public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Akihiro Nagai <akihiro.nagai.hw@hitachi.com>
To: David Ahern <dsahern@gmail.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>,
	Ingo Molnar <mingo@elte.hu>,
	Peter Zijlstra <peterz@infradead.org>,
	Frederic Weisbecker <fweisbec@gmail.com>,
	linux-kernel@vger.kernel.org,
	Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>,
	yrl.pp-manager.tt@hitachi.com, Paul Mackerras <paulus@samba.org>
Subject: Re: [PATCH -tip v2 3/6] perf script: resolve DSOs and symbols for user-space
Date: Thu, 21 Jul 2011 18:36:47 +0900	[thread overview]
Message-ID: <4E27F32F.4020606@hitachi.com> (raw)
In-Reply-To: <4E230BDA.5020305@gmail.com>

(2011/07/18 1:20), David Ahern wrote:
> On 07/17/2011 03:30 AM, Akihiro Nagai wrote:
>> Resolve user-space DSOs and symbols.
>> Latest perf-script can resolve DSOs and symbols for only kernel
>> and kernel modules. This patch resolves them for other
>> executable binaries.
>
> The description is a bit misleading. perf script does resolve symbols
> for userspace. e.g., the example in the bug fix I submitted in May:
> https://lkml.org/lkml/2011/5/30/223
>
> Do you look into why the cpumode setting is not working that you have to
> try specific settings?
Indeed, perf already can resolve user-space symbols and DSOs if cpumode has
the flag PERF_RECORD_MISC_USER. I found this change is incorrect.
To solve this, I'd like to set both flags PERF_RECORD_MISC_KERNEL and USER
to BTS records, because BTS traces both kernel and user space while it
generates interrupts.

And also, I think there is the probrem in thread__find_addr_map().
When this function is called with cpumode that is set (PERF_RECORD_MISC_KERNEL | USER),
this function processes only PERF_RECORD_MISC_KERNEL. So, I'd like to fix it too.

Thank you.
>
> David
>
>
>>
>> # perf script -f ip,addr,sym,dso
>> 3f03e016b0 ffffffff814675d2 irq_return ([kernel.kallsyms])
>> 3f03e016b0 ffffffff814675d2 irq_return ([kernel.kallsyms])
>> 3f03e04b80       3f03e016b3 _start (/lib64/ld-2.14.so)
>> 3f03e04b80 ffffffff814675d2 irq_return ([kernel.kallsyms])
>> 3f03e04ba6 ffffffff814675d2 irq_return ([kernel.kallsyms])
>> 3f03e04bad ffffffff814675d2 irq_return ([kernel.kallsyms])
>> 3f03e04c1d       3f03e04bfb _dl_start (/lib64/ld-2.14.so)
>> 3f03e04c00       3f03e04c21 _dl_start (/lib64/ld-2.14.so)
>> 3f03e04c00       3f03e04c21 _dl_start (/lib64/ld-2.14.so)
>> [snip]
>>
>> Signed-off-by: Akihiro Nagai<akihiro.nagai.hw@hitachi.com>
>> Cc: Peter Zijlstra<peterz@infradead.org>
>> Cc: Frederic Weisbecker<fweisbec@gmail.com>
>> Cc: Paul Mackerras<paulus@samba.org>
>> Cc: Ingo Molnar<mingo@elte.hu>
>> Cc: Arnaldo Carvalho de Melo<acme@infradead.org>
>> Cc: David Ahern<dsahern@gmail.com>
>> Cc: Masami Hiramatsu<masami.hiramatsu.pt@hitachi.com>
>> ---
>>
>>   tools/perf/builtin-script.c |    4 ++++
>>   tools/perf/util/event.c     |    5 +++++
>>   2 files changed, 9 insertions(+), 0 deletions(-)
>>
>> diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
>> index b3e0951..2356198 100644
>> --- a/tools/perf/builtin-script.c
>> +++ b/tools/perf/builtin-script.c
>> @@ -328,6 +328,10 @@ static void print_sample_addr(union perf_event *event,
>>
>>   	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
>>   			      event->ip.pid, sample->addr,&al);
>> +	/* try to resolve for user space */
>> +	if (!al.map)
>> +		thread__find_addr_map(thread, session, PERF_RECORD_MISC_USER,
>> +			MAP__FUNCTION, event->ip.pid, sample->addr,&al);
>>   	if (!al.map)
>>   		thread__find_addr_map(thread, session, cpumode, MAP__VARIABLE,
>>   				      event->ip.pid, sample->addr,&al);
>> diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
>> index 3c1b8a6..49a9315 100644
>> --- a/tools/perf/util/event.c
>> +++ b/tools/perf/util/event.c
>> @@ -771,6 +771,11 @@ int perf_event__preprocess_sample(const union perf_event *event,
>>
>>   	thread__find_addr_map(thread, session, cpumode, MAP__FUNCTION,
>>   			      event->ip.pid, event->ip.ip, al);
>> +	/* try to resolve for user space */
>> +	if (!al->map)
>> +		thread__find_addr_map(thread, session, PERF_RECORD_MISC_USER,
>> +				MAP__FUNCTION, event->ip.pid, event->ip.ip, al);
>> +
>>   	dump_printf(" ...... dso: %s\n",
>>   		    al->map ? al->map->dso->long_name :
>>   			al->level == 'H' ? "[hypervisor]" : "<not found>");
>>

  reply	other threads:[~2011-07-21  9:36 UTC|newest]

Thread overview: 22+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-07-17  9:30 [PATCH -tip v2 0/6] perf script: add BTS analysis features Akihiro Nagai
2011-07-17  9:30 ` [PATCH -tip v2 1/6] [BUGFIX] perf script: print correct IP address Akihiro Nagai
2011-07-17 15:59   ` David Ahern
2011-07-17 17:29     ` Frederic Weisbecker
2011-07-17  9:30 ` [PATCH -tip v2 2/6] perf script: add magic word to indicate the failure of resolving symbols Akihiro Nagai
2011-07-17 16:07   ` David Ahern
2011-07-17 16:30     ` David Ahern
2011-07-21  9:36       ` Akihiro Nagai
2011-07-21  9:42         ` Peter Zijlstra
2011-07-21 14:39         ` David Ahern
2011-07-22  4:25           ` Akihiro Nagai
2011-07-17  9:30 ` [PATCH -tip v2 3/6] perf script: resolve DSOs and symbols for user-space Akihiro Nagai
2011-07-17 16:20   ` David Ahern
2011-07-21  9:36     ` Akihiro Nagai [this message]
2011-07-17  9:31 ` [PATCH -tip v2 4/6] perf script: print DSOs and symbols for BTS branch_from addr Akihiro Nagai
2011-07-17 16:22   ` David Ahern
2011-07-21  9:36     ` Akihiro Nagai
2011-07-17  9:31 ` [PATCH -tip v2 5/6] perf script: add the offset field specifier Akihiro Nagai
2011-07-17 16:28   ` David Ahern
2011-07-17  9:31 ` [PATCH -tip v2 6/6] perf script: add option resolving vmlinux path Akihiro Nagai
2011-07-17 16:36   ` David Ahern
2011-07-21  9:36     ` Akihiro Nagai

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4E27F32F.4020606@hitachi.com \
    --to=akihiro.nagai.hw@hitachi.com \
    --cc=acme@infradead.org \
    --cc=dsahern@gmail.com \
    --cc=fweisbec@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=masami.hiramatsu.pt@hitachi.com \
    --cc=mingo@elte.hu \
    --cc=paulus@samba.org \
    --cc=peterz@infradead.org \
    --cc=yrl.pp-manager.tt@hitachi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox