[PATCH v5 5/6] bpf: add option for bpf_load.c to use perf_kprobe

[Song Liu <songliubraving@fb.com>]

Function load_and_attach() is updated to be able to create kprobes
with either old text based API, or the new perf_event_open API.

A global flag use_perf_kprobe is added to select between the two
APIs.

Signed-off-by: Song Liu <songliubraving@fb.com>
Reviewed-by: Josef Bacik <jbacik@fb.com>
---
 samples/bpf/bpf_load.c | 61 +++++++++++++++++++++++++++++++++++++++++++-------
 samples/bpf/bpf_load.h | 10 +++++++++
 2 files changed, 63 insertions(+), 8 deletions(-)

diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c
index 2325d7a..86e3818 100644
--- a/samples/bpf/bpf_load.c
+++ b/samples/bpf/bpf_load.c
@@ -8,7 +8,6 @@
 #include <errno.h>
 #include <unistd.h>
 #include <string.h>
-#include <stdbool.h>
 #include <stdlib.h>
 #include <linux/bpf.h>
 #include <linux/filter.h>
@@ -29,6 +28,7 @@
 #include "perf-sys.h"
 
 #define DEBUGFS "/sys/kernel/debug/tracing/"
+#define KPROBE_TYPE_FILE "/sys/bus/event_source/devices/kprobe/type"
 
 static char license[128];
 static int kern_version;
@@ -42,6 +42,8 @@ int prog_array_fd = -1;
 
 struct bpf_map_data map_data[MAX_MAPS];
 int map_data_count = 0;
+bool use_perf_kprobe = true;
+int perf_kprobe_type = -1;
 
 static int populate_prog_array(const char *event, int prog_fd)
 {
@@ -55,6 +57,26 @@ static int populate_prog_array(const char *event, int prog_fd)
 	return 0;
 }
 
+int get_perf_kprobe_type_id(void)
+{
+	int tfd;
+	int err;
+	char buf[16];
+
+	tfd = open(KPROBE_TYPE_FILE, O_RDONLY);
+	if (tfd < 0)
+		return -1;
+
+	err = read(tfd, buf, sizeof(buf));
+	close(tfd);
+
+	if (err < 0 || err >= sizeof(buf))
+		return -1;
+	buf[err] = 0;
+	perf_kprobe_type = atoi(buf);
+	return perf_kprobe_type;
+}
+
 static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 {
 	bool is_socket = strncmp(event, "socket", 6) == 0;
@@ -70,7 +92,7 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 	size_t insns_cnt = size / sizeof(struct bpf_insn);
 	enum bpf_prog_type prog_type;
 	char buf[256];
-	int fd, efd, err, id;
+	int fd, efd, err, id = -1;
 	struct perf_event_attr attr = {};
 
 	attr.type = PERF_TYPE_TRACEPOINT;
@@ -128,7 +150,13 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		return populate_prog_array(event, fd);
 	}
 
-	if (is_kprobe || is_kretprobe) {
+	if (use_perf_kprobe && perf_kprobe_type == -1) {
+		get_perf_kprobe_type_id();
+		if (perf_kprobe_type == -1)
+			use_perf_kprobe = false;
+	}
+
+	if (!use_perf_kprobe && (is_kprobe || is_kretprobe)) {
 		if (is_kprobe)
 			event += 7;
 		else
@@ -169,27 +197,44 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size)
 		strcat(buf, "/id");
 	}
 
+	if (use_perf_kprobe && (is_kprobe || is_kretprobe)) {
+		attr.type = perf_kprobe_type;
+		attr.kprobe_func = ptr_to_u64(
+			event + strlen(is_kprobe ? "kprobe/" : "kretprobe/"));
+		attr.probe_offset = 0;
+
+		/* PERF_PROBE_CONFIG_IS_RETPROBE in kernel/events/core.c */
+		if (is_kretprobe)
+			attr.config |= 1 << 0;
+	} else {
 		efd = open(buf, O_RDONLY, 0);
 		if (efd < 0) {
 			printf("failed to open event %s\n", event);
 			return -1;
 		}
-
 		err = read(efd, buf, sizeof(buf));
 		if (err < 0 || err >= sizeof(buf)) {
-		printf("read from '%s' failed '%s'\n", event, strerror(errno));
+			printf("read from '%s' failed '%s'\n", event,
+			       strerror(errno));
 			return -1;
 		}
-
 		close(efd);
-
 		buf[err] = 0;
 		id = atoi(buf);
 		attr.config = id;
+	}
 
 	efd = sys_perf_event_open(&attr, -1/*pid*/, 0/*cpu*/, -1/*group_fd*/, 0);
 	if (efd < 0) {
-		printf("event %d fd %d err %s\n", id, efd, strerror(errno));
+		if (use_perf_kprobe && (is_kprobe || is_kretprobe))
+			printf("k%sprobe %s fd %d err %s\n",
+			       is_kprobe ? "" : "ret",
+			       event + strlen(is_kprobe ? "kprobe/"
+					      : "kretprobe/"),
+			       efd, strerror(errno));
+		else
+			printf("event %d fd %d err %s\n", id, efd,
+			       strerror(errno));
 		return -1;
 	}
 	event_fd[prog_cnt - 1] = efd;
diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h
index 7d57a42..95d6be5 100644
--- a/samples/bpf/bpf_load.h
+++ b/samples/bpf/bpf_load.h
@@ -2,6 +2,7 @@
 #ifndef __BPF_LOAD_H
 #define __BPF_LOAD_H
 
+#include <stdbool.h>
 #include "libbpf.h"
 
 #define MAX_MAPS 32
@@ -38,6 +39,10 @@ extern int map_fd[MAX_MAPS];
 extern struct bpf_map_data map_data[MAX_MAPS];
 extern int map_data_count;
 
+extern bool use_perf_kprobe;
+extern int perf_kprobe_type;
+extern int get_perf_kprobe_type_id(void);
+
 /* parses elf file compiled by llvm .c->.o
  * . parses 'maps' section and creates maps via BPF syscall
  * . parses 'license' section and passes it to syscall
@@ -59,6 +64,11 @@ struct ksym {
 	char *name;
 };
 
+static inline __u64 ptr_to_u64(const void *ptr)
+{
+	return (__u64) (unsigned long) ptr;
+}
+
 int load_kallsyms(void);
 struct ksym *ksym_search(long key);
 int set_link_xdp_fd(int ifindex, int fd, __u32 flags);
-- 
2.9.5