[PATCH] perf report: fix off-by-one for non-activation frames

* [PATCH] perf report: fix off-by-one for non-activation frames
@ 2017-05-15 15:04 Milian Wolff
  2017-05-15 15:13 ` Milian Wolff
  2017-06-16  6:14 ` Jan Kratochvil
  0 siblings, 2 replies; 13+ messages in thread
From: Milian Wolff @ 2017-05-15 15:04 UTC (permalink / raw)
  To: Linux-kernel
  Cc: linux-perf-users, Milian Wolff, Arnaldo Carvalho de Melo,
	David Ahern, Namhyung Kim, Peter Zijlstra, Yao Jin

As the documentation for dwfl_frame_pc says, frames that
are no activation frames need to have their program counter
decremented by one to properly find the function of the caller.

This fixes many cases where perf report currently attributes
the cost to the next line. I.e. I have code like this:

~~~~~~~~~~~~~~~
  #include <thread>
  #include <chrono>

  using namespace std;

  int main()
  {
    this_thread::sleep_for(chrono::milliseconds(1000));
    this_thread::sleep_for(chrono::milliseconds(100));
    this_thread::sleep_for(chrono::milliseconds(10));

    return 0;
  }
~~~~~~~~~~~~~~~

Now compile and record it:

~~~~~~~~~~~~~~~
g++ -std=c++11 -g -O2 test.cpp
echo 1 | sudo tee /proc/sys/kernel/sched_schedstats
perf record \
    --event sched:sched_stat_sleep \
    --event sched:sched_process_exit \
    --event sched:sched_switch --call-graph=dwarf \
    --output perf.data.raw \
    ./a.out
echo 0 | sudo tee /proc/sys/kernel/sched_schedstats
perf inject --sched-stat --input perf.data.raw --output perf.data
~~~~~~~~~~~~~~~

Before this patch, the report clearly shows the off-by-one issue.
Most notably, the last sleep invocation is incorrectly attributed
to the "return 0;" line:

~~~~~~~~~~~~~~~
  Overhead  Source:Line
  ........  ...........

   100.00%  core.c:0
            |
            ---__schedule core.c:0
               schedule
               do_nanosleep hrtimer.c:0
               hrtimer_nanosleep
               sys_nanosleep
               entry_SYSCALL_64_fastpath .tmp_entry_64.o:0
               __nanosleep_nocancel .:0
               std::this_thread::sleep_for<long, std::ratio<1l, 1000l> > thread:323
               |
               |--90.08%--main test.cpp:9
               |          __libc_start_main
               |          _start
               |
               |--9.01%--main test.cpp:10
               |          __libc_start_main
               |          _start
               |
                --0.91%--main test.cpp:13
                          __libc_start_main
                          _start
~~~~~~~~~~~~~~~

When compiling perf using libdwfl for unwinding instead of libunwind
and having this patch here applied, the issue is fixed. The report
becomes much more usable:

~~~~~~~~~~~~~~~
  Overhead  Source:Line
  ........  ...........

   100.00%  core.c:0
            |
            ---__schedule core.c:0
               schedule
               do_nanosleep hrtimer.c:0
               hrtimer_nanosleep
               sys_nanosleep
               entry_SYSCALL_64_fastpath .tmp_entry_64.o:0
               __nanosleep_nocancel .:0
               std::this_thread::sleep_for<long, std::ratio<1l, 1000l> > thread:323
               |
               |--90.08%--main test.cpp:8
               |          __libc_start_main
               |          _start
               |
               |--9.01%--main test.cpp:9
               |          __libc_start_main
               |          _start
               |
                --0.91%--main test.cpp:10
                          __libc_start_main
                          _start
~~~~~~~~~~~~~~~

Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Yao Jin <yao.jin@linux.intel.com>
Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
---
 tools/perf/util/unwind-libdw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index f90e11a555b2..943a06291587 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -168,12 +168,16 @@ frame_callback(Dwfl_Frame *state, void *arg)
 {
 	struct unwind_info *ui = arg;
 	Dwarf_Addr pc;
+	bool isactivation;
 
-	if (!dwfl_frame_pc(state, &pc, NULL)) {
+	if (!dwfl_frame_pc(state, &pc, &isactivation)) {
 		pr_err("%s", dwfl_errmsg(-1));
 		return DWARF_CB_ABORT;
 	}
 
+	if (!isactivation)
+		--pc;
+
 	return entry(pc, ui) || !(--ui->max_stack) ?
 	       DWARF_CB_ABORT : DWARF_CB_OK;
 }
-- 
2.13.0

^ permalink raw reply related	[flat|nested] 13+ messages in thread