2009-06-06 20:19:13 +07:00
|
|
|
perf-annotate(1)
|
2010-05-05 21:23:27 +07:00
|
|
|
================
|
2009-06-06 20:19:13 +07:00
|
|
|
|
|
|
|
|
NAME
|
|
|
|
|
----
|
perf_counter tools: Add 'perf annotate' feature
Add new perf sub-command to display annotated source code:
$ perf annotate decode_tree_entry
------------------------------------------------
Percent | Source code & Disassembly of /home/mingo/git/git
------------------------------------------------
:
: /home/mingo/git/git: file format elf64-x86-64
:
:
: Disassembly of section .text:
:
: 00000000004a0da0 <decode_tree_entry>:
: *modep = mode;
: return str;
: }
:
: static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
: {
3.82 : 4a0da0: 41 54 push %r12
: const char *path;
: unsigned int mode, len;
:
: if (size < 24 || buf[size - 21])
0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx
: *modep = mode;
: return str;
: }
:
: static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
: {
0.00 : 4a0da6: 49 89 fc mov %rdi,%r12
0.00 : 4a0da9: 55 push %rbp
3.37 : 4a0daa: 53 push %rbx
: const char *path;
: unsigned int mode, len;
:
: if (size < 24 || buf[size - 21])
0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80>
0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1)
3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80>
: static const char *get_mode(const char *str, unsigned int *modep)
: {
: unsigned char c;
: unsigned int mode = 0;
:
: if (*str == ' ')
1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax
0.39 : 4a0db7: 3c 20 cmp $0x20,%al
0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80>
: return NULL;
:
: while ((c = *str++) != ' ') {
0.06 : 4a0dbb: 89 c2 mov %eax,%edx
: if (c < '0' || c > '7')
1.99 : 4a0dbd: 31 ed xor %ebp,%ebp
: unsigned int mode = 0;
:
: if (*str == ' ')
: return NULL;
:
: while ((c = *str++) != ' ') {
1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx
: if (c < '0' || c > '7')
0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax
0.17 : 4a0dc6: 3c 07 cmp $0x7,%al
0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37>
0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80>
0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax)
16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax
0.14 : 4a0dd3: 3c 07 cmp $0x7,%al
0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80>
: return NULL;
: mode = (mode << 3) + (c - '0');
3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax
: unsigned int mode = 0;
:
: if (*str == ' ')
: return NULL;
:
: while ((c = *str++) != ' ') {
0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx
16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx
: if (c < '0' || c > '7')
: return NULL;
: mode = (mode << 3) + (c - '0');
The first column is the percentage of samples that arrived on that
particular line - relative to the total cost of the function.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 20:48:52 +07:00
|
|
|
perf-annotate - Read perf.data (created by perf record) and display annotated code
|
2009-06-06 20:19:13 +07:00
|
|
|
|
|
|
|
|
SYNOPSIS
|
|
|
|
|
--------
|
|
|
|
|
[verse]
|
2010-08-21 20:38:16 +07:00
|
|
|
'perf annotate' [-i <file> | --input=file] [symbol_name]
|
2009-06-06 20:19:13 +07:00
|
|
|
|
|
|
|
|
DESCRIPTION
|
|
|
|
|
-----------
|
perf_counter tools: Add 'perf annotate' feature
Add new perf sub-command to display annotated source code:
$ perf annotate decode_tree_entry
------------------------------------------------
Percent | Source code & Disassembly of /home/mingo/git/git
------------------------------------------------
:
: /home/mingo/git/git: file format elf64-x86-64
:
:
: Disassembly of section .text:
:
: 00000000004a0da0 <decode_tree_entry>:
: *modep = mode;
: return str;
: }
:
: static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
: {
3.82 : 4a0da0: 41 54 push %r12
: const char *path;
: unsigned int mode, len;
:
: if (size < 24 || buf[size - 21])
0.17 : 4a0da2: 48 83 fa 17 cmp $0x17,%rdx
: *modep = mode;
: return str;
: }
:
: static void decode_tree_entry(struct tree_desc *desc, const char *buf, unsigned long size)
: {
0.00 : 4a0da6: 49 89 fc mov %rdi,%r12
0.00 : 4a0da9: 55 push %rbp
3.37 : 4a0daa: 53 push %rbx
: const char *path;
: unsigned int mode, len;
:
: if (size < 24 || buf[size - 21])
0.08 : 4a0dab: 76 73 jbe 4a0e20 <decode_tree_entry+0x80>
0.00 : 4a0dad: 80 7c 16 eb 00 cmpb $0x0,-0x15(%rsi,%rdx,1)
3.48 : 4a0db2: 75 6c jne 4a0e20 <decode_tree_entry+0x80>
: static const char *get_mode(const char *str, unsigned int *modep)
: {
: unsigned char c;
: unsigned int mode = 0;
:
: if (*str == ' ')
1.94 : 4a0db4: 0f b6 06 movzbl (%rsi),%eax
0.39 : 4a0db7: 3c 20 cmp $0x20,%al
0.00 : 4a0db9: 74 65 je 4a0e20 <decode_tree_entry+0x80>
: return NULL;
:
: while ((c = *str++) != ' ') {
0.06 : 4a0dbb: 89 c2 mov %eax,%edx
: if (c < '0' || c > '7')
1.99 : 4a0dbd: 31 ed xor %ebp,%ebp
: unsigned int mode = 0;
:
: if (*str == ' ')
: return NULL;
:
: while ((c = *str++) != ' ') {
1.74 : 4a0dbf: 48 8d 5e 01 lea 0x1(%rsi),%rbx
: if (c < '0' || c > '7')
0.00 : 4a0dc3: 8d 42 d0 lea -0x30(%rdx),%eax
0.17 : 4a0dc6: 3c 07 cmp $0x7,%al
0.00 : 4a0dc8: 76 0d jbe 4a0dd7 <decode_tree_entry+0x37>
0.00 : 4a0dca: eb 54 jmp 4a0e20 <decode_tree_entry+0x80>
0.00 : 4a0dcc: 0f 1f 40 00 nopl 0x0(%rax)
16.57 : 4a0dd0: 8d 42 d0 lea -0x30(%rdx),%eax
0.14 : 4a0dd3: 3c 07 cmp $0x7,%al
0.00 : 4a0dd5: 77 49 ja 4a0e20 <decode_tree_entry+0x80>
: return NULL;
: mode = (mode << 3) + (c - '0');
3.12 : 4a0dd7: 0f b6 c2 movzbl %dl,%eax
: unsigned int mode = 0;
:
: if (*str == ' ')
: return NULL;
:
: while ((c = *str++) != ' ') {
0.00 : 4a0dda: 0f b6 13 movzbl (%rbx),%edx
16.74 : 4a0ddd: 48 83 c3 01 add $0x1,%rbx
: if (c < '0' || c > '7')
: return NULL;
: mode = (mode << 3) + (c - '0');
The first column is the percentage of samples that arrived on that
particular line - relative to the total cost of the function.
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
LKML-Reference: <new-submission>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-06-06 20:48:52 +07:00
|
|
|
This command reads the input file and displays an annotated version of the
|
|
|
|
|
code. If the object file has debug symbols then the source code will be
|
|
|
|
|
displayed alongside assembly code.
|
|
|
|
|
|
|
|
|
|
If there is no debug info in the object, then annotated assembly is displayed.
|
2009-06-06 20:19:13 +07:00
|
|
|
|
|
|
|
|
OPTIONS
|
|
|
|
|
-------
|
|
|
|
|
-i::
|
2018-02-07 16:52:05 +07:00
|
|
|
--input=<file>::
|
2011-12-07 16:02:54 +07:00
|
|
|
Input file name. (default: perf.data unless stdin is a fifo)
|
2009-06-06 20:19:13 +07:00
|
|
|
|
2010-12-01 08:57:09 +07:00
|
|
|
-d::
|
|
|
|
|
--dsos=<dso[,dso...]>::
|
|
|
|
|
Only consider symbols in these dsos.
