License cleanup: add SPDX GPL-2.0 license identifier to files with no license
Many source files in the tree are missing licensing information, which
makes it harder for compliance tools to determine the correct license.
By default all files without license information are under the default
license of the kernel, which is GPL version 2.
Update the files which contain no license information with the 'GPL-2.0'
SPDX license identifier. The SPDX identifier is a legally binding
shorthand, which can be used instead of the full boiler plate text.
This patch is based on work done by Thomas Gleixner and Kate Stewart and
Philippe Ombredanne.
How this work was done:
Patches were generated and checked against linux-4.14-rc6 for a subset of
the use cases:
- file had no licensing information it it.
- file was a */uapi/* one with no licensing information in it,
- file was a */uapi/* one with existing licensing information,
Further patches will be generated in subsequent months to fix up cases
where non-standard license headers were used, and references to license
had to be inferred by heuristics based on keywords.
The analysis to determine which SPDX License Identifier to be applied to
a file was done in a spreadsheet of side by side results from of the
output of two independent scanners (ScanCode & Windriver) producing SPDX
tag:value files created by Philippe Ombredanne. Philippe prepared the
base worksheet, and did an initial spot review of a few 1000 files.
The 4.13 kernel was the starting point of the analysis with 60,537 files
assessed. Kate Stewart did a file by file comparison of the scanner
results in the spreadsheet to determine which SPDX license identifier(s)
to be applied to the file. She confirmed any determination that was not
immediately clear with lawyers working with the Linux Foundation.
Criteria used to select files for SPDX license identifier tagging was:
- Files considered eligible had to be source code files.
- Make and config files were included as candidates if they contained >5
lines of source
- File already had some variant of a license header in it (even if <5
lines).
All documentation files were explicitly excluded.
The following heuristics were used to determine which SPDX license
identifiers to apply.
- when both scanners couldn't find any license traces, file was
considered to have no license information in it, and the top level
COPYING file license applied.
For non */uapi/* files that summary was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 11139
and resulted in the first patch in this series.
If that file was a */uapi/* path one, it was "GPL-2.0 WITH
Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was:
SPDX license identifier # files
---------------------------------------------------|-------
GPL-2.0 WITH Linux-syscall-note 930
and resulted in the second patch in this series.
- if a file had some form of licensing information in it, and was one
of the */uapi/* ones, it was denoted with the Linux-syscall-note if
any GPL family license was found in the file or had no licensing in
it (per prior point). Results summary:
SPDX license identifier # files
---------------------------------------------------|------
GPL-2.0 WITH Linux-syscall-note 270
GPL-2.0+ WITH Linux-syscall-note 169
((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21
((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17
LGPL-2.1+ WITH Linux-syscall-note 15
GPL-1.0+ WITH Linux-syscall-note 14
((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5
LGPL-2.0+ WITH Linux-syscall-note 4
LGPL-2.1 WITH Linux-syscall-note 3
((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3
((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1
and that resulted in the third patch in this series.
- when the two scanners agreed on the detected license(s), that became
the concluded license(s).
- when there was disagreement between the two scanners (one detected a
license but the other didn't, or they both detected different
licenses) a manual inspection of the file occurred.
- In most cases a manual inspection of the information in the file
resulted in a clear resolution of the license that should apply (and
which scanner probably needed to revisit its heuristics).
- When it was not immediately clear, the license identifier was
confirmed with lawyers working with the Linux Foundation.
- If there was any question as to the appropriate license identifier,
the file was flagged for further research and to be revisited later
in time.
In total, over 70 hours of logged manual review was done on the
spreadsheet to determine the SPDX license identifiers to apply to the
source files by Kate, Philippe, Thomas and, in some cases, confirmation
by lawyers working with the Linux Foundation.
Kate also obtained a third independent scan of the 4.13 code base from
FOSSology, and compared selected files where the other two scanners
disagreed against that SPDX file, to see if there was new insights. The
Windriver scanner is based on an older version of FOSSology in part, so
they are related.
Thomas did random spot checks in about 500 files from the spreadsheets
for the uapi headers and agreed with SPDX license identifier in the
files he inspected. For the non-uapi files Thomas did random spot checks
in about 15000 files.
In initial set of patches against 4.14-rc6, 3 files were found to have
copy/paste license identifier errors, and have been fixed to reflect the
correct identifier.
Additionally Philippe spent 10 hours this week doing a detailed manual
inspection and review of the 12,461 patched files from the initial patch
version early this week with:
- a full scancode scan run, collecting the matched texts, detected
license ids and scores
- reviewing anything where there was a license detected (about 500+
files) to ensure that the applied SPDX license was correct
- reviewing anything where there was no detection but the patch license
was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied
SPDX license was correct
This produced a worksheet with 20 files needing minor correction. This
worksheet was then exported into 3 different .csv files for the
different types of files to be modified.
These .csv files were then reviewed by Greg. Thomas wrote a script to
parse the csv files and add the proper SPDX tag to the file, in the
format that the file expected. This script was further refined by Greg
based on the output to detect more types of files automatically and to
distinguish between header and source .c files (which need different
comment types.) Finally Greg ran the script using the .csv files to
generate the patches.
Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org>
Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 14:07:57 +00:00
|
|
|
// SPDX-License-Identifier: GPL-2.0
|
2010-08-10 17:54:09 +00:00
|
|
|
#include "../browser.h"
|
|
|
|
#include "../helpline.h"
|
2011-10-26 10:00:55 +00:00
|
|
|
#include "../ui.h"
|
2012-04-04 07:14:26 +00:00
|
|
|
#include "../../util/annotate.h"
|
2019-08-29 18:56:40 +00:00
|
|
|
#include "../../util/debug.h"
|
2019-08-30 14:11:01 +00:00
|
|
|
#include "../../util/dso.h"
|
2012-04-04 07:14:26 +00:00
|
|
|
#include "../../util/hist.h"
|
|
|
|
#include "../../util/sort.h"
|
2019-01-27 12:42:37 +00:00
|
|
|
#include "../../util/map.h"
|
2012-04-04 07:14:26 +00:00
|
|
|
#include "../../util/symbol.h"
|
2013-03-05 05:53:21 +00:00
|
|
|
#include "../../util/evsel.h"
|
perf annotate: Check for fused instructions
Macro fusion merges two instructions to a single micro-op. Intel core
platform performs this hardware optimization under limited
circumstances.
For example, CMP + JCC can be "fused" and executed /retired together.
While with sampling this can result in the sample sometimes being on the
JCC and sometimes on the CMP. So for the fused instruction pair, they
could be considered together.
On Nehalem, fused instruction pairs:
cmp/test + jcc.
On other new CPU:
cmp/test/add/sub/and/inc/dec + jcc.
This patch adds an x86-specific function which checks if 2 instructions
are in a "fused" pair. For non-x86 arch, the function is just NULL.
Changelog:
v4: Move the CPU model checking to symbol__disassemble and save the CPU
family/model in arch structure.
It avoids checking every time when jump arrow printed.
v3: Add checking for Nehalem (CMP, TEST). For other newer Intel CPUs
just check it by default (CMP, TEST, ADD, SUB, AND, INC, DEC).
v2: Remove the original weak function. Arnaldo points out that doing it
as a weak function that will be overridden by the host arch doesn't
work. So now it's implemented as an arch-specific function.
Committer fix:
Do not access evsel->evlist->env->cpuid, ->env can be null, introduce
perf_evsel__env_cpuid(), just like perf_evsel__env_arch(), also used in
this function call.
The original patch was segfaulting 'perf top' + annotation.
But this essentially disables this fused instructions augmentation in
'perf top', the right thing is to get the cpuid from the running kernel,
left for a later patch tho.
Signed-off-by: Yao Jin <yao.jin@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1499403995-19857-2-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-07-07 05:06:34 +00:00
|
|
|
#include "../../util/evlist.h"
|
2017-04-17 18:23:08 +00:00
|
|
|
#include <inttypes.h>
|
2011-02-22 15:02:07 +00:00
|
|
|
#include <pthread.h>
|
2017-04-17 14:39:06 +00:00
|
|
|
#include <linux/kernel.h>
|
2017-07-20 18:27:39 +00:00
|
|
|
#include <linux/string.h>
|
2019-07-04 14:32:27 +00:00
|
|
|
#include <linux/zalloc.h>
|
2017-04-18 14:08:10 +00:00
|
|
|
#include <sys/ttydefaults.h>
|
2018-08-04 13:05:17 +00:00
|
|
|
#include <asm/bug.h>
|
2010-08-10 17:54:09 +00:00
|
|
|
|
2015-06-19 19:10:43 +00:00
|
|
|
struct disasm_line_samples {
|
2017-07-27 14:24:59 +00:00
|
|
|
double percent;
|
|
|
|
struct sym_hist_entry he;
|
2015-06-19 19:10:43 +00:00
|
|
|
};
|
|
|
|
|
2017-06-19 02:55:56 +00:00
|
|
|
struct arch;
|
|
|
|
|
2010-08-09 18:30:40 +00:00
|
|
|
struct annotate_browser {
|
2017-11-06 10:56:17 +00:00
|
|
|
struct ui_browser b;
|
|
|
|
struct rb_root entries;
|
|
|
|
struct rb_node *curr_hot;
|
|
|
|
struct annotation_line *selection;
|
|
|
|
struct arch *arch;
|
2018-05-28 16:54:59 +00:00
|
|
|
struct annotation_options *opts;
|
2017-11-06 10:56:17 +00:00
|
|
|
bool searching_backwards;
|
|
|
|
char search_bf[128];
|
2010-08-09 18:30:40 +00:00
|
|
|
};
|
|
|
|
|
2018-03-15 18:04:33 +00:00
|
|
|
static inline struct annotation *browser__annotation(struct ui_browser *browser)
|
|
|
|
{
|
|
|
|
struct map_symbol *ms = browser->priv;
|
|
|
|
return symbol__annotation(ms->sym);
|
|
|
|
}
|
|
|
|
|
2018-03-15 15:33:56 +00:00
|
|
|
static bool disasm_line__filter(struct ui_browser *browser, void *entry)
|
2011-10-14 15:31:21 +00:00
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(browser);
|
2018-03-16 13:39:24 +00:00
|
|
|
struct annotation_line *al = list_entry(entry, struct annotation_line, node);
|
|
|
|
return annotation_line__filter(al, notes);
|
2011-10-14 15:31:21 +00:00
|
|
|
}
|
|
|
|
|
2018-03-15 18:14:45 +00:00
|
|
|
static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, bool current)
|
2012-05-12 19:21:53 +00:00
|
|
|
{
|
2018-03-15 18:14:45 +00:00
|
|
|
struct annotation *notes = browser__annotation(browser);
|
2018-03-15 18:10:28 +00:00
|
|
|
|
2018-03-15 18:14:45 +00:00
|
|
|
if (current && (!browser->use_navkeypressed || browser->navkeypressed))
|
2012-05-12 19:21:53 +00:00
|
|
|
return HE_COLORSET_SELECTED;
|
2018-03-15 18:10:28 +00:00
|
|
|
if (nr == notes->max_jump_sources)
|
2012-05-12 19:21:53 +00:00
|
|
|
return HE_COLORSET_TOP;
|
|
|
|
if (nr > 1)
|
|
|
|
return HE_COLORSET_MEDIUM;
|
|
|
|
return HE_COLORSET_NORMAL;
|
|
|
|
}
|
|
|
|
|
2018-03-15 22:12:39 +00:00
|
|
|
static int ui_browser__set_jumps_percent_color(void *browser, int nr, bool current)
|
2012-05-12 19:21:53 +00:00
|
|
|
{
|
2018-03-15 18:14:45 +00:00
|
|
|
int color = ui_browser__jumps_percent_color(browser, nr, current);
|
|
|
|
return ui_browser__set_color(browser, color);
|
2012-05-12 19:21:53 +00:00
|
|
|
}
|
|
|
|
|
2018-03-15 22:12:39 +00:00
|
|
|
static int annotate_browser__set_color(void *browser, int color)
|
2017-10-11 15:01:57 +00:00
|
|
|
{
|
2018-03-15 22:12:39 +00:00
|
|
|
return ui_browser__set_color(browser, color);
|
|
|
|
}
|
2017-10-11 15:01:57 +00:00
|
|
|
|
2018-03-15 22:12:39 +00:00
|
|
|
static void annotate_browser__write_graph(void *browser, int graph)
|
|
|
|
{
|
|
|
|
ui_browser__write_graph(browser, graph);
|
2017-10-11 15:01:57 +00:00
|
|
|
}
|
|
|
|
|
2018-03-15 20:54:36 +00:00
|
|
|
static void annotate_browser__set_percent_color(void *browser, double percent, bool current)
|
|
|
|
{
|
|
|
|
ui_browser__set_percent_color(browser, percent, current);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void annotate_browser__printf(void *browser, const char *fmt, ...)
