perf tools: Enable passing event to BPF object

A new syntax is added to the parser so that the user can access
predefined perf events in BPF objects.

After this patch, BPF programs for perf are finally able to utilize
bpf_perf_event_read() introduced in commit 35578d798400 ("bpf: Implement
function bpf_perf_event_read() that get the selected hardware PMU
counter").

Test result:

  # cat test_bpf_map_2.c
  /************************ BEGIN **************************/
  #include <uapi/linux/bpf.h>
  #define SEC(NAME) __attribute__((section(NAME), used))
  struct bpf_map_def {
      unsigned int type;
      unsigned int key_size;
      unsigned int value_size;
      unsigned int max_entries;
  };
  static int (*trace_printk)(const char *fmt, int fmt_size, ...) =
      (void *)BPF_FUNC_trace_printk;
  static int (*get_smp_processor_id)(void) =
      (void *)BPF_FUNC_get_smp_processor_id;
  static int (*perf_event_read)(struct bpf_map_def *, int) =
      (void *)BPF_FUNC_perf_event_read;

  struct bpf_map_def SEC("maps") pmu_map = {
      .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
      .key_size = sizeof(int),
      .value_size = sizeof(int),
      .max_entries = __NR_CPUS__,
  };
  SEC("func_write=sys_write")
  int func_write(void *ctx)
  {
      unsigned long long val;
      char fmt[] = "sys_write:        pmu=%llu\n";
      val = perf_event_read(&pmu_map, get_smp_processor_id());
      trace_printk(fmt, sizeof(fmt), val);
      return 0;
  }

  SEC("func_write_return=sys_write%return")
  int func_write_return(void *ctx)
  {
      unsigned long long val = 0;
      char fmt[] = "sys_write_return: pmu=%llu\n";
      val = perf_event_read(&pmu_map, get_smp_processor_id());
      trace_printk(fmt, sizeof(fmt), val);
      return 0;
  }
  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;
  /************************* END ***************************/

Normal case:

  # echo "" > /sys/kernel/debug/tracing/trace
  # perf record -i -e cycles -e './test_bpf_map_2.c/map:pmu_map.event=cycles/' ls /
  [SNIP]
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.013 MB perf.data (7 samples) ]
  # cat /sys/kernel/debug/tracing/trace | grep ls
                ls-17066 [000] d... 938449.863301: : sys_write:        pmu=1157327
                ls-17066 [000] dN.. 938449.863342: : sys_write_return: pmu=1225218
                ls-17066 [000] d... 938449.863349: : sys_write:        pmu=1241922
                ls-17066 [000] dN.. 938449.863369: : sys_write_return: pmu=1267445

Normal case (system wide):

  # echo "" > /sys/kernel/debug/tracing/trace
  # perf record -i -e cycles -e './test_bpf_map_2.c/map:pmu_map.event=cycles/' -a
  ^C[ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.811 MB perf.data (120 samples) ]

  # cat /sys/kernel/debug/tracing/trace | grep -v '18446744073709551594' | grep -v perf | head -n 20
  [SNIP]
  #           TASK-PID   CPU#  ||||    TIMESTAMP  FUNCTION
  #              | |       |   ||||       |         |
             gmain-30828 [002] d... 2740551.068992: : sys_write:        pmu=84373
             gmain-30828 [002] d... 2740551.068992: : sys_write_return: pmu=87696
             gmain-30828 [002] d... 2740551.068996: : sys_write:        pmu=100658
             gmain-30828 [002] d... 2740551.068997: : sys_write_return: pmu=102572

Error case 1:

  # perf record -e './test_bpf_map_2.c' ls /
  [SNIP]
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.014 MB perf.data ]
  # cat /sys/kernel/debug/tracing/trace | grep ls
                ls-17115 [007] d... 2724279.665625: : sys_write:        pmu=18446744073709551614
                ls-17115 [007] dN.. 2724279.665651: : sys_write_return: pmu=18446744073709551614
                ls-17115 [007] d... 2724279.665658: : sys_write:        pmu=18446744073709551614
                ls-17115 [007] dN.. 2724279.665677: : sys_write_return: pmu=18446744073709551614

  (18446744073709551614 is 0xfffffffffffffffe (-2))

Error case 2:

  # perf record -e cycles -e './test_bpf_map_2.c/map:pmu_map.event=evt/' -a
  event syntax error: '..ps:pmu_map.event=evt/'
                                    \___ Event not found for map setting

  Hint:	Valid config terms:
       	map:[<arraymap>].value=[value]
       	map:[<eventmap>].event=[event]
  [SNIP]

Error case 3:
  # ls /proc/2348/task/
  2348  2505  2506  2507  2508
  # perf record -i -e cycles -e './test_bpf_map_2.c/map:pmu_map.event=cycles/' -p 2348
  ERROR: Apply config to BPF failed: Cannot set event to BPF map in multi-thread tracing

Error case 4:
  # perf record -e cycles -e './test_bpf_map_2.c/map:pmu_map.event=cycles/' ls /
  ERROR: Apply config to BPF failed: Doesn't support inherit event (Hint: use -i to turn off inherit)

Error case 5:
  # perf record -i -e raw_syscalls:sys_enter -e './test_bpf_map_2.c/map:pmu_map.event=raw_syscalls:sys_enter/' ls
  ERROR: Apply config to BPF failed: Can only put raw, hardware and BPF output event into a BPF map

Error case 6:
  # perf record -i -e './test_bpf_map_2.c/map:pmu_map.event=123/' ls /
  event syntax error: '.._map.event=123/'
                                    \___ Incorrect value type for map
  [SNIP]

Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Cody P Schafer <dev@codyps.com>
Cc: He Kuang <hekuang@huawei.com>
Cc: Jeremie Galarneau <jeremie.galarneau@efficios.com>
Cc: Kirill Smelkov <kirr@nexedi.com>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1456132275-98875-7-git-send-email-wangnan0@huawei.com
Signed-off-by: He Kuang <hekuang@huawei.com>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
6 files changed