|
|
|
static int perf_evsel__init_raw_syscall_tp(struct perf_evsel *evsel, void *handler)
|
2013-11-12 18:51:45 +07:00
|
|
|
{
|
|
|
|
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:
|
2013-12-27 03:41:15 +07:00
|
|
|
zfree(&evsel->priv);
|
2013-11-12 18:51:45 +07:00
|
|
|
return -ENOENT;
|
|
|
|
}
|
|
|
|
|
2018-08-03 00:27:09 +07:00
|
|
|
static struct perf_evsel *perf_evsel__raw_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>
2013-11-07 02:35:57 +07:00
|
|
|
{
|
2013-11-08 02:41:19 +07:00
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
|
2013-12-05 09:41:39 +07:00
|
|
|
/* older kernel (e.g., RHEL6) use syscalls:{enter,exit} */
|
2015-09-07 15:38:06 +07:00
|
|
|
if (IS_ERR(evsel))
|
2013-12-05 09:41:39 +07:00
|
|
|
evsel = perf_evsel__newtp("syscalls", direction);
|
|
|
|
|
2015-09-07 15:38:06 +07:00
|
|
|
if (IS_ERR(evsel))
|
|
|
|
return NULL;
|
|
|
|
|
2018-08-03 00:27:09 +07:00
|
|
|
if (perf_evsel__init_raw_syscall_tp(evsel, handler))
|
2015-09-07 15:38:06 +07:00
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
|
|
|
|
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); })
|
|
|
|
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, bool show_prefix, int val)
|
2017-07-17 20:31:42 +07:00
|
|
|
{
|
|
|
|
int idx = val - sa->offset;
|
2013-09-04 01:50:28 +07:00
|
|
|
|
2018-12-18 20:54:19 +07:00
|
|
|
if (idx < 0 || idx >= sa->nr_entries || sa->entries[idx] == NULL) {
|
|
|
|
size_t printed = scnprintf(bf, size, intfmt, val);
|
|
|
|
if (show_prefix)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, " /* %s??? */", sa->prefix);
|
|
|
|
return printed;
|
|
|
|
}
|
2013-09-04 01:50:28 +07:00
|
|
|
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
return scnprintf(bf, size, "%s%s", show_prefix ? sa->prefix : "", sa->entries[idx]);
|
2013-10-09 02:00:21 +07:00
|
|
|
}
|
|
|
|
|
2013-10-09 03:17:43 +07:00
|
|
|
static size_t __syscall_arg__scnprintf_strarray(char *bf, size_t size,
|
|
|
|
const char *intfmt,
|
|
|
|
struct syscall_arg *arg)
|
2013-09-04 01:50:28 +07:00
|
|
|
{
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
return strarray__scnprintf(arg->parm, bf, size, intfmt, arg->show_string_prefix, arg->val);
|
2013-09-04 01:50:28 +07:00
|
|
|
}
|
|
|
|
|
2013-10-09 03:17:43 +07:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2013-09-04 01:50:28 +07:00
|
|
|
#define SCA_STRARRAY syscall_arg__scnprintf_strarray
|
|
|
|
|
2018-12-18 20:25:28 +07:00
|
|
|
size_t strarrays__scnprintf(struct strarrays *sas, char *bf, size_t size, const char *intfmt, bool show_prefix, int val)
|
2017-07-14 03:14:11 +07:00
|
|
|
{
|
2018-12-18 20:54:19 +07:00
|
|
|
size_t printed;
|
2017-07-14 03:14:11 +07:00
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < sas->nr_entries; ++i) {
|
|
|
|
struct strarray *sa = sas->entries[i];
|
2018-12-18 20:25:28 +07:00
|
|
|
int idx = val - sa->offset;
|
2017-07-14 03:14:11 +07:00
|
|
|
|
|
|
|
if (idx >= 0 && idx < sa->nr_entries) {
|
|
|
|
if (sa->entries[idx] == NULL)
|
|
|
|
break;
|
2018-12-18 20:25:28 +07:00
|
|
|
return scnprintf(bf, size, "%s%s", show_prefix ? sa->prefix : "", sa->entries[idx]);
|
2017-07-14 03:14:11 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-12-18 20:54:19 +07:00
|
|
|
printed = scnprintf(bf, size, intfmt, val);
|
|
|
|
if (show_prefix)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, " /* %s??? */", sas->entries[0]->prefix);
|
|
|
|
return printed;
|
2018-12-18 20:25:28 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
size_t syscall_arg__scnprintf_strarrays(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
return strarrays__scnprintf(arg->parm, bf, size, "%d", arg->show_string_prefix, arg->val);
|
2017-07-14 03:14:11 +07:00
|
|
|
}
|
|
|
|
|
2016-07-06 00:43:27 +07:00
|
|
|
#ifndef AT_FDCWD
|
|
|
|
#define AT_FDCWD -100
|
|
|
|
#endif
|
|
|
|
|
2013-09-24 21:04:32 +07:00
|
|
|
static size_t syscall_arg__scnprintf_fd_at(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
int fd = arg->val;
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
const char *prefix = "AT_FD";
|
2013-09-24 21:04:32 +07:00
|
|
|
|
|
|
|
if (fd == AT_FDCWD)
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
return scnprintf(bf, size, "%s%s", arg->show_string_prefix ? prefix : "", "CWD");
|
2013-09-24 21:04:32 +07:00
|
|
|
|
|
|
|
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
|
|
|
|
|
2017-07-14 20:19:18 +07:00
|
|
|
size_t syscall_arg__scnprintf_hex(char *bf, size_t size, struct syscall_arg *arg)
|
2013-08-24 04:14:48 +07:00
|
|
|
{
|
2013-09-03 22:20:12 +07:00
|
|
|
return scnprintf(bf, size, "%#lx", arg->val);
|
2013-08-24 04:14:48 +07:00
|
|
|
}
|
|
|
|
|
2018-12-17 22:21:09 +07:00
|
|
|
size_t syscall_arg__scnprintf_ptr(char *bf, size_t size, struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
if (arg->val == 0)
|
|
|
|
return scnprintf(bf, size, "NULL");
|
|
|
|
return syscall_arg__scnprintf_hex(bf, size, arg);
|
|
|
|
}
|
|
|
|
|
2017-07-14 20:19:18 +07:00
|
|
|
size_t syscall_arg__scnprintf_int(char *bf, size_t size, struct syscall_arg *arg)
|
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 08:47:54 +07:00
|
|
|
{
|
|
|
|
return scnprintf(bf, size, "%d", arg->val);
|
|
|
|
}
|
|
|
|
|
2017-07-14 20:34:16 +07:00
|
|
|
size_t syscall_arg__scnprintf_long(char *bf, size_t size, struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
return scnprintf(bf, size, "%ld", arg->val);
|
|
|
|
}
|
|
|
|
|
2015-10-29 21:48:18 +07:00
|
|
|
static const char *bpf_cmd[] = {
|
|
|
|
"MAP_CREATE", "MAP_LOOKUP_ELEM", "MAP_UPDATE_ELEM", "MAP_DELETE_ELEM",
|
|
|
|
"MAP_GET_NEXT_KEY", "PROG_LOAD",
|
|
|
|
};
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(bpf_cmd, "BPF_");
|
2015-10-29 21:48:18 +07:00
|
|
|
|
2013-10-09 02:00:21 +07:00
|
|
|
static const char *epoll_ctl_ops[] = { "ADD", "DEL", "MOD", };
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY_OFFSET(epoll_ctl_ops, "EPOLL_CTL_", 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 21:27:32 +07:00
|
|
|
|
2013-09-04 01:50:28 +07:00
|
|
|
static const char *itimers[] = { "REAL", "VIRTUAL", "PROF", };
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(itimers, "ITIMER_");
|
2013-09-04 01:50:28 +07:00
|
|
|
|
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 21:05:36 +07:00
|
|
|
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",
|
|
|
|
};
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(keyctl_options, "KEYCTL_");
|
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 21:05:36 +07:00
|
|
|
|
2013-09-04 02:15:12 +07:00
|
|
|
static const char *whences[] = { "SET", "CUR", "END",
|
|
|
|
#ifdef SEEK_DATA
|
|
|
|
"DATA",
|
|
|
|
#endif
|
|
|
|
#ifdef SEEK_HOLE
|
|
|
|
"HOLE",
|
|
|
|
#endif
|
|
|
|
};
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(whences, "SEEK_");
|
2013-09-02 23:46:44 +07:00
|
|
|
|
2013-09-04 02:28:58 +07:00
|
|
|
static const char *fcntl_cmds[] = {
|
|
|
|
"DUPFD", "GETFD", "SETFD", "GETFL", "SETFL", "GETLK", "SETLK",
|
2017-07-13 23:07:00 +07:00
|
|
|
"SETLKW", "SETOWN", "GETOWN", "SETSIG", "GETSIG", "GETLK64",
|
|
|
|
"SETLK64", "SETLKW64", "SETOWN_EX", "GETOWN_EX",
|
|
|
|
"GETOWNER_UIDS",
|
2013-09-04 02:28:58 +07:00
|
|
|
};
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(fcntl_cmds, "F_");
|
2013-09-04 02:28:58 +07:00
|
|
|
|
2017-07-14 03:14:11 +07:00
|
|
|
static const char *fcntl_linux_specific_cmds[] = {
|
|
|
|
"SETLEASE", "GETLEASE", "NOTIFY", [5] = "CANCELLK", "DUPFD_CLOEXEC",
|
|
|
|
"SETPIPE_SZ", "GETPIPE_SZ", "ADD_SEALS", "GET_SEALS",
|
2017-07-14 03:34:46 +07:00
|
|
|
"GET_RW_HINT", "SET_RW_HINT", "GET_FILE_RW_HINT", "SET_FILE_RW_HINT",
|
2017-07-14 03:14:11 +07:00
|
|
|
};
|
|
|
|
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY_OFFSET(fcntl_linux_specific_cmds, "F_", F_LINUX_SPECIFIC_BASE);
|
2017-07-14 03:14:11 +07:00
|
|
|
|
|
|
|
static struct strarray *fcntl_cmds_arrays[] = {
|
|
|
|
&strarray__fcntl_cmds,
|
|
|
|
&strarray__fcntl_linux_specific_cmds,
|
|
|
|
};
|
|
|
|
|
|
|
|
static DEFINE_STRARRAYS(fcntl_cmds_arrays);
|
|
|
|
|
2013-09-04 21:52:33 +07:00
|
|
|
static const char *rlimit_resources[] = {
|
|
|
|
"CPU", "FSIZE", "DATA", "STACK", "CORE", "RSS", "NPROC", "NOFILE",
|
|
|
|
"MEMLOCK", "AS", "LOCKS", "SIGPENDING", "MSGQUEUE", "NICE", "RTPRIO",
|
|
|
|
"RTTIME",
|
|
|
|
};
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(rlimit_resources, "RLIMIT_");
|
2013-09-04 21:52:33 +07:00
|
|
|
|
2013-09-04 02:37:46 +07:00
|
|
|
static const char *sighow[] = { "BLOCK", "UNBLOCK", "SETMASK", };
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(sighow, "SIG_");
|
2013-09-04 02:37:46 +07:00
|
|
|
|
2013-09-23 08:45:00 +07:00
|
|
|
static const char *clockid[] = {
|
|
|
|
"REALTIME", "MONOTONIC", "PROCESS_CPUTIME_ID", "THREAD_CPUTIME_ID",
|
2015-08-11 20:38:38 +07:00
|
|
|
"MONOTONIC_RAW", "REALTIME_COARSE", "MONOTONIC_COARSE", "BOOTTIME",
|
|
|
|
"REALTIME_ALARM", "BOOTTIME_ALARM", "SGI_CYCLE", "TAI"
|
2013-09-23 08:45:00 +07:00
|
|
|
};
|
2018-12-15 01:08:40 +07:00
|
|
|
static DEFINE_STRARRAY(clockid, "CLOCK_");
|
2013-09-23 08:45:00 +07:00
|
|
|
|
2013-09-04 21:42:27 +07:00
|
|
|
static size_t syscall_arg__scnprintf_access_mode(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
bool show_prefix = arg->show_string_prefix;
|
|
|
|
const char *suffix = "_OK";
|
2013-09-04 21:42:27 +07:00
|
|
|
size_t printed = 0;
|
|
|
|
int mode = arg->val;
|
|
|
|
|
|
|
|
if (mode == F_OK) /* 0 */
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
return scnprintf(bf, size, "F%s", show_prefix ? suffix : "");
|
2013-09-04 21:42:27 +07:00
|
|
|
#define P_MODE(n) \
|
|
|
|
if (mode & n##_OK) { \
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%s", #n, show_prefix ? suffix : ""); \
|
2013-09-04 21:42:27 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
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 22:52:04 +07:00
|
|
|
static size_t syscall_arg__scnprintf_pipe_flags(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
bool show_prefix = arg->show_string_prefix;
|
|
|
|
const char *prefix = "O_";
|
2013-09-23 22:52:04 +07:00
|
|
|
int printed = 0, flags = arg->val;
|
|
|
|
|
|
|
|
#define P_FLAG(n) \
|
|
|
|
if (flags & O_##n) { \
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%s%s", printed ? "|" : "", show_prefix ? prefix : "", #n); \
|
2013-09-23 22:52:04 +07:00
|
|
|
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
|
|
|
|
|
2016-04-13 21:55:18 +07:00
|
|
|
#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>
2016-03-31 06:02:15 +07:00
|
|
|
static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
bool show_prefix = arg->show_string_prefix;
|
|
|
|
const char *prefix = "GRND_";
|
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>
2016-03-31 06:02:15 +07:00
|
|
|
int printed = 0, flags = arg->val;
|
|
|
|
|
|
|
|
#define P_FLAG(n) \
|
|
|
|
if (flags & GRND_##n) { \
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s%s%s", printed ? "|" : "", show_prefix ? prefix : "", #n); \
|
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>
2016-03-31 06:02:15 +07:00
|
|
|
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
|
|
|
|
|
2017-07-18 01:22:47 +07:00
|
|
|
#define STRARRAY(name, array) \
|
|
|
|
{ .scnprintf = SCA_STRARRAY, \
|
|
|
|
.parm = &strarray__##array, }
|
2013-09-20 22:13:37 +07:00
|
|
|
|
2018-01-19 15:56:16 +07:00
|
|
|
#include "trace/beauty/arch_errno_names.c"
|
2016-04-13 22:10:19 +07:00
|
|
|
#include "trace/beauty/eventfd.c"
|
2016-05-06 22:45:25 +07:00
|
|
|
#include "trace/beauty/futex_op.c"
|
perf trace beauty futex: Beautify FUTEX_BITSET_MATCH_ANY
E.g.:
# strace -e futex -p 14437
strace: Process 14437 attached
futex(0x7f46f4808d70, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7f46f24e68b0, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME, 0, {tv_sec=1516636744, tv_nsec=221969000}, 0xffffffff) = -1 ETIMEDOUT (Connection timed out)
<detached ...>
#
Should pretty print that 0xffffffff value, like:
# trace -e futex --tid 14437
0.028 ( 0.005 ms): futex(uaddr: 0x7f46f4808d70, op: WAKE|PRIV, val: 1 ) = 0
0.037 (1000.092 ms): futex(uaddr: 0x7f46f24e68b0, op: WAIT_BITSET|PRIV|CLKRT, utime: 0x7f46f23fedf0, val3: MATCH_ANY) = -1 ETIMEDOUT Connection timed out
^C#
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: https://lkml.kernel.org/n/tip-raef6e352la90600yksthao1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 22:56:59 +07:00
|
|
|
#include "trace/beauty/futex_val3.c"
|
2016-04-13 22:05:44 +07:00
|
|
|
#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 22:05:51 +07:00
|
|
|
#include "trace/beauty/mode_t.c"
|
2016-04-28 05:01:52 +07:00
|
|
|
#include "trace/beauty/msg_flags.c"
|
2016-05-06 20:02:32 +07:00
|
|
|
#include "trace/beauty/open_flags.c"
|
2016-04-26 21:03:03 +07:00
|
|
|
#include "trace/beauty/perf_event_open.c"
|
2016-05-06 22:45:25 +07:00
|
|
|
#include "trace/beauty/pid.c"
|
2016-04-06 22:51:33 +07:00
|
|
|
#include "trace/beauty/sched_policy.c"
|
2016-05-11 20:32:20 +07:00
|
|
|
#include "trace/beauty/seccomp.c"
|
2016-05-06 19:58:02 +07:00
|
|
|
#include "trace/beauty/signum.c"
|
2016-04-14 23:53:10 +07:00
|
|
|
#include "trace/beauty/socket_type.c"
|
2016-04-07 00:11:36 +07:00
|
|
|
#include "trace/beauty/waitid_options.c"
|
2016-04-06 22:51:33 +07:00
|
|
|
|
2017-07-18 01:22:47 +07:00
|
|
|
struct syscall_arg_fmt {
|
|
|
|
size_t (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
|
2018-10-26 02:09:47 +07:00
|
|
|
unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val);
|
2017-07-18 01:22:47 +07:00
|
|
|
void *parm;
|
2017-07-20 01:47:30 +07:00
|
|
|
const char *name;
|
perf trace: Allow syscall arg formatters to request non suppression of zeros
The 'perf trace' tool is suppressing args set to zero, with the
exception of string tables (strarrays), which are kinda like enums, i.e.
we have maps to go from numbers to strings.
But the 'cmd' fcntl arg requires more specialized treatment, as its
value will regulate if the next fcntl syscall arg, 'arg', should be
ignored (not used) and also how to format the syscall return (fd, file
flags, etc), so add a 'show_zero" bool to struct syscall_arg_fmt, to
regulate this more explicitely.
Will be used in a following patch with fcntl, here is just the
mechanism.
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-all738jctxets8ffyizp5lzo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-18 01:59:03 +07:00
|
|
|
bool show_zero;
|
2017-07-18 01:22:47 +07:00
|
|
|
};
|
|
|
|
|
2012-09-27 06:05:56 +07:00
|
|
|
static struct syscall_fmt {
|
|
|
|
const char *name;
|
2012-09-27 23:16:00 +07:00
|
|
|
const char *alias;
|
2017-07-18 01:22:47 +07:00
|
|
|
struct syscall_arg_fmt arg[6];
|
2017-07-20 01:08:14 +07:00
|
|
|
u8 nr_args;
|
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>
2016-04-07 00:33:07 +07:00
|
|
|
bool errpid;
|
2012-09-27 06:05:56 +07:00
|
|
|
bool timeout;
|
2013-08-26 21:36:30 +07:00
|
|
|
bool hexret;
|
2012-09-27 06:05:56 +07:00
|
|
|
} syscall_fmts[] = {
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "access",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_ACCMODE, /* mode */ }, }, },
|
perf trace beauty: Beautify arch_prctl()'s arguments
This actually so far, AFAIK is available only in x86, so the code was
put in place with x86 prefixes, in arches where it is not available it
will just not be called, so no further mechanisms are needed at this
time.
Later, when other arches wire this up, we'll just look at the uname
(live sessions) or perf_env data in the perf.data header to auto-wire
the right beautifier.
With this the output is the same as produced by 'strace' when used with
the following ~/.perfconfig:
# cat ~/.perfconfig
[llvm]
dump-obj = true
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
show_zeros = yes
show_duration = no
no_inherit = yes
show_timestamp = no
show_arg_names = no
args_alignment = -40
show_prefix = yes
#
And, on fedora 29, since the string tables are generated from the kernel
sources, we don't know about 0x3001, just like strace:
--- /tmp/strace 2018-12-17 11:22:08.707586721 -0300
+++ /tmp/trace 2018-12-18 11:11:32.037512729 -0300
@@ -1,49 +1,49 @@
-arch_prctl(0x3001 /* ARCH_??? */, 0x7ffc8a92dc80) = -1 EINVAL (Invalid argument)
+arch_prctl(0x3001 /* ARCH_??? */, 0x7ffe4eb93ae0) = -1 EINVAL (Invalid argument)
-arch_prctl(ARCH_SET_FS, 0x7faf6700f540) = 0
+arch_prctl(ARCH_SET_FS, 0x7fb507364540) = 0
And that seems to be related to the CET/Shadow Stack feature, that
userland in Fedora 29 (glibc 2.28) are querying the kernel about, that
0x3001 seems to be ARCH_CET_STATUS, I'll check the situation and test
with a fedora 29 kernel to see if the other codes are used.
A diff that ignores the different pointers for different runs needs to
be put in place in the upcoming regression tests comparing 'perf trace's
output to strace's.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-73a9prs8ktkrt97trtdmdjs8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-18 21:05:56 +07:00
|
|
|
{ .name = "arch_prctl",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_X86_ARCH_PRCTL_CODE, /* code */ },
|
|
|
|
[1] = { .scnprintf = SCA_PTR, /* arg2 */ }, }, },
|
perf trace augmented_syscalls: Augment bind's 'myaddr' sockaddr arg
One more, to reuse the augmented_sockaddr_syscall_enter() macro
introduced from the augmentation of connect's sockaddr arg, also to get
a subset of the struct arg augmentations done using the manual method,
before switching to something automatic, using tracefs's format file or,
even better, BTF containing the syscall args structs.
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c
0.000 sshd/11479 bind(fd: 3<socket:[170336]>, umyaddr: { .family: NETLINK }, addrlen: 12)
1.752 sshd/11479 bind(fd: 3<socket:[170336]>, umyaddr: { .family: INET, port: 22, addr: 0.0.0.0 }, addrlen: 16)
1.924 sshd/11479 bind(fd: 4<socket:[170338]>, umyaddr: { .family: INET6, port: 22, addr: :: }, addrlen: 28)
^C#
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: https://lkml.kernel.org/n/tip-a2drqpahpmc7uwb3n3gj2plu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-29 03:03:53 +07:00
|
|
|
{ .name = "bind",
|
|
|
|
.arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* umyaddr */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "bpf",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(cmd, bpf_cmd), }, },
|
2013-08-26 22:29:38 +07:00
|
|
|
{ .name = "brk", .hexret = true,
|
2018-12-17 22:21:09 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_PTR, /* brk */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "clock_gettime",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(clk_id, clockid), }, },
|
perf trace beauty clone: Beautify syscall arguments
Now, syswide tracing, selected entries:
# trace -e clone
24417.203 ( 0.158 ms): bash/11323 clone(flags: CHILD_CLEARTID|CHILD_SETTID|0x11, child_stack: 0, parent_tidptr: 0, child_tidptr: 0x7f0778e5c9d0, tls: 0x7f0778e5c700) = 11325 (bash)
? ( ? ): bash/11325 ... [continued]: clone()) = 0
24419.355 ( 0.093 ms): bash/10586 clone(flags: CHILD_CLEARTID|CHILD_SETTID|0x11, child_stack: 0, parent_tidptr: 0, child_tidptr: 0x7f0778e5c9d0, tls: 0x7f0778e5c700) = 11326 (bash)
? ( ? ): bash/11326 ... [continued]: clone()) = 0
24419.744 ( 0.102 ms): bash/11326 clone(flags: CHILD_CLEARTID|CHILD_SETTID|0x11, child_stack: 0, parent_tidptr: 0, child_tidptr: 0x7f0778e5c9d0, tls: 0x7f0778e5c700) = 11327 (bash)
? ( ? ): bash/11327 ... [continued]: clone()) = 0
24420.138 ( 0.105 ms): bash/11327 clone(flags: CHILD_CLEARTID|CHILD_SETTID|0x11, child_stack: 0, parent_tidptr: 0, child_tidptr: 0x7f0778e5c9d0, tls: 0x7f0778e5c700) = 11328 (bash)
? ( ? ): bash/11328 ... [continued]: clone()) = 0
35747.722 ( 0.044 ms): gpg-agent/18087 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ff0755f6ff0, parent_tidptr: 0x7ff0755f79d0, child_tidptr: 0x7ff0755f79d0, tls: 0x7ff0755f7700) = 11329 (gpg-agent)
? ( ? ): gpg-agent/11329 ... [continued]: clone()) = 0
35748.359 ( 0.022 ms): gpg-agent/18087 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ff075df7ff0, parent_tidptr: 0x7ff075df89d0, child_tidptr: 0x7ff075df89d0, tls: 0x7ff075df8700) = 11330 (gpg-agent)
? ( ? ): gpg-agent/11330 ... [continued]: clone()) = 0
35781.422 ( 0.452 ms): NetworkManager/1112 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7f2f1fffedb0, parent_tidptr: 0x7f2f1ffff9d0, child_tidptr: 0x7f2f1ffff9d0, tls: 0x7f2f1ffff700) = 11331 (NetworkManager)
? ( ? ): NetworkManager/11331 ... [continued]: clone()) = 0
Need to improve the formatting of the second return, to the child, this
cset only focused on the argument formatting.
If we trace just one pid:
# trace -e clone -p 19863
0.349 ( 0.025 ms): Chrome_IOThrea/19863 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ffb84eaac70, parent_tidptr: 0x7ffb84eab9d0, child_tidptr: 0x7ffb84eab9d0, tls: 0x7ffb84eab700) = 11637 (Chrome_IOThread)
0.392 ( 0.013 ms): Chrome_IOThrea/19863 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ffb664b8c70, parent_tidptr: 0x7ffb664b99d0, child_tidptr: 0x7ffb664b99d0, tls: 0x7ffb664b9700) = 11638 (Chrome_IOThread)
0.573 ( 0.015 ms): Chrome_IOThrea/19863 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ffb6046cc70, parent_tidptr: 0x7ffb6046d9d0, child_tidptr: 0x7ffb6046d9d0, tls: 0x7ffb6046d700) = 11639 (Chrome_IOThread)
0.617 ( 0.014 ms): Chrome_IOThrea/19863 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ffb730dcc70, parent_tidptr: 0x7ffb730dd9d0, child_tidptr: 0x7ffb730dd9d0, tls: 0x7ffb730dd700) = 11640 (Chrome_IOThread)
4.350 ( 0.065 ms): Chrome_IOThrea/19863 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ffb720d9c70, parent_tidptr: 0x7ffb720da9d0, child_tidptr: 0x7ffb720da9d0, tls: 0x7ffb720da700) = 11642 (Chrome_IOThread)
5.642 ( 0.079 ms): Chrome_IOThrea/19863 clone(flags: VM|FS|FILES|SIGHAND|THREAD|SYSVSEM|SETTLS|PARENT_SETTID|CHILD_CLEARTID, child_stack: 0x7ffb718d8c70, parent_tidptr: 0x7ffb718d99d0, child_tidptr: 0x7ffb718d99d0, tls: 0x7ffb718d9700) = 11643 (Chrome_IOThread)
^C#
We'll also have to fix the argument ordering in different arches,
probably having multiple syscall_fmt entries with each possible order
and then use perf_evsel__env_arch() (if dealing with a perf.data file)
or the current system info, for live sessions.
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-am068uyubgj83snepolwhbfe@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-20 02:15:17 +07:00
|
|
|
{ .name = "clone", .errpid = true, .nr_args = 5,
|
|
|
|
.arg = { [0] = { .name = "flags", .scnprintf = SCA_CLONE_FLAGS, },
|
|
|
|
[1] = { .name = "child_stack", .scnprintf = SCA_HEX, },
|
|
|
|
[2] = { .name = "parent_tidptr", .scnprintf = SCA_HEX, },
|
|
|
|
[3] = { .name = "child_tidptr", .scnprintf = SCA_HEX, },
|
|
|
|
[4] = { .name = "tls", .scnprintf = SCA_HEX, }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "close",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_CLOSE_FD, /* fd */ }, }, },
|
perf trace augmented_syscalls: Augment connect's 'sockaddr' arg
As the first example of augmenting something other than a 'filename',
augment the 'struct sockaddr' argument for the 'connect' syscall:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c ssh -6 fedorapeople.org
0.000 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
0.042 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
1.329 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
1.362 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
1.458 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
1.478 ssh/29669 connect(fd: 3, uservaddr: { .family: LOCAL, path: /var/run/nscd/socket }, addrlen: 110)
1.683 ssh/29669 connect(fd: 3<socket:[125942]>, uservaddr: { .family: INET, port: 53, addr: 192.168.43.1 }, addrlen: 16)
4.710 ssh/29669 connect(fd: 3<socket:[125942]>, uservaddr: { .family: INET6, port: 22, addr: 2610:28:3090:3001:5054:ff:fea7:9474 }, addrlen: 28)
root@fedorapeople.org: Permission denied (publickey).
#
This is still just augmenting the syscalls:sys_enter_connect part, later
we'll wire this up to augment the enter+exit combo, like in the
tradicional 'perf trace' and 'strace' outputs.
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: https://lkml.kernel.org/n/tip-s7l541cbiqb22ifio6z7dpf6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-29 02:24:44 +07:00
|
|
|
{ .name = "connect",
|
|
|
|
.arg = { [1] = { .scnprintf = SCA_SOCKADDR, /* servaddr */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "epoll_ctl",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "eventfd2",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_EFD_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "fchmodat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "fchownat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "fcntl",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_FCNTL_CMD, /* cmd */
|
2017-07-18 02:02:52 +07:00
|
|
|
.parm = &strarrays__fcntl_cmds_arrays,
|
|
|
|
.show_zero = true, },
|
2017-07-18 01:22:47 +07:00
|
|
|
[2] = { .scnprintf = SCA_FCNTL_ARG, /* arg */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "flock",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_FLOCK, /* cmd */ }, }, },
|
perf trace: Beautify 'fspick' arguments
Use existing beautifiers for the first 2 args (dfd, path) and wire up
the recently introduced fspick flags table generator.
Now it should be possible to just use:
perf trace -e fspick
As root and see all move_mount syscalls with its args beautified, either
using the vfs_getname perf probe method or using the
augmented_raw_syscalls.c eBPF helper to get the pathnames, the other
args should work in all cases, i.e. all that is needed can be obtained
directly from the raw_syscalls:sys_enter tracepoint args.
# cat sys_fspick.c
#define _GNU_SOURCE /* See feature_test_macros(7) */
#include <unistd.h>
#include <sys/syscall.h> /* For SYS_xxx definitions */
#include <fcntl.h>
#define __NR_fspick 433
#define FSPICK_CLOEXEC 0x00000001
#define FSPICK_SYMLINK_NOFOLLOW 0x00000002
#define FSPICK_NO_AUTOMOUNT 0x00000004
#define FSPICK_EMPTY_PATH 0x00000008
static inline int sys_fspick(int fd, const char *path, int flags)
{
syscall(__NR_fspick, fd, path, flags);
}
int main(int argc, char *argv[])
{
int flags = 0, fd = 0;
open("/foo", 0);
sys_fspick(fd++, "/foo1", flags);
flags |= FSPICK_CLOEXEC;
sys_fspick(fd++, "/foo2", flags);
flags |= FSPICK_SYMLINK_NOFOLLOW;
sys_fspick(fd++, "/foo3", flags);
flags |= FSPICK_NO_AUTOMOUNT;
sys_fspick(fd++, "/foo4", flags);
flags |= FSPICK_EMPTY_PATH;
return sys_fspick(fd++, "/foo5", flags);
}
# perf trace -e fspick ./sys_fspick
LLVM: dumping /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
fspick(0, "/foo1", 0) = -1 ENOENT (No such file or directory)
fspick(1, "/foo2", FSPICK_CLOEXEC) = -1 ENOENT (No such file or directory)
fspick(2, "/foo3", FSPICK_CLOEXEC|FSPICK_SYMLINK_NOFOLLOW) = -1 ENOENT (No such file or directory)
fspick(3, "/foo4", FSPICK_CLOEXEC|FSPICK_SYMLINK_NOFOLLOW|FSPICK_NO_AUTOMOUNT) = -1 ENOENT (No such file or directory)
fspick(4, "/foo5", FSPICK_CLOEXEC|FSPICK_SYMLINK_NOFOLLOW|FSPICK_NO_AUTOMOUNT|FSPICK_EMPTY_PATH) = -1 ENOENT (No such file or directory)
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-erau5xjtt8wvgnhvdbchstuk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-05-21 02:24:15 +07:00
|
|
|
{ .name = "fspick",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
|
|
|
|
[1] = { .scnprintf = SCA_FILENAME, /* path */ },
|
|
|
|
[2] = { .scnprintf = SCA_FSPICK_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "fstat", .alias = "newfstat", },
|
|
|
|
{ .name = "fstatat", .alias = "newfstatat", },
|
|
|
|
{ .name = "futex",
|
perf trace beauty futex: Beautify FUTEX_BITSET_MATCH_ANY
E.g.:
# strace -e futex -p 14437
strace: Process 14437 attached
futex(0x7f46f4808d70, FUTEX_WAKE_PRIVATE, 1) = 0
futex(0x7f46f24e68b0, FUTEX_WAIT_BITSET_PRIVATE|FUTEX_CLOCK_REALTIME, 0, {tv_sec=1516636744, tv_nsec=221969000}, 0xffffffff) = -1 ETIMEDOUT (Connection timed out)
<detached ...>
#
Should pretty print that 0xffffffff value, like:
# trace -e futex --tid 14437
0.028 ( 0.005 ms): futex(uaddr: 0x7f46f4808d70, op: WAKE|PRIV, val: 1 ) = 0
0.037 (1000.092 ms): futex(uaddr: 0x7f46f24e68b0, op: WAIT_BITSET|PRIV|CLKRT, utime: 0x7f46f23fedf0, val3: MATCH_ANY) = -1 ETIMEDOUT Connection timed out
^C#
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: https://lkml.kernel.org/n/tip-raef6e352la90600yksthao1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 22:56:59 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ },
|
|
|
|
[5] = { .scnprintf = SCA_FUTEX_VAL3, /* val3 */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "futimesat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "getitimer",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(which, itimers), }, },
|
2016-04-07 00:55:18 +07:00
|
|
|
{ .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>
2016-04-07 04:02:41 +07:00
|
|
|
{ .name = "getpgid", .errpid = true, },
|
2016-04-07 00:55:18 +07:00
|
|
|
{ .name = "getppid", .errpid = true, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "getrandom",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_GETRANDOM_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "getrlimit",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
|
2018-01-09 22:03:47 +07:00
|
|
|
{ .name = "gettid", .errpid = true, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "ioctl",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = {
|
2014-02-11 00:09:48 +07:00
|
|
|
#if defined(__i386__) || defined(__x86_64__)
|
|
|
|
/*
|
|
|
|
* FIXME: Make this available to all arches.
|
|
|
|
*/
|
perf trace beauty ioctl: Improve 'cmd' beautifier
By using the _IOC_(DIR,NR,TYPE,SIZE) macros to lookup a 'type' keyed
table that then gets indexed by 'nr', falling back to a notation similar
to the one used by 'strace', only more compact, i.e.:
474.356 ( 0.007 ms): gnome-shell/22401 ioctl(fd: 8</dev/dri/card0>, cmd: (READ|WRITE, 0x64, 0xae, 0x1c), arg: 0x7ffc934f7880) = 0
474.369 ( 0.053 ms): gnome-shell/22401 ioctl(fd: 8</dev/dri/card0>, cmd: (READ|WRITE, 0x64, 0xb0, 0x18), arg: 0x7ffc934f77d0) = 0
505.055 ( 0.014 ms): gnome-shell/22401 ioctl(fd: 8</dev/dri/card0>, cmd: (READ|WRITE, 0x64, 0xaf, 0x4), arg: 0x7ffc934f741c) = 0
This also moves it out of builtin-trace.c and into trace/beauty/ioctl.c
to better compartimentalize all these formatters.
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-s3enursdxsvnhdomh6qlte4g@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-31 23:20:14 +07:00
|
|
|
[1] = { .scnprintf = SCA_IOCTL_CMD, /* cmd */ },
|
2017-07-18 01:22:47 +07:00
|
|
|
[2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
|
2014-02-11 00:09:48 +07:00
|
|
|
#else
|
2017-07-18 01:22:47 +07:00
|
|
|
[2] = { .scnprintf = SCA_HEX, /* arg */ }, }, },
|
2014-02-11 00:09:48 +07:00
|
|
|
#endif
|
perf trace beauty kcmp: Beautify arguments
For some unknown reason there is no entry in tracefs's syscalls for
kcmp, i.e. no tracefs/events/syscalls/sys_{enter,exit}_kcmp, so we need
to provide a data dictionary for the fields.
To beautify the 'type' argument we automatically generate a strarray
from tools/include/uapi/kcmp.h, the idx1 and idx2 args, nowadays used
only if type == KCMP_FILE, are masked for all the other types and a
lookup is made for the thread and fd to show the path, if possible,
getting it from the probe:vfs_getname if in place or from procfs, races
allowing.
A system wide strace like tracing session, with callchains shows just
one user so far in this fedora 25 machine:
# perf trace --max-stack 5 -e kcmp
<SNIP>
1502914.400 ( 0.001 ms): systemd/1 kcmp(pid1: 1 (systemd), pid2: 1 (systemd), type: FILE, idx1: 271<socket:[4723475]>, idx2: 25<socket:[4788686]>) = -1 ENOSYS Function not implemented
syscall (/usr/lib64/libc-2.25.so)
same_fd (/usr/lib/systemd/libsystemd-shared-233.so)
service_add_fd_store (/usr/lib/systemd/systemd)
service_notify_message.lto_priv.127 (/usr/lib/systemd/systemd)
1502914.407 ( 0.001 ms): systemd/1 kcmp(pid1: 1 (systemd), pid2: 1 (systemd), type: FILE, idx1: 270<socket:[4726396]>, idx2: 25<socket:[4788686]>) = -1 ENOSYS Function not implemented
syscall (/usr/lib64/libc-2.25.so)
same_fd (/usr/lib/systemd/libsystemd-shared-233.so)
service_add_fd_store (/usr/lib/systemd/systemd)
service_notify_message.lto_priv.127 (/usr/lib/systemd/systemd)
<SNIP>
The backtraces seem to agree this is really kcmp(), but this system
doesn't have the sys_kcmp(), bummer:
# uname -a
Linux jouet 4.14.0-rc3+ #1 SMP Fri Oct 13 12:21:12 -03 2017 x86_64 x86_64 x86_64 GNU/Linux
# grep kcmp /proc/kallsyms
ffffffffb60b8890 W sys_kcmp
$ grep CONFIG_CHECKPOINT_RESTORE ../build/v4.14.0-rc3+/.config
# CONFIG_CHECKPOINT_RESTORE is not set
$
So systemd uses it, good fedora kernel config has it:
$ grep CONFIG_CHECKPOINT_RESTORE /boot/config-4.13.4-200.fc26.x86_64
CONFIG_CHECKPOINT_RESTORE=y
[acme@jouet linux]$
/me goes to rebuild a kernel...
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andrey Vagin <avagin@openvz.org>
Cc: Cyrill Gorcunov <gorcunov@openvz.org>
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-gz5fca968viw8m7hryjqvrln@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-31 21:32:23 +07:00
|
|
|
{ .name = "kcmp", .nr_args = 5,
|
|
|
|
.arg = { [0] = { .name = "pid1", .scnprintf = SCA_PID, },
|
|
|
|
[1] = { .name = "pid2", .scnprintf = SCA_PID, },
|
|
|
|
[2] = { .name = "type", .scnprintf = SCA_KCMP_TYPE, },
|
|
|
|
[3] = { .name = "idx1", .scnprintf = SCA_KCMP_IDX, },
|
|
|
|
[4] = { .name = "idx2", .scnprintf = SCA_KCMP_IDX, }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "keyctl",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(option, keyctl_options), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "kill",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "linkat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "lseek",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = STRARRAY(whence, whences), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "lstat", .alias = "newlstat", },
|
|
|
|
{ .name = "madvise",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
|
|
|
|
[2] = { .scnprintf = SCA_MADV_BHV, /* behavior */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "mkdirat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "mknodat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
|
2013-08-26 22:29:38 +07:00
|
|
|
{ .name = "mmap", .hexret = true,
|
2017-05-31 18:35:57 +07:00
|
|
|
/* The standard mmap maps to old_mmap on s390x */
|
|
|
|
#if defined(__s390x__)
|
|
|
|
.alias = "old_mmap",
|
|
|
|
#endif
|
2018-12-17 22:21:09 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ },
|
2018-12-18 21:25:08 +07:00
|
|
|
[3] = { .scnprintf = SCA_MMAP_FLAGS, /* flags */ },
|
|
|
|
[5] = { .scnprintf = SCA_HEX, /* offset */ }, }, },
|
perf trace beauty: Beautify mount/umount's 'flags' argument
# trace -e mount mount -o ro -t debugfs nodev /mnt
0.000 ( 1.040 ms): mount/27235 mount(dev_name: 0x5601cc8c64e0, dir_name: 0x5601cc8c6500, type: 0x5601cc8c6480, flags: RDONLY) = 0
# trace -e mount mount -o remount,relatime -t debugfs nodev /mnt
0.000 ( 2.946 ms): mount/27262 mount(dev_name: 0x55f4a73d64e0, dir_name: 0x55f4a73d6500, type: 0x55f4a73d6480, flags: REMOUNT|RELATIME) = 0
# trace -e mount mount -o remount,strictatime -t debugfs nodev /mnt
0.000 ( 2.934 ms): mount/27265 mount(dev_name: 0x5617f71d94e0, dir_name: 0x5617f71d9500, type: 0x5617f71d9480, flags: REMOUNT|STRICTATIME) = 0
# trace -e mount mount -o remount,suid,silent -t debugfs nodev /mnt
0.000 ( 0.049 ms): mount/27273 mount(dev_name: 0x55ad65df24e0, dir_name: 0x55ad65df2500, type: 0x55ad65df2480, flags: REMOUNT|SILENT) = 0
# trace -e mount mount -o remount,rw,sync,lazytime -t debugfs nodev /mnt
0.000 ( 2.684 ms): mount/27281 mount(dev_name: 0x561216055530, dir_name: 0x561216055550, type: 0x561216055510, flags: SYNCHRONOUS|REMOUNT|LAZYTIME) = 0
# trace -e mount mount -o remount,dirsync -t debugfs nodev /mnt
0.000 ( 3.512 ms): mount/27314 mount(dev_name: 0x55c4e7188480, dir_name: 0x55c4e7188530, type: 0x55c4e71884a0, flags: REMOUNT|DIRSYNC, data: 0x55c4e71884e0) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
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: https://lkml.kernel.org/n/tip-i5ncao73c0bd02qprgrq6wb9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-26 01:18:06 +07:00
|
|
|
{ .name = "mount",
|
2018-10-26 23:51:45 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
|
|
|
|
[3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
|
perf trace beauty: Beautify mount/umount's 'flags' argument
# trace -e mount mount -o ro -t debugfs nodev /mnt
0.000 ( 1.040 ms): mount/27235 mount(dev_name: 0x5601cc8c64e0, dir_name: 0x5601cc8c6500, type: 0x5601cc8c6480, flags: RDONLY) = 0
# trace -e mount mount -o remount,relatime -t debugfs nodev /mnt
0.000 ( 2.946 ms): mount/27262 mount(dev_name: 0x55f4a73d64e0, dir_name: 0x55f4a73d6500, type: 0x55f4a73d6480, flags: REMOUNT|RELATIME) = 0
# trace -e mount mount -o remount,strictatime -t debugfs nodev /mnt
0.000 ( 2.934 ms): mount/27265 mount(dev_name: 0x5617f71d94e0, dir_name: 0x5617f71d9500, type: 0x5617f71d9480, flags: REMOUNT|STRICTATIME) = 0
# trace -e mount mount -o remount,suid,silent -t debugfs nodev /mnt
0.000 ( 0.049 ms): mount/27273 mount(dev_name: 0x55ad65df24e0, dir_name: 0x55ad65df2500, type: 0x55ad65df2480, flags: REMOUNT|SILENT) = 0
# trace -e mount mount -o remount,rw,sync,lazytime -t debugfs nodev /mnt
0.000 ( 2.684 ms): mount/27281 mount(dev_name: 0x561216055530, dir_name: 0x561216055550, type: 0x561216055510, flags: SYNCHRONOUS|REMOUNT|LAZYTIME) = 0
# trace -e mount mount -o remount,dirsync -t debugfs nodev /mnt
0.000 ( 3.512 ms): mount/27314 mount(dev_name: 0x55c4e7188480, dir_name: 0x55c4e7188530, type: 0x55c4e71884a0, flags: REMOUNT|DIRSYNC, data: 0x55c4e71884e0) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Benjamin Peterson <benjamin@python.org>
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: https://lkml.kernel.org/n/tip-i5ncao73c0bd02qprgrq6wb9@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-26 01:18:06 +07:00
|
|
|
.mask_val = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
|
perf trace: Beautify 'move_mount' arguments
Use existing beautifiers for the first 4 args (to/from fds, pathnames)
and wire up the recently introduced move_mount flags table generator.
