perf report: Prefer DWARF callstacks to LBR ones when captured both

Display DWARF based callchains when the perf.data file contains raw thread
stack data as LBR callstack data.

Commiter testing:

This changes the output from the branch stack based one, i.e. without
this patch, for the same file as in the previous csets:

  # perf report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  # Total Lost Samples: 0
  #
  # Samples: 13  of event 'cycles'
  # Event count (approx.): 13
  #
  # Overhead  Command  Source Shared Object  Source Symbol                Target Symbol                              Basic Block Cycles
  # ........  .......  ....................  ...........................  .........................................  ..................
  #
       7.69%  ls       libpthread-2.29.so    [.] _init                    [.] __pthread_initialize_minimal_internal  6827
       7.69%  ls       ld-2.29.so            [k] _start                   [k] _dl_start                              -
       7.69%  ls       ld-2.29.so            [.] _dl_start_user           [.] _dl_init                               -24790
       7.69%  ls       ld-2.29.so            [k] _dl_start                [k] _dl_sysdep_start                       278
       7.69%  ls       ld-2.29.so            [k] dl_main                  [k] _dl_map_object_deps                    15581
       7.69%  ls       ld-2.29.so            [k] open_verify.constprop.0  [k] lseek64                                4228
       7.69%  ls       ld-2.29.so            [k] _dl_map_object           [k] open_verify.constprop.0                55
       7.69%  ls       ld-2.29.so            [k] openaux                  [k] _dl_map_object                         67
       7.69%  ls       ld-2.29.so            [k] _dl_map_object_deps      [k] 0x00007f441b57c090                     112
       7.69%  ls       ld-2.29.so            [.] call_init.part.0         [.] _init                                  334
       7.69%  ls       ld-2.29.so            [.] _dl_init                 [.] call_init.part.0                       383
       7.69%  ls       ld-2.29.so            [k] _dl_sysdep_start         [k] dl_main                                45
       7.69%  ls       ld-2.29.so            [k] _dl_catch_exception      [k] openaux                                116

  #
  # (Tip: For memory address profiling, try: perf mem record / perf mem report)
  #

To the one that shows call chains:

  # perf report --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 10  of event 'cycles'
  # Event count (approx.): 3204047
  #
  # Children      Self  Command  Shared Object       Symbol
  # ........  ........  .......  ..................  .........................................
  #
      55.01%     0.00%  ls       [kernel.vmlinux]    [k] entry_SYSCALL_64_after_hwframe
              |
              ---entry_SYSCALL_64_after_hwframe
                 do_syscall_64
                 |
                  --16.01%--__x64_sys_execve
                            __do_execve_file.isra.0
                            search_binary_handler
                            load_elf_binary
                            elf_map
                            vm_mmap_pgoff
                            do_mmap
                            mmap_region
                            perf_event_mmap
                            perf_iterate_sb
                            perf_iterate_ctx
                            perf_event_mmap_output
                            perf_output_copy
                            memcpy_erms

      55.01%    39.00%  ls       [kernel.vmlinux]    [k] do_syscall_64
              |
              |--39.00%--0xffffffffffffffff
              |          _dl_map_object
              |          open_verify.constprop.0
              |          __lseek64 (inlined)
              |          entry_SYSCALL_64_after_hwframe
              |          do_syscall_64
              |
               --16.01%--do_syscall_64
                         __x64_sys_execve
                         __do_execve_file.isra.0
                         search_binary_handler
                         load_elf_binary
                         elf_map
                         vm_mmap_pgoff
                         do_mmap
                         mmap_region
                         perf_event_mmap
                         perf_iterate_sb
                         perf_iterate_ctx
                         perf_event_mmap_output
                         perf_output_copy
                         memcpy_erms

      42.95%    42.95%  ls       libpthread-2.29.so  [.] __pthread_initialize_minimal_internal
              |
              ---_init
                 __pthread_initialize_minimal_internal

      42.95%     0.00%  ls       libpthread-2.29.so  [.] _init
              |
              ---_init
                 __pthread_initialize_minimal_internal

  <SNIP>

  #
  # (Tip: Profiling branch (mis)predictions with: perf record -b / perf report)
  #
  #

The branch stack view be explicitely selected using:

  # perf report -h branch-stack

   Usage: perf report [<options>]

      -b, --branch-stack    use branch records for per branch histogram filling

  #

I.e. after this patch:

  # perf report -b --stdio
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 13  of event 'cycles'
  # Event count (approx.): 13
  #
  # Overhead  Command  Source Shared Object  Source Symbol                Target Symbol                              Basic Block Cycles
  # ........  .......  ....................  ...........................  .........................................  ..................
  #
       7.69%  ls       libpthread-2.29.so    [.] _init                    [.] __pthread_initialize_minimal_internal  6827
       7.69%  ls       ld-2.29.so            [k] _start                   [k] _dl_start                              -
       7.69%  ls       ld-2.29.so            [.] _dl_start_user           [.] _dl_init                               -24790
       7.69%  ls       ld-2.29.so            [k] _dl_start                [k] _dl_sysdep_start                       278
       7.69%  ls       ld-2.29.so            [k] dl_main                  [k] _dl_map_object_deps                    15581
       7.69%  ls       ld-2.29.so            [k] open_verify.constprop.0  [k] lseek64                                4228
       7.69%  ls       ld-2.29.so            [k] _dl_map_object           [k] open_verify.constprop.0                55
       7.69%  ls       ld-2.29.so            [k] openaux                  [k] _dl_map_object                         67
       7.69%  ls       ld-2.29.so            [k] _dl_map_object_deps      [k] 0x00007f441b57c090                     112
       7.69%  ls       ld-2.29.so            [.] call_init.part.0         [.] _init                                  334
       7.69%  ls       ld-2.29.so            [.] _dl_init                 [.] call_init.part.0                       383
       7.69%  ls       ld-2.29.so            [k] _dl_sysdep_start         [k] dl_main                                45
       7.69%  ls       ld-2.29.so            [k] _dl_catch_exception      [k] openaux                                116

  #
  # (Tip: Show current config key-value pairs: perf config --list)
  #
  #

Signed-off-by: Alexey Budankov <alexey.budankov@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/ccbd9583-82f4-dec5-7e84-64bf56e351fb@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

1 files changed, 2 insertions, 0 deletions

diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 5e003d02821e..79dfb1139f94 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -1281,6 +1281,8 @@ repeat:
 
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
+	if (perf_evlist__combined_sample_type(session->evlist) & PERF_SAMPLE_STACK_USER)
+		has_br_stack = false;
 
 	setup_forced_leader(&report, session->evlist);