|
|
|
|
|
-s::
|
|
|
|
|
--symbol=<symbol>::
|
|
|
|
|
Symbol to annotate.
|
|
|
|
|
|
|
|
|
|
-f::
|
|
|
|
|
--force::
|
2016-03-24 19:52:19 +07:00
|
|
|
Don't do ownership validation.
|
2010-12-01 08:57:09 +07:00
|
|
|
|
|
|
|
|
-v::
|
|
|
|
|
--verbose::
|
|
|
|
|
Be more verbose. (Show symbol address, etc)
|
|
|
|
|
|
2017-02-17 15:17:41 +07:00
|
|
|
-q::
|
|
|
|
|
--quiet::
|
|
|
|
|
Do not show any message. (Suppress -v)
|
|
|
|
|
|
2017-08-18 15:46:48 +07:00
|
|
|
-n::
|
|
|
|
|
--show-nr-samples::
|
|
|
|
|
Show the number of samples for each symbol
|
|
|
|
|
|
2010-12-01 08:57:09 +07:00
|
|
|
-D::
|
|
|
|
|
--dump-raw-trace::
|
|
|
|
|
Dump raw trace in ASCII.
|
|
|
|
|
|
|
|
|
|
-k::
|
|
|
|
|
--vmlinux=<file>::
|
|
|
|
|
vmlinux pathname.
|
|
|
|
|
|
perf annotate: Introduce --ignore-vmlinux command line option
This is already present in 'perf top', albeit undocumented (will fix),
and is useful to use /proc/kcore instead of vmlinux and then get what is
really in place, not what the kernel starts with, before alternatives,
ftrace .text patching, etc, see the differences:
# perf annotate --stdio2 _raw_spin_lock_irqsave
_raw_spin_lock_irqsave() /lib/modules/4.16.0-rc4/build/vmlinux
Event: anon group { cycles, instructions }
0.00 3.17 → callq __fentry__
0.00 7.94 push %rbx
7.69 36.51 → callq __page_file_index
mov %rax,%rbx
7.69 3.17 → callq *ffffffff82225cd0
xor %eax,%eax
mov $0x1,%edx
80.77 49.21 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
3.85 0.00 mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
[root@jouet ~]# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
_raw_spin_lock_irqsave() /proc/kcore
Event: anon group { cycles, instructions }
0.00 3.17 nop
0.00 7.94 push %rbx
0.00 23.81 pushfq
7.69 12.70 pop %rax
nop
mov %rax,%rbx
7.69 3.17 cli
nop
xor %eax,%eax
mov $0x1,%edx
80.77 49.21 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
3.85 0.00 mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq *ffffffff820e96b0
mov %rbx,%rax
pop %rbx
← retq
#
Diff of the output of those commands:
# perf annotate --stdio2 _raw_spin_lock_irqsave > /tmp/vmlinux
# perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave > /tmp/kcore
# diff -y /tmp/vmlinux /tmp/kcore
_raw_spin_lock_irqsave() vmlinux | _raw_spin_lock_irqsave() /proc/kcore
Event: anon group { cycles, instructions } Event: anon group { cycles, instructions }
0.00 3.17 → callq __fentry__ | 0.00 3.17 nop
0.00 7.94 push %rbx 0.00 7.94 push %rbx
7.69 36.51 → callq __page_file_index | 0.00 23.81 pushfq
> 7.69 12.70 pop %rax
> nop
mov %rax,%rbx mov %rax,%rbx
7.69 3.17 → callq *ffffffff82225cd0 | 7.69 3.17 cli
> nop
xor %eax,%eax xor %eax,%eax
mov $0x1,%edx mov $0x1,%edx
80.77 49.21 lock cmpxchg %edx,(%rdi) 80.77 49.21 lock cmpxchg %edx,(%rdi)
test %eax,%eax test %eax,%eax
↓ jne 2b ↓ jne 2b
3.85 0.00 mov %rbx,%rax 3.85 0.00 mov %rbx,%rax
pop %rbx pop %rbx
← retq ← retq
2b: mov %eax,%esi 2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath| → callq *ffffffff820e96b0
mov %rbx,%rax mov %rbx,%rax
pop %rbx pop %rbx
← retq ← retq
#
This should be further streamlined by doing both annotations and
allowing the TUI to toggle initial/current, and show the patched
instructions in a slightly different color.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.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-wz8d269hxkcwaczr0r4rhyjg@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-17 01:58:35 +07:00
|
|
|
--ignore-vmlinux::
|
|
|
|
|
Ignore vmlinux files.
