bpf: Add mptcp [gs]etsockopt per subflow

Closes: multipath-tcp#76
Signed-off-by: Geliang Tang <[email protected]>

tools/testing/selftests/bpf/prog_tests/mptcp.c

@@ -10,6 +10,7 @@
 #include "network_helpers.h"
 #include "mptcp_sock.skel.h"
 #include "mptcpify.skel.h"
+#include "mptcp_set_sf_sockopt_kern.skel.h"
 #include "mptcp_bpf_first.skel.h"
 #include "mptcp_bpf_bkup.skel.h"
 #include "mptcp_bpf_rr.skel.h"
@@ -329,6 +330,73 @@ static void test_mptcpify(void)
 	close(cgroup_fd);
 }
 
+static int getsetsockopt(int map_fd)
+{
+	int server_fd, client_fd, err = 0;
+
+	server_fd = start_mptcp_server(AF_INET, NULL, 0, 0);
+	if (!ASSERT_GE(server_fd, 0, "start_mptcp_server")) {
+		err = -EIO;
+		goto out;
+	}
+
+	client_fd = connect_to_fd(server_fd, 0);
+	if (!ASSERT_GE(client_fd, 0, "connect to fd")) {
+		err = -EIO;
+		goto close_server;
+	}
+
+	send_byte(client_fd);
+	SYS(out, "ip netns exec %s ss -Menita", NS_TEST);
+
+	close(client_fd);
+close_server:
+	close(server_fd);
+out:
+	return err;
+}
+
+static void run_test_sockopt(int cgroup_fd)
+{
+	int prog_fd, map_fd, err;
+	struct mptcp_set_sf_sockopt_kern *skel;
+
+	skel = mptcp_set_sf_sockopt_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_load"))
+		goto cleanup;
+
+	prog_fd = bpf_program__fd(skel->progs.mark_mptcp_sf);
+	map_fd = bpf_map__fd(skel->maps.mptcp_sf);
+	err = bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_SOCK_OPS, 0);
+	if (!ASSERT_OK(err, "bpf_prog_attach"))
+		goto cleanup;
+
+	ASSERT_OK(getsetsockopt(map_fd), "getsetsockopt");
+
+cleanup:
+	mptcp_set_sf_sockopt_kern__destroy(skel);
+}
+
+void test_sockopt_mptcp(void)
+{
+	struct nstoken *nstoken = NULL;
+	int cgroup_fd;
+
+	cgroup_fd = test__join_cgroup("/sockopt_mptcp");
+	if (!ASSERT_GE(cgroup_fd, 0, "join_cgroup /sockopt_mptcp"))
+		return;
+
+	nstoken = create_netns();
+	if (!ASSERT_OK_PTR(nstoken, "create_netns"))
+		goto fail;
+
+	run_test_sockopt(cgroup_fd);
+
+fail:
+	cleanup_netns(nstoken);
+	close(cgroup_fd);
+}
+
 static const unsigned int total_bytes = 10 * 1024 * 1024;
 static int stop, duration;
 
@@ -693,6 +761,8 @@ void test_mptcp(void)
 		test_base();
 	if (test__start_subtest("mptcpify"))
 		test_mptcpify();
+	if (test__start_subtest("sockopt"))
+		test_sockopt_mptcp();
 	if (test__start_subtest("default"))
 		test_default();
 	if (test__start_subtest("first"))

tools/testing/selftests/bpf/progs/mptcp_set_sf_sockopt_kern.c

@@ -0,0 +1,96 @@
+#include <asm/socket.h>	// SOL_SOCKET, SO_MARK, ...
+#include <linux/tcp.h>	// TCP_CONGESTION
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include "bpf_tcp_helpers.h"
+
+char _license[] SEC("license") = "GPL";
+
+#ifndef SOL_TCP
+#define SOL_TCP 6
+#endif
+
+#ifndef TCP_CA_NAME_MAX
+#define TCP_CA_NAME_MAX 16
+#endif
+
+char cc[TCP_CA_NAME_MAX] = "reno";
+
+/* Associate a subflow counter to each token */
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u32));
+	__uint(max_entries, 100);
+} mptcp_sf SEC(".maps");
+
+#define DEBUG 1
+
+#ifdef DEBUG
+char fmt1[] = "Mark <%u> : return code <%i>\n";
+char fmt2[] = "Failed to get bpf_sock\n";
+char fmt3[] = "Failed to get bpf_mptcp_sock\n";
+char fmt4[] = "Failed to update sockopt cc err=%d\n";
+char fmt5[] = "Failed to update sockopt mark\n";
+
+#define pr_debug(msg, ...) bpf_trace_printk(msg, sizeof(msg), ##__VA_ARGS__);
+
+#else
+
+#define pr_debug(msg, ...)
+
+#endif
+
+SEC("sockops")
+int mark_mptcp_sf(struct bpf_sock_ops *skops)
+{
+	__u32 init = 1, key, mark, *cnt;
+	int err;
+
+	if (skops->op != BPF_SOCK_OPS_TCP_CONNECT_CB)
+		goto out;
+
+	struct bpf_sock *sk = skops->sk;
+	if (!sk) {
+		pr_debug(fmt2);
+		goto out;
+	}
+
+	struct mptcp_sock *msk = bpf_skc_to_mptcp_sock(sk);
+	if (!msk) {
+		pr_debug(fmt3);
+		goto out;
+	}
+
+	key = msk->token;
+	cnt = bpf_map_lookup_elem(&mptcp_sf, &key);
+
+	if (cnt) {
+		/* A new subflow is added to an existing MPTCP connection */
+		__sync_fetch_and_add(cnt, 1);
+		mark = *cnt;
+	} else {
+		/* A new MPTCP connection is just initiated and this is its primary
+		 *  subflow
+		 */
+		bpf_map_update_elem(&mptcp_sf, &key, &init, BPF_ANY);
+		mark = init;
+	}
+
+	/* Set the mark of the subflow's socket to its apparition order */
+	err = bpf_setsockopt(skops, SOL_SOCKET, SO_MARK, &mark, sizeof(mark));
+	pr_debug(fmt1, mark, err);
+
+	if (err < 0)
+		pr_debug(fmt5);
+
+	if (mark == 1)
+		err = err ?: bpf_setsockopt(skops, SOL_TCP, TCP_CONGESTION, cc,
+					    TCP_CA_NAME_MAX);
+
+	if (err < 0)
+		pr_debug(fmt4, err);
+
+out:
+	return 0;
+}

tools/testing/selftests/bpf/progs/mptcp_sock.c

@@ -9,6 +9,8 @@
 char _license[] SEC("license") = "GPL";
 __u32 token = 0;
 
+int page_size = 0; /* userspace should set it */
+
 struct mptcp_storage {
 	__u32 invoked;
 	__u32 is_mptcp;
@@ -86,3 +88,15 @@ int BPF_PROG(trace_mptcp_pm_new_connection, struct mptcp_sock *msk,
 
 	return 0;
 }
+
+SEC("cgroup/getsockopt")
+int _getsockopt(struct bpf_sockopt *ctx)
+{
+	return 1;
+}
+
+SEC("cgroup/setsockopt")
+int _setsockopt(struct bpf_sockopt *ctx)
+{
+	return 1;
+}