Now it should be possible to just use:
perf trace -e move_mount
As root and see all move_mount syscalls with its args beautified, except
for the filenames, that need work in the augmented_raw_syscalls.c eBPF
helper to pass more than one, see comment in the
augmented_raw_syscalls.c source code, the other args should work in all
cases, i.e. all that is needed can be obtained directly from the
raw_syscalls:sys_enter tracepoint args.
Running without the strace "skin" (.perfconfig setting output formatting
switches to look like strace output + BPF to collect strings, as we
still need to support collecting multiple string args for the same
syscall, like with move_mount):
# cat sys_move_mount.c
#define _GNU_SOURCE /* See feature_test_macros(7) */
#include <unistd.h>
#include <sys/syscall.h> /* For SYS_xxx definitions */
#define __NR_move_mount 429
#define MOVE_MOUNT_F_SYMLINKS 0x00000001 /* Follow symlinks on from path */
#define MOVE_MOUNT_F_AUTOMOUNTS 0x00000002 /* Follow automounts on from path */
#define MOVE_MOUNT_F_EMPTY_PATH 0x00000004 /* Empty from path permitted */
#define MOVE_MOUNT_T_SYMLINKS 0x00000010 /* Follow symlinks on to path */
#define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */
#define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */
static inline int sys_move_mount(int from_fd, const char *from_pathname,
int to_fd, const char *to_pathname,
int flags)
{
syscall(__NR_move_mount, from_fd, from_pathname, to_fd, to_pathname, flags);
}
int main(int argc, char *argv[])
{
int flags = 0, from_fd = 0, to_fd = 100;
sys_move_mount(from_fd++, "/foo", to_fd++, "bar", flags);
flags |= MOVE_MOUNT_F_SYMLINKS;
sys_move_mount(from_fd++, "/foo1", to_fd++, "bar1", flags);
flags |= MOVE_MOUNT_F_AUTOMOUNTS;
sys_move_mount(from_fd++, "/foo2", to_fd++, "bar2", flags);
flags |= MOVE_MOUNT_F_EMPTY_PATH;
sys_move_mount(from_fd++, "/foo3", to_fd++, "bar3", flags);
flags |= MOVE_MOUNT_T_SYMLINKS;
sys_move_mount(from_fd++, "/foo4", to_fd++, "bar4", flags);
flags |= MOVE_MOUNT_T_AUTOMOUNTS;
sys_move_mount(from_fd++, "/foo5", to_fd++, "bar5", flags);
flags |= MOVE_MOUNT_T_EMPTY_PATH;
return sys_move_mount(from_fd++, "/foo6", to_fd++, "bar6", flags);
}
# mv ~/.perfconfig ~/.perfconfig.OFF
# perf trace -e move_mount ./sys_move_mount
0.000 ( 0.009 ms): sys_move_mount/28971 move_mount(from_pathname: 0x402010, to_dfd: 100, to_pathname: 0x402015) = -1 ENOENT (No such file or directory)
0.011 ( 0.003 ms): sys_move_mount/28971 move_mount(from_dfd: 1, from_pathname: 0x40201e, to_dfd: 101, to_pathname: 0x402019, flags: F_SYMLINKS) = -1 ENOENT (No such file or directory)
0.016 ( 0.002 ms): sys_move_mount/28971 move_mount(from_dfd: 2, from_pathname: 0x402029, to_dfd: 102, to_pathname: 0x402024, flags: F_SYMLINKS|F_AUTOMOUNTS) = -1 ENOENT (No such file or directory)
0.020 ( 0.002 ms): sys_move_mount/28971 move_mount(from_dfd: 3, from_pathname: 0x402034, to_dfd: 103, to_pathname: 0x40202f, flags: F_SYMLINKS|F_AUTOMOUNTS|F_EMPTY_PATH) = -1 ENOENT (No such file or directory)
0.023 ( 0.002 ms): sys_move_mount/28971 move_mount(from_dfd: 4, from_pathname: 0x40203f, to_dfd: 104, to_pathname: 0x40203a, flags: F_SYMLINKS|F_AUTOMOUNTS|F_EMPTY_PATH|T_SYMLINKS) = -1 ENOENT (No such file or directory)
0.027 ( 0.002 ms): sys_move_mount/28971 move_mount(from_dfd: 5, from_pathname: 0x40204a, to_dfd: 105, to_pathname: 0x402045, flags: F_SYMLINKS|F_AUTOMOUNTS|F_EMPTY_PATH|T_SYMLINKS|T_AUTOMOUNTS) = -1 ENOENT (No such file or directory)
0.031 ( 0.017 ms): sys_move_mount/28971 move_mount(from_dfd: 6, from_pathname: 0x402055, to_dfd: 106, to_pathname: 0x402050, flags: F_SYMLINKS|F_AUTOMOUNTS|F_EMPTY_PATH|T_SYMLINKS|T_AUTOMOUNTS|T_EMPTY_PATH) = -1 ENOENT (No such file or directory)
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-83rim8g4k0s4gieieh5nnlck@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-05-21 00:58:03 +07:00
|
|
|
{ .name = "move_mount",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* from_dfd */ },
|
|
|
|
[1] = { .scnprintf = SCA_FILENAME, /* from_pathname */ },
|
|
|
|
[2] = { .scnprintf = SCA_FDAT, /* to_dfd */ },
|
|
|
|
[3] = { .scnprintf = SCA_FILENAME, /* to_pathname */ },
|
|
|
|
[4] = { .scnprintf = SCA_MOVE_MOUNT_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "mprotect",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
|
|
|
|
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "mq_unlink",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = 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>
2013-08-21 03:44:42 +07:00
|
|
|
{ .name = "mremap", .hexret = true,
|
2018-12-17 22:21:09 +07:00
|
|
|
.arg = { [3] = { .scnprintf = SCA_MREMAP_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "name_to_handle_at",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "newfstatat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "open",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "open_by_handle_at",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
|
|
|
|
[2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "openat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ },
|
|
|
|
[2] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "perf_event_open",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_INT, /* cpu */ },
|
|
|
|
[3] = { .scnprintf = SCA_FD, /* group_fd */ },
|
|
|
|
[4] = { .scnprintf = SCA_PERF_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "pipe2",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_PIPE_FLAGS, /* flags */ }, }, },
|
perf trace beauty: Beautify pkey_{alloc,free,mprotect} arguments
Reuse 'mprotect' beautifiers for 'pkey_mprotect'.
System wide tracing pkey_alloc, pkey_free and pkey_mprotect calls, with
backtraces:
# perf trace -e pkey_alloc,pkey_mprotect,pkey_free --max-stack=5
0.000 ( 0.011 ms): pkey/7818 pkey_alloc(init_val: DISABLE_ACCESS|DISABLE_WRITE) = -1 EINVAL Invalid argument
syscall (/usr/lib64/libc-2.25.so)
pkey_alloc (/home/acme/c/pkey)
0.022 ( 0.003 ms): pkey/7818 pkey_mprotect(start: 0x7f28c3890000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
syscall (/usr/lib64/libc-2.25.so)
pkey_mprotect (/home/acme/c/pkey)
0.030 ( 0.002 ms): pkey/7818 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
syscall (/usr/lib64/libc-2.25.so)
pkey_free (/home/acme/c/pkey)
The tools/include/uapi/asm-generic/mman-common.h file is used to find
the access rights defines for the pkey_alloc syscall second argument.
Since we have the detector of changes for the tools/include header files
versus its kernel origin (include/uapi/asm-generic/mman-common.h), we'll
get whatever new flag appears for that argument automatically.
This method should be used in other cases where it is easy to generate
those flags tables because the header has properly namespaced defines
like PKEY_DISABLE_ACCESS and PKEY_DISABLE_WRITE.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Dave Hansen <dave.hansen@linux.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-3xq5312qlks7wtfzv2sk3nct@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-28 21:47:11 +07:00
|
|
|
{ .name = "pkey_alloc",
|
|
|
|
.arg = { [1] = { .scnprintf = SCA_PKEY_ALLOC_ACCESS_RIGHTS, /* access_rights */ }, }, },
|
|
|
|
{ .name = "pkey_free",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_INT, /* key */ }, }, },
|
|
|
|
{ .name = "pkey_mprotect",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_HEX, /* start */ },
|
|
|
|
[2] = { .scnprintf = SCA_MMAP_PROT, /* prot */ },
|
|
|
|
[3] = { .scnprintf = SCA_INT, /* pkey */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "poll", .timeout = true, },
|
|
|
|
{ .name = "ppoll", .timeout = true, },
|
perf trace beauty: Beautify arch_prctl()'s arguments
This actually so far, AFAIK is available only in x86, so the code was
put in place with x86 prefixes, in arches where it is not available it
will just not be called, so no further mechanisms are needed at this
time.
Later, when other arches wire this up, we'll just look at the uname
(live sessions) or perf_env data in the perf.data header to auto-wire
the right beautifier.
With this the output is the same as produced by 'strace' when used with
the following ~/.perfconfig:
# cat ~/.perfconfig
[llvm]
dump-obj = true
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
show_zeros = yes
show_duration = no
no_inherit = yes
show_timestamp = no
show_arg_names = no
args_alignment = -40
show_prefix = yes
#
And, on fedora 29, since the string tables are generated from the kernel
sources, we don't know about 0x3001, just like strace:
--- /tmp/strace 2018-12-17 11:22:08.707586721 -0300
+++ /tmp/trace 2018-12-18 11:11:32.037512729 -0300
@@ -1,49 +1,49 @@
-arch_prctl(0x3001 /* ARCH_??? */, 0x7ffc8a92dc80) = -1 EINVAL (Invalid argument)
+arch_prctl(0x3001 /* ARCH_??? */, 0x7ffe4eb93ae0) = -1 EINVAL (Invalid argument)
-arch_prctl(ARCH_SET_FS, 0x7faf6700f540) = 0
+arch_prctl(ARCH_SET_FS, 0x7fb507364540) = 0
And that seems to be related to the CET/Shadow Stack feature, that
userland in Fedora 29 (glibc 2.28) are querying the kernel about, that
0x3001 seems to be ARCH_CET_STATUS, I'll check the situation and test
with a fedora 29 kernel to see if the other codes are used.
A diff that ignores the different pointers for different runs needs to
be put in place in the upcoming regression tests comparing 'perf trace's
output to strace's.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-73a9prs8ktkrt97trtdmdjs8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-18 21:05:56 +07:00
|
|
|
{ .name = "prctl",
|
perf trace beauty prctl: Generate 'option' string table from kernel headers
This is one more case where the way that syscall parameter values are
defined in kernel headers are easy to parse using a shell script that
will then generate the string table that gets used by the prctl 'option'
argument beautifier.
This way as soon as the header syncronization mechanism in perf's build
system detects a change in a copy of a kernel ABI header and that file
is syncronized, we get 'perf trace' updated automagically.
Further work needed for the PR_SET_ values, as well for using eBPF to
copy the non-integer arguments to/from the kernel.
E.g.: System wide prctl tracing:
# perf trace -e prctl
1668.028 ( 0.025 ms): TaskSchedulerR/10649 prctl(option: SET_NAME, arg2: 0x2b61d5db15d0) = 0
3365.663 ( 0.018 ms): chrome/10650 prctl(option: SET_SECCOMP, arg2: 2, arg4: 8 ) = -1 EFAULT Bad address
3366.585 ( 0.010 ms): chrome/10650 prctl(option: SET_NO_NEW_PRIVS, arg2: 1 ) = 0
3367.173 ( 0.009 ms): TaskSchedulerR/10652 prctl(option: SET_NAME, arg2: 0x2b61d2aaa300) = 0
3367.222 ( 0.003 ms): TaskSchedulerR/10653 prctl(option: SET_NAME, arg2: 0x2b61d2aaa1e0) = 0
3367.244 ( 0.002 ms): TaskSchedulerR/10654 prctl(option: SET_NAME, arg2: 0x2b61d2aaa0c0) = 0
3367.265 ( 0.002 ms): TaskSchedulerR/10655 prctl(option: SET_NAME, arg2: 0x2b61d2ac7f90) = 0
3367.281 ( 0.002 ms): Chrome_ChildIO/10656 prctl(option: SET_NAME, arg2: 0x7efbe406bb11) = 0
3367.220 ( 0.004 ms): TaskSchedulerS/10651 prctl(option: SET_NAME, arg2: 0x2b61d2ac1be0) = 0
3370.906 ( 0.010 ms): GpuMemoryThrea/10657 prctl(option: SET_NAME, arg2: 0x7efbe386ab11) = 0
3370.983 ( 0.003 ms): File/10658 prctl(option: SET_NAME, arg2: 0x7efbe3069b11 ) = 0
3384.272 ( 0.020 ms): Compositor/10659 prctl(option: SET_NAME, arg2: 0x7efbe2868b11 ) = 0
3612.091 ( 0.012 ms): DOM Worker/11489 prctl(option: SET_NAME, arg2: 0x7f49ab97ebf2 ) = 0
<SNIP>
4512.437 ( 0.004 ms): (sa1)/11490 prctl(option: SET_NAME, arg2: 0x7ffca15af844 ) = 0
4512.468 ( 0.002 ms): (sa1)/11490 prctl(option: SET_MM, arg2: ARG_START, arg3: 0x7f5cb7c81000) = 0
4512.472 ( 0.001 ms): (sa1)/11490 prctl(option: SET_MM, arg2: ARG_END, arg3: 0x7f5cb7c81006) = 0
4514.667 ( 0.002 ms): (sa1)/11490 prctl(option: GET_SECUREBITS ) = 0
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
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-q0s2uw579o5ei6xlh2zjirgz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-27 01:19:35 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_PRCTL_OPTION, /* option */ },
|
|
|
|
[1] = { .scnprintf = SCA_PRCTL_ARG2, /* arg2 */ },
|
|
|
|
[2] = { .scnprintf = SCA_PRCTL_ARG3, /* arg3 */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "pread", .alias = "pread64", },
|
|
|
|
{ .name = "preadv", .alias = "pread", },
|
|
|
|
{ .name = "prlimit64",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = STRARRAY(resource, rlimit_resources), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "pwrite", .alias = "pwrite64", },
|
|
|
|
{ .name = "readlinkat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "recvfrom",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "recvmmsg",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "recvmsg",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "renameat",
|
2018-12-11 21:19:23 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
|
|
|
|
[2] = { .scnprintf = SCA_FDAT, /* newdirfd */ }, }, },
|
perf trace beauty: Beautify renameat2's fd arg wrt AT_FDCWD
Just like is done with the 'renameat' syscall.
# strace -e renameat2 -f perf trace -e rename* mv c /tmp
[pid 12334] renameat2(AT_FDCWD, "c", AT_FDCWD, "/tmp", RENAME_NOREPLACE) = -1 EXDEV (Invalid cross-device link)
[pid 12334] renameat2(AT_FDCWD, "c", AT_FDCWD, "/tmp/c", RENAME_NOREPLACE) = -1 EEXIST (File exists)
1.947 ( 0.007 ms): mv/12334 renameat2(olddfd: CWD, oldname: 0x7ffce8b7fd81, newdfd: CWD, newname: 0x7ffce8b7fd83, flags: 1) = -1 EXDEV Invalid cross-device link
2.073 ( 0.009 ms): mv/12334 renameat2(olddfd: CWD, oldname: 0x7ffce8b7fd81, newdfd: CWD, newname: 0x55ce7f0a1cc0, flags: 1mv: ) = -1 EEXIST File exists'c' and '/tmp/c' are the same file
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-8q9l92eh9eee3y2bwyqku3tc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-11 19:53:21 +07:00
|
|
|
{ .name = "renameat2",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* olddirfd */ },
|
perf trace: Beautify renameat2's flags argument
# strace -e renameat2 -f perf trace -e rename* mv c /tmp
strace: Process 10824 attached
[pid 10824] renameat2(AT_FDCWD, "c", AT_FDCWD, "/tmp", RENAME_NOREPLACE) = -1 EXDEV (Invalid cross-device link)
[pid 10824] renameat2(AT_FDCWD, "c", AT_FDCWD, "/tmp/c", RENAME_NOREPLACE) = -1 EEXIST (File exists)
1.857 ( 0.008 ms): mv/10824 renameat2(olddfd: CWD, oldname: 0x7ffc72ff3d81, newdfd: CWD, newname: 0x7ffc72ff3d83, flags: NOREPLACE) = -1 EXDEV Invalid cross-device link
2.002 ( 0.006 ms): mv/10824 renameat2(olddfd: CWD, oldname: 0x7ffc72ff3d81, newdfd: CWD, newname: 0x55ad609efcc0, flags: NOREPLACE) = -1 EEXIST File exists
mv: 'c' and '/tmp/c' are the same file
[pid 10824] +++ exited with 1 +++
--- SIGCHLD {si_signo=SIGCHLD, si_code=CLD_EXITED, si_pid=10824, si_uid=0, si_status=1, si_utime=0, si_stime=0} ---
+++ exited with 0 +++
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-glyt6nzlt1yx56m5bshy6g83@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-11 20:39:30 +07:00
|
|
|
[2] = { .scnprintf = SCA_FDAT, /* newdirfd */ },
|
|
|
|
[4] = { .scnprintf = SCA_RENAMEAT2_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "rt_sigaction",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "rt_sigprocmask",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(how, sighow), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "rt_sigqueueinfo",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "rt_tgsigqueueinfo",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "sched_setscheduler",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_SCHED_POLICY, /* policy */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "seccomp",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_SECCOMP_OP, /* op */ },
|
|
|
|
[1] = { .scnprintf = SCA_SECCOMP_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "select", .timeout = true, },
|
|
|
|
{ .name = "sendmmsg",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "sendmsg",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "sendto",
|
2018-08-29 18:47:08 +07:00
|
|
|
.arg = { [3] = { .scnprintf = SCA_MSG_FLAGS, /* flags */ },
|
|
|
|
[4] = { .scnprintf = SCA_SOCKADDR, /* addr */ }, }, },
|
2016-04-07 00:55:18 +07:00
|
|
|
{ .name = "set_tid_address", .errpid = true, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "setitimer",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(which, itimers), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "setrlimit",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(resource, rlimit_resources), }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "socket",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(family, socket_families),
|
perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args
For instance:
$ trace -e socket* ssh sandy
0.000 ( 0.031 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
0.052 ( 0.015 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.568 ( 0.020 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.603 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.699 ( 0.014 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.724 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.804 ( 0.020 ms): ssh/19919 socket(family: INET, type: STREAM, protocol: TCP ) = 3
17.549 ( 0.098 ms): ssh/19919 socket(family: LOCAL, type: STREAM ) = 4
acme@sandy's password:
Just like with other syscall args, the common bits are supressed so that
the output is more compact, i.e. we use "TCP" instead of "IPPROTO_TCP",
but we can make this show the original constant names if we like it by
using some command line knob or ~/.perfconfig "[trace]" section
variable.
Also needed is to make perf's event parser accept things like:
$ perf trace -e socket*/protocol=TCP/
By using both the tracefs event 'format' files and these tables built
from the kernel sources.
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: https://lkml.kernel.org/n/tip-l39jz1vnyda0b6jsufuc8bz7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-07-26 19:26:13 +07:00
|
|
|
[1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
|
|
|
|
[2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "socketpair",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = STRARRAY(family, socket_families),
|
perf trace: Beautify the AF_INET & AF_INET6 'socket' syscall 'protocol' args
For instance:
$ trace -e socket* ssh sandy
0.000 ( 0.031 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
0.052 ( 0.015 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.568 ( 0.020 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.603 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.699 ( 0.014 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.724 ( 0.012 ms): ssh/19919 socket(family: LOCAL, type: STREAM|CLOEXEC|NONBLOCK ) = 3
1.804 ( 0.020 ms): ssh/19919 socket(family: INET, type: STREAM, protocol: TCP ) = 3
17.549 ( 0.098 ms): ssh/19919 socket(family: LOCAL, type: STREAM ) = 4
acme@sandy's password:
Just like with other syscall args, the common bits are supressed so that
the output is more compact, i.e. we use "TCP" instead of "IPPROTO_TCP",
but we can make this show the original constant names if we like it by
using some command line knob or ~/.perfconfig "[trace]" section
variable.
Also needed is to make perf's event parser accept things like:
$ perf trace -e socket*/protocol=TCP/
By using both the tracefs event 'format' files and these tables built
from the kernel sources.
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: https://lkml.kernel.org/n/tip-l39jz1vnyda0b6jsufuc8bz7@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-07-26 19:26:13 +07:00
|
|
|
[1] = { .scnprintf = SCA_SK_TYPE, /* type */ },
|
|
|
|
[2] = { .scnprintf = SCA_SK_PROTO, /* protocol */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "stat", .alias = "newstat", },
|
|
|
|
{ .name = "statx",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* fdat */ },
|
|
|
|
[2] = { .scnprintf = SCA_STATX_FLAGS, /* flags */ } ,
|
|
|
|
[3] = { .scnprintf = SCA_STATX_MASK, /* mask */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "swapoff",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "swapon",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "symlinkat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "tgkill",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "tkill",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
|
2018-10-26 23:23:25 +07:00
|
|
|
{ .name = "umount2", .alias = "umount",
|
|
|
|
.arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "uname", .alias = "newuname", },
|
|
|
|
{ .name = "unlinkat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
|
2017-07-18 22:45:57 +07:00
|
|
|
{ .name = "utimensat",
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [0] = { .scnprintf = SCA_FDAT, /* dirfd */ }, }, },
|
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>
2016-04-07 00:33:07 +07:00
|
|
|
{ .name = "wait4", .errpid = true,
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [2] = { .scnprintf = 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>
2016-04-07 00:33:07 +07:00
|
|
|
{ .name = "waitid", .errpid = true,
|
2017-07-18 01:22:47 +07:00
|
|
|
.arg = { [3] = { .scnprintf = SCA_WAITID_OPTIONS, /* options */ }, }, },
|
2012-09-27 06:05:56 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2018-10-26 03:24:45 +07:00
|
|
|
static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias)
|
|
|
|
{
|
|
|
|
int i, nmemb = ARRAY_SIZE(syscall_fmts);
|
|
|
|
|
|
|
|
for (i = 0; i < nmemb; ++i) {
|
|
|
|
if (syscall_fmts[i].alias && strcmp(syscall_fmts[i].alias, alias) == 0)
|
|
|
|
return &syscall_fmts[i];
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
perf trace: Associate vfs_getname()'ed pathname with fd returned from 'openat'
When the vfs_getname() wannabe tracepoint is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
#
'perf trace' will use it to get the pathname when it is copied from
userspace to the kernel, right after syscalls:sys_enter_open, copied
in the 'probe:vfs_getname', stash it somewhere and then, at
syscalls:sys_exit_open time, if the 'open' return is not -1, i.e. a
successfull open syscall, associate that pathname to this return, i.e.
the fd.
We were not doing this for the 'openat' syscall, which would cause 'perf
trace' to fallback to using /proc to get the fd, change it so that we
use what we got from probe:vfs_getname, reducing the 'openat'
beautification process cost, ditching the syscalls performed to read
procfs state and avoiding some possible races in the process.
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: https://lkml.kernel.org/n/tip-xnp44ao3bkb6ejeczxfnjwsh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 20:30:08 +07:00
|
|
|
/*
|
|
|
|
* is_exit: is this "exit" or "exit_group"?
|
|
|
|
* is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
|
2018-08-21 03:58:17 +07:00
|
|
|
* args_size: sum of the sizes of the syscall arguments, anything after that is augmented stuff: pathname for openat, etc.
|
perf trace: Associate vfs_getname()'ed pathname with fd returned from 'openat'
When the vfs_getname() wannabe tracepoint is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
#
'perf trace' will use it to get the pathname when it is copied from
userspace to the kernel, right after syscalls:sys_enter_open, copied
in the 'probe:vfs_getname', stash it somewhere and then, at
syscalls:sys_exit_open time, if the 'open' return is not -1, i.e. a
successfull open syscall, associate that pathname to this return, i.e.
the fd.
We were not doing this for the 'openat' syscall, which would cause 'perf
trace' to fallback to using /proc to get the fd, change it so that we
use what we got from probe:vfs_getname, reducing the 'openat'
beautification process cost, ditching the syscalls performed to read
procfs state and avoiding some possible races in the process.
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: https://lkml.kernel.org/n/tip-xnp44ao3bkb6ejeczxfnjwsh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 20:30:08 +07:00
|
|
|
*/
|
2012-09-27 06:05:56 +07:00
|
|
|
struct syscall {
|
2018-11-30 22:44:07 +07:00
|
|
|
struct tep_event *tp_format;
|
2015-03-21 03:46:53 +07:00
|
|
|
int nr_args;
|
2018-08-21 03:58:17 +07:00
|
|
|
int args_size;
|
perf trace: Associate vfs_getname()'ed pathname with fd returned from 'openat'
When the vfs_getname() wannabe tracepoint is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
#
'perf trace' will use it to get the pathname when it is copied from
userspace to the kernel, right after syscalls:sys_enter_open, copied
in the 'probe:vfs_getname', stash it somewhere and then, at
syscalls:sys_exit_open time, if the 'open' return is not -1, i.e. a
successfull open syscall, associate that pathname to this return, i.e.
the fd.
We were not doing this for the 'openat' syscall, which would cause 'perf
trace' to fallback to using /proc to get the fd, change it so that we
use what we got from probe:vfs_getname, reducing the 'openat'
beautification process cost, ditching the syscalls performed to read
procfs state and avoiding some possible races in the process.
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: https://lkml.kernel.org/n/tip-xnp44ao3bkb6ejeczxfnjwsh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 20:30:08 +07:00
|
|
|
bool is_exit;
|
|
|
|
bool is_open;
|
2018-09-20 01:56:45 +07:00
|
|
|
struct tep_format_field *args;
|
2012-09-27 06:05:56 +07:00
|
|
|
const char *name;
|
|
|
|
struct syscall_fmt *fmt;
|
2017-07-18 01:22:47 +07:00
|
|
|
struct syscall_arg_fmt *arg_fmt;
|
2012-09-27 06:05:56 +07:00
|
|
|
};
|
|
|
|
|
2018-12-13 02:54:09 +07:00
|
|
|
struct bpf_map_syscall_entry {
|
|
|
|
bool enabled;
|
|
|
|
};
|
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
/*
|
|
|
|
* 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>
2012-10-25 02:24:47 +07:00
|
|
|
{
|
|
|
|
double duration = (double)t / NSEC_PER_MSEC;
|
|
|
|
size_t printed = fprintf(fp, "(");
|
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
if (!calculated)
|
perf trace: Do not print from time delta for interrupted syscall lines
We were calculating the delta from a in-flight syscall that got its
output interrupted by another syscall, which doesn't seem like useful
information, we will print the syscall duration (sys_exit - sys_enter)
when the raw_syscalls:sys_exit event happens.
The problem here is how we're consuming the multiple ring buffers,
without using the ordered_events code used by perf_session, which may
cause some reordering of syscalls for diferent CPUs, so just stop
printing that delta, to avoid things like:
# trace --print-sample -p 9626 -e futex
raw_syscalls:sys_enter 411967179.269 Timer 9609/9626 [2]
raw_syscalls:sys_enter 411967179.213 file:// Content 9609/9609 [3]
328.038 (18446744073709.496 ms): Timer/9626 futex(uaddr: 0x7fc0d4027044, op: WAIT|PRIV, utime: 0x7fc0b0ffdb50 ) ...
raw_syscalls:sys_exit 411967179.225 file:// Content 9609/9609 [3]
327.982 ( 0.012 ms): file:// Conten/9609 futex(uaddr: 0x7fc0d4027040, op: WAKE|PRIV, val: 1 ) = 1
This is a bandaid, we should better try and use the ordered_events code,
possibly with some refactoring prep work, but for now at least we don't
show those false long deltas for the lines ending in '...'.
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: https://lkml.kernel.org/n/tip-q6xgsqrju1sr6ltud9kjjhmb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 21:42:11 +07:00
|
|
|
printed += fprintf(fp, " ");
|
2017-03-30 02:37:51 +07:00
|
|
|
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>
2012-10-25 02:24:47 +07:00
|
|
|
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 22:01:10 +07:00
|
|
|
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>
2012-10-25 02:24:47 +07:00
|
|
|
}
|
|
|
|
|
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 08:30:09 +07:00
|
|
|
/**
|
|
|
|
* 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.
|
2017-07-14 21:35:03 +07:00
|
|
|
* ret_scnprintf: syscall args may set this to a different syscall return
|
|
|
|
* formatter, for instance, fcntl may return fds, file flags, etc.
|
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 08:30:09 +07:00
|
|
|
*/
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
struct thread_trace {
|
|
|
|
u64 entry_time;
|
|
|
|
bool entry_pending;
|
2012-10-18 03:09:46 +07:00
|
|
|
unsigned long nr_events;
|
2014-07-09 01:05:16 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
char *entry_str;
|
2012-10-18 03:13:12 +07:00
|
|
|
double runtime_ms;
|
2017-07-15 01:16:54 +07:00
|
|
|
size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
|
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 08:30:09 +07:00
|
|
|
struct {
|
|
|
|
unsigned long ptr;
|
2015-08-14 23:16:27 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
} filename;
|
2013-09-24 21:04:32 +07:00
|
|
|
struct {
|
2018-12-27 20:56:12 +07:00
|
|
|
int max;
|
|
|
|
struct file *table;
|
|
|
|
} files;
|
2013-10-09 10:26:53 +07:00
|
|
|
|
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
};
|
|
|
|
|
|
|
|
static struct thread_trace *thread_trace__new(void)
|
|
|
|
{
|
2013-09-24 21:04:32 +07:00
|
|
|
struct thread_trace *ttrace = zalloc(sizeof(struct thread_trace));
|
|
|
|
|
|
|
|
if (ttrace)
|
2018-12-27 20:56:12 +07:00
|
|
|
ttrace->files.max = -1;
|
2013-09-24 21:04:32 +07:00
|
|
|
|
2013-10-09 10:26:53 +07:00
|
|
|
ttrace->syscall_stats = intlist__new(NULL);
|
|
|
|
|
2013-09-24 21:04:32 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
}
|
|
|
|
|
2013-08-19 22:01:10 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
{
|
2012-10-18 03:09:46 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
if (thread == NULL)
|
|
|
|
goto fail;
|
|
|
|
|
2014-10-06 07:46:03 +07:00
|
|
|
if (thread__priv(thread) == NULL)
|
|
|
|
thread__set_priv(thread, thread_trace__new());
|
2014-12-18 03:24:45 +07:00
|
|
|
|
2014-10-06 07:46:03 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
goto fail;
|
|
|
|
|
2014-10-06 07:46:03 +07:00
|
|
|
ttrace = thread__priv(thread);
|
2012-10-18 03:09:46 +07:00
|
|
|
++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>
2012-10-07 04:43:19 +07:00
|
|
|
fail:
|
2013-08-19 22:01:10 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
"WARNING: not enough memory, dropping samples!\n");
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2017-07-14 21:35:03 +07:00
|
|
|
|
|
|
|
void syscall_arg__set_ret_scnprintf(struct syscall_arg *arg,
|
2017-07-15 01:16:54 +07:00
|
|
|
size_t (*ret_scnprintf)(char *bf, size_t size, struct syscall_arg *arg))
|
2017-07-14 21:35:03 +07:00
|
|
|
{
|
|
|
|
struct thread_trace *ttrace = thread__priv(arg->thread);
|
|
|
|
|
|
|
|
ttrace->ret_scnprintf = ret_scnprintf;
|
|
|
|
}
|
|
|
|
|
2014-06-26 23:14:25 +07:00
|
|
|
#define TRACE_PFMAJ (1 << 0)
|
|
|
|
#define TRACE_PFMIN (1 << 1)
|
|
|
|
|
2015-08-05 08:17:29 +07:00
|
|
|
static const size_t trace__entry_str_size = 2048;
|
|
|
|
|
2018-12-27 21:05:18 +07:00
|
|
|
static struct file *thread_trace__files_entry(struct thread_trace *ttrace, int fd)
|
2013-09-24 21:04:32 +07:00
|
|
|
{
|
perf trace: Check if the 'fd' is negative when mapping it to pathname
We were crashing when processing a negative fd:
Program received signal SIGSEGV, Segmentation fault.
0x0000000000609bbf in syscall_arg__scnprintf_ioctl_cmd (bf=0x1172eca "", size=2038, arg=0x7fffffff8360) at trace/beauty/ioctl.c:182
182 if (file->dev_maj == USB_DEVICE_MAJOR)
Missing separate debuginfos, use: dnf debuginfo-install bzip2-libs-1.0.6-28.fc29.x86_64 elfutils-libelf-0.174-5.fc29.x86_64 elfutils-libs-0.174-5.fc29.x86_64 glib2-2.58.3-1.fc29.x86_64 libbabeltrace-1.5.6-1.fc29.x86_64 libunwind-1.2.1-6.fc29.x86_64 libuuid-2.32.1-1.fc29.x86_64 libxcrypt-4.4.3-2.fc29.x86_64 numactl-libs-2.0.12-1.fc29.x86_64 openssl-libs-1.1.1a-1.fc29.x86_64 pcre-8.42-6.fc29.x86_64 perl-libs-5.28.1-427.fc29.x86_64 popt-1.16-15.fc29.x86_64 python2-libs-2.7.15-11.fc29.x86_64 slang-2.3.2-4.fc29.x86_64 xz-libs-5.2.4-3.fc29.x86_64
(gdb) bt
#0 0x0000000000609bbf in syscall_arg__scnprintf_ioctl_cmd (bf=0x1172eca "", size=2038, arg=0x7fffffff8360) at trace/beauty/ioctl.c:182
#1 0x000000000048e295 in syscall__scnprintf_val (sc=0x123b500, bf=0x1172eca "", size=2038, arg=0x7fffffff8360, val=21519)
at builtin-trace.c:1594
#2 0x000000000048e60d in syscall__scnprintf_args (sc=0x123b500, bf=0x1172ec6 "-1, ", size=2042, args=0x7ffff6a7c034 "\377\377\377\377",
augmented_args=0x7ffff6a7c064, augmented_args_size=4, trace=0x7fffffffa8d0, thread=0x1175cd0) at builtin-trace.c:1661
#3 0x000000000048f04e in trace__sys_enter (trace=0x7fffffffa8d0, evsel=0xb260b0, event=0x7ffff6a7bfe8, sample=0x7fffffff84f0)
at builtin-trace.c:1880
#4 0x00000000004915a4 in trace__handle_event (trace=0x7fffffffa8d0, event=0x7ffff6a7bfe8, sample=0x7fffffff84f0) at builtin-trace.c:2590
#5 0x0000000000491eed in __trace__deliver_event (trace=0x7fffffffa8d0, event=0x7ffff6a7bfe8) at builtin-trace.c:2818
#6 0x0000000000492030 in trace__deliver_event (trace=0x7fffffffa8d0, event=0x7ffff6a7bfe8) at builtin-trace.c:2845
#7 0x0000000000492896 in trace__run (trace=0x7fffffffa8d0, argc=0, argv=0x7fffffffdb58) at builtin-trace.c:3040
#8 0x000000000049603a in cmd_trace (argc=0, argv=0x7fffffffdb58) at builtin-trace.c:3952
#9 0x00000000004d5103 in main (argc=1, argv=0x7fffffffdb58) at perf.c:474
(gdb) p fd
$1 = -1
(gdb) p file
$7 = (struct file *) 0xfffffffffffffff0
(gdb) p ((struct thread_trace *)arg->thread)->files.table + fd
$8 = (struct file *) 0xfffffffffffffff0
(gdb)
Check for that and return NULL instead.
This problem was introduced recently, the other codepaths leading to
thread_trace__files_entry() check for negative fds, like thread__fd_path(),
but we need to do it at thread_trace__files_entry() as more users are now
calling it directly.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Fixes: 2d473389f87a ("perf trace beauty: Export function to get the files for a thread")
Link: https://lkml.kernel.org/n/tip-oq7bvaaf07gsd4yqty3107u2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-12 20:18:36 +07:00
|
|
|
if (fd < 0)
|
|
|
|
return NULL;
|
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
if (fd > ttrace->files.max) {
|
|
|
|
struct file *nfiles = realloc(ttrace->files.table, (fd + 1) * sizeof(struct file));
|
2013-09-24 21:04:32 +07:00
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
if (nfiles == NULL)
|
2018-12-27 21:05:18 +07:00
|
|
|
return NULL;
|
2013-09-24 21:04:32 +07:00
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
if (ttrace->files.max != -1) {
|
|
|
|
memset(nfiles + ttrace->files.max + 1, 0,
|
|
|
|
(fd - ttrace->files.max) * sizeof(struct file));
|
2013-09-24 21:04:32 +07:00
|
|
|
} else {
|
2018-12-27 20:56:12 +07:00
|
|
|
memset(nfiles, 0, (fd + 1) * sizeof(struct file));
|
2013-09-24 21:04:32 +07:00
|
|
|
}
|
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
ttrace->files.table = nfiles;
|
|
|
|
ttrace->files.max = fd;
|
2013-09-24 21:04:32 +07:00
|
|
|
}
|
|
|
|
|
2018-12-27 21:05:18 +07:00
|
|
|
return ttrace->files.table + fd;
|
|
|
|
}
|
|
|
|
|
2018-12-28 02:19:33 +07:00
|
|
|
struct file *thread__files_entry(struct thread *thread, int fd)
|
|
|
|
{
|
|
|
|
return thread_trace__files_entry(thread__priv(thread), fd);
|
|
|
|
}
|
|
|
|
|
2018-12-27 21:05:18 +07:00
|
|
|
static int trace__set_fd_pathname(struct thread *thread, int fd, const char *pathname)
|
|
|
|
{
|
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
|
|
|
struct file *file = thread_trace__files_entry(ttrace, fd);
|
|
|
|
|
|
|
|
if (file != NULL) {
|
2018-12-27 23:32:59 +07:00
|
|
|
struct stat st;
|
|
|
|
if (stat(pathname, &st) == 0)
|
|
|
|
file->dev_maj = major(st.st_rdev);
|
2018-12-27 21:05:18 +07:00
|
|
|
file->pathname = strdup(pathname);
|
|
|
|
if (file->pathname)
|
|
|
|
return 0;
|
|
|
|
}
|
2013-09-24 21:04:32 +07:00
|
|
|
|
2018-12-27 21:05:18 +07:00
|
|
|
return -1;
|
2013-09-24 21:04:32 +07:00
|
|
|
}
|
|
|
|
|
2013-09-28 03:34:10 +07:00
|
|
|
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);
|
|
|
|
}
|
|
|
|
|
2013-09-28 04:06:19 +07:00
|
|
|
static const char *thread__fd_path(struct thread *thread, int fd,
|
|
|
|
struct trace *trace)
|
2013-09-24 21:04:32 +07:00
|
|
|
{
|
2014-10-06 07:46:03 +07:00
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
2013-09-24 21:04:32 +07:00
|
|
|
|
|
|
|
if (ttrace == NULL)
|
|
|
|
return NULL;
|
|
|
|
|
|
|
|
if (fd < 0)
|
|
|
|
return NULL;
|
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
if ((fd > ttrace->files.max || ttrace->files.table[fd].pathname == NULL)) {
|
2013-09-28 04:06:19 +07:00
|
|
|
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>
2014-06-11 02:00:18 +07:00
|
|
|
if (thread__read_fd_path(thread, fd))
|
2013-09-28 04:06:19 +07:00
|
|
|
return NULL;
|
|
|
|
}
|
2013-09-24 21:04:32 +07:00
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
return ttrace->files.table[fd].pathname;
|
2013-09-24 21:04:32 +07:00
|
|
|
}
|
|
|
|
|
2017-07-15 01:21:40 +07:00
|
|
|
size_t syscall_arg__scnprintf_fd(char *bf, size_t size, struct syscall_arg *arg)
|
2013-09-24 21:04:32 +07:00
|
|
|
{
|
|
|
|
int fd = arg->val;
|
|
|
|
size_t printed = scnprintf(bf, size, "%d", fd);
|
2013-09-28 04:06:19 +07:00
|
|
|
const char *path = thread__fd_path(arg->thread, fd, arg->trace);
|
2013-09-24 21:04:32 +07:00
|
|
|
|
|
|
|
if (path)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "<%s>", path);
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2017-10-31 21:30:09 +07:00
|
|
|
size_t pid__scnprintf_fd(struct trace *trace, pid_t pid, int fd, char *bf, size_t size)
|
|
|
|
{
|
|
|
|
size_t printed = scnprintf(bf, size, "%d", fd);
|
|
|
|
struct thread *thread = machine__find_thread(trace->host, pid, pid);
|
|
|
|
|
|
|
|
if (thread) {
|
|
|
|
const char *path = thread__fd_path(thread, fd, trace);
|
|
|
|
|
|
|
|
if (path)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "<%s>", path);
|
|
|
|
|
|
|
|
thread__put(thread);
|
|
|
|
}
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2013-09-24 21:04:32 +07:00
|
|
|
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 07:46:03 +07:00
|
|
|
struct thread_trace *ttrace = thread__priv(arg->thread);
|
2013-09-24 21:04:32 +07:00
|
|
|
|
2018-12-27 20:56:12 +07:00
|
|
|
if (ttrace && fd >= 0 && fd <= ttrace->files.max)
|
|
|
|
zfree(&ttrace->files.table[fd].pathname);
|
2013-09-24 21:04:32 +07:00
|
|
|
|
|
|
|
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 08:30:09 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
perf trace: Use the augmented filename, expanding syscall enter pointers
This is the final touch in showing how a syscall argument beautifier can
access the augmented args put in place by the
tools/perf/examples/bpf/augmented_syscalls.c eBPF script, right after
the regular raw syscall args, i.e. the up to 6 long integer values in
the syscall interface.
With this we are able to show the 'openat' syscall arg, now with up to
64 bytes, but in time this will be configurable, just like with the
'strace -s strsize' argument, from 'strace''s man page:
-s strsize Specify the maximum string size to print (the default is 32).
This actually is the maximum string to _collect_ and store in the ring
buffer, not just print.
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC)
0.017 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC) = 3
0.049 ( ): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC)
0.051 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC) = 3
0.377 ( ): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b)
0.379 ( 0.005 ms): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): cat/11966 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
0.006 ( 0.006 ms): cat/11966 openat(dfd: CWD, filename: 0x4bfdcda8, flags: CLOEXEC) = 3
0.034 ( ): cat/11966 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.036 ( 0.008 ms): cat/11966 openat(dfd: CWD, filename: 0x4c1e4ce0, flags: CLOEXEC) = 3
0.375 ( ): cat/11966 openat(dfd: CWD, filename: /etc/passwd)
0.377 ( 0.005 ms): cat/11966 openat(dfd: CWD, filename: 0xe87906b) = 3
#
This cset should show all the aspects of establishing a protocol between
an eBPF syscall arg augmenter program, tools/perf/examples/bpf/augmented_syscalls.c and
a 'perf trace' beautifier, the one associated with all 'char *' point
syscall args with names that can heuristically be associated with
filenames.
Now to wire up 'open' to show a second syscall using this scheme, all we
have to do now is to change tools/perf/examples/bpf/augmented_syscalls.c,
as 'perf trace' will notice that the perf_sample.raw_size is more than
what is expected for a particular syscall payload as defined by its
tracefs format file and will then use the augmented payload in the
'filename' syscall arg beautifier.