|
|
|
|
{
|
|
|
|
va_list args;
|
|
|
|
|
|
|
|
va_start(args, fmt);
|
|
|
|
ui_browser__vprintf(browser, fmt, args);
|
|
|
|
va_end(args);
|
|
|
|
}
|
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
|
2010-08-10 17:54:09 +00:00
|
|
|
{
|
2012-05-30 01:42:18 +00:00
|
|
|
struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(browser);
|
2017-10-11 15:01:57 +00:00
|
|
|
struct annotation_line *al = list_entry(entry, struct annotation_line, node);
|
2019-05-28 19:02:56 +00:00
|
|
|
const bool is_current_entry = ui_browser__is_current_entry(browser, row);
|
2018-03-16 02:14:51 +00:00
|
|
|
struct annotation_write_ops ops = {
|
|
|
|
.first_line = row == 0,
|
2019-05-28 19:02:56 +00:00
|
|
|
.current_entry = is_current_entry,
|
2018-03-16 02:14:51 +00:00
|
|
|
.change_color = (!notes->options->hide_src_code &&
|
2019-05-28 19:02:56 +00:00
|
|
|
(!is_current_entry ||
|
2018-03-16 02:14:51 +00:00
|
|
|
(browser->use_navkeypressed &&
|
|
|
|
!browser->navkeypressed))),
|
|
|
|
.width = browser->width,
|
|
|
|
.obj = browser,
|
|
|
|
.set_color = annotate_browser__set_color,
|
|
|
|
.set_percent_color = annotate_browser__set_percent_color,
|
|
|
|
.set_jumps_percent_color = ui_browser__set_jumps_percent_color,
|
|
|
|
.printf = annotate_browser__printf,
|
|
|
|
.write_graph = annotate_browser__write_graph,
|
|
|
|
};
|
2011-10-18 16:31:35 +00:00
|
|
|
|
|
|
|
/* The scroll bar isn't being used */
|
2012-05-30 01:42:18 +00:00
|
|
|
if (!browser->navkeypressed)
|
2018-03-16 02:14:51 +00:00
|
|
|
ops.width += 1;
|
2011-10-18 16:31:35 +00:00
|
|
|
|
2018-08-04 13:05:15 +00:00
|
|
|
annotation_line__write(al, notes, &ops, ab->opts);
|
2011-02-09 15:59:14 +00:00
|
|
|
|
2018-03-16 02:14:51 +00:00
|
|
|
if (ops.current_entry)
|
2017-10-11 15:01:57 +00:00
|
|
|
ab->selection = al;
|
2010-08-09 18:30:40 +00:00
|
|
|
}
|
|
|
|
|
2017-07-07 05:06:35 +00:00
|
|
|
static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
|
|
|
|
{
|
2017-10-11 15:01:25 +00:00
|
|
|
struct disasm_line *pos = list_prev_entry(cursor, al.node);
|
2017-07-07 05:06:35 +00:00
|
|
|
const char *name;
|
|
|
|
|
|
|
|
if (!pos)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
if (ins__is_lock(&pos->ins))
|
|
|
|
name = pos->ops.locked.ins.name;
|
|
|
|
else
|
|
|
|
name = pos->ins.name;
|
|
|
|
|
|
|
|
if (!name || !cursor->ins.name)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return ins__is_fused(ab->arch, name, cursor->ins.name);
|
|
|
|
}
|
|
|
|
|
2012-04-27 19:35:29 +00:00
|
|
|
static void annotate_browser__draw_current_jump(struct ui_browser *browser)
|
2012-04-24 17:24:28 +00:00
|
|
|
{
|
|
|
|
struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
|
2017-11-06 10:56:17 +00:00
|
|
|
struct disasm_line *cursor = disasm_line(ab->selection);
|
2017-10-11 15:01:54 +00:00
|
|
|
struct annotation_line *target;
|
2012-05-03 16:12:49 +00:00
|
|
|
unsigned int from, to;
|
2012-11-09 17:27:15 +00:00
|
|
|
struct map_symbol *ms = ab->b.priv;
|
|
|
|
struct symbol *sym = ms->sym;
|
2018-03-15 13:35:04 +00:00
|
|
|
struct annotation *notes = symbol__annotation(sym);
|
2018-03-15 15:41:39 +00:00
|
|
|
u8 pcnt_width = annotation__pcnt_width(notes);
|
2018-03-15 13:28:06 +00:00
|
|
|
int width;
|
2012-11-09 17:27:15 +00:00
|
|
|
|
|
|
|
/* PLT symbols contain external offsets */
|
|
|
|
if (strstr(sym->name, "@plt"))
|
|
|
|
return;
|
2012-04-24 17:24:28 +00:00
|
|
|
|
perf annotate: Add "_local" to jump/offset validation routines
Because they all really check if we can access data structures/visual
constructs where a "jump" instruction targets code in the same function,
i.e. things like:
__pthread_mutex_lock /usr/lib64/libpthread-2.26.so
1.95 │ mov __pthread_force_elision,%ecx
│ ┌──test %ecx,%ecx
0.07 │ ├──je 60
│ │ test $0x300,%esi
│ │↓ jne 60
│ │ or $0x100,%esi
│ │ mov %esi,0x10(%rdi)
│ 42:│ mov %esi,%edx
│ │ lea 0x16(%r8),%rsi
│ │ mov %r8,%rdi
│ │ and $0x80,%edx
│ │ add $0x8,%rsp
│ │→ jmpq __lll_lock_elision
│ │ nop
0.29 │ 60:└─→and $0x80,%esi
0.07 │ mov $0x1,%edi
0.29 │ xor %eax,%eax
2.53 │ lock cmpxchg %edi,(%r8)
And not things like that "jmpq __lll_lock_elision", that instead should behave
like a "call" instruction and "jump" to the disassembly of "___lll_lock_elision".
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-3cwx39u3h66dfw9xjrlt7ca2@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:12:33 +00:00
|
|
|
if (!disasm_line__is_valid_local_jump(cursor, sym))
|
2012-04-27 19:35:29 +00:00
|
|
|
return;
|
2012-04-24 17:24:28 +00:00
|
|
|
|
2018-03-01 14:33:59 +00:00
|
|
|
/*
|
|
|
|
* This first was seen with a gcc function, _cpp_lex_token, that
|
|
|
|
* has the usual jumps:
|
|
|
|
*
|
|
|
|
* │1159e6c: ↓ jne 115aa32 <_cpp_lex_token@@Base+0xf92>
|
|
|
|
*
|
|
|
|
* I.e. jumps to a label inside that function (_cpp_lex_token), and
|
|
|
|
* those works, but also this kind:
|
|
|
|
*
|
|
|
|
* │1159e8b: ↓ jne c469be <cpp_named_operator2name@@Base+0xa72>
|
|
|
|
*
|
|
|
|
* I.e. jumps to another function, outside _cpp_lex_token, which
|
|
|
|
* are not being correctly handled generating as a side effect references
|
|
|
|
* to ab->offset[] entries that are set to NULL, so to make this code
|
|
|
|
* more robust, check that here.
|
|
|
|
*
|
|
|
|
* A proper fix for will be put in place, looking at the function
|
|
|
|
* name right after the '<' token and probably treating this like a
|
|
|
|
* 'call' instruction.
|
|
|
|
*/
|
2018-03-15 13:47:54 +00:00
|
|
|
target = notes->offsets[cursor->ops.target.offset];
|
2018-03-01 14:33:59 +00:00
|
|
|
if (target == NULL) {
|
2018-03-15 13:47:54 +00:00
|
|
|
ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n",
|
2018-03-01 14:33:59 +00:00
|
|
|
cursor->ops.target.offset);
|
|
|
|
return;
|
|
|
|
}
|
2017-10-11 15:01:53 +00:00
|
|
|
|
2018-03-15 15:33:56 +00:00
|
|
|
if (notes->options->hide_src_code) {
|
2018-03-15 18:43:18 +00:00
|
|
|
from = cursor->al.idx_asm;
|
|
|
|
to = target->idx_asm;
|
2012-04-24 17:24:28 +00:00
|
|
|
} else {
|
2018-03-15 18:43:18 +00:00
|
|
|
from = (u64)cursor->al.idx;
|
|
|
|
to = (u64)target->idx;
|
2012-04-24 17:24:28 +00:00
|
|
|
}
|
|
|
|
|
2018-03-15 13:35:04 +00:00
|
|
|
width = annotation__cycles_width(notes);
|
perf report: Fix wrong jump arrow
When we use perf report interactive annotate view, we can see
the position of jump arrow is not correct. For example,
1. perf record -b ...
2. perf report
3. In interactive mode, select Annotate 'function'
Percent│ IPC Cycle
│ if (flag)
1.37 │0.4┌── 1 ↓ je 82
│ │ x += x / y + y / x;
0.00 │0.4│ 1310 movsd (%rsp),%xmm0
0.00 │0.4│ 565 movsd 0x8(%rsp),%xmm4
│0.4│ movsd 0x8(%rsp),%xmm1
│0.4│ movsd (%rsp),%xmm3
│0.4│ divsd %xmm4,%xmm0
0.00 │0.4│ 579 divsd %xmm3,%xmm1
│0.4│ movsd (%rsp),%xmm2
│0.4│ addsd %xmm1,%xmm0
│0.4│ addsd %xmm2,%xmm0
0.00 │0.4│ movsd %xmm0,(%rsp)
│ │ volatile double x = 1212121212, y = 121212;
│ │
│ │ s_randseed = time(0);
│ │ srand(s_randseed);
│ │
│ │ for (i = 0; i < 2000000000; i++) {
1.37 │0.4└─→ 82: sub $0x1,%ebx
28.21 │0.48 17 ↑ jne 38
The jump arrow in above example is not correct. It should add the
width of IPC and Cycle.
With this patch, the result is:
Percent│ IPC Cycle
│ if (flag)
1.37 │0.48 1 ┌──je 82
│ │ x += x / y + y / x;
0.00 │0.48 1310 │ movsd (%rsp),%xmm0
0.00 │0.48 565 │ movsd 0x8(%rsp),%xmm4
│0.48 │ movsd 0x8(%rsp),%xmm1
│0.48 │ movsd (%rsp),%xmm3
│0.48 │ divsd %xmm4,%xmm0
0.00 │0.48 579 │ divsd %xmm3,%xmm1
│0.48 │ movsd (%rsp),%xmm2
│0.48 │ addsd %xmm1,%xmm0
│0.48 │ addsd %xmm2,%xmm0
0.00 │0.48 │ movsd %xmm0,(%rsp)
│ │ volatile double x = 1212121212, y = 121212;
│ │
│ │ s_randseed = time(0);
│ │ srand(s_randseed);
│ │
│ │ for (i = 0; i < 2000000000; i++) {
1.37 │0.48 82:└─→sub $0x1,%ebx
28.21 │0.48 17 ↑ jne 38
Committer notes:
Please note that only from LBRv5 (according to Jiri) onwards, i.e. >=
Skylake is that we'll have the cycles counts in each branch record
entry, so to see the Cycles and IPC columns, and be able to test this
patch, one need a capable hardware.
