perf tools: Introduce bpf-output event

Commit a43eec30 ("bpf: introduce bpf_perf_event_output() helper")
adds a helper to enable a BPF program to output data to a perf ring
buffer through a new type of perf event, PERF_COUNT_SW_BPF_OUTPUT. This
patch enables perf to create events of that type. Now a perf user can
use the following cmdline to receive output data from BPF programs:

  # perf record -a -e bpf-output/no-inherit,name=evt/ \
                    -e ./test_bpf_output.c/map:channel.event=evt/ ls /
  # perf script
     perf 1560 [004] 347747.086295:  evt: ffffffff811fd201 sys_write ...
     perf 1560 [004] 347747.086300:  evt: ffffffff811fd201 sys_write ...
     perf 1560 [004] 347747.086315:  evt: ffffffff811fd201 sys_write ...
            ...

Test result:

  # cat test_bpf_output.c
  /************************ 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") channel = {
 	.type = BPF_MAP_TYPE_PERF_EVENT_ARRAY,
 	.key_size = sizeof(int),
 	.value_size = sizeof(u32),
 	.max_entries = __NR_CPUS__,
  };

  SEC("func_write=sys_write")
  int func_write(void *ctx)
  {
 	struct {
 		u64 ktime;
 		int cpuid;
 	} __attribute__((packed)) output_data;
 	char error_data[] = "Error: failed to output: %d\n";

 	output_data.cpuid = get_smp_processor_id();
 	output_data.ktime = ktime_get_ns();
 	int err = perf_event_output(ctx, &channel, get_smp_processor_id(),
 				    &output_data, sizeof(output_data));
 	if (err)
 		trace_printk(error_data, sizeof(error_data), err);
 	return 0;
  }
  char _license[] SEC("license") = "GPL";
  int _version SEC("version") = LINUX_VERSION_CODE;
  /************************ END ***************************/

  # perf record -a -e bpf-output/no-inherit,name=evt/ \
                    -e ./test_bpf_output.c/map:channel.event=evt/ ls /
  # perf script | grep ls
     ls  2242 [003] 347851.557563:   evt: ffffffff811fd201 sys_write ...
     ls  2242 [003] 347851.557571:   evt: ffffffff811fd201 sys_write ...
Signed-off-by: Wang Nan <wangnan0@huawei.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: Jiri Olsa <jolsa@kernel.org>
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/1456132275-98875-11-git-send-email-wangnan0@huawei.comSigned-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/bpf-loader.c

@@ -1331,13 +1331,12 @@ apply_config_evsel_for_key(const char *name, int map_fd, void *pkey,
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTINH;
 	}
 
+	if (perf_evsel__is_bpf_output(evsel))
+		check_pass = true;
 	if (attr->type == PERF_TYPE_RAW)
 		check_pass = true;
 	if (attr->type == PERF_TYPE_HARDWARE)
 		check_pass = true;
-	if (attr->type == PERF_TYPE_SOFTWARE &&
-			attr->config == PERF_COUNT_SW_BPF_OUTPUT)
-		check_pass = true;
 	if (!check_pass) {
 		pr_debug("ERROR: Event type is wrong for map %s\n", name);
 		return -BPF_LOADER_ERRNO__OBJCONF_MAP_EVTTYPE;

tools/perf/util/evsel.c

@@ -225,6 +225,11 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if (perf_evsel__is_bpf_output(evsel)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 

tools/perf/util/evsel.h

@@ -364,6 +364,14 @@ static inline bool perf_evsel__is_function_event(struct perf_evsel *evsel)
 #undef FUNCTION_EVENT
 }
 
+static inline bool perf_evsel__is_bpf_output(struct perf_evsel *evsel)
+{
+	struct perf_event_attr *attr = &evsel->attr;
+
+	return (attr->config == PERF_COUNT_SW_BPF_OUTPUT) &&
+		(attr->type == PERF_TYPE_SOFTWARE);
+}
+
 struct perf_attr_details {
 	bool freq;
 	bool verbose;

tools/perf/util/parse-events.l

@@ -248,6 +248,7 @@ cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU
 alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
 emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
 dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
 
 	/*
 	 * We have to handle the kernel PMU event cycles-ct/cycles-t/mem-loads/mem-stores separately.