The same protocol will be used for structs such as 'struct sockaddr *',
'struct pollfd', etc, with additions for handling arrays.
This will all be done under the hood when 'perf trace' realizes the
system has the necessary components, and also can be done by providing
a precompiled augmented_syscalls.c eBPF ELF object.
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: https://lkml.kernel.org/n/tip-gj9kqb61wo7m3shtpzercbcr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 22:00:39 +07:00
|
|
|
static size_t syscall_arg__scnprintf_augmented_string(struct syscall_arg *arg, char *bf, size_t size)
|
|
|
|
{
|
|
|
|
struct augmented_arg *augmented_arg = arg->augmented.args;
|
|
|
|
|
2018-12-15 00:02:03 +07:00
|
|
|
return scnprintf(bf, size, "\"%.*s\"", augmented_arg->size, augmented_arg->value);
|
perf trace: Use the augmented filename, expanding syscall enter pointers
This is the final touch in showing how a syscall argument beautifier can
access the augmented args put in place by the
tools/perf/examples/bpf/augmented_syscalls.c eBPF script, right after
the regular raw syscall args, i.e. the up to 6 long integer values in
the syscall interface.
With this we are able to show the 'openat' syscall arg, now with up to
64 bytes, but in time this will be configurable, just like with the
'strace -s strsize' argument, from 'strace''s man page:
-s strsize Specify the maximum string size to print (the default is 32).
This actually is the maximum string to _collect_ and store in the ring
buffer, not just print.
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC)
0.017 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC) = 3
0.049 ( ): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC)
0.051 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC) = 3
0.377 ( ): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b)
0.379 ( 0.005 ms): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): cat/11966 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
0.006 ( 0.006 ms): cat/11966 openat(dfd: CWD, filename: 0x4bfdcda8, flags: CLOEXEC) = 3
0.034 ( ): cat/11966 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.036 ( 0.008 ms): cat/11966 openat(dfd: CWD, filename: 0x4c1e4ce0, flags: CLOEXEC) = 3
0.375 ( ): cat/11966 openat(dfd: CWD, filename: /etc/passwd)
0.377 ( 0.005 ms): cat/11966 openat(dfd: CWD, filename: 0xe87906b) = 3
#
This cset should show all the aspects of establishing a protocol between
an eBPF syscall arg augmenter program, tools/perf/examples/bpf/augmented_syscalls.c and
a 'perf trace' beautifier, the one associated with all 'char *' point
syscall args with names that can heuristically be associated with
filenames.
Now to wire up 'open' to show a second syscall using this scheme, all we
have to do now is to change tools/perf/examples/bpf/augmented_syscalls.c,
as 'perf trace' will notice that the perf_sample.raw_size is more than
what is expected for a particular syscall payload as defined by its
tracefs format file and will then use the augmented payload in the
'filename' syscall arg beautifier.
The same protocol will be used for structs such as 'struct sockaddr *',
'struct pollfd', etc, with additions for handling arrays.
This will all be done under the hood when 'perf trace' realizes the
system has the necessary components, and also can be done by providing
a precompiled augmented_syscalls.c eBPF ELF object.
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: https://lkml.kernel.org/n/tip-gj9kqb61wo7m3shtpzercbcr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 22:00:39 +07:00
|
|
|
}
|
|
|
|
|
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 08:30:09 +07:00
|
|
|
static size_t syscall_arg__scnprintf_filename(char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
unsigned long ptr = arg->val;
|
|
|
|
|
perf trace: Use the augmented filename, expanding syscall enter pointers
This is the final touch in showing how a syscall argument beautifier can
access the augmented args put in place by the
tools/perf/examples/bpf/augmented_syscalls.c eBPF script, right after
the regular raw syscall args, i.e. the up to 6 long integer values in
the syscall interface.
With this we are able to show the 'openat' syscall arg, now with up to
64 bytes, but in time this will be configurable, just like with the
'strace -s strsize' argument, from 'strace''s man page:
-s strsize Specify the maximum string size to print (the default is 32).
This actually is the maximum string to _collect_ and store in the ring
buffer, not just print.
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC)
0.017 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x6626eda8, flags: CLOEXEC) = 3
0.049 ( ): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC)
0.051 ( 0.007 ms): cat/9658 openat(dfd: CWD, filename: 0x66476ce0, flags: CLOEXEC) = 3
0.377 ( ): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b)
0.379 ( 0.005 ms): cat/9658 openat(dfd: CWD, filename: 0x1e8f806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): cat/11966 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
0.006 ( 0.006 ms): cat/11966 openat(dfd: CWD, filename: 0x4bfdcda8, flags: CLOEXEC) = 3
0.034 ( ): cat/11966 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.036 ( 0.008 ms): cat/11966 openat(dfd: CWD, filename: 0x4c1e4ce0, flags: CLOEXEC) = 3
0.375 ( ): cat/11966 openat(dfd: CWD, filename: /etc/passwd)
0.377 ( 0.005 ms): cat/11966 openat(dfd: CWD, filename: 0xe87906b) = 3
#
This cset should show all the aspects of establishing a protocol between
an eBPF syscall arg augmenter program, tools/perf/examples/bpf/augmented_syscalls.c and
a 'perf trace' beautifier, the one associated with all 'char *' point
syscall args with names that can heuristically be associated with
filenames.
Now to wire up 'open' to show a second syscall using this scheme, all we
have to do now is to change tools/perf/examples/bpf/augmented_syscalls.c,
as 'perf trace' will notice that the perf_sample.raw_size is more than
what is expected for a particular syscall payload as defined by its
tracefs format file and will then use the augmented payload in the
'filename' syscall arg beautifier.
The same protocol will be used for structs such as 'struct sockaddr *',
'struct pollfd', etc, with additions for handling arrays.
This will all be done under the hood when 'perf trace' realizes the
system has the necessary components, and also can be done by providing
a precompiled augmented_syscalls.c eBPF ELF object.
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: https://lkml.kernel.org/n/tip-gj9kqb61wo7m3shtpzercbcr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 22:00:39 +07:00
|
|
|
if (arg->augmented.args)
|
|
|
|
return syscall_arg__scnprintf_augmented_string(arg, bf, size);
|
|
|
|
|
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 08:30:09 +07:00
|
|
|
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 19:56:00 +07:00
|
|
|
static bool trace__filter_duration(struct trace *trace, double t)
|
|
|
|
{
|
|
|
|
return t < (trace->duration_filter * NSEC_PER_MSEC);
|
|
|
|
}
|
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
{
|
|
|
|
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>
2012-10-25 02:24:47 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
}
|
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
/*
|
|
|
|
* 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 12:02:16 +07:00
|
|
|
static bool done = false;
|
2013-10-16 21:57:33 +07:00
|
|
|
static bool interrupted = false;
|
2012-10-05 12:02:16 +07:00
|
|
|
|
2013-10-16 21:57:33 +07:00
|
|
|
static void sig_handler(int sig)
|
2012-10-05 12:02:16 +07:00
|
|
|
{
|
|
|
|
done = true;
|
2013-10-16 21:57:33 +07:00
|
|
|
interrupted = sig == SIGINT;
|
2012-10-05 12:02:16 +07:00
|
|
|
}
|
|
|
|
|
2018-08-21 21:40:09 +07:00
|
|
|
static size_t trace__fprintf_comm_tid(struct trace *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>
2012-10-07 04:43:19 +07:00
|
|
|
{
|
2018-08-21 21:40:09 +07:00
|
|
|
size_t printed = 0;
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
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 22:35:21 +07:00
|
|
|
if (trace->multiple_threads) {
|
|
|
|
if (trace->show_comm)
|
2013-09-11 21:56:44 +07:00
|
|
|
printed += fprintf(fp, "%.14s/", thread__comm_str(thread));
|
2013-07-04 20:20:31 +07:00
|
|
|
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 22:35:21 +07:00
|
|
|
}
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2018-08-21 21:40:09 +07:00
|
|
|
static size_t trace__fprintf_entry_head(struct trace *trace, struct thread *thread,
|
|
|
|
u64 duration, bool duration_calculated, u64 tstamp, FILE *fp)
|
|
|
|
{
|
perf trace: Allow configuring if the syscall start timestamp should be printed
# trace -e open*,close,*sleep sleep 1
0.000 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
0.016 close(fd: 3 ) = 0
0.024 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
0.074 close(fd: 3 ) = 0
0.235 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.251 close(fd: 3 ) = 0
0.285 nanosleep(rqtp: 0x7ffd68e6d620, rmtp: 0 ) = 0
1000.386 close(fd: 1 ) = 0
1000.395 close(fd: 2 ) = 0
#
# perf config trace.show_timestamp=no
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: , flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7fffa79c38e0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mjjnicy48367jah6ls4k0nk8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:17:19 +07:00
|
|
|
size_t printed = 0;
|
|
|
|
|
|
|
|
if (trace->show_tstamp)
|
|
|
|
printed = trace__fprintf_tstamp(trace, tstamp, fp);
|
2018-12-14 20:22:18 +07:00
|
|
|
if (trace->show_duration)
|
|
|
|
printed += fprintf_duration(duration, duration_calculated, fp);
|
2018-08-21 21:40:09 +07:00
|
|
|
return printed + trace__fprintf_comm_tid(trace, thread, fp);
|
|
|
|
}
|
|
|
|
|
2013-08-19 22:01:10 +07:00
|
|
|
static int trace__process_event(struct trace *trace, struct machine *machine,
|
2013-09-11 21:18:24 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
{
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
switch (event->header.type) {
|
|
|
|
case PERF_RECORD_LOST:
|
2013-08-19 22:01:10 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
"LOST %" PRIu64 " events!\n", event->lost.lost);
|
2013-09-11 21:18:24 +07:00
|
|
|
ret = machine__process_lost_event(machine, event, sample);
|
2016-03-31 02:51:17 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
default:
|
2013-09-11 21:18:24 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2013-08-19 22:01:10 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
union perf_event *event,
|
2013-09-11 21:18:24 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
struct machine *machine)
|
|
|
|
{
|
2013-08-19 22:01:10 +07:00
|
|
|
struct trace *trace = container_of(tool, struct trace, tool);
|
2013-09-11 21:18:24 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
}
|
|
|
|
|
2016-05-17 21:56:24 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
static int trace__symbols_init(struct trace *trace, struct perf_evlist *evlist)
|
|
|
|
{
|
2014-08-12 13:40:45 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
2013-09-29 02:13:00 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
2017-11-08 07:22:46 +07:00
|
|
|
err = trace_event__register_resolver(trace->host, trace__machine__resolve_kernel_addr);
|
|
|
|
if (err < 0)
|
|
|
|
goto out;
|
2015-07-23 02:16:16 +07:00
|
|
|
|
2013-11-11 21:36:12 +07:00
|
|
|
err = __machine__synthesize_threads(trace->host, &trace->tool, &trace->opts.target,
|
2015-06-17 20:51:11 +07:00
|
|
|
evlist->threads, trace__tool_process, false,
|
2018-12-05 03:34:20 +07:00
|
|
|
1);
|
2017-11-08 07:22:46 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
if (err)
|
|
|
|
symbol__exit();
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2017-11-08 07:22:45 +07:00
|
|
|
static void trace__symbols__exit(struct trace *trace)
|
|
|
|
{
|
|
|
|
machine__exit(trace->host);
|
|
|
|
trace->host = NULL;
|
|
|
|
|
|
|
|
symbol__exit();
|
|
|
|
}
|
|
|
|
|
2017-07-20 00:32:11 +07:00
|
|
|
static int syscall__alloc_arg_fmts(struct syscall *sc, int nr_args)
|
2013-08-24 04:14:48 +07:00
|
|
|
{
|
2017-07-20 00:32:11 +07:00
|
|
|
int idx;
|
2013-08-24 04:14:48 +07:00
|
|
|
|
2017-07-20 01:08:14 +07:00
|
|
|
if (nr_args == 6 && sc->fmt && sc->fmt->nr_args != 0)
|
|
|
|
nr_args = sc->fmt->nr_args;
|
|
|
|
|
2017-07-20 00:32:11 +07:00
|
|
|
sc->arg_fmt = calloc(nr_args, sizeof(*sc->arg_fmt));
|
2017-07-18 01:22:47 +07:00
|
|
|
if (sc->arg_fmt == NULL)
|
2013-08-24 04:14:48 +07:00
|
|
|
return -1;
|
|
|
|
|
2017-07-20 00:32:11 +07:00
|
|
|
for (idx = 0; idx < nr_args; ++idx) {
|
|
|
|
if (sc->fmt)
|
2017-07-18 01:22:47 +07:00
|
|
|
sc->arg_fmt[idx] = sc->fmt->arg[idx];
|
2017-07-20 00:32:11 +07:00
|
|
|
}
|
2017-07-18 01:22:47 +07:00
|
|
|
|
2017-07-20 00:32:11 +07:00
|
|
|
sc->nr_args = nr_args;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int syscall__set_arg_fmts(struct syscall *sc)
|
|
|
|
{
|
2018-09-20 01:56:45 +07:00
|
|
|
struct tep_format_field *field, *last_field = NULL;
|
2017-07-20 00:32:11 +07:00
|
|
|
int idx = 0, len;
|
|
|
|
|
|
|
|
for (field = sc->args; field; field = field->next, ++idx) {
|
2018-08-21 03:58:17 +07:00
|
|
|
last_field = field;
|
|
|
|
|
2017-07-20 00:32:11 +07:00
|
|
|
if (sc->fmt && sc->fmt->arg[idx].scnprintf)
|
|
|
|
continue;
|
2013-09-04 01:50:28 +07:00
|
|
|
|
2017-07-18 01:22:47 +07:00
|
|
|
if (strcmp(field->type, "const char *") == 0 &&
|
2016-05-24 02:37:55 +07:00
|
|
|
(strcmp(field->name, "filename") == 0 ||
|
|
|
|
strcmp(field->name, "path") == 0 ||
|
|
|
|
strcmp(field->name, "pathname") == 0))
|
2017-07-18 01:22:47 +07:00
|
|
|
sc->arg_fmt[idx].scnprintf = SCA_FILENAME;
|
2018-12-17 22:21:09 +07:00
|
|
|
else if ((field->flags & TEP_FIELD_IS_POINTER) || strstr(field->name, "addr"))
|
|
|
|
sc->arg_fmt[idx].scnprintf = SCA_PTR;
|
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>
2016-04-07 04:02:41 +07:00
|
|
|
else if (strcmp(field->type, "pid_t") == 0)
|
2017-07-18 01:22:47 +07:00
|
|
|
sc->arg_fmt[idx].scnprintf = 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 22:05:51 +07:00
|
|
|
else if (strcmp(field->type, "umode_t") == 0)
|
2017-07-18 01:22:47 +07:00
|
|
|
sc->arg_fmt[idx].scnprintf = SCA_MODE_T;
|
2016-05-23 22:59:53 +07:00
|
|
|
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
|
|
|
|
*/
|
2017-07-18 01:22:47 +07:00
|
|
|
sc->arg_fmt[idx].scnprintf = SCA_FD;
|
2016-05-23 22:59:53 +07:00
|
|
|
}
|
2013-08-24 04:14:48 +07:00
|
|
|
}
|
|
|
|
|
2018-08-21 03:58:17 +07:00
|
|
|
if (last_field)
|
|
|
|
sc->args_size = last_field->offset + last_field->size;
|
|
|
|
|
2013-08-24 04:14:48 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-09-27 06:05:56 +07:00
|
|
|
static int trace__read_syscall_info(struct trace *trace, int id)
|
|
|
|
{
|
|
|
|
char tp_name[128];
|
|
|
|
struct syscall *sc;
|
2016-04-04 23:32:20 +07:00
|
|
|
const char *name = syscalltbl__name(trace->sctbl, id);
|
2012-10-20 22:39:03 +07:00
|
|
|
|
|
|
|
if (name == NULL)
|
|
|
|
return -1;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
|
|
|
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 22:39:03 +07:00
|
|
|
sc->name = name;
|
2013-08-09 22:28:31 +07:00
|
|
|
|
2012-10-20 22:39:03 +07:00
|
|
|
sc->fmt = syscall_fmt__find(sc->name);
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2012-09-27 23:16:00 +07:00
|
|
|
snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->name);
|
2013-12-03 20:09:24 +07:00
|
|
|
sc->tp_format = trace_event__tp_format("syscalls", tp_name);
|
2012-09-27 23:16:00 +07:00
|
|
|
|
2015-09-07 15:38:06 +07:00
|
|
|
if (IS_ERR(sc->tp_format) && sc->fmt && sc->fmt->alias) {
|
2012-09-27 23:16:00 +07:00
|
|
|
snprintf(tp_name, sizeof(tp_name), "sys_enter_%s", sc->fmt->alias);
|
2013-12-03 20:09:24 +07:00
|
|
|
sc->tp_format = trace_event__tp_format("syscalls", tp_name);
|
2012-09-27 23:16:00 +07:00
|
|
|
}
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2017-07-20 00:32:11 +07:00
|
|
|
if (syscall__alloc_arg_fmts(sc, IS_ERR(sc->tp_format) ? 6 : sc->tp_format->format.nr_fields))
|
|
|
|
return -1;
|
|
|
|
|
2015-09-07 15:38:06 +07:00
|
|
|
if (IS_ERR(sc->tp_format))
|
2013-08-24 04:14:48 +07:00
|
|
|
return -1;
|
|
|
|
|
2015-03-21 03:46:53 +07:00
|
|
|
sc->args = sc->tp_format->format.fields;
|
2016-02-26 20:14:25 +07:00
|
|
|
/*
|
|
|
|
* 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"))) {
|
2015-03-21 03:46:53 +07:00
|
|
|
sc->args = sc->args->next;
|
|
|
|
--sc->nr_args;
|
|
|
|
}
|
|
|
|
|
2014-06-18 00:29:24 +07:00
|
|
|
sc->is_exit = !strcmp(name, "exit_group") || !strcmp(name, "exit");
|
perf trace: Associate vfs_getname()'ed pathname with fd returned from 'openat'
When the vfs_getname() wannabe tracepoint is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
#
'perf trace' will use it to get the pathname when it is copied from
userspace to the kernel, right after syscalls:sys_enter_open, copied
in the 'probe:vfs_getname', stash it somewhere and then, at
syscalls:sys_exit_open time, if the 'open' return is not -1, i.e. a
successfull open syscall, associate that pathname to this return, i.e.
the fd.
We were not doing this for the 'openat' syscall, which would cause 'perf
trace' to fallback to using /proc to get the fd, change it so that we
use what we got from probe:vfs_getname, reducing the 'openat'
beautification process cost, ditching the syscalls performed to read
procfs state and avoiding some possible races in the process.
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: https://lkml.kernel.org/n/tip-xnp44ao3bkb6ejeczxfnjwsh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 20:30:08 +07:00
|
|
|
sc->is_open = !strcmp(name, "open") || !strcmp(name, "openat");
|
2014-06-18 00:29:24 +07:00
|
|
|
|
2013-08-24 04:14:48 +07:00
|
|
|
return syscall__set_arg_fmts(sc);
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
|
|
|
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
static int trace__validate_ev_qualifier(struct trace *trace)
|
|
|
|
{
|
2015-07-03 04:28:11 +07:00
|
|
|
int err = 0, i;
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
size_t nr_allocated;
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
struct str_node *pos;
|
|
|
|
|
2015-07-03 04:28:11 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
nr_allocated = trace->ev_qualifier_ids.nr;
|
2015-07-03 04:28:11 +07:00
|
|
|
i = 0;
|
|
|
|
|
2016-06-23 21:31:20 +07:00
|
|
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
const char *sc = pos->s;
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
int id = syscalltbl__id(trace->sctbl, sc), match_next = -1;
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
|
2015-07-03 04:28:11 +07:00
|
|
|
if (id < 0) {
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
id = syscalltbl__strglobmatch_first(trace->sctbl, sc, &match_next);
|
|
|
|
if (id >= 0)
|
|
|
|
goto matches;
|
|
|
|
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
if (err == 0) {
|
|
|
|
fputs("Error:\tInvalid syscall ", trace->output);
|
|
|
|
err = -EINVAL;
|
|
|
|
} else {
|
|
|
|
fputs(", ", trace->output);
|
|
|
|
}
|
|
|
|
|
|
|
|
fputs(sc, trace->output);
|
|
|
|
}
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
matches:
|
2015-07-03 04:28:11 +07:00
|
|
|
trace->ev_qualifier_ids.entries[i++] = id;
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
if (match_next == -1)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
while (1) {
|
|
|
|
id = syscalltbl__strglobmatch_next(trace->sctbl, sc, &match_next);
|
|
|
|
if (id < 0)
|
|
|
|
break;
|
|
|
|
if (nr_allocated == trace->ev_qualifier_ids.nr) {
|
|
|
|
void *entries;
|
|
|
|
|
|
|
|
nr_allocated += 8;
|
|
|
|
entries = realloc(trace->ev_qualifier_ids.entries,
|
|
|
|
nr_allocated * sizeof(trace->ev_qualifier_ids.entries[0]));
|
|
|
|
if (entries == NULL) {
|
|
|
|
err = -ENOMEM;
|
|
|
|
fputs("\nError:\t Not enough memory for parsing\n", trace->output);
|
|
|
|
goto out_free;
|
|
|
|
}
|
|
|
|
trace->ev_qualifier_ids.entries = entries;
|
|
|
|
}
|
|
|
|
trace->ev_qualifier_ids.nr++;
|
|
|
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
if (err < 0) {
|
|
|
|
fputs("\nHint:\ttry 'perf list syscalls:sys_enter_*'"
|
|
|
|
"\nHint:\tand: 'man syscalls'\n", trace->output);
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
out_free:
|
2015-07-03 04:28:11 +07:00
|
|
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
}
|
2015-07-03 04:28:11 +07:00
|
|
|
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>
2015-06-26 05:32:33 +07:00
|
|
|
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>
2015-02-20 03:00:22 +07:00
|
|
|
/*
|
|
|
|
* 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
|
|
|
|
*/
|
2017-07-20 01:02:43 +07:00
|
|
|
unsigned long syscall_arg__val(struct syscall_arg *arg, u8 idx)
|
2017-07-14 20:13:56 +07:00
|
|
|
{
|
|
|
|
unsigned long val;
|
2017-07-20 01:02:43 +07:00
|
|
|
unsigned char *p = arg->args + sizeof(unsigned long) * idx;
|
2017-07-14 20:13:56 +07:00
|
|
|
|
|
|
|
memcpy(&val, p, sizeof(val));
|
|
|
|
return val;
|
|
|
|
}
|
|
|
|
|
2017-07-20 01:47:30 +07:00
|
|
|
static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg)
|
|
|
|
{
|
|
|
|
if (sc->arg_fmt && sc->arg_fmt[arg->idx].name)
|
|
|
|
return scnprintf(bf, size, "%s: ", sc->arg_fmt[arg->idx].name);
|
|
|
|
|
|
|
|
return scnprintf(bf, size, "arg%d: ", arg->idx);
|
|
|
|
}
|
|
|
|
|
2018-10-26 02:09:47 +07:00
|
|
|
/*
|
|
|
|
* Check if the value is in fact zero, i.e. mask whatever needs masking, such
|
|
|
|
* as mount 'flags' argument that needs ignoring some magic flag, see comment
|
|
|
|
* in tools/perf/trace/beauty/mount_flags.c
|
|
|
|
*/
|
|
|
|
static unsigned long syscall__mask_val(struct syscall *sc, struct syscall_arg *arg, unsigned long val)
|
|
|
|
{
|
|
|
|
if (sc->arg_fmt && sc->arg_fmt[arg->idx].mask_val)
|
|
|
|
return sc->arg_fmt[arg->idx].mask_val(arg, val);
|
|
|
|
|
|
|
|
return val;
|
|
|
|
}
|
|
|
|
|
2017-07-20 00:36:13 +07:00
|
|
|
static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
|
|
|
|
struct syscall_arg *arg, unsigned long val)
|
|
|
|
{
|
|
|
|
if (sc->arg_fmt && sc->arg_fmt[arg->idx].scnprintf) {
|
|
|
|
arg->val = val;
|
|
|
|
if (sc->arg_fmt[arg->idx].parm)
|
|
|
|
arg->parm = sc->arg_fmt[arg->idx].parm;
|
|
|
|
return sc->arg_fmt[arg->idx].scnprintf(bf, size, arg);
|
|
|
|
}
|
|
|
|
return scnprintf(bf, size, "%ld", 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>
2012-10-07 04:43:19 +07:00
|
|
|
static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
|
2018-08-21 03:58:17 +07:00
|
|
|
unsigned char *args, void *augmented_args, int augmented_args_size,
|
|
|
|
struct trace *trace, struct thread *thread)
|
2012-09-27 06:05:56 +07:00
|
|
|
{
|
|
|
|
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>
2015-02-20 03:00:22 +07:00
|
|
|
unsigned long val;
|
2017-07-20 00:36:13 +07:00
|
|
|
u8 bit = 1;
|
|
|
|
struct syscall_arg arg = {
|
|
|
|
.args = args,
|
2018-08-21 03:58:17 +07:00
|
|
|
.augmented = {
|
|
|
|
.size = augmented_args_size,
|
|
|
|
.args = augmented_args,
|
|
|
|
},
|
2017-07-20 00:36:13 +07:00
|
|
|
.idx = 0,
|
|
|
|
.mask = 0,
|
|
|
|
.trace = trace,
|
|
|
|
.thread = thread,
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
.show_string_prefix = trace->show_string_prefix,
|
2017-07-20 00:36:13 +07:00
|
|
|
};
|
2017-07-14 21:35:03 +07:00
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Things like fcntl will set this in its 'cmd' formatter to pick the
|
|
|
|
* right formatter for the return value (an fd? file flags?), which is
|
|
|
|
* not needed for syscalls that always return a given type, say an fd.
|
|
|
|
*/
|
|
|
|
ttrace->ret_scnprintf = NULL;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2015-03-21 03:46:53 +07:00
|
|
|
if (sc->args != NULL) {
|
2018-09-20 01:56:45 +07:00
|
|
|
struct tep_format_field *field;
|
2013-09-02 20:39:21 +07:00
|
|
|
|
2015-03-21 03:46:53 +07:00
|
|
|
for (field = sc->args; field;
|
2013-09-03 22:20:12 +07:00
|
|
|
field = field->next, ++arg.idx, bit <<= 1) {
|
|
|
|
if (arg.mask & bit)
|
2013-09-02 20:39:21 +07:00
|
|
|
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>
2015-02-20 03:00:22 +07:00
|
|
|
|
2017-07-14 20:13:56 +07:00
|
|
|
val = syscall_arg__val(&arg, arg.idx);
|
2018-10-26 02:09:47 +07:00
|
|
|
/*
|
|
|
|
* Some syscall args need some mask, most don't and
|
|
|
|
* return val untouched.
|
|
|
|
*/
|
|
|
|
val = syscall__mask_val(sc, &arg, val);
|
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>
2015-02-20 03:00:22 +07:00
|
|
|
|
2013-09-20 22:19:41 +07:00
|
|
|
/*
|
|
|
|
* 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>
2015-02-20 03:00:22 +07:00
|
|
|
if (val == 0 &&
|
2018-12-14 20:12:09 +07:00
|
|
|
!trace->show_zeros &&
|
2017-07-18 01:22:47 +07:00
|
|
|
!(sc->arg_fmt &&
|
perf trace: Allow syscall arg formatters to request non suppression of zeros
The 'perf trace' tool is suppressing args set to zero, with the
exception of string tables (strarrays), which are kinda like enums, i.e.
we have maps to go from numbers to strings.
But the 'cmd' fcntl arg requires more specialized treatment, as its
value will regulate if the next fcntl syscall arg, 'arg', should be
ignored (not used) and also how to format the syscall return (fd, file
flags, etc), so add a 'show_zero" bool to struct syscall_arg_fmt, to
regulate this more explicitely.
Will be used in a following patch with fcntl, here is just the
mechanism.
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-all738jctxets8ffyizp5lzo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-18 01:59:03 +07:00
|
|
|
(sc->arg_fmt[arg.idx].show_zero ||
|
|
|
|
sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAY ||
|
2017-07-18 01:22:47 +07:00
|
|
|
sc->arg_fmt[arg.idx].scnprintf == SCA_STRARRAYS) &&
|
|
|
|
sc->arg_fmt[arg.idx].parm))
|
2013-09-12 21:27:34 +07:00
|
|
|
continue;
|
|
|
|
|
perf trace: Allow suppressing the syscall argument names
To show just the values:
Default:
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Remove it:
# perf config trace.show_arg_names=no
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3
close(3 ) = 0
nanosleep(0x7ffced3a8c40, 0 ) = 0
close(1 ) = 0
close(2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:32:02 +07:00
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s", printed ? ", " : "");
|
|
|
|
|
|
|
|
if (trace->show_arg_names)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, "%s: ", field->name);
|
|
|
|
|
2017-07-20 00:36:13 +07:00
|
|
|
printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
2016-05-06 09:38:05 +07:00
|
|
|
} 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.
|
|
|
|
*/
|
2017-07-20 01:08:14 +07:00
|
|
|
while (arg.idx < sc->nr_args) {
|
2017-07-20 00:36:13 +07:00
|
|
|
if (arg.mask & bit)
|
|
|
|
goto next_arg;
|
|
|
|
val = syscall_arg__val(&arg, arg.idx);
|
2017-07-20 01:47:30 +07:00
|
|
|
if (printed)
|
|
|
|
printed += scnprintf(bf + printed, size - printed, ", ");
|
|
|
|
printed += syscall__scnprintf_name(sc, bf + printed, size - printed, &arg);
|
2017-07-20 00:36:13 +07:00
|
|
|
printed += syscall__scnprintf_val(sc, bf + printed, size - printed, &arg, val);
|
|
|
|
next_arg:
|
|
|
|
++arg.idx;
|
|
|
|
bit <<= 1;
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2012-09-29 03:58:36 +07:00
|
|
|
typedef int (*tracepoint_handler)(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 23:14:24 +07:00
|
|
|
union perf_event *event,
|
2012-09-29 03:58:36 +07:00
|
|
|
struct perf_sample *sample);
|
|
|
|
|
|
|
|
static struct syscall *trace__syscall_info(struct trace *trace,
|
2013-10-09 10:26:53 +07:00
|
|
|
struct perf_evsel *evsel, int id)
|
2012-09-29 03:58:36 +07:00
|
|
|
{
|
|
|
|
|
|
|
|
if (id < 0) {
|
2013-08-23 03:55:25 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* 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);
|
|
|
|
}
|
2012-09-29 03:58:36 +07:00
|
|
|
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 15:17:38 +07:00
|
|
|
if (verbose > 0) {
|
2013-08-23 02:49:54 +07:00
|
|
|
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);
|
|
|
|
}
|
2012-09-29 03:58:36 +07:00
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2013-10-09 10:26:53 +07:00
|
|
|
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: Do not print from time delta for interrupted syscall lines
We were calculating the delta from a in-flight syscall that got its
output interrupted by another syscall, which doesn't seem like useful
information, we will print the syscall duration (sys_exit - sys_enter)
when the raw_syscalls:sys_exit event happens.
The problem here is how we're consuming the multiple ring buffers,
without using the ordered_events code used by perf_session, which may
cause some reordering of syscalls for diferent CPUs, so just stop
printing that delta, to avoid things like:
# trace --print-sample -p 9626 -e futex
raw_syscalls:sys_enter 411967179.269 Timer 9609/9626 [2]
raw_syscalls:sys_enter 411967179.213 file:// Content 9609/9609 [3]
328.038 (18446744073709.496 ms): Timer/9626 futex(uaddr: 0x7fc0d4027044, op: WAIT|PRIV, utime: 0x7fc0b0ffdb50 ) ...
raw_syscalls:sys_exit 411967179.225 file:// Content 9609/9609 [3]
327.982 ( 0.012 ms): file:// Conten/9609 futex(uaddr: 0x7fc0d4027040, op: WAKE|PRIV, val: 1 ) = 1
This is a bandaid, we should better try and use the ordered_events code,
possibly with some refactoring prep work, but for now at least we don't
show those false long deltas for the lines ending in '...'.
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: https://lkml.kernel.org/n/tip-q6xgsqrju1sr6ltud9kjjhmb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 21:42:11 +07:00
|
|
|
static int trace__printf_interrupted_entry(struct trace *trace)
|
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 23:22:21 +07:00
|
|
|
{
|
|
|
|
struct thread_trace *ttrace;
|
|
|
|
size_t printed;
|
2019-01-08 02:24:27 +07:00
|
|
|
int len;
|
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 23:22:21 +07:00
|
|
|
|
perf trace: Show only failing syscalls
For instance:
# 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
# perf trace --failure sleep 1
0.043 ( 0.010 ms): sleep/10978 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
For reference, here are all the syscalls in this case:
# perf trace sleep 1
? ( ): sleep/10976 ... [continued]: execve()) = 0
0.027 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.044 ( 0.010 ms): sleep/10976 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
0.057 ( 0.006 ms): sleep/10976 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.064 ( 0.002 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b370) = 0
0.067 ( 0.003 ms): sleep/10976 mmap(len: 111457, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec8615000
0.071 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.080 ( 0.007 ms): sleep/10976 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.088 ( 0.002 ms): sleep/10976 read(fd: 3, buf: 0x7fffac22b538, count: 832) = 832
0.092 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b3d0) = 0
0.094 ( 0.002 ms): sleep/10976 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7feec8613000
0.099 ( 0.004 ms): sleep/10976 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7feec8057000
0.104 ( 0.007 ms): sleep/10976 mprotect(start: 0x7feec8203000, len: 2097152) = 0
0.112 ( 0.005 ms): sleep/10976 mmap(addr: 0x7feec8403000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1753088) = 0x7feec8403000
0.120 ( 0.003 ms): sleep/10976 mmap(addr: 0x7feec8409000, len: 14976, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED) = 0x7feec8409000
0.128 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.139 ( 0.001 ms): sleep/10976 arch_prctl(option: 4098, arg2: 140663540761856) = 0
0.186 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8403000, len: 16384, prot: READ) = 0
0.204 ( 0.003 ms): sleep/10976 mprotect(start: 0x55bdc0ec3000, len: 4096, prot: READ) = 0
0.209 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8631000, len: 4096, prot: READ) = 0
0.214 ( 0.010 ms): sleep/10976 munmap(addr: 0x7feec8615000, len: 111457) = 0
0.269 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.271 ( 0.002 ms): sleep/10976 brk(brk: 0x55bdc2d25000) = 0x55bdc2d25000
0.274 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d25000
0.278 ( 0.007 ms): sleep/10976 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.288 ( 0.001 ms): sleep/10976 fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7feec8408aa0) = 0
0.290 ( 0.003 ms): sleep/10976 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec1488000
0.297 ( 0.001 ms): sleep/10976 close(fd: 3</usr/lib/locale/locale-archive>) = 0
0.325 (1000.193 ms): sleep/10976 nanosleep(rqtp: 0x7fffac22c0b0) = 0
1000.560 ( 0.006 ms): sleep/10976 close(fd: 1) = 0
1000.573 ( 0.005 ms): sleep/10976 close(fd: 2) = 0
1000.596 ( ): sleep/10976 exit_group()
#
And can be done systemwide, etc, with backtraces:
# perf trace --max-stack=16 --failure sleep 1
0.048 ( 0.015 ms): sleep/11092 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
__access (inlined)
dl_main (/usr/lib64/ld-2.26.so)
#
Or for some specific syscalls:
# perf trace --max-stack=16 -e openat --failure cat /tmp/rien
cat: /tmp/rien: No such file or directory
0.251 ( 0.012 ms): cat/11106 openat(dfd: CWD, filename: /tmp/rien) = -1 ENOENT No such file or directory
__libc_open64 (inlined)
main (/usr/bin/cat)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/cat)
#
Look for inotify* syscalls that fail, system wide, for 2 seconds, with backtraces:
# perf trace -a --max-stack=16 --failure -e inotify* sleep 2
819.165 ( 0.058 ms): gmain/1724 inotify_add_watch(fd: 8<anon_inode:inotify>, pathname: /home/acme/~, mask: 16789454) = -1 ENOENT No such file or directory
__GI_inotify_add_watch (inlined)
_ik_watch (/usr/lib64/libgio-2.0.so.0.5400.3)
_ip_start_watching (/usr/lib64/libgio-2.0.so.0.5400.3)
im_scan_missing (/usr/lib64/libgio-2.0.so.0.5400.3)
g_timeout_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iterate.isra.23 (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iteration (/usr/lib64/libglib-2.0.so.0.5400.3)
glib_worker_main (/usr/lib64/libglib-2.0.so.0.5400.3)
g_thread_proxy (/usr/lib64/libglib-2.0.so.0.5400.3)
start_thread (/usr/lib64/libpthread-2.26.so)
__GI___clone (inlined)
#
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: https://lkml.kernel.org/n/tip-8f7d3mngaxvi7tlzloz3n7cs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-29 22:22:59 +07:00
|
|
|
if (trace->failure_only || trace->current == NULL)
|
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 23:22:21 +07:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
ttrace = thread__priv(trace->current);
|
|
|
|
|
|
|
|
if (!ttrace->entry_pending)
|
|
|
|
return 0;
|
|
|
|
|
perf trace: Do not print from time delta for interrupted syscall lines
We were calculating the delta from a in-flight syscall that got its
output interrupted by another syscall, which doesn't seem like useful
information, we will print the syscall duration (sys_exit - sys_enter)
when the raw_syscalls:sys_exit event happens.
The problem here is how we're consuming the multiple ring buffers,
without using the ordered_events code used by perf_session, which may
cause some reordering of syscalls for diferent CPUs, so just stop
printing that delta, to avoid things like:
# trace --print-sample -p 9626 -e futex
raw_syscalls:sys_enter 411967179.269 Timer 9609/9626 [2]
raw_syscalls:sys_enter 411967179.213 file:// Content 9609/9609 [3]
328.038 (18446744073709.496 ms): Timer/9626 futex(uaddr: 0x7fc0d4027044, op: WAIT|PRIV, utime: 0x7fc0b0ffdb50 ) ...
raw_syscalls:sys_exit 411967179.225 file:// Content 9609/9609 [3]
327.982 ( 0.012 ms): file:// Conten/9609 futex(uaddr: 0x7fc0d4027040, op: WAKE|PRIV, val: 1 ) = 1
This is a bandaid, we should better try and use the ordered_events code,
possibly with some refactoring prep work, but for now at least we don't
show those false long deltas for the lines ending in '...'.
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: https://lkml.kernel.org/n/tip-q6xgsqrju1sr6ltud9kjjhmb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 21:42:11 +07:00
|
|
|
printed = trace__fprintf_entry_head(trace, trace->current, 0, false, ttrace->entry_time, trace->output);
|
2019-01-08 02:24:27 +07:00
|
|
|
printed += len = fprintf(trace->output, "%s)", ttrace->entry_str);
|
|
|
|
|
|
|
|
if (len < trace->args_alignment - 4)
|
|
|
|
printed += fprintf(trace->output, "%-*s", trace->args_alignment - 4 - len, " ");
|
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 23:22:21 +07:00
|
|
|
|
2019-01-08 02:24:27 +07:00
|
|
|
printed += fprintf(trace->output, " ...\n");
|
|
|
|
|
|
|
|
ttrace->entry_pending = false;
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
++trace->nr_events_printed;
|
|
|
|
|
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 23:22:21 +07:00
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2018-01-22 21:38:54 +07:00
|
|
|
static int trace__fprintf_sample(struct trace *trace, struct perf_evsel *evsel,
|
|
|
|
struct perf_sample *sample, struct thread *thread)
|
|
|
|
{
|
|
|
|
int printed = 0;
|
|
|
|
|
|
|
|
if (trace->print_sample) {
|
|
|
|
double ts = (double)sample->time / NSEC_PER_MSEC;
|
|
|
|
|
|
|
|
printed += fprintf(trace->output, "%22s %10.3f %s %d/%d [%d]\n",
|
|
|
|
perf_evsel__name(evsel), ts,
|
|
|
|
thread__comm_str(thread),
|
|
|
|
sample->pid, sample->tid, sample->cpu);
|
|
|
|
}
|
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
static void *syscall__augmented_args(struct syscall *sc, struct perf_sample *sample, int *augmented_args_size, int raw_augmented_args_size)
|
2018-09-04 02:07:53 +07:00
|
|
|
{
|
|
|
|
void *augmented_args = NULL;
|
2018-11-03 18:19:56 +07:00
|
|
|
/*
|
|
|
|
* For now with BPF raw_augmented we hook into raw_syscalls:sys_enter
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
* and there we get all 6 syscall args plus the tracepoint common fields
|
|
|
|
* that gets calculated at the start and the syscall_nr (another long).
|
|
|
|
* So we check if that is the case and if so don't look after the
|
|
|
|
* sc->args_size but always after the full raw_syscalls:sys_enter payload,
|
|
|
|
* which is fixed.
|
2018-11-03 18:19:56 +07:00
|
|
|
*
|
|
|
|
* We'll revisit this later to pass s->args_size to the BPF augmenter
|
|
|
|
* (now tools/perf/examples/bpf/augmented_raw_syscalls.c, so that it
|
|
|
|
* copies only what we need for each syscall, like what happens when we
|
|
|
|
* use syscalls:sys_enter_NAME, so that we reduce the kernel/userspace
|
|
|
|
* traffic to just what is needed for each syscall.
|
|
|
|
*/
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
int args_size = raw_augmented_args_size ?: sc->args_size;
|
2018-09-04 02:07:53 +07:00
|
|
|
|
2018-11-03 18:19:56 +07:00
|
|
|
*augmented_args_size = sample->raw_size - args_size;
|
2018-09-04 02:07:53 +07:00
|
|
|
if (*augmented_args_size > 0)
|
2018-11-03 18:19:56 +07:00
|
|
|
augmented_args = sample->raw_data + args_size;
|
2018-09-04 02:07:53 +07:00
|
|
|
|
|
|
|
return augmented_args;
|
|
|
|
}
|
|
|
|
|
2012-09-29 03:58:36 +07:00
|
|
|
static int trace__sys_enter(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 23:14:24 +07:00
|
|
|
union perf_event *event __maybe_unused,
|
2012-09-29 03:58:36 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
char *msg;
|
2012-09-29 03:58:36 +07:00
|
|
|
void *args;
|
2018-12-17 21:48:46 +07:00
|
|
|
int printed = 0;
|
2013-08-09 22:28:31 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
|
2018-09-04 02:24:09 +07:00
|
|
|
int augmented_args_size = 0;
|
|
|
|
void *augmented_args = NULL;
|
2013-10-09 10:26:53 +07:00
|
|
|
struct syscall *sc = trace__syscall_info(trace, evsel, id);
|
2013-08-09 22:28:31 +07:00
|
|
|
struct thread_trace *ttrace;
|
|
|
|
|
|
|
|
if (sc == NULL)
|
|
|
|
return -1;
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2013-09-29 02:13:00 +07:00
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2013-08-19 22:01:10 +07:00
|
|
|
ttrace = thread__trace(thread, trace->output);
|
2013-08-09 22:28:31 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
goto out_put;
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2018-01-22 21:38:54 +07:00
|
|
|
trace__fprintf_sample(trace, evsel, sample, thread);
|
|
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
|
|
|
if (ttrace->entry_str == NULL) {
|
2015-08-05 08:17:29 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
}
|
|
|
|
|
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 21:10:31 +07:00
|
|
|
if (!(trace->duration_filter || trace->summary_only || trace->min_stack))
|
perf trace: Do not print from time delta for interrupted syscall lines
We were calculating the delta from a in-flight syscall that got its
output interrupted by another syscall, which doesn't seem like useful
information, we will print the syscall duration (sys_exit - sys_enter)
when the raw_syscalls:sys_exit event happens.