While applying this I first tested it on a Broadwell class machine and
couldn't get those columns, will add code to the annotate browser to
warn the user about that, i.e. you have branch records, but no cycles,
use a more recent hardware to get the cycles and IPC columns.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1517223473-14750-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-29 10:57:53 +00:00
|
|
|
|
2016-01-08 08:16:11 +00:00
|
|
|
ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
|
perf report: Fix wrong jump arrow
When we use perf report interactive annotate view, we can see
the position of jump arrow is not correct. For example,
1. perf record -b ...
2. perf report
3. In interactive mode, select Annotate 'function'
Percent│ IPC Cycle
│ if (flag)
1.37 │0.4┌── 1 ↓ je 82
│ │ x += x / y + y / x;
0.00 │0.4│ 1310 movsd (%rsp),%xmm0
0.00 │0.4│ 565 movsd 0x8(%rsp),%xmm4
│0.4│ movsd 0x8(%rsp),%xmm1
│0.4│ movsd (%rsp),%xmm3
│0.4│ divsd %xmm4,%xmm0
0.00 │0.4│ 579 divsd %xmm3,%xmm1
│0.4│ movsd (%rsp),%xmm2
│0.4│ addsd %xmm1,%xmm0
│0.4│ addsd %xmm2,%xmm0
0.00 │0.4│ movsd %xmm0,(%rsp)
│ │ volatile double x = 1212121212, y = 121212;
│ │
│ │ s_randseed = time(0);
│ │ srand(s_randseed);
│ │
│ │ for (i = 0; i < 2000000000; i++) {
1.37 │0.4└─→ 82: sub $0x1,%ebx
28.21 │0.48 17 ↑ jne 38
The jump arrow in above example is not correct. It should add the
width of IPC and Cycle.
With this patch, the result is:
Percent│ IPC Cycle
│ if (flag)
1.37 │0.48 1 ┌──je 82
│ │ x += x / y + y / x;
0.00 │0.48 1310 │ movsd (%rsp),%xmm0
0.00 │0.48 565 │ movsd 0x8(%rsp),%xmm4
│0.48 │ movsd 0x8(%rsp),%xmm1
│0.48 │ movsd (%rsp),%xmm3
│0.48 │ divsd %xmm4,%xmm0
0.00 │0.48 579 │ divsd %xmm3,%xmm1
│0.48 │ movsd (%rsp),%xmm2
│0.48 │ addsd %xmm1,%xmm0
│0.48 │ addsd %xmm2,%xmm0
0.00 │0.48 │ movsd %xmm0,(%rsp)
│ │ volatile double x = 1212121212, y = 121212;
│ │
│ │ s_randseed = time(0);
│ │ srand(s_randseed);
│ │
│ │ for (i = 0; i < 2000000000; i++) {
1.37 │0.48 82:└─→sub $0x1,%ebx
28.21 │0.48 17 ↑ jne 38
Committer notes:
Please note that only from LBRv5 (according to Jiri) onwards, i.e. >=
Skylake is that we'll have the cycles counts in each branch record
entry, so to see the Cycles and IPC columns, and be able to test this
patch, one need a capable hardware.
While applying this I first tested it on a Broadwell class machine and
couldn't get those columns, will add code to the annotate browser to
warn the user about that, i.e. you have branch records, but no cycles,
use a more recent hardware to get the cycles and IPC columns.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1517223473-14750-1-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-01-29 10:57:53 +00:00
|
|
|
__ui_browser__line_arrow(browser,
|
2018-03-15 19:18:21 +00:00
|
|
|
pcnt_width + 2 + notes->widths.addr + width,
|
2012-11-09 16:21:02 +00:00
|
|
|
from, to);
|
2017-07-07 05:06:35 +00:00
|
|
|
|
|
|
|
if (is_fused(ab, cursor)) {
|
|
|
|
ui_browser__mark_fused(browser,
|
2018-03-15 19:18:21 +00:00
|
|
|
pcnt_width + 3 + notes->widths.addr + width,
|
2017-07-07 05:06:35 +00:00
|
|
|
from - 1,
|
2020-04-20 12:35:28 +00:00
|
|
|
to > from);
|
2017-07-07 05:06:35 +00:00
|
|
|
}
|
2012-04-24 17:24:28 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static unsigned int annotate_browser__refresh(struct ui_browser *browser)
|
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(browser);
|
2012-04-24 17:24:28 +00:00
|
|
|
int ret = ui_browser__list_head_refresh(browser);
|
2018-03-15 15:41:39 +00:00
|
|
|
int pcnt_width = annotation__pcnt_width(notes);
|
2012-04-24 17:24:28 +00:00
|
|
|
|
2018-03-15 15:33:56 +00:00
|
|
|
if (notes->options->jump_arrows)
|
2012-04-27 19:35:29 +00:00
|
|
|
annotate_browser__draw_current_jump(browser);
|
2012-04-24 17:24:28 +00:00
|
|
|
|
2012-05-03 16:12:49 +00:00
|
|
|
ui_browser__set_color(browser, HE_COLORSET_NORMAL);
|
2018-04-05 14:35:32 +00:00
|
|
|
__ui_browser__vline(browser, pcnt_width, 0, browser->rows - 1);
|
2012-04-24 17:24:28 +00:00
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2019-01-20 16:05:22 +00:00
|
|
|
static double disasm__cmp(struct annotation_line *a, struct annotation_line *b,
|
|
|
|
int percent_type)
|
2012-11-09 16:21:02 +00:00
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
2018-08-04 13:05:05 +00:00
|
|
|
for (i = 0; i < a->data_nr; i++) {
|
2019-01-20 16:05:22 +00:00
|
|
|
if (a->data[i].percent[percent_type] == b->data[i].percent[percent_type])
|
2012-11-09 16:21:02 +00:00
|
|
|
continue;
|
2019-01-20 16:05:22 +00:00
|
|
|
return a->data[i].percent[percent_type] -
|
|
|
|
b->data[i].percent[percent_type];
|
2012-11-09 16:21:02 +00:00
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-01-20 16:05:22 +00:00
|
|
|
static void disasm_rb_tree__insert(struct annotate_browser *browser,
|
|
|
|
struct annotation_line *al)
|
2010-08-09 18:30:40 +00:00
|
|
|
{
|
2019-01-20 16:05:22 +00:00
|
|
|
struct rb_root *root = &browser->entries;
|
2012-04-15 18:24:39 +00:00
|
|
|
struct rb_node **p = &root->rb_node;
|
2010-08-09 18:30:40 +00:00
|
|
|
struct rb_node *parent = NULL;
|
2017-10-11 15:01:48 +00:00
|
|
|
struct annotation_line *l;
|
2010-08-09 18:30:40 +00:00
|
|
|
|
|
|
|
while (*p != NULL) {
|
|
|
|
parent = *p;
|
2017-10-11 15:01:48 +00:00
|
|
|
l = rb_entry(parent, struct annotation_line, rb_node);
|
2012-11-09 16:21:02 +00:00
|
|
|
|
2019-01-20 16:05:22 +00:00
|
|
|
if (disasm__cmp(al, l, browser->opts->percent_type) < 0)
|
2010-08-09 18:30:40 +00:00
|
|
|
p = &(*p)->rb_left;
|
|
|
|
else
|
|
|
|
p = &(*p)->rb_right;
|
|
|
|
}
|
2017-10-11 15:01:48 +00:00
|
|
|
rb_link_node(&al->rb_node, parent, p);
|
|
|
|
rb_insert_color(&al->rb_node, root);
|
2010-08-10 17:54:09 +00:00
|
|
|
}
|
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
static void annotate_browser__set_top(struct annotate_browser *browser,
|
2017-10-11 15:01:56 +00:00
|
|
|
struct annotation_line *pos, u32 idx)
|
2010-08-10 18:14:53 +00:00
|
|
|
{
|
2018-03-16 13:39:24 +00:00
|
|
|
struct annotation *notes = browser__annotation(&browser->b);
|
2010-08-10 18:14:53 +00:00
|
|
|
unsigned back;
|
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
ui_browser__refresh_dimensions(&browser->b);
|
|
|
|
back = browser->b.height / 2;
|
|
|
|
browser->b.top_idx = browser->b.index = idx;
|
2010-08-10 18:14:53 +00:00
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
while (browser->b.top_idx != 0 && back != 0) {
|
2017-10-11 15:01:56 +00:00
|
|
|
pos = list_entry(pos->node.prev, struct annotation_line, node);
|
2010-08-10 18:14:53 +00:00
|
|
|
|
2018-03-16 13:39:24 +00:00
|
|
|
if (annotation_line__filter(pos, notes))
|
2012-04-04 00:35:35 +00:00
|
|
|
continue;
|
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
--browser->b.top_idx;
|
2010-08-10 18:14:53 +00:00
|
|
|
--back;
|
|
|
|
}
|
|
|
|
|
2017-10-11 15:01:56 +00:00
|
|
|
browser->b.top = pos;
|
2012-05-30 01:42:18 +00:00
|
|
|
browser->b.navkeypressed = true;
|
2012-04-03 18:32:45 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
static void annotate_browser__set_rb_top(struct annotate_browser *browser,
|
|
|
|
struct rb_node *nd)
|
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(&browser->b);
|
2018-03-15 18:43:18 +00:00
|
|
|
struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node);
|
|
|
|
u32 idx = pos->idx;
|
2017-10-11 15:01:36 +00:00
|
|
|
|
2018-03-15 15:33:56 +00:00
|
|
|
if (notes->options->hide_src_code)
|
2018-03-15 18:43:18 +00:00
|
|
|
idx = pos->idx_asm;
|
2012-05-29 23:49:14 +00:00
|
|
|
annotate_browser__set_top(browser, pos, idx);
|
2012-04-03 18:32:45 +00:00
|
|
|
browser->curr_hot = nd;
|
2010-08-10 18:14:53 +00:00
|
|
|
}
|
|
|
|
|
2011-02-22 15:02:07 +00:00
|
|
|
static void annotate_browser__calc_percent(struct annotate_browser *browser,
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel *evsel)
|
2010-08-10 18:14:53 +00:00
|
|
|
{
|
2011-10-05 22:35:54 +00:00
|
|
|
struct map_symbol *ms = browser->b.priv;
|
|
|
|
struct symbol *sym = ms->sym;
|
2011-02-22 15:02:07 +00:00
|
|
|
struct annotation *notes = symbol__annotation(sym);
|
2017-10-11 15:01:34 +00:00
|
|
|
struct disasm_line *pos;
|
2011-02-22 15:02:07 +00:00
|
|
|
|
|
|
|
browser->entries = RB_ROOT;
|
|
|
|
|
|
|
|
pthread_mutex_lock(¬es->lock);
|
|
|
|
|
2017-10-11 15:01:43 +00:00
|
|
|
symbol__calc_percent(sym, evsel);
|
|
|
|
|
2017-10-11 15:01:25 +00:00
|
|
|
list_for_each_entry(pos, ¬es->src->source, al.node) {
|
2012-11-09 16:21:02 +00:00
|
|
|
double max_percent = 0.0;
|
|
|
|
int i;
|
2013-03-05 05:53:30 +00:00
|
|
|
|
2017-10-11 15:01:26 +00:00
|
|
|
if (pos->al.offset == -1) {
|
2017-10-11 15:01:36 +00:00
|
|
|
RB_CLEAR_NODE(&pos->al.rb_node);
|
2013-03-05 05:53:30 +00:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2018-08-04 13:05:05 +00:00
|
|
|
for (i = 0; i < pos->al.data_nr; i++) {
|
2018-08-04 13:05:09 +00:00
|
|
|
double percent;
|
2017-10-11 15:01:43 +00:00
|
|
|
|
2018-08-04 13:05:09 +00:00
|
|
|
percent = annotation_data__percent(&pos->al.data[i],
|
2018-08-04 13:05:16 +00:00
|
|
|
browser->opts->percent_type);
|
2018-08-04 13:05:09 +00:00
|
|
|
|
|
|
|
if (max_percent < percent)
|
|
|
|
max_percent = percent;
|
2012-11-09 16:21:02 +00:00
|
|
|
}
|
|
|
|
|
2017-10-11 15:01:27 +00:00
|
|
|
if (max_percent < 0.01 && pos->al.ipc == 0) {
|
2017-10-11 15:01:36 +00:00
|
|
|
RB_CLEAR_NODE(&pos->al.rb_node);
|
2011-02-22 15:02:07 +00:00
|
|
|
continue;
|
|
|
|
}
|
2019-01-20 16:05:22 +00:00
|
|
|
disasm_rb_tree__insert(browser, &pos->al);
|
2011-02-22 15:02:07 +00:00
|
|
|
}
|
|
|
|
pthread_mutex_unlock(¬es->lock);
|
|
|
|
|
|
|
|
browser->curr_hot = rb_last(&browser->entries);
|
