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>

7 files changed, 92 insertions, 12 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e1e021594cff..03964e088180 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -468,6 +468,17 @@ tcp_syncookies - BOOLEAN
         SYN flood warnings in logs not being really flooded, your server
         is seriously misconfigured.
 
+tcp_fastopen - INTEGER
+        Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data
+        in the opening SYN packet. To use this feature, the client application
+        must not use connect(). Instead, it should use sendmsg() or sendto()
+        with MSG_FASTOPEN flag which performs a TCP handshake automatically.
+
+        The values (bitmap) are:
+        1: Enables sending data in the opening SYN on the client
+
+        Default: 0
+
 tcp_syn_retries - INTEGER
         Number of times initial SYNs for an active TCP connection attempt
         will be retransmitted. Should not be higher than 255. Default value
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 25d6322fb635..ba7b2e817cfa 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -268,6 +268,7 @@ struct ucred {
 #define MSG_SENDPAGE_NOTLAST 0x20000 /* sendpage() internal : not the last page */
 #define MSG_EOF         MSG_FIN
 
+#define MSG_FASTOPEN    0x20000000      /* Send data in TCP SYN */
 #define MSG_CMSG_CLOEXEC 0x40000000     /* Set close_on_exit for file
                                            descriptor received through
                                            SCM_RIGHTS */
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 22fac9892b16..234008782c8c 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -14,9 +14,11 @@ struct sockaddr;
 struct socket;
 
 extern int inet_release(struct socket *sock);
-extern int inet_stream_connect(struct socket *sock, struct sockaddr * uaddr,
+extern int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
                                int addr_len, int flags);
-extern int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
+extern int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+                                 int addr_len, int flags);
+extern int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
                               int addr_len, int flags);
 extern int inet_accept(struct socket *sock, struct socket *newsock, int flags);
 extern int inet_sendmsg(struct kiocb *iocb, struct socket *sock,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 867557b4244a..c0258100d70c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -212,6 +212,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
 /* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */
 #define TCP_INIT_CWND           10
 
+/* Bit Flags for sysctl_tcp_fastopen */
+#define TFO_CLIENT_ENABLE       1
+
 extern struct inet_timewait_death_row tcp_death_row;
 
 /* sysctl variables for tcp */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index edc414625be2..fe4582ca969a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -585,8 +585,8 @@ static long inet_wait_for_connect(struct sock *sk, long timeo, int writebias)
  *      Connect to a remote host. There is regrettably still a little
  *      TCP 'magic' in here.
  */
-int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
-                        int addr_len, int flags)
+int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+                          int addr_len, int flags)
 {
         struct sock *sk = sock->sk;
         int err;
@@ -595,8 +595,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
         if (addr_len < sizeof(uaddr->sa_family))
                 return -EINVAL;
 
-        lock_sock(sk);
-
         if (uaddr->sa_family == AF_UNSPEC) {
                 err = sk->sk_prot->disconnect(sk, flags);
                 sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
@@ -663,7 +661,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
         sock->state = SS_CONNECTED;
         err = 0;
 out:
-        release_sock(sk);
         return err;
 
 sock_error:
@@ -673,6 +670,18 @@ sock_error:
                 sock->state = SS_DISCONNECTING;
         goto out;
 }
+EXPORT_SYMBOL(__inet_stream_connect);
+
+int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+                        int addr_len, int flags)
+{
+        int err;
+
+        lock_sock(sock->sk);
+        err = __inet_stream_connect(sock, uaddr, addr_len, flags);
+        release_sock(sock->sk);
+        return err;
+}
 EXPORT_SYMBOL(inet_stream_connect);
 
 /*
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);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 01aa77a97020..1d8b75a58981 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1952,6 +1952,9 @@ void tcp_v4_destroy_sock(struct sock *sk)
                 tp->cookie_values = NULL;
         }
 
+        /* If socket is aborted during connect operation */
+        tcp_free_fastopen_req(tp);
+
         sk_sockets_allocated_dec(sk);
         sock_release_memcg(sk);
 }