net/tcp-fastopen: Add new API support

This patch adds a new socket option, TCP_FASTOPEN_CONNECT, as an
alternative way to perform Fast Open on the active side (client). Prior
to this patch, a client needs to replace the connect() call with
sendto(MSG_FASTOPEN). This can be cumbersome for applications who want
to use Fast Open: these socket operations are often done in lower layer
libraries used by many other applications. Changing these libraries
and/or the socket call sequences are not trivial. A more convenient
approach is to perform Fast Open by simply enabling a socket option when
the socket is created w/o changing other socket calls sequence:
  s = socket()
    create a new socket
  setsockopt(s, IPPROTO_TCP, TCP_FASTOPEN_CONNECT …);
    newly introduced sockopt
    If set, new functionality described below will be used.
    Return ENOTSUPP if TFO is not supported or not enabled in the
    kernel.

  connect()
    With cookie present, return 0 immediately.
    With no cookie, initiate 3WHS with TFO cookie-request option and
    return -1 with errno = EINPROGRESS.

  write()/sendmsg()
    With cookie present, send out SYN with data and return the number of
    bytes buffered.
    With no cookie, and 3WHS not yet completed, return -1 with errno =
    EINPROGRESS.
    No MSG_FASTOPEN flag is needed.

  read()
    Return -1 with errno = EWOULDBLOCK/EAGAIN if connect() is called but
    write() is not called yet.
    Return -1 with errno = EWOULDBLOCK/EAGAIN if connection is
    established but no msg is received yet.
    Return number of bytes read if socket is established and there is
    msg received.

The new API simplifies life for applications that always perform a write()
immediately after a successful connect(). Such applications can now take
advantage of Fast Open by merely making one new setsockopt() call at the time
of creating the socket. Nothing else about the application's socket call
sequence needs to change.

Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 34 insertions, 1 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c43eb1a831d7..d9735b76d073 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -533,6 +533,12 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
 
 		if (tp->urg_data & TCP_URG_VALID)
 			mask |= POLLPRI;
+	} else if (sk->sk_state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+		/* Active TCP fastopen socket with defer_connect
+		 * Return POLLOUT so application can call write()
+		 * in order for kernel to generate SYN+data
+		 */
+		mask |= POLLOUT | POLLWRNORM;
 	}
 	/* This barrier is coupled with smp_wmb() in tcp_reset() */
 	smp_rmb();
@@ -1071,6 +1077,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 				int *copied, size_t size)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
+	struct inet_sock *inet = inet_sk(sk);
 	int err, flags;
 
 	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
@@ -1085,9 +1092,19 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
 	tp->fastopen_req->data = msg;
 	tp->fastopen_req->size = size;
 
+	if (inet->defer_connect) {
+		err = tcp_connect(sk);
+		/* Same failure procedure as in tcp_v4/6_connect */
+		if (err) {
+			tcp_set_state(sk, TCP_CLOSE);
+			inet->inet_dport = 0;
+			sk->sk_route_caps = 0;
+		}
+	}
 	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
 	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
 				    msg->msg_namelen, flags);
+	inet->defer_connect = 0;
 	*copied = tp->fastopen_req->copied;
 	tcp_free_fastopen_req(tp);
 	return err;
@@ -1107,7 +1124,7 @@ int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	lock_sock(sk);
 
 	flags = msg->msg_flags;
-	if (flags & MSG_FASTOPEN) {
+	if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) {
 		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size);
 		if (err == -EINPROGRESS && copied_syn > 0)
 			goto out;
@@ -2656,6 +2673,18 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
 			err = -EINVAL;
 		}
 		break;
+	case TCP_FASTOPEN_CONNECT:
+		if (val > 1 || val < 0) {
+			err = -EINVAL;
+		} else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+			if (sk->sk_state == TCP_CLOSE)
+				tp->fastopen_connect = val;
+			else
+				err = -EINVAL;
+		} else {
+			err = -EOPNOTSUPP;
+		}
+		break;
 	case TCP_TIMESTAMP:
 		if (!tp->repair)
 			err = -EPERM;
@@ -3016,6 +3045,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		val = icsk->icsk_accept_queue.fastopenq.max_qlen;
 		break;
 
+	case TCP_FASTOPEN_CONNECT:
+		val = tp->fastopen_connect;
+		break;
+
 	case TCP_TIMESTAMP:
 		val = tcp_time_stamp + tp->tsoffset;
 		break;