|
|
|
}
|
|
|
|
|
2021-06-24 22:34:22 +00:00
|
|
|
static struct annotation_line *annotate_browser__find_next_asm_line(
|
|
|
|
struct annotate_browser *browser,
|
|
|
|
struct annotation_line *al)
|
|
|
|
{
|
|
|
|
struct annotation_line *it = al;
|
|
|
|
|
|
|
|
/* find next asm line */
|
|
|
|
list_for_each_entry_continue(it, browser->b.top, node) {
|
|
|
|
if (it->idx_asm >= 0)
|
|
|
|
return it;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* no asm line found forwards, try backwards */
|
|
|
|
it = al;
|
|
|
|
list_for_each_entry_continue_reverse(it, browser->b.top, node) {
|
|
|
|
if (it->idx_asm >= 0)
|
|
|
|
return it;
|
|
|
|
}
|
|
|
|
|
|
|
|
/* There are no asm lines */
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
2011-10-14 15:31:21 +00:00
|
|
|
static bool annotate_browser__toggle_source(struct annotate_browser *browser)
|
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(&browser->b);
|
2017-10-11 15:01:56 +00:00
|
|
|
struct annotation_line *al;
|
2011-10-14 15:31:21 +00:00
|
|
|
off_t offset = browser->b.index - browser->b.top_idx;
|
|
|
|
|
|
|
|
browser->b.seek(&browser->b, offset, SEEK_CUR);
|
2017-10-11 15:01:56 +00:00
|
|
|
al = list_entry(browser->b.top, struct annotation_line, node);
|
2011-10-14 15:31:21 +00:00
|
|
|
|
2018-03-15 15:33:56 +00:00
|
|
|
if (notes->options->hide_src_code) {
|
2018-03-15 18:43:18 +00:00
|
|
|
if (al->idx_asm < offset)
|
|
|
|
offset = al->idx;
|
2011-10-14 15:31:21 +00:00
|
|
|
|
2018-03-15 18:52:33 +00:00
|
|
|
browser->b.nr_entries = notes->nr_entries;
|
2018-03-15 15:33:56 +00:00
|
|
|
notes->options->hide_src_code = false;
|
2011-10-14 15:31:21 +00:00
|
|
|
browser->b.seek(&browser->b, -offset, SEEK_CUR);
|
2018-03-15 18:43:18 +00:00
|
|
|
browser->b.top_idx = al->idx - offset;
|
|
|
|
browser->b.index = al->idx;
|
2011-10-14 15:31:21 +00:00
|
|
|
} else {
|
2018-03-15 18:43:18 +00:00
|
|
|
if (al->idx_asm < 0) {
|
2021-06-24 22:34:22 +00:00
|
|
|
/* move cursor to next asm line */
|
|
|
|
al = annotate_browser__find_next_asm_line(browser, al);
|
|
|
|
if (!al) {
|
|
|
|
browser->b.seek(&browser->b, -offset, SEEK_CUR);
|
|
|
|
return false;
|
|
|
|
}
|
2011-10-14 15:31:21 +00:00
|
|
|
}
|
|
|
|
|
2018-03-15 18:43:18 +00:00
|
|
|
if (al->idx_asm < offset)
|
|
|
|
offset = al->idx_asm;
|
2011-10-14 15:31:21 +00:00
|
|
|
|
2018-03-15 18:52:33 +00:00
|
|
|
browser->b.nr_entries = notes->nr_asm_entries;
|
2018-03-15 15:33:56 +00:00
|
|
|
notes->options->hide_src_code = true;
|
2011-10-14 15:31:21 +00:00
|
|
|
browser->b.seek(&browser->b, -offset, SEEK_CUR);
|
2018-03-15 18:43:18 +00:00
|
|
|
browser->b.top_idx = al->idx_asm - offset;
|
|
|
|
browser->b.index = al->idx_asm;
|
2011-10-14 15:31:21 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2021-02-15 11:34:46 +00:00
|
|
|
#define SYM_TITLE_MAX_SIZE (PATH_MAX + 64)
|
|
|
|
|
|
|
|
static void annotate_browser__show_full_location(struct ui_browser *browser)
|
|
|
|
{
|
|
|
|
struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
|
|
|
|
struct disasm_line *cursor = disasm_line(ab->selection);
|
|
|
|
struct annotation_line *al = &cursor->al;
|
|
|
|
|
|
|
|
if (al->offset != -1)
|
|
|
|
ui_helpline__puts("Only available for source code lines.");
|
|
|
|
else if (al->fileloc == NULL)
|
|
|
|
ui_helpline__puts("No source file location.");
|
|
|
|
else {
|
|
|
|
char help_line[SYM_TITLE_MAX_SIZE];
|
|
|
|
sprintf (help_line, "Source file location: %s", al->fileloc);
|
|
|
|
ui_helpline__puts(help_line);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-03-15 18:52:33 +00:00
|
|
|
static void ui_browser__init_asm_mode(struct ui_browser *browser)
|
2012-05-30 00:24:05 +00:00
|
|
|
{
|
2018-03-15 18:52:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(browser);
|
|
|
|
ui_browser__reset_index(browser);
|
|
|
|
browser->nr_entries = notes->nr_asm_entries;
|
2012-05-30 00:24:05 +00:00
|
|
|
}
|
|
|
|
|
2013-08-07 11:38:55 +00:00
|
|
|
static int sym_title(struct symbol *sym, struct map *map, char *title,
|
2018-08-04 13:05:17 +00:00
|
|
|
size_t sz, int percent_type)
|
2013-08-07 11:38:55 +00:00
|
|
|
{
|
2018-08-04 13:05:17 +00:00
|
|
|
return snprintf(title, sz, "%s %s [Percent: %s]", sym->name, map->dso->long_name,
|
|
|
|
percent_type_str(percent_type));
|
2013-08-07 11:38:55 +00:00
|
|
|
}
|
|
|
|
|
perf annotate: Support jumping from one function to another
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
It'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.
Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
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-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:50:35 +00:00
|
|
|
/*
|
2021-03-23 16:09:15 +00:00
|
|
|
* This can be called from external jumps, i.e. jumps from one function
|
perf annotate: Support jumping from one function to another
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
It'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.
Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
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-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:50:35 +00:00
|
|
|
* to another, like from the kernel's entry_SYSCALL_64 function to the
|
|
|
|
* swapgs_restore_regs_and_return_to_usermode() function.
|
|
|
|
*
|
|
|
|
* So all we check here is that dl->ops.target.sym is set, if it is, just
|
|
|
|
* go to that function and when exiting from its disassembly, come back
|
|
|
|
* to the calling function.
|
|
|
|
*/
|
2013-03-05 05:53:21 +00:00
|
|
|
static bool annotate_browser__callq(struct annotate_browser *browser,
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel *evsel,
|
2012-11-02 05:50:05 +00:00
|
|
|
struct hist_browser_timer *hbt)
|
2012-04-02 16:58:33 +00:00
|
|
|
{
|
2019-11-04 14:10:00 +00:00
|
|
|
struct map_symbol *ms = browser->b.priv, target_ms;
|
2017-11-06 10:56:17 +00:00
|
|
|
struct disasm_line *dl = disasm_line(browser->selection);
|
2012-04-02 16:58:33 +00:00
|
|
|
struct annotation *notes;
|
2013-08-07 11:38:55 +00:00
|
|
|
char title[SYM_TITLE_MAX_SIZE];
|
2012-04-02 16:58:33 +00:00
|
|
|
|
2018-03-02 14:59:36 +00:00
|
|
|
if (!dl->ops.target.sym) {
|
2012-04-02 16:58:33 +00:00
|
|
|
ui_helpline__puts("The called function was not found.");
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2018-03-02 14:59:36 +00:00
|
|
|
notes = symbol__annotation(dl->ops.target.sym);
|
2012-04-02 16:58:33 +00:00
|
|
|
pthread_mutex_lock(¬es->lock);
|
|
|
|
|
2019-07-21 11:24:28 +00:00
|
|
|
if (!symbol__hists(dl->ops.target.sym, evsel->evlist->core.nr_entries)) {
|
2012-04-02 16:58:33 +00:00
|
|
|
pthread_mutex_unlock(¬es->lock);
|
|
|
|
ui__warning("Not enough memory for annotating '%s' symbol!\n",
|
2018-03-02 14:59:36 +00:00
|
|
|
dl->ops.target.sym->name);
|
2012-04-02 16:58:33 +00:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2019-11-26 01:15:35 +00:00
|
|
|
target_ms.maps = ms->maps;
|
2019-11-04 14:10:00 +00:00
|
|
|
target_ms.map = ms->map;
|
|
|
|
target_ms.sym = dl->ops.target.sym;
|
2012-04-02 16:58:33 +00:00
|
|
|
pthread_mutex_unlock(¬es->lock);
|
2019-11-04 14:10:00 +00:00
|
|
|
symbol__tui_annotate(&target_ms, evsel, hbt, browser->opts);
|
2018-08-04 13:05:17 +00:00
|
|
|
sym_title(ms->sym, ms->map, title, sizeof(title), browser->opts->percent_type);
|
2013-08-07 11:38:55 +00:00
|
|
|
ui_browser__show_title(&browser->b, title);
|
2012-04-02 16:58:33 +00:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2012-04-15 18:24:39 +00:00
|
|
|
static
|
|
|
|
struct disasm_line *annotate_browser__find_offset(struct annotate_browser *browser,
|
|
|
|
s64 offset, s64 *idx)
|
2012-04-04 00:35:35 +00:00
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(&browser->b);
|
2012-04-15 18:24:39 +00:00
|
|
|
struct disasm_line *pos;
|
2012-04-04 00:35:35 +00:00
|
|
|
|
|
|
|
*idx = 0;
|
2017-10-11 15:01:25 +00:00
|
|
|
list_for_each_entry(pos, ¬es->src->source, al.node) {
|
2017-10-11 15:01:26 +00:00
|
|
|
if (pos->al.offset == offset)
|
2012-04-04 00:35:35 +00:00
|
|
|
return pos;
|
2018-03-16 13:39:24 +00:00
|
|
|
if (!annotation_line__filter(&pos->al, notes))
|
2012-04-04 00:35:35 +00:00
|
|
|
++*idx;
|
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
perf annotate: Support jumping from one function to another
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
It'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.
Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
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-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:50:35 +00:00
|
|
|
static bool annotate_browser__jump(struct annotate_browser *browser,
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel *evsel,
|
perf annotate: Support jumping from one function to another
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
It'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.
Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
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-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:50:35 +00:00
|
|
|
struct hist_browser_timer *hbt)
|
2012-04-04 00:35:35 +00:00
|
|
|
{
|
2017-11-06 10:56:17 +00:00
|
|
|
struct disasm_line *dl = disasm_line(browser->selection);
|
2016-11-25 18:56:34 +00:00
|
|
|
u64 offset;
|
2012-04-18 16:58:34 +00:00
|
|
|
s64 idx;
|
2012-04-04 00:35:35 +00:00
|
|
|
|
2016-11-24 14:16:06 +00:00
|
|
|
if (!ins__is_jump(&dl->ins))
|
2012-04-04 00:35:35 +00:00
|
|
|
return false;
|
|
|
|
|
perf annotate: Support jumping from one function to another
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
It'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.
Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
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-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:50:35 +00:00
|
|
|
if (dl->ops.target.outside) {
|
|
|
|
annotate_browser__callq(browser, evsel, hbt);
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2016-11-25 18:56:34 +00:00
|
|
|
offset = dl->ops.target.offset;
|
|
|
|
dl = annotate_browser__find_offset(browser, offset, &idx);
|
2012-04-15 18:24:39 +00:00
|
|
|
if (dl == NULL) {
|
2016-11-25 18:56:34 +00:00
|
|
|
ui_helpline__printf("Invalid jump offset: %" PRIx64, offset);
|
2012-04-04 00:35:35 +00:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2017-10-11 15:01:56 +00:00
|
|
|
annotate_browser__set_top(browser, &dl->al, idx);
|
2014-12-17 20:24:45 +00:00
|
|
|
|
2012-04-04 00:35:35 +00:00
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2012-04-15 18:24:39 +00:00
|
|
|
static
|
2017-10-11 15:01:55 +00:00
|
|
|
struct annotation_line *annotate_browser__find_string(struct annotate_browser *browser,
|
2012-04-15 18:24:39 +00:00
|
|
|
char *s, s64 *idx)
|
2012-04-07 20:10:30 +00:00
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(&browser->b);
|
2017-10-11 15:01:55 +00:00
|
|
|
struct annotation_line *al = browser->selection;
|
2012-04-07 20:10:30 +00:00
|
|
|
|
|
|
|
*idx = browser->b.index;
|
2017-10-11 15:01:55 +00:00
|
|
|
list_for_each_entry_continue(al, ¬es->src->source, node) {
|
2018-03-16 13:39:24 +00:00
|
|
|
if (annotation_line__filter(al, notes))
|
2012-04-07 20:10:30 +00:00
|
|
|
continue;
|
|
|
|
|
|
|
|
++*idx;
|
|
|
|
|
2017-10-11 15:01:55 +00:00
|
|
|
if (al->line && strstr(al->line, s) != NULL)
|
|
|
|
return al;
|
2012-04-07 20:10:30 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool __annotate_browser__search(struct annotate_browser *browser)
|
|
|
|
{
|
2017-10-11 15:01:55 +00:00
|
|
|
struct annotation_line *al;
|
2012-04-07 20:10:30 +00:00
|
|
|
s64 idx;
|
|
|
|
|
2017-10-11 15:01:55 +00:00
|
|
|
al = annotate_browser__find_string(browser, browser->search_bf, &idx);
|
|
|
|
if (al == NULL) {
|
2012-04-07 20:10:30 +00:00
|
|
|
ui_helpline__puts("String not found!");
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2017-10-11 15:01:56 +00:00
|
|
|
annotate_browser__set_top(browser, al, idx);
|
2012-04-07 20:10:30 +00:00
|
|
|
browser->searching_backwards = false;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
2012-04-15 18:24:39 +00:00
|
|
|
static
|
2017-10-11 15:01:55 +00:00
|
|
|
struct annotation_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
|
2012-04-15 18:24:39 +00:00
|
|
|
char *s, s64 *idx)
|
2012-04-07 20:10:30 +00:00
|
|
|
{
|
2018-03-15 18:04:33 +00:00
|
|
|
struct annotation *notes = browser__annotation(&browser->b);
|
2017-10-11 15:01:55 +00:00
|
|
|
struct annotation_line *al = browser->selection;
|
2012-04-07 20:10:30 +00:00
|
|
|
|
|
|
|
*idx = browser->b.index;
|
2017-10-11 15:01:55 +00:00
|
|
|
list_for_each_entry_continue_reverse(al, ¬es->src->source, node) {
|
2018-03-16 13:39:24 +00:00
|
|
|
if (annotation_line__filter(al, notes))
|
2012-04-07 20:10:30 +00:00
|
|
|
continue;
|
|
|
|
|
|
|
|
--*idx;
|
|
|
|
|
2017-10-11 15:01:55 +00:00
|
|
|
if (al->line && strstr(al->line, s) != NULL)
|
|
|
|
return al;
|
2012-04-07 20:10:30 +00:00
|
|
|
}
|
|
|
|
|
|
|
|
return NULL;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool __annotate_browser__search_reverse(struct annotate_browser *browser)
|
|
|
|
{
|
2017-10-11 15:01:55 +00:00
|
|
|
struct annotation_line *al;
|
2012-04-07 20:10:30 +00:00
|
|
|
s64 idx;
|
|
|
|
|
2017-10-11 15:01:55 +00:00
|
|
|
al = annotate_browser__find_string_reverse(browser, browser->search_bf, &idx);
|
|
|
|
if (al == NULL) {
|
2012-04-07 20:10:30 +00:00
|
|
|
ui_helpline__puts("String not found!");
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
2017-10-11 15:01:56 +00:00
|
|
|
annotate_browser__set_top(browser, al, idx);
|
2012-04-07 20:10:30 +00:00
|
|
|
browser->searching_backwards = true;
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool annotate_browser__search_window(struct annotate_browser *browser,
|
|
|
|
int delay_secs)
|
|
|
|
{
|
|
|
|
if (ui_browser__input_window("Search", "String: ", browser->search_bf,
|
|
|
|
"ENTER: OK, ESC: Cancel",
|
|
|
|
delay_secs * 2) != K_ENTER ||
|
|
|
|
!*browser->search_bf)
|
|
|
|
return false;
|
|
|
|
|
|
|
|
return true;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool annotate_browser__search(struct annotate_browser *browser, int delay_secs)
|
|
|
|
{
|
|
|
|
if (annotate_browser__search_window(browser, delay_secs))
|
|
|
|
return __annotate_browser__search(browser);
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool annotate_browser__continue_search(struct annotate_browser *browser,
|
|
|
|
int delay_secs)
|
|
|
|
{
|
|
|
|
if (!*browser->search_bf)
|
|
|
|
return annotate_browser__search(browser, delay_secs);
|
|
|
|
|
|
|
|
return __annotate_browser__search(browser);
|
|
|
|
}
|
|
|
|
|
|
|
|
static bool annotate_browser__search_reverse(struct annotate_browser *browser,
|
|
|
|
int delay_secs)
|
|
|
|
{
|
|
|
|
if (annotate_browser__search_window(browser, delay_secs))
|
|
|
|
return __annotate_browser__search_reverse(browser);
|
|
|
|
|
|
|
|
return false;
|
|
|
|
}
|
|
|
|
|
|
|
|
static
|
|
|
|
bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
|
|
|
|
int delay_secs)
|
|
|
|
{
|
|
|
|
if (!*browser->search_bf)
|
|
|
|
return annotate_browser__search_reverse(browser, delay_secs);
|
|
|
|
|
|
|
|
return __annotate_browser__search_reverse(browser);
|
|
|
|
}
|
|
|
|
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
static int annotate_browser__show(struct ui_browser *browser, char *title, const char *help)
|
|
|
|
{
|
2018-08-04 13:05:17 +00:00
|
|
|
struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
struct map_symbol *ms = browser->priv;
|
|
|
|
struct symbol *sym = ms->sym;
|
|
|
|
char symbol_dso[SYM_TITLE_MAX_SIZE];
|
|
|
|
|
|
|
|
if (ui_browser__show(browser, title, help) < 0)
|
|
|
|
return -1;
|
|
|
|
|
2018-08-04 13:05:17 +00:00
|
|
|
sym_title(sym, ms->map, symbol_dso, sizeof(symbol_dso), ab->opts->percent_type);
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
|
|
|
|
ui_browser__gotorc_title(browser, 0, 0);
|
|
|
|
ui_browser__set_color(browser, HE_COLORSET_ROOT);
|
|
|
|
ui_browser__write_nstring(browser, symbol_dso, browser->width + 1);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2018-08-04 13:05:17 +00:00
|
|
|
static void
|
|
|
|
switch_percent_type(struct annotation_options *opts, bool base)
|
|
|
|
{
|
|
|
|
switch (opts->percent_type) {
|
|
|
|
case PERCENT_HITS_LOCAL:
|
|
|
|
if (base)
|
|
|
|
opts->percent_type = PERCENT_PERIOD_LOCAL;
|
|
|
|
else
|
|
|
|
opts->percent_type = PERCENT_HITS_GLOBAL;
|
|
|
|
break;
|
|
|
|
case PERCENT_HITS_GLOBAL:
|
|
|
|
if (base)
|
|
|
|
opts->percent_type = PERCENT_PERIOD_GLOBAL;
|
|
|
|
else
|
|
|
|
opts->percent_type = PERCENT_HITS_LOCAL;
|
|
|
|
break;
|
|
|
|
case PERCENT_PERIOD_LOCAL:
|
|
|
|
if (base)
|
|
|
|
opts->percent_type = PERCENT_HITS_LOCAL;
|
|
|
|
else
|
|
|
|
opts->percent_type = PERCENT_PERIOD_GLOBAL;
|
|
|
|
break;
|
|
|
|
case PERCENT_PERIOD_GLOBAL:
|
|
|
|
if (base)
|
|
|
|
opts->percent_type = PERCENT_HITS_GLOBAL;
|
|
|
|
else
|
|
|
|
opts->percent_type = PERCENT_PERIOD_LOCAL;
|
|
|
|
break;
|
|
|
|
default:
|
|
|
|
WARN_ON(1);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2013-03-05 05:53:21 +00:00
|
|
|
static int annotate_browser__run(struct annotate_browser *browser,
|
2019-07-21 11:23:51 +00:00
|
|
|
struct evsel *evsel,
|
2012-11-02 05:50:05 +00:00
|
|
|
struct hist_browser_timer *hbt)
|
2011-02-22 15:02:07 +00:00
|
|
|
{
|
|
|
|
struct rb_node *nd = NULL;
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
struct hists *hists = evsel__hists(evsel);
|
2012-05-30 01:42:18 +00:00
|
|
|
struct map_symbol *ms = browser->b.priv;
|
2011-10-05 22:35:54 +00:00
|
|
|
struct symbol *sym = ms->sym;
|
2018-03-15 15:33:56 +00:00
|
|
|
struct annotation *notes = symbol__annotation(ms->sym);
|
2012-05-12 19:36:55 +00:00
|
|
|
const char *help = "Press 'h' for help on key bindings";
|
2012-11-02 05:50:05 +00:00
|
|
|
int delay_secs = hbt ? hbt->refresh : 0;
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
char title[256];
|
2010-08-11 13:07:43 +00:00
|
|
|
int key;
|
2010-08-10 18:14:53 +00:00
|
|
|
|
2018-08-04 13:05:04 +00:00
|
|
|
hists__scnprintf_title(hists, title, sizeof(title));
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
if (annotate_browser__show(&browser->b, title, help) < 0)
|
2010-08-10 18:14:53 +00:00
|
|
|
return -1;
|
2011-02-22 15:02:07 +00:00
|
|
|
|
2013-03-05 05:53:21 +00:00
|
|
|
annotate_browser__calc_percent(browser, evsel);
|
2011-02-22 15:02:07 +00:00
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
if (browser->curr_hot) {
|
|
|
|
annotate_browser__set_rb_top(browser, browser->curr_hot);
|
|
|
|
browser->b.navkeypressed = false;
|
2012-04-07 20:10:30 +00:00
|
|
|
}
|
2010-08-10 18:14:53 +00:00
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
nd = browser->curr_hot;
|
2011-02-22 15:02:07 +00:00
|
|
|
|
2010-08-10 18:14:53 +00:00
|
|
|
while (1) {
|
2012-05-30 01:42:18 +00:00
|
|
|
key = ui_browser__run(&browser->b, delay_secs);
|
2010-08-10 18:14:53 +00:00
|
|
|
|
2011-10-05 22:11:32 +00:00
|
|
|
if (delay_secs != 0) {
|
2013-03-05 05:53:21 +00:00
|
|
|
annotate_browser__calc_percent(browser, evsel);
|
2011-02-22 15:02:07 +00:00
|
|
|
/*
|
|
|
|
* Current line focus got out of the list of most active
|
|
|
|
* lines, NULL it so that if TAB|UNTAB is pressed, we
|
|
|
|
* move to curr_hot (current hottest line).
