[PATCH v3 09/13] perf tools: Introduce bpf-output event

[Wang Nan]

Commit a43eec304259a6c637f4014a6d4767159b6a3aa3 (bpf: introduce
bpf_perf_event_output() helper) add a helper to enable BPF program
output data to perf ring buffer through a new type of perf event
PERF_COUNT_SW_BPF_OUTPUT. This patch enable perf to create perf
event of that type. Now perf user can use following cmdline to
receive output data from BPF programs:

 # ./perf record -a -e evt=bpf-output/no-inherit/ \
                    -e ./test_bpf_output.c/maps:channel.event=evt/ ls /
 # ./perf script
	perf 12927 [004] 355971.129276:          0 evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write
	perf 12927 [004] 355971.129279:          0 evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write
	...

Test result:
 # cat ./test_bpf_output.c
 /************************ BEGIN **************************/
 typedef int u32;
 typedef unsigned long long u64;

 enum bpf_map_type {
 	BPF_MAP_TYPE_PERF_EVENT_ARRAY = 4,
 };

 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 (*bpf_ktime_get_ns)(void) =
 	(void *)5;
 static int (*bpf_trace_printk)(const char *fmt, int fmt_size, ...) =
 	(void *)6;
 static int (*bpf_get_smp_processor_id)(void) =
 	(void *)8;
 static int (*bpf_perf_event_output)(void *, struct bpf_map_def *, int, void *, unsigned long) =
 	(void *)23;

 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\n";

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

 # ./perf record -a -e evt=bpf-output/no-inherit/ \
                    -e ./test_bpf_output.c/maps:channel.event=evt/ ls /
 # ./perf script | grep ls
              ls  4085 [000] 2746114.230215: evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write (/lib/modules/4.3.0-rc4+/build/vmlinux)
              ls  4085 [000] 2746114.230244: evt=bpf-output/no-inherit/:  ffffffff811ed5f1 sys_write (/lib/modules/4.3.0-rc4+/build/vmlinux)

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxx>
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Brendan Gregg <brendan.d.gregg@xxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Zefan Li <lizefan@xxxxxxxxxx>
Cc: pi3orama@xxxxxxx
---
 tools/perf/util/evsel.c        | 6 ++++++
 tools/perf/util/parse-events.l | 1 +
 2 files changed, 7 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 32131fc..4dee8e3 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -224,6 +224,12 @@ struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
 	if (evsel != NULL)
 		perf_evsel__init(evsel, attr, idx);
 
+	if ((evsel->attr.type == PERF_TYPE_SOFTWARE) &&
+	    (evsel->attr.config == PERF_COUNT_SW_BPF_OUTPUT)) {
+		evsel->attr.sample_type |= PERF_SAMPLE_RAW;
+		evsel->attr.sample_period = 1;
+	}
+
 	return evsel;
 }
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 8bb3437..27d567f 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -249,6 +249,7 @@ 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.
-- 
1.8.3.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/