samples/bpf: bpf_tail_call example for networking

Usage:
$ sudo ./sockex3
IP     src.port -> dst.port               bytes      packets
127.0.0.1.42010 -> 127.0.0.1.12865         1568            8
127.0.0.1.59526 -> 127.0.0.1.33778     11422636       173070
127.0.0.1.33778 -> 127.0.0.1.59526  11260224828       341974
127.0.0.1.12865 -> 127.0.0.1.42010         1832           12
IP     src.port -> dst.port               bytes      packets
127.0.0.1.42010 -> 127.0.0.1.12865         1568            8
127.0.0.1.59526 -> 127.0.0.1.33778     23198092       351486
127.0.0.1.33778 -> 127.0.0.1.59526  22972698518       698616
127.0.0.1.12865 -> 127.0.0.1.42010         1832           12

this example is similar to sockex2 in a way that it accumulates per-flow
statistics, but it does packet parsing differently.
sockex2 inlines full packet parser routine into single bpf program.
This sockex3 example have 4 independent programs that parse vlan, mpls, ip, ipv6
and one main program that starts the process.
bpf_tail_call() mechanism allows each program to be small and be called
on demand potentially multiple times, so that many vlan, mpls, ip in ip,
gre encapsulations can be parsed. These and other protocol parsers can
be added or removed at runtime. TLVs can be parsed in similar manner.
Note, tail_call_cnt dynamic check limits the number of tail calls to 32.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 66 insertions, 0 deletions

diff --git a/samples/bpf/sockex3_user.c b/samples/bpf/sockex3_user.c
new file mode 100644
index 000000000000..2617772d060d
--- /dev/null
+++ b/samples/bpf/sockex3_user.c
@@ -0,0 +1,66 @@
+#include <stdio.h>
+#include <assert.h>
+#include <linux/bpf.h>
+#include "libbpf.h"
+#include "bpf_load.h"
+#include <unistd.h>
+#include <arpa/inet.h>
+
+struct flow_keys {
+	__be32 src;
+	__be32 dst;
+	union {
+		__be32 ports;
+		__be16 port16[2];
+	};
+	__u32 ip_proto;
+};
+
+struct pair {
+	__u64 packets;
+	__u64 bytes;
+};
+
+int main(int argc, char **argv)
+{
+	char filename[256];
+	FILE *f;
+	int i, sock;
+
+	snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]);
+
+	if (load_bpf_file(filename)) {
+		printf("%s", bpf_log_buf);
+		return 1;
+	}
+
+	sock = open_raw_sock("lo");
+
+	assert(setsockopt(sock, SOL_SOCKET, SO_ATTACH_BPF, &prog_fd[4],
+			  sizeof(__u32)) == 0);
+
+	if (argc > 1)
+		f = popen("ping -c5 localhost", "r");
+	else
+		f = popen("netperf -l 4 localhost", "r");
+	(void) f;
+
+	for (i = 0; i < 5; i++) {
+		struct flow_keys key = {}, next_key;
+		struct pair value;
+
+		sleep(1);
+		printf("IP     src.port -> dst.port               bytes      packets\n");
+		while (bpf_get_next_key(map_fd[2], &key, &next_key) == 0) {
+			bpf_lookup_elem(map_fd[2], &next_key, &value);
+			printf("%s.%05d -> %s.%05d %12lld %12lld\n",
+			       inet_ntoa((struct in_addr){htonl(next_key.src)}),
+			       next_key.port16[0],
+			       inet_ntoa((struct in_addr){htonl(next_key.dst)}),
+			       next_key.port16[1],
+			       value.bytes, value.packets);
+			key = next_key;
+		}
+	}
+	return 0;
+}