|
|
|
|
*/
|
|
|
|
if (nd != NULL && RB_EMPTY_NODE(nd))
|
|
|
|
nd = NULL;
|
|
|
|
}
|
|
|
|
|
2010-08-11 13:07:43 +00:00
|
|
|
switch (key) {
|
2011-10-20 18:59:15 +00:00
|
|
|
case K_TIMER:
|
2012-11-02 05:50:05 +00:00
|
|
|
if (hbt)
|
|
|
|
hbt->timer(hbt->arg);
|
2011-10-05 22:11:32 +00:00
|
|
|
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
if (delay_secs != 0) {
|
2013-03-05 05:53:21 +00:00
|
|
|
symbol__annotate_decay_histogram(sym, evsel->idx);
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
hists__scnprintf_title(hists, title, sizeof(title));
|
|
|
|
annotate_browser__show(&browser->b, title, help);
|
|
|
|
}
|
2011-02-22 15:02:07 +00:00
|
|
|
continue;
|
2011-10-20 18:59:15 +00:00
|
|
|
case K_TAB:
|
2011-02-22 15:02:07 +00:00
|
|
|
if (nd != NULL) {
|
|
|
|
nd = rb_prev(nd);
|
|
|
|
if (nd == NULL)
|
2012-05-30 01:42:18 +00:00
|
|
|
nd = rb_last(&browser->entries);
|
2011-02-22 15:02:07 +00:00
|
|
|
} else
|
2012-05-30 01:42:18 +00:00
|
|
|
nd = browser->curr_hot;
|
2010-08-10 18:14:53 +00:00
|
|
|
break;
|
2011-10-20 18:59:15 +00:00
|
|
|
case K_UNTAB:
|
2015-12-14 15:44:03 +00:00
|
|
|
if (nd != NULL) {
|
2011-02-22 15:02:07 +00:00
|
|
|
nd = rb_next(nd);
|
|
|
|
if (nd == NULL)
|
2012-05-30 01:42:18 +00:00
|
|
|
nd = rb_first(&browser->entries);
|
2015-12-14 15:44:03 +00:00
|
|
|
} else
|
2012-05-30 01:42:18 +00:00
|
|
|
nd = browser->curr_hot;
|
2011-02-22 15:02:07 +00:00
|
|
|
break;
|
2012-05-12 19:36:55 +00:00
|
|
|
case K_F1:
|
2012-02-23 08:46:21 +00:00
|
|
|
case 'h':
|
2012-05-30 01:42:18 +00:00
|
|
|
ui_browser__help_window(&browser->b,
|
2012-05-12 19:36:55 +00:00
|
|
|
"UP/DOWN/PGUP\n"
|
|
|
|
"PGDN/SPACE Navigate\n"
|
|
|
|
"q/ESC/CTRL+C Exit\n\n"
|
2015-10-12 16:56:50 +00:00
|
|
|
"ENTER Go to target\n"
|
|
|
|
"ESC Exit\n"
|
2017-09-01 17:55:40 +00:00
|
|
|
"H Go to hottest instruction\n"
|
|
|
|
"TAB/shift+TAB Cycle thru hottest instructions\n"
|
2012-05-12 19:36:55 +00:00
|
|
|
"j Toggle showing jump to target arrows\n"
|
|
|
|
"J Toggle showing number of jump sources on targets\n"
|
|
|
|
"n Search next string\n"
|
|
|
|
"o Toggle disassembler output/simplified view\n"
|
perf annotate browser: Allow showing offsets in more than just jump targets
Jesper wanted to see offsets at callq sites when doing some performance
investigation related to retpolines, so save him some time by providing
a 'O' hotkey to allow showing offsets from function start at call
instructions or in all instructions, just go on pressing 'O' till the
offsets you need appear.
Example:
Starts with:
Samples: 64 of event 'cycles:ppp', 100000 Hz, Event count (approx.): 318963
ixgbe_read_reg /proc/kcore
Percent│ ↑ je 2a
│ ┌──cmp $0xffffffff,%r13d
│ ├──je d0
│ │ mov $0x53e3,%edi
│ │→ callq __const_udelay
│ │ sub $0x1,%r15d
│ │↑ jne 83
│ │ mov 0x8(%rbp),%rax
│ │ testb $0x20,0x1799(%rax)
│ │↑ je 2a
│ │ mov 0x200(%rax),%rdi
│ │ mov %r13d,%edx
│ │ mov $0xffffffffc02595d8,%rsi
│ │→ callq netdev_warn
│ │↑ jmpq 2a
│d0:└─→mov 0x8(%rbp),%rsi
│ mov %rbp,%rdi
│ mov %eax,0x4(%rsp)
│ → callq ixgbe_remove_adapter.isra.77
│ mov 0x4(%rsp),%eax
Press 'h' for help on key bindings
============================================================================
Pess 'O':
Samples: 64 of event 'cycles:ppp', 100000 Hz, Event count (approx.): 318963
ixgbe_read_reg /proc/kcore
Percent│ ↑ je 2a
│ ┌──cmp $0xffffffff,%r13d
│ ├──je d0
│ │ mov $0x53e3,%edi
│99:│→ callq __const_udelay
│ │ sub $0x1,%r15d
│ │↑ jne 83
│ │ mov 0x8(%rbp),%rax
│ │ testb $0x20,0x1799(%rax)
│ │↑ je 2a
│ │ mov 0x200(%rax),%rdi
│ │ mov %r13d,%edx
│ │ mov $0xffffffffc02595d8,%rsi
│c6:│→ callq netdev_warn
│ │↑ jmpq 2a
│d0:└─→mov 0x8(%rbp),%rsi
│ mov %rbp,%rdi
│ mov %eax,0x4(%rsp)
│db: → callq ixgbe_remove_adapter.isra.77
│ mov 0x4(%rsp),%eax
Press 'h' for help on key bindings
============================================================================
Press 'O' again:
Samples: 64 of event 'cycles:ppp', 100000 Hz, Event count (approx.): 318963
ixgbe_read_reg /proc/kcore
Percent│8c: ↑ je 2a
│8e:┌──cmp $0xffffffff,%r13d
│92:├──je d0
│94:│ mov $0x53e3,%edi
│99:│→ callq __const_udelay
│9e:│ sub $0x1,%r15d
│a2:│↑ jne 83
│a4:│ mov 0x8(%rbp),%rax
│a8:│ testb $0x20,0x1799(%rax)
│af:│↑ je 2a
│b5:│ mov 0x200(%rax),%rdi
│bc:│ mov %r13d,%edx
│bf:│ mov $0xffffffffc02595d8,%rsi
│c6:│→ callq netdev_warn
│cb:│↑ jmpq 2a
│d0:└─→mov 0x8(%rbp),%rsi
│d4: mov %rbp,%rdi
│d7: mov %eax,0x4(%rsp)
│db: → callq ixgbe_remove_adapter.isra.77
│e0: mov 0x4(%rsp),%eax
Press 'h' for help on key bindings
============================================================================
Press 'O' again and it will show just jump target offsets.
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Liška <mliska@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-upp6pfdetwlsx18ec2uf1od4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-11 13:41:23 +00:00
|
|
|
"O Bump offset level (jump targets -> +call -> all -> cycle thru)\n"
|
2012-05-12 19:36:55 +00:00
|
|
|
"s Toggle source code view\n"
|
2017-08-18 08:47:08 +00:00
|
|
|
"t Circulate percent, total period, samples view\n"
|
perf annotate: Create hotkey 'c' to show min/max cycles
In the 'perf annotate' view, a new hotkey 'c' is created for showing the
min/max cycles.
For example, when press 'c', the annotate view is:
Percent│ IPC Cycle(min/max)
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@G
│3.92 1(2/1) ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_P
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+
8.93 │1.10 1(5/1) ↓ je 43
When press 'c' again, the annotate view is switched back:
Percent│ IPC Cycle
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x
│3.92 1 ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
8.93 │1.10 1 ↓ je 43
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1526569118-14217-3-git-send-email-yao.jin@linux.intel.com
[ Rename all maxmin to minmax ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-17 14:58:38 +00:00
|
|
|
"c Show min/max cycle\n"
|
2012-05-12 19:36:55 +00:00
|
|
|
"/ Search string\n"
|
2014-11-13 02:05:26 +00:00
|
|
|
"k Toggle line numbers\n"
|
2021-02-15 11:34:46 +00:00
|
|
|
"l Show full source file location\n"
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
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-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 19:57:47 +00:00
|
|
|
"P Print to [symbol_name].annotation file.\n"
|
2012-10-30 03:56:05 +00:00
|
|
|
"r Run available scripts\n"
|
2018-08-04 13:05:17 +00:00
|
|
|
"p Toggle percent type [local/global]\n"
|
|
|
|
"b Toggle percent base [period/hits]\n"
|
2013-08-07 18:55:48 +00:00
|
|
|
"? Search string backwards\n");
|
2012-05-12 19:36:55 +00:00
|
|
|
continue;
|
2012-10-30 03:56:05 +00:00
|
|
|
case 'r':
|
2020-02-13 06:42:59 +00:00
|
|
|
script_browse(NULL, NULL);
|
|
|
|
annotate_browser__show(&browser->b, title, help);
|
|
|
|
continue;
|
2014-11-13 02:05:26 +00:00
|
|
|
case 'k':
|
2018-03-15 15:33:56 +00:00
|
|
|
notes->options->show_linenr = !notes->options->show_linenr;
|
2021-02-15 12:45:25 +00:00
|
|
|
continue;
|
2021-02-15 11:34:46 +00:00
|
|
|
case 'l':
|
|
|
|
annotate_browser__show_full_location (&browser->b);
|
|
|
|
continue;
|
2012-05-12 19:36:55 +00:00
|
|
|
case 'H':
|
2012-05-30 01:42:18 +00:00
|
|
|
nd = browser->curr_hot;
|
2010-08-10 18:14:53 +00:00
|
|
|
break;
|
2012-02-23 08:46:21 +00:00
|
|
|
case 's':
|
2012-05-30 01:42:18 +00:00
|
|
|
if (annotate_browser__toggle_source(browser))
|
2011-10-14 15:31:21 +00:00
|
|
|
ui_helpline__puts(help);
|
|
|
|
continue;
|
2012-04-02 16:21:55 +00:00
|
|
|
case 'o':
|
2018-03-15 15:33:56 +00:00
|
|
|
notes->options->use_offset = !notes->options->use_offset;
|
2018-03-15 19:18:21 +00:00
|
|
|
annotation__update_column_widths(notes);
|
2012-04-02 16:21:55 +00:00
|
|
|
continue;
|
perf annotate browser: Allow showing offsets in more than just jump targets
Jesper wanted to see offsets at callq sites when doing some performance
investigation related to retpolines, so save him some time by providing
a 'O' hotkey to allow showing offsets from function start at call
instructions or in all instructions, just go on pressing 'O' till the
offsets you need appear.
