[RFC PATCH v4 00/17] virtio/vsock: introduce SOCK_SEQPACKET support

@@ -604,8 +604,8 @@ static void vsock_pending_work(struct work_struct *work)
 
 /**** SOCKET OPERATIONS ****/
 
-static int __vsock_bind_stream(struct vsock_sock *vsk,
-			       struct sockaddr_vm *addr)
+static int __vsock_bind_connectible(struct vsock_sock *vsk,
+				    struct sockaddr_vm *addr)
 {
 	static u32 port;
 	struct sockaddr_vm new_addr;

@@ -685,7 +685,7 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 	switch (sk->sk_socket->type) {
 	case SOCK_STREAM:
 		spin_lock_bh(&vsock_table_lock);
-		retval = __vsock_bind_stream(vsk, addr);
+		retval = __vsock_bind_connectible(vsk, addr);
 		spin_unlock_bh(&vsock_table_lock);
 		break;
 

@@ -767,6 +767,11 @@ static struct sock *__vsock_create(struct net *net,
 	return sk;
 }
 
+static bool sock_type_connectible(u16 type)
+{
+	return type == SOCK_STREAM;
+}
+
 static void __vsock_release(struct sock *sk, int level)
 {
 	if (sk) {

@@ -785,7 +790,7 @@ static void __vsock_release(struct sock *sk, int level)
 
 		if (vsk->transport)
 			vsk->transport->release(vsk);
-		else if (sk->sk_type == SOCK_STREAM)
+		else if (sock_type_connectible(sk->sk_type))
 			vsock_remove_sock(vsk);
 
 		sock_orphan(sk);

@@ -945,7 +950,7 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	sk = sock->sk;
 	if (sock->state == SS_UNCONNECTED) {
 		err = -ENOTCONN;
-		if (sk->sk_type == SOCK_STREAM)
+		if (sock_type_connectible(sk->sk_type))
 			return err;
 	} else {
 		sock->state = SS_DISCONNECTING;

@@ -960,7 +965,7 @@ static int vsock_shutdown(struct socket *sock, int mode)
 		sk->sk_state_change(sk);
 		release_sock(sk);
 
-		if (sk->sk_type == SOCK_STREAM) {
+		if (sock_type_connectible(sk->sk_type)) {
 			sock_reset_flag(sk, SOCK_DONE);
 			vsock_send_shutdown(sk, mode);
 		}

@@ -1013,7 +1018,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock,
 		if (!(sk->sk_shutdown & SEND_SHUTDOWN))
 			mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND;
 
-	} else if (sock->type == SOCK_STREAM) {
+	} else if (sock_type_connectible(sk->sk_type)) {
 		const struct vsock_transport *transport;
 
 		lock_sock(sk);

@@ -1263,8 +1268,8 @@ static void vsock_connect_timeout(struct work_struct *work)
 	sock_put(sk);
 }
 
-static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
-				int addr_len, int flags)
+static int vsock_connect(struct socket *sock, struct sockaddr *addr,
+			 int addr_len, int flags)
 {
 	int err;
 	struct sock *sk;

@@ -1414,7 +1419,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 
 	lock_sock(listener);
 
-	if (sock->type != SOCK_STREAM) {
+	if (!sock_type_connectible(sock->type)) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}

@@ -1491,7 +1496,7 @@ static int vsock_listen(struct socket *sock, int backlog)
 
 	lock_sock(sk);
 
-	if (sock->type != SOCK_STREAM) {
+	if (!sock_type_connectible(sk->sk_type)) {
 		err = -EOPNOTSUPP;
 		goto out;
 	}

@@ -1535,11 +1540,11 @@ static void vsock_update_buffer_size(struct vsock_sock *vsk,
 	vsk->buffer_size = val;
 }
 
-static int vsock_stream_setsockopt(struct socket *sock,
-				   int level,
-				   int optname,
-				   sockptr_t optval,
-				   unsigned int optlen)
+static int vsock_connectible_setsockopt(struct socket *sock,
+					int level,
+					int optname,
+					sockptr_t optval,
+					unsigned int optlen)
 {
 	int err;
 	struct sock *sk;

@@ -1617,10 +1622,10 @@ static int vsock_stream_setsockopt(struct socket *sock,
 	return err;
 }
 
-static int vsock_stream_getsockopt(struct socket *sock,
-				   int level, int optname,
-				   char __user *optval,
-				   int __user *optlen)
+static int vsock_connectible_getsockopt(struct socket *sock,
+					int level, int optname,
+					char __user *optval,
+					int __user *optlen)
 {
 	int err;
 	int len;

@@ -1688,8 +1693,8 @@ static int vsock_stream_getsockopt(struct socket *sock,
 	return 0;
 }
 
-static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
-				size_t len)
+static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
+				     size_t len)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;

@@ -1828,10 +1833,9 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	return err;
 }
 
-
 static int
-vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
-		     int flags)
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
 {
 	struct sock *sk;
 	struct vsock_sock *vsk;

@@ -2007,7 +2011,7 @@ static const struct proto_ops vsock_stream_ops = {
 	.owner = THIS_MODULE,
 	.release = vsock_release,
 	.bind = vsock_bind,
-	.connect = vsock_stream_connect,
+	.connect = vsock_connect,
 	.socketpair = sock_no_socketpair,
 	.accept = vsock_accept,
 	.getname = vsock_getname,

@@ -2015,10 +2019,10 @@ static const struct proto_ops vsock_stream_ops = {
 	.ioctl = sock_no_ioctl,
 	.listen = vsock_listen,
 	.shutdown = vsock_shutdown,
-	.setsockopt = vsock_stream_setsockopt,
-	.getsockopt = vsock_stream_getsockopt,
-	.sendmsg = vsock_stream_sendmsg,
-	.recvmsg = vsock_stream_recvmsg,
+	.setsockopt = vsock_connectible_setsockopt,
+	.getsockopt = vsock_connectible_getsockopt,
+	.sendmsg = vsock_connectible_sendmsg,
+	.recvmsg = vsock_connectible_recvmsg,
 	.mmap = sock_no_mmap,
 	.sendpage = sock_no_sendpage,
 };

@@ -1833,6 +1833,71 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 	return err;
 }
 
+static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait,
+			   long timeout,
+			   struct vsock_transport_recv_notify_data *recv_data,
+			   size_t target)
+{
+	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	s64 data;
+	int err;
+
+	vsk = vsock_sk(sk);
+	err = 0;
+	transport = vsk->transport;
+	prepare_to_wait(sk_sleep(sk), wait, TASK_INTERRUPTIBLE);
+
+	while ((data = vsock_stream_has_data(vsk)) == 0) {
+		if (sk->sk_err != 0 ||
+		    (sk->sk_shutdown & RCV_SHUTDOWN) ||
+		    (vsk->peer_shutdown & SEND_SHUTDOWN)) {
+			goto out;
+		}
+
+		/* Don't wait for non-blocking sockets. */
+		if (timeout == 0) {
+			err = -EAGAIN;
+			goto out;
+		}
+
+		if (recv_data) {
+			err = transport->notify_recv_pre_block(vsk, target, recv_data);
+			if (err < 0)
+				goto out;
+		}
+
+		release_sock(sk);
+		timeout = schedule_timeout(timeout);
+		lock_sock(sk);
+
+		if (signal_pending(current)) {
+			err = sock_intr_errno(timeout);
+			goto out;
+		} else if (timeout == 0) {
+			err = -EAGAIN;
+			goto out;
+		}
+	}
+
+	finish_wait(sk_sleep(sk), wait);
+
+	/* Invalid queue pair content. XXX This should
+	 * be changed to a connection reset in a later
+	 * change.
+	 */
+	if (data < 0)
+		return -ENOMEM;
+
+	/* Have some data, return. */
+	if (data)
+		return data;
+
+out:
+	finish_wait(sk_sleep(sk), wait);
+	return err;
+}
+
 static int
 vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			  int flags)

@@ -1912,85 +1977,34 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 
 	while (1) {
-		s64 ready;
+		ssize_t read;
 
-		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
-		ready = vsock_stream_has_data(vsk);
-
-		if (ready == 0) {
-			if (sk->sk_err != 0 ||
-			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
-			    (vsk->peer_shutdown & SEND_SHUTDOWN)) {
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-			/* Don't wait for non-blocking sockets. */
-			if (timeout == 0) {
-				err = -EAGAIN;
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-
-			err = transport->notify_recv_pre_block(
-					vsk, target, &recv_data);
-			if (err < 0) {
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-			release_sock(sk);
-			timeout = schedule_timeout(timeout);
-			lock_sock(sk);
-
-			if (signal_pending(current)) {
-				err = sock_intr_errno(timeout);
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			} else if (timeout == 0) {
-				err = -EAGAIN;
-				finish_wait(sk_sleep(sk), &wait);
-				break;
-			}
-		} else {
-			ssize_t read;
+		err = vsock_wait_data(sk, &wait, timeout, &recv_data, target);
+		if (err <= 0)
+			break;
 
-			finish_wait(sk_sleep(sk), &wait);
-
-			if (ready < 0) {
-				/* Invalid queue pair content. XXX This should
-				* be changed to a connection reset in a later
-				* change.
-				*/
-
-				err = -ENOMEM;
-				goto out;
-			}
-
-			err = transport->notify_recv_pre_dequeue(
-					vsk, target, &recv_data);
-			if (err < 0)
-				break;
+		err = transport->notify_recv_pre_dequeue(vsk, target,
+							 &recv_data);
+		if (err < 0)
+			break;
 