The problem here is how we're consuming the multiple ring buffers,
without using the ordered_events code used by perf_session, which may
cause some reordering of syscalls for diferent CPUs, so just stop
printing that delta, to avoid things like:
# trace --print-sample -p 9626 -e futex
raw_syscalls:sys_enter 411967179.269 Timer 9609/9626 [2]
raw_syscalls:sys_enter 411967179.213 file:// Content 9609/9609 [3]
328.038 (18446744073709.496 ms): Timer/9626 futex(uaddr: 0x7fc0d4027044, op: WAIT|PRIV, utime: 0x7fc0b0ffdb50 ) ...
raw_syscalls:sys_exit 411967179.225 file:// Content 9609/9609 [3]
327.982 ( 0.012 ms): file:// Conten/9609 futex(uaddr: 0x7fc0d4027040, op: WAKE|PRIV, val: 1 ) = 1
This is a bandaid, we should better try and use the ordered_events code,
possibly with some refactoring prep work, but for now at least we don't
show those false long deltas for the lines ending in '...'.
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: https://lkml.kernel.org/n/tip-q6xgsqrju1sr6ltud9kjjhmb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 21:42:11 +07:00
|
|
|
trace__printf_interrupted_entry(trace);
|
2018-09-04 02:24:09 +07:00
|
|
|
/*
|
|
|
|
* If this is raw_syscalls.sys_enter, then it always comes with the 6 possible
|
|
|
|
* arguments, even if the syscall being handled, say "openat", uses only 4 arguments
|
|
|
|
* this breaks syscall__augmented_args() check for augmented args, as we calculate
|
|
|
|
* syscall->args_size using each syscalls:sys_enter_NAME tracefs format file,
|
|
|
|
* so when handling, say the openat syscall, we end up getting 6 args for the
|
|
|
|
* raw_syscalls:sys_enter event, when we expected just 4, we end up mistakenly
|
|
|
|
* thinking that the extra 2 u64 args are the augmented filename, so just check
|
|
|
|
* here and avoid using augmented syscalls when the evsel is the raw_syscalls one.
|
|
|
|
*/
|
|
|
|
if (evsel != trace->syscalls.events.sys_enter)
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_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>
2012-10-07 04:43:19 +07:00
|
|
|
ttrace->entry_time = sample->time;
|
|
|
|
msg = ttrace->entry_str;
|
2015-08-05 08:17:29 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
2015-08-05 08:17:29 +07:00
|
|
|
printed += syscall__scnprintf_args(sc, msg + printed, trace__entry_str_size - printed,
|
2018-09-04 02:24:09 +07:00
|
|
|
args, augmented_args, augmented_args_size, 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>
2012-10-07 04:43:19 +07:00
|
|
|
|
2014-06-18 00:29:24 +07:00
|
|
|
if (sc->is_exit) {
|
perf trace: Show only failing syscalls
For instance:
# 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
# perf trace --failure sleep 1
0.043 ( 0.010 ms): sleep/10978 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
For reference, here are all the syscalls in this case:
# perf trace sleep 1
? ( ): sleep/10976 ... [continued]: execve()) = 0
0.027 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.044 ( 0.010 ms): sleep/10976 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
0.057 ( 0.006 ms): sleep/10976 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.064 ( 0.002 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b370) = 0
0.067 ( 0.003 ms): sleep/10976 mmap(len: 111457, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec8615000
0.071 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.080 ( 0.007 ms): sleep/10976 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.088 ( 0.002 ms): sleep/10976 read(fd: 3, buf: 0x7fffac22b538, count: 832) = 832
0.092 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b3d0) = 0
0.094 ( 0.002 ms): sleep/10976 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7feec8613000
0.099 ( 0.004 ms): sleep/10976 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7feec8057000
0.104 ( 0.007 ms): sleep/10976 mprotect(start: 0x7feec8203000, len: 2097152) = 0
0.112 ( 0.005 ms): sleep/10976 mmap(addr: 0x7feec8403000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1753088) = 0x7feec8403000
0.120 ( 0.003 ms): sleep/10976 mmap(addr: 0x7feec8409000, len: 14976, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED) = 0x7feec8409000
0.128 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.139 ( 0.001 ms): sleep/10976 arch_prctl(option: 4098, arg2: 140663540761856) = 0
0.186 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8403000, len: 16384, prot: READ) = 0
0.204 ( 0.003 ms): sleep/10976 mprotect(start: 0x55bdc0ec3000, len: 4096, prot: READ) = 0
0.209 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8631000, len: 4096, prot: READ) = 0
0.214 ( 0.010 ms): sleep/10976 munmap(addr: 0x7feec8615000, len: 111457) = 0
0.269 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.271 ( 0.002 ms): sleep/10976 brk(brk: 0x55bdc2d25000) = 0x55bdc2d25000
0.274 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d25000
0.278 ( 0.007 ms): sleep/10976 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.288 ( 0.001 ms): sleep/10976 fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7feec8408aa0) = 0
0.290 ( 0.003 ms): sleep/10976 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec1488000
0.297 ( 0.001 ms): sleep/10976 close(fd: 3</usr/lib/locale/locale-archive>) = 0
0.325 (1000.193 ms): sleep/10976 nanosleep(rqtp: 0x7fffac22c0b0) = 0
1000.560 ( 0.006 ms): sleep/10976 close(fd: 1) = 0
1000.573 ( 0.005 ms): sleep/10976 close(fd: 2) = 0
1000.596 ( ): sleep/10976 exit_group()
#
And can be done systemwide, etc, with backtraces:
# perf trace --max-stack=16 --failure sleep 1
0.048 ( 0.015 ms): sleep/11092 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
__access (inlined)
dl_main (/usr/lib64/ld-2.26.so)
#
Or for some specific syscalls:
# perf trace --max-stack=16 -e openat --failure cat /tmp/rien
cat: /tmp/rien: No such file or directory
0.251 ( 0.012 ms): cat/11106 openat(dfd: CWD, filename: /tmp/rien) = -1 ENOENT No such file or directory
__libc_open64 (inlined)
main (/usr/bin/cat)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/cat)
#
Look for inotify* syscalls that fail, system wide, for 2 seconds, with backtraces:
# perf trace -a --max-stack=16 --failure -e inotify* sleep 2
819.165 ( 0.058 ms): gmain/1724 inotify_add_watch(fd: 8<anon_inode:inotify>, pathname: /home/acme/~, mask: 16789454) = -1 ENOENT No such file or directory
__GI_inotify_add_watch (inlined)
_ik_watch (/usr/lib64/libgio-2.0.so.0.5400.3)
_ip_start_watching (/usr/lib64/libgio-2.0.so.0.5400.3)
im_scan_missing (/usr/lib64/libgio-2.0.so.0.5400.3)
g_timeout_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iterate.isra.23 (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iteration (/usr/lib64/libglib-2.0.so.0.5400.3)
glib_worker_main (/usr/lib64/libglib-2.0.so.0.5400.3)
g_thread_proxy (/usr/lib64/libglib-2.0.so.0.5400.3)
start_thread (/usr/lib64/libpthread-2.26.so)
__GI___clone (inlined)
#
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: https://lkml.kernel.org/n/tip-8f7d3mngaxvi7tlzloz3n7cs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-29 22:22:59 +07:00
|
|
|
if (!(trace->duration_filter || trace->summary_only || trace->failure_only || trace->min_stack)) {
|
2018-12-17 21:48:46 +07:00
|
|
|
int alignment = 0;
|
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
trace__fprintf_entry_head(trace, thread, 0, false, ttrace->entry_time, trace->output);
|
2018-12-17 21:48:46 +07:00
|
|
|
printed = fprintf(trace->output, "%s)", ttrace->entry_str);
|
|
|
|
if (trace->args_alignment > printed)
|
|
|
|
alignment = trace->args_alignment - printed;
|
|
|
|
fprintf(trace->output, "%*s= ?\n", alignment, " ");
|
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 19:56:00 +07:00
|
|
|
}
|
2015-08-14 23:16:27 +07:00
|
|
|
} 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>
2012-10-07 04:43:19 +07:00
|
|
|
ttrace->entry_pending = true;
|
2015-08-14 23:16:27 +07:00
|
|
|
/* See trace__vfs_getname & trace__sys_exit */
|
|
|
|
ttrace->filename.pending_open = false;
|
|
|
|
}
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2015-03-03 08:21:35 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
2012-09-29 03:58:36 +07:00
|
|
|
}
|
|
|
|
|
perf trace: Use beautifiers on syscalls:sys_enter_ handlers
We were using the beautifiers only when processing the
raw_syscalls:sys_enter events, but we can as well use them for the
syscalls:sys_enter_NAME events, as the layout is the same.
Some more tweaking is needed as we're processing them straight away,
i.e. there is no buffering in the sys_enter_NAME event to wait for
things like vfs_getname to provide pointer contents and then flushing
at sys_exit_NAME, so we need to state in the syscall_arg that this
is unbuffered, just print the pointer values, beautifying just
non-pointer syscall args.
This just shows an alternative way of processing tracepoints, that we
will end up using when creating "tracepoint" payloads that already copy
pointer contents (or chunks of it, i.e. not the whole filename, but just
the end of it, not all the bf for a read/write, but just the start,
etc), directly in the kernel using eBPF.
E.g.:
# perf trace -e syscalls:*enter*sleep,*sleep sleep 1
0.303 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffc93d5ecc0
0.305 (1000.229 ms): sleep/8746 nanosleep(rqtp: 0x7ffc93d5ecc0) = 0
# perf trace -e syscalls:*_*sleep,*sleep sleep 1
0.288 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffecde87e40
0.289 ( ): sleep/8748 nanosleep(rqtp: 0x7ffecde87e40) ...
1000.479 ( ): syscalls:sys_exit_nanosleep:0x0
0.289 (1000.208 ms): sleep/8748 ... [continued]: nanosleep()) = 0
#
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jehyd2zwhw00z3p7v7mg9632@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-03 00:05:09 +07:00
|
|
|
static int trace__fprintf_sys_enter(struct trace *trace, struct perf_evsel *evsel,
|
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
struct thread_trace *ttrace;
|
|
|
|
struct thread *thread;
|
2018-08-03 01:11:58 +07:00
|
|
|
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1;
|
|
|
|
struct syscall *sc = trace__syscall_info(trace, evsel, id);
|
perf trace: Use beautifiers on syscalls:sys_enter_ handlers
We were using the beautifiers only when processing the
raw_syscalls:sys_enter events, but we can as well use them for the
syscalls:sys_enter_NAME events, as the layout is the same.
Some more tweaking is needed as we're processing them straight away,
i.e. there is no buffering in the sys_enter_NAME event to wait for
things like vfs_getname to provide pointer contents and then flushing
at sys_exit_NAME, so we need to state in the syscall_arg that this
is unbuffered, just print the pointer values, beautifying just
non-pointer syscall args.
This just shows an alternative way of processing tracepoints, that we
will end up using when creating "tracepoint" payloads that already copy
pointer contents (or chunks of it, i.e. not the whole filename, but just
the end of it, not all the bf for a read/write, but just the start,
etc), directly in the kernel using eBPF.
E.g.:
# perf trace -e syscalls:*enter*sleep,*sleep sleep 1
0.303 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffc93d5ecc0
0.305 (1000.229 ms): sleep/8746 nanosleep(rqtp: 0x7ffc93d5ecc0) = 0
# perf trace -e syscalls:*_*sleep,*sleep sleep 1
0.288 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffecde87e40
0.289 ( ): sleep/8748 nanosleep(rqtp: 0x7ffecde87e40) ...
1000.479 ( ): syscalls:sys_exit_nanosleep:0x0
0.289 (1000.208 ms): sleep/8748 ... [continued]: nanosleep()) = 0
#
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jehyd2zwhw00z3p7v7mg9632@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-03 00:05:09 +07:00
|
|
|
char msg[1024];
|
2018-08-21 03:58:17 +07:00
|
|
|
void *args, *augmented_args = NULL;
|
|
|
|
int augmented_args_size;
|
perf trace: Use beautifiers on syscalls:sys_enter_ handlers
We were using the beautifiers only when processing the
raw_syscalls:sys_enter events, but we can as well use them for the
syscalls:sys_enter_NAME events, as the layout is the same.
Some more tweaking is needed as we're processing them straight away,
i.e. there is no buffering in the sys_enter_NAME event to wait for
things like vfs_getname to provide pointer contents and then flushing
at sys_exit_NAME, so we need to state in the syscall_arg that this
is unbuffered, just print the pointer values, beautifying just
non-pointer syscall args.
This just shows an alternative way of processing tracepoints, that we
will end up using when creating "tracepoint" payloads that already copy
pointer contents (or chunks of it, i.e. not the whole filename, but just
the end of it, not all the bf for a read/write, but just the start,
etc), directly in the kernel using eBPF.
E.g.:
# perf trace -e syscalls:*enter*sleep,*sleep sleep 1
0.303 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffc93d5ecc0
0.305 (1000.229 ms): sleep/8746 nanosleep(rqtp: 0x7ffc93d5ecc0) = 0
# perf trace -e syscalls:*_*sleep,*sleep sleep 1
0.288 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffecde87e40
0.289 ( ): sleep/8748 nanosleep(rqtp: 0x7ffecde87e40) ...
1000.479 ( ): syscalls:sys_exit_nanosleep:0x0
0.289 (1000.208 ms): sleep/8748 ... [continued]: nanosleep()) = 0
#
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jehyd2zwhw00z3p7v7mg9632@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-03 00:05:09 +07:00
|
|
|
|
|
|
|
if (sc == NULL)
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
|
|
|
ttrace = thread__trace(thread, trace->output);
|
|
|
|
/*
|
|
|
|
* We need to get ttrace just to make sure it is there when syscall__scnprintf_args()
|
|
|
|
* and the rest of the beautifiers accessing it via struct syscall_arg touches it.
|
|
|
|
*/
|
|
|
|
if (ttrace == NULL)
|
|
|
|
goto out_put;
|
|
|
|
|
2018-08-03 01:11:58 +07:00
|
|
|
args = perf_evsel__sc_tp_ptr(evsel, args, sample);
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
augmented_args = syscall__augmented_args(sc, sample, &augmented_args_size, trace->raw_augmented_syscalls_args_size);
|
2018-08-21 03:58:17 +07:00
|
|
|
syscall__scnprintf_args(sc, msg, sizeof(msg), args, augmented_args, augmented_args_size, trace, thread);
|
perf trace: Use beautifiers on syscalls:sys_enter_ handlers
We were using the beautifiers only when processing the
raw_syscalls:sys_enter events, but we can as well use them for the
syscalls:sys_enter_NAME events, as the layout is the same.
Some more tweaking is needed as we're processing them straight away,
i.e. there is no buffering in the sys_enter_NAME event to wait for
things like vfs_getname to provide pointer contents and then flushing
at sys_exit_NAME, so we need to state in the syscall_arg that this
is unbuffered, just print the pointer values, beautifying just
non-pointer syscall args.
This just shows an alternative way of processing tracepoints, that we
will end up using when creating "tracepoint" payloads that already copy
pointer contents (or chunks of it, i.e. not the whole filename, but just
the end of it, not all the bf for a read/write, but just the start,
etc), directly in the kernel using eBPF.
E.g.:
# perf trace -e syscalls:*enter*sleep,*sleep sleep 1
0.303 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffc93d5ecc0
0.305 (1000.229 ms): sleep/8746 nanosleep(rqtp: 0x7ffc93d5ecc0) = 0
# perf trace -e syscalls:*_*sleep,*sleep sleep 1
0.288 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffecde87e40
0.289 ( ): sleep/8748 nanosleep(rqtp: 0x7ffecde87e40) ...
1000.479 ( ): syscalls:sys_exit_nanosleep:0x0
0.289 (1000.208 ms): sleep/8748 ... [continued]: nanosleep()) = 0
#
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jehyd2zwhw00z3p7v7mg9632@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-03 00:05:09 +07:00
|
|
|
fprintf(trace->output, "%s", msg);
|
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
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 21:10:31 +07:00
|
|
|
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 20:11:07 +07:00
|
|
|
{
|
|
|
|
struct addr_location al;
|
2018-01-30 12:30:53 +07:00
|
|
|
int max_stack = evsel->attr.sample_max_stack ?
|
|
|
|
evsel->attr.sample_max_stack :
|
|
|
|
trace->max_stack;
|
2018-10-20 19:18:50 +07:00
|
|
|
int err;
|
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 21:10:31 +07:00
|
|
|
|
2018-10-20 19:18:50 +07:00
|
|
|
if (machine__resolve(trace->host, &al, sample) < 0)
|
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 21:10:31 +07:00
|
|
|
return -1;
|
|
|
|
|
2018-10-20 19:18:50 +07:00
|
|
|
err = thread__resolve_callchain(al.thread, cursor, evsel, sample, NULL, NULL, max_stack);
|
|
|
|
addr_location__put(&al);
|
|
|
|
return err;
|
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 21:10:31 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
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 20:11:07 +07:00
|
|
|
/* TODO: user-configurable print_opts */
|
2016-04-13 01:16:15 +07:00
|
|
|
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 20:11:07 +07:00
|
|
|
|
2016-04-15 03:53:49 +07:00
|
|
|
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 20:11:07 +07:00
|
|
|
}
|
|
|
|
|
2018-01-19 15:56:16 +07:00
|
|
|
static const char *errno_to_name(struct perf_evsel *evsel, int err)
|
|
|
|
{
|
|
|
|
struct perf_env *env = perf_evsel__env(evsel);
|
|
|
|
const char *arch_name = perf_env__arch(env);
|
|
|
|
|
|
|
|
return arch_syscalls__strerrno(arch_name, err);
|
|
|
|
}
|
|
|
|
|
2012-09-29 03:58:36 +07:00
|
|
|
static int trace__sys_exit(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 23:14:24 +07:00
|
|
|
union perf_event *event __maybe_unused,
|
2012-09-29 03:58:36 +07:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
2014-09-26 19:54:01 +07:00
|
|
|
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>
2012-10-25 02:24:47 +07:00
|
|
|
u64 duration = 0;
|
2017-03-30 02:37:51 +07:00
|
|
|
bool duration_calculated = false;
|
2013-08-09 22:28:31 +07:00
|
|
|
struct thread *thread;
|
2018-12-17 21:48:46 +07:00
|
|
|
int id = perf_evsel__sc_tp_uint(evsel, id, sample), err = -1, callchain_ret = 0, printed = 0;
|
|
|
|
int alignment = trace->args_alignment;
|
2013-10-09 10:26:53 +07:00
|
|
|
struct syscall *sc = trace__syscall_info(trace, evsel, id);
|
2013-08-09 22:28:31 +07:00
|
|
|
struct thread_trace *ttrace;
|
|
|
|
|
|
|
|
if (sc == NULL)
|
|
|
|
return -1;
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2013-09-29 02:13:00 +07:00
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2013-08-19 22:01:10 +07:00
|
|
|
ttrace = thread__trace(thread, trace->output);
|
2013-08-09 22:28:31 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
goto out_put;
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2018-01-22 21:38:54 +07:00
|
|
|
trace__fprintf_sample(trace, evsel, sample, thread);
|
|
|
|
|
2013-10-09 10:26:53 +07:00
|
|
|
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>
2013-11-07 02:35:57 +07:00
|
|
|
ret = perf_evsel__sc_tp_uint(evsel, ret, sample);
|
2012-09-29 03:58:36 +07:00
|
|
|
|
perf trace: Associate vfs_getname()'ed pathname with fd returned from 'openat'
When the vfs_getname() wannabe tracepoint is in place:
# perf probe -l
probe:vfs_getname (on getname_flags:73@acme/git/linux/fs/namei.c with pathname)
#
'perf trace' will use it to get the pathname when it is copied from
userspace to the kernel, right after syscalls:sys_enter_open, copied
in the 'probe:vfs_getname', stash it somewhere and then, at
syscalls:sys_exit_open time, if the 'open' return is not -1, i.e. a
successfull open syscall, associate that pathname to this return, i.e.
the fd.
We were not doing this for the 'openat' syscall, which would cause 'perf
trace' to fallback to using /proc to get the fd, change it so that we
use what we got from probe:vfs_getname, reducing the 'openat'
beautification process cost, ditching the syscalls performed to read
procfs state and avoiding some possible races in the process.
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: https://lkml.kernel.org/n/tip-xnp44ao3bkb6ejeczxfnjwsh@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 20:30:08 +07:00
|
|
|
if (sc->is_open && ret >= 0 && ttrace->filename.pending_open) {
|
2015-08-14 23:16:27 +07:00
|
|
|
trace__set_fd_pathname(thread, ret, ttrace->filename.name);
|
|
|
|
ttrace->filename.pending_open = false;
|
2013-09-28 04:06:19 +07:00
|
|
|
++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 19:56:00 +07:00
|
|
|
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>
2012-10-25 02:24:47 +07:00
|
|
|
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 19:56:00 +07:00
|
|
|
if (trace__filter_duration(trace, duration))
|
|
|
|
goto out;
|
2017-03-30 02:37:51 +07:00
|
|
|
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 19:56:00 +07:00
|
|
|
} 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>
2012-10-25 02:24:47 +07:00
|
|
|
|
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 21:10:31 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
perf trace: Show only failing syscalls
For instance:
# 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
# perf trace --failure sleep 1
0.043 ( 0.010 ms): sleep/10978 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
For reference, here are all the syscalls in this case:
# perf trace sleep 1
? ( ): sleep/10976 ... [continued]: execve()) = 0
0.027 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.044 ( 0.010 ms): sleep/10976 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
0.057 ( 0.006 ms): sleep/10976 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.064 ( 0.002 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b370) = 0
0.067 ( 0.003 ms): sleep/10976 mmap(len: 111457, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec8615000
0.071 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.080 ( 0.007 ms): sleep/10976 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.088 ( 0.002 ms): sleep/10976 read(fd: 3, buf: 0x7fffac22b538, count: 832) = 832
0.092 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b3d0) = 0
0.094 ( 0.002 ms): sleep/10976 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7feec8613000
0.099 ( 0.004 ms): sleep/10976 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7feec8057000
0.104 ( 0.007 ms): sleep/10976 mprotect(start: 0x7feec8203000, len: 2097152) = 0
0.112 ( 0.005 ms): sleep/10976 mmap(addr: 0x7feec8403000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1753088) = 0x7feec8403000
0.120 ( 0.003 ms): sleep/10976 mmap(addr: 0x7feec8409000, len: 14976, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED) = 0x7feec8409000
0.128 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.139 ( 0.001 ms): sleep/10976 arch_prctl(option: 4098, arg2: 140663540761856) = 0
0.186 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8403000, len: 16384, prot: READ) = 0
0.204 ( 0.003 ms): sleep/10976 mprotect(start: 0x55bdc0ec3000, len: 4096, prot: READ) = 0
0.209 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8631000, len: 4096, prot: READ) = 0
0.214 ( 0.010 ms): sleep/10976 munmap(addr: 0x7feec8615000, len: 111457) = 0
0.269 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.271 ( 0.002 ms): sleep/10976 brk(brk: 0x55bdc2d25000) = 0x55bdc2d25000
0.274 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d25000
0.278 ( 0.007 ms): sleep/10976 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.288 ( 0.001 ms): sleep/10976 fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7feec8408aa0) = 0
0.290 ( 0.003 ms): sleep/10976 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec1488000
0.297 ( 0.001 ms): sleep/10976 close(fd: 3</usr/lib/locale/locale-archive>) = 0
0.325 (1000.193 ms): sleep/10976 nanosleep(rqtp: 0x7fffac22c0b0) = 0
1000.560 ( 0.006 ms): sleep/10976 close(fd: 1) = 0
1000.573 ( 0.005 ms): sleep/10976 close(fd: 2) = 0
1000.596 ( ): sleep/10976 exit_group()
#
And can be done systemwide, etc, with backtraces:
# perf trace --max-stack=16 --failure sleep 1
0.048 ( 0.015 ms): sleep/11092 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
__access (inlined)
dl_main (/usr/lib64/ld-2.26.so)
#
Or for some specific syscalls:
# perf trace --max-stack=16 -e openat --failure cat /tmp/rien
cat: /tmp/rien: No such file or directory
0.251 ( 0.012 ms): cat/11106 openat(dfd: CWD, filename: /tmp/rien) = -1 ENOENT No such file or directory
__libc_open64 (inlined)
main (/usr/bin/cat)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/cat)
#
Look for inotify* syscalls that fail, system wide, for 2 seconds, with backtraces:
# perf trace -a --max-stack=16 --failure -e inotify* sleep 2
819.165 ( 0.058 ms): gmain/1724 inotify_add_watch(fd: 8<anon_inode:inotify>, pathname: /home/acme/~, mask: 16789454) = -1 ENOENT No such file or directory
__GI_inotify_add_watch (inlined)
_ik_watch (/usr/lib64/libgio-2.0.so.0.5400.3)
_ip_start_watching (/usr/lib64/libgio-2.0.so.0.5400.3)
im_scan_missing (/usr/lib64/libgio-2.0.so.0.5400.3)
g_timeout_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iterate.isra.23 (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iteration (/usr/lib64/libglib-2.0.so.0.5400.3)
glib_worker_main (/usr/lib64/libglib-2.0.so.0.5400.3)
g_thread_proxy (/usr/lib64/libglib-2.0.so.0.5400.3)
start_thread (/usr/lib64/libpthread-2.26.so)
__GI___clone (inlined)
#
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: https://lkml.kernel.org/n/tip-8f7d3mngaxvi7tlzloz3n7cs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-29 22:22:59 +07:00
|
|
|
if (trace->summary_only || (ret >= 0 && trace->failure_only))
|
2013-11-12 23:31:15 +07:00
|
|
|
goto out;
|
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
|
|
|
|
if (ttrace->entry_pending) {
|
2018-12-17 21:48:46 +07:00
|
|
|
printed = fprintf(trace->output, "%s", 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>
2012-10-07 04:43:19 +07:00
|
|
|
} else {
|
2019-01-08 02:54:38 +07:00
|
|
|
printed += fprintf(trace->output, " ... [");
|
2013-08-19 22:01:10 +07:00
|
|
|
color_fprintf(trace->output, PERF_COLOR_YELLOW, "continued");
|
2019-01-08 02:54:38 +07:00
|
|
|
printed += 9;
|
|
|
|
printed += 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>
2012-10-07 04:43:19 +07:00
|
|
|
}
|
|
|
|
|
2018-12-17 21:48:46 +07:00
|
|
|
printed++; /* the closing ')' */
|
|
|
|
|
|
|
|
if (alignment > printed)
|
|
|
|
alignment -= printed;
|
|
|
|
else
|
|
|
|
alignment = 0;
|
|
|
|
|
|
|
|
fprintf(trace->output, ")%*s= ", alignment, " ");
|
|
|
|
|
2013-08-26 21:28:34 +07:00
|
|
|
if (sc->fmt == NULL) {
|
2017-07-18 22:45:57 +07:00
|
|
|
if (ret < 0)
|
|
|
|
goto errno_print;
|
2013-08-26 21:28:34 +07:00
|
|
|
signed_print:
|
2018-12-17 21:48:46 +07:00
|
|
|
fprintf(trace->output, "%ld", ret);
|
2017-07-18 22:45:57 +07:00
|
|
|
} else if (ret < 0) {
|
|
|
|
errno_print: {
|
2014-08-14 09:22:41 +07:00
|
|
|
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 21:56:20 +07:00
|
|
|
const char *emsg = str_error_r(-ret, bf, sizeof(bf)),
|
2018-01-19 15:56:16 +07:00
|
|
|
*e = errno_to_name(evsel, -ret);
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2018-12-17 22:06:34 +07:00
|
|
|
fprintf(trace->output, "-1 %s (%s)", e, emsg);
|
2017-07-18 22:45:57 +07:00
|
|
|
}
|
2013-08-26 21:28:34 +07:00
|
|
|
} else if (ret == 0 && sc->fmt->timeout)
|
2018-12-17 22:06:34 +07:00
|
|
|
fprintf(trace->output, "0 (Timeout)");
|
2017-07-14 21:35:03 +07:00
|
|
|
else if (ttrace->ret_scnprintf) {
|
|
|
|
char bf[1024];
|
2017-07-15 01:16:54 +07:00
|
|
|
struct syscall_arg arg = {
|
|
|
|
.val = ret,
|
|
|
|
.thread = thread,
|
|
|
|
.trace = trace,
|
|
|
|
};
|
|
|
|
ttrace->ret_scnprintf(bf, sizeof(bf), &arg);
|
2017-07-14 21:35:03 +07:00
|
|
|
ttrace->ret_scnprintf = NULL;
|
2018-12-17 21:48:46 +07:00
|
|
|
fprintf(trace->output, "%s", bf);
|
2017-07-14 21:35:03 +07:00
|
|
|
} else if (sc->fmt->hexret)
|
2018-12-17 21:48:46 +07:00
|
|
|
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>
2016-04-07 00:33:07 +07:00
|
|
|
else if (sc->fmt->errpid) {
|
|
|
|
struct thread *child = machine__find_thread(trace->host, ret, ret);
|
|
|
|
|
|
|
|
if (child != NULL) {
|
2018-12-17 21:48:46 +07:00
|
|
|
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>
2016-04-07 00:33:07 +07:00
|
|
|
if (child->comm_set)
|
|
|
|
fprintf(trace->output, " (%s)", thread__comm_str(child));
|
|
|
|
thread__put(child);
|
|
|
|
}
|
|
|
|
} else
|
2013-08-26 21:28:34 +07:00
|
|
|
goto signed_print;
|
2012-09-29 03:58:36 +07:00
|
|
|
|
2013-08-19 22:01:10 +07:00
|
|
|
fputc('\n', trace->output);
|
2016-04-08 18:34:15 +07:00
|
|
|
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
/*
|
|
|
|
* We only consider an 'event' for the sake of --max-events a non-filtered
|
|
|
|
* sys_enter + sys_exit and other tracepoint events.
|
|
|
|
*/
|
|
|
|
if (++trace->nr_events_printed == trace->max_events && trace->max_events != ULONG_MAX)
|
|
|
|
interrupted = true;
|
|
|
|
|
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 21:10:31 +07:00
|
|
|
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 19:56:00 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
2012-09-29 03:58:36 +07:00
|
|
|
}
|
|
|
|
|
2013-09-28 04:06:19 +07:00
|
|
|
static int trace__vfs_getname(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 23:14:24 +07:00
|
|
|
union perf_event *event __maybe_unused,
|
2013-09-28 04:06:19 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
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 23:16:27 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
|
|
|
|
if (!thread)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
ttrace = thread__priv(thread);
|
|
|
|
if (!ttrace)
|
2017-03-25 01:03:19 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
|
2015-08-14 23:16:27 +07:00
|
|
|
filename_len = strlen(filename);
|
2017-03-25 00:51:28 +07:00
|
|
|
if (filename_len == 0)
|
2017-03-25 01:03:19 +07:00
|
|
|
goto out_put;
|
2015-08-14 23:16:27 +07:00
|
|
|
|
|
|
|
if (ttrace->filename.namelen < filename_len) {
|
|
|
|
char *f = realloc(ttrace->filename.name, filename_len + 1);
|
|
|
|
|
|
|
|
if (f == NULL)
|
2017-03-25 01:03:19 +07:00
|
|
|
goto out_put;
|
2015-08-14 23:16:27 +07:00
|
|
|
|
|
|
|
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 08:30:09 +07:00
|
|
|
if (!ttrace->filename.ptr)
|
2017-03-25 01:03:19 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
|
|
|
|
entry_str_len = strlen(ttrace->entry_str);
|
|
|
|
remaining_space = trace__entry_str_size - entry_str_len - 1; /* \0 */
|
|
|
|
if (remaining_space <= 0)
|
2017-03-25 01:03:19 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
|
|
|
|
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;
|
2017-03-25 01:03:19 +07:00
|
|
|
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 08:30:09 +07:00
|
|
|
out:
|
2013-09-28 04:06:19 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2012-10-18 03:13:12 +07:00
|
|
|
static int trace__sched_stat_runtime(struct trace *trace, struct perf_evsel *evsel,
|
2014-06-26 23:14:24 +07:00
|
|
|
union perf_event *event __maybe_unused,
|
2012-10-18 03:13:12 +07:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
u64 runtime = perf_evsel__intval(evsel, sample, "runtime");
|
|
|
|
double runtime_ms = (double)runtime / NSEC_PER_MSEC;
|
2013-09-29 02:13:00 +07:00
|
|
|
struct thread *thread = machine__findnew_thread(trace->host,
|
2013-08-27 15:23:03 +07:00
|
|
|
sample->pid,
|
|
|
|
sample->tid);
|
2013-08-19 22:01:10 +07:00
|
|
|
struct thread_trace *ttrace = thread__trace(thread, trace->output);
|
2012-10-18 03:13:12 +07:00
|
|
|
|
|
|
|
if (ttrace == NULL)
|
|
|
|
goto out_dump;
|
|
|
|
|
|
|
|
ttrace->runtime_ms += runtime_ms;
|
|
|
|
trace->runtime_ms += runtime_ms;
|
2017-03-25 01:03:19 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
thread__put(thread);
|
2012-10-18 03:13:12 +07:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
out_dump:
|
2013-08-19 22:01:10 +07:00
|
|
|
fprintf(trace->output, "%s: comm=%s,pid=%u,runtime=%" PRIu64 ",vruntime=%" PRIu64 ")\n",
|
2012-10-18 03:13:12 +07:00
|
|
|
evsel->name,
|
|
|
|
perf_evsel__strval(evsel, sample, "comm"),
|
|
|
|
(pid_t)perf_evsel__intval(evsel, sample, "pid"),
|
|
|
|
runtime,
|
|
|
|
perf_evsel__intval(evsel, sample, "vruntime"));
|
2017-03-25 01:03:19 +07:00
|
|
|
goto out_put;
|
2012-10-18 03:13:12 +07:00
|
|
|
}
|
|
|
|
|
2017-10-17 20:35:00 +07:00
|
|
|
static int bpf_output__printer(enum binary_printer_ops op,
|
|
|
|
unsigned int val, void *extra __maybe_unused, FILE *fp)
|
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 16:31:55 +07:00
|
|
|
{
|
|
|
|
unsigned char ch = (unsigned char)val;
|
|
|
|
|
|
|
|
switch (op) {
|
|
|
|
case BINARY_PRINT_CHAR_DATA:
|
2017-10-17 20:35:00 +07:00
|
|
|
return fprintf(fp, "%c", isprint(ch) ? ch : '.');
|
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 16:31:55 +07:00
|
|
|
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;
|
|
|
|
}
|
2017-10-17 20:35:00 +07:00
|
|
|
|
|
|
|
return 0;
|
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 16:31:55 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static void bpf_output__fprintf(struct trace *trace,
|
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
2017-10-17 20:35:00 +07:00
|
|
|
binary__fprintf(sample->raw_data, sample->raw_size, 8,
|
|
|
|
bpf_output__printer, NULL, trace->output);
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
++trace->nr_events_printed;
|
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 16:31:55 +07:00
|
|
|
}
|
|
|
|
|
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 22:58:57 +07:00
|
|
|
static int trace__event_handler(struct trace *trace, struct perf_evsel *evsel,
|
|
|
|
union perf_event *event __maybe_unused,
|
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
perf trace: Introduce per-event maximum number of events property
Call it 'nr', as in this context it should be expressive enough, i.e.:
# perf trace -e sched:*waking/nr=8,call-graph=fp/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
try_to_wake_up ([kernel.kallsyms])
try_to_wake_up ([kernel.kallsyms])
wake_up_q ([kernel.kallsyms])
futex_wake ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
#
# perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
__dev_queue_xmit ([kernel.kallsyms])
1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
__dev_queue_xmit ([kernel.kallsyms])
3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
__dev_queue_xmit ([kernel.kallsyms])
4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
#
The global --max-events has precendence:
# trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
__dev_queue_xmit ([kernel.kallsyms])
__libc_send (/usr/lib64/libpthread-2.26.so)
#
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: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-23 00:14:16 +07:00
|
|
|
struct thread *thread;
|
2016-04-21 05:55:48 +07:00
|
|
|
int callchain_ret = 0;
|
perf trace: Introduce per-event maximum number of events property
Call it 'nr', as in this context it should be expressive enough, i.e.:
# perf trace -e sched:*waking/nr=8,call-graph=fp/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
try_to_wake_up ([kernel.kallsyms])
try_to_wake_up ([kernel.kallsyms])
wake_up_q ([kernel.kallsyms])
futex_wake ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
#
# perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
__dev_queue_xmit ([kernel.kallsyms])
1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
__dev_queue_xmit ([kernel.kallsyms])
3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
__dev_queue_xmit ([kernel.kallsyms])
4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
#
The global --max-events has precendence:
# trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
__dev_queue_xmit ([kernel.kallsyms])
__libc_send (/usr/lib64/libpthread-2.26.so)
#
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: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-23 00:14:16 +07:00
|
|
|
/*
|
|
|
|
* Check if we called perf_evsel__disable(evsel) due to, for instance,
|
|
|
|
* this event's max_events having been hit and this is an entry coming
|
|
|
|
* from the ring buffer that we should discard, since the max events
|
|
|
|
* have already been considered/printed.
|
|
|
|
*/
|
|
|
|
if (evsel->disabled)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2016-04-21 05:55:48 +07:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
perf trace: Do not print from time delta for interrupted syscall lines
We were calculating the delta from a in-flight syscall that got its
output interrupted by another syscall, which doesn't seem like useful
information, we will print the syscall duration (sys_exit - sys_enter)
when the raw_syscalls:sys_exit event happens.
The problem here is how we're consuming the multiple ring buffers,
without using the ordered_events code used by perf_session, which may
cause some reordering of syscalls for diferent CPUs, so just stop
printing that delta, to avoid things like:
# trace --print-sample -p 9626 -e futex
raw_syscalls:sys_enter 411967179.269 Timer 9609/9626 [2]
raw_syscalls:sys_enter 411967179.213 file:// Content 9609/9609 [3]
328.038 (18446744073709.496 ms): Timer/9626 futex(uaddr: 0x7fc0d4027044, op: WAIT|PRIV, utime: 0x7fc0b0ffdb50 ) ...
raw_syscalls:sys_exit 411967179.225 file:// Content 9609/9609 [3]
327.982 ( 0.012 ms): file:// Conten/9609 futex(uaddr: 0x7fc0d4027040, op: WAKE|PRIV, val: 1 ) = 1
This is a bandaid, we should better try and use the ordered_events code,
possibly with some refactoring prep work, but for now at least we don't
show those false long deltas for the lines ending in '...'.
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: https://lkml.kernel.org/n/tip-q6xgsqrju1sr6ltud9kjjhmb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-22 21:42:11 +07:00
|
|
|
trace__printf_interrupted_entry(trace);
|
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 22:58:57 +07:00
|
|
|
trace__fprintf_tstamp(trace, sample->time, trace->output);
|
2015-02-20 12:51:50 +07:00
|
|
|
|
2018-12-14 20:22:18 +07:00
|
|
|
if (trace->trace_syscalls && trace->show_duration)
|
2015-02-20 12:51:50 +07:00
|
|
|
fprintf(trace->output, "( ): ");
|
|
|
|
|
perf trace: Show comm and tid for tracepoint events
So that all events have that info, improving reading by having
information better aligned, etc.
Before:
# echo 1 > /proc/sys/vm/drop_caches
# perf trace -e block:*,ext4:*,tools/perf/examples/bpf/augmented_syscalls.c,close cat tools/perf/examples/bpf/hello.c
0.000 ( ): #include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
cat/2731 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
0.025 ( ): syscalls:sys_exit_openat:0x3
0.063 ( 0.022 ms): cat/2731 close(fd: 3) = 0
0.110 ( ): cat/2731 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.123 ( ): syscalls:sys_exit_openat:0x3
0.243 ( 0.008 ms): cat/2731 close(fd: 3) = 0
0.485 ( ): cat/2731 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
0.500 ( ): syscalls:sys_exit_open:0x3
0.531 ( 0.017 ms): cat/2731 close(fd: 3) = 0
0.587 ( ): cat/2731 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c)
0.601 ( ): syscalls:sys_exit_openat:0x3
0.631 ( ): ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 1311399 lblk 0
0.639 ( ): ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 1311399 found 1 [0/1) 5276651 W0x10
0.654 ( ): block:block_bio_queue:253,2 R 42213208 + 8 [cat]
0.663 ( ): block:block_bio_remap:8,0 R 58206040 + 8 <- (253,2) 42213208
0.671 ( ): block:block_bio_remap:8,0 R 175570776 + 8 <- (8,6) 58206040
0.678 ( ): block:block_bio_queue:8,0 R 175570776 + 8 [cat]
0.692 ( ): block:block_getrq:8,0 R 175570776 + 8 [cat]
0.700 ( ): block:block_plug:[cat]
0.708 ( ): block:block_rq_insert:8,0 R 4096 () 175570776 + 8 [cat]
0.713 ( ): block:block_unplug:[cat] 1
0.716 ( ): block:block_rq_issue:8,0 R 4096 () 175570776 + 8 [cat]
0.949 ( 0.007 ms): cat/2731 close(fd: 3) = 0
0.969 ( 0.006 ms): cat/2731 close(fd: 1) = 0
0.982 ( 0.006 ms): cat/2731 close(fd: 2) = 0
#
After:
# echo 1 > /proc/sys/vm/drop_caches
# perf trace -e block:*,ext4:*,tools/perf/examples/bpf/augmented_syscalls.c,close cat tools/perf/examples/bpf/hello.c
0.000 ( ): cat/1380 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)#include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
0.024 ( ): cat/1380 syscalls:sys_exit_openat:0x3
0.063 ( 0.024 ms): cat/1380 close(fd: 3) = 0
0.114 ( ): cat/1380 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.127 ( ): cat/1380 syscalls:sys_exit_openat:0x3
0.247 ( 0.009 ms): cat/1380 close(fd: 3) = 0
0.484 ( ): cat/1380 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
0.499 ( ): cat/1380 syscalls:sys_exit_open:0x3
0.613 ( 0.010 ms): cat/1380 close(fd: 3) = 0
0.662 ( ): cat/1380 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c)
0.678 ( ): cat/1380 syscalls:sys_exit_openat:0x3
0.712 ( ): cat/1380 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 1311399 lblk 0
0.721 ( ): cat/1380 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 1311399 found 1 [0/1) 5276651 W0x10
0.734 ( ): cat/1380 block:block_bio_queue:253,2 R 42213208 + 8 [cat]
0.745 ( ): cat/1380 block:block_bio_remap:8,0 R 58206040 + 8 <- (253,2) 42213208
0.754 ( ): cat/1380 block:block_bio_remap:8,0 R 175570776 + 8 <- (8,6) 58206040
0.761 ( ): cat/1380 block:block_bio_queue:8,0 R 175570776 + 8 [cat]
0.780 ( ): cat/1380 block:block_getrq:8,0 R 175570776 + 8 [cat]
0.791 ( ): cat/1380 block:block_plug:[cat]
0.802 ( ): cat/1380 block:block_rq_insert:8,0 R 4096 () 175570776 + 8 [cat]
0.806 ( ): cat/1380 block:block_unplug:[cat] 1
0.810 ( ): cat/1380 block:block_rq_issue:8,0 R 4096 () 175570776 + 8 [cat]
1.005 ( 0.011 ms): cat/1380 close(fd: 3) = 0
1.031 ( 0.008 ms): cat/1380 close(fd: 1) = 0
1.048 ( 0.008 ms): cat/1380 close(fd: 2) = 0
#
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: https://lkml.kernel.org/n/tip-us1mwsupxffs4jlm3uqm5dvj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-30 23:37:28 +07:00
|
|
|
if (thread)
|
|
|
|
trace__fprintf_comm_tid(trace, thread, trace->output);
|
|
|
|
|
perf trace: Print the syscall name for augmented_syscalls
Since we copy all the payload for raw_syscalls:sys_enter plus add
expanded pointers, we can use the syscall id to get its name, etc:
# grep 'field:.* id' /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
field:long id; offset:8; size:8; signed:1;
#
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC
0.006 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC) = 3
0.041 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC
0.042 ( 0.007 ms): cat/2395 openat(dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC) = 3
0.376 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xac0a806b
0.379 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xac0a806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC)
0.009 ( 0.009 ms): cat/3619 openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC) = 3
0.051 ( ): openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC)
0.054 ( 0.010 ms): cat/3619 openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC) = 3
0.539 ( ): openat(dfd: CWD, filename: 0xca71506b)
0.543 ( 0.115 ms): cat/3619 openat(dfd: CWD, filename: 0xca71506b) = 3
#
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: https://lkml.kernel.org/n/tip-epz6y9i0eavmerc5ha98t7gn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 21:44:23 +07:00
|
|
|
if (evsel == trace->syscalls.events.augmented) {
|
|
|
|
int id = perf_evsel__sc_tp_uint(evsel, id, sample);
|
|
|
|
struct syscall *sc = trace__syscall_info(trace, evsel, id);
|
|
|
|
|
|
|
|
if (sc) {
|
perf trace: Show comm and tid for tracepoint events
So that all events have that info, improving reading by having
information better aligned, etc.
Before:
# echo 1 > /proc/sys/vm/drop_caches
# perf trace -e block:*,ext4:*,tools/perf/examples/bpf/augmented_syscalls.c,close cat tools/perf/examples/bpf/hello.c
0.000 ( ): #include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
cat/2731 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)
0.025 ( ): syscalls:sys_exit_openat:0x3
0.063 ( 0.022 ms): cat/2731 close(fd: 3) = 0
0.110 ( ): cat/2731 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.123 ( ): syscalls:sys_exit_openat:0x3
0.243 ( 0.008 ms): cat/2731 close(fd: 3) = 0
0.485 ( ): cat/2731 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
0.500 ( ): syscalls:sys_exit_open:0x3
0.531 ( 0.017 ms): cat/2731 close(fd: 3) = 0
0.587 ( ): cat/2731 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c)
0.601 ( ): syscalls:sys_exit_openat:0x3
0.631 ( ): ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 1311399 lblk 0
0.639 ( ): ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 1311399 found 1 [0/1) 5276651 W0x10
0.654 ( ): block:block_bio_queue:253,2 R 42213208 + 8 [cat]
0.663 ( ): block:block_bio_remap:8,0 R 58206040 + 8 <- (253,2) 42213208
0.671 ( ): block:block_bio_remap:8,0 R 175570776 + 8 <- (8,6) 58206040
0.678 ( ): block:block_bio_queue:8,0 R 175570776 + 8 [cat]
0.692 ( ): block:block_getrq:8,0 R 175570776 + 8 [cat]
0.700 ( ): block:block_plug:[cat]
0.708 ( ): block:block_rq_insert:8,0 R 4096 () 175570776 + 8 [cat]
0.713 ( ): block:block_unplug:[cat] 1
0.716 ( ): block:block_rq_issue:8,0 R 4096 () 175570776 + 8 [cat]
0.949 ( 0.007 ms): cat/2731 close(fd: 3) = 0
0.969 ( 0.006 ms): cat/2731 close(fd: 1) = 0
0.982 ( 0.006 ms): cat/2731 close(fd: 2) = 0
#
After:
# echo 1 > /proc/sys/vm/drop_caches
# perf trace -e block:*,ext4:*,tools/perf/examples/bpf/augmented_syscalls.c,close cat tools/perf/examples/bpf/hello.c
0.000 ( ): cat/1380 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC)#include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
0.024 ( ): cat/1380 syscalls:sys_exit_openat:0x3
0.063 ( 0.024 ms): cat/1380 close(fd: 3) = 0
0.114 ( ): cat/1380 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC)
0.127 ( ): cat/1380 syscalls:sys_exit_openat:0x3
0.247 ( 0.009 ms): cat/1380 close(fd: 3) = 0
0.484 ( ): cat/1380 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC)
0.499 ( ): cat/1380 syscalls:sys_exit_open:0x3
0.613 ( 0.010 ms): cat/1380 close(fd: 3) = 0
0.662 ( ): cat/1380 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c)
0.678 ( ): cat/1380 syscalls:sys_exit_openat:0x3
0.712 ( ): cat/1380 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 1311399 lblk 0
0.721 ( ): cat/1380 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 1311399 found 1 [0/1) 5276651 W0x10
0.734 ( ): cat/1380 block:block_bio_queue:253,2 R 42213208 + 8 [cat]
0.745 ( ): cat/1380 block:block_bio_remap:8,0 R 58206040 + 8 <- (253,2) 42213208
0.754 ( ): cat/1380 block:block_bio_remap:8,0 R 175570776 + 8 <- (8,6) 58206040
0.761 ( ): cat/1380 block:block_bio_queue:8,0 R 175570776 + 8 [cat]
0.780 ( ): cat/1380 block:block_getrq:8,0 R 175570776 + 8 [cat]
0.791 ( ): cat/1380 block:block_plug:[cat]
0.802 ( ): cat/1380 block:block_rq_insert:8,0 R 4096 () 175570776 + 8 [cat]
0.806 ( ): cat/1380 block:block_unplug:[cat] 1
0.810 ( ): cat/1380 block:block_rq_issue:8,0 R 4096 () 175570776 + 8 [cat]
1.005 ( 0.011 ms): cat/1380 close(fd: 3) = 0
1.031 ( 0.008 ms): cat/1380 close(fd: 1) = 0
1.048 ( 0.008 ms): cat/1380 close(fd: 2) = 0
#
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: https://lkml.kernel.org/n/tip-us1mwsupxffs4jlm3uqm5dvj@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-30 23:37:28 +07:00
|
|
|
fprintf(trace->output, "%s(", sc->name);
|
|
|
|
trace__fprintf_sys_enter(trace, evsel, sample);
|
|
|
|
fputc(')', trace->output);
|
|
|
|
goto newline;
|
perf trace: Print the syscall name for augmented_syscalls
Since we copy all the payload for raw_syscalls:sys_enter plus add
expanded pointers, we can use the syscall id to get its name, etc:
# grep 'field:.* id' /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
field:long id; offset:8; size:8; signed:1;
#
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC
0.006 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC) = 3
0.041 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC
0.042 ( 0.007 ms): cat/2395 openat(dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC) = 3
0.376 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xac0a806b
0.379 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xac0a806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC)
0.009 ( 0.009 ms): cat/3619 openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC) = 3
0.051 ( ): openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC)
0.054 ( 0.010 ms): cat/3619 openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC) = 3
0.539 ( ): openat(dfd: CWD, filename: 0xca71506b)
0.543 ( 0.115 ms): cat/3619 openat(dfd: CWD, filename: 0xca71506b) = 3
#
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: https://lkml.kernel.org/n/tip-epz6y9i0eavmerc5ha98t7gn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 21:44:23 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* XXX: Not having the associated syscall info or not finding/adding
|
|
|
|
* the thread should never happen, but if it does...
|
|
|
|
* fall thru and print it as a bpf_output event.
|
|
|
|
*/
|
|
|
|
}
|
|
|
|
|
2015-02-20 12:51:50 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
|
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 16:31:55 +07:00
|
|
|
if (perf_evsel__is_bpf_output(evsel)) {
|
perf trace: Print the syscall name for augmented_syscalls
Since we copy all the payload for raw_syscalls:sys_enter plus add
expanded pointers, we can use the syscall id to get its name, etc:
# grep 'field:.* id' /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
field:long id; offset:8; size:8; signed:1;
#
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC
0.006 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC) = 3
0.041 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC
0.042 ( 0.007 ms): cat/2395 openat(dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC) = 3
0.376 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xac0a806b
0.379 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xac0a806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC)
0.009 ( 0.009 ms): cat/3619 openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC) = 3
0.051 ( ): openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC)
0.054 ( 0.010 ms): cat/3619 openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC) = 3
0.539 ( ): openat(dfd: CWD, filename: 0xca71506b)
0.543 ( 0.115 ms): cat/3619 openat(dfd: CWD, filename: 0xca71506b) = 3
#
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: https://lkml.kernel.org/n/tip-epz6y9i0eavmerc5ha98t7gn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 21:44:23 +07:00
|
|
|
bpf_output__fprintf(trace, sample);
|
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 16:31:55 +07:00
|
|
|
} else if (evsel->tp_format) {
|
perf trace: Use beautifiers on syscalls:sys_enter_ handlers
We were using the beautifiers only when processing the
raw_syscalls:sys_enter events, but we can as well use them for the
syscalls:sys_enter_NAME events, as the layout is the same.
Some more tweaking is needed as we're processing them straight away,
i.e. there is no buffering in the sys_enter_NAME event to wait for
things like vfs_getname to provide pointer contents and then flushing
at sys_exit_NAME, so we need to state in the syscall_arg that this
is unbuffered, just print the pointer values, beautifying just
non-pointer syscall args.
This just shows an alternative way of processing tracepoints, that we
will end up using when creating "tracepoint" payloads that already copy
pointer contents (or chunks of it, i.e. not the whole filename, but just
the end of it, not all the bf for a read/write, but just the start,
etc), directly in the kernel using eBPF.
E.g.:
# perf trace -e syscalls:*enter*sleep,*sleep sleep 1
0.303 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffc93d5ecc0
0.305 (1000.229 ms): sleep/8746 nanosleep(rqtp: 0x7ffc93d5ecc0) = 0
# perf trace -e syscalls:*_*sleep,*sleep sleep 1
0.288 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffecde87e40
0.289 ( ): sleep/8748 nanosleep(rqtp: 0x7ffecde87e40) ...
1000.479 ( ): syscalls:sys_exit_nanosleep:0x0
0.289 (1000.208 ms): sleep/8748 ... [continued]: nanosleep()) = 0
#
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jehyd2zwhw00z3p7v7mg9632@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-03 00:05:09 +07:00
|
|
|
if (strncmp(evsel->tp_format->name, "sys_enter_", 10) ||
|
|
|
|
trace__fprintf_sys_enter(trace, evsel, sample)) {
|
|
|
|
event_format__fprintf(evsel->tp_format, sample->cpu,
|
|
|
|
sample->raw_data, sample->raw_size,
|
|
|
|
trace->output);
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
++trace->nr_events_printed;
|
perf trace: Introduce per-event maximum number of events property
Call it 'nr', as in this context it should be expressive enough, i.e.:
# perf trace -e sched:*waking/nr=8,call-graph=fp/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
try_to_wake_up ([kernel.kallsyms])
try_to_wake_up ([kernel.kallsyms])
wake_up_q ([kernel.kallsyms])
futex_wake ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
#
# perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
__dev_queue_xmit ([kernel.kallsyms])
1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
__dev_queue_xmit ([kernel.kallsyms])
3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
__dev_queue_xmit ([kernel.kallsyms])
4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
#
The global --max-events has precendence:
# trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
__dev_queue_xmit ([kernel.kallsyms])
__libc_send (/usr/lib64/libpthread-2.26.so)
#
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: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-23 00:14:16 +07:00
|
|
|
|
|
|
|
if (evsel->max_events != ULONG_MAX && ++evsel->nr_events_printed == evsel->max_events) {
|
|
|
|
perf_evsel__disable(evsel);
|
|
|
|
perf_evsel__close(evsel);
|
|
|
|
}
|
perf trace: Use beautifiers on syscalls:sys_enter_ handlers
We were using the beautifiers only when processing the
raw_syscalls:sys_enter events, but we can as well use them for the
syscalls:sys_enter_NAME events, as the layout is the same.
Some more tweaking is needed as we're processing them straight away,
i.e. there is no buffering in the sys_enter_NAME event to wait for
things like vfs_getname to provide pointer contents and then flushing
at sys_exit_NAME, so we need to state in the syscall_arg that this
is unbuffered, just print the pointer values, beautifying just
non-pointer syscall args.
This just shows an alternative way of processing tracepoints, that we
will end up using when creating "tracepoint" payloads that already copy
pointer contents (or chunks of it, i.e. not the whole filename, but just
the end of it, not all the bf for a read/write, but just the start,
etc), directly in the kernel using eBPF.
E.g.:
# perf trace -e syscalls:*enter*sleep,*sleep sleep 1
0.303 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffc93d5ecc0
0.305 (1000.229 ms): sleep/8746 nanosleep(rqtp: 0x7ffc93d5ecc0) = 0
# perf trace -e syscalls:*_*sleep,*sleep sleep 1
0.288 ( ): syscalls:sys_enter_nanosleep:rqtp: 0x7ffecde87e40
0.289 ( ): sleep/8748 nanosleep(rqtp: 0x7ffecde87e40) ...
1000.479 ( ): syscalls:sys_exit_nanosleep:0x0
0.289 (1000.208 ms): sleep/8748 ... [continued]: nanosleep()) = 0
#
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: Steven Rostedt <rostedt@goodmis.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-jehyd2zwhw00z3p7v7mg9632@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-03 00:05:09 +07:00
|
|
|
}
|
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 22:58:57 +07:00
|
|
|
}
|
|
|
|
|
perf trace: Print the syscall name for augmented_syscalls
Since we copy all the payload for raw_syscalls:sys_enter plus add
expanded pointers, we can use the syscall id to get its name, etc:
# grep 'field:.* id' /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
field:long id; offset:8; size:8; signed:1;
#
Before:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC
0.006 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xec9f9da8, flags: CLOEXEC) = 3
0.041 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC
0.042 ( 0.007 ms): cat/2395 openat(dfd: CWD, filename: 0xecc01ce0, flags: CLOEXEC) = 3
0.376 ( ): __augmented_syscalls__:dfd: CWD, filename: 0xac0a806b
0.379 ( 0.006 ms): cat/2395 openat(dfd: CWD, filename: 0xac0a806b) = 3
#
After:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC)
0.009 ( 0.009 ms): cat/3619 openat(dfd: CWD, filename: 0x31b6dda8, flags: CLOEXEC) = 3
0.051 ( ): openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC)
0.054 ( 0.010 ms): cat/3619 openat(dfd: CWD, filename: 0x31d75ce0, flags: CLOEXEC) = 3
0.539 ( ): openat(dfd: CWD, filename: 0xca71506b)
0.543 ( 0.115 ms): cat/3619 openat(dfd: CWD, filename: 0xca71506b) = 3
#
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: https://lkml.kernel.org/n/tip-epz6y9i0eavmerc5ha98t7gn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-21 21:44:23 +07:00
|
|
|
newline:
|
2018-03-13 17:40:01 +07:00
|
|
|
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 20:11:07 +07:00
|
|
|
|
2016-04-21 05:55:48 +07:00
|
|
|
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:
|
2018-10-20 19:27:52 +07:00
|
|
|
thread__put(thread);
|
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 22:58:57 +07:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2014-06-26 23:14:25 +07:00
|
|
|
static void print_location(FILE *f, struct perf_sample *sample,
|
|
|
|
struct addr_location *al,
|
|
|
|
bool print_dso, bool print_sym)
|
|
|
|
{
|
|
|
|
|
2017-02-17 15:17:38 +07:00
|
|
|
if ((verbose > 0 || print_dso) && al->map)
|
2014-06-26 23:14:25 +07:00
|
|
|
fprintf(f, "%s@", al->map->dso->long_name);
|
|
|
|
|
2017-02-17 15:17:38 +07:00
|
|
|
if ((verbose > 0 || print_sym) && al->sym)
|
2014-07-09 01:39:21 +07:00
|
|
|
fprintf(f, "%s+0x%" PRIx64, al->sym->name,
|
2014-06-26 23:14:25 +07:00
|
|
|
al->addr - al->sym->start);
|
|
|
|
else if (al->map)
|
2014-07-09 01:39:21 +07:00
|
|
|
fprintf(f, "0x%" PRIx64, al->addr);
|
2014-06-26 23:14:25 +07:00
|
|
|
else
|
2014-07-09 01:39:21 +07:00
|
|
|
fprintf(f, "0x%" PRIx64, sample->addr);
|
2014-06-26 23:14:25 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static int trace__pgfault(struct trace *trace,
|
|
|
|
struct perf_evsel *evsel,
|
2016-03-23 04:23:43 +07:00
|
|
|
union perf_event *event __maybe_unused,
|
2014-06-26 23:14:25 +07:00
|
|
|
struct perf_sample *sample)
|
|
|
|
{
|
|
|
|
struct thread *thread;
|
|
|
|
struct addr_location al;
|
|
|
|
char map_type = 'd';
|
2014-07-09 01:05:16 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
int err = -1;
|
2016-04-21 06:06:02 +07:00
|
|
|
int callchain_ret = 0;
|
2014-06-26 23:14:25 +07:00
|
|
|
|
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
2016-04-21 06:06:02 +07:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-07-09 01:05:16 +07:00
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
goto out_put;
|
2014-07-09 01:05:16 +07:00
|
|
|
|
|
|
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
goto out;
|
2014-06-26 23:14:25 +07:00
|
|
|
|
2018-04-24 21:24:49 +07:00
|
|
|
thread__find_symbol(thread, sample->cpumode, sample->ip, &al);
|
2014-06-26 23:14:25 +07:00
|
|
|
|
2017-03-30 02:37:51 +07:00
|
|
|
trace__fprintf_entry_head(trace, thread, 0, true, sample->time, trace->output);
|
2014-06-26 23:14:25 +07:00
|
|
|
|
|
|
|
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, "] => ");
|
|
|
|
|
2018-04-26 04:16:53 +07:00
|
|
|
thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
|
2014-06-26 23:14:25 +07:00
|
|
|
|
|
|
|
if (!al.map) {
|
2018-04-24 21:24:49 +07:00
|
|
|
thread__find_symbol(thread, sample->cpumode, sample->addr, &al);
|
2014-06-26 23:14:25 +07:00
|
|
|
|
|
|
|
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);
|
2016-04-20 02:31:12 +07:00
|
|
|
|
2016-04-21 06:06:02 +07:00
|
|
|
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: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
|
|
|
|
++trace->nr_events_printed;
|
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>
2015-04-07 06:43:22 +07:00
|
|
|
out:
|
|
|
|
err = 0;
|
|
|
|
out_put:
|
|
|
|
thread__put(thread);
|
|
|
|
return err;
|
2014-06-26 23:14:25 +07:00
|
|
|
}
|
|
|
|
|
2016-04-01 01:16:28 +07:00
|
|
|
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>
2016-04-01 01:19:39 +07:00
|
|
|
struct perf_evsel *evsel,
|
2016-04-01 01:16:28 +07:00
|
|
|
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>
2016-04-01 01:19:39 +07:00
|
|
|
/*
|
|
|
|
* 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))
|
2016-04-01 01:16:28 +07:00
|
|
|
trace->base_time = sample->time;
|
|
|
|
}
|
|
|
|
|
2013-08-29 11:29:52 +07:00
|
|
|
static int trace__process_sample(struct perf_tool *tool,
|
2014-06-26 23:14:24 +07:00
|
|
|
union perf_event *event,
|
2013-08-29 11:29:52 +07:00
|
|
|
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 23:29:52 +07:00
|
|
|
struct thread *thread;
|
2013-08-29 11:29:52 +07:00
|
|
|
int err = 0;
|
|
|
|
|
2013-11-06 20:17:38 +07:00
|
|
|
tracepoint_handler handler = evsel->handler;
|
2013-08-29 11:29:52 +07:00
|
|
|
|
2016-11-25 23:29:52 +07:00
|
|
|
thread = machine__findnew_thread(trace->host, sample->pid, sample->tid);
|
|
|
|
if (thread && thread__is_filtered(thread))
|
2017-03-25 01:03:19 +07:00
|
|
|
goto out;
|
2013-08-29 11:29:53 +07:00
|
|
|
|
2016-04-01 01:16:28 +07:00
|
|
|
trace__set_base_time(trace, evsel, sample);
|
2013-08-29 11:29:52 +07:00
|
|
|
|
2013-12-05 09:41:41 +07:00
|
|
|
if (handler) {
|
|
|
|
++trace->nr_events;
|
2014-06-26 23:14:24 +07:00
|
|
|
handler(trace, evsel, event, sample);
|
2013-12-05 09:41:41 +07:00
|
|
|
}
|
2017-03-25 01:03:19 +07:00
|
|
|
out:
|
|
|
|
thread__put(thread);
|
2013-08-29 11:29:52 +07:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2014-06-26 23:14:26 +07:00
|
|
|
static int trace__record(struct trace *trace, int argc, const char **argv)
|
2013-09-29 02:13:01 +07:00
|
|
|
{
|
|
|
|
unsigned int rec_argc, i, j;
|
|
|
|
const char **rec_argv;
|
|
|
|
const char * const record_args[] = {
|
|
|
|
"record",
|
|
|
|
"-R",
|
|
|
|
"-m", "1024",
|
|
|
|
"-c", "1",
|
|
|
|
};
|
|
|
|
|
2014-06-26 23:14:26 +07:00
|
|
|
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 09:41:39 +07:00
|
|
|
/* +1 is for the event string below */
|
2014-06-26 23:14:26 +07:00
|
|
|
rec_argc = ARRAY_SIZE(record_args) + sc_args_nr + 1 +
|
|
|
|
majpf_args_nr + minpf_args_nr + argc;
|
2013-09-29 02:13:01 +07:00
|
|
|
rec_argv = calloc(rec_argc + 1, sizeof(char *));
|
|
|
|
|
|
|
|
if (rec_argv == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
2014-06-26 23:14:26 +07:00
|
|
|
j = 0;
|
2013-09-29 02:13:01 +07:00
|
|
|
for (i = 0; i < ARRAY_SIZE(record_args); i++)
|
2014-06-26 23:14:26 +07:00
|
|
|
rec_argv[j++] = record_args[i];
|
|
|
|
|
2014-06-26 23:14:28 +07:00
|
|
|
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");
|
2017-09-14 02:14:19 +07:00
|
|
|
free(rec_argv);
|
2014-06-26 23:14:28 +07:00
|
|
|
return -1;
|
|
|
|
}
|
2013-12-05 09:41:39 +07:00
|
|
|
}
|
|
|
|
|
2014-06-26 23:14:26 +07:00
|
|
|
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];
|
2013-09-29 02:13:01 +07:00
|
|
|
|
2017-03-27 21:47:20 +07:00
|
|
|
return cmd_record(j, rec_argv);
|
2013-09-29 02:13:01 +07:00
|
|
|
}
|
|
|
|
|
2013-10-09 10:26:53 +07:00
|
|
|
static size_t trace__fprintf_thread_summary(struct trace *trace, FILE *fp);
|
|
|
|
|
2015-08-05 03:01:04 +07:00
|
|
|
static bool perf_evlist__add_vfs_getname(struct perf_evlist *evlist)
|
2013-09-28 04:06:19 +07:00
|
|
|
{
|
perf trace: Support multiple "vfs_getname" probes
With a suitably defined "probe:vfs_getname" probe, 'perf trace' can
"beautify" its output, so syscalls like open() or openat() can print the
"filename" argument instead of just its hex address, like:
$ perf trace -e open -- touch /dev/null
[...]
0.590 ( 0.014 ms): touch/18063 open(filename: /dev/null, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
[...]
The output without such beautifier looks like:
0.529 ( 0.011 ms): touch/18075 open(filename: 0xc78cf288, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
However, when the vfs_getname probe expands to multiple probes and it is
not the first one that is hit, the beautifier fails, as following:
0.326 ( 0.010 ms): touch/18072 open(filename: , flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
Fix it by hooking into all the expanded probes (inlines), now, for instance:
[root@quaco ~]# perf probe -l
probe:vfs_getname (on getname_flags:73@fs/namei.c with pathname)
probe:vfs_getname_1 (on getname_flags:73@fs/namei.c with pathname)
[root@quaco ~]# perf trace -e open* sleep 1
0.010 ( 0.005 ms): sleep/5588 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: RDONLY|CLOEXEC) = 3
0.029 ( 0.006 ms): sleep/5588 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: RDONLY|CLOEXEC) = 3
0.194 ( 0.008 ms): sleep/5588 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: RDONLY|CLOEXEC) = 3
[root@quaco ~]#
Works, further verified with:
[root@quaco ~]# perf test vfs
65: Use vfs_getname probe to get syscall args filenames : Ok
66: Add vfs_getname probe to get syscall args filenames : Ok
67: Check open filename arg using perf trace + vfs_getname: Ok
[root@quaco ~]#
Reported-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-mv8kolk17xla1smvmp3qabv1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-29 21:12:34 +07:00
|
|
|
bool found = false;
|
|
|
|
struct perf_evsel *evsel, *tmp;
|
|
|
|
struct parse_events_error err = { .idx = 0, };
|
|
|
|
int ret = parse_events(evlist, "probe:vfs_getname*", &err);
|
2015-09-07 15:38:06 +07:00
|
|
|
|
perf trace: Support multiple "vfs_getname" probes
With a suitably defined "probe:vfs_getname" probe, 'perf trace' can
"beautify" its output, so syscalls like open() or openat() can print the
"filename" argument instead of just its hex address, like:
$ perf trace -e open -- touch /dev/null
[...]
0.590 ( 0.014 ms): touch/18063 open(filename: /dev/null, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
[...]
The output without such beautifier looks like:
0.529 ( 0.011 ms): touch/18075 open(filename: 0xc78cf288, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
However, when the vfs_getname probe expands to multiple probes and it is
not the first one that is hit, the beautifier fails, as following:
0.326 ( 0.010 ms): touch/18072 open(filename: , flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
Fix it by hooking into all the expanded probes (inlines), now, for instance:
[root@quaco ~]# perf probe -l
probe:vfs_getname (on getname_flags:73@fs/namei.c with pathname)
probe:vfs_getname_1 (on getname_flags:73@fs/namei.c with pathname)
[root@quaco ~]# perf trace -e open* sleep 1
0.010 ( 0.005 ms): sleep/5588 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: RDONLY|CLOEXEC) = 3
0.029 ( 0.006 ms): sleep/5588 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: RDONLY|CLOEXEC) = 3
0.194 ( 0.008 ms): sleep/5588 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: RDONLY|CLOEXEC) = 3
[root@quaco ~]#
Works, further verified with:
[root@quaco ~]# perf test vfs
65: Use vfs_getname probe to get syscall args filenames : Ok
66: Add vfs_getname probe to get syscall args filenames : Ok
67: Check open filename arg using perf trace + vfs_getname: Ok
[root@quaco ~]#
Reported-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-mv8kolk17xla1smvmp3qabv1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-29 21:12:34 +07:00
|
|
|
if (ret)
|
2015-08-05 03:01:04 +07:00
|
|
|
return false;
|
2013-09-28 04:06:19 +07:00
|
|
|
|
perf trace: Support multiple "vfs_getname" probes
With a suitably defined "probe:vfs_getname" probe, 'perf trace' can
"beautify" its output, so syscalls like open() or openat() can print the
"filename" argument instead of just its hex address, like:
$ perf trace -e open -- touch /dev/null
[...]
0.590 ( 0.014 ms): touch/18063 open(filename: /dev/null, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
[...]
The output without such beautifier looks like:
0.529 ( 0.011 ms): touch/18075 open(filename: 0xc78cf288, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
However, when the vfs_getname probe expands to multiple probes and it is
not the first one that is hit, the beautifier fails, as following:
0.326 ( 0.010 ms): touch/18072 open(filename: , flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
Fix it by hooking into all the expanded probes (inlines), now, for instance:
[root@quaco ~]# perf probe -l
probe:vfs_getname (on getname_flags:73@fs/namei.c with pathname)
probe:vfs_getname_1 (on getname_flags:73@fs/namei.c with pathname)
[root@quaco ~]# perf trace -e open* sleep 1
0.010 ( 0.005 ms): sleep/5588 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: RDONLY|CLOEXEC) = 3
0.029 ( 0.006 ms): sleep/5588 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: RDONLY|CLOEXEC) = 3
0.194 ( 0.008 ms): sleep/5588 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: RDONLY|CLOEXEC) = 3
[root@quaco ~]#
Works, further verified with:
[root@quaco ~]# perf test vfs
65: Use vfs_getname probe to get syscall args filenames : Ok
66: Add vfs_getname probe to get syscall args filenames : Ok
67: Check open filename arg using perf trace + vfs_getname: Ok
[root@quaco ~]#
Reported-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-mv8kolk17xla1smvmp3qabv1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-29 21:12:34 +07:00
|
|
|
evlist__for_each_entry_safe(evlist, evsel, tmp) {
|
|
|
|
if (!strstarts(perf_evsel__name(evsel), "probe:vfs_getname"))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (perf_evsel__field(evsel, "pathname")) {
|
|
|
|
evsel->handler = trace__vfs_getname;
|
|
|
|
found = true;
|
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
|
|
|
list_del_init(&evsel->node);
|
|
|
|
evsel->evlist = NULL;
|
2013-09-28 04:06:19 +07:00
|
|
|
perf_evsel__delete(evsel);
|
|
|
|
}
|
|
|
|
|
perf trace: Support multiple "vfs_getname" probes
With a suitably defined "probe:vfs_getname" probe, 'perf trace' can
"beautify" its output, so syscalls like open() or openat() can print the
"filename" argument instead of just its hex address, like:
$ perf trace -e open -- touch /dev/null
[...]
0.590 ( 0.014 ms): touch/18063 open(filename: /dev/null, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
[...]
The output without such beautifier looks like:
0.529 ( 0.011 ms): touch/18075 open(filename: 0xc78cf288, flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
However, when the vfs_getname probe expands to multiple probes and it is
not the first one that is hit, the beautifier fails, as following:
0.326 ( 0.010 ms): touch/18072 open(filename: , flags: CREAT|NOCTTY|NONBLOCK|WRONLY, mode: IRUGO|IWUGO) = 3
Fix it by hooking into all the expanded probes (inlines), now, for instance:
[root@quaco ~]# perf probe -l
probe:vfs_getname (on getname_flags:73@fs/namei.c with pathname)
probe:vfs_getname_1 (on getname_flags:73@fs/namei.c with pathname)
[root@quaco ~]# perf trace -e open* sleep 1
0.010 ( 0.005 ms): sleep/5588 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: RDONLY|CLOEXEC) = 3
0.029 ( 0.006 ms): sleep/5588 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: RDONLY|CLOEXEC) = 3
0.194 ( 0.008 ms): sleep/5588 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: RDONLY|CLOEXEC) = 3
[root@quaco ~]#
Works, further verified with:
[root@quaco ~]# perf test vfs
65: Use vfs_getname probe to get syscall args filenames : Ok
66: Add vfs_getname probe to get syscall args filenames : Ok
67: Check open filename arg using perf trace + vfs_getname: Ok
[root@quaco ~]#
Reported-by: Michael Petlan <mpetlan@redhat.com>
Tested-by: Michael Petlan <mpetlan@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-mv8kolk17xla1smvmp3qabv1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-29 21:12:34 +07:00
|
|
|
return found;
|
2013-09-28 04:06:19 +07:00
|
|
|
}
|
|
|
|
|
2016-04-20 02:00:01 +07:00
|
|
|
static struct perf_evsel *perf_evsel__new_pgfault(u64 config)
|
2014-06-26 23:14:25 +07:00
|
|
|
{
|
|
|
|
struct perf_evsel *evsel;
|
|
|
|
struct perf_event_attr attr = {
|
|
|
|
.type = PERF_TYPE_SOFTWARE,
|
|
|
|
.mmap_data = 1,
|
|
|
|
};
|
|
|
|
|
|
|
|
attr.config = config;
|
2014-07-24 04:15:09 +07:00
|
|
|
attr.sample_period = 1;
|
2014-06-26 23:14:25 +07:00
|
|
|
|
|
|
|
event_attr_init(&attr);
|
|
|
|
|
|
|
|
evsel = perf_evsel__new(&attr);
|
2016-04-20 02:00:01 +07:00
|
|
|
if (evsel)
|
|
|
|
evsel->handler = trace__pgfault;
|
2014-06-26 23:14:25 +07:00
|
|
|
|
2016-04-20 02:00:01 +07:00
|
|
|
return evsel;
|
2014-06-26 23:14:25 +07:00
|
|
|
}
|
|
|
|
|
2015-02-22 03:10:29 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2016-04-01 01:16:28 +07:00
|
|
|
trace__set_base_time(trace, evsel, sample);
|
|
|
|
|
2015-02-22 03:10:29 +07:00
|
|
|
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);
|
|
|
|
}
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
|
|
|
|
if (trace->nr_events_printed >= trace->max_events && trace->max_events != ULONG_MAX)
|
|
|
|
interrupted = true;
|
2015-02-22 03:10:29 +07:00
|
|
|
}
|
|
|
|
|
2015-07-03 04:24:51 +07:00
|
|
|
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;
|
|
|
|
|
2018-08-03 00:27:09 +07:00
|
|
|
sys_enter = perf_evsel__raw_syscall_newtp("sys_enter", trace__sys_enter);
|
2015-07-03 04:24:51 +07:00
|
|
|
if (sys_enter == NULL)
|
|
|
|
goto out;
|
|
|
|
|
|
|
|
if (perf_evsel__init_sc_tp_ptr_field(sys_enter, args))
|
|
|
|
goto out_delete_sys_enter;
|
|
|
|
|
2018-08-03 00:27:09 +07:00
|
|
|
sys_exit = perf_evsel__raw_syscall_newtp("sys_exit", trace__sys_exit);
|
2015-07-03 04:24:51 +07:00
|
|
|
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 trace: Fix setting of --call-graph/--max-stack for non-syscall events
The raw_syscalls:sys_{enter,exit} were first supported in 'perf trace',
together with minor and major page faults, then we supported
--call-graph, then --max-stack, but when the other tracepoints got
supported, and bpf, etc, I forgot to make those global call-graph
settings apply to them.
Fix it by realizing that the global --max-stack and --call-graph
settings are done via:
OPT_CALLBACK(0, "call-graph", &trace.opts,
"record_mode[,record_size]", record_callchain_help,
&record_parse_callchain_opt),
And then, when we go to parse the events in -e via:
OPT_CALLBACK('e', "event", &trace, "event",
"event/syscall selector. use 'perf list' to list available events",
trace__parse_events_option),
And trace__parse_sevents_option() calls:
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);
parse_events_option() will override the global --call-graph and
--max-stack if the "call-graph" and/or "max-stack" terms are in the
event definition, such as in the probe_libc:inet_pton event in one of the
examples below (-e probe_libc:inet_pton/max-stack=2).
Before:
# perf trace --mmap 1024 --call-graph dwarf -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
1.525 ( ): probe_libc:inet_pton:(7f77f3ac9350))
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.071 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.071/0.071/0.071/0.000 ms
1.677 ( 0.081 ms): ping/31296 sendto(fd: 3, buff: 0x55681b652720, len: 64, addr: 0x55681b650640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa97e4bc9cef] (/usr/bin/ping)
[0xffffaa97e4bc656d] (/usr/bin/ping)
[0xffffaa97e4bc7d0a] (/usr/bin/ping)
[0xffffaa97e4bca447] (/usr/bin/ping)
[0xffffaa97e4bc2f91] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa97e4bc3379] (/usr/bin/ping)
#
After:
# perf trace --mmap 1024 --call-graph dwarf -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.089 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.089/0.089/0.089/0.000 ms
1.955 ( ): probe_libc:inet_pton:(7f383a311350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
[0xffffaa5d91444f3f] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa5d91445379] (/usr/bin/ping)
2.140 ( 0.101 ms): ping/32047 sendto(fd: 3, buff: 0x55a26edd0720, len: 64, addr: 0x55a26edce640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa5d9144bcef] (/usr/bin/ping)
[0xffffaa5d9144856d] (/usr/bin/ping)
[0xffffaa5d91449d0a] (/usr/bin/ping)
[0xffffaa5d9144c447] (/usr/bin/ping)
[0xffffaa5d91444f91] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa5d91445379] (/usr/bin/ping)
#
Same thing for --max-stack, the global one:
# perf trace --max-stack 3 -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.097 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.097/0.097/0.097/0.000 ms
1.577 ( ): probe_libc:inet_pton:(7f32f3957350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
1.738 ( 0.108 ms): ping/32103 sendto(fd: 3, buff: 0x55c3132d7720, len: 64, addr: 0x55c3132d5640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa3cecf44cef] (/usr/bin/ping)
[0xffffaa3cecf4156d] (/usr/bin/ping)
#
And then setting up a global setting (dwarf, max-stack=4), that will
affect the raw_syscall:sys_enter for the 'sendto' syscall and that will
be overriden in the probe_libc:inet_pton call to just one entry.
# perf trace --max-stack=4 --call-graph dwarf -e sendto -e probe_libc:inet_pton/max-stack=1/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.090 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.090/0.090/0.090/0.000 ms
2.140 ( ): probe_libc:inet_pton:(7f9fe9337350))
__GI___inet_pton (/usr/lib64/libc-2.26.so)
2.283 ( 0.103 ms): ping/31804 sendto(fd: 3, buff: 0x55c7f3e19720, len: 64, addr: 0x55c7f3e17640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa380c402cef] (/usr/bin/ping)
[0xffffaa380c3ff56d] (/usr/bin/ping)
[0xffffaa380c400d0a] (/usr/bin/ping)
#
Install iputils-debuginfo to get those /usr/bin/ping addresses resolved,
those routines are not on its .dymsym nor .symtab :-)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-qgl2gse8elhh9zztw4ajopg3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-12 23:29:05 +07:00
|
|
|
perf_evsel__config_callchain(sys_enter, &trace->opts, &callchain_param);
|
|
|
|
perf_evsel__config_callchain(sys_exit, &trace->opts, &callchain_param);
|
|
|
|
|
2015-07-03 04:24:51 +07:00
|
|
|
perf_evlist__add(evlist, sys_enter);
|
|
|
|
perf_evlist__add(evlist, sys_exit);
|
|
|
|
|
2016-04-18 22:09:08 +07:00
|
|
|
if (callchain_param.enabled && !trace->kernel_syscallchains) {
|
2016-04-12 01:49:11 +07:00
|
|
|
/*
|
|
|
|
* 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;
|
|
|
|
}
|
|
|
|
|
2015-07-03 04:28:11 +07:00
|
|
|
trace->syscalls.events.sys_enter = sys_enter;
|
|
|
|
trace->syscalls.events.sys_exit = sys_exit;
|
2015-07-03 04:24:51 +07:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2018-12-12 21:06:53 +07:00
|
|
|
static int trace__set_ev_qualifier_tp_filter(struct trace *trace)
|
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 22:44:59 +07:00
|
|
|
{
|
|
|
|
int err = -1;
|
2016-09-16 21:44:03 +07:00
|
|
|
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 22:44:59 +07:00
|
|
|
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 21:44:04 +07:00
|
|
|
if (!perf_evsel__append_tp_filter(trace->syscalls.events.sys_enter,
|
|
|
|
filter)) {
|
2016-09-16 21:44:03 +07:00
|
|
|
sys_exit = trace->syscalls.events.sys_exit;
|
2016-09-16 21:44:04 +07:00
|
|
|
err = perf_evsel__append_tp_filter(sys_exit, filter);
|
2016-09-16 21:44:03 +07:00
|
|
|
}
|
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 22:44:59 +07:00
|
|
|
|
|
|
|
free(filter);
|
|
|
|
out:
|
|
|
|
return err;
|
|
|
|
out_enomem:
|
|
|
|
errno = ENOMEM;
|
|
|
|
goto out;
|
|
|
|
}
|
2015-07-03 04:24:51 +07:00
|
|
|
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
#ifdef HAVE_LIBBPF_SUPPORT
|
|
|
|
static int trace__set_ev_qualifier_bpf_filter(struct trace *trace)
|
|
|
|
{
|
|
|
|
int fd = bpf_map__fd(trace->syscalls.map);
|
2018-12-13 02:54:09 +07:00
|
|
|
struct bpf_map_syscall_entry value = {
|
|
|
|
.enabled = !trace->not_ev_qualifier,
|
|
|
|
};
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
int err = 0;
|
|
|
|
size_t i;
|
|
|
|
|
|
|
|
for (i = 0; i < trace->ev_qualifier_ids.nr; ++i) {
|
|
|
|
int key = trace->ev_qualifier_ids.entries[i];
|
|
|
|
|
|
|
|
err = bpf_map_update_elem(fd, &key, &value, BPF_EXIST);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int __trace__init_syscalls_bpf_map(struct trace *trace, bool enabled)
|
|
|
|
{
|
|
|
|
int fd = bpf_map__fd(trace->syscalls.map);
|
2018-12-13 02:54:09 +07:00
|
|
|
struct bpf_map_syscall_entry value = {
|
|
|
|
.enabled = enabled,
|
|
|
|
};
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
int err = 0, key;
|
|
|
|
|
|
|
|
for (key = 0; key < trace->sctbl->syscalls.nr_entries; ++key) {
|
2018-12-13 02:54:09 +07:00
|
|
|
err = bpf_map_update_elem(fd, &key, &value, BPF_ANY);
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int trace__init_syscalls_bpf_map(struct trace *trace)
|
|
|
|
{
|
|
|
|
bool enabled = true;
|
|
|
|
|
|
|
|
if (trace->ev_qualifier_ids.nr)
|
|
|
|
enabled = trace->not_ev_qualifier;
|
|
|
|
|
|
|
|
return __trace__init_syscalls_bpf_map(trace, enabled);
|
|
|
|
}
|
|
|
|
#else
|
|
|
|
static int trace__set_ev_qualifier_bpf_filter(struct trace *trace __maybe_unused)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int trace__init_syscalls_bpf_map(struct trace *trace __maybe_unused)
|
|
|
|
{
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif // HAVE_LIBBPF_SUPPORT
|
|
|
|
|
2018-12-12 21:06:53 +07:00
|
|
|
static int trace__set_ev_qualifier_filter(struct trace *trace)
|
|
|
|
{
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
if (trace->syscalls.map)
|
|
|
|
return trace__set_ev_qualifier_bpf_filter(trace);
|
2018-12-19 20:01:20 +07:00
|
|
|
if (trace->syscalls.events.sys_enter)
|
|
|
|
return trace__set_ev_qualifier_tp_filter(trace);
|
|
|
|
return 0;
|
2018-12-12 21:06:53 +07:00
|
|
|
}
|
|
|
|
|
2018-11-07 20:08:00 +07:00
|
|
|
static int bpf_map__set_filter_pids(struct bpf_map *map __maybe_unused,
|
|
|
|
size_t npids __maybe_unused, pid_t *pids __maybe_unused)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
#ifdef HAVE_LIBBPF_SUPPORT
|
|
|
|
bool value = true;
|
|
|
|
int map_fd = bpf_map__fd(map);
|
|
|
|
size_t i;
|
|
|
|
|
|
|
|
for (i = 0; i < npids; ++i) {
|
|
|
|
err = bpf_map_update_elem(map_fd, &pids[i], &value, BPF_ANY);
|
|
|
|
if (err)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
#endif
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2017-07-20 21:17:51 +07:00
|
|
|
static int trace__set_filter_loop_pids(struct trace *trace)
|
|
|
|
{
|
2018-11-07 20:08:00 +07:00
|
|
|
unsigned int nr = 1, err;
|
2017-07-20 21:17:51 +07:00
|
|
|
pid_t pids[32] = {
|
|
|
|
getpid(),
|
|
|
|
};
|
perf trace: Filter out 'sshd' in the tracer ancestry in syswide tracing
Avoiding a loop, so now its quite convenient to ssh to a machine and
then simply do:
# perf trace
To trace all syscalls without causing a loop.
This was possible using --filter-pids, i.e. once you noticed the loop,
get the sshd pid and add it to --filter-pids, restarting the 'perf
trace'.
Now to figure out how to do that in a X terminal, the other common
scenario, which is way more involved, as there are multiple processes
communicating to process terminal activity...
Using --filter-pids + '-e \!syscall,names,you,dont,need' may be a good
approximation when having to do syswide tracing on your workstation.
