perf report: Append inlines to non-DWARF callchains

Append information about inlined functions to FP and LBR callchains from
DWARF debuginfo when available. Do so by calling append_inlines() from
add_callchain_ip().

Testing it:

Frame-pointer mode recorded with 'perf record --call-graph=fp --freq=max -- ./a.out'

  #include <stdio.h>
  #include <stdint.h>

  static __attribute__((noinline)) uint32_t func5(uint32_t i)
  {
          return i + 10;
  }

  static uint32_t func4(uint32_t i)
  {
          return func5(i + 5);
  }

  static inline uint32_t func3(uint32_t i)
  {
          return func4(i + 4);
  }

  static __attribute__((noinline)) uint32_t func2(uint32_t i)
  {
          return func3(i + 3);
  }

  static uint32_t func1(uint32_t i)
  {
          return func2(i + 2);
  }

  __attribute__((noinline)) uint64_t entry(void)
  {
          uint64_t ret = 0;
          uint32_t i = 0;
          for (i = 0; i < 1000000; i++) {
                  ret += func1(i);
                  ret -= func2(i);
                  ret += func3(i);
                  ret += func4(i);
                  ret -= func5(i);
          }
          return ret;
  }

  int main(int argc, char **argv)
  {
          printf("%s\n", __func__);
          return entry();
  }
  ======

Here is the output I get with '--call-graph callee --no-children'

  ======
  # To display the perf.data header info, please use --header/--header-only options.
  #
  #
  # Total Lost Samples: 0
  #
  # Samples: 250  of event 'cycles:u'
  # Event count (approx.): 26819859
  #
  # Overhead  Command  Shared Object         Symbol
  # ........  .......  ....................  .....................................
  #
      43.58%  a.out    a.out                 [.] func5
              |
              |--28.93%--entry
              |          main
              |          __libc_start_call_main
              |
               --14.65%--func4 (inlined)
                         |
                         |--10.45%--entry
                         |          main
                         |          __libc_start_call_main
                         |
                          --4.20%--func3 (inlined)
                                    entry
                                    main
                                    __libc_start_call_main

      38.80%  a.out    a.out                 [.] entry
              |
              |--23.27%--func4 (inlined)
              |          |
              |          |--20.28%--func3 (inlined)
              |          |          func2
              |          |          main
              |          |          __libc_start_call_main
              |          |
              |           --2.99%--entry
              |                     main
              |                     __libc_start_call_main
              |
              |--8.17%--func5
              |          main
              |          __libc_start_call_main
              |
              |--3.89%--func1 (inlined)
              |          entry
              |          main
              |          __libc_start_call_main
              |
               --3.48%--entry
                         main
                         __libc_start_call_main

      13.07%  a.out    a.out                 [.] func2
              |
              ---func5
                 main
                 __libc_start_call_main

       1.54%  a.out    [unknown]             [k] 0xffffffff81e011b7
       1.16%  a.out    [unknown]             [k] 0xffffffff81e00193
              |
               --0.57%--__mmap64 (inlined)
                         __mmap64 (inlined)

       0.34%  a.out    ld-linux-x86-64.so.2  [.] __tunable_get_val
       0.34%  a.out    ld-linux-x86-64.so.2  [.] strcmp
       0.32%  a.out    libc.so.6             [.] strchr
       0.31%  a.out    ld-linux-x86-64.so.2  [.] _dl_relocate_object
       0.22%  a.out    ld-linux-x86-64.so.2  [.] _dl_init_paths
       0.18%  a.out    ld-linux-x86-64.so.2  [.] get_common_cache_info.constprop.0
       0.14%  a.out    ld-linux-x86-64.so.2  [.] __GI___tunables_init

  #
  # (Tip: Show individual samples with: perf script)
  #
  ======

  It does not seem to be out of order, or at least it is consistent with
  what I get with dwarf unwinders.

Committer notes:

Adrian Hunter pointed out that this breaks --branch-history, so don't do
it for branches, see the second Link below.

Suggested-by: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Signed-off-by: <asavkov@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Milian Wolff <milian.wolff@kdab.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20230316133557.868731-2-asavkov@redhat.com
Link: https://lore.kernel.org/r/54129783-2960-84e1-05e9-97ac70ffb432@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 803c9d1803dd26ef6d4a296fb66ba3c9de9fca3a..3182815c73c6f9127d745d3e6775fa98b66ef13c 100644 (file)
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -44,6 +44,7 @@
 #include <linux/zalloc.h>
 
 static void __machine__remove_thread(struct machine *machine, struct thread *th, bool lock);
+static int append_inlines(struct callchain_cursor *cursor, struct map_symbol *ms, u64 ip);
 
 static struct dso *machine__kernel_dso(struct machine *machine)
 {
@@ -2322,6 +2323,10 @@ static int add_callchain_ip(struct thread *thread,
        ms.maps = al.maps;
        ms.map = al.map;
        ms.sym = al.sym;
+
+       if (!branch && append_inlines(cursor, &ms, ip) == 0)
+               return 0;
+
        srcline = callchain_srcline(&ms, al.addr);
        return callchain_cursor_append(cursor, ip, &ms,
                                       branch, flags, nr_loop_iter,