Example:
Starts with:
Samples: 64 of event 'cycles:ppp', 100000 Hz, Event count (approx.): 318963
ixgbe_read_reg /proc/kcore
Percent│ ↑ je 2a
│ ┌──cmp $0xffffffff,%r13d
│ ├──je d0
│ │ mov $0x53e3,%edi
│ │→ callq __const_udelay
│ │ sub $0x1,%r15d
│ │↑ jne 83
│ │ mov 0x8(%rbp),%rax
│ │ testb $0x20,0x1799(%rax)
│ │↑ je 2a
│ │ mov 0x200(%rax),%rdi
│ │ mov %r13d,%edx
│ │ mov $0xffffffffc02595d8,%rsi
│ │→ callq netdev_warn
│ │↑ jmpq 2a
│d0:└─→mov 0x8(%rbp),%rsi
│ mov %rbp,%rdi
│ mov %eax,0x4(%rsp)
│ → callq ixgbe_remove_adapter.isra.77
│ mov 0x4(%rsp),%eax
Press 'h' for help on key bindings
============================================================================
Pess 'O':
Samples: 64 of event 'cycles:ppp', 100000 Hz, Event count (approx.): 318963
ixgbe_read_reg /proc/kcore
Percent│ ↑ je 2a
│ ┌──cmp $0xffffffff,%r13d
│ ├──je d0
│ │ mov $0x53e3,%edi
│99:│→ callq __const_udelay
│ │ sub $0x1,%r15d
│ │↑ jne 83
│ │ mov 0x8(%rbp),%rax
│ │ testb $0x20,0x1799(%rax)
│ │↑ je 2a
│ │ mov 0x200(%rax),%rdi
│ │ mov %r13d,%edx
│ │ mov $0xffffffffc02595d8,%rsi
│c6:│→ callq netdev_warn
│ │↑ jmpq 2a
│d0:└─→mov 0x8(%rbp),%rsi
│ mov %rbp,%rdi
│ mov %eax,0x4(%rsp)
│db: → callq ixgbe_remove_adapter.isra.77
│ mov 0x4(%rsp),%eax
Press 'h' for help on key bindings
============================================================================
Press 'O' again:
Samples: 64 of event 'cycles:ppp', 100000 Hz, Event count (approx.): 318963
ixgbe_read_reg /proc/kcore
Percent│8c: ↑ je 2a
│8e:┌──cmp $0xffffffff,%r13d
│92:├──je d0
│94:│ mov $0x53e3,%edi
│99:│→ callq __const_udelay
│9e:│ sub $0x1,%r15d
│a2:│↑ jne 83
│a4:│ mov 0x8(%rbp),%rax
│a8:│ testb $0x20,0x1799(%rax)
│af:│↑ je 2a
│b5:│ mov 0x200(%rax),%rdi
│bc:│ mov %r13d,%edx
│bf:│ mov $0xffffffffc02595d8,%rsi
│c6:│→ callq netdev_warn
│cb:│↑ jmpq 2a
│d0:└─→mov 0x8(%rbp),%rsi
│d4: mov %rbp,%rdi
│d7: mov %eax,0x4(%rsp)
│db: → callq ixgbe_remove_adapter.isra.77
│e0: mov 0x4(%rsp),%eax
Press 'h' for help on key bindings
============================================================================
Press 'O' again and it will show just jump target offsets.
Suggested-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Liška <mliska@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-upp6pfdetwlsx18ec2uf1od4@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-11 13:41:23 +00:00
|
|
|
case 'O':
|
|
|
|
if (++notes->options->offset_level > ANNOTATION__MAX_OFFSET_LEVEL)
|
|
|
|
notes->options->offset_level = ANNOTATION__MIN_OFFSET_LEVEL;
|
|
|
|
continue;
|
2012-04-27 19:35:29 +00:00
|
|
|
case 'j':
|
2018-03-15 15:33:56 +00:00
|
|
|
notes->options->jump_arrows = !notes->options->jump_arrows;
|
2012-04-27 19:35:29 +00:00
|
|
|
continue;
|
2012-05-12 19:21:53 +00:00
|
|
|
case 'J':
|
2018-03-15 15:33:56 +00:00
|
|
|
notes->options->show_nr_jumps = !notes->options->show_nr_jumps;
|
2018-03-15 19:18:21 +00:00
|
|
|
annotation__update_column_widths(notes);
|
2012-05-30 00:24:05 +00:00
|
|
|
continue;
|
2012-04-07 20:10:30 +00:00
|
|
|
case '/':
|
2012-05-30 01:42:18 +00:00
|
|
|
if (annotate_browser__search(browser, delay_secs)) {
|
2012-04-07 20:10:30 +00:00
|
|
|
show_help:
|
|
|
|
ui_helpline__puts(help);
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
case 'n':
|
2012-05-30 01:42:18 +00:00
|
|
|
if (browser->searching_backwards ?
|
|
|
|
annotate_browser__continue_search_reverse(browser, delay_secs) :
|
|
|
|
annotate_browser__continue_search(browser, delay_secs))
|
2012-04-07 20:10:30 +00:00
|
|
|
goto show_help;
|
|
|
|
continue;
|
|
|
|
case '?':
|
2012-05-30 01:42:18 +00:00
|
|
|
if (annotate_browser__search_reverse(browser, delay_secs))
|
2012-04-07 20:10:30 +00:00
|
|
|
goto show_help;
|
|
|
|
continue;
|
2012-05-30 00:24:05 +00:00
|
|
|
case 'D': {
|
|
|
|
static int seq;
|
|
|
|
ui_helpline__pop();
|
|
|
|
ui_helpline__fpush("%d: nr_ent=%d, height=%d, idx=%d, top_idx=%d, nr_asm_entries=%d",
|
2012-05-30 01:42:18 +00:00
|
|
|
seq++, browser->b.nr_entries,
|
|
|
|
browser->b.height,
|
|
|
|
browser->b.index,
|
|
|
|
browser->b.top_idx,
|
2018-03-15 18:52:33 +00:00
|
|
|
notes->nr_asm_entries);
|
2012-05-30 00:24:05 +00:00
|
|
|
}
|
|
|
|
continue;
|
2011-10-20 18:59:15 +00:00
|
|
|
case K_ENTER:
|
|
|
|
case K_RIGHT:
|
2017-11-06 10:56:17 +00:00
|
|
|
{
|
|
|
|
struct disasm_line *dl = disasm_line(browser->selection);
|
|
|
|
|
2012-05-30 01:42:18 +00:00
|
|
|
if (browser->selection == NULL)
|
2011-10-06 12:45:29 +00:00
|
|
|
ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
|
2017-11-06 10:56:17 +00:00
|
|
|
else if (browser->selection->offset == -1)
|
2011-10-06 12:45:29 +00:00
|
|
|
ui_helpline__puts("Actions are only available for assembly lines.");
|
2017-11-06 10:56:17 +00:00
|
|
|
else if (!dl->ins.ops)
|
2016-06-24 11:53:58 +00:00
|
|
|
goto show_sup_ins;
|
2017-11-06 10:56:17 +00:00
|
|
|
else if (ins__is_ret(&dl->ins))
|
2012-04-20 18:57:15 +00:00
|
|
|
goto out;
|
perf annotate: Support jumping from one function to another
For instance:
entry_SYSCALL_64 /lib/modules/4.16.0-rc5-00086-gdf09348f78dc/build/vmlinux
5.50 │ → callq do_syscall_64
14.56 │ mov 0x58(%rsp),%rcx
7.44 │ mov 0x80(%rsp),%r11
0.32 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ shl $0x10,%rcx
0.32 │ sar $0x10,%rcx
3.24 │ cmp %rcx,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
2.27 │ cmpq $0x33,0x88(%rsp)
1.29 │ → jne swapgs_restore_regs_and_return_to_usermode
│ mov 0x30(%rsp),%r11
8.74 │ cmp %r11,0x90(%rsp)
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ test $0x10100,%r11
│ → jne swapgs_restore_regs_and_return_to_usermode
0.32 │ cmpq $0x2b,0xa0(%rsp)
0.65 │ → jne swapgs_restore_regs_and_return_to_usermode
It'll behave just like a "call" instruction, i.e. press enter or right
arrow over one such line and the browser will navigate to the annotated
disassembly of that function, which when exited, via left arrow or esc,
will come back to the calling function.
Now to support jump to an offset on a different function...
Reported-by: Linus Torvalds <torvalds@linux-foundation.org>
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-78o508mqvr8inhj63ddtw7mo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-23 13:50:35 +00:00
|
|
|
else if (!(annotate_browser__jump(browser, evsel, hbt) ||
|
2013-03-05 05:53:21 +00:00
|
|
|
annotate_browser__callq(browser, evsel, hbt))) {
|
2012-04-20 18:57:15 +00:00
|
|
|
show_sup_ins:
|
2016-06-24 11:53:58 +00:00
|
|
|
ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
|
2012-04-20 18:57:15 +00:00
|
|
|
}
|
2011-10-19 15:18:13 +00:00
|
|
|
continue;
|
2017-11-06 10:56:17 +00:00
|
|
|
}
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
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-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 19:57:47 +00:00
|
|
|
case 'P':
|
2018-08-04 13:05:15 +00:00
|
|
|
map_symbol__annotation_dump(ms, evsel, browser->opts);
|
perf annotate browser: Add 'P' hotkey to dump annotation to file
Just like we have in the histograms browser used as the main screen for
'perf top --tui' and 'perf report --tui', to print the current
annotation to a file with a named composed by the symbol name and the
".annotation" suffix.
Here is one example of pressing 'A' on 'perf top' to live annotate a
kernel function and then press 'P' to dump that annotation, the
resulting file:
# cat _raw_spin_lock_irqsave.annotation
_raw_spin_lock_irqsave() /proc/kcore
Event: cycles:ppp
7.14 nop
21.43 push %rbx
7.14 pushfq
pop %rax
nop
mov %rax,%rbx
cli
nop
xor %eax,%eax
mov $0x1,%edx
64.29 lock cmpxchg %edx,(%rdi)
test %eax,%eax
↓ jne 2b
mov %rbx,%rax
pop %rbx
← retq
2b: mov %eax,%esi
→ callq queued_spin_lock_slowpath
mov %rbx,%rax
pop %rbx
← retq
#
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-zzmnrwugb5vtk7bvg0rbx150@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-03-16 19:57:47 +00:00
|
|
|
continue;
|
2015-06-19 19:10:43 +00:00
|
|
|
case 't':
|
2020-02-13 06:43:00 +00:00
|
|
|
if (symbol_conf.show_total_period) {
|
|
|
|
symbol_conf.show_total_period = false;
|
2020-02-13 06:43:01 +00:00
|
|
|
symbol_conf.show_nr_samples = true;
|
|
|
|
} else if (symbol_conf.show_nr_samples)
|
|
|
|
symbol_conf.show_nr_samples = false;
|
2017-08-18 08:47:08 +00:00
|
|
|
else
|
2020-02-13 06:43:00 +00:00
|
|
|
symbol_conf.show_total_period = true;
|
2018-03-15 19:18:21 +00:00
|
|
|
annotation__update_column_widths(notes);
|
2015-06-19 19:10:43 +00:00
|
|
|
continue;
|
perf annotate: Create hotkey 'c' to show min/max cycles
In the 'perf annotate' view, a new hotkey 'c' is created for showing the
min/max cycles.
For example, when press 'c', the annotate view is:
Percent│ IPC Cycle(min/max)
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@G
│3.92 1(2/1) ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_P
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+
8.93 │1.10 1(5/1) ↓ je 43
When press 'c' again, the annotate view is switched back:
Percent│ IPC Cycle
│
│
│ Disassembly of section .text:
│
│ 000000000003aab0 <random@@GLIBC_2.2.5>:
8.22 │3.92 sub $0x18,%rsp
│3.92 mov $0x1,%esi
│3.92 xor %eax,%eax
│3.92 cmpl $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x
│3.92 1 ↓ je 20
│ lock cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
│ ↓ jne 29
│ ↓ jmp 43
│1.10 20: cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
8.93 │1.10 1 ↓ je 43
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1526569118-14217-3-git-send-email-yao.jin@linux.intel.com
[ Rename all maxmin to minmax ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-05-17 14:58:38 +00:00
|
|
|
case 'c':
|
|
|
|
if (notes->options->show_minmax_cycle)
|
|
|
|
notes->options->show_minmax_cycle = false;
|
|
|
|
else
|
|
|
|
notes->options->show_minmax_cycle = true;
|
|
|
|
annotation__update_column_widths(notes);
|
|
|
|
continue;
|
2018-08-04 13:05:17 +00:00
|
|
|
case 'p':
|
|
|
|
case 'b':
|
|
|
|
switch_percent_type(browser->opts, key == 'b');
|
|
|
|
hists__scnprintf_title(hists, title, sizeof(title));
|
|
|
|
annotate_browser__show(&browser->b, title, help);
|
|
|
|
continue;
|
2011-10-20 18:59:15 +00:00
|
|
|
case K_LEFT:
|
|
|
|
case K_ESC:
|
2011-10-13 11:31:22 +00:00
|
|
|
case 'q':
|
|
|
|
case CTRL('c'):
|
2010-08-10 18:14:53 +00:00
|
|
|
goto out;
|
2011-10-13 11:31:22 +00:00
|
|
|
default:
|
|
|
|
continue;
|
2010-08-10 18:14:53 +00:00
|
|
|
}
|
2011-02-22 15:02:07 +00:00
|
|
|
|
|
|
|
if (nd != NULL)
|
2012-05-30 01:42:18 +00:00
|
|
|
annotate_browser__set_rb_top(browser, nd);
|
2010-08-10 18:14:53 +00:00
|
|
|
}
|
|
|
|
out:
|
2012-05-30 01:42:18 +00:00
|
|
|
ui_browser__hide(&browser->b);
|
2010-08-11 13:07:43 +00:00
|
|
|
return key;
|
2010-08-10 18:14:53 +00:00
|
|
|
}
|
|
|
|
|
2019-07-21 11:23:51 +00:00
|
|
|
int map_symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
|
2018-05-28 16:54:59 +00:00
|
|
|
struct hist_browser_timer *hbt,
|
|
|
|
struct annotation_options *opts)
|
2015-03-17 21:27:28 +00:00
|
|
|
{
|
2019-11-04 14:10:00 +00:00
|
|
|
return symbol__tui_annotate(ms, evsel, hbt, opts);
|
2015-03-17 21:27:28 +00:00
|
|
|
}
|
|
|
|
|
2019-07-21 11:23:51 +00:00
|
|
|
int hist_entry__tui_annotate(struct hist_entry *he, struct evsel *evsel,
|
2018-05-28 16:54:59 +00:00
|
|
|
struct hist_browser_timer *hbt,
|
|
|
|
struct annotation_options *opts)
|
2011-02-04 11:45:46 +00:00
|
|
|
{
|
2015-05-29 12:53:44 +00:00
|
|
|
/* reset abort key so that it can get Ctrl-C as a key */
|
|
|
|
SLang_reset_tty();
|
|
|
|
SLang_init_tty(0, 0, 0);
|
|
|
|
|
2018-05-28 16:54:59 +00:00
|
|
|
return map_symbol__tui_annotate(&he->ms, evsel, hbt, opts);
|
2011-02-04 11:45:46 +00:00
|
|
|
}
|
|
|
|
|
2019-11-04 14:10:00 +00:00
|
|
|
int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
|
2018-05-28 16:54:59 +00:00
|
|
|
struct hist_browser_timer *hbt,
|
|
|
|
struct annotation_options *opts)
|
2010-08-10 17:54:09 +00:00
|
|
|
{
|
2019-11-04 14:10:00 +00:00
|
|
|
struct symbol *sym = ms->sym;
|
2018-03-15 13:47:54 +00:00
|
|
|
struct annotation *notes = symbol__annotation(sym);
|
2010-08-09 18:30:40 +00:00
|
|
|
struct annotate_browser browser = {
|
|
|
|
.b = {
|
2012-04-24 17:24:28 +00:00
|
|
|
.refresh = annotate_browser__refresh,
|
2010-08-09 18:30:40 +00:00
|
|
|
.seek = ui_browser__list_head_seek,
|
|
|
|
.write = annotate_browser__write,
|
2012-04-15 18:24:39 +00:00
|
|
|
.filter = disasm_line__filter,
|
perf annotate browser: Show extra title line with event information
So at the top we'll have two lines, like this, from 'perf report':
# perf report --group --ignore-vmlinux
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Percent │ nop
│ push %rbx
0.00 14.29 0.00 │ pushfq
9.09 0.00 0.00 │ pop %rax
9.09 0.00 20.00 │ nop
│ mov %rax,%rbx
│ cli
4.55 7.14 0.00 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
77.27 78.57 70.00 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0.00 0.00 10.00 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
9.09 + 9.09 + 4.55 + 77.27 = 100
14.29 + 7.14 + 78.57 = 100
20 + 70 + 10 = 100
We can do the math by using 't' to toggle from 'percent' to nr
=====================================================================================================
Samples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Period │ nop
│ push %rbx
0 79273 0 │ pushfq
190455 0 0 │ pop %rax
198038 0 3045 │ nop
│ mov %rax,%rbx
│ cli
217233 32562 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
3421649 979174 28273 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 5193 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on│key bindings
=====================================================================================================
79273 + 190455 + 198038 + 3045 + 217233 + 32562 + 3421649 + 979174 + 28273 + 5193 = 5154895
Or number of samples:
=====================================================================================================
ooSamples: 46 of events 'cycles', 4000 Hz, Event count (approx.): 5154895
_raw_spin_lock_irqsave /proc/kcore
Samples │ nop
│ push %rbx
0 2 0 │ pushfq
2 0 0 │ pop %rax
2 0 2 │ nop
│ mov %rax,%rbx
│ cli
1 1 0 │ nop
│ xor %eax,%eax
│ mov $0x1,%edx
│ lock cmpxchg %edx,(%rdi)
17 11 7 │ test %eax,%eax
│ ↓ jne 2b
│ mov %rbx,%rax
0 0 1 │ pop %rbx
│ ← retq
│2b: mov %eax,%esi
│ → callq queued_spin_lock_slowpath
│ mov %rbx,%rax
│ pop %rbx
Press 'h' for help on key bindings
=====================================================================================================
2 + 2 + 2 + 2 + 1 + 1 + 17 + 11 + 7 + 1 = 46
Suggested-by: Martin Liška <mliska@suse.cz>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Wang Nan <wangnan0@huawei.com>
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196935
Link: https://lkml.kernel.org/n/tip-ezccyxld50wtwyt66np6aomo@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-04-02 19:18:45 +00:00
|
|
|
.extra_title_lines = 1, /* for hists__scnprintf_title() */
|
2019-11-04 14:10:00 +00:00
|
|
|
.priv = ms,
|
2011-10-18 16:31:35 +00:00
|
|
|
.use_navkeypressed = true,
|
2010-08-09 18:30:40 +00:00
|
|
|
},
|
2018-05-28 16:54:59 +00:00
|
|
|
.opts = opts,
|
2010-08-10 17:54:09 +00:00
|
|
|
};
|
2016-07-29 19:27:18 +00:00
|
|
|
int ret = -1, err;
|
2010-08-10 17:54:09 +00:00
|
|
|
|
2011-02-04 11:45:46 +00:00
|
|
|
if (sym == NULL)
|
2010-08-10 17:54:09 +00:00
|
|
|
return -1;
|
|
|
|
|
2019-11-04 14:10:00 +00:00
|
|
|
if (ms->map->dso->annotate_warned)
|
2010-08-10 17:54:09 +00:00
|
|
|
return -1;
|
|
|
|
|
2019-11-04 14:10:00 +00:00
|
|
|
err = symbol__annotate2(ms, evsel, opts, &browser.arch);
|
2016-07-29 19:27:18 +00:00
|
|
|
if (err) {
|
|
|
|
char msg[BUFSIZ];
|
2019-11-04 14:10:00 +00:00
|
|
|
symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
|
2016-07-29 19:27:18 +00:00
|
|
|
ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
|
perf annotate browser: Hide non jump target addresses in offset mode
This:
0.00 : ffffffff8116bd00: lock btsl $0x0,(%r12)
100.00 : ffffffff8116bd07: sbb %eax,%eax
0.00 : ffffffff8116bd09: test %eax,%eax
0.00 : ffffffff8116bd0b: jne ffffffff8116bf5f <__mem_cgroup_commit_charge+0x28f>
0.00 : ffffffff8116bd11: mov (%r12),%rax
0.00 : ffffffff8116bd15: test $0x2,%al
0.00 : ffffffff8116bd17: jne ffffffff8116bf6e <__mem_cgroup_commit_charge+0x29e>
0.00 : ffffffff8116bd1d: test %r9b,%r9b
0.00 : ffffffff8116bd20: jne ffffffff8116be30 <__mem_cgroup_commit_charge+0x160>
0.00 : ffffffff8116bd26: xor %eax,%eax
0.00 : ffffffff8116bd28: mov %r13,0x8(%r12)
0.00 : ffffffff8116bd2d: lock orb $0x2,(%r12)
0.00 : ffffffff8116bd33: test %r9b,%r9b
0.00 : ffffffff8116bd36: je ffffffff8116bdf3 <__mem_cgroup_commit_charge+0x123>
Becomes:
0.00 : 30: lock btsl $0x0,(%r12)
100.00 : sbb %eax,%eax
0.00 : test %eax,%eax
0.00 : jne 28f
0.00 : mov (%r12),%rax
0.00 : test $0x2,%al
0.00 : jne 29e
0.00 : test %r9b,%r9b
0.00 : jne 160
0.00 : 56: xor %eax,%eax
0.00 : 58: mov %r13,0x8(%r12)
0.00 : lock orb $0x2,(%r12)
0.00 : test %r9b,%r9b
0.00 : je 123
I.e. We trow away all those useless addresses and keep just jump labels.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.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-r2vmbtgz0l8coluj8flztgrn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-19 15:19:22 +00:00
|
|
|
goto out_free_offsets;
|
2010-08-10 17:54:09 +00:00
|
|
|
}
|
|
|
|
|
2015-10-12 16:56:50 +00:00
|
|
|
ui_helpline__push("Press ESC to exit");
|
2010-08-10 17:54:09 +00:00
|
|
|
|
2018-03-15 18:59:01 +00:00
|
|
|
browser.b.width = notes->max_line_len;
|
2018-03-15 18:52:33 +00:00
|
|
|
browser.b.nr_entries = notes->nr_entries;
|
2011-04-08 06:31:26 +00:00
|
|
|
browser.b.entries = ¬es->src->source,
|
2010-08-09 18:30:40 +00:00
|
|
|
browser.b.width += 18; /* Percentage */
|
2012-05-30 00:24:05 +00:00
|
|
|
|
2018-03-15 15:33:56 +00:00
|
|
|
if (notes->options->hide_src_code)
|
2018-03-15 18:52:33 +00:00
|
|
|
ui_browser__init_asm_mode(&browser.b);
|
2012-05-30 00:24:05 +00:00
|
|
|
|
2013-03-05 05:53:21 +00:00
|
|
|
ret = annotate_browser__run(&browser, evsel, hbt);
|
2017-10-11 15:01:38 +00:00
|
|
|
|
|
|
|
annotated_source__purge(notes->src);
|
perf annotate browser: Hide non jump target addresses in offset mode
This:
0.00 : ffffffff8116bd00: lock btsl $0x0,(%r12)
100.00 : ffffffff8116bd07: sbb %eax,%eax
0.00 : ffffffff8116bd09: test %eax,%eax
0.00 : ffffffff8116bd0b: jne ffffffff8116bf5f <__mem_cgroup_commit_charge+0x28f>
0.00 : ffffffff8116bd11: mov (%r12),%rax
0.00 : ffffffff8116bd15: test $0x2,%al
0.00 : ffffffff8116bd17: jne ffffffff8116bf6e <__mem_cgroup_commit_charge+0x29e>
0.00 : ffffffff8116bd1d: test %r9b,%r9b
0.00 : ffffffff8116bd20: jne ffffffff8116be30 <__mem_cgroup_commit_charge+0x160>
0.00 : ffffffff8116bd26: xor %eax,%eax
0.00 : ffffffff8116bd28: mov %r13,0x8(%r12)
0.00 : ffffffff8116bd2d: lock orb $0x2,(%r12)
0.00 : ffffffff8116bd33: test %r9b,%r9b
0.00 : ffffffff8116bd36: je ffffffff8116bdf3 <__mem_cgroup_commit_charge+0x123>
Becomes:
0.00 : 30: lock btsl $0x0,(%r12)
100.00 : sbb %eax,%eax
0.00 : test %eax,%eax
0.00 : jne 28f
0.00 : mov (%r12),%rax
0.00 : test $0x2,%al
0.00 : jne 29e
0.00 : test %r9b,%r9b
0.00 : jne 160
0.00 : 56: xor %eax,%eax
0.00 : 58: mov %r13,0x8(%r12)
0.00 : lock orb $0x2,(%r12)
0.00 : test %r9b,%r9b
0.00 : je 123
I.e. We trow away all those useless addresses and keep just jump labels.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.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-r2vmbtgz0l8coluj8flztgrn@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-19 15:19:22 +00:00
|
|
|
|
|
|
|
out_free_offsets:
|
2018-03-15 13:47:54 +00:00
|
|
|
zfree(¬es->offsets);
|
2010-08-10 17:54:09 +00:00
|
|
|
return ret;
|
|
|
|
}
|