AcoSail/kernel_optimize_test
8
0
Fork 0
forked from luck/tmp_suning_uos_patched
Code Pull Requests Activity

perf annotate: Allow setting the offset level in .perfconfig

Browse Source 
The default is 1 (jump_target):

  # perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
  Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
  _raw_spin_lock_irqsave() /proc/kcore
    0.26        nop
    4.61        push   %rbx
   19.33        pushfq
    7.97        pop    %rax
    0.32        nop
    0.06        mov    %rax,%rbx
   14.63        cli
    0.06        nop
                xor    %eax,%eax
                mov    $0x1,%edx
   49.94        lock   cmpxchg %edx,(%rdi)
    0.16        test   %eax,%eax
              ↓ jne    2b
    2.66        mov    %rbx,%rax
                pop    %rbx
              ← retq
          2b:   mov    %eax,%esi
              → callq  *ffffffffb30eaed0
                mov    %rbx,%rax
                pop    %rbx
              ← retq
  #

But one can ask for showing offsets for call instructions by setting
this:

  # perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
  Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
  _raw_spin_lock_irqsave() /proc/kcore
    0.26        nop
    4.61        push   %rbx
   19.33        pushfq
    7.97        pop    %rax
    0.32        nop
    0.06        mov    %rax,%rbx
   14.63        cli
    0.06        nop
                xor    %eax,%eax
                mov    $0x1,%edx
   49.94        lock   cmpxchg %edx,(%rdi)
    0.16        test   %eax,%eax
              ↓ jne    2b
    2.66        mov    %rbx,%rax
                pop    %rbx
              ← retq
          2b:   mov    %eax,%esi
          2d: → callq  *ffffffffb30eaed0
                mov    %rbx,%rax
                pop    %rbx
              ← retq
  #

Or using a big value to ask for all offsets to be shown:

  # cat ~/.perfconfig
  [annotate]

	offset_level = 100

	hide_src_code = true
  # perf annotate --ignore-vmlinux --stdio2 _raw_spin_lock_irqsave
  Samples: 3K of event 'cycles:ppp', 3000 Hz, Event count (approx.): 2766398574
  _raw_spin_lock_irqsave() /proc/kcore
    0.26   0:   nop
    4.61   5:   push   %rbx
   19.33   6:   pushfq
    7.97   7:   pop    %rax
    0.32   8:   nop
    0.06   d:   mov    %rax,%rbx
   14.63  10:   cli
    0.06  11:   nop
          17:   xor    %eax,%eax
          19:   mov    $0x1,%edx
   49.94  1e:   lock   cmpxchg %edx,(%rdi)
    0.16  22:   test   %eax,%eax
          24: ↓ jne    2b
    2.66  26:   mov    %rbx,%rax
          29:   pop    %rbx
          2a: ← retq
          2b:   mov    %eax,%esi
          2d: → callq  *ffffffffb30eaed0
          32:   mov    %rbx,%rax
          35:   pop    %rbx
          36: ← retq
   #

This also affects the TUI, i.e. the default 'perf annotate' and 'perf
top/report' -> A hotkey -> annotate interfaces, when slang-devel is present
in the build, i.e.:

  # perf version --build-options | grep slang
              libslang: [ on  ]  # HAVE_SLANG_SUPPORT
  #

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Martin Liška <mliska@suse.cz>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Thomas Richter <tmricht@linux.vnet.ibm.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: https://lkml.kernel.org/n/tip-venm6x5zrt40eu8hxdsmqxz6@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
This commit is contained in:
Arnaldo Carvalho de Melo 2018-04-12 15:23:02 -03:00
parent 7b366142a5
commit 43c4023152
2 changed files with 17 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tools/perf/Documentation/perf-config.txt
View File

@ -334,6 +334,11 @@ annotate.*::
99.93 │ mov %eax,%eax
annotate.offset_level::
Default is '1', meaning just jump targets will have offsets show right beside
the instruction. When set to '2' 'call' instructions will also have its offsets
shown, 3 or higher will show offsets for all instructions.
hist.*::
hist.percentage::
This option control the way to calculate overhead of filtered entries -

15
tools/perf/util/annotate.c
View File

@ -2649,10 +2649,11 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
*/
static struct annotation_config {
const char *name;
bool *value;
void *value;
} annotation__configs[] = {
ANNOTATION__CFG(hide_src_code),
ANNOTATION__CFG(jump_arrows),
ANNOTATION__CFG(offset_level),
ANNOTATION__CFG(show_linenr),
ANNOTATION__CFG(show_nr_jumps),
ANNOTATION__CFG(show_nr_samples),
@ -2684,8 +2685,16 @@ static int annotation__config(const char *var, const char *value,
if (cfg == NULL)
pr_debug("%s variable unknown, ignoring...", var);
else
*cfg->value = perf_config_bool(name, value);
else if (strcmp(var, "annotate.offset_level") == 0) {
perf_config_int(cfg->value, name, value);
if (*(int *)cfg->value > ANNOTATION__MAX_OFFSET_LEVEL)
*(int *)cfg->value = ANNOTATION__MAX_OFFSET_LEVEL;
else if (*(int *)cfg->value < ANNOTATION__MIN_OFFSET_LEVEL)
*(int *)cfg->value = ANNOTATION__MIN_OFFSET_LEVEL;
} else {
*(bool *)cfg->value = perf_config_bool(name, value);
}
return 0;
}