|
|
|
|
|
|
2010-12-01 08:57:09 +07:00
|
|
|
-m::
|
|
|
|
|
--modules::
|
|
|
|
|
Load module symbols. WARNING: use only with -k and LIVE kernel.
|
|
|
|
|
|
|
|
|
|
-l::
|
|
|
|
|
--print-line::
|
|
|
|
|
Print matching source lines (may be slow).
|
|
|
|
|
|
|
|
|
|
-P::
|
|
|
|
|
--full-paths::
|
|
|
|
|
Don't shorten the displayed pathnames.
|
|
|
|
|
|
2010-08-21 20:38:16 +07:00
|
|
|
--stdio:: Use the stdio interface.
|
|
|
|
|
|
2018-03-16 09:44:34 +07:00
|
|
|
--stdio2:: Use the stdio2 interface, non-interactive, uses the TUI formatting.
|
|
|
|
|
|
2018-02-07 16:52:05 +07:00
|
|
|
--stdio-color=<mode>::
|
2016-07-05 21:08:17 +07:00
|
|
|
'always', 'never' or 'auto', allowing configuring color output
|
|
|
|
|
via the command line, in addition to via "color.ui" .perfconfig.
|
|
|
|
|
Use '--stdio-color always' to generate color even when redirecting
|
|
|
|
|
to a pipe or file. Using just '--stdio-color' is equivalent to
|
|
|
|
|
using 'always'.
|
|
|
|
|
|
2013-02-07 16:02:08 +07:00
|
|
|
--tui:: Use the TUI interface. Use of --tui requires a tty, if one is not
|
2010-08-21 20:38:16 +07:00
|
|
|
present, as when piping to other commands, the stdio interface is
|
|
|
|
|
used. This interfaces starts by centering on the line with more
|
2010-12-01 08:57:09 +07:00
|
|
|
samples, TAB/UNTAB cycles through the lines with more samples.
|
2010-08-21 20:38:16 +07:00
|
|
|
|
2013-02-07 16:02:08 +07:00
|
|
|
--gtk:: Use the GTK interface.
|
|
|
|
|
|
2011-11-14 01:30:08 +07:00
|
|
|
-C::
|
2018-02-07 16:52:05 +07:00
|
|
|
--cpu=<cpu>:: Only report samples for the list of CPUs provided. Multiple CPUs can
|
2011-07-04 18:57:50 +07:00
|
|
|
be provided as a comma-separated list with no space: 0,1. Ranges of
|
|
|
|
|
CPUs are specified with -: 0-2. Default is to report samples on all
|
|
|
|
|
CPUs.
|
|
|
|
|
|
2011-05-17 22:32:07 +07:00
|
|
|
--asm-raw::
|
2011-10-06 22:48:31 +07:00
|
|
|
Show raw instruction encoding of assembly instructions.
|
2011-05-17 22:32:07 +07:00
|
|
|
|
2017-08-18 15:46:53 +07:00
|
|
|
--show-total-period:: Show a column with the sum of periods.
|
|
|
|
|
|
2011-05-17 22:32:07 +07:00
|
|
|
--source::
|
|
|
|
|
Interleave source code with assembly code. Enabled by default,
|
|
|
|
|
disable with --no-source.
|
|
|
|
|
|
2011-07-30 06:20:40 +07:00
|
|
|
--symfs=<directory>::
|
|
|
|
|
Look for files with symbols relative to this directory.
|
|
|
|
|
|
2011-09-16 04:31:41 +07:00
|
|
|
-M::
|
|
|
|
|
--disassembler-style=:: Set disassembler style for objdump.
|
|
|
|
|
|
2012-09-04 17:32:30 +07:00
|
|
|
--objdump=<path>::
|
|
|
|
|
Path to objdump binary.
|
|
|
|
|
|
2013-02-07 16:02:14 +07:00
|
|
|
--skip-missing::
|
|
|
|
|
Skip symbols that cannot be annotated.
|
|
|
|
|
|
perf annotate: Add basic support to event group view
Add --group option to enable event grouping. When enabled, all the
group members information will be shown with the leader so skip
non-leader events.
It only supports --stdio output currently. Later patches will extend
additional features.
$ perf annotate --group --stdio
...
Percent | Source code & Disassembly of libpthread-2.15.so
--------------------------------------------------------------------------------
:
:
:
: Disassembly of section .text:
:
: 000000387dc0aa50 <__pthread_mutex_unlock_usercnt>:
8.08 2.40 5.29 : 387dc0aa50: mov %rdi,%rdx
0.00 0.00 0.00 : 387dc0aa53: mov 0x10(%rdi),%edi
0.00 0.00 0.00 : 387dc0aa56: mov %edi,%eax
0.00 0.80 0.00 : 387dc0aa58: and $0x7f,%eax
3.03 2.40 3.53 : 387dc0aa5b: test $0x7c,%dil
0.00 0.00 0.00 : 387dc0aa5f: jne 387dc0aaa9 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa61: test %eax,%eax
0.00 0.00 0.00 : 387dc0aa63: jne 387dc0aa85 <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa65: and $0x80,%edi
0.00 0.00 0.00 : 387dc0aa6b: test %esi,%esi
3.03 5.60 7.06 : 387dc0aa6d: movl $0x0,0x8(%rdx)
0.00 0.00 0.59 : 387dc0aa74: je 387dc0aa7a <__pthread_mutex_unlock_use
0.00 0.00 0.00 : 387dc0aa76: subl $0x1,0xc(%rdx)
2.02 5.60 1.18 : 387dc0aa7a: mov %edi,%esi
0.00 0.00 0.00 : 387dc0aa7c: lock decl (%rdx)
83.84 83.20 82.35 : 387dc0aa7f: jne 387dc0aada <_L_unlock_586>
0.00 0.00 0.00 : 387dc0aa81: nop
0.00 0.00 0.00 : 387dc0aa82: xor %eax,%eax
0.00 0.00 0.00 : 387dc0aa84: retq
...
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1362462812-30885-6-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-03-05 12:53:25 +07:00
|
|
|
--group::
|
|
|
|
|
Show event group information together
|
|
|
|
|
|
2018-08-04 20:05:20 +07:00
|
|
|
--percent-type::
|
|
|
|
|
Set annotation percent type from following choices:
|
|
|
|
|
global-period, local-period, global-hits, local-hits
|
|
|
|
|
|
|
|
|
|
The local/global keywords set if the percentage is computed
|
|
|
|
|
in the scope of the function (local) or the whole data (global).
|
|
|
|
|
The period/hits keywords set the base the percentage is computed
|
|
|
|
|
on - the samples period or the number of samples (hits).
|
|
|
|
|
|
2009-06-06 20:19:13 +07:00
|
|
|
SEE ALSO
|
|
|
|
|
--------
|
2010-08-21 20:38:16 +07:00
|
|
|
linkperf:perf-record[1], linkperf:perf-report[1]
|