[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABPqkBTVBG92pUu-H+CSO4T1HojQsun7ngZ8Z8PJUFt-MwXkRg@mail.gmail.com>
Date: Wed, 13 Jun 2012 15:51:11 +0200
From: Stephane Eranian <eranian@...gle.com>
To: Peter Zijlstra <a.p.zijlstra@...llo.nl>
Cc: Jiri Olsa <jolsa@...hat.com>, acme@...hat.com, mingo@...e.hu,
paulus@...ba.org, cjashfor@...ux.vnet.ibm.com, fweisbec@...il.com,
gorcunov@...nvz.org, tzanussi@...il.com, mhiramat@...hat.com,
robert.richter@....com, fche@...hat.com,
linux-kernel@...r.kernel.org, masami.hiramatsu.pt@...achi.com,
drepper@...il.com, asharma@...com, benjamin.redelings@...cent.org
Subject: Re: [PATCH 02/19] perf: Add ability to attach user level registers
dump to sample
On Wed, Jun 13, 2012 at 3:41 PM, Stephane Eranian <eranian@...gle.com> wrote:
> On Wed, Jun 13, 2012 at 3:40 PM, Peter Zijlstra <a.p.zijlstra@...llo.nl> wrote:
>> On Wed, 2012-06-13 at 15:18 +0200, Stephane Eranian wrote:
>>>
>>> If you look carefully at perf_output_sample(), you will notice that data is
>>> written in the exact order of the enum perf_event_sample_format.
>>
>> Not so actually.. CALLCHAIN is out of order. Not sure why we did that
>> though.
>>
>>
>> But it should match the comment near PERF_RECORD_SAMPLE.
>
> Ok, yes that one. It would have been much nicer to follow the enum
> order.
In that case, the comment needs to be update to show the sample_user_regs[]
in the right order.
* { u32 size;
* char data[size];}&& PERF_SAMPLE_RAW
*
* { u64 from, to, flags } lbr[nr];} && PERF_SAMPLE_BRANCH_STACK
* { u64 size; u64 regs[size];} && PERF_SAMPLE_USER_REGS
Same thing for the user stack.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists