Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 27 2月, 2020 4 次提交
    • R
      perf annotate: Simplify disasm_line allocation and freeing code · 2316f861
      由 Ravi Bangoria 提交于 
      We are allocating disasm_line object in annotation_line__new() instead
of disasm_line__new(). Similarly annotation_line__delete() is actually
freeing disasm_line object as well. This complexity is because of
privsize.  But we don't need privsize anymore so get rid of privsize and
simplify disasm_line allocation and freeing code.
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: NJiri Olsa <jolsa@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Link: http://lore.kernel.org/lkml/20200204045233.474937-3-ravi.bangoria@linux.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      2316f861
    • R
      perf annotate: Remove privsize from symbol__annotate() args · e0ad4d68
      由 Ravi Bangoria 提交于 
      privsize is passed as 0 from all the symbol__annotate() callers.
Remove it from argument list.
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Acked-by: NJiri Olsa <jolsa@redhat.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Link: http://lore.kernel.org/lkml/20200204045233.474937-2-ravi.bangoria@linux.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      e0ad4d68
    • R
      perf annotate: Make perf config effective · 7384083b
      由 Ravi Bangoria 提交于 
      perf default config set by user in [annotate] section is totally ignored
by annotate code. Fix it.

Before:

  $ ./perf config
  annotate.hide_src_code=true
  annotate.show_nr_jumps=true
  annotate.show_nr_samples=true

  $ ./perf annotate shash
         │    unsigned h = 0;
         │      movl   $0x0,-0xc(%rbp)
         │    while (*s)
         │    ↓ jmp    44
         │    h = 65599 * h + *s++;
   11.33 │24:   mov    -0xc(%rbp),%eax
   43.50 │      imul   $0x1003f,%eax,%ecx
         │      mov    -0x18(%rbp),%rax

After:

         │        movl   $0x0,-0xc(%rbp)
         │      ↓ jmp    44
       1 │1 24:   mov    -0xc(%rbp),%eax
       4 │        imul   $0x1003f,%eax,%ecx
         │        mov    -0x18(%rbp),%rax

Note that we have removed show_nr_samples and show_total_period from
annotation_options because they are not used. Instead of them we use
symbol_conf.show_nr_samples and symbol_conf.show_total_period.

Committer testing:

Using 'perf annotate --stdio2' to use the TUI rendering but emitting the output to stdio:

  # perf config
  #
  # perf config annotate.hide_src_code=true
  # perf config
  annotate.hide_src_code=true
  #
  # perf config annotate.show_nr_jumps=true
  # perf config annotate.show_nr_samples=true
  # perf config
  annotate.hide_src_code=true
  annotate.show_nr_jumps=true
  annotate.show_nr_samples=true
  #
  #

Before:

  # perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized
  Samples: 1  of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
  ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
  Percent
              00000000000609f0 <ObjectInstance::weak_pointer_was_finalized()@@base>:
                endbr64
                cmpq    $0x0,0x20(%rdi)
              ↓ je      10
                xor     %eax,%eax
              ← retq
                xchg    %ax,%ax
  100.00  10:   push    %rbp
                cmpq    $0x0,0x18(%rdi)
                mov     %rdi,%rbp
              ↓ jne     20
          1b:   xor     %eax,%eax
                pop     %rbp
              ← retq
                nop
          20:   lea     0x18(%rdi),%rdi
              → callq   JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
                cmpq    $0x0,0x18(%rbp)
              ↑ jne     1b
                mov     %rbp,%rdi
              → callq   ObjectBase::jsobj_addr() const@plt
                mov     $0x1,%eax
                pop     %rbp
              ← retq
  #

After:

  # perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
  Samples: 1  of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
  ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
  Samples       endbr64
                cmpq    $0x0,0x20(%rdi)
              ↓ je      10
                xor     %eax,%eax
              ← retq
                xchg    %ax,%ax
     1  1 10:   push    %rbp
                cmpq    $0x0,0x18(%rdi)
                mov     %rdi,%rbp
              ↓ jne     20
        1 1b:   xor     %eax,%eax
                pop     %rbp
              ← retq
                nop
        1 20:   lea     0x18(%rdi),%rdi
              → callq   JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
                cmpq    $0x0,0x18(%rbp)
              ↑ jne     1b
                mov     %rbp,%rdi
              → callq   ObjectBase::jsobj_addr() const@plt
                mov     $0x1,%eax
                pop     %rbp
              ← retq
  #
  # perf config annotate.show_nr_jumps
  annotate.show_nr_jumps=true
  # perf config annotate.show_nr_jumps=false
  # perf config annotate.show_nr_jumps
  annotate.show_nr_jumps=false
  #
  # perf annotate --stdio2 ObjectInstance::weak_pointer_was_finalized 2> /dev/null
  Samples: 1  of event 'cycles', 4000 Hz, Event count (approx.): 830873, [percent: local period]
  ObjectInstance::weak_pointer_was_finalized() /usr/lib64/libgjs.so.0.0.0
  Samples       endbr64
                cmpq    $0x0,0x20(%rdi)
              ↓ je      10
                xor     %eax,%eax
              ← retq
                xchg    %ax,%ax
       1  10:   push    %rbp
                cmpq    $0x0,0x18(%rdi)
                mov     %rdi,%rbp
              ↓ jne     20
          1b:   xor     %eax,%eax
                pop     %rbp
              ← retq
                nop
          20:   lea     0x18(%rdi),%rdi
              → callq   JS_UpdateWeakPointerAfterGC(JS::Heap<JSObject*
                cmpq    $0x0,0x18(%rbp)
              ↑ jne     1b
                mov     %rbp,%rdi
              → callq   ObjectBase::jsobj_addr() const@plt
                mov     $0x1,%eax
                pop     %rbp
              ← retq
  #
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-6-ravi.bangoria@linux.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      7384083b
    • R
      perf annotate: Fix --show-total-period for tui/stdio2 · 68aac855
      由 Ravi Bangoria 提交于 
      perf annotate --show-total-period does not really show total period.

The reason is we have two separate variables for the same purpose.

One is in symbol_conf.show_total_period and another is
annotation_options.show_total_period.

We save command line option in symbol_conf.show_total_period but uses
annotation_option.show_total_period while rendering tui/stdio2 browser.

Though, we copy symbol_conf.show_total_period to
annotation__default_options.show_total_period but that is not really
effective as we don't use annotation__default_options once we copy
default options to dynamic variable annotate.opts in cmd_annotate().

Instead of all these complication, keep only one variable and use it all
over. symbol_conf.show_total_period is used by perf report/top as well.
So let's kill annotation_options.show_total_period.

On a side note, I've kept annotation_options.show_total_period
definition because it's still used by perf-config code. Follow up patch
to fix perf-config for annotate will remove
annotation_options.show_total_period.
Signed-off-by: NRavi Bangoria <ravi.bangoria@linux.ibm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Yisheng Xie <xieyisheng1@huawei.com>
Link: http://lore.kernel.org/lkml/20200213064306.160480-3-ravi.bangoria@linux.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      68aac855
  3. 14 1月, 2020 1 次提交
    • A
      perf tools: Support --prefix/--prefix-strip · 3b0b16bf
      由 Andi Kleen 提交于 
      The objdump utility has useful --prefix / --prefix-strip options to
allow changing source code file names hardcoded into executables' debug
info. Add options to 'perf report', 'perf top' and 'perf annotate',
which are then passed to objdump.

  $ mkdir foo
  $ echo 'main() { for (;;); }' > foo/foo.c
  $ gcc -g foo/foo.c
  foo/foo.c:1:1: warning: return type defaults to ‘int’ [-Wimplicit-int]
      1 | main() { for (;;); }
        | ^~~~
  $ perf record ./a.out
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.230 MB perf.data (5721 samples) ]
  $ mv foo bar
  $ perf annotate
  <does not show source code>
  $ perf annotate --prefix=/home/ak/lsrc/git/bar --prefix-strip=5
  <does show source code>
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Tested-by: NJiri Olsa <jolsa@redhat.com>
LPU-Reference: 20200107210444.214071-1-andi@firstfloor.org
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      3b0b16bf
  5. 12 11月, 2019 1 次提交
  7. 11 10月, 2019 1 次提交
    • J
      perf diff: Report noisy for cycles diff · cebf7d51
      由 Jin Yao 提交于 
      This patch prints the stddev and hist for the cycles diff of program
block. It can help us to understand if the cycles is noisy or not.

This patch is inspired by Andi Kleen's patch:

  https://lwn.net/Articles/600471/

We create new option '--cycles-hist'.

Example:

  perf record -b ./div
  perf record -b ./div
  perf diff -c cycles

  # Baseline                                [Program Block Range] Cycles Diff  Shared Object      Symbol
  # ........  .......................................................... ....  .................  ............................
  #
      46.72%                                      [div.c:40 -> div.c:40]    0  div                [.] main
      46.72%                                      [div.c:42 -> div.c:44]    0  div                [.] main
      46.72%                                      [div.c:42 -> div.c:39]    0  div                [.] main
      20.54%                          [random_r.c:357 -> random_r.c:394]    1  libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:357 -> random_r.c:380]    0  libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:388]    0  libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:391]    0  libc-2.27.so       [.] __random_r
      17.04%                              [random.c:288 -> random.c:291]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:291 -> random.c:291]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:293 -> random.c:293]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0  libc-2.27.so       [.] __random
      17.04%                              [random.c:298 -> random.c:298]    0  libc-2.27.so       [.] __random
       8.40%                                      [div.c:22 -> div.c:25]    0  div                [.] compute_flag
       8.40%                                      [div.c:27 -> div.c:28]    0  div                [.] compute_flag
       5.14%                                    [rand.c:26 -> rand.c:27]    0  libc-2.27.so       [.] rand
       5.14%                                    [rand.c:28 -> rand.c:28]    0  libc-2.27.so       [.] rand
       2.15%                                  [rand@plt+0 -> rand@plt+0]    0  div                [.] rand@plt
       0.00%                                                                   [kernel.kallsyms]  [k] __x86_indirect_thunk_rax
       0.00%                                [do_mmap+714 -> do_mmap+732]  -10  [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+737 -> do_mmap+765]    1  [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+262 -> do_mmap+299]    0  [kernel.kallsyms]  [k] do_mmap
       0.00%  [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0]    7  [kernel.kallsyms]  [k] __x86_indirect_thunk_r15
       0.00%            [native_sched_clock+0 -> native_sched_clock+119]   -1  [kernel.kallsyms]  [k] native_sched_clock
       0.00%                 [native_write_msr+0 -> native_write_msr+16]  -13  [kernel.kallsyms]  [k] native_write_msr

When we enable the option '--cycles-hist', the output is

  perf diff -c cycles --cycles-hist

  # Baseline                                [Program Block Range] Cycles Diff        stddev/Hist  Shared Object      Symbol
  # ........  .......................................................... ....  .................  .................  ............................
  #
      46.72%                                      [div.c:40 -> div.c:40]    0  ± 37.8% ▁█▁▁██▁█   div                [.] main
      46.72%                                      [div.c:42 -> div.c:44]    0  ± 49.4% ▁▁▂█▂▂▂▂   div                [.] main
      46.72%                                      [div.c:42 -> div.c:39]    0  ± 24.1% ▃█▂▄▁▃▂▁   div                [.] main
      20.54%                          [random_r.c:357 -> random_r.c:394]    1  ± 33.5% ▅▂▁█▃▁▂▁   libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:357 -> random_r.c:380]    0  ± 39.4% ▁▁█▁██▅▁   libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:388]    0                     libc-2.27.so       [.] __random_r
      20.54%                          [random_r.c:388 -> random_r.c:391]    0  ± 41.2% ▁▃▁▂█▄▃▁   libc-2.27.so       [.] __random_r
      17.04%                              [random.c:288 -> random.c:291]    0  ± 48.8% ▁▁▁▁███▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:291 -> random.c:291]    0  ±100.0% ▁█▁▁▁▁▁▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:293 -> random.c:293]    0  ±100.0% ▁█▁▁▁▁▁▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0  ±100.0% ▁█▁▁▁▁▁▁   libc-2.27.so       [.] __random
      17.04%                              [random.c:295 -> random.c:295]    0                     libc-2.27.so       [.] __random
      17.04%                              [random.c:298 -> random.c:298]    0  ± 75.6% ▃█▁▁▁▁▁▁   libc-2.27.so       [.] __random
       8.40%                                      [div.c:22 -> div.c:25]    0  ± 42.1% ▁▃▁▁███▁   div                [.] compute_flag
       8.40%                                      [div.c:27 -> div.c:28]    0  ± 41.8% ██▁▁▄▁▁▄   div                [.] compute_flag
       5.14%                                    [rand.c:26 -> rand.c:27]    0  ± 37.8% ▁▁▁████▁   libc-2.27.so       [.] rand
       5.14%                                    [rand.c:28 -> rand.c:28]    0                     libc-2.27.so       [.] rand
       2.15%                                  [rand@plt+0 -> rand@plt+0]    0                     div                [.] rand@plt
       0.00%                                                                                      [kernel.kallsyms]  [k] __x86_indirect_thunk_rax
       0.00%                                [do_mmap+714 -> do_mmap+732]  -10                     [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+737 -> do_mmap+765]    1                     [kernel.kallsyms]  [k] do_mmap
       0.00%                                [do_mmap+262 -> do_mmap+299]    0                     [kernel.kallsyms]  [k] do_mmap
       0.00%  [__x86_indirect_thunk_r15+0 -> __x86_indirect_thunk_r15+0]    7                     [kernel.kallsyms]  [k] __x86_indirect_thunk_r15
       0.00%            [native_sched_clock+0 -> native_sched_clock+119]   -1  ± 38.5% ▄█▁        [kernel.kallsyms]  [k] native_sched_clock
       0.00%                 [native_write_msr+0 -> native_write_msr+16]  -13  ± 47.1% ▁█▇▃▁▁     [kernel.kallsyms]  [k] native_write_msr

 v8:
 ---
 Rebase to perf/core branch

 v7:
 ---
 1. v6 got Jiri's ACK.
 2. Rebase to latest perf/core branch.

 v6:
 ---
 1. Jiri provides better code for using data__hpp_register() in ui_init().
    Use this code in v6.

 v5:
 ---
 1. Refine the use of data__hpp_register() in ui_init() according to
    Jiri's suggestion.

 v4:
 ---
 1. Rename the new option from '--noisy' to '--cycles-hist'
 2. Remove the option '-n'.
 3. Only update the spark value and stats when '--cycles-hist' is enabled.
 4. Remove the code of printing '..'.

 v3:
 ---
 1. Move the histogram to a separate column
 2. Move the svals[] out of struct stats

 v2:
 ---
 Jiri got a compile error,

  CC       builtin-diff.o
  builtin-diff.c: In function ‘compute_cycles_diff’:
  builtin-diff.c:712:10: error: taking the absolute value of unsigned type ‘u64’ {aka ‘long unsigned int’} has no effect [-Werror=absolute-value]
  712 |          labs(pair->block_info->cycles_spark[i] -
      |          ^~~~

 Because the result of u64 - u64 is still u64. Now we change the type of
 cycles_spark[] to s64.
Signed-off-by: NJin Yao <yao.jin@linux.intel.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20190925011446.30678-1-yao.jin@linux.intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      cebf7d51
  9. 01 10月, 2019 2 次提交
  11. 30 7月, 2019 2 次提交
  13. 21 3月, 2019 1 次提交
    • S
      perf annotate: Enable annotation of BPF programs · 6987561c
      由 Song Liu 提交于 
      In symbol__disassemble(), DSO_BINARY_TYPE__BPF_PROG_INFO dso calls into
a new function symbol__disassemble_bpf(), where annotation line
information is filled based on the bpf_prog_info and btf data saved in
given perf_env.

symbol__disassemble_bpf() uses binutils's libopcodes to disassemble bpf
programs.

Committer testing:

After fixing this:

  -               u64 *addrs = (u64 *)(info_linear->info.jited_ksyms);
  +               u64 *addrs = (u64 *)(uintptr_t)(info_linear->info.jited_ksyms);

Detected when crossbuilding to a 32-bit arch.

And making all this dependent on HAVE_LIBBFD_SUPPORT and
HAVE_LIBBPF_SUPPORT:

1) Have a BPF program running, one that has BTF info, etc, I used
   the tools/perf/examples/bpf/augmented_raw_syscalls.c put in place
   by 'perf trace'.

  # grep -B1 augmented_raw ~/.perfconfig
  [trace]
	add_events = /home/acme/git/perf/tools/perf/examples/bpf/augmented_raw_syscalls.c
  #
  # perf trace -e *mmsg
  dnf/6245 sendmmsg(20, 0x7f5485a88030, 2, MSG_NOSIGNAL) = 2
  NetworkManager/10055 sendmmsg(22<socket:[1056822]>, 0x7f8126ad1bb0, 2, MSG_NOSIGNAL) = 2

2) Then do a 'perf record' system wide for a while:

  # perf record -a
  ^C[ perf record: Woken up 68 times to write data ]
  [ perf record: Captured and wrote 19.427 MB perf.data (366891 samples) ]
  #

3) Check that we captured BPF and BTF info in the perf.data file:

  # perf report --header-only | grep 'b[pt]f'
  # event : name = cycles:ppp, , id = { 294789, 294790, 294791, 294792, 294793, 294794, 294795, 294796 }, size = 112, { sample_period, sample_freq } = 4000, sample_type = IP|TID|TIME|CPU|PERIOD, read_format = ID, disabled = 1, inherit = 1, mmap = 1, comm = 1, freq = 1, task = 1, precise_ip = 3, sample_id_all = 1, exclude_guest = 1, mmap2 = 1, comm_exec = 1, ksymbol = 1, bpf_event = 1
  # bpf_prog_info of id 13
  # bpf_prog_info of id 14
  # bpf_prog_info of id 15
  # bpf_prog_info of id 16
  # bpf_prog_info of id 17
  # bpf_prog_info of id 18
  # bpf_prog_info of id 21
  # bpf_prog_info of id 22
  # bpf_prog_info of id 41
  # bpf_prog_info of id 42
  # btf info of id 2
  #

4) Check which programs got recorded:

   # perf report | grep bpf_prog | head
     0.16%  exe              bpf_prog_819967866022f1e1_sys_enter      [k] bpf_prog_819967866022f1e1_sys_enter
     0.14%  exe              bpf_prog_c1bd85c092d6e4aa_sys_exit       [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
     0.08%  fuse-overlayfs   bpf_prog_819967866022f1e1_sys_enter      [k] bpf_prog_819967866022f1e1_sys_enter
     0.07%  fuse-overlayfs   bpf_prog_c1bd85c092d6e4aa_sys_exit       [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
     0.01%  clang-4.0        bpf_prog_c1bd85c092d6e4aa_sys_exit       [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
     0.01%  clang-4.0        bpf_prog_819967866022f1e1_sys_enter      [k] bpf_prog_819967866022f1e1_sys_enter
     0.00%  clang            bpf_prog_c1bd85c092d6e4aa_sys_exit       [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
     0.00%  runc             bpf_prog_819967866022f1e1_sys_enter      [k] bpf_prog_819967866022f1e1_sys_enter
     0.00%  clang            bpf_prog_819967866022f1e1_sys_enter      [k] bpf_prog_819967866022f1e1_sys_enter
     0.00%  sh               bpf_prog_c1bd85c092d6e4aa_sys_exit       [k] bpf_prog_c1bd85c092d6e4aa_sys_exit
  #

  This was with the default --sort order for 'perf report', which is:

    --sort comm,dso,symbol

  If we just look for the symbol, for instance:

   # perf report --sort symbol | grep bpf_prog | head
     0.26%  [k] bpf_prog_819967866022f1e1_sys_enter                -      -
     0.24%  [k] bpf_prog_c1bd85c092d6e4aa_sys_exit                 -      -
   #

  or the DSO:

   # perf report --sort dso | grep bpf_prog | head
     0.26%  bpf_prog_819967866022f1e1_sys_enter
     0.24%  bpf_prog_c1bd85c092d6e4aa_sys_exit
  #

We'll see the two BPF programs that augmented_raw_syscalls.o puts in
place,  one attached to the raw_syscalls:sys_enter and another to the
raw_syscalls:sys_exit tracepoints, as expected.

