[PATCH 06/22] perf tools: Attach eBPF program to perf event

[Wang Nan]

This is the final patch which makes basic BPF filter work. After
applying this patch, users are allowed to use BPF filter like:

 # perf record --event ./hello_world.o ls

A bpf_fd field is appended to 'struct evsel', and setup during the
callback function add_bpf_event() for each 'probe_trace_event'.

PERF_EVENT_IOC_SET_BPF ioctl is used to attach eBPF program to a newly
created perf event. The file descriptor of the eBPF program is passed to
perf record using previous patches, and stored into evsel->bpf_fd.

It is possible that different perf event are created for one kprobe
events for different CPUs. In this case, when trying to call the
ioctl, EEXIST will be return. This patch doesn't treat it as an error.

Signed-off-by: Wang Nan <wangnan0@xxxxxxxxxx>
Cc: Alexei Starovoitov <ast@xxxxxxxxxxxx>
Cc: Brendan Gregg <brendan.d.gregg@xxxxxxxxx>
Cc: Daniel Borkmann <daniel@xxxxxxxxxxxxx>
Cc: David Ahern <dsahern@xxxxxxxxx>
Cc: He Kuang <hekuang@xxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Kaixu Xia <xiakaixu@xxxxxxxxxx>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@xxxxxxxxxxx>
Cc: Namhyung Kim <namhyung@xxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxx>
Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx>
Cc: Zefan Li <lizefan@xxxxxxxxxx>
Cc: pi3orama@xxxxxxx
Cc: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Link: http://lkml.kernel.org/n/ebpf-6yw9eg0ej3l4jnqhinngkw86@xxxxxxxxxxxxxx
---
 tools/perf/util/evsel.c        | 17 +++++++++++++++++
 tools/perf/util/evsel.h        |  1 +
 tools/perf/util/parse-events.c |  4 ++++
 3 files changed, 22 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 5889004..3f69d72 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -208,6 +208,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->unit	   = "";
 	evsel->scale	   = 1.0;
 	evsel->evlist	   = NULL;
+	evsel->bpf_fd	   = -1;
 	INIT_LIST_HEAD(&evsel->node);
 	INIT_LIST_HEAD(&evsel->config_terms);
 	perf_evsel__object.init(evsel);
@@ -1343,6 +1344,22 @@ retry_open:
 					  err);
 				goto try_fallback;
 			}
+
+			if (evsel->bpf_fd >= 0) {
+				int evt_fd = FD(evsel, cpu, thread);
+				int bpf_fd = evsel->bpf_fd;
+
+				err = ioctl(evt_fd,
+					    PERF_EVENT_IOC_SET_BPF,
+					    bpf_fd);
+				if (err && errno != EEXIST) {
+					pr_err("failed to attach bpf fd %d: %s\n",
+					       bpf_fd, strerror(errno));
+					err = -EINVAL;
+					goto out_close;
+				}
+			}
+
 			set_rlimit = NO_CHANGE;
 
 			/*
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 7906666..96f1294 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -120,6 +120,7 @@ struct perf_evsel {
 	char			*group_name;
 	bool			cmdline_group_boundary;
 	struct list_head	config_terms;
+	int			bpf_fd;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c3505fb..37cb196 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -527,6 +527,7 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 	struct __add_bpf_event_param *param = _param;
 	struct parse_events_evlist *evlist = param->data;
 	struct list_head *list = param->list;
+	struct perf_evsel *pos;
 	int err;
 
 	pr_debug("add bpf event %s:%s and attach bpf program %d\n",
@@ -546,6 +547,9 @@ static int add_bpf_event(struct probe_trace_event *tev, int fd,
 		return err;
 	}
 	pr_debug("adding %s:%s\n", tev->group, tev->event);
+
+	list_for_each_entry(pos, list, node)
+		pos->bpf_fd = fd;
 	return 0;
 }
 
-- 
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/