[tip:perf/core] perf bpf: Automatically create bpf-output event __bpf_stdout__

[tip-bot for Wang Nan]

Commit-ID:  72c0809856b9174e71eab4e293089f6a114e0d41
Gitweb:     http://git.kernel.org/tip/72c0809856b9174e71eab4e293089f6a114e0d41
Author:     Wang Nan <wangnan0@xxxxxxxxxx>
AuthorDate: Fri, 8 Apr 2016 15:07:25 +0000
Committer:  Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
CommitDate: Mon, 11 Apr 2016 22:18:04 -0300

perf bpf: Automatically create bpf-output event __bpf_stdout__

This patch removes the need to set a bpf-output event in cmdline.  By
referencing a map named '__bpf_stdout__', perf automatically creates an
event for it.

For example:

  # perf record -e ./test_bpf_trace.c usleep 100000
  [ perf record: Woken up 1 times to write data ]
  [ perf record: Captured and wrote 0.012 MB perf.data (2 samples) ]
  # perf script
           usleep  4639 [000] 261895.307826:        0            __bpf_stdout__:  ffffffff810eb9a1 ...
       BPF output: 0000: 52 61 69 73 65 20 61 20  Raise a
                   0008: 42 50 46 20 65 76 65 6e  BPF even
                   0010: 74 21 00 00              t!..
       BPF string: "Raise a BPF event!"

           usleep  4639 [000] 261895.407883:        0            __bpf_stdout__:  ffffffff8105d609 ...
       BPF output: 0000: 52 61 69 73 65 20 61 20  Raise a
                   0008: 42 50 46 20 65 76 65 6e  BPF even
                   0010: 74 21 00 00              t!..
       BPF string: "Raise a BPF event!"

  perf record -e ./test_bpf_trace.c usleep 100000

  equals to:

  perf record -e bpf-output/no-inherit=1,name=__bpf_stdout__/ \
              -e ./test_bpf_trace.c/map:__bpf_stdout__.event=__bpf_stdout__/ \
              usleep 100000

Where test_bpf_trace.c is:

  /************************ BEGIN **************************/
  #include <uapi/linux/bpf.h>
  struct bpf_map_def {
         unsigned int type;
         unsigned int key_size;
         unsigned int value_size;
         unsigned int max_entries;
  };
  #define SEC(NAME) __attribute__((section(NAME), used))
  static u64 (*ktime_get_ns)(void) =
         (void *)BPF_FUNC_ktime_get_ns;
  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_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
         (void *)BPF_FUNC_perf_event_output;

  struct bpf_map_def SEC("maps") __bpf_stdout__ = {
         .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
         .key_size = sizeof(int),
         .value_size = sizeof(u32),
         .max_entries = __NR_CPUS__,
  };

  static inline int __attribute__((always_inline))
  func(void *ctx, int type)
  {
	char output_str[] = "Raise a BPF event!";
	char err_str[] = "BAD %d\n";
	int err;

        err = perf_event_output(ctx, &__bpf_stdout__, get_smp_processor_id(),
			        &output_str, sizeof(output_str));
	if (err)
		trace_printk(err_str, sizeof(err_str), err);
        return 1;
  }
  SEC("func_begin=sys_nanosleep")
  int func_begin(void *ctx) {return func(ctx, 1);}
  SEC("func_end=sys_nanosleep%return")
  int func_end(void *ctx) { return func(ctx, 2);}
  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;
  /************************* END ***************************/

Committer note:

Testing with 'perf trace':

  # trace -e nanosleep --ev test_bpf_stdout.c usleep 1
     0.007 ( 0.007 ms): usleep/729 nanosleep(rqtp: 0x7ffc5bbc5fe0) ...
     0.007 (         ): __bpf_stdout__:Raise a BPF event!..)
     0.008 (         ): perf_bpf_probe:func_begin:(ffffffff81112460))
     0.069 (         ): __bpf_stdout__:Raise a BPF event!..)
     0.070 (         ): perf_bpf_probe:func_end:(ffffffff81112460 <- ffffffff81003d92))
     0.072 ( 0.072 ms): usleep/729  ... [continued]: nanosleep()) = 0
  #

Suggested-and-Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Zefan Li <lizefan@xxxxxxxxxx>
Cc: pi3orama@xxxxxxx
Link: http://lkml.kernel.org/r/1460128045-97310-5-git-send-email-wangnan0@xxxxxxxxxx
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
 tools/perf/util/bpf-loader.c | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 67f61a9..493307d 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -1483,6 +1483,7 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 {
 	struct bpf_map_priv *tmpl_priv = NULL;
 	struct bpf_object *obj, *tmp;
+	struct perf_evsel *evsel = NULL;
 	struct bpf_map *map;
 	int err;
 	bool need_init = false;
@@ -1507,8 +1508,16 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 	if (!need_init)
 		return 0;
 
-	if (!tmpl_priv)
-		return 0;
+	if (!tmpl_priv) {
+		err = parse_events(evlist, "bpf-output/no-inherit=1,name=__bpf_stdout__/",
+				   NULL);
+		if (err) {
+			pr_debug("ERROR: failed to create bpf-output event\n");
+			return -err;
+		}
+
+		evsel = perf_evlist__last(evlist);
+	}
 
 	bpf__for_each_stdout_map(map, obj, tmp) {
 		struct bpf_map_priv *priv;
@@ -1519,14 +1528,24 @@ int bpf__setup_stdout(struct perf_evlist *evlist __maybe_unused)
 		if (priv)
 			continue;
 
-		priv = bpf_map_priv__clone(tmpl_priv);
-		if (!priv)
-			return -ENOMEM;
+		if (tmpl_priv) {
+			priv = bpf_map_priv__clone(tmpl_priv);
+			if (!priv)
+				return -ENOMEM;
 
-		err = bpf_map__set_private(map, priv, bpf_map_priv__clear);
-		if (err) {
-			bpf_map_priv__clear(map, priv);
-			return err;
+			err = bpf_map__set_private(map, priv, bpf_map_priv__clear);
+			if (err) {
+				bpf_map_priv__clear(map, priv);
+				return err;
+			}
+		} else if (evsel) {
+			struct bpf_map_op *op;
+
+			op = bpf_map__add_newop(map, NULL);
+			if (IS_ERR(op))
+				return PTR_ERR(op);
+			op->op_type = BPF_MAP_OP_SET_EVSEL;
+			op->v.evsel = evsel;
 		}
 	}