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-68rjeao9wnpylla41htk7xps@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-20 21:32:05 +07:00
|
|
|
struct thread *thread = machine__find_thread(trace->host, pids[0], pids[0]);
|
|
|
|
|
|
|
|
while (thread && nr < ARRAY_SIZE(pids)) {
|
|
|
|
struct thread *parent = machine__find_thread(trace->host, thread->ppid, thread->ppid);
|
|
|
|
|
|
|
|
if (parent == NULL)
|
|
|
|
break;
|
|
|
|
|
2019-02-12 23:51:49 +07:00
|
|
|
if (!strcmp(thread__comm_str(parent), "sshd") ||
|
|
|
|
strstarts(thread__comm_str(parent), "gnome-terminal")) {
|
perf trace: Filter out 'sshd' in the tracer ancestry in syswide tracing
Avoiding a loop, so now its quite convenient to ssh to a machine and
then simply do:
# perf trace
To trace all syscalls without causing a loop.
This was possible using --filter-pids, i.e. once you noticed the loop,
get the sshd pid and add it to --filter-pids, restarting the 'perf
trace'.
Now to figure out how to do that in a X terminal, the other common
scenario, which is way more involved, as there are multiple processes
communicating to process terminal activity...
Using --filter-pids + '-e \!syscall,names,you,dont,need' may be a good
approximation when having to do syswide tracing on your workstation.
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-68rjeao9wnpylla41htk7xps@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-20 21:32:05 +07:00
|
|
|
pids[nr++] = parent->tid;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
thread = parent;
|
|
|
|
}
|
2017-07-20 21:17:51 +07:00
|
|
|
|
2018-11-07 20:08:00 +07:00
|
|
|
err = perf_evlist__set_tp_filter_pids(trace->evlist, nr, pids);
|
|
|
|
if (!err && trace->filter_pids.map)
|
|
|
|
err = bpf_map__set_filter_pids(trace->filter_pids.map, nr, pids);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int trace__set_filter_pids(struct trace *trace)
|
|
|
|
{
|
|
|
|
int err = 0;
|
|
|
|
/*
|
|
|
|
* 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.
|
|
|
|
*/
|
|
|
|
if (trace->filter_pids.nr > 0) {
|
|
|
|
err = perf_evlist__set_tp_filter_pids(trace->evlist, trace->filter_pids.nr,
|
|
|
|
trace->filter_pids.entries);
|
|
|
|
if (!err && trace->filter_pids.map) {
|
|
|
|
err = bpf_map__set_filter_pids(trace->filter_pids.map, trace->filter_pids.nr,
|
|
|
|
trace->filter_pids.entries);
|
|
|
|
}
|
|
|
|
} else if (thread_map__pid(trace->evlist->threads, 0) == -1) {
|
|
|
|
err = trace__set_filter_loop_pids(trace);
|
|
|
|
}
|
|
|
|
|
|
|
|
return err;
|
2017-07-20 21:17:51 +07:00
|
|
|
}
|
|
|
|
|
2018-12-11 02:09:51 +07:00
|
|
|
static int __trace__deliver_event(struct trace *trace, union perf_event *event)
|
2018-12-05 23:05:08 +07:00
|
|
|
{
|
|
|
|
struct perf_evlist *evlist = trace->evlist;
|
|
|
|
struct perf_sample sample;
|
|
|
|
int err;
|
|
|
|
|
|
|
|
err = perf_evlist__parse_sample(evlist, event, &sample);
|
|
|
|
if (err)
|
|
|
|
fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
|
|
|
|
else
|
|
|
|
trace__handle_event(trace, event, &sample);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-12-11 02:27:33 +07:00
|
|
|
static int __trace__flush_events(struct trace *trace)
|
2018-12-05 23:05:09 +07:00
|
|
|
{
|
|
|
|
u64 first = ordered_events__first_time(&trace->oe.data);
|
|
|
|
u64 flush = trace->oe.last - NSEC_PER_SEC;
|
|
|
|
|
|
|
|
/* Is there some thing to flush.. */
|
|
|
|
if (first && first < flush)
|
|
|
|
return ordered_events__flush_time(&trace->oe.data, flush);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-12-11 02:27:33 +07:00
|
|
|
static int trace__flush_events(struct trace *trace)
|
|
|
|
{
|
|
|
|
return !trace->sort_events ? 0 : __trace__flush_events(trace);
|
|
|
|
}
|
|
|
|
|
2018-12-11 02:09:51 +07:00
|
|
|
static int trace__deliver_event(struct trace *trace, union perf_event *event)
|
2018-12-05 23:05:09 +07:00
|
|
|
{
|
|
|
|
int err;
|
|
|
|
|
2018-12-11 02:27:33 +07:00
|
|
|
if (!trace->sort_events)
|
|
|
|
return __trace__deliver_event(trace, event);
|
|
|
|
|
|
|
|
err = perf_evlist__parse_sample_timestamp(trace->evlist, event, &trace->oe.last);
|
2018-12-05 23:05:09 +07:00
|
|
|
if (err && err != -1)
|
|
|
|
return err;
|
|
|
|
|
|
|
|
err = ordered_events__queue(&trace->oe.data, event, trace->oe.last, 0);
|
|
|
|
if (err)
|
|
|
|
return err;
|
|
|
|
|
2018-12-11 02:09:51 +07:00
|
|
|
return trace__flush_events(trace);
|
2018-12-05 23:05:09 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
static int ordered_events__deliver_event(struct ordered_events *oe,
|
|
|
|
struct ordered_event *event)
|
|
|
|
{
|
|
|
|
struct trace *trace = container_of(oe, struct trace, oe.data);
|
|
|
|
|
2018-12-11 02:09:51 +07:00
|
|
|
return __trace__deliver_event(trace, event->event);
|
2018-12-05 23:05:09 +07:00
|
|
|
}
|
|
|
|
|
2012-10-05 12:02:16 +07:00
|
|
|
static int trace__run(struct trace *trace, int argc, const char **argv)
|
2012-09-27 06:05:56 +07:00
|
|
|
{
|
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 22:58:57 +07:00
|
|
|
struct perf_evlist *evlist = trace->evlist;
|
2016-04-20 02:00:01 +07:00
|
|
|
struct perf_evsel *evsel, *pgfault_maj = NULL, *pgfault_min = NULL;
|
2012-10-18 03:09:46 +07:00
|
|
|
int err = -1, i;
|
|
|
|
unsigned long before;
|
2012-10-05 12:02:16 +07:00
|
|
|
const bool forks = argc > 0;
|
2014-09-23 00:39:48 +07:00
|
|
|
bool draining = false;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2013-09-24 21:04:32 +07:00
|
|
|
trace->live = true;
|
|
|
|
|
2018-12-12 23:47:40 +07:00
|
|
|
if (!trace->raw_augmented_syscalls) {
|
|
|
|
if (trace->trace_syscalls && trace__add_syscall_newtp(trace))
|
|
|
|
goto out_error_raw_syscalls;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2018-12-12 23:47:40 +07:00
|
|
|
if (trace->trace_syscalls)
|
|
|
|
trace->vfs_getname = perf_evlist__add_vfs_getname(evlist);
|
|
|
|
}
|
2013-09-28 04:06:19 +07:00
|
|
|
|
2016-04-20 02:00:01 +07:00
|
|
|
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 trace: Fix setting of --call-graph/--max-stack for non-syscall events
The raw_syscalls:sys_{enter,exit} were first supported in 'perf trace',
together with minor and major page faults, then we supported
--call-graph, then --max-stack, but when the other tracepoints got
supported, and bpf, etc, I forgot to make those global call-graph
settings apply to them.
Fix it by realizing that the global --max-stack and --call-graph
settings are done via:
OPT_CALLBACK(0, "call-graph", &trace.opts,
"record_mode[,record_size]", record_callchain_help,
&record_parse_callchain_opt),
And then, when we go to parse the events in -e via:
OPT_CALLBACK('e', "event", &trace, "event",
"event/syscall selector. use 'perf list' to list available events",
trace__parse_events_option),
And trace__parse_sevents_option() calls:
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);
parse_events_option() will override the global --call-graph and
--max-stack if the "call-graph" and/or "max-stack" terms are in the
event definition, such as in the probe_libc:inet_pton event in one of the
examples below (-e probe_libc:inet_pton/max-stack=2).
Before:
# perf trace --mmap 1024 --call-graph dwarf -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
1.525 ( ): probe_libc:inet_pton:(7f77f3ac9350))
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.071 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.071/0.071/0.071/0.000 ms
1.677 ( 0.081 ms): ping/31296 sendto(fd: 3, buff: 0x55681b652720, len: 64, addr: 0x55681b650640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa97e4bc9cef] (/usr/bin/ping)
[0xffffaa97e4bc656d] (/usr/bin/ping)
[0xffffaa97e4bc7d0a] (/usr/bin/ping)
[0xffffaa97e4bca447] (/usr/bin/ping)
[0xffffaa97e4bc2f91] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa97e4bc3379] (/usr/bin/ping)
#
After:
# perf trace --mmap 1024 --call-graph dwarf -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.089 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.089/0.089/0.089/0.000 ms
1.955 ( ): probe_libc:inet_pton:(7f383a311350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
[0xffffaa5d91444f3f] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa5d91445379] (/usr/bin/ping)
2.140 ( 0.101 ms): ping/32047 sendto(fd: 3, buff: 0x55a26edd0720, len: 64, addr: 0x55a26edce640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa5d9144bcef] (/usr/bin/ping)
[0xffffaa5d9144856d] (/usr/bin/ping)
[0xffffaa5d91449d0a] (/usr/bin/ping)
[0xffffaa5d9144c447] (/usr/bin/ping)
[0xffffaa5d91444f91] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa5d91445379] (/usr/bin/ping)
#
Same thing for --max-stack, the global one:
# perf trace --max-stack 3 -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.097 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.097/0.097/0.097/0.000 ms
1.577 ( ): probe_libc:inet_pton:(7f32f3957350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
1.738 ( 0.108 ms): ping/32103 sendto(fd: 3, buff: 0x55c3132d7720, len: 64, addr: 0x55c3132d5640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa3cecf44cef] (/usr/bin/ping)
[0xffffaa3cecf4156d] (/usr/bin/ping)
#
And then setting up a global setting (dwarf, max-stack=4), that will
affect the raw_syscall:sys_enter for the 'sendto' syscall and that will
be overriden in the probe_libc:inet_pton call to just one entry.
# perf trace --max-stack=4 --call-graph dwarf -e sendto -e probe_libc:inet_pton/max-stack=1/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.090 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.090/0.090/0.090/0.000 ms
2.140 ( ): probe_libc:inet_pton:(7f9fe9337350))
__GI___inet_pton (/usr/lib64/libc-2.26.so)
2.283 ( 0.103 ms): ping/31804 sendto(fd: 3, buff: 0x55c7f3e19720, len: 64, addr: 0x55c7f3e17640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa380c402cef] (/usr/bin/ping)
[0xffffaa380c3ff56d] (/usr/bin/ping)
[0xffffaa380c400d0a] (/usr/bin/ping)
#
Install iputils-debuginfo to get those /usr/bin/ping addresses resolved,
those routines are not on its .dymsym nor .symtab :-)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-qgl2gse8elhh9zztw4ajopg3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-12 23:29:05 +07:00
|
|
|
perf_evsel__config_callchain(pgfault_maj, &trace->opts, &callchain_param);
|
2016-04-20 02:00:01 +07:00
|
|
|
perf_evlist__add(evlist, pgfault_maj);
|
2015-01-22 20:34:22 +07:00
|
|
|
}
|
2014-06-26 23:14:25 +07:00
|
|
|
|
2016-04-20 02:00:01 +07:00
|
|
|
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 trace: Fix setting of --call-graph/--max-stack for non-syscall events
The raw_syscalls:sys_{enter,exit} were first supported in 'perf trace',
together with minor and major page faults, then we supported
--call-graph, then --max-stack, but when the other tracepoints got
supported, and bpf, etc, I forgot to make those global call-graph
settings apply to them.
Fix it by realizing that the global --max-stack and --call-graph
settings are done via:
OPT_CALLBACK(0, "call-graph", &trace.opts,
"record_mode[,record_size]", record_callchain_help,
&record_parse_callchain_opt),
And then, when we go to parse the events in -e via:
OPT_CALLBACK('e', "event", &trace, "event",
"event/syscall selector. use 'perf list' to list available events",
trace__parse_events_option),
And trace__parse_sevents_option() calls:
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);
parse_events_option() will override the global --call-graph and
--max-stack if the "call-graph" and/or "max-stack" terms are in the
event definition, such as in the probe_libc:inet_pton event in one of the
examples below (-e probe_libc:inet_pton/max-stack=2).
Before:
# perf trace --mmap 1024 --call-graph dwarf -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
1.525 ( ): probe_libc:inet_pton:(7f77f3ac9350))
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.071 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.071/0.071/0.071/0.000 ms
1.677 ( 0.081 ms): ping/31296 sendto(fd: 3, buff: 0x55681b652720, len: 64, addr: 0x55681b650640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa97e4bc9cef] (/usr/bin/ping)
[0xffffaa97e4bc656d] (/usr/bin/ping)
[0xffffaa97e4bc7d0a] (/usr/bin/ping)
[0xffffaa97e4bca447] (/usr/bin/ping)
[0xffffaa97e4bc2f91] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa97e4bc3379] (/usr/bin/ping)
#
After:
# perf trace --mmap 1024 --call-graph dwarf -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.089 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.089/0.089/0.089/0.000 ms
1.955 ( ): probe_libc:inet_pton:(7f383a311350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
[0xffffaa5d91444f3f] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa5d91445379] (/usr/bin/ping)
2.140 ( 0.101 ms): ping/32047 sendto(fd: 3, buff: 0x55a26edd0720, len: 64, addr: 0x55a26edce640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa5d9144bcef] (/usr/bin/ping)
[0xffffaa5d9144856d] (/usr/bin/ping)
[0xffffaa5d91449d0a] (/usr/bin/ping)
[0xffffaa5d9144c447] (/usr/bin/ping)
[0xffffaa5d91444f91] (/usr/bin/ping)
__libc_start_main (/usr/lib64/libc-2.26.so)
[0xffffaa5d91445379] (/usr/bin/ping)
#
Same thing for --max-stack, the global one:
# perf trace --max-stack 3 -e sendto,probe_libc:inet_pton ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.097 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.097/0.097/0.097/0.000 ms
1.577 ( ): probe_libc:inet_pton:(7f32f3957350))
__inet_pton (inlined)
gaih_inet.constprop.7 (/usr/lib64/libc-2.26.so)
__GI_getaddrinfo (inlined)
1.738 ( 0.108 ms): ping/32103 sendto(fd: 3, buff: 0x55c3132d7720, len: 64, addr: 0x55c3132d5640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa3cecf44cef] (/usr/bin/ping)
[0xffffaa3cecf4156d] (/usr/bin/ping)
#
And then setting up a global setting (dwarf, max-stack=4), that will
affect the raw_syscall:sys_enter for the 'sendto' syscall and that will
be overriden in the probe_libc:inet_pton call to just one entry.
# perf trace --max-stack=4 --call-graph dwarf -e sendto -e probe_libc:inet_pton/max-stack=1/ ping -6 -c 1 ::1
PING ::1(::1) 56 data bytes
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.090 ms
--- ::1 ping statistics ---
1 packets transmitted, 1 received, 0% packet loss, time 0ms
rtt min/avg/max/mdev = 0.090/0.090/0.090/0.000 ms
2.140 ( ): probe_libc:inet_pton:(7f9fe9337350))
__GI___inet_pton (/usr/lib64/libc-2.26.so)
2.283 ( 0.103 ms): ping/31804 sendto(fd: 3, buff: 0x55c7f3e19720, len: 64, addr: 0x55c7f3e17640, addr_len: 28) = 64
__libc_sendto (/usr/lib64/libc-2.26.so)
[0xffffaa380c402cef] (/usr/bin/ping)
[0xffffaa380c3ff56d] (/usr/bin/ping)
[0xffffaa380c400d0a] (/usr/bin/ping)
#
Install iputils-debuginfo to get those /usr/bin/ping addresses resolved,
those routines are not on its .dymsym nor .symtab :-)
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrick Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-qgl2gse8elhh9zztw4ajopg3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-12 23:29:05 +07:00
|
|
|
perf_evsel__config_callchain(pgfault_min, &trace->opts, &callchain_param);
|
2016-04-20 02:00:01 +07:00
|
|
|
perf_evlist__add(evlist, pgfault_min);
|
|
|
|
}
|
2014-06-26 23:14:25 +07:00
|
|
|
|
2012-10-18 03:13:12 +07:00
|
|
|
if (trace->sched &&
|
2015-01-22 21:13:43 +07:00
|
|
|
perf_evlist__add_newtp(evlist, "sched", "sched_stat_runtime",
|
|
|
|
trace__sched_stat_runtime))
|
|
|
|
goto out_error_sched_stat_runtime;
|
2012-10-18 03:13:12 +07:00
|
|
|
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
/*
|
|
|
|
* If a global cgroup was set, apply it to all the events without an
|
|
|
|
* explicit cgroup. I.e.:
|
|
|
|
*
|
|
|
|
* trace -G A -e sched:*switch
|
|
|
|
*
|
|
|
|
* Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
|
|
|
|
* _and_ sched:sched_switch to the 'A' cgroup, while:
|
|
|
|
*
|
|
|
|
* trace -e sched:*switch -G A
|
|
|
|
*
|
|
|
|
* will only set the sched:sched_switch event to the 'A' cgroup, all the
|
|
|
|
* other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
|
|
|
|
* a cgroup (on the root cgroup, sys wide, etc).
|
|
|
|
*
|
|
|
|
* Multiple cgroups:
|
|
|
|
*
|
|
|
|
* trace -G A -e sched:*switch -G B
|
|
|
|
*
|
|
|
|
* the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
|
|
|
|
* to the 'B' cgroup.
|
|
|
|
*
|
|
|
|
* evlist__set_default_cgroup() grabs a reference of the passed cgroup
|
|
|
|
* only for the evsels still without a cgroup, i.e. evsel->cgroup == NULL.
|
|
|
|
*/
|
|
|
|
if (trace->cgroup)
|
|
|
|
evlist__set_default_cgroup(trace->evlist, trace->cgroup);
|
|
|
|
|
2012-09-27 06:05:56 +07:00
|
|
|
err = perf_evlist__create_maps(evlist, &trace->opts.target);
|
|
|
|
if (err < 0) {
|
2013-08-19 22:01:10 +07:00
|
|
|
fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
|
2012-09-27 06:05:56 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
err = trace__symbols_init(trace, evlist);
|
|
|
|
if (err < 0) {
|
2013-08-19 22:01:10 +07:00
|
|
|
fprintf(trace->output, "Problems initializing symbol libraries!\n");
|
2014-01-04 01:56:06 +07:00
|
|
|
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>
2012-10-07 04:43:19 +07:00
|
|
|
}
|
|
|
|
|
2018-01-15 20:39:55 +07:00
|
|
|
perf_evlist__config(evlist, &trace->opts, &callchain_param);
|
2016-04-12 04:42:37 +07:00
|
|
|
|
2012-10-05 12:02:16 +07:00
|
|
|
signal(SIGCHLD, sig_handler);
|
|
|
|
signal(SIGINT, sig_handler);
|
|
|
|
|
|
|
|
if (forks) {
|
2013-03-11 14:43:15 +07:00
|
|
|
err = perf_evlist__prepare_workload(evlist, &trace->opts.target,
|
2014-01-04 00:56:49 +07:00
|
|
|
argv, false, NULL);
|
2012-10-05 12:02:16 +07:00
|
|
|
if (err < 0) {
|
2013-08-19 22:01:10 +07:00
|
|
|
fprintf(trace->output, "Couldn't run the workload!\n");
|
2014-01-04 01:56:06 +07:00
|
|
|
goto out_delete_evlist;
|
2012-10-05 12:02:16 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2012-09-27 06:05:56 +07:00
|
|
|
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>
2013-10-18 03:38:29 +07:00
|
|
|
if (err < 0)
|
|
|
|
goto out_error_open;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2016-02-26 16:31:54 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2018-11-07 20:08:00 +07:00
|
|
|
err = trace__set_filter_pids(trace);
|
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>
2015-07-04 03:42:03 +07:00
|
|
|
if (err < 0)
|
|
|
|
goto out_error_mem;
|
|
|
|
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
if (trace->syscalls.map)
|
|
|
|
trace__init_syscalls_bpf_map(trace);
|
|
|
|
|
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 22:44:59 +07:00
|
|
|
if (trace->ev_qualifier_ids.nr > 0) {
|
|
|
|
err = trace__set_ev_qualifier_filter(trace);
|
|
|
|
if (err < 0)
|
|
|
|
goto out_errno;
|
|
|
|
|
2018-12-12 23:47:40 +07:00
|
|
|
if (trace->syscalls.events.sys_exit) {
|
|
|
|
pr_debug("event qualifier tracepoint filter: %s\n",
|
|
|
|
trace->syscalls.events.sys_exit->filter);
|
|
|
|
}
|
2015-08-04 03:12:29 +07:00
|
|
|
}
|
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 22:44:59 +07:00
|
|
|
|
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>
2015-07-04 03:42:03 +07:00
|
|
|
err = perf_evlist__apply_filters(evlist, &evsel);
|
|
|
|
if (err < 0)
|
|
|
|
goto out_error_apply_filters;
|
2015-02-22 01:15:21 +07:00
|
|
|
|
perf trace: Allow dumping a BPF map after setting up BPF events
Initial use case:
Dumping the maps setup by tools/perf/examples/bpf/augmented_raw_syscalls.c,
which so far are just booleans, showing just non-zeroed entries:
# cat ~/.perfconfig
[llvm]
dump-obj = true
clang-opt = -g
[trace]
#add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
add_events = /wb/augmented_raw_syscalls.o
$ date
Tue Feb 19 16:29:33 -03 2019
$ ls -la /wb/augmented_raw_syscalls.o
-rwxr-xr-x. 1 root root 14048 Jan 24 12:09 /wb/augmented_raw_syscalls.o
$ file /wb/augmented_raw_syscalls.o
/wb/augmented_raw_syscalls.o: ELF 64-bit LSB relocatable, eBPF, version 1 (SYSV), with debug_info, not stripped
$
# trace -e recvmmsg,sendmmsg --map-dump foobar
ERROR: BPF map "foobar" not found
# trace -e recvmmsg,sendmmsg --map-dump filtered_pids
ERROR: BPF map "filtered_pids" not found
# trace -e recvmmsg,sendmmsg --map-dump pids_filtered
[2583] = 1,
[2267] = 1,
^Z
[1]+ Stopped trace -e recvmmsg,sendmmsg --map-dump pids_filtered
# pidof trace
2267
# ps ax|grep gnome-terminal|grep -v grep
2583 ? Ssl 58:33 /usr/libexec/gnome-terminal-server
^C
# trace -e recvmmsg,sendmmsg --map-dump syscalls
[299] = 1,
[307] = 1,
^C
# grep x64_recvmmsg arch/x86/entry/syscalls/syscall_64.tbl
299 64 recvmmsg __x64_sys_recvmmsg
# grep x64_sendmmsg arch/x86/entry/syscalls/syscall_64.tbl
307 64 sendmmsg __x64_sys_sendmmsg
#
Next step probably will be something like 'perf stat's --interval-print and
--interval-clear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-ztxj25rtx37ixo9cfajt8ocy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-20 02:17:33 +07:00
|
|
|
if (trace->dump.map)
|
|
|
|
bpf_map__fprintf(trace->dump.map, trace->output);
|
|
|
|
|
2017-12-03 09:00:37 +07:00
|
|
|
err = perf_evlist__mmap(evlist, trace->opts.mmap_pages);
|
2014-12-12 04:04:10 +07:00
|
|
|
if (err < 0)
|
|
|
|
goto out_error_mmap;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
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 12:43:28 +07:00
|
|
|
if (!target__none(&trace->opts.target) && !trace->opts.initial_delay)
|
2015-04-22 20:04:23 +07:00
|
|
|
perf_evlist__enable(evlist);
|
|
|
|
|
2012-10-05 12:02:16 +07:00
|
|
|
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 12:43:28 +07:00
|
|
|
if (trace->opts.initial_delay) {
|
|
|
|
usleep(trace->opts.initial_delay * 1000);
|
|
|
|
perf_evlist__enable(evlist);
|
|
|
|
}
|
|
|
|
|
2015-06-23 05:36:02 +07:00
|
|
|
trace->multiple_threads = thread_map__pid(evlist->threads, 0) == -1 ||
|
2015-02-13 22:32:45 +07:00
|
|
|
evlist->threads->nr > 1 ||
|
|
|
|
perf_evlist__first(evlist)->attr.inherit;
|
2018-01-15 21:33:53 +07:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Now that we already used evsel->attr to ask the kernel to setup the
|
|
|
|
* events, lets reuse evsel->attr.sample_max_stack as the limit in
|
|
|
|
* trace__resolve_callchain(), allowing per-event max-stack settings
|
2018-12-03 17:22:00 +07:00
|
|
|
* to override an explicitly set --max-stack global setting.
|
2018-01-15 21:33:53 +07:00
|
|
|
*/
|
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
2018-05-29 02:00:29 +07:00
|
|
|
if (evsel__has_callchain(evsel) &&
|
2018-01-15 21:33:53 +07:00
|
|
|
evsel->attr.sample_max_stack == 0)
|
|
|
|
evsel->attr.sample_max_stack = trace->max_stack;
|
|
|
|
}
|
2012-09-27 06:05:56 +07:00
|
|
|
again:
|
2012-10-18 03:09:46 +07:00
|
|
|
before = trace->nr_events;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
|
|
|
for (i = 0; i < evlist->nr_mmaps; i++) {
|
|
|
|
union perf_event *event;
|
2018-03-02 06:08:59 +07:00
|
|
|
struct perf_mmap *md;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2018-03-02 06:08:59 +07:00
|
|
|
md = &evlist->mmap[i];
|
2018-03-06 22:36:07 +07:00
|
|
|
if (perf_mmap__read_init(md) < 0)
|
2018-03-02 06:08:59 +07:00
|
|
|
continue;
|
|
|
|
|
2018-03-06 22:36:06 +07:00
|
|
|
while ((event = perf_mmap__read_event(md)) != NULL) {
|
2012-10-18 03:09:46 +07:00
|
|
|
++trace->nr_events;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2018-12-11 02:09:51 +07:00
|
|
|
err = trace__deliver_event(trace, event);
|
2018-12-05 23:05:09 +07:00
|
|
|
if (err)
|
|
|
|
goto out_disable;
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2018-03-06 22:36:05 +07:00
|
|
|
perf_mmap__consume(md);
|
2013-09-03 21:55:07 +07:00
|
|
|
|
2013-10-16 21:57:33 +07:00
|
|
|
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 21:11:57 +07:00
|
|
|
|
|
|
|
if (done && !draining) {
|
|
|
|
perf_evlist__disable(evlist);
|
|
|
|
draining = true;
|
|
|
|
}
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
2018-03-02 06:08:59 +07:00
|
|
|
perf_mmap__read_done(md);
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
|
|
|
|
2012-10-18 03:09:46 +07:00
|
|
|
if (trace->nr_events == before) {
|
2013-10-16 21:57:33 +07:00
|
|
|
int timeout = done ? 100 : -1;
|
2012-10-05 12:02:16 +07:00
|
|
|
|
2014-09-23 00:39:48 +07:00
|
|
|
if (!draining && perf_evlist__poll(evlist, timeout) > 0) {
|
perf trace: Introduce per-event maximum number of events property
Call it 'nr', as in this context it should be expressive enough, i.e.:
# perf trace -e sched:*waking/nr=8,call-graph=fp/
0.000 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.933 :0/0 sched:sched_waking:comm=rcu_sched pid=10 prio=120 target_cpu=001
try_to_wake_up ([kernel.kallsyms])
sched_clock ([kernel.kallsyms])
3.970 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
20.069 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
37.170 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
53.267 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
70.365 IPDL Backgroun/3622 sched:sched_waking:comm=Gecko_IOThread pid=3569 prio=120 target_cpu=003
try_to_wake_up ([kernel.kallsyms])
__libc_write (/usr/lib64/libpthread-2.26.so)
75.781 Web Content/3649 sched:sched_waking:comm=JS Helper pid=3670 prio=120 target_cpu=000
try_to_wake_up ([kernel.kallsyms])
try_to_wake_up ([kernel.kallsyms])
wake_up_q ([kernel.kallsyms])
futex_wake ([kernel.kallsyms])
do_futex ([kernel.kallsyms])
__x64_sys_futex ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64_after_hwframe ([kernel.kallsyms])
pthread_cond_signal@@GLIBC_2.3.2 (/usr/lib64/libpthread-2.26.so)
#
# perf trace -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> trace:3367 [120]
0.046 :0/0 sched:sched_switch:swapper/1:0 [120] S ==> kworker/u16:58:2722 [120]
570.670 irq/50-iwlwifi/680 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff93498051ef00 len=66
__dev_queue_xmit ([kernel.kallsyms])
1106.141 jbd2/dm-0-8/476 block:block_plug:[jbd2/dm-0-8]
1106.175 jbd2/dm-0-8/476 block:block_unplug:[jbd2/dm-0-8] 1
1618.088 kworker/u16:30/2694 block:block_plug:[kworker/u16:30]
1810.000 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051ef00 len=52
__dev_queue_xmit ([kernel.kallsyms])
3857.974 :0/0 net:net_dev_queue:dev=vnet0 skbaddr=0xffff93498051f900 len=52
__dev_queue_xmit ([kernel.kallsyms])
4790.277 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
4790.448 jbd2/dm-2-8/748 block:block_plug:[jbd2/dm-2-8]
#
The global --max-events has precendence:
# trace --max-events 3 -e sched:*switch/nr=2/,block:*_plug/nr=4/,block:*_unplug/nr=1/,net:*dev_queue/nr=3,max-stack=16/
0.000 :0/0 sched:sched_switch:swapper/0:0 [120] S ==> qemu-system-x86:2252 [120]
0.029 qemu-system-x8/2252 sched:sched_switch:qemu-system-x86:2252 [120] D ==> swapper/0:0 [120]
58.047 DNS Res~er #14/31661 net:net_dev_queue:dev=wlp3s0 skbaddr=0xffff9346966af100 len=84
__dev_queue_xmit ([kernel.kallsyms])
__libc_send (/usr/lib64/libpthread-2.26.so)
#
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: https://lkml.kernel.org/n/tip-s4jswltvh660ughvg9nwngah@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-23 00:14:16 +07:00
|
|
|
if (perf_evlist__filter_pollfd(evlist, POLLERR | POLLHUP | POLLNVAL) == 0)
|
2014-09-23 00:39:48 +07:00
|
|
|
draining = true;
|
|
|
|
|
2013-10-16 21:57:33 +07:00
|
|
|
goto again;
|
2018-12-05 23:05:09 +07:00
|
|
|
} else {
|
2018-12-11 02:09:51 +07:00
|
|
|
if (trace__flush_events(trace))
|
2018-12-05 23:05:09 +07:00
|
|
|
goto out_disable;
|
2014-09-23 00:39:48 +07:00
|
|
|
}
|
2013-10-16 21:57:33 +07:00
|
|
|
} else {
|
|
|
|
goto again;
|
2012-10-05 12:02:16 +07:00
|
|
|
}
|
|
|
|
|
2013-10-16 21:57:33 +07:00
|
|
|
out_disable:
|
2015-03-03 08:21:35 +07:00
|
|
|
thread__zput(trace->current);
|
|
|
|
|
2013-10-16 21:57:33 +07:00
|
|
|
perf_evlist__disable(evlist);
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2018-12-11 02:27:33 +07:00
|
|
|
if (trace->sort_events)
|
|
|
|
ordered_events__flush(&trace->oe.data, OE_FLUSH__FINAL);
|
2018-12-05 23:05:09 +07:00
|
|
|
|
2013-09-28 04:06:19 +07:00
|
|
|
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 10:26:53 +07:00
|
|
|
|
2012-09-27 06:05:56 +07:00
|
|
|
out_delete_evlist:
|
2017-11-08 07:22:45 +07:00
|
|
|
trace__symbols__exit(trace);
|
|
|
|
|
2012-09-27 06:05:56 +07:00
|
|
|
perf_evlist__delete(evlist);
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
cgroup__put(trace->cgroup);
|
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 22:58:57 +07:00
|
|
|
trace->evlist = NULL;
|
2013-09-24 21:04:32 +07:00
|
|
|
trace->live = false;
|
2012-09-27 06:05:56 +07:00
|
|
|
return err;
|
2013-10-17 22:07:58 +07:00
|
|
|
{
|
|
|
|
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>
2013-10-18 03:38:29 +07:00
|
|
|
|
2015-01-22 21:13:43 +07:00
|
|
|
out_error_sched_stat_runtime:
|
2015-09-02 14:56:35 +07:00
|
|
|
tracing_path__strerror_open_tp(errno, errbuf, sizeof(errbuf), "sched", "sched_stat_runtime");
|
2015-01-22 21:13:43 +07:00
|
|
|
goto out_error;
|
|
|
|
|
2015-01-22 20:52:55 +07:00
|
|
|
out_error_raw_syscalls:
|
2015-09-02 14:56:35 +07:00
|
|
|
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>
2013-10-18 03:38:29 +07:00
|
|
|
goto out_error;
|
|
|
|
|
2014-12-12 04:04:10 +07:00
|
|
|
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>
2013-10-18 03:38:29 +07:00
|
|
|
out_error_open:
|
|
|
|
perf_evlist__strerror_open(evlist, errno, errbuf, sizeof(errbuf));
|
|
|
|
|
|
|
|
out_error:
|
2013-10-17 22:07:58 +07:00
|
|
|
fprintf(trace->output, "%s\n", errbuf);
|
2013-10-04 12:17:31 +07:00
|
|
|
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>
2015-07-04 03:42:03 +07:00
|
|
|
|
|
|
|
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 21:56:20 +07:00
|
|
|
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>
2015-07-04 03:42:03 +07:00
|
|
|
goto out_delete_evlist;
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
2015-01-22 21:08:04 +07:00
|
|
|
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 22:44:59 +07:00
|
|
|
|
|
|
|
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>
2013-10-18 03:38:29 +07:00
|
|
|
}
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2013-08-29 11:29:52 +07:00
|
|
|
static int trace__replay(struct trace *trace)
|
|
|
|
{
|
|
|
|
const struct perf_evsel_str_handler handlers[] = {
|
2013-09-28 04:06:19 +07:00
|
|
|
{ "probe:vfs_getname", trace__vfs_getname, },
|
2013-08-29 11:29:52 +07:00
|
|
|
};
|
2017-01-24 04:07:59 +07:00
|
|
|
struct perf_data data = {
|
2019-02-21 16:41:30 +07:00
|
|
|
.path = input_name,
|
|
|
|
.mode = PERF_DATA_MODE_READ,
|
|
|
|
.force = trace->force,
|
2013-10-15 21:27:32 +07:00
|
|
|
};
|
2013-08-29 11:29:52 +07:00
|
|
|
struct perf_session *session;
|
2013-11-12 13:25:00 +07:00
|
|
|
struct perf_evsel *evsel;
|
2013-08-29 11:29:52 +07:00
|
|
|
int err = -1;
|
|
|
|
|
|
|
|
trace->tool.sample = trace__process_sample;
|
|
|
|
trace->tool.mmap = perf_event__process_mmap;
|
2013-09-23 08:44:58 +07:00
|
|
|
trace->tool.mmap2 = perf_event__process_mmap2;
|
2013-08-29 11:29:52 +07:00
|
|
|
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>
2017-03-08 03:41:43 +07:00
|
|
|
trace->tool.tracing_data = perf_event__process_tracing_data;
|
2013-08-29 11:29:52 +07:00
|
|
|
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>
2017-03-08 03:41:43 +07:00
|
|
|
trace->tool.namespaces = perf_event__process_namespaces;
|
2013-08-29 11:29:52 +07:00
|
|
|
|
2014-07-06 19:18:21 +07:00
|
|
|
trace->tool.ordered_events = true;
|
2013-08-29 11:29:52 +07:00
|
|
|
trace->tool.ordering_requires_timestamps = true;
|
|
|
|
|
|
|
|
/* add tid to output */
|
|
|
|
trace->multiple_threads = true;
|
|
|
|
|
2017-01-24 04:07:59 +07:00
|
|
|
session = perf_session__new(&data, false, &trace->tool);
|
2013-08-29 11:29:52 +07:00
|
|
|
if (session == NULL)
|
2014-09-24 08:33:37 +07:00
|
|
|
return -1;
|
2013-08-29 11:29:52 +07:00
|
|
|
|
2016-11-25 23:29:52 +07:00
|
|
|
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 13:40:45 +07:00
|
|
|
if (symbol__init(&session->header.env) < 0)
|
2014-08-12 13:40:44 +07:00
|
|
|
goto out;
|
|
|
|
|
2013-09-29 02:13:00 +07:00
|
|
|
trace->host = &session->machines.host;
|
|
|
|
|
2013-08-29 11:29:52 +07:00
|
|
|
err = perf_session__set_tracepoints_handlers(session, handlers);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
2013-11-12 13:25:00 +07:00
|
|
|
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
|
|
|
|
"raw_syscalls:sys_enter");
|
2013-12-05 09:41:39 +07:00
|
|
|
/* 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 13:25:00 +07:00
|
|
|
|
2014-06-26 23:14:28 +07:00
|
|
|
if (evsel &&
|
2018-08-03 00:27:09 +07:00
|
|
|
(perf_evsel__init_raw_syscall_tp(evsel, trace__sys_enter) < 0 ||
|
2014-06-26 23:14:28 +07:00
|
|
|
perf_evsel__init_sc_tp_ptr_field(evsel, args))) {
|
2013-11-12 13:25:00 +07:00
|
|
|
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 09:41:39 +07:00
|
|
|
if (evsel == NULL)
|
|
|
|
evsel = perf_evlist__find_tracepoint_by_name(session->evlist,
|
|
|
|
"syscalls:sys_exit");
|
2014-06-26 23:14:28 +07:00
|
|
|
if (evsel &&
|
2018-08-03 00:27:09 +07:00
|
|
|
(perf_evsel__init_raw_syscall_tp(evsel, trace__sys_exit) < 0 ||
|
2014-06-26 23:14:28 +07:00
|
|
|
perf_evsel__init_sc_tp_uint_field(evsel, ret))) {
|
2013-11-12 13:25:00 +07:00
|
|
|
pr_err("Error during initialize raw_syscalls:sys_exit event\n");
|
2013-08-29 11:29:52 +07:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2016-06-23 21:26:15 +07:00
|
|
|
evlist__for_each_entry(session->evlist, evsel) {
|
2014-06-26 23:14:26 +07:00
|
|
|
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 11:29:52 +07:00
|
|
|
setup_pager();
|
|
|
|
|
2015-03-03 21:58:45 +07:00
|
|
|
err = perf_session__process_events(session);
|
2013-08-29 11:29:52 +07:00
|
|
|
if (err)
|
|
|
|
pr_err("Failed to process events, error %d", err);
|
|
|
|
|
2013-10-09 10:26:53 +07:00
|
|
|
else if (trace->summary)
|
|
|
|
trace__fprintf_thread_summary(trace, trace->output);
|
|
|
|
|
2013-08-29 11:29:52 +07:00
|
|
|
out:
|
|
|
|
perf_session__delete(session);
|
|
|
|
|
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2012-10-18 03:13:12 +07:00
|
|
|
static size_t trace__fprintf_threads_header(FILE *fp)
|
|
|
|
{
|
|
|
|
size_t printed;
|
|
|
|
|
2013-11-12 21:42:14 +07:00
|
|
|
printed = fprintf(fp, "\n Summary of events:\n\n");
|
2013-10-09 10:26:53 +07:00
|
|
|
|
|
|
|
return printed;
|
|
|
|
}
|
|
|
|
|
2016-05-05 02:06:26 +07:00
|
|
|
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 10:26:53 +07:00
|
|
|
static size_t thread__dump_stats(struct thread_trace *ttrace,
|
|
|
|
struct trace *trace, FILE *fp)
|
|
|
|
{
|
|
|
|
size_t printed = 0;
|
|
|
|
struct syscall *sc;
|
2016-05-05 02:06:26 +07:00
|
|
|
struct rb_node *nd;
|
|
|
|
DECLARE_RESORT_RB_INTLIST(syscall_stats, ttrace->syscall_stats);
|
2013-10-09 10:26:53 +07:00
|
|
|
|
2016-05-05 02:06:26 +07:00
|
|
|
if (syscall_stats == NULL)
|
2013-10-09 10:26:53 +07:00
|
|
|
return 0;
|
|
|
|
|
|
|
|
printed += fprintf(fp, "\n");
|
|
|
|
|
2015-08-06 16:24:29 +07:00
|
|
|
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 21:42:14 +07:00
|
|
|
|
2016-06-23 21:34:10 +07:00
|
|
|
resort_rb__for_each_entry(nd, syscall_stats) {
|
2016-05-05 02:06:26 +07:00
|
|
|
struct stats *stats = syscall_stats_entry->stats;
|
2013-10-09 10:26:53 +07:00
|
|
|
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;
|
|
|
|
|
2016-05-05 02:06:26 +07:00
|
|
|
sc = &trace->syscalls.table[syscall_stats_entry->syscall];
|
2013-11-12 21:42:14 +07:00
|
|
|
printed += fprintf(fp, " %-15s", sc->name);
|
2015-08-06 16:24:29 +07:00
|
|
|
printed += fprintf(fp, " %8" PRIu64 " %9.3f %9.3f %9.3f",
|
2016-05-05 02:06:26 +07:00
|
|
|
n, syscall_stats_entry->msecs, min, avg);
|
2013-11-13 19:21:48 +07:00
|
|
|
printed += fprintf(fp, " %9.3f %9.2f%%\n", max, pct);
|
2013-10-09 10:26:53 +07:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-05-05 02:06:26 +07:00
|
|
|
resort_rb__delete(syscall_stats);
|
2013-10-09 10:26:53 +07:00
|
|
|
printed += fprintf(fp, "\n\n");
|
2012-10-18 03:13:12 +07:00
|
|
|
|
|
|
|
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 22:47:16 +07:00
|
|
|
static size_t trace__fprintf_thread(FILE *fp, struct thread *thread, struct trace *trace)
|
2013-09-29 02:12:59 +07:00
|
|
|
{
|
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 22:47:16 +07:00
|
|
|
size_t printed = 0;
|
2014-10-06 07:46:03 +07:00
|
|
|
struct thread_trace *ttrace = thread__priv(thread);
|
2013-09-29 02:12:59 +07:00
|
|
|
double ratio;
|
|
|
|
|
|
|
|
if (ttrace == NULL)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
ratio = (double)ttrace->nr_events / trace->nr_events * 100.0;
|
|
|
|
|
2013-11-14 23:43:30 +07:00
|
|
|
printed += fprintf(fp, " %s (%d), ", thread__comm_str(thread), thread->tid);
|
2013-11-12 21:42:14 +07:00
|
|
|
printed += fprintf(fp, "%lu events, ", ttrace->nr_events);
|
2013-11-14 23:43:30 +07:00
|
|
|
printed += fprintf(fp, "%.1f%%", ratio);
|
2014-07-09 01:05:16 +07:00
|
|
|
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>
2016-05-06 01:46:50 +07:00
|
|
|
if (trace->sched)
|
|
|
|
printed += fprintf(fp, ", %.3f msec\n", ttrace->runtime_ms);
|
|
|
|
else if (fputc('\n', fp) != EOF)
|
|
|
|
++printed;
|
|
|
|
|
2013-10-09 10:26:53 +07:00
|
|
|
printed += thread__dump_stats(ttrace, trace, fp);
|
2013-09-29 02:12:59 +07:00
|
|
|
|
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 22:47:16 +07:00
|
|
|
return printed;
|
|
|
|
}
|
2013-09-29 02:12:59 +07:00
|
|
|
|
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 22:47:16 +07:00
|
|
|
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);
|
2013-09-29 02:12:59 +07:00
|
|
|
}
|
|
|
|
|
2012-10-18 03:13:12 +07:00
|
|
|
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 22:47:16 +07:00
|
|
|
size_t printed = trace__fprintf_threads_header(fp);
|
|
|
|
struct rb_node *nd;
|
2017-09-11 09:23:14 +07:00
|
|
|
int i;
|
2012-10-18 03:13:12 +07:00
|
|
|
|
2017-09-11 09:23:14 +07:00
|
|
|
for (i = 0; i < THREADS__TABLE_SIZE; i++) {
|
|
|
|
DECLARE_RESORT_RB_MACHINE_THREADS(threads, trace->host, i);
|
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 22:47:16 +07:00
|
|
|
|
2017-09-11 09:23:14 +07:00
|
|
|
if (threads == NULL) {
|
|
|
|
fprintf(fp, "%s", "Error sorting output by nr_events!\n");
|
|
|
|
return 0;
|
|
|
|
}
|
2013-09-29 02:12:59 +07:00
|
|
|
|
2017-09-11 09:23:14 +07:00
|
|
|
resort_rb__for_each_entry(nd, threads)
|
|
|
|
printed += trace__fprintf_thread(fp, threads_entry->thread, trace);
|
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 22:47:16 +07:00
|
|
|
|
2017-09-11 09:23:14 +07:00
|
|
|
resort_rb__delete(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 22:47:16 +07:00
|
|
|
return printed;
|
2012-10-18 03:13:12 +07:00
|
|
|
}
|
|
|
|
|
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 19:56:00 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2018-11-07 19:38:49 +07:00
|
|
|
static int trace__set_filter_pids_from_option(const struct option *opt, const char *str,
|
|
|
|
int unset __maybe_unused)
|
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>
2015-02-22 02:36:52 +07:00
|
|
|
{
|
|
|
|
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 22:01:10 +07:00
|
|
|
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 23:14:25 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
static void evlist__set_evsel_handler(struct perf_evlist *evlist, void *handler)
|
|
|
|
{
|
|
|
|
struct perf_evsel *evsel;
|
|
|
|
|
2016-06-23 21:26:15 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
evsel->handler = handler;
|
|
|
|
}
|
|
|
|
|
2018-08-03 01:09:24 +07:00
|
|
|
static int evlist__set_syscall_tp_fields(struct perf_evlist *evlist)
|
|
|
|
{
|
|
|
|
struct perf_evsel *evsel;
|
|
|
|
|
|
|
|
evlist__for_each_entry(evlist, evsel) {
|
|
|
|
if (evsel->priv || !evsel->tp_format)
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (strcmp(evsel->tp_format->system, "syscalls"))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
if (perf_evsel__init_syscall_tp(evsel))
|
|
|
|
return -1;
|
|
|
|
|
|
|
|
if (!strncmp(evsel->tp_format->name, "sys_enter_", 10)) {
|
|
|
|
struct syscall_tp *sc = evsel->priv;
|
|
|
|
|
|
|
|
if (__tp_field__init_ptr(&sc->args, sc->id.offset + sizeof(u64)))
|
|
|
|
return -1;
|
|
|
|
} else if (!strncmp(evsel->tp_format->name, "sys_exit_", 9)) {
|
|
|
|
struct syscall_tp *sc = evsel->priv;
|
|
|
|
|
|
|
|
if (__tp_field__init_uint(&sc->ret, sizeof(u64), sc->id.offset + sizeof(u64), evsel->needs_swap))
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-01-10 03:26:26 +07:00
|
|
|
/*
|
|
|
|
* 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, };
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
int len = strlen(str) + 1, err = -1, list, idx;
|
2017-01-10 03:26:26 +07:00
|
|
|
char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
|
|
|
|
char group_name[PATH_MAX];
|
2018-10-26 03:24:45 +07:00
|
|
|
struct syscall_fmt *fmt;
|
2017-01-10 03:26:26 +07:00
|
|
|
|
|
|
|
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;
|
perf trace: Support syscall name globbing
So now we can use:
# perf trace -e pkey_*
532.784 ( 0.006 ms): pkey/16018 pkey_alloc(init_val: DISABLE_WRITE) = -1 EINVAL Invalid argument
532.795 ( 0.004 ms): pkey/16018 pkey_mprotect(start: 0x7f380d0a6000, len: 4096, prot: READ|WRITE, pkey: -1) = 0
532.801 ( 0.002 ms): pkey/16018 pkey_free(pkey: -1 ) = -1 EINVAL Invalid argument
^C[root@jouet ~]#
Or '-e epoll*', '-e *msg*', etc.