Now we can finally do, from the command line, annotation for one of
those two symbols, with the original BPF program source coude intermixed
with the disassembled JITed code:

  # perf annotate --stdio2 bpf_prog_819967866022f1e1_sys_enter

  Samples: 950  of event 'cycles:ppp', 4000 Hz, Event count (approx.): 553756947, [percent: local period]
  bpf_prog_819967866022f1e1_sys_enter() bpf_prog_819967866022f1e1_sys_enter
  Percent      int sys_enter(struct syscall_enter_args *args)
   53.41         push   %rbp

    0.63         mov    %rsp,%rbp
    0.31         sub    $0x170,%rsp
    1.93         sub    $0x28,%rbp
    7.02         mov    %rbx,0x0(%rbp)
    3.20         mov    %r13,0x8(%rbp)
    1.07         mov    %r14,0x10(%rbp)
    0.61         mov    %r15,0x18(%rbp)
    0.11         xor    %eax,%eax
    1.29         mov    %rax,0x20(%rbp)
    0.11         mov    %rdi,%rbx
               	return bpf_get_current_pid_tgid();
    2.02       → callq  *ffffffffda6776d9
    2.76         mov    %eax,-0x148(%rbp)
                 mov    %rbp,%rsi
               int sys_enter(struct syscall_enter_args *args)
                 add    $0xfffffffffffffeb8,%rsi
               	return bpf_map_lookup_elem(pids, &pid) != NULL;
                 movabs $0xffff975ac2607800,%rdi

    1.26       → callq  *ffffffffda6789e9
                 cmp    $0x0,%rax
    2.43       → je     0
                 add    $0x38,%rax
    0.21         xor    %r13d,%r13d
               	if (pid_filter__has(&pids_filtered, getpid()))
    0.81         cmp    $0x0,%rax
               → jne    0
                 mov    %rbp,%rdi
               	probe_read(&augmented_args.args, sizeof(augmented_args.args), args);
    2.22         add    $0xfffffffffffffeb8,%rdi
    0.11         mov    $0x40,%esi
    0.32         mov    %rbx,%rdx
    2.74       → callq  *ffffffffda658409
               	syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
    0.22         mov    %rbp,%rsi
    1.69         add    $0xfffffffffffffec0,%rsi
               	syscall = bpf_map_lookup_elem(&syscalls, &augmented_args.args.syscall_nr);
                 movabs $0xffff975bfcd36000,%rdi

                 add    $0xd0,%rdi
    0.21         mov    0x0(%rsi),%eax
    0.93         cmp    $0x200,%rax
               → jae    0
    0.10         shl    $0x3,%rax

    0.11         add    %rdi,%rax
    0.11       → jmp    0
                 xor    %eax,%eax
               	if (syscall == NULL || !syscall->enabled)
    1.07         cmp    $0x0,%rax
               → je     0
               	if (syscall == NULL || !syscall->enabled)
    6.57         movzbq 0x0(%rax),%rdi

               	if (syscall == NULL || !syscall->enabled)
                 cmp    $0x0,%rdi
    0.95       → je     0
                 mov    $0x40,%r8d
               	switch (augmented_args.args.syscall_nr) {
                 mov    -0x140(%rbp),%rdi
               	switch (augmented_args.args.syscall_nr) {
                 cmp    $0x2,%rdi
               → je     0
                 cmp    $0x101,%rdi
               → je     0
                 cmp    $0x15,%rdi
               → jne    0
               	case SYS_OPEN:	 filename_arg = (const void *)args->args[0];
                 mov    0x10(%rbx),%rdx
               → jmp    0
               	case SYS_OPENAT: filename_arg = (const void *)args->args[1];
                 mov    0x18(%rbx),%rdx
               	if (filename_arg != NULL) {
                 cmp    $0x0,%rdx
               → je     0
                 xor    %edi,%edi
               		augmented_args.filename.reserved = 0;
                 mov    %edi,-0x104(%rbp)
               		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
                 mov    %rbp,%rdi
                 add    $0xffffffffffffff00,%rdi
               		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
                 mov    $0x100,%esi
               → callq  *ffffffffda658499
                 mov    $0x148,%r8d
               		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
                 mov    %eax,-0x108(%rbp)
               		augmented_args.filename.size = probe_read_str(&augmented_args.filename.value,
                 mov    %rax,%rdi
                 shl    $0x20,%rdi

                 shr    $0x20,%rdi

               		if (augmented_args.filename.size < sizeof(augmented_args.filename.value)) {
                 cmp    $0xff,%rdi
               → ja     0
               			len -= sizeof(augmented_args.filename.value) - augmented_args.filename.size;
                 add    $0x48,%rax
               			len &= sizeof(augmented_args.filename.value) - 1;
                 and    $0xff,%rax
                 mov    %rax,%r8
                 mov    %rbp,%rcx
               	return perf_event_output(args, &__augmented_syscalls__, BPF_F_CURRENT_CPU, &augmented_args, len);
                 add    $0xfffffffffffffeb8,%rcx
                 mov    %rbx,%rdi
                 movabs $0xffff975fbd72d800,%rsi

                 mov    $0xffffffff,%edx
               → callq  *ffffffffda658ad9
                 mov    %rax,%r13
               }
                 mov    %r13,%rax
    0.72         mov    0x0(%rbp),%rbx
                 mov    0x8(%rbp),%r13
    1.16         mov    0x10(%rbp),%r14
    0.10         mov    0x18(%rbp),%r15
    0.42         add    $0x28,%rbp
    0.54         leaveq
    0.54       ← retq
  #

Please see 'man perf-config' to see how to control what should be seen,
via ~/.perfconfig [annotate] section, for instance, one can suppress the
source code and see just the disassembly, etc.

Alternatively, use the TUI bu just using 'perf annotate', press
'/bpf_prog' to see the bpf symbols, press enter and do the interactive
annotation, which allows for dumping to a file after selecting the
the various output tunables, for instance, the above without source code
intermixed, plus showing all the instruction offsets:

  # perf annotate bpf_prog_819967866022f1e1_sys_enter

Then press: 's' to hide the source code + 'O' twice to show all
instruction offsets, then 'P' to print to the
bpf_prog_819967866022f1e1_sys_enter.annotation file, which will have:

  # cat bpf_prog_819967866022f1e1_sys_enter.annotation
  bpf_prog_819967866022f1e1_sys_enter() bpf_prog_819967866022f1e1_sys_enter
  Event: cycles:ppp

   53.41    0:   push   %rbp

    0.63    1:   mov    %rsp,%rbp
    0.31    4:   sub    $0x170,%rsp
    1.93    b:   sub    $0x28,%rbp
    7.02    f:   mov    %rbx,0x0(%rbp)
    3.20   13:   mov    %r13,0x8(%rbp)
    1.07   17:   mov    %r14,0x10(%rbp)
    0.61   1b:   mov    %r15,0x18(%rbp)
    0.11   1f:   xor    %eax,%eax
    1.29   21:   mov    %rax,0x20(%rbp)
    0.11   25:   mov    %rdi,%rbx
    2.02   28: → callq  *ffffffffda6776d9
    2.76   2d:   mov    %eax,-0x148(%rbp)
           33:   mov    %rbp,%rsi
           36:   add    $0xfffffffffffffeb8,%rsi
           3d:   movabs $0xffff975ac2607800,%rdi

    1.26   47: → callq  *ffffffffda6789e9
           4c:   cmp    $0x0,%rax
    2.43   50: → je     0
           52:   add    $0x38,%rax
    0.21   56:   xor    %r13d,%r13d
    0.81   59:   cmp    $0x0,%rax
           5d: → jne    0
           63:   mov    %rbp,%rdi
    2.22   66:   add    $0xfffffffffffffeb8,%rdi
    0.11   6d:   mov    $0x40,%esi
    0.32   72:   mov    %rbx,%rdx
    2.74   75: → callq  *ffffffffda658409
    0.22   7a:   mov    %rbp,%rsi
    1.69   7d:   add    $0xfffffffffffffec0,%rsi
           84:   movabs $0xffff975bfcd36000,%rdi

           8e:   add    $0xd0,%rdi
    0.21   95:   mov    0x0(%rsi),%eax
    0.93   98:   cmp    $0x200,%rax
           9f: → jae    0
    0.10   a1:   shl    $0x3,%rax

    0.11   a5:   add    %rdi,%rax
    0.11   a8: → jmp    0
           aa:   xor    %eax,%eax
    1.07   ac:   cmp    $0x0,%rax
           b0: → je     0
    6.57   b6:   movzbq 0x0(%rax),%rdi

           bb:   cmp    $0x0,%rdi
    0.95   bf: → je     0
           c5:   mov    $0x40,%r8d
           cb:   mov    -0x140(%rbp),%rdi
           d2:   cmp    $0x2,%rdi
           d6: → je     0
           d8:   cmp    $0x101,%rdi
           df: → je     0
           e1:   cmp    $0x15,%rdi
           e5: → jne    0
           e7:   mov    0x10(%rbx),%rdx
           eb: → jmp    0
           ed:   mov    0x18(%rbx),%rdx
           f1:   cmp    $0x0,%rdx
           f5: → je     0
           f7:   xor    %edi,%edi
           f9:   mov    %edi,-0x104(%rbp)
           ff:   mov    %rbp,%rdi
          102:   add    $0xffffffffffffff00,%rdi
          109:   mov    $0x100,%esi
          10e: → callq  *ffffffffda658499
          113:   mov    $0x148,%r8d
          119:   mov    %eax,-0x108(%rbp)
          11f:   mov    %rax,%rdi
          122:   shl    $0x20,%rdi

          126:   shr    $0x20,%rdi

          12a:   cmp    $0xff,%rdi
          131: → ja     0
          133:   add    $0x48,%rax
          137:   and    $0xff,%rax
          13d:   mov    %rax,%r8
          140:   mov    %rbp,%rcx
          143:   add    $0xfffffffffffffeb8,%rcx
          14a:   mov    %rbx,%rdi
          14d:   movabs $0xffff975fbd72d800,%rsi

          157:   mov    $0xffffffff,%edx
          15c: → callq  *ffffffffda658ad9
          161:   mov    %rax,%r13
          164:   mov    %r13,%rax
    0.72  167:   mov    0x0(%rbp),%rbx
          16b:   mov    0x8(%rbp),%r13
    1.16  16f:   mov    0x10(%rbp),%r14
    0.10  173:   mov    0x18(%rbp),%r15
    0.42  177:   add    $0x28,%rbp
    0.54  17b:   leaveq
    0.54  17c: ← retq

Another cool way to test all this is to symple use 'perf top' look for
those symbols, go there and press enter, annotate it live :-)
Signed-off-by: NSong Liu <songliubraving@fb.com>
Reviewed-by: NJiri Olsa <jolsa@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stanislav Fomichev <sdf@google.com>
Link: http://lkml.kernel.org/r/20190312053051.2690567-13-songliubraving@fb.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      6987561c
  15. 07 3月, 2019 1 次提交
    • A
      perf annotate: Calculate the max instruction name, align column to that · bc3bb795
      由 Arnaldo Carvalho de Melo 提交于 
      We were hardcoding '6' as the max instruction name, and we have lots
that are longer than that, see the diff from two 'P' printed TUI
annotations for a libc function that uses instructions with long names,
such as 'vpmovmskb' with its 9 chars:

  --- __strcmp_avx2.annotation.before	2019-03-06 16:31:39.368020425 -0300
  +++ __strcmp_avx2.annotation	2019-03-06 16:32:12.079450508 -0300
  @@ -2,284 +2,284 @@
   Event: cycles:ppp

   Percent        endbr64
  -  0.10         mov    %edi,%eax
  +  0.10         mov        %edi,%eax
  -               xor    %edx,%edx
  +               xor        %edx,%edx
  -  3.54         vpxor  %ymm7,%ymm7,%ymm7
  +  3.54         vpxor      %ymm7,%ymm7,%ymm7
  -               or     %esi,%eax
  +               or         %esi,%eax
  -               and    $0xfff,%eax
  +               and        $0xfff,%eax
  -               cmp    $0xf80,%eax
  +               cmp        $0xf80,%eax
  -             ↓ jg     370
  +             ↓ jg         370
  - 27.07         vmovdqu (%rdi),%ymm1
  + 27.07         vmovdqu    (%rdi),%ymm1
  -  7.97         vpcmpeqb (%rsi),%ymm1,%ymm0
  +  7.97         vpcmpeqb   (%rsi),%ymm1,%ymm0
  -  2.15         vpminub %ymm1,%ymm0,%ymm0
  +  2.15         vpminub    %ymm1,%ymm0,%ymm0
  -  4.09         vpcmpeqb %ymm7,%ymm0,%ymm0
  +  4.09         vpcmpeqb   %ymm7,%ymm0,%ymm0
  -  0.43         vpmovmskb %ymm0,%ecx
  +  0.43         vpmovmskb  %ymm0,%ecx
  -  1.53         test   %ecx,%ecx
  +  1.53         test       %ecx,%ecx
  -             ↓ je     b0
  +             ↓ je         b0
  -  5.26         tzcnt  %ecx,%edx
  +  5.26         tzcnt      %ecx,%edx
  - 18.40         movzbl (%rdi,%rdx,1),%eax
  + 18.40         movzbl     (%rdi,%rdx,1),%eax
  -  7.09         movzbl (%rsi,%rdx,1),%edx
  +  7.09         movzbl     (%rsi,%rdx,1),%edx
  -  3.34         sub    %edx,%eax
  +  3.34         sub        %edx,%eax
     2.37         vzeroupper
                ← retq
                  nop
  -         50:   tzcnt  %ecx,%edx
  +         50:   tzcnt      %ecx,%edx
  -               movzbl 0x20(%rdi,%rdx,1),%eax
  +               movzbl     0x20(%rdi,%rdx,1),%eax
  -               movzbl 0x20(%rsi,%rdx,1),%edx
  +               movzbl     0x20(%rsi,%rdx,1),%edx
  -               sub    %edx,%eax
  +               sub        %edx,%eax
                  vzeroupper
                ← retq
  -               data16 nopw %cs:0x0(%rax,%rax,1)
  +               data16     nopw %cs:0x0(%rax,%rax,1)
Reported-by: NTravis Downs <travis.downs@gmail.com>
LPU-Reference: CAOBGo4z1KfmWeOm6Et0cnX5Z6DWsG2PQbAvRn1MhVPJmXHrc5g@mail.gmail.com
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-89wsdd9h9g6bvq52sgp6d0u4@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      bc3bb795
  17. 25 1月, 2019 1 次提交
  19. 18 12月, 2018 1 次提交
    • J
      perf annotate: Compute average IPC and IPC coverage per symbol · ace4f8fa
      由 Jin Yao 提交于 
      Add support to 'perf report' annotate view or 'perf annotate --stdio2'
to aggregate the IPC derived from timed LBRs per symbol. We compute the
average IPC and the IPC coverage percentage.

For example:

  $ perf annotate --stdio2

  Percent  IPC Cycle (Average IPC: 2.30, IPC Coverage: 54.8%)

                          Disassembly of section .text:

                          000000000003aac0 <random@@GLIBC_2.2.5>:
    8.32  3.28              sub    $0x18,%rsp
          3.28              mov    $0x1,%esi
          3.28              xor    %eax,%eax
          3.28              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
   11.57  3.28     1      ↓ je     20
                            lock   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
                          ↓ jne    29
                          ↓ jmp    43
   11.57  1.10        20:   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
    0.00  1.10     1      ↓ je     43
                      29:   lea    __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
                            sub    $0x80,%rsp
                          → callq  __lll_lock_wait_private
                            add    $0x80,%rsp
    0.00  3.00        43:   lea    __ctype_b@GLIBC_2.2.5+0x38,%rdi
          3.00              lea    0xc(%rsp),%rsi
    8.49  3.00     1      → callq  __random_r
    7.91  1.94              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x1e0
    0.00  1.94     1      ↓ je     68
                            lock   decl   __abort_msg@@GLIBC_PRIVATE+0x8a0
                          ↓ jne    70
                          ↓ jmp    8a
    0.00  2.00        68:   decl   __abort_msg@@GLIBC_PRIVATE+0x8a0
   21.56  2.00     1      ↓ je     8a
                      70:   lea    __abort_msg@@GLIBC_PRIVATE+0x8a0,%rdi
                            sub    $0x80,%rsp
                          → callq  __lll_unlock_wake_private
                            add    $0x80,%rsp
   21.56  2.90        8a:   movslq 0xc(%rsp),%rax
          2.90              add    $0x18,%rsp
    9.03  2.90     1      ← retq

