[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20151119063709.GA14852@gmail.com>
Date: Thu, 19 Nov 2015 07:37:10 +0100
From: Ingo Molnar <mingo@...nel.org>
To: "Wangnan (F)" <wangnan0@...wei.com>
Cc: Jiri Olsa <jolsa@...nel.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
David Ahern <dsahern@...il.com>,
Peter Zijlstra <peterz@...radead.org>,
Milian Wolff <milian.wolff@...b.com>,
linux-kernel@...r.kernel.org, pi3orama <pi3orama@....com>,
lizefan 00213767 <lizefan@...wei.com>
Subject: Re: [BUG REPORT] perf tools: x86_64: Broken calllchain when sampling
taken at 'callq' instruction
* Wangnan (F) <wangnan0@...wei.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@...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