Combining syscall names with perf events, tracepoints, etc, continues to
be valid, i.e. this is possible:
# perf probe -L sys_nanosleep
<SyS_nanosleep@/home/acme/git/linux/kernel/time/hrtimer.c:0>
0 SYSCALL_DEFINE2(nanosleep, struct timespec __user *, rqtp,
struct timespec __user *, rmtp)
{
struct timespec64 tu;
5 if (get_timespec64(&tu, rqtp))
6 return -EFAULT;
if (!timespec64_valid(&tu))
9 return -EINVAL;
11 current->restart_block.nanosleep.type = rmtp ? TT_NATIVE : TT_NONE;
12 current->restart_block.nanosleep.rmtp = rmtp;
13 return hrtimer_nanosleep(&tu, HRTIMER_MODE_REL, CLOCK_MONOTONIC);
}
# perf probe my_probe="sys_nanosleep:12 rmtp"
Added new event:
probe:my_probe (on sys_nanosleep:12 with rmtp)
You can now use it in all perf tools, such as:
perf record -e probe:my_probe -aR sleep 1
#
# perf trace -e probe:my_probe/max-stack=5/,*sleep sleep 1
0.427 ( 0.003 ms): sleep/16690 nanosleep(rqtp: 0x7ffefc245090) ...
0.430 ( ): probe:my_probe:(ffffffffbd112923) rmtp=0)
sys_nanosleep ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
return_from_SYSCALL_64 ([kernel.kallsyms])
__nanosleep_nocancel (/usr/lib64/libc-2.25.so)
0.427 (1000.208 ms): sleep/16690 ... [continued]: nanosleep()) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.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-elycoi8wy6y0w9dkj7ox1mzz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-08-31 21:50:04 +07:00
|
|
|
if (syscalltbl__id(trace->sctbl, s) >= 0 ||
|
|
|
|
syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
|
2017-01-10 03:26:26 +07:00
|
|
|
list = 1;
|
2018-10-26 03:24:45 +07:00
|
|
|
goto do_concat;
|
|
|
|
}
|
|
|
|
|
|
|
|
fmt = syscall_fmt__find_by_alias(s);
|
|
|
|
if (fmt != NULL) {
|
|
|
|
list = 1;
|
|
|
|
s = fmt->name;
|
2017-01-10 03:26:26 +07:00
|
|
|
} else {
|
|
|
|
path__join(group_name, sizeof(group_name), strace_groups_dir, s);
|
|
|
|
if (access(group_name, R_OK) == 0)
|
|
|
|
list = 1;
|
|
|
|
}
|
2018-10-26 03:24:45 +07:00
|
|
|
do_concat:
|
2017-01-10 03:26:26 +07:00
|
|
|
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;
|
perf trace: Do not require --no-syscalls to suppress strace like output
So far the --syscalls option was the default, requiring explicit
--no-syscalls when wanting to process just some other event, invert that
and assume it only when no other event was specified, allowing its
explicit enablement when wanting to see all syscalls together with some
other event:
E.g:
The existing default is maintained for a single workload:
# perf trace sleep 1
<SNIP>
0.264 ( 0.003 ms): sleep/12762 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f62cbf04000
0.271 ( 0.001 ms): sleep/12762 close(fd: 3) = 0
0.295 (1000.130 ms): sleep/12762 nanosleep(rqtp: 0x7ffd15194fd0) = 0
1000.469 ( 0.006 ms): sleep/12762 close(fd: 1) = 0
1000.480 ( 0.004 ms): sleep/12762 close(fd: 2) = 0
1000.502 ( ): sleep/12762 exit_group()
#
For a pid:
# pidof ssh
7826 3961 3226 2628 2493
# perf trace -p 3961
? ( ): ... [continued]: select()) = 1
0.023 ( 0.005 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce870 ) = 0
0.036 ( 0.009 ms): read(fd: 5</dev/pts/7>, buf: 0x7ffcc8fca7b0, count: 16384 ) = 3
0.060 ( 0.004 ms): getpid( ) = 3961 (ssh)
0.079 ( 0.004 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce8e0 ) = 0
0.088 ( 0.003 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce7c0 ) = 0
<SNIP>
For system wide, threads, cgroups, user, etc when no event is specified,
the existing behaviour is maintained, i.e. --syscalls is selected.
When some event is specified, then --no-syscalls doesn't need to be
specified:
# perf trace -e tcp:tcp_probe ssh localhost
0.000 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=53 snd_nxt=0xb67ce8f7 snd_una=0xb67ce8f7 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43690
0.010 tcp:tcp_probe:src=[::1]:39074 dest=[::1]:22 mark=0 length=32 snd_nxt=0xa8f9ef38 snd_una=0xa8f9ef23 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43690 srtt=31 rcv_wnd=43776
4.525 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=1240 snd_nxt=0xb67ce90c snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43776
7.242 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=80 snd_nxt=0xb67ced44 snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=174720
The authenticity of host 'localhost (::1)' can't be established.
ECDSA key fingerprint is SHA256:TKZS58923458203490asekfjaklskljmkjfgPMBfHzY.
ECDSA key fingerprint is MD5:d8:29:54:40:71:fa:b8:44:89:52:64:8a:35:42:d0:e8.
Are you sure you want to continue connecting (yes/no)?
^C
#
To get the previous behaviour just use --syscalls and get all syscalls formatted
strace like + the specified extra events:
# trace -e sched:*switch --syscalls sleep 1
<SNIP>
0.160 ( 0.003 ms): sleep/12877 mprotect(start: 0x7fdfe2361000, len: 4096, prot: READ) = 0
0.164 ( 0.009 ms): sleep/12877 munmap(addr: 0x7fdfe2345000, len: 113155) = 0
0.211 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce68e000
0.212 ( 0.002 ms): sleep/12877 brk(brk: 0x55d3ce6af000) = 0x55d3ce6af000
0.215 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce6af000
0.219 ( 0.004 ms): sleep/12877 open(filename: 0xe1f07c00, flags: CLOEXEC) = 3
0.225 ( 0.001 ms): sleep/12877 fstat(fd: 3, statbuf: 0x7fdfe2138aa0) = 0
0.227 ( 0.003 ms): sleep/12877 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7fdfdb1b8000
0.234 ( 0.001 ms): sleep/12877 close(fd: 3) = 0
0.257 ( ): sleep/12877 nanosleep(rqtp: 0x7fffb36b6020) ...
0.260 ( ): sched:sched_switch:prev_comm=sleep prev_pid=12877 prev_prio=120 prev_state=D ==> next_comm=swapper/3 next_pid=0 next_prio=120
0.257 (1000.134 ms): sleep/12877 ... [continued]: nanosleep()) = 0
1000.428 ( 0.006 ms): sleep/12877 close(fd: 1) = 0
1000.440 ( 0.004 ms): sleep/12877 close(fd: 2) = 0
1000.461 ( ): sleep/12877 exit_group()
#
When specifiying just some syscalls, the behaviour doesn't change, i.e.:
# trace -e nanosleep -e sched:*switch sleep 1
0.000 ( ): sleep/14974 nanosleep(rqtp: 0x7ffc344ba9c0 ) ...
0.007 ( ): sched:sched_switch:prev_comm=sleep prev_pid=14974 prev_prio=120 prev_state=D ==> next_comm=swapper/2 next_pid=0 next_prio=120
0.000 (1000.139 ms): sleep/14974 ... [continued]: nanosleep()) = 0
#
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: https://lkml.kernel.org/n/tip-om2fulll97ytnxv40ler8jkf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 02:20:28 +07:00
|
|
|
trace->trace_syscalls = true;
|
2017-01-10 03:26:26 +07:00
|
|
|
}
|
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
static int trace__parse_cgroups(const struct option *opt, const char *str, int unset)
|
|
|
|
{
|
|
|
|
struct trace *trace = opt->value;
|
|
|
|
|
|
|
|
if (!list_empty(&trace->evlist->entries))
|
|
|
|
return parse_cgroups(opt, str, unset);
|
|
|
|
|
|
|
|
trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-11-07 20:04:51 +07:00
|
|
|
static struct bpf_map *bpf__find_map_by_name(const char *name)
|
|
|
|
{
|
|
|
|
struct bpf_object *obj, *tmp;
|
|
|
|
|
|
|
|
bpf_object__for_each_safe(obj, tmp) {
|
|
|
|
struct bpf_map *map = bpf_object__find_map_by_name(obj, name);
|
|
|
|
if (map)
|
|
|
|
return map;
|
|
|
|
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static void trace__set_bpf_map_filtered_pids(struct trace *trace)
|
|
|
|
{
|
|
|
|
trace->filter_pids.map = bpf__find_map_by_name("pids_filtered");
|
|
|
|
}
|
|
|
|
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
static void trace__set_bpf_map_syscalls(struct trace *trace)
|
|
|
|
{
|
|
|
|
trace->syscalls.map = bpf__find_map_by_name("syscalls");
|
|
|
|
}
|
|
|
|
|
perf trace: Allow specifying a set of events to add in perfconfig
To add augmented_raw_syscalls to the events speficied by the user, or be
the only one if no events were specified by the user, one can add this
to perfconfig:
# cat ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
#
I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it
always load, this way:
# perf trace -e open* cat /etc/passwd > /dev/null
0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 03:30:20 +07:00
|
|
|
static int trace__config(const char *var, const char *value, void *arg)
|
|
|
|
{
|
2018-12-14 20:12:09 +07:00
|
|
|
struct trace *trace = arg;
|
perf trace: Allow specifying a set of events to add in perfconfig
To add augmented_raw_syscalls to the events speficied by the user, or be
the only one if no events were specified by the user, one can add this
to perfconfig:
# cat ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
#
I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it
always load, this way:
# perf trace -e open* cat /etc/passwd > /dev/null
0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 03:30:20 +07:00
|
|
|
int err = 0;
|
|
|
|
|
|
|
|
if (!strcmp(var, "trace.add_events")) {
|
|
|
|
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, value, 0);
|
perf trace: Allow configuring if the syscall start timestamp should be printed
# trace -e open*,close,*sleep sleep 1
0.000 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
0.016 close(fd: 3 ) = 0
0.024 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
0.074 close(fd: 3 ) = 0
0.235 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.251 close(fd: 3 ) = 0
0.285 nanosleep(rqtp: 0x7ffd68e6d620, rmtp: 0 ) = 0
1000.386 close(fd: 1 ) = 0
1000.395 close(fd: 2 ) = 0
#
# perf config trace.show_timestamp=no
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: , flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7fffa79c38e0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mjjnicy48367jah6ls4k0nk8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:17:19 +07:00
|
|
|
} else if (!strcmp(var, "trace.show_timestamp")) {
|
|
|
|
trace->show_tstamp = perf_config_bool(var, value);
|
2018-12-14 20:22:18 +07:00
|
|
|
} else if (!strcmp(var, "trace.show_duration")) {
|
|
|
|
trace->show_duration = perf_config_bool(var, value);
|
perf trace: Allow suppressing the syscall argument names
To show just the values:
Default:
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Remove it:
# perf config trace.show_arg_names=no
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3
close(3 ) = 0
nanosleep(0x7ffced3a8c40, 0 ) = 0
close(1 ) = 0
close(2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:32:02 +07:00
|
|
|
} else if (!strcmp(var, "trace.show_arg_names")) {
|
|
|
|
trace->show_arg_names = perf_config_bool(var, value);
|
|
|
|
if (!trace->show_arg_names)
|
|
|
|
trace->show_zeros = true;
|
2018-12-14 20:12:09 +07:00
|
|
|
} else if (!strcmp(var, "trace.show_zeros")) {
|
perf trace: Allow suppressing the syscall argument names
To show just the values:
Default:
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Remove it:
# perf config trace.show_arg_names=no
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3
close(3 ) = 0
nanosleep(0x7ffced3a8c40, 0 ) = 0
close(1 ) = 0
close(2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:32:02 +07:00
|
|
|
bool new_show_zeros = perf_config_bool(var, value);
|
|
|
|
if (!trace->show_arg_names && !new_show_zeros) {
|
|
|
|
pr_warning("trace.show_zeros has to be set when trace.show_arg_names=no\n");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
trace->show_zeros = new_show_zeros;
|
perf trace: Allow asking for not suppressing common string prefixes
So far we've been suppressing common stuff such as "MAP_" in the mmap
flags, showing "SHARED" instead of "MAP_SHARED", allow for those
prefixes (and a few suffixes) to be shown:
# trace -e *map,open*,*seek sleep 1
openat("/etc/ld.so.cache", CLOEXEC) = 3
mmap(0, 109093, READ, PRIVATE, 3, 0) = 0x7ff61c695000
openat("/lib64/libc.so.6", CLOEXEC) = 3
lseek(3, 792, SET) = 792
mmap(0, 8192, READ|WRITE, PRIVATE|ANONYMOUS) = 0x7ff61c693000
lseek(3, 792, SET) = 792
lseek(3, 864, SET) = 864
mmap(0, 1857568, READ, PRIVATE|DENYWRITE, 3, 0) = 0x7ff61c4cd000
mmap(0x7ff61c4ef000, 1363968, EXEC|READ, PRIVATE|FIXED|DENYWRITE, 3, 139264) = 0x7ff61c4ef000
mmap(0x7ff61c63c000, 311296, READ, PRIVATE|FIXED|DENYWRITE, 3, 1503232) = 0x7ff61c63c000
mmap(0x7ff61c689000, 24576, READ|WRITE, PRIVATE|FIXED|DENYWRITE, 3, 1814528) = 0x7ff61c689000
mmap(0x7ff61c68f000, 14368, READ|WRITE, PRIVATE|FIXED|ANONYMOUS) = 0x7ff61c68f000
munmap(0x7ff61c695000, 109093) = 0
openat("/usr/lib/locale/locale-archive", CLOEXEC) = 3
mmap(0, 217749968, READ, PRIVATE, 3, 0) = 0x7ff60f523000
#
# vim ~/.perfconfig
#
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
trace.string_quote="
trace.show_prefix=yes
#
#
# trace -e *map,open*,*seek sleep 1
openat(AT_FDCWD, "/etc/ld.so.cache", O_CLOEXEC) = 3
mmap(0, 109093, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7ebbe59000
openat(AT_FDCWD, "/lib64/libc.so.6", O_CLOEXEC) = 3
lseek(3, 792, SEEK_SET) = 792
mmap(0, 8192, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS) = 0x7f7ebbe57000
lseek(3, 792, SEEK_SET) = 792
lseek(3, 864, SEEK_SET) = 864
mmap(0, 1857568, PROT_READ, MAP_PRIVATE|MAP_DENYWRITE, 3, 0) = 0x7f7ebbc91000
mmap(0x7f7ebbcb3000, 1363968, PROT_EXEC|PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 139264) = 0x7f7ebbcb3000
mmap(0x7f7ebbe00000, 311296, PROT_READ, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1503232) = 0x7f7ebbe00000
mmap(0x7f7ebbe4d000, 24576, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_DENYWRITE, 3, 1814528) = 0x7f7ebbe4d000
mmap(0x7f7ebbe53000, 14368, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_FIXED|MAP_ANONYMOUS) = 0x7f7ebbe53000
munmap(0x7f7ebbe59000, 109093) = 0
openat(AT_FDCWD, "/usr/lib/locale/locale-archive", O_CLOEXEC) = 3
mmap(0, 217749968, PROT_READ, MAP_PRIVATE, 3, 0) = 0x7f7eaece7000
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mtn1i4rjowjl72trtnbmvjd4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-15 03:06:47 +07:00
|
|
|
} else if (!strcmp(var, "trace.show_prefix")) {
|
|
|
|
trace->show_string_prefix = perf_config_bool(var, value);
|
perf trace: Allow configuring default for perf_event_attr.inherit
I.f. if children should inherit the parent perf_event configuration,
i.e. if we should trace children as well or just the parent.
The default is to follow children, to disable this and have a behaviour
similar to strace, set this config option or use the --no_inherit 'perf
trace' option.
E.g.:
Default:
# perf config trace.no_inherit
# trace -e clone,*sleep time sleep 1
0.000 time/21107 clone(clone_flags: CHILD_CLEARTID|CHILD_SETTID|0x11, newsp: 0, child_tidptr: 0x7f7b8f9ae810) = 21108 (time)
? time/21108 ... [continued]: clone()
0.691 sleep/21108 nanosleep(rqtp: 0x7ffed01d0540, rmtp: 0 ) = 0
0.00user 0.00system 0:01.00elapsed 0%CPU (0avgtext+0avgdata 1988maxresident)k
0inputs+0outputs (0major+76minor)pagefaults 0swaps
#
Disable it:
# trace -e clone,*sleep time sleep 1
0.000 clone(clone_flags: CHILD_CLEARTID|CHILD_SETTID|0x11, newsp: 0, child_tidptr: 0x7ff41e100810) = 21414 (time)
0.00user 0.00system 0:01.00elapsed 0%CPU (0avgtext+0avgdata 1964maxresident)k
0inputs+0outputs (0major+76minor)pagefaults 0swaps
#
Notice that since there is just one thread, the "comm/TID" column is
suppressed.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-thd8s16pagyza71ufi5vjlan@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:06:16 +07:00
|
|
|
} else if (!strcmp(var, "trace.no_inherit")) {
|
|
|
|
trace->opts.no_inherit = perf_config_bool(var, value);
|
perf trace: Make the alignment of the syscall args be configurable
Since the start 'perf trace' aligns the parens enclosing the list of
syscall args to align the syscall results, allow this to be
configurable, keeping the default of 70. Using:
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC) = 3
close(3) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC) = 3
close(3) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC) = 3
close(3) = 0
nanosleep(0x7ffc00de66f0, 0) = 0
close(1) = 0
close(2) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-r8cbhoz1lr5npq9tutpvoigr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 23:40:49 +07:00
|
|
|
} else if (!strcmp(var, "trace.args_alignment")) {
|
|
|
|
int args_alignment = 0;
|
|
|
|
if (perf_config_int(&args_alignment, var, value) == 0)
|
|
|
|
trace->args_alignment = args_alignment;
|
perf trace: Allow specifying a set of events to add in perfconfig
To add augmented_raw_syscalls to the events speficied by the user, or be
the only one if no events were specified by the user, one can add this
to perfconfig:
# cat ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
#
I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it
always load, this way:
# perf trace -e open* cat /etc/passwd > /dev/null
0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 03:30:20 +07:00
|
|
|
}
|
perf trace: Allow suppressing the syscall argument names
To show just the values:
Default:
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Remove it:
# perf config trace.show_arg_names=no
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3
close(3 ) = 0
nanosleep(0x7ffced3a8c40, 0 ) = 0
close(1 ) = 0
close(2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:32:02 +07:00
|
|
|
out:
|
perf trace: Allow specifying a set of events to add in perfconfig
To add augmented_raw_syscalls to the events speficied by the user, or be
the only one if no events were specified by the user, one can add this
to perfconfig:
# cat ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
#
I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it
always load, this way:
# perf trace -e open* cat /etc/passwd > /dev/null
0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 03:30:20 +07:00
|
|
|
return err;
|
|
|
|
}
|
|
|
|
|
2017-03-27 21:47:20 +07:00
|
|
|
int cmd_trace(int argc, const char **argv)
|
2012-09-27 06:05:56 +07:00
|
|
|
{
|
2015-03-18 20:35:57 +07:00
|
|
|
const char *trace_usage[] = {
|
2012-10-05 12:02:16 +07:00
|
|
|
"perf trace [<options>] [<command>]",
|
|
|
|
"perf trace [<options>] -- <command> [<options>]",
|
2013-09-29 02:13:01 +07:00
|
|
|
"perf trace record [<options>] [<command>]",
|
|
|
|
"perf trace record [<options>] -- <command> [<options>]",
|
2012-09-27 06:05:56 +07:00
|
|
|
NULL
|
|
|
|
};
|
|
|
|
struct trace trace = {
|
|
|
|
.syscalls = {
|
|
|
|
. max = -1,
|
|
|
|
},
|
|
|
|
.opts = {
|
|
|
|
.target = {
|
|
|
|
.uid = UINT_MAX,
|
|
|
|
.uses_mmap = true,
|
|
|
|
},
|
|
|
|
.user_freq = UINT_MAX,
|
|
|
|
.user_interval = ULLONG_MAX,
|
2014-01-15 03:52:14 +07:00
|
|
|
.no_buffering = true,
|
2014-12-13 03:28:32 +07:00
|
|
|
.mmap_pages = UINT_MAX,
|
2012-09-27 06:05:56 +07:00
|
|
|
},
|
2015-08-06 02:52:23 +07:00
|
|
|
.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 22:35:21 +07:00
|
|
|
.show_comm = true,
|
perf trace: Allow configuring if the syscall start timestamp should be printed
# trace -e open*,close,*sleep sleep 1
0.000 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
0.016 close(fd: 3 ) = 0
0.024 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
0.074 close(fd: 3 ) = 0
0.235 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.251 close(fd: 3 ) = 0
0.285 nanosleep(rqtp: 0x7ffd68e6d620, rmtp: 0 ) = 0
1000.386 close(fd: 1 ) = 0
1000.395 close(fd: 2 ) = 0
#
# perf config trace.show_timestamp=no
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: , flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7fffa79c38e0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-mjjnicy48367jah6ls4k0nk8@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:17:19 +07:00
|
|
|
.show_tstamp = true,
|
2018-12-14 20:22:18 +07:00
|
|
|
.show_duration = true,
|
perf trace: Allow suppressing the syscall argument names
To show just the values:
Default:
# trace -e open*,close,*sleep sleep 1
openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC ) = 3
close(fd: 3 ) = 0
openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
close(fd: 3 ) = 0
nanosleep(rqtp: 0x7ffc0c4ea0d0, rmtp: 0 ) = 0
close(fd: 1 ) = 0
close(fd: 2 ) = 0
#
Remove it:
# perf config trace.show_arg_names=no
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC ) = 3
close(3 ) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC ) = 3
close(3 ) = 0
nanosleep(0x7ffced3a8c40, 0 ) = 0
close(1 ) = 0
close(2 ) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-ta9tbdwgodpw719sr2bjm8eb@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 21:32:02 +07:00
|
|
|
.show_arg_names = true,
|
perf trace: Make the alignment of the syscall args be configurable
Since the start 'perf trace' aligns the parens enclosing the list of
syscall args to align the syscall results, allow this to be
configurable, keeping the default of 70. Using:
# perf config
llvm.dump-obj=true
trace.add_events=/home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
trace.show_zeros=yes
trace.show_duration=no
trace.no_inherit=yes
trace.show_timestamp=no
trace.show_arg_names=no
trace.args_alignment=0
# trace -e open*,close,*sleep sleep 1
openat(CWD, /etc/ld.so.cache, CLOEXEC) = 3
close(3) = 0
openat(CWD, /lib64/libc.so.6, CLOEXEC) = 3
close(3) = 0
openat(CWD, /usr/lib/locale/locale-archive, CLOEXEC) = 3
close(3) = 0
nanosleep(0x7ffc00de66f0, 0) = 0
close(1) = 0
close(2) = 0
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-r8cbhoz1lr5npq9tutpvoigr@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 23:40:49 +07:00
|
|
|
.args_alignment = 70,
|
perf trace: Do not require --no-syscalls to suppress strace like output
So far the --syscalls option was the default, requiring explicit
--no-syscalls when wanting to process just some other event, invert that
and assume it only when no other event was specified, allowing its
explicit enablement when wanting to see all syscalls together with some
other event:
E.g:
The existing default is maintained for a single workload:
# perf trace sleep 1
<SNIP>
0.264 ( 0.003 ms): sleep/12762 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f62cbf04000
0.271 ( 0.001 ms): sleep/12762 close(fd: 3) = 0
0.295 (1000.130 ms): sleep/12762 nanosleep(rqtp: 0x7ffd15194fd0) = 0
1000.469 ( 0.006 ms): sleep/12762 close(fd: 1) = 0
1000.480 ( 0.004 ms): sleep/12762 close(fd: 2) = 0
1000.502 ( ): sleep/12762 exit_group()
#
For a pid:
# pidof ssh
7826 3961 3226 2628 2493
# perf trace -p 3961
? ( ): ... [continued]: select()) = 1
0.023 ( 0.005 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce870 ) = 0
0.036 ( 0.009 ms): read(fd: 5</dev/pts/7>, buf: 0x7ffcc8fca7b0, count: 16384 ) = 3
0.060 ( 0.004 ms): getpid( ) = 3961 (ssh)
0.079 ( 0.004 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce8e0 ) = 0
0.088 ( 0.003 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce7c0 ) = 0
<SNIP>
For system wide, threads, cgroups, user, etc when no event is specified,
the existing behaviour is maintained, i.e. --syscalls is selected.
When some event is specified, then --no-syscalls doesn't need to be
specified:
# perf trace -e tcp:tcp_probe ssh localhost
0.000 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=53 snd_nxt=0xb67ce8f7 snd_una=0xb67ce8f7 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43690
0.010 tcp:tcp_probe:src=[::1]:39074 dest=[::1]:22 mark=0 length=32 snd_nxt=0xa8f9ef38 snd_una=0xa8f9ef23 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43690 srtt=31 rcv_wnd=43776
4.525 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=1240 snd_nxt=0xb67ce90c snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43776
7.242 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=80 snd_nxt=0xb67ced44 snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=174720
The authenticity of host 'localhost (::1)' can't be established.
ECDSA key fingerprint is SHA256:TKZS58923458203490asekfjaklskljmkjfgPMBfHzY.
ECDSA key fingerprint is MD5:d8:29:54:40:71:fa:b8:44:89:52:64:8a:35:42:d0:e8.
Are you sure you want to continue connecting (yes/no)?
^C
#
To get the previous behaviour just use --syscalls and get all syscalls formatted
strace like + the specified extra events:
# trace -e sched:*switch --syscalls sleep 1
<SNIP>
0.160 ( 0.003 ms): sleep/12877 mprotect(start: 0x7fdfe2361000, len: 4096, prot: READ) = 0
0.164 ( 0.009 ms): sleep/12877 munmap(addr: 0x7fdfe2345000, len: 113155) = 0
0.211 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce68e000
0.212 ( 0.002 ms): sleep/12877 brk(brk: 0x55d3ce6af000) = 0x55d3ce6af000
0.215 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce6af000
0.219 ( 0.004 ms): sleep/12877 open(filename: 0xe1f07c00, flags: CLOEXEC) = 3
0.225 ( 0.001 ms): sleep/12877 fstat(fd: 3, statbuf: 0x7fdfe2138aa0) = 0
0.227 ( 0.003 ms): sleep/12877 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7fdfdb1b8000
0.234 ( 0.001 ms): sleep/12877 close(fd: 3) = 0
0.257 ( ): sleep/12877 nanosleep(rqtp: 0x7fffb36b6020) ...
0.260 ( ): sched:sched_switch:prev_comm=sleep prev_pid=12877 prev_prio=120 prev_state=D ==> next_comm=swapper/3 next_pid=0 next_prio=120
0.257 (1000.134 ms): sleep/12877 ... [continued]: nanosleep()) = 0
1000.428 ( 0.006 ms): sleep/12877 close(fd: 1) = 0
1000.440 ( 0.004 ms): sleep/12877 close(fd: 2) = 0
1000.461 ( ): sleep/12877 exit_group()
#
When specifiying just some syscalls, the behaviour doesn't change, i.e.:
# trace -e nanosleep -e sched:*switch sleep 1
0.000 ( ): sleep/14974 nanosleep(rqtp: 0x7ffc344ba9c0 ) ...
0.007 ( ): sched:sched_switch:prev_comm=sleep prev_pid=14974 prev_prio=120 prev_state=D ==> next_comm=swapper/2 next_pid=0 next_prio=120
0.000 (1000.139 ms): sleep/14974 ... [continued]: nanosleep()) = 0
#
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: https://lkml.kernel.org/n/tip-om2fulll97ytnxv40ler8jkf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 02:20:28 +07:00
|
|
|
.trace_syscalls = false,
|
2016-04-12 01:49:11 +07:00
|
|
|
.kernel_syscallchains = false,
|
2016-04-16 02:41:19 +07:00
|
|
|
.max_stack = UINT_MAX,
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
.max_events = ULONG_MAX,
|
2012-09-27 06:05:56 +07:00
|
|
|
};
|
perf trace: Allow dumping a BPF map after setting up BPF events
Initial use case:
Dumping the maps setup by tools/perf/examples/bpf/augmented_raw_syscalls.c,
which so far are just booleans, showing just non-zeroed entries:
# cat ~/.perfconfig
[llvm]
dump-obj = true
clang-opt = -g
[trace]
#add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
add_events = /wb/augmented_raw_syscalls.o
$ date
Tue Feb 19 16:29:33 -03 2019
$ ls -la /wb/augmented_raw_syscalls.o
-rwxr-xr-x. 1 root root 14048 Jan 24 12:09 /wb/augmented_raw_syscalls.o
$ file /wb/augmented_raw_syscalls.o
/wb/augmented_raw_syscalls.o: ELF 64-bit LSB relocatable, eBPF, version 1 (SYSV), with debug_info, not stripped
$
# trace -e recvmmsg,sendmmsg --map-dump foobar
ERROR: BPF map "foobar" not found
# trace -e recvmmsg,sendmmsg --map-dump filtered_pids
ERROR: BPF map "filtered_pids" not found
# trace -e recvmmsg,sendmmsg --map-dump pids_filtered
[2583] = 1,
[2267] = 1,
^Z
[1]+ Stopped trace -e recvmmsg,sendmmsg --map-dump pids_filtered
# pidof trace
2267
# ps ax|grep gnome-terminal|grep -v grep
2583 ? Ssl 58:33 /usr/libexec/gnome-terminal-server
^C
# trace -e recvmmsg,sendmmsg --map-dump syscalls
[299] = 1,
[307] = 1,
^C
# grep x64_recvmmsg arch/x86/entry/syscalls/syscall_64.tbl
299 64 recvmmsg __x64_sys_recvmmsg
# grep x64_sendmmsg arch/x86/entry/syscalls/syscall_64.tbl
307 64 sendmmsg __x64_sys_sendmmsg
#
Next step probably will be something like 'perf stat's --interval-print and
--interval-clear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-ztxj25rtx37ixo9cfajt8ocy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-20 02:17:33 +07:00
|
|
|
const char *map_dump_str = NULL;
|
2013-08-19 22:01:10 +07:00
|
|
|
const char *output_name = NULL;
|
2012-09-27 06:05:56 +07:00
|
|
|
const struct option trace_options[] = {
|
2017-01-10 03:26:26 +07:00
|
|
|
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 22:35:21 +07:00
|
|
|
OPT_BOOLEAN(0, "comm", &trace.show_comm,
|
|
|
|
"show the thread COMM next to its id"),
|
2013-09-28 04:06:19 +07:00
|
|
|
OPT_BOOLEAN(0, "tool_stats", &trace.show_tool_stats, "show tool stats"),
|
2017-01-10 03:26:26 +07:00
|
|
|
OPT_CALLBACK(0, "expr", &trace, "expr", "list of syscalls/events to trace",
|
|
|
|
trace__parse_events_option),
|
2013-08-19 22:01:10 +07:00
|
|
|
OPT_STRING('o', "output", &output_name, "file", "output file name"),
|
2013-08-29 11:29:52 +07:00
|
|
|
OPT_STRING('i', "input", &input_name, "file", "Analyze events in file"),
|
2012-09-27 06:05:56 +07:00
|
|
|
OPT_STRING('p', "pid", &trace.opts.target.pid, "pid",
|
|
|
|
"trace events on existing process id"),
|
2013-08-21 00:15:45 +07:00
|
|
|
OPT_STRING('t', "tid", &trace.opts.target.tid, "tid",
|
2012-09-27 06:05:56 +07:00
|
|
|
"trace events on existing thread id"),
|
2015-04-23 21:59:20 +07:00
|
|
|
OPT_CALLBACK(0, "filter-pids", &trace, "CSV list of pids",
|
2018-11-07 19:38:49 +07:00
|
|
|
"pids to filter (by the kernel)", trace__set_filter_pids_from_option),
|
2013-08-21 00:15:45 +07:00
|
|
|
OPT_BOOLEAN('a', "all-cpus", &trace.opts.target.system_wide,
|
2012-09-27 06:05:56 +07:00
|
|
|
"system-wide collection from all CPUs"),
|
2013-08-21 00:15:45 +07:00
|
|
|
OPT_STRING('C', "cpu", &trace.opts.target.cpu_list, "cpu",
|
2012-09-27 06:05:56 +07:00
|
|
|
"list of cpus to monitor"),
|
2013-08-29 11:29:52 +07:00
|
|
|
OPT_BOOLEAN(0, "no-inherit", &trace.opts.no_inherit,
|
2012-09-27 06:05:56 +07:00
|
|
|
"child tasks do not inherit counters"),
|
2013-09-01 17:36:12 +07:00
|
|
|
OPT_CALLBACK('m', "mmap-pages", &trace.opts.mmap_pages, "pages",
|
|
|
|
"number of mmap data pages",
|
|
|
|
perf_evlist__parse_mmap_pages),
|
2013-08-21 00:15:45 +07:00
|
|
|
OPT_STRING('u', "uid", &trace.opts.target.uid_str, "user",
|
2012-09-27 06:05:56 +07:00
|
|
|
"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 19:56:00 +07:00
|
|
|
OPT_CALLBACK(0, "duration", &trace, "float",
|
|
|
|
"show only events with duration > N.M ms",
|
|
|
|
trace__set_duration),
|
perf trace: Allow dumping a BPF map after setting up BPF events
Initial use case:
Dumping the maps setup by tools/perf/examples/bpf/augmented_raw_syscalls.c,
which so far are just booleans, showing just non-zeroed entries:
# cat ~/.perfconfig
[llvm]
dump-obj = true
clang-opt = -g
[trace]
#add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
add_events = /wb/augmented_raw_syscalls.o
$ date
Tue Feb 19 16:29:33 -03 2019
$ ls -la /wb/augmented_raw_syscalls.o
-rwxr-xr-x. 1 root root 14048 Jan 24 12:09 /wb/augmented_raw_syscalls.o
$ file /wb/augmented_raw_syscalls.o
/wb/augmented_raw_syscalls.o: ELF 64-bit LSB relocatable, eBPF, version 1 (SYSV), with debug_info, not stripped
$
# trace -e recvmmsg,sendmmsg --map-dump foobar
ERROR: BPF map "foobar" not found
# trace -e recvmmsg,sendmmsg --map-dump filtered_pids
ERROR: BPF map "filtered_pids" not found
# trace -e recvmmsg,sendmmsg --map-dump pids_filtered
[2583] = 1,
[2267] = 1,
^Z
[1]+ Stopped trace -e recvmmsg,sendmmsg --map-dump pids_filtered
# pidof trace
2267
# ps ax|grep gnome-terminal|grep -v grep
2583 ? Ssl 58:33 /usr/libexec/gnome-terminal-server
^C
# trace -e recvmmsg,sendmmsg --map-dump syscalls
[299] = 1,
[307] = 1,
^C
# grep x64_recvmmsg arch/x86/entry/syscalls/syscall_64.tbl
299 64 recvmmsg __x64_sys_recvmmsg
# grep x64_sendmmsg arch/x86/entry/syscalls/syscall_64.tbl
307 64 sendmmsg __x64_sys_sendmmsg
#
Next step probably will be something like 'perf stat's --interval-print and
--interval-clear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-ztxj25rtx37ixo9cfajt8ocy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-20 02:17:33 +07:00
|
|
|
#ifdef HAVE_LIBBPF_SUPPORT
|
|
|
|
OPT_STRING(0, "map-dump", &map_dump_str, "BPF map", "BPF map to periodically dump"),
|
|
|
|
#endif
|
2012-10-18 03:13:12 +07:00
|
|
|
OPT_BOOLEAN(0, "sched", &trace.sched, "show blocking scheduler events"),
|
2013-08-23 02:49:54 +07:00
|
|
|
OPT_INCR('v', "verbose", &verbose, "be more verbose"),
|
2013-09-05 01:37:43 +07:00
|
|
|
OPT_BOOLEAN('T', "time", &trace.full_time,
|
|
|
|
"Show full timestamp, not time relative to first start"),
|
perf trace: Show only failing syscalls
For instance:
# 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
# perf trace --failure sleep 1
0.043 ( 0.010 ms): sleep/10978 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
For reference, here are all the syscalls in this case:
# perf trace sleep 1
? ( ): sleep/10976 ... [continued]: execve()) = 0
0.027 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.044 ( 0.010 ms): sleep/10976 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
0.057 ( 0.006 ms): sleep/10976 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.064 ( 0.002 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b370) = 0
0.067 ( 0.003 ms): sleep/10976 mmap(len: 111457, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec8615000
0.071 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.080 ( 0.007 ms): sleep/10976 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.088 ( 0.002 ms): sleep/10976 read(fd: 3, buf: 0x7fffac22b538, count: 832) = 832
0.092 ( 0.001 ms): sleep/10976 fstat(fd: 3, statbuf: 0x7fffac22b3d0) = 0
0.094 ( 0.002 ms): sleep/10976 mmap(len: 8192, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS) = 0x7feec8613000
0.099 ( 0.004 ms): sleep/10976 mmap(len: 3889792, prot: EXEC|READ, flags: PRIVATE|DENYWRITE, fd: 3) = 0x7feec8057000
0.104 ( 0.007 ms): sleep/10976 mprotect(start: 0x7feec8203000, len: 2097152) = 0
0.112 ( 0.005 ms): sleep/10976 mmap(addr: 0x7feec8403000, len: 24576, prot: READ|WRITE, flags: PRIVATE|DENYWRITE|FIXED, fd: 3, off: 1753088) = 0x7feec8403000
0.120 ( 0.003 ms): sleep/10976 mmap(addr: 0x7feec8409000, len: 14976, prot: READ|WRITE, flags: PRIVATE|ANONYMOUS|FIXED) = 0x7feec8409000
0.128 ( 0.001 ms): sleep/10976 close(fd: 3) = 0
0.139 ( 0.001 ms): sleep/10976 arch_prctl(option: 4098, arg2: 140663540761856) = 0
0.186 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8403000, len: 16384, prot: READ) = 0
0.204 ( 0.003 ms): sleep/10976 mprotect(start: 0x55bdc0ec3000, len: 4096, prot: READ) = 0
0.209 ( 0.004 ms): sleep/10976 mprotect(start: 0x7feec8631000, len: 4096, prot: READ) = 0
0.214 ( 0.010 ms): sleep/10976 munmap(addr: 0x7feec8615000, len: 111457) = 0
0.269 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d04000
0.271 ( 0.002 ms): sleep/10976 brk(brk: 0x55bdc2d25000) = 0x55bdc2d25000
0.274 ( 0.001 ms): sleep/10976 brk() = 0x55bdc2d25000
0.278 ( 0.007 ms): sleep/10976 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.288 ( 0.001 ms): sleep/10976 fstat(fd: 3</usr/lib/locale/locale-archive>, statbuf: 0x7feec8408aa0) = 0
0.290 ( 0.003 ms): sleep/10976 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7feec1488000
0.297 ( 0.001 ms): sleep/10976 close(fd: 3</usr/lib/locale/locale-archive>) = 0
0.325 (1000.193 ms): sleep/10976 nanosleep(rqtp: 0x7fffac22c0b0) = 0
1000.560 ( 0.006 ms): sleep/10976 close(fd: 1) = 0
1000.573 ( 0.005 ms): sleep/10976 close(fd: 2) = 0
1000.596 ( ): sleep/10976 exit_group()
#
And can be done systemwide, etc, with backtraces:
# perf trace --max-stack=16 --failure sleep 1
0.048 ( 0.015 ms): sleep/11092 access(filename: /etc/ld.so.preload, mode: R) = -1 ENOENT No such file or directory
__access (inlined)
dl_main (/usr/lib64/ld-2.26.so)
#
Or for some specific syscalls:
# perf trace --max-stack=16 -e openat --failure cat /tmp/rien
cat: /tmp/rien: No such file or directory
0.251 ( 0.012 ms): cat/11106 openat(dfd: CWD, filename: /tmp/rien) = -1 ENOENT No such file or directory
__libc_open64 (inlined)
main (/usr/bin/cat)
__libc_start_main (/usr/lib64/libc-2.26.so)
_start (/usr/bin/cat)
#
Look for inotify* syscalls that fail, system wide, for 2 seconds, with backtraces:
# perf trace -a --max-stack=16 --failure -e inotify* sleep 2
819.165 ( 0.058 ms): gmain/1724 inotify_add_watch(fd: 8<anon_inode:inotify>, pathname: /home/acme/~, mask: 16789454) = -1 ENOENT No such file or directory
__GI_inotify_add_watch (inlined)
_ik_watch (/usr/lib64/libgio-2.0.so.0.5400.3)
_ip_start_watching (/usr/lib64/libgio-2.0.so.0.5400.3)
im_scan_missing (/usr/lib64/libgio-2.0.so.0.5400.3)
g_timeout_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_dispatch (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iterate.isra.23 (/usr/lib64/libglib-2.0.so.0.5400.3)
g_main_context_iteration (/usr/lib64/libglib-2.0.so.0.5400.3)
glib_worker_main (/usr/lib64/libglib-2.0.so.0.5400.3)
g_thread_proxy (/usr/lib64/libglib-2.0.so.0.5400.3)
start_thread (/usr/lib64/libpthread-2.26.so)
__GI___clone (inlined)
#
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: https://lkml.kernel.org/n/tip-8f7d3mngaxvi7tlzloz3n7cs@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-29 22:22:59 +07:00
|
|
|
OPT_BOOLEAN(0, "failure", &trace.failure_only,
|
|
|
|
"Show only syscalls that failed"),
|
2013-11-12 23:31:15 +07:00
|
|
|
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 23:14:25 +07:00
|
|
|
OPT_CALLBACK_DEFAULT('F', "pf", &trace.trace_pgfaults, "all|maj|min",
|
|
|
|
"Trace pagefaults", parse_pagefaults, "maj"),
|
2014-06-26 23:14:28 +07:00
|
|
|
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 20:47:18 +07:00
|
|
|
OPT_BOOLEAN('f', "force", &trace.force, "don't complain, do it"),
|
2016-04-08 18:34:15 +07:00
|
|
|
OPT_CALLBACK(0, "call-graph", &trace.opts,
|
|
|
|
"record_mode[,record_size]", record_callchain_help,
|
|
|
|
&record_parse_callchain_opt),
|
2016-04-12 01:49:11 +07:00
|
|
|
OPT_BOOLEAN(0, "kernel-syscall-graph", &trace.kernel_syscallchains,
|
|
|
|
"Show the kernel callchains on the syscall exit path"),
|
perf trace: Introduce --max-events
Allow stopping tracing after a number of events take place, considering
strace-like syscalls formatting as one event per enter/exit pair or when
in a multi-process tracing session a syscall is interrupted and printed
ending with '...'.
