Merge branch 'mptcp-mptcp-support-for-tcp_fastopen_connect'

Mat Martineau says:

====================
mptcp: MPTCP support for TCP_FASTOPEN_CONNECT

RFC 8684 appendix B describes how to use TCP Fast Open with MPTCP. This
series allows TFO use with MPTCP using the TCP_FASTOPEN_CONNECT socket
option. The scope here is limited to the initiator of the connection -
support for MSG_FASTOPEN and the listener side of the connection will be
in a separate series. The preexisting TCP fastopen code does most of the
work, so these changes mostly involve plumbing MPTCP through to those
TCP functions.

Patch 1 changes the MPTCP socket option code to pass the
TCP_FASTOPEN_CONNECT option through to the initial unconnected subflow.

Patch 2 exports the existing tcp_sendmsg_fastopen() function from tcp.c

Patch 3 adds the call to tcp_sendmsg_fastopen() from the MPTCP send
function.

Patch 4 modifies mptcp_poll() to handle the deferred TFO connection.
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

include/net/tcp.h

@@ -327,6 +327,8 @@ void tcp_remove_empty_skb(struct sock *sk);
 int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw);
 int tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
 int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size);
+int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
+			 size_t size, struct ubuf_info *uarg);
 int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size,
 		 int flags);
 int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset,

net/ipv4/tcp.c

@@ -1162,9 +1162,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp)
 	}
 }
 
-static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
-				int *copied, size_t size,
-				struct ubuf_info *uarg)
+int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied,
+			 size_t size, struct ubuf_info *uarg)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct inet_sock *inet = inet_sk(sk);

net/mptcp/protocol.c

@@ -1677,6 +1677,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
 	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct page_frag *pfrag;
+	struct socket *ssock;
 	size_t copied = 0;
 	int ret = 0;
 	long timeo;
@@ -1690,6 +1691,27 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	lock_sock(sk);
 
+	ssock = __mptcp_nmpc_socket(msk);
+	if (unlikely(ssock && inet_sk(ssock->sk)->defer_connect)) {
+		struct sock *ssk = ssock->sk;
+		int copied_syn = 0;
+
+		lock_sock(ssk);
+
+		ret = tcp_sendmsg_fastopen(ssk, msg, &copied_syn, len, NULL);
+		copied += copied_syn;
+		if (ret == -EINPROGRESS && copied_syn > 0) {
+			/* reflect the new state on the MPTCP socket */
+			inet_sk_state_store(sk, inet_sk_state_load(ssk));
+			release_sock(ssk);
+			goto out;
+		} else if (ret) {
+			release_sock(ssk);
+			goto out;
+		}
+		release_sock(ssk);
+	}
+
 	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
 
 	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) {
@@ -3526,6 +3548,7 @@ static int mptcp_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 
 do_connect:
 	err = ssock->ops->connect(ssock, uaddr, addr_len, flags);
+	inet_sk(sock->sk)->defer_connect = inet_sk(ssock->sk)->defer_connect;
 	sock->state = ssock->state;
 
 	/* on successful connect, the msk state will be moved to established by
@@ -3676,6 +3699,9 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
 	if (state != TCP_SYN_SENT && state != TCP_SYN_RECV) {
 		mask |= mptcp_check_readable(msk);
 		mask |= mptcp_check_writeable(msk);
+	} else if (state == TCP_SYN_SENT && inet_sk(sk)->defer_connect) {
+		/* cf tcp_poll() note about TFO */
+		mask |= EPOLLOUT | EPOLLWRNORM;
 	}
 	if (sk->sk_shutdown == SHUTDOWN_MASK || state == TCP_CLOSE)
 		mask |= EPOLLHUP;

net/mptcp/sockopt.c

@@ -559,6 +559,7 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		case TCP_NOTSENT_LOWAT:
 		case TCP_TX_DELAY:
 		case TCP_INQ:
+		case TCP_FASTOPEN_CONNECT:
 			return true;
 		}
 
@@ -567,7 +568,7 @@ static bool mptcp_supported_sockopt(int level, int optname)
 		/* TCP_REPAIR, TCP_REPAIR_QUEUE, TCP_QUEUE_SEQ, TCP_REPAIR_OPTIONS,
 		 * TCP_REPAIR_WINDOW are not supported, better avoid this mess
 		 */
-		/* TCP_FASTOPEN_KEY, TCP_FASTOPEN TCP_FASTOPEN_CONNECT, TCP_FASTOPEN_NO_COOKIE,
+		/* TCP_FASTOPEN_KEY, TCP_FASTOPEN, TCP_FASTOPEN_NO_COOKIE,
 		 * are not supported fastopen is currently unsupported
 		 */
 	}
@@ -768,6 +769,19 @@ static int mptcp_setsockopt_sol_tcp_defer(struct mptcp_sock *msk, sockptr_t optv
 	return tcp_setsockopt(listener->sk, SOL_TCP, TCP_DEFER_ACCEPT, optval, optlen);
 }
 
+static int mptcp_setsockopt_sol_tcp_fastopen_connect(struct mptcp_sock *msk, sockptr_t optval,
+						     unsigned int optlen)
+{
+	struct socket *sock;
+
+	/* Limit to first subflow */
+	sock = __mptcp_nmpc_socket(msk);
+	if (!sock)
+		return -EINVAL;
+
+	return tcp_setsockopt(sock->sk, SOL_TCP, TCP_FASTOPEN_CONNECT, optval, optlen);
+}
+
 static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 				    sockptr_t optval, unsigned int optlen)
 {
@@ -796,6 +810,8 @@ static int mptcp_setsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 		return mptcp_setsockopt_sol_tcp_nodelay(msk, optval, optlen);
 	case TCP_DEFER_ACCEPT:
 		return mptcp_setsockopt_sol_tcp_defer(msk, optval, optlen);
+	case TCP_FASTOPEN_CONNECT:
+		return mptcp_setsockopt_sol_tcp_fastopen_connect(msk, optval, optlen);
 	}
 
 	return -EOPNOTSUPP;
@@ -1157,6 +1173,7 @@ static int mptcp_getsockopt_sol_tcp(struct mptcp_sock *msk, int optname,
 	case TCP_INFO:
 	case TCP_CC_INFO:
 	case TCP_DEFER_ACCEPT:
+	case TCP_FASTOPEN_CONNECT:
 		return mptcp_getsockopt_first_sf_only(msk, SOL_TCP, optname,
 						      optval, optlen);
 	case TCP_INQ: