Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling taken at 'callq' instruction

From	Ingo Molnar <mingo@kernel.org>
Newsgroups	linux.kernel
Subject	Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling taken at 'callq' instruction
Date	2015-11-19 07:40 +0100
Message-ID	<qwr2V-5I2-5@gated-at.bofh.it> (permalink)
References	<qw5lL-8cX-3@gated-at.bofh.it> <qw68a-jO-27@gated-at.bofh.it> <qw6hQ-nn-15@gated-at.bofh.it> <qw6KS-Af-9@gated-at.bofh.it> <qw6KS-Af-7@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

* Wangnan (F) <wangnan0@huawei.com> wrote:

> >perf cmdline is
> >
> ># ./pref record  -g -F 9 --call-graph dwarf ./test_dwarf_unwind
> >
> >Use default events, precise_ip == 2 so uses PEBS.
> >
> 
> Testetd 'cycles', 'cycles:p' and 'cycles:pp'. Only 'cycles:pp' captures
> sample at callq. So maybe a PEBS problem?

Well, that's how our PEBS sampling works: we roll back the instruction pointer to 
point at the instruction generating the sample. The state itself is 
post-instruction.

So dwarf unwind has to take this into account. Should the kernel pass in the 
original (uncorrected) RIP as well, perhaps?

Thanks,

	Ingo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Thread

[BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-18 08:30 +0100
  Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-18 09:20 +0100
    Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Ingo Molnar <mingo@kernel.org> - 2015-11-18 09:30 +0100
      Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-18 10:00 +0100
        Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Ingo Molnar <mingo@kernel.org> - 2015-11-19 07:40 +0100
          Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-19 07:50 +0100
            Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Ingo Molnar <mingo@kernel.org> - 2015-11-19 11:30 +0100
              Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-19 11:50 +0100
                Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Peter Zijlstra <peterz@infradead.org> - 2015-11-19 12:30 +0100
              Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Peter Zijlstra <peterz@infradead.org> - 2015-11-19 12:30 +0100
                Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Ingo Molnar <mingo@kernel.org> - 2015-11-27 09:40 +0100
                Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Peter Zijlstra <peterz@infradead.org> - 2015-11-30 10:30 +0100
      Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-18 10:10 +0100
  Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction Jiri Olsa <jolsa@redhat.com> - 2015-11-18 09:50 +0100
    Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling  taken at 'callq' instruction "Wangnan (F)" <wangnan0@huawei.com> - 2015-11-18 10:20 +0100

csiph-web