Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 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
  3. 01 10月, 2019 6 次提交
  5. 26 9月, 2019 1 次提交
  7. 25 9月, 2019 1 次提交
  9. 20 9月, 2019 1 次提交
  11. 01 9月, 2019 3 次提交
  13. 26 8月, 2019 1 次提交
  15. 09 8月, 2019 1 次提交
    • A
      perf annotate: Fix printing of unaugmented disassembled instructions from BPF · 85127775
      由 Arnaldo Carvalho de Melo 提交于 
      The code to disassemble BPF programs uses binutil's disassembling
routines, and those use in turn fprintf to print to a memstream FILE,
adding a newline at the end of each line, which ends up confusing the
TUI routines called from:

  annotate_browser__write()
    annotate_line__write()
      annotate_browser__printf()
        ui_browser__vprintf()
          SLsmg_vprintf()

The SLsmg_vprintf() function in the slang library gets confused with the
terminating newline, so make the disasm_line__parse() function that
parses the lines produced by the BPF specific disassembler (that uses
binutil's libopcodes) and the lines produced by the objdump based
disassembler used for everything else (and that doesn't adds this
terminating newline) trim the end of the line in addition of the
beginning.

This way when disasm_line->ops.raw, i.e. for instructions without a
special scnprintf() method, we'll not have that \n getting in the way of
filling the screen right after the instruction with spaces to avoid
leaving what was on the screen before and thus garbling the annotation
screen, breaking scrolling, etc.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Song Liu <songliubraving@fb.com>
Fixes: 6987561c ("perf annotate: Enable annotation of BPF programs")
Link: https://lkml.kernel.org/n/tip-unbr5a5efakobfr6rhxq99ta@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      85127775
  17. 30 7月, 2019 3 次提交
  19. 09 7月, 2019 3 次提交
    • A
      perf tools: Use list_del_init() more thorougly · e56fbc9d
      由 Arnaldo Carvalho de Melo 提交于 
      To allow for destructors to check if they're operating on a object still
in a list, and to avoid going from use after free list entries into
still valid, or even also other already removed from list entries.

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-deh17ub44atyox3j90e6rksu@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      e56fbc9d
    • A
      perf tools: Use zfree() where applicable · d8f9da24
      由 Arnaldo Carvalho de Melo 提交于 
      In places where the equivalent was already being done, i.e.:

   free(a);
   a = NULL;

And in placs where struct members are being freed so that if we have
some erroneous reference to its struct, then accesses to freed members
will result in segfaults, which we can detect faster than use after free
to areas that may still have something seemingly valid.

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-jatyoofo5boc1bsvoig6bb6i@git.kernel.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      d8f9da24
    • L
      perf annotate: Fix dereferencing freed memory found by the smatch tool · 600c787d
      由 Leo Yan 提交于 
      Based on the following report from Smatch, fix the potential
dereferencing freed memory check.

  tools/perf/util/annotate.c:1125
  disasm_line__parse() error: dereferencing freed memory 'namep'

  tools/perf/util/annotate.c
  1100 static int disasm_line__parse(char *line, const char **namep, char **rawp)
  1101 {
  1102         char tmp, *name = ltrim(line);

  [...]

  1114         *namep = strdup(name);
  1115
  1116         if (*namep == NULL)
  1117                 goto out_free_name;

  [...]

  1124 out_free_name:
  1125         free((void *)namep);
                            ^^^^^
  1126         *namep = NULL;
               ^^^^^^
  1127         return -1;
  1128 }

If strdup() fails to allocate memory space for *namep, we don't need to
free memory with pointer 'namep', which is resident in data structure
disasm_line::ins::name; and *namep is NULL pointer for this failure, so
it's pointless to assign NULL to *namep again.

Committer note:

Freeing namep, which is the address of the first entry of the 'struct
ins' that is the first member of struct disasm_line would in fact free
that disasm_line instance, if it was allocated via malloc/calloc, which,
later, would a dereference of freed memory.
Signed-off-by: NLeo Yan <leo.yan@linaro.org>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Alexios Zavras <alexios.zavras@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Changbin Du <changbin.du@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Eric Saint-Etienne <eric.saint.etienne@oracle.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Song Liu <songliubraving@fb.com>
Cc: Suzuki Poulouse <suzuki.poulose@arm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: http://lkml.kernel.org/r/20190702103420.27540-5-leo.yan@linaro.orgSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      600c787d
  21. 02 7月, 2019 2 次提交
  23. 26 6月, 2019 2 次提交
  25. 11 6月, 2019 1 次提交
    • T
      perf report: Fix OOM error in TUI mode on s390 · 8a07aa4e
      由 Thomas Richter 提交于 
      Debugging a OOM error using the TUI interface revealed this issue
on s390:

