lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ffd1839b-df82-7e49-62dd-704811af651b@gmail.com>
Date:   Tue, 28 Mar 2017 23:21:33 +0900
From:   Taeung Song <treeze.taeung@...il.com>
To:     Arnaldo Carvalho de Melo <arnaldo.melo@...il.com>
Cc:     linux-kernel@...r.kernel.org, Jiri Olsa <jolsa@...nel.org>,
        Namhyung Kim <namhyung@...nel.org>,
        Ingo Molnar <mingo@...nel.org>,
        Peter Zijlstra <peterz@...radead.org>,
        Wang Nan <wangnan0@...wei.com>,
        Masami Hiramatsu <mhiramat@...nel.org>,
        Jiri Olsa <jolsa@...hat.com>, Martin Liska <mliska@...e.cz>
Subject: Re: [PATCH v4] perf annotate: Fix missing number of samples for
 source_line_samples



On 03/28/2017 10:48 PM, Arnaldo Carvalho de Melo wrote:
> Em Tue, Mar 28, 2017 at 09:12:05PM +0900, Taeung Song escreveu:
>> The option 'show-total-period' works fine without a option '-l'.
>> But if running 'perf annotate --stdio -l --show-total-period',
>> you can see a problem showing only zero '0' for number of samples.
>
> If you do that at that point, don't you have to change the TUI not to do
> it again?
>
> - Arnaldo
>

Yes, there isn't the same problem when using 't' on TUI of 'perf annotate'.
(As you know, 't' is show-total-period option)

In 'annotate' TUI, we can use the 't' functionality without the problem.
Because of the code (util/annotate.c:911 and ui/browsers/annotate.c:412) 
as below.

  881 double disasm__calc_percent(struct annotation *notes, int evidx, 
s64 offset,
  882                             s64 end, const char **path, u64 
*nr_samples)
  883 {
  ...
  910                 if (h->sum) {
  911                         *nr_samples = hits;

And,

  378 static void annotate_browser__calc_percent(struct annotate_browser 
*browser,
  379                                            struct perf_evsel *evsel)
  380 {
  ...
  407                         bpos->samples[i].percent = 
disasm__calc_percent(notes,
  408                                                 evsel->idx + i,
  409                                                 pos->offset,
  410                                                 next ? 
next->offset : len,
  411                                                 &path, &nr_samples);
  412                         bpos->samples[i].nr = nr_samples;


And 'perf annotate --stdio --show-total-period' hasn't the problem, too.
Because of the same code (util/annotate.c:911).


But if with '-l', i.e. 'perf annotate --stdio -l --show-total-period',
the problem happen. Because 'nr' of source_line_samples aren't 
ordinarily set
in symbol__get_source_line() (util/annotate.c:1634~..)
,so fix it as this patch

Are there something I missed or misunderstand ?


Thanks,
Taeung


>> Before:
>>     $ perf annotate --stdio -l --show-total-period
>> ...
>>        0 :        400816:       push   %rbp
>>        0 :        400817:       mov    %rsp,%rbp
>>        0 :        40081a:       mov    %edi,-0x24(%rbp)
>>        0 :        40081d:       mov    %rsi,-0x30(%rbp)
>>        0 :        400821:       mov    -0x24(%rbp),%eax
>>        0 :        400824:       mov    -0x30(%rbp),%rdx
>>        0 :        400828:       mov    (%rdx),%esi
>>        0 :        40082a:       mov    $0x0,%edx
>> ...
>>
>> The reason is it was missed to set number of samples
>> of source_line_samples, so set it ordinarily.
>>
>> After:
>>     $ perf annotate --stdio -l --show-total-period
>> ...
>>        3 :        400816:       push   %rbp
>>        4 :        400817:       mov    %rsp,%rbp
>>        0 :        40081a:       mov    %edi,-0x24(%rbp)
>>        0 :        40081d:       mov    %rsi,-0x30(%rbp)
>>        1 :        400821:       mov    -0x24(%rbp),%eax
>>        2 :        400824:       mov    -0x30(%rbp),%rdx
>>        0 :        400828:       mov    (%rdx),%esi
>>        1 :        40082a:       mov    $0x0,%edx
>> ...
>>
>> Cc: Namhyung Kim <namhyung@...nel.org>
>> Cc: Jiri Olsa <jolsa@...hat.com>
>> Cc: Martin Liska <mliska@...e.cz>
>> Fixes: 0c4a5bcea460 ("perf annotate: Display total number of samples with --show-total-period")
>> Signed-off-by: Taeung Song <treeze.taeung@...il.com>
>> ---
>>  tools/perf/util/annotate.c | 6 ++++--
>>  tools/perf/util/annotate.h | 2 +-
>>  2 files changed, 5 insertions(+), 3 deletions(-)
>>
>> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
>> index 11af5f0..a37032b 100644
>> --- a/tools/perf/util/annotate.c
>> +++ b/tools/perf/util/annotate.c
>> @@ -1665,7 +1665,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
>>  	start = map__rip_2objdump(map, sym->start);
>>
>>  	for (i = 0; i < len; i++) {
>> -		u64 offset;
>> +		u64 offset, nr_samples;
>>  		double percent_max = 0.0;
>>
>>  		src_line->nr_pcnt = nr_pcnt;
>> @@ -1674,12 +1674,14 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
>>  			double percent = 0.0;
>>
>>  			h = annotation__histogram(notes, evidx + k);
>> +			nr_samples = h->addr[i];
>>  			if (h->sum)
>> -				percent = 100.0 * h->addr[i] / h->sum;
>> +				percent = 100.0 * nr_samples / h->sum;
>>
>>  			if (percent > percent_max)
>>  				percent_max = percent;
>>  			src_line->samples[k].percent = percent;
>> +			src_line->samples[k].nr = nr_samples;
>>  		}
>>
>>  		if (percent_max <= 0.5)
>> diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
>> index 09776b5..948aa8e 100644
>> --- a/tools/perf/util/annotate.h
>> +++ b/tools/perf/util/annotate.h
>> @@ -98,7 +98,7 @@ struct cyc_hist {
>>  struct source_line_samples {
>>  	double		percent;
>>  	double		percent_sum;
>> -	double          nr;
>> +	u64		nr;
>>  };
>>
>>  struct source_line {
>> --
>> 2.7.4

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