Examples included in the documentation:
Trace the first 4 open, openat or open_by_handle_at syscalls (in the future more syscalls may match here):
$ perf trace -e open* --max-events 4
[root@jouet perf]# trace -e open* --max-events 4
2272.992 ( 0.037 ms): gnome-shell/1370 openat(dfd: CWD, filename: /proc/self/stat) = 31
2277.481 ( 0.139 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
3026.398 ( 0.076 ms): gnome-shell/3039 openat(dfd: CWD, filename: /proc/self/stat) = 65
4294.665 ( 0.015 ms): sed/15879 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
$
Trace the first minor page fault when running a workload:
# perf trace -F min --max-stack=7 --max-events 1 sleep 1
0.000 ( 0.000 ms): sleep/18006 minfault [__clear_user+0x1a] => 0x5626efa56080 (?k)
__clear_user ([kernel.kallsyms])
load_elf_binary ([kernel.kallsyms])
search_binary_handler ([kernel.kallsyms])
__do_execve_file.isra.33 ([kernel.kallsyms])
__x64_sys_execve ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
#
Trace the next min page page fault to take place on the first CPU:
# perf trace -F min --call-graph=dwarf --max-events 1 --cpu 0
0.000 ( 0.000 ms): Web Content/17136 minfault [js::gc::Chunk::fetchNextDecommittedArena+0x4b] => 0x7fbe6181b000 (?.)
js::gc::FreeSpan::initAsEmpty (inlined)
js::gc::Arena::setAsNotAllocated (inlined)
js::gc::Chunk::fetchNextDecommittedArena (/usr/lib64/firefox/libxul.so)
js::gc::Chunk::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::allocateArena (/usr/lib64/firefox/libxul.so)
js::gc::ArenaLists::allocateFromArena (/usr/lib64/firefox/libxul.so)
js::gc::GCRuntime::tryNewTenuredThing<JSString, (js::AllowGC)1> (inlined)
js::AllocateString<JSString, (js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
js::Allocate<JSThinInlineString, (js::AllowGC)1> (inlined)
JSThinInlineString::new_<(js::AllowGC)1> (inlined)
AllocateInlineString<(js::AllowGC)1, unsigned char> (inlined)
js::ConcatStrings<(js::AllowGC)1> (/usr/lib64/firefox/libxul.so)
[0x18b26e6bc2bd] (/tmp/perf-17136.map)
Tracing the next four ext4 operations on a specific CPU:
# perf trace -e ext4:*/call-graph=fp/ --max-events 4 --cpu 3
0.000 mutt/3849 ext4:ext4_es_lookup_extent_enter:dev 253,2 ino 57277 lblk 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.097 mutt/3849 ext4:ext4_es_lookup_extent_exit:dev 253,2 ino 57277 found 0 [0/0) 0
ext4_es_lookup_extent ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.141 mutt/3849 ext4:ext4_ext_map_blocks_enter:dev 253,2 ino 57277 lblk 0 len 1 flags
ext4_ext_map_blocks ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
0.184 mutt/3849 ext4:ext4_ext_load_extent:dev 253,2 ino 57277 lblk 1516511 pblk 18446744071750013657
__read_extent_tree_block ([kernel.kallsyms])
__read_extent_tree_block ([kernel.kallsyms])
ext4_find_extent ([kernel.kallsyms])
ext4_ext_map_blocks ([kernel.kallsyms])
ext4_map_blocks ([kernel.kallsyms])
ext4_mpage_readpages ([kernel.kallsyms])
read_pages ([kernel.kallsyms])
__do_page_cache_readahead ([kernel.kallsyms])
ondemand_readahead ([kernel.kallsyms])
generic_file_read_iter ([kernel.kallsyms])
__vfs_read ([kernel.kallsyms])
vfs_read ([kernel.kallsyms])
ksys_read ([kernel.kallsyms])
do_syscall_64 ([kernel.kallsyms])
entry_SYSCALL_64 ([kernel.kallsyms])
read (/usr/lib64/libc-2.26.so)
#
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: Rudá Moura <ruda.moura@gmail.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-sweh107bs7ol5bzls0m4tqdz@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-10-19 02:38:27 +07:00
|
|
|
OPT_ULONG(0, "max-events", &trace.max_events,
|
|
|
|
"Set the maximum number of events to print, exit after that is reached. "),
|
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 21:10:31 +07:00
|
|
|
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."),
|
2016-04-15 04:29:08 +07:00
|
|
|
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 20:16:24 +07:00
|
|
|
"Default: kernel.perf_event_max_stack or " __stringify(PERF_MAX_STACK_DEPTH)),
|
2018-12-11 02:27:33 +07:00
|
|
|
OPT_BOOLEAN(0, "sort-events", &trace.sort_events,
|
|
|
|
"Sort batch of events before processing, use if getting out of order events"),
|
2018-01-22 21:38:54 +07:00
|
|
|
OPT_BOOLEAN(0, "print-sample", &trace.print_sample,
|
|
|
|
"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
|
2018-12-05 03:34:20 +07:00
|
|
|
OPT_UINTEGER(0, "proc-map-timeout", &proc_map_timeout,
|
2015-06-17 20:51:11 +07:00
|
|
|
"per thread proc mmap processing timeout in ms"),
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
|
|
|
|
trace__parse_cgroups),
|
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 12:43:28 +07:00
|
|
|
OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
|
|
|
|
"ms to wait before starting measurement after program "
|
|
|
|
"start"),
|
2012-09-27 06:05:56 +07:00
|
|
|
OPT_END()
|
|
|
|
};
|
2016-04-16 19:36:32 +07:00
|
|
|
bool __maybe_unused max_stack_user_set = true;
|
2016-04-16 03:52:34 +07:00
|
|
|
bool mmap_pages_user_set = true;
|
2018-08-08 02:19:05 +07:00
|
|
|
struct perf_evsel *evsel;
|
2015-03-18 20:35:57 +07:00
|
|
|
const char * const trace_subcommands[] = { "record", NULL };
|
2018-08-08 02:19:05 +07:00
|
|
|
int err = -1;
|
2012-10-05 12:02:13 +07:00
|
|
|
char bf[BUFSIZ];
|
2012-09-27 06:05:56 +07:00
|
|
|
|
2015-02-25 01:35:55 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
trace.evlist = perf_evlist__new();
|
2016-04-04 23:32:20 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
|
2016-04-04 23:32:20 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
pr_err("Not enough memory to run!\n");
|
2015-05-11 19:28:36 +07:00
|
|
|
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 22:58:57 +07:00
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
perf trace: Allow specifying a set of events to add in perfconfig
To add augmented_raw_syscalls to the events speficied by the user, or be
the only one if no events were specified by the user, one can add this
to perfconfig:
# cat ~/.perfconfig
[trace]
add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
#
I.e. pre-compile the augmented_raw_syscalls.c BPF program and make it
always load, this way:
# perf trace -e open* cat /etc/passwd > /dev/null
0.000 ( 0.013 ms): cat/31557 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.035 ( 0.007 ms): cat/31557 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.353 ( 0.009 ms): cat/31557 openat(dfd: CWD, filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.424 ( 0.006 ms): cat/31557 openat(dfd: CWD, filename: /etc/passwd) = 3
#
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-0lgj7vh64hg3ce44gsmvj7ud@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-14 03:30:20 +07:00
|
|
|
err = perf_config(trace__config, &trace);
|
|
|
|
if (err)
|
|
|
|
goto out;
|
|
|
|
|
2015-03-18 20:35:57 +07:00
|
|
|
argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
|
|
|
|
trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
|
2013-11-12 23:31:15 +07:00
|
|
|
|
perf trace: Support setting cgroups as targets
One can set a cgroup as a default cgroup to be used by all events or
set cgroups with the 'perf stat' and 'perf record' behaviour, i.e.
'-G A' will be the cgroup for events defined so far in the command line.
Here in my main machine, with a kvm instance running a rhel6 guinea pig
I have:
# ls -la /sys/fs/cgroup/perf_event/ | grep drw
drwxr-xr-x. 14 root root 360 Mar 6 12:04 ..
drwxr-xr-x. 3 root root 0 Mar 6 15:05 machine.slice
#
So I can go ahead and use that cgroup hierarchy, say lets see what
syscalls are being emitted by threads in that 'machine.slice' hierarchy
that are taking more than 100ms:
# perf trace --duration 100 -G machine.slice
0.188 (249.850 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
250.274 (249.743 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
500.224 (249.755 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
750.097 (249.934 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1000.244 (249.780 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1250.197 (249.796 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1500.124 (249.859 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
1750.076 (172.900 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
902.570 (1021.116 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
1923.825 (305.133 ms): qemu-system-x8/23667 ppoll(ufds: 0x558151e03180, nfds: 74, tsp: 0x7ffc00cd0900, sigsetsize: 8) = 1
2000.172 (229.002 ms): CPU 0/KVM/23744 ioctl(fd: 16<anon_inode:kvm-vcpu:0>, cmd: KVM_RUN) = 0
^C #
If we look inside that cgroup hierarchy we get:
# ls -la /sys/fs/cgroup/perf_event/machine.slice/ | grep drw
drwxr-xr-x. 3 root root 0 Mar 6 15:05 .
drwxr-xr-x. 2 root root 0 Mar 6 16:16 machine-qemu\x2d2\x2drhel6.sandy.scope
#
There is just one, but lets say there were more and we would want to see
5 seconds worth of syscall summary for the threads in that cgroup:
# perf trace --summary -G machine.slice/machine-qemu\\x2d2\\x2drhel6.sandy.scope/ -a sleep 5
Summary of events:
qemu-system-x86 (23667), 143858 events, 24.2%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ppoll 28492 4348.631 0.000 0.153 11.616 1.05%
futex 19661 140.801 0.001 0.007 2.993 3.20%
read 18440 68.084 0.001 0.004 1.653 4.33%
ioctl 5387 24.768 0.002 0.005 0.134 1.62%
CPU 0/KVM (23744), 449455 events, 75.8%
syscall calls total min avg max stddev
(msec) (msec) (msec) (msec) (%)
--------------- -------- --------- --------- --------- --------- ------
ioctl 148364 3401.812 0.000 0.023 11.801 1.15%
futex 36131 404.127 0.001 0.011 7.377 2.63%
writev 29452 339.688 0.003 0.012 1.740 1.36%
write 11315 45.992 0.001 0.004 0.105 1.10%
#
See the documentation about how to set more than one cgroup for
different events in the same command line.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-t126jh4occqvu0xdqlcjygex@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-07 02:30:51 +07:00
|
|
|
if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) {
|
|
|
|
usage_with_options_msg(trace_usage, trace_options,
|
|
|
|
"cgroup monitoring only available in system-wide mode");
|
|
|
|
}
|
|
|
|
|
2018-08-08 02:19:05 +07:00
|
|
|
evsel = bpf__setup_output_event(trace.evlist, "__augmented_syscalls__");
|
|
|
|
if (IS_ERR(evsel)) {
|
|
|
|
bpf__strerror_setup_output_event(trace.evlist, PTR_ERR(evsel), bf, sizeof(bf));
|
perf trace: Handle "bpf-output" events associated with "__augmented_syscalls__" BPF map
Add an example BPF script that writes syscalls:sys_enter_openat raw
tracepoint payloads augmented with the first 64 bytes of the "filename"
syscall pointer arg.
Then catch it and print it just like with things written to the
"__bpf_stdout__" map associated with a PERF_COUNT_SW_BPF_OUTPUT software
event, by just letting the default tracepoint handler in 'perf trace',
trace__event_handler(), to use bpf_output__fprintf(trace, sample), just
like it does with all other PERF_COUNT_SW_BPF_OUTPUT events, i.e. just
do a dump on the payload, so that we can check if what is being printed
has at least the first 64 bytes of the "filename" arg:
The augmented_syscalls.c eBPF script:
# cat tools/perf/examples/bpf/augmented_syscalls.c
// SPDX-License-Identifier: GPL-2.0
#include <stdio.h>
struct bpf_map SEC("maps") __augmented_syscalls__ = {
.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
.key_size = sizeof(int),
.value_size = sizeof(u32),
.max_entries = __NR_CPUS__,
};
struct syscall_enter_openat_args {
unsigned long long common_tp_fields;
long syscall_nr;
long dfd;
char *filename_ptr;
long flags;
long mode;
};
struct augmented_enter_openat_args {
struct syscall_enter_openat_args args;
char filename[64];
};
int syscall_enter(openat)(struct syscall_enter_openat_args *args)
{
struct augmented_enter_openat_args augmented_args;
probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
probe_read_str(&augmented_args.filename, sizeof(augmented_args.filename), args->filename_ptr);
perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU,
&augmented_args, sizeof(augmented_args));
return 1;
}
license(GPL);
#
So it will just prepare a raw_syscalls:sys_enter payload for the
"openat" syscall.
This will eventually be done for all syscalls with pointer args,
globally or just when the user asks, using some spec, which args of
which syscalls it wants "expanded" this way, we'll probably start with
just all the syscalls that have char * pointers with familiar names, the
ones we already handle with the probe:vfs_getname kprobe if it is in
place hooking the kernel getname_flags() function used to copy from user
the paths.
Running it we get:
# perf trace -e perf/tools/perf/examples/bpf/augmented_syscalls.c,openat cat /etc/passwd > /dev/null
0.000 ( ): __augmented_syscalls__:X?.C......................`\..................../etc/ld.so.cache..#......,....ao.k...............k......1.".........
0.006 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC
0.008 ( 0.005 ms): cat/31292 openat(dfd: CWD, filename: 0x5c600da8, flags: CLOEXEC ) = 3
0.036 ( ): __augmented_syscalls__:X?.C.......................\..................../lib64/libc.so.6......... .\....#........?.......=.C..../.".........
0.037 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC
0.039 ( 0.007 ms): cat/31292 openat(dfd: CWD, filename: 0x5c808ce0, flags: CLOEXEC ) = 3
0.323 ( ): __augmented_syscalls__:X?.C.....................P....................../etc/passwd......>.C....@................>.C.....,....ao.>.C........
0.325 ( ): syscalls:sys_enter_openat:dfd: CWD, filename: 0xe8be50d6
0.327 ( 0.004 ms): cat/31292 openat(dfd: CWD, filename: 0xe8be50d6 ) = 3
#
We need to go on optimizing this to avoid seding trash or zeroes in the
pointer content payload, using the return from bpf_probe_read_str(), but
to keep things simple at this stage and make incremental progress, lets
leave it at that for now.
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: https://lkml.kernel.org/n/tip-g360n1zbj6bkbk6q0qo11c28@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-08 01:40:13 +07:00
|
|
|
pr_err("ERROR: Setup trace syscalls enter failed: %s\n", bf);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2018-11-07 20:04:51 +07:00
|
|
|
if (evsel) {
|
2018-08-08 02:21:44 +07:00
|
|
|
trace.syscalls.events.augmented = evsel;
|
2018-11-07 20:04:51 +07:00
|
|
|
trace__set_bpf_map_filtered_pids(&trace);
|
perf trace: Implement syscall filtering in augmented_syscalls
Just another map, this time an BPF_MAP_TYPE_ARRAY, stating with
one bool per syscall, stating if it should be filtered or not.
So, with a pre-built augmented_raw_syscalls.o file, we use:
# perf trace -e open*,augmented_raw_syscalls.o
0.000 ( 0.016 ms): DNS Res~er #37/29652 openat(dfd: CWD, filename: /etc/hosts, flags: CLOEXEC ) = 138
187.039 ( 0.048 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /etc/fstab, flags: CLOEXEC ) = 11
187.348 ( 0.041 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
188.793 ( 0.036 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
189.803 ( 0.029 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
190.774 ( 0.027 ms): gsd-housekeepi/2436 openat(dfd: CWD, filename: /proc/self/mountinfo, flags: CLOEXEC ) = 11
284.620 ( 0.149 ms): DataStorage/3076 openat(dfd: CWD, filename: /home/acme/.mozilla/firefox/ina67tev.default/SiteSecurityServiceState.txt, flags: CREAT|TRUNC|WRONLY, mode: IRUGO|IWUSR|IWGRP) = 167
^C#
What is it that this gsd-housekeeping thingy needs to open
/proc/self/mountinfo four times periodically? :-)
This map will be extended to tell per-syscall parameters, i.e. how many
bytes to copy per arg, using the function signature to get the types and
then the size of those types, via BTF.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-cy222g9ucvnym3raqvxp0hpg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-12 23:39:24 +07:00
|
|
|
trace__set_bpf_map_syscalls(&trace);
|
2018-11-07 20:04:51 +07:00
|
|
|
}
|
2018-08-08 02:21:44 +07:00
|
|
|
|
2016-04-08 22:07:24 +07:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2016-04-13 02:05:02 +07:00
|
|
|
err = -1;
|
|
|
|
|
perf trace: Allow dumping a BPF map after setting up BPF events
Initial use case:
Dumping the maps setup by tools/perf/examples/bpf/augmented_raw_syscalls.c,
which so far are just booleans, showing just non-zeroed entries:
# cat ~/.perfconfig
[llvm]
dump-obj = true
clang-opt = -g
[trace]
#add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.o
add_events = /wb/augmented_raw_syscalls.o
$ date
Tue Feb 19 16:29:33 -03 2019
$ ls -la /wb/augmented_raw_syscalls.o
-rwxr-xr-x. 1 root root 14048 Jan 24 12:09 /wb/augmented_raw_syscalls.o
$ file /wb/augmented_raw_syscalls.o
/wb/augmented_raw_syscalls.o: ELF 64-bit LSB relocatable, eBPF, version 1 (SYSV), with debug_info, not stripped
$
# trace -e recvmmsg,sendmmsg --map-dump foobar
ERROR: BPF map "foobar" not found
# trace -e recvmmsg,sendmmsg --map-dump filtered_pids
ERROR: BPF map "filtered_pids" not found
# trace -e recvmmsg,sendmmsg --map-dump pids_filtered
[2583] = 1,
[2267] = 1,
^Z
[1]+ Stopped trace -e recvmmsg,sendmmsg --map-dump pids_filtered
# pidof trace
2267
# ps ax|grep gnome-terminal|grep -v grep
2583 ? Ssl 58:33 /usr/libexec/gnome-terminal-server
^C
# trace -e recvmmsg,sendmmsg --map-dump syscalls
[299] = 1,
[307] = 1,
^C
# grep x64_recvmmsg arch/x86/entry/syscalls/syscall_64.tbl
299 64 recvmmsg __x64_sys_recvmmsg
# grep x64_sendmmsg arch/x86/entry/syscalls/syscall_64.tbl
307 64 sendmmsg __x64_sys_sendmmsg
#
Next step probably will be something like 'perf stat's --interval-print and
--interval-clear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin KaFai Lau <kafai@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Link: https://lkml.kernel.org/n/tip-ztxj25rtx37ixo9cfajt8ocy@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-02-20 02:17:33 +07:00
|
|
|
if (map_dump_str) {
|
|
|
|
trace.dump.map = bpf__find_map_by_name(map_dump_str);
|
|
|
|
if (trace.dump.map == NULL) {
|
|
|
|
pr_err("ERROR: BPF map \"%s\" not found\n", map_dump_str);
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-06-26 23:14:25 +07:00
|
|
|
if (trace.trace_pgfaults) {
|
|
|
|
trace.opts.sample_address = true;
|
|
|
|
trace.opts.sample_time = true;
|
|
|
|
}
|
|
|
|
|
2016-04-16 03:52:34 +07:00
|
|
|
if (trace.opts.mmap_pages == UINT_MAX)
|
|
|
|
mmap_pages_user_set = false;
|
|
|
|
|
2016-04-16 02:41:19 +07:00
|
|
|
if (trace.max_stack == UINT_MAX) {
|
2018-05-18 02:31:32 +07:00
|
|
|
trace.max_stack = input_name ? PERF_MAX_STACK_DEPTH : sysctl__max_stack();
|
2016-04-16 02:41:19 +07:00
|
|
|
max_stack_user_set = false;
|
|
|
|
}
|
|
|
|
|
|
|
|
#ifdef HAVE_DWARF_UNWIND_SUPPORT
|
2018-01-15 20:39:55 +07:00
|
|
|
if ((trace.min_stack || max_stack_user_set) && !callchain_param.enabled) {
|
2016-04-16 02:41:19 +07:00
|
|
|
record_opts__parse_callchain(&trace.opts, &callchain_param, "dwarf", false);
|
2018-01-15 20:39:55 +07:00
|
|
|
}
|
2016-04-16 02:41:19 +07:00
|
|
|
#endif
|
|
|
|
|
2016-04-18 22:09:08 +07:00
|
|
|
if (callchain_param.enabled) {
|
2016-04-16 03:52:34 +07:00
|
|
|
if (!mmap_pages_user_set && geteuid() == 0)
|
|
|
|
trace.opts.mmap_pages = perf_event_mlock_kb_in_pages() * 4;
|
|
|
|
|
2016-04-08 18:34:15 +07:00
|
|
|
symbol_conf.use_callchain = true;
|
2016-04-16 03:52:34 +07:00
|
|
|
}
|
2016-04-08 18:34:15 +07:00
|
|
|
|
2018-08-03 01:09:24 +07:00
|
|
|
if (trace.evlist->nr_entries > 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 22:58:57 +07:00
|
|
|
evlist__set_evsel_handler(trace.evlist, trace__event_handler);
|
2018-08-03 01:09:24 +07:00
|
|
|
if (evlist__set_syscall_tp_fields(trace.evlist)) {
|
|
|
|
perror("failed to set syscalls:* tracepoint fields");
|
|
|
|
goto 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 22:58:57 +07:00
|
|
|
|
2018-12-11 02:27:33 +07:00
|
|
|
if (trace.sort_events) {
|
|
|
|
ordered_events__init(&trace.oe.data, ordered_events__deliver_event, &trace);
|
|
|
|
ordered_events__set_copy_on_queue(&trace.oe.data, true);
|
|
|
|
}
|
2018-12-05 23:05:09 +07:00
|
|
|
|
perf trace: Use the raw_syscalls:sys_enter for the augmented syscalls
Now we combine what comes from the "bpf-output" event, i.e. what is
added in the augmented_syscalls.c BPF program via the
__augmented_syscalls__ BPF map, i.e. the payload we get with
raw_syscalls:sys_enter tracepoints plus the pointer contents, right
after that payload, with the raw_syscall:sys_exit also added, without
augmentation, in the augmented_syscalls.c program.
The end result is that for the hooked syscalls, we get strace like
output with pointer expansion, something that wasn't possible before
with just raw_syscalls:sys_enter + raw_syscalls:sys_exit.
E.g.:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c ping -c 2 ::1
0.000 ( 0.008 ms): ping/19573 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.036 ( 0.006 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
0.070 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
0.095 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
0.127 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
0.156 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
0.181 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.212 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
0.242 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
0.266 ( 0.003 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
0.709 ( 0.006 ms): ping/19573 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
PING ::1(::1) 56 data bytes
1.133 ( 0.011 ms): ping/19573 connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.033 ms
1.234 ( 0.036 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
64 bytes from ::1: icmp_seq=2 ttl=64 time=0.120 ms
--- ::1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.033/0.076/0.120/0.044 ms
1002.060 ( 0.129 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, flags: CONFIRM, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
#
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat tools/perf/examples/bpf/hello.c
#include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
0.000 ( 0.008 ms): cat/20054 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.020 ( 0.005 ms): cat/20054 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.176 ( 0.011 ms): cat/20054 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.243 ( 0.006 ms): cat/20054 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c) = 3
#
Now to think how to hook on all syscalls, fallbacking to the non-augmented
raw_syscalls:sys_enter payload.
Probably the best way is to use a BPF_MAP_TYPE_PROG_ARRAY just like
samples/bpf/tracex5_kern.c does.
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: https://lkml.kernel.org/n/tip-nlt60y69o26xi59z5vtpdrj5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-09-04 02:29:39 +07:00
|
|
|
/*
|
|
|
|
* If we are augmenting syscalls, then combine what we put in the
|
|
|
|
* __augmented_syscalls__ BPF map with what is in the
|
|
|
|
* syscalls:sys_exit_FOO tracepoints, i.e. just like we do without BPF,
|
|
|
|
* combining raw_syscalls:sys_enter with raw_syscalls:sys_exit.
|
|
|
|
*
|
|
|
|
* We'll switch to look at two BPF maps, one for sys_enter and the
|
|
|
|
* other for sys_exit when we start augmenting the sys_exit paths with
|
|
|
|
* buffers that are being copied from kernel to userspace, think 'read'
|
|
|
|
* syscall.
|
|
|
|
*/
|
|
|
|
if (trace.syscalls.events.augmented) {
|
|
|
|
evlist__for_each_entry(trace.evlist, evsel) {
|
2018-11-03 18:19:56 +07:00
|
|
|
bool raw_syscalls_sys_exit = strcmp(perf_evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
|
|
|
|
|
|
|
|
if (raw_syscalls_sys_exit) {
|
|
|
|
trace.raw_augmented_syscalls = true;
|
|
|
|
goto init_augmented_syscall_tp;
|
|
|
|
}
|
|
|
|
|
2019-01-24 21:39:15 +07:00
|
|
|
if (trace.syscalls.events.augmented->priv == NULL &&
|
|
|
|
strstr(perf_evsel__name(evsel), "syscalls:sys_enter")) {
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
struct perf_evsel *augmented = trace.syscalls.events.augmented;
|
|
|
|
if (perf_evsel__init_augmented_syscall_tp(augmented, evsel) ||
|
|
|
|
perf_evsel__init_augmented_syscall_tp_args(augmented))
|
|
|
|
goto out;
|
|
|
|
augmented->handler = trace__sys_enter;
|
|
|
|
}
|
|
|
|
|
2018-11-03 18:19:56 +07:00
|
|
|
if (strstarts(perf_evsel__name(evsel), "syscalls:sys_exit_")) {
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
struct syscall_tp *sc;
|
2018-11-03 18:19:56 +07:00
|
|
|
init_augmented_syscall_tp:
|
perf trace: Do not hardcode the size of the tracepoint common_ fields
We shouldn't hardcode the size of the tracepoint common_ fields, use the
offset of the 'id'/'__syscallnr' field in the sys_enter event instead.
This caused the augmented syscalls code to fail on a particular build of a
PREEMPT_RT_FULL kernel where these extra 'common_migrate_disable' and
'common_padding' fields were before the syscall id one:
# cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/format
name: sys_enter
ID: 22
format:
field:unsigned short common_type; offset:0; size:2; signed:0;
field:unsigned char common_flags; offset:2; size:1; signed:0;
field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
field:int common_pid; offset:4; size:4; signed:1;
field:unsigned short common_migrate_disable; offset:8; size:2; signed:0;
field:unsigned short common_padding; offset:10; size:2; signed:0;
field:long id; offset:16; size:8; signed:1;
field:unsigned long args[6]; offset:24; size:48; signed:0;
print fmt: "NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)", REC->id, REC->args[0], REC->args[1], REC->args[2], REC->args[3], REC->args[4], REC->args[5]
#
All those 'common_' prefixed fields are zeroed when they hit a BPF tracepoint
hook, we better just discard those, i.e. somehow pass an offset to the
BPF program from the start of the ctx and make adjustments in the 'perf trace'
handlers to adjust the offset of the syscall arg offsets obtained from tracefs.
Till then, fix it the quick way and add this to the augmented_raw_syscalls.c to
bet it to work in such kernels:
diff --git a/tools/perf/examples/bpf/augmented_raw_syscalls.c b/tools/perf/examples/bpf/augmented_raw_syscalls.c
index 53c233370fae..1f746f931e13 100644
--- a/tools/perf/examples/bpf/augmented_raw_syscalls.c
+++ b/tools/perf/examples/bpf/augmented_raw_syscalls.c
@@ -38,12 +38,14 @@ struct bpf_map SEC("maps") syscalls = {
struct syscall_enter_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
unsigned long args[6];
};
struct syscall_exit_args {
unsigned long long common_tp_fields;
+ long rt_common_tp_fields;
long syscall_nr;
long ret;
};
Just to check that this was the case. Fix it properly later, for now remove the
hardcoding of the offset in the 'perf trace' side and document the situation
with this patch.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Luis Cláudio Gonçalves <lclaudio@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-2pqavrktqkliu5b9nzouio21@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-20 04:54:36 +07:00
|
|
|
if (perf_evsel__init_augmented_syscall_tp(evsel, evsel))
|
|
|
|
goto out;
|
|
|
|
sc = evsel->priv;
|
|
|
|
/*
|
|
|
|
* For now with BPF raw_augmented we hook into
|
|
|
|
* raw_syscalls:sys_enter and there we get all
|
|
|
|
* 6 syscall args plus the tracepoint common
|
|
|
|
* fields and the syscall_nr (another long).
|
|
|
|
* So we check if that is the case and if so
|
|
|
|
* don't look after the sc->args_size but
|
|
|
|
* always after the full raw_syscalls:sys_enter
|
|
|
|
* payload, which is fixed.
|
|
|
|
*
|
|
|
|
* We'll revisit this later to pass
|
|
|
|
* s->args_size to the BPF augmenter (now
|
|
|
|
* tools/perf/examples/bpf/augmented_raw_syscalls.c,
|
|
|
|
* so that it copies only what we need for each
|
|
|
|
* syscall, like what happens when we use
|
|
|
|
* syscalls:sys_enter_NAME, so that we reduce
|
|
|
|
* the kernel/userspace traffic to just what is
|
|
|
|
* needed for each syscall.
|
|
|
|
*/
|
|
|
|
if (trace.raw_augmented_syscalls)
|
|
|
|
trace.raw_augmented_syscalls_args_size = (6 + 1) * sizeof(long) + sc->id.offset;
|
perf trace: Use the raw_syscalls:sys_enter for the augmented syscalls
Now we combine what comes from the "bpf-output" event, i.e. what is
added in the augmented_syscalls.c BPF program via the
__augmented_syscalls__ BPF map, i.e. the payload we get with
raw_syscalls:sys_enter tracepoints plus the pointer contents, right
after that payload, with the raw_syscall:sys_exit also added, without
augmentation, in the augmented_syscalls.c program.
The end result is that for the hooked syscalls, we get strace like
output with pointer expansion, something that wasn't possible before
with just raw_syscalls:sys_enter + raw_syscalls:sys_exit.
E.g.:
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c ping -c 2 ::1
0.000 ( 0.008 ms): ping/19573 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.036 ( 0.006 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcap.so.2, flags: CLOEXEC) = 3
0.070 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libidn.so.11, flags: CLOEXEC) = 3
0.095 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libcrypto.so.1.1, flags: CLOEXEC) = 3
0.127 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libresolv.so.2, flags: CLOEXEC) = 3
0.156 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libm.so.6, flags: CLOEXEC) = 3
0.181 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.212 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libz.so.1, flags: CLOEXEC) = 3
0.242 ( 0.004 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libdl.so.2, flags: CLOEXEC) = 3
0.266 ( 0.003 ms): ping/19573 openat(dfd: CWD, filename: /lib64/libpthread.so.0, flags: CLOEXEC) = 3
0.709 ( 0.006 ms): ping/19573 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
PING ::1(::1) 56 data bytes
1.133 ( 0.011 ms): ping/19573 connect(fd: 5, uservaddr: { .family: INET6, port: 1025, addr: ::1 }, addrlen: 28) = 0
64 bytes from ::1: icmp_seq=1 ttl=64 time=0.033 ms
1.234 ( 0.036 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
64 bytes from ::1: icmp_seq=2 ttl=64 time=0.120 ms
--- ::1 ping statistics ---
2 packets transmitted, 2 received, 0% packet loss, time 1000ms
rtt min/avg/max/mdev = 0.033/0.076/0.120/0.044 ms
1002.060 ( 0.129 ms): ping/19573 sendto(fd: 4<socket:[1498931]>, buff: 0x555e5b975720, len: 64, flags: CONFIRM, addr: { .family: INET6, port: 58, addr: ::1 }, addr_len: 28) = 64
#
# perf trace -e tools/perf/examples/bpf/augmented_syscalls.c cat tools/perf/examples/bpf/hello.c
#include <stdio.h>
int syscall_enter(openat)(void *args)
{
puts("Hello, world\n");
return 0;
}
license(GPL);
0.000 ( 0.008 ms): cat/20054 openat(dfd: CWD, filename: /etc/ld.so.cache, flags: CLOEXEC) = 3
0.020 ( 0.005 ms): cat/20054 openat(dfd: CWD, filename: /lib64/libc.so.6, flags: CLOEXEC) = 3
0.176 ( 0.011 ms): cat/20054 open(filename: /usr/lib/locale/locale-archive, flags: CLOEXEC) = 3
0.243 ( 0.006 ms): cat/20054 openat(dfd: CWD, filename: tools/perf/examples/bpf/hello.c) = 3
#
Now to think how to hook on all syscalls, fallbacking to the non-augmented
raw_syscalls:sys_enter payload.
Probably the best way is to use a BPF_MAP_TYPE_PROG_ARRAY just like
samples/bpf/tracex5_kern.c does.
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: https://lkml.kernel.org/n/tip-nlt60y69o26xi59z5vtpdrj5@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-09-04 02:29:39 +07:00
|
|
|
perf_evsel__init_augmented_syscall_tp_ret(evsel);
|
|
|
|
evsel->handler = trace__sys_exit;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2014-06-26 23:14:26 +07:00
|
|
|
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 16:16:45 +07:00
|
|
|
if (!trace.trace_syscalls && !trace.trace_pgfaults &&
|
|
|
|
trace.evlist->nr_entries == 0 /* Was --events used? */) {
|
perf trace: Do not require --no-syscalls to suppress strace like output
So far the --syscalls option was the default, requiring explicit
--no-syscalls when wanting to process just some other event, invert that
and assume it only when no other event was specified, allowing its
explicit enablement when wanting to see all syscalls together with some
other event:
E.g:
The existing default is maintained for a single workload:
# perf trace sleep 1
<SNIP>
0.264 ( 0.003 ms): sleep/12762 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7f62cbf04000
0.271 ( 0.001 ms): sleep/12762 close(fd: 3) = 0
0.295 (1000.130 ms): sleep/12762 nanosleep(rqtp: 0x7ffd15194fd0) = 0
1000.469 ( 0.006 ms): sleep/12762 close(fd: 1) = 0
1000.480 ( 0.004 ms): sleep/12762 close(fd: 2) = 0
1000.502 ( ): sleep/12762 exit_group()
#
For a pid:
# pidof ssh
7826 3961 3226 2628 2493
# perf trace -p 3961
? ( ): ... [continued]: select()) = 1
0.023 ( 0.005 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce870 ) = 0
0.036 ( 0.009 ms): read(fd: 5</dev/pts/7>, buf: 0x7ffcc8fca7b0, count: 16384 ) = 3
0.060 ( 0.004 ms): getpid( ) = 3961 (ssh)
0.079 ( 0.004 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce8e0 ) = 0
0.088 ( 0.003 ms): clock_gettime(which_clock: BOOTTIME, tp: 0x7ffcc8fce7c0 ) = 0
<SNIP>
For system wide, threads, cgroups, user, etc when no event is specified,
the existing behaviour is maintained, i.e. --syscalls is selected.
When some event is specified, then --no-syscalls doesn't need to be
specified:
# perf trace -e tcp:tcp_probe ssh localhost
0.000 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=53 snd_nxt=0xb67ce8f7 snd_una=0xb67ce8f7 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43690
0.010 tcp:tcp_probe:src=[::1]:39074 dest=[::1]:22 mark=0 length=32 snd_nxt=0xa8f9ef38 snd_una=0xa8f9ef23 snd_cwnd=10 ssthresh=2147483647 snd_wnd=43690 srtt=31 rcv_wnd=43776
4.525 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=1240 snd_nxt=0xb67ce90c snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=43776
7.242 tcp:tcp_probe:src=[::1]:22 dest=[::1]:39074 mark=0 length=80 snd_nxt=0xb67ced44 snd_una=0xb67ce90c snd_cwnd=10 ssthresh=2147483647 snd_wnd=43776 srtt=18 rcv_wnd=174720
The authenticity of host 'localhost (::1)' can't be established.
ECDSA key fingerprint is SHA256:TKZS58923458203490asekfjaklskljmkjfgPMBfHzY.
ECDSA key fingerprint is MD5:d8:29:54:40:71:fa:b8:44:89:52:64:8a:35:42:d0:e8.
Are you sure you want to continue connecting (yes/no)?
^C
#
To get the previous behaviour just use --syscalls and get all syscalls formatted
strace like + the specified extra events:
# trace -e sched:*switch --syscalls sleep 1
<SNIP>
0.160 ( 0.003 ms): sleep/12877 mprotect(start: 0x7fdfe2361000, len: 4096, prot: READ) = 0
0.164 ( 0.009 ms): sleep/12877 munmap(addr: 0x7fdfe2345000, len: 113155) = 0
0.211 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce68e000
0.212 ( 0.002 ms): sleep/12877 brk(brk: 0x55d3ce6af000) = 0x55d3ce6af000
0.215 ( 0.001 ms): sleep/12877 brk() = 0x55d3ce6af000
0.219 ( 0.004 ms): sleep/12877 open(filename: 0xe1f07c00, flags: CLOEXEC) = 3
0.225 ( 0.001 ms): sleep/12877 fstat(fd: 3, statbuf: 0x7fdfe2138aa0) = 0
0.227 ( 0.003 ms): sleep/12877 mmap(len: 113045344, prot: READ, flags: PRIVATE, fd: 3) = 0x7fdfdb1b8000
0.234 ( 0.001 ms): sleep/12877 close(fd: 3) = 0
0.257 ( ): sleep/12877 nanosleep(rqtp: 0x7fffb36b6020) ...
0.260 ( ): sched:sched_switch:prev_comm=sleep prev_pid=12877 prev_prio=120 prev_state=D ==> next_comm=swapper/3 next_pid=0 next_prio=120
0.257 (1000.134 ms): sleep/12877 ... [continued]: nanosleep()) = 0
1000.428 ( 0.006 ms): sleep/12877 close(fd: 1) = 0
1000.440 ( 0.004 ms): sleep/12877 close(fd: 2) = 0
1000.461 ( ): sleep/12877 exit_group()
#
When specifiying just some syscalls, the behaviour doesn't change, i.e.:
# trace -e nanosleep -e sched:*switch sleep 1
0.000 ( ): sleep/14974 nanosleep(rqtp: 0x7ffc344ba9c0 ) ...
0.007 ( ): sched:sched_switch:prev_comm=sleep prev_pid=14974 prev_prio=120 prev_state=D ==> next_comm=swapper/2 next_pid=0 next_prio=120
0.000 (1000.139 ms): sleep/14974 ... [continued]: nanosleep()) = 0
#
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: https://lkml.kernel.org/n/tip-om2fulll97ytnxv40ler8jkf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-02 02:20:28 +07:00
|
|
|
trace.trace_syscalls = true;
|
2016-04-13 02:05:02 +07:00
|
|
|
}
|
|
|
|
|
2013-08-19 22:01:10 +07:00
|
|
|
if (output_name != NULL) {
|
|
|
|
err = trace__open_output(&trace, output_name);
|
|
|
|
if (err < 0) {
|
|
|
|
perror("failed to create output file");
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-11-13 02:46:16 +07:00
|
|
|
err = target__validate(&trace.opts.target);
|
2012-10-05 12:02:13 +07:00
|
|
|
if (err) {
|
2013-11-13 02:46:16 +07:00
|
|
|
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
|
2013-08-19 22:01:10 +07:00
|
|
|
fprintf(trace.output, "%s", bf);
|
|
|
|
goto out_close;
|
2012-10-05 12:02:13 +07:00
|
|
|
}
|
|
|
|
|
2013-11-13 02:46:16 +07:00
|
|
|
err = target__parse_uid(&trace.opts.target);
|
2012-09-27 06:05:56 +07:00
|
|
|
if (err) {
|
2013-11-13 02:46:16 +07:00
|
|
|
target__strerror(&trace.opts.target, err, bf, sizeof(bf));
|
2013-08-19 22:01:10 +07:00
|
|
|
fprintf(trace.output, "%s", bf);
|
|
|
|
goto out_close;
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|
|
|
|
|
2013-11-13 02:46:16 +07:00
|
|
|
if (!argc && target__none(&trace.opts.target))
|
2012-10-05 12:02:14 +07:00
|
|
|
trace.opts.target.system_wide = true;
|
|
|
|
|
2013-08-29 11:29:52 +07:00
|
|
|
if (input_name)
|
|
|
|
err = trace__replay(&trace);
|
|
|
|
else
|
|
|
|
err = trace__run(&trace, argc, argv);
|
2012-10-18 03:13:12 +07:00
|
|
|
|
2013-08-19 22:01:10 +07:00
|
|
|
out_close:
|
|
|
|
if (output_name != NULL)
|
|
|
|
fclose(trace.output);
|
|
|
|
out:
|
2012-10-18 03:13:12 +07:00
|
|
|
return err;
|
2012-09-27 06:05:56 +07:00
|
|
|
}
|