[tmricht@m83lp54 perf]$ cat /proc/kallsyms |sort
....
00000001119b7158 B radix_tree_node_cachep
00000001119b8000 B __bss_stop
00000001119b8000 B _end
000003ff80002850 t autofs_mount	[autofs4]
000003ff80002868 t autofs_show_options	[autofs4]
000003ff80002a98 t autofs_evict_inode	[autofs4]
....

There is a huge gap between the last kernel symbol
__bss_stop/_end and the first kernel module symbol
autofs_mount (from autofs4 module).

After reading the kernel symbol table via functions:

 dso__load()
 +--> dso__load_kernel_sym()
      +--> dso__load_kallsyms()
	   +--> __dso_load_kallsyms()
	        +--> symbols__fixup_end()

the symbol __bss_stop has a start address of 1119b8000 and
an end address of 3ff80002850, as can be seen by this debug statement:

  symbols__fixup_end __bss_stop start:0x1119b8000 end:0x3ff80002850

The size of symbol __bss_stop is 0x3fe6e64a850 bytes!
It is the last kernel symbol and fills up the space until
the first kernel module symbol.

This size kills the TUI interface when executing the following
code:

  process_sample_event()
    hist_entry_iter__add()
      hist_iter__report_callback()
        hist_entry__inc_addr_samples()
          symbol__inc_addr_samples(symbol = __bss_stop)
            symbol__cycles_hist()
               annotated_source__alloc_histograms(...,
				                symbol__size(sym),
		                                ...)

This function allocates memory to save sample histograms.
The symbol_size() marco is defined as sym->end - sym->start, which
results in above value of 0x3fe6e64a850 bytes and
the call to calloc() in annotated_source__alloc_histograms() fails.

The histgram memory allocation might fail, make this failure
no-fatal and continue processing.

Output before:
[tmricht@m83lp54 perf]$ ./perf --debug stderr=1 report -vvvvv \
					      -i ~/slow.data 2>/tmp/2
[tmricht@m83lp54 perf]$ tail -5 /tmp/2
  __symbol__inc_addr_samples(875): ENOMEM! sym->name=__bss_stop,
		start=0x1119b8000, addr=0x2aa0005eb08, end=0x3ff80002850,
		func: 0
problem adding hist entry, skipping event
0x938b8 [0x8]: failed to process type: 68 [Cannot allocate memory]
[tmricht@m83lp54 perf]$

Output after:
[tmricht@m83lp54 perf]$ ./perf --debug stderr=1 report -vvvvv \
					      -i ~/slow.data 2>/tmp/2
[tmricht@m83lp54 perf]$ tail -5 /tmp/2
   symbol__inc_addr_samples map:0x1597830 start:0x110730000 end:0x3ff80002850
   symbol__hists notes->src:0x2aa2a70 nr_hists:1
   symbol__inc_addr_samples sym:unlink_anon_vmas src:0x2aa2a70
   __symbol__inc_addr_samples: addr=0x11094c69e
   0x11094c670 unlink_anon_vmas: period++ [addr: 0x11094c69e, 0x2e, evidx=0]
   	=> nr_samples: 1, period: 526008
[tmricht@m83lp54 perf]$

There is no error about failed memory allocation and the TUI interface
shows all entries.
Signed-off-by: NThomas Richter <tmricht@linux.ibm.com>
Reviewed-by: NHendrik Brueckner <brueckner@linux.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/90cb5607-3e12-5167-682d-978eba7dafa8@linux.ibm.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      8a07aa4e
  27. 05 6月, 2019 1 次提交
  29. 16 5月, 2019 1 次提交
    • J
      perf annotate: Remove hist__account_cycles() from callback · bdd1666b
      由 Jin Yao 提交于 
      The hist__account_cycles() function is executed when the
hist_iter__branch_callback() is called.

But it looks it's not necessary.  In hist__account_cycles, it already
walks on all branch entries.

This patch moves the hist__account_cycles out of callback, now the data
processing is much faster than before.

Previous code has an issue that the ch[offset].num++ (in
__symbol__account_cycles) is executed repeatedly since
hist__account_cycles is called in each hist_iter__branch_callback, so
the counting of ch[offset].num is not correct (too big).

With this patch, the issue is fixed. And we don't need the code of
"ch->reset >= ch->num / 2" to check if there are too many overlaps (in
annotation__count_and_fill), otherwise some data would be hidden.

Now, we can try, for example:

  perf record -b ...
  perf annotate or perf report -s symbol

The before/after output should be no change.

 v3:
 ---
 Fix the crash in stdio mode.
 Like previous code, it needs the checking of ui__has_annotation()
 before hist__account_cycles()

 v2:
 ---
 1. Cover the similar perf report
 2. Remove the checking code "ch->reset >= ch->num / 2"
Signed-off-by: NJin Yao <yao.jin@linux.intel.com>
Tested-by: NArnaldo 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@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/1552684577-29041-1-git-send-email-yao.jin@linux.intel.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      bdd1666b
  31. 03 5月, 2019 1 次提交
  33. 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
  35. 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
  37. 22 2月, 2019 1 次提交
    • W
      perf annotate: Fix getting source line failure · 11db1ad4
      由 Wei Li 提交于 
      The output of "perf annotate -l --stdio xxx" changed since commit 425859ff
("perf annotate: No need to calculate notes->start twice") removed notes->start
assignment in symbol__calc_lines(). It will get failed in
find_address_in_section() from symbol__tty_annotate() subroutine as the
a2l->addr is wrong. So the annotate summary doesn't report the line number of
source code correctly.

Before fix:

  liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ cat common_while_1.c
  void hotspot_1(void)
  {
	volatile int i;

	for (i = 0; i < 0x10000000; i++);
	for (i = 0; i < 0x10000000; i++);
	for (i = 0; i < 0x10000000; i++);
  }

  int main(void)
  {
	hotspot_1();

	return 0;
  }
  liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ gcc common_while_1.c -g -o common_while_1

  liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf record ./common_while_1
  [ perf record: Woken up 2 times to write data ]
  [ perf record: Captured and wrote 0.488 MB perf.data (12498 samples) ]
  liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf annotate -l -s hotspot_1 --stdio

  Sorted summary for file /home/liwei/main_code/hulk_work/hulk/tools/perf/common_while_1
  ----------------------------------------------

   19.30 common_while_1[32]
   19.03 common_while_1[4e]
   19.01 common_while_1[16]
    5.04 common_while_1[13]
    4.99 common_while_1[4b]
    4.78 common_while_1[2c]
    4.77 common_while_1[10]
    4.66 common_while_1[2f]
    4.59 common_while_1[51]
    4.59 common_while_1[35]
    4.52 common_while_1[19]
    4.20 common_while_1[56]
    0.51 common_while_1[48]
   Percent |      Source code & Disassembly of common_while_1 for cycles:ppp (12480 samples, percent: local period)
  -----------------------------------------------------------------------------------------------------------------
         :
         :
         :
         :         Disassembly of section .text:
         :
         :         00000000000005fa <hotspot_1>:
         :         hotspot_1():
         :         void hotspot_1(void)
         :         {
    0.00 :   5fa:   push   %rbp
    0.00 :   5fb:   mov    %rsp,%rbp
         :                 volatile int i;
         :
         :                 for (i = 0; i < 0x10000000; i++);
    0.00 :   5fe:   movl   $0x0,-0x4(%rbp)
    0.00 :   605:   jmp    610 <hotspot_1+0x16>
    0.00 :   607:   mov    -0x4(%rbp),%eax
   common_while_1[10]    4.77 :   60a:   add    $0x1,%eax
   common_while_1[13]    5.04 :   60d:   mov    %eax,-0x4(%rbp)
   common_while_1[16]   19.01 :   610:   mov    -0x4(%rbp),%eax
   common_while_1[19]    4.52 :   613:   cmp    $0xfffffff,%eax
      0.00 :   618:   jle    607 <hotspot_1+0xd>
           :                 for (i = 0; i < 0x10000000; i++);
  ...

After fix:

  liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf record ./common_while_1
  [ perf record: Woken up 2 times to write data ]
  [ perf record: Captured and wrote 0.488 MB perf.data (12500 samples) ]
  liwei@euler:~/main_code/hulk_work/hulk/tools/perf$ sudo ./perf annotate -l -s hotspot_1 --stdio

  Sorted summary for file /home/liwei/main_code/hulk_work/hulk/tools/perf/common_while_1
  ----------------------------------------------

   33.34 common_while_1.c:5
   33.34 common_while_1.c:6
   33.32 common_while_1.c:7
   Percent |      Source code & Disassembly of common_while_1 for cycles:ppp (12482 samples, percent: local period)
  -----------------------------------------------------------------------------------------------------------------
         :
         :
         :
         :         Disassembly of section .text:
         :
         :         00000000000005fa <hotspot_1>:
         :         hotspot_1():
         :         void hotspot_1(void)
         :         {
    0.00 :   5fa:   push   %rbp
    0.00 :   5fb:   mov    %rsp,%rbp
         :                 volatile int i;
         :
         :                 for (i = 0; i < 0x10000000; i++);
    0.00 :   5fe:   movl   $0x0,-0x4(%rbp)
    0.00 :   605:   jmp    610 <hotspot_1+0x16>
    0.00 :   607:   mov    -0x4(%rbp),%eax
   common_while_1.c:5    4.70 :   60a:   add    $0x1,%eax
    4.89 :   60d:   mov    %eax,-0x4(%rbp)
   common_while_1.c:5   19.03 :   610:   mov    -0x4(%rbp),%eax
   common_while_1.c:5    4.72 :   613:   cmp    $0xfffffff,%eax
    0.00 :   618:   jle    607 <hotspot_1+0xd>
         :                 for (i = 0; i < 0x10000000; i++);
    0.00 :   61a:   movl   $0x0,-0x4(%rbp)
    0.00 :   621:   jmp    62c <hotspot_1+0x32>
    0.00 :   623:   mov    -0x4(%rbp),%eax
   common_while_1.c:6    4.54 :   626:   add    $0x1,%eax
    4.73 :   629:   mov    %eax,-0x4(%rbp)
   common_while_1.c:6   19.54 :   62c:   mov    -0x4(%rbp),%eax
   common_while_1.c:6    4.54 :   62f:   cmp    $0xfffffff,%eax
  ...
Signed-off-by: NWei Li <liwei391@huawei.com>
Acked-by: NJiri Olsa <jolsa@kernel.org>
Tested-by: NArnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: 425859ff ("perf annotate: No need to calculate notes->start twice")
Link: http://lkml.kernel.org/r/20190221095716.39529-1-liwei391@huawei.comSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      11db1ad4
  39. 06 2月, 2019 1 次提交
  41. 25 1月, 2019 1 次提交
  43. 04 1月, 2019 1 次提交
  45. 18 12月, 2018 4 次提交
  47. 18 10月, 2018 1 次提交
    • D
      perf annotate: Add Sparc support · 0ab41886
      由 David Miller 提交于 
      E.g.:

  $ perf annotate --stdio2
  Samples: 7K of event 'cycles:ppp', 4000 Hz, Event count (approx.): 3086733887
  __gettimeofday  /lib32/libc-2.27.so [Percent: local period]
  Percent│
         │
         │
         │    Disassembly of section .text:
         │
         │    000a6fa0 <__gettimeofday@@GLIBC_2.0>:
    0.47 │      save   %sp, -96, %sp
    0.73 │      sethi  %hi(0xe9000), %l7
         │    → call   __frame_state_for@@GLIBC_2.0+0x480
    0.30 │      add    %l7, 0x58, %l7     ! e9058 <nftw64@@GLIBC_2.3.3+0x818>
    1.33 │      mov    %i0, %o0
         │      mov    %i1, %o1
    0.43 │      mov    0x74, %g1
         │      ta     0x10
   88.92 │    ↓ bcc    30
    2.95 │      clr    %g1
         │      neg    %o0
         │      mov    1, %g1
    0.31 │30:   cmp    %g1, 0
         │      bne,pn %icc, a6fe4 <__gettimeofday@@GLIBC_2.0+0x44>
         │      mov    %o0, %i0
    1.96 │    ← return %i7 + 8
    2.62 │      nop
         │      sethi  %hi(0), %g1
         │      neg    %o0, %g2
         │      add    %g1, 0x160, %g1
         │      ld     [ %l7 + %g1 ], %g1
         │      st     %g2, [ %g7 + %g1 ]
         │    ← return %i7 + 8
         │      mov    -1, %o0
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
Link: http://lkml.kernel.org/r/20181016.205555.1070918198627611771.davem@davemloft.netSigned-off-by: NArnaldo Carvalho de Melo <acme@redhat.com>
      0ab41886