It shows for this symbol the average IPC is 2.30 and the IPC coverage is
54.8%.
Signed-off-by: NJin Yao <yao.jin@linux.intel.com>
Reviewed-by: NIngo Molnar <mingo@kernel.org>
Reviewed-by: NJiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1543586097-27632-2-git-send-email-yao.jin@linux.intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      ace4f8fa
  21. 31 8月, 2018 1 次提交
    • K
      perf annotate: Fix parsing aarch64 branch instructions after objdump update · 4e67b2a5
      由 Kim Phillips 提交于 
      Starting with binutils 2.28, aarch64 objdump adds comments to the
disassembly output to show the alternative names of a condition code
[1].

It is assumed that commas in objdump comments could occur in other
arches now or in the future, so this fix is arch-independent.

The fix could have been done with arm64 specific jump__parse and
jump__scnprintf functions, but the jump__scnprintf instruction would
have to have its comment character be a literal, since the scnprintf
functions cannot receive a struct arch easily.

This inconvenience also applies to the generic jump__scnprintf, which is
why we add a raw_comment pointer to struct ins_operands, so the __parse
function assigns it to be re-used by its corresponding __scnprintf
function.

Example differences in 'perf annotate --stdio2' output on an aarch64
perf.data file:

BEFORE: → b.cs   ffff200008133d1c <unwind_frame+0x18c>  // b.hs, dffff7ecc47b
AFTER : ↓ b.cs   18c

BEFORE: → b.cc   ffff200008d8d9cc <get_alloc_profile+0x31c>  // b.lo, b.ul, dffff727295b
AFTER : ↓ b.cc   31c

The branch target labels 18c and 31c also now appear in the output:

BEFORE:        add    x26, x29, #0x80
AFTER : 18c:   add    x26, x29, #0x80

BEFORE:        add    x21, x21, #0x8
AFTER : 31c:   add    x21, x21, #0x8

The Fixes: tag below is added so stable branches will get the update; it
doesn't necessarily mean that commit was broken at the time, rather it
didn't withstand the aarch64 objdump update.

Tested no difference in output for sample x86_64, power arch perf.data files.

[1] https://sourceware.org/git/gitweb.cgi?p=binutils-gdb.git;a=commit;h=bb7eff5206e4795ac79c177a80fe9f4630aaf730Signed-off-by: NKim Phillips <kim.phillips@arm.com>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Taeung Song <treeze.taeung@gmail.com>
Cc: linux-arm-kernel@lists.infradead.org
Fixes: b13bbeee ("perf annotate: Fix branch instruction with multiple operands")
Link: http://lkml.kernel.org/r/20180827125340.a2f7e291901d17cea05daba4@arm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      4e67b2a5
  23. 09 8月, 2018 12 次提交
  25. 04 6月, 2018 11 次提交
  27. 19 5月, 2018 1 次提交
    • J
      perf annotate: Create hotkey 'c' to show min/max cycles · 3e71fc03
      由 Jin Yao 提交于 
      In the 'perf annotate' view, a new hotkey 'c' is created for showing the
min/max cycles.

For example, when press 'c', the annotate view is:

  Percent│ IPC     Cycle(min/max)
         │
         │
         │                             Disassembly of section .text:
         │
         │                             000000000003aab0 <random@@GLIBC_2.2.5>:
    8.22 │3.92                           sub    $0x18,%rsp
         │3.92                           mov    $0x1,%esi
         │3.92                           xor    %eax,%eax
         │3.92                           cmpl   $0x0,argp_program_version_hook@@G
         │3.92             1(2/1)      ↓ je     20
         │                               lock   cmpxchg %esi,__abort_msg@@GLIBC_P
         │                             ↓ jne    29
         │                             ↓ jmp    43
         │1.10                     20:   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+
    8.93 │1.10             1(5/1)      ↓ je     43

When press 'c' again, the annotate view is switched back:

  Percent│ IPC Cycle
         │
         │
         │                Disassembly of section .text:
         │
         │                000000000003aab0 <random@@GLIBC_2.2.5>:
    8.22 │3.92              sub    $0x18,%rsp
         │3.92              mov    $0x1,%esi
         │3.92              xor    %eax,%eax
         │3.92              cmpl   $0x0,argp_program_version_hook@@GLIBC_2.2.5+0x
         │3.92     1      ↓ je     20
         │                  lock   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
         │                ↓ jne    29
         │                ↓ jmp    43
         │1.10        20:   cmpxchg %esi,__abort_msg@@GLIBC_PRIVATE+0x8a0
    8.93 │1.10     1      ↓ je     43
Signed-off-by: NJin Yao <yao.jin@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1526569118-14217-3-git-send-email-yao.jin@linux.intel.com
[ Rename all maxmin to minmax ]
Signed-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      3e71fc03