net-tcp: Fast Open client - sendmsg(MSG_FASTOPEN)

sendmsg() (or sendto()) with MSG_FASTOPEN is a combo of connect(2)
and write(2). The application should replace connect() with it to
send data in the opening SYN packet.

For blocking socket, sendmsg() blocks until all the data are buffered
locally and the handshake is completed like connect() call. It
returns similar errno like connect() if the TCP handshake fails.

For non-blocking socket, it returns the number of bytes queued (and
transmitted in the SYN-data packet) if cookie is available. If cookie
is not available, it transmits a data-less SYN packet with Fast Open
cookie request option and returns -EINPROGRESS like connect().

Using MSG_FASTOPEN on connecting or connected socket will result in
simlar errno like repeating connect() calls. Therefore the application
should only use this flag on new sockets.

The buffer size of sendmsg() is independent of the MSS of the connection.

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

1 files changed, 56 insertions, 5 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4252cd8f39fd..581ecf02c6b5 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -270,6 +270,7 @@
 #include <linux/slab.h>
 
 #include <net/icmp.h>
+#include <net/inet_common.h>
 #include <net/tcp.h>
 #include <net/xfrm.h>
 #include <net/ip.h>
@@ -982,26 +983,67 @@ static inline int select_size(const struct sock *sk, bool sg)
 	return tmp;
 }
 
+void tcp_free_fastopen_req(struct tcp_sock *tp)
+{
+	if (tp->fastopen_req != NULL) {
+		kfree(tp->fastopen_req);
+		tp->fastopen_req = NULL;
+	}
+}
+
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	int err, flags;
+
+	if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
+		return -EOPNOTSUPP;
+	if (tp->fastopen_req != NULL)
+		return -EALREADY; /* Another Fast Open is in progress */
+
+	tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
+				   sk->sk_allocation);
+	if (unlikely(tp->fastopen_req == NULL))
+		return -ENOBUFS;
+	tp->fastopen_req->data = msg;
+
+	flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
+	err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
+				    msg->msg_namelen, flags);
+	*size = tp->fastopen_req->copied;
+	tcp_free_fastopen_req(tp);
+	return err;
+}
+
 int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		size_t size)
 {
 	struct iovec *iov;
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int iovlen, flags, err, copied;
-	int mss_now = 0, size_goal;
+	int iovlen, flags, err, copied = 0;
+	int mss_now = 0, size_goal, copied_syn = 0, offset = 0;
 	bool sg;
 	long timeo;
 
 	lock_sock(sk);
 
 	flags = msg->msg_flags;
+	if (flags & MSG_FASTOPEN) {
+		err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+		if (err == -EINPROGRESS && copied_syn > 0)
+			goto out;
+		else if (err)
+			goto out_err;
+		offset = copied_syn;
+	}
+
 	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
 
 	/* Wait for a connection to finish. */
 	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
 		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
-			goto out_err;
+			goto do_error;
 
 	if (unlikely(tp->repair)) {
 		if (tp->repair_queue == TCP_RECV_QUEUE) {
@@ -1037,6 +1079,15 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		unsigned char __user *from = iov->iov_base;
 
 		iov++;
+		if (unlikely(offset > 0)) {  /* Skip bytes copied in SYN */
+			if (offset >= seglen) {
+				offset -= seglen;
+				continue;
+			}
+			seglen -= offset;
+			from += offset;
+			offset = 0;
+		}
 
 		while (seglen > 0) {
 			int copy = 0;
@@ -1199,7 +1250,7 @@ out:
 	if (copied && likely(!tp->repair))
 		tcp_push(sk, flags, mss_now, tp->nonagle);
 	release_sock(sk);
-	return copied;
+	return copied + copied_syn;
 
 do_fault:
 	if (!skb->len) {
@@ -1212,7 +1263,7 @@ do_fault:
 	}
 
 do_error:
-	if (copied)
+	if (copied + copied_syn)
 		goto out;
 out_err:
 	err = sk_stream_error(sk, flags, err);