-			read = transport->stream_dequeue(
-					vsk, msg,
-					len - copied, flags);
-			if (read < 0) {
-				err = -ENOMEM;
-				break;
-			}
+		read = transport->stream_dequeue(vsk, msg, len - copied, flags);
+		if (read < 0) {
+			err = -ENOMEM;
+			break;
+		}
 
-			copied += read;
+		copied += read;
 
-			err = transport->notify_recv_post_dequeue(
-					vsk, target, read,
-					!(flags & MSG_PEEK), &recv_data);
-			if (err < 0)
-				goto out;
+		err = transport->notify_recv_post_dequeue(vsk, target, read,
+						!(flags & MSG_PEEK), &recv_data);
+		if (err < 0)
+			goto out;
 
-			if (read >= target || flags & MSG_PEEK)
-				break;
+		if (read >= target || flags & MSG_PEEK)
+			break;
 
-			target -= read;
-		}
+		target -= read;
 	}
 
 	if (sk->sk_err)

@@ -1898,65 +1898,22 @@ static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait,
 	return err;
 }
 
-static int
-vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
-			  int flags)
+static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg,
+				  size_t len, int flags)
 {
-	struct sock *sk;
-	struct vsock_sock *vsk;
+	struct vsock_transport_recv_notify_data recv_data;
 	const struct vsock_transport *transport;
-	int err;
-	size_t target;
+	struct vsock_sock *vsk;
 	ssize_t copied;
+	size_t target;
 	long timeout;
-	struct vsock_transport_recv_notify_data recv_data;
+	int err;
 
 	DEFINE_WAIT(wait);
 
-	sk = sock->sk;
 	vsk = vsock_sk(sk);
-	err = 0;
-
-	lock_sock(sk);
-
 	transport = vsk->transport;
 
-	if (!transport || sk->sk_state != TCP_ESTABLISHED) {
-		/* Recvmsg is supposed to return 0 if a peer performs an
-		 * orderly shutdown. Differentiate between that case and when a
-		 * peer has not connected or a local shutdown occured with the
-		 * SOCK_DONE flag.
-		 */
-		if (sock_flag(sk, SOCK_DONE))
-			err = 0;
-		else
-			err = -ENOTCONN;
-
-		goto out;
-	}
-
-	if (flags & MSG_OOB) {
-		err = -EOPNOTSUPP;
-		goto out;
-	}
-
-	/* We don't check peer_shutdown flag here since peer may actually shut
-	 * down, but there can be data in the queue that a local socket can
-	 * receive.
-	 */
-	if (sk->sk_shutdown & RCV_SHUTDOWN) {
-		err = 0;
-		goto out;
-	}
-
-	/* It is valid on Linux to pass in a zero-length receive buffer.  This
-	 * is not an error.  We may as well bail out now.
-	 */
-	if (!len) {
-		err = 0;
-		goto out;
-	}
-
 	/* We must not copy less than target bytes into the user's buffer
 	 * before returning successfully, so we wait for the consume queue to
 	 * have that much data to consume before dequeueing.  Note that this

@@ -2020,6 +1977,68 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	return err;
 }
 
+static int
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
+{
+	struct sock *sk;
+	struct vsock_sock *vsk;
+	const struct vsock_transport *transport;
+	int err;
+
+	DEFINE_WAIT(wait);
+
+	sk = sock->sk;
+	vsk = vsock_sk(sk);
+	err = 0;
+
+	lock_sock(sk);
+
+	transport = vsk->transport;
+
+	if (!transport || sk->sk_state != TCP_ESTABLISHED) {
+		/* Recvmsg is supposed to return 0 if a peer performs an
+		 * orderly shutdown. Differentiate between that case and when a
+		 * peer has not connected or a local shutdown occurred with the
+		 * SOCK_DONE flag.
+		 */
+		if (sock_flag(sk, SOCK_DONE))
+			err = 0;
+		else
+			err = -ENOTCONN;
+
+		goto out;
+	}
+
+	if (flags & MSG_OOB) {
+		err = -EOPNOTSUPP;
+		goto out;
+	}
+
+	/* We don't check peer_shutdown flag here since peer may actually shut
+	 * down, but there can be data in the queue that a local socket can
+	 * receive.
+	 */
+	if (sk->sk_shutdown & RCV_SHUTDOWN) {
+		err = 0;
+		goto out;
+	}
+
+	/* It is valid on Linux to pass in a zero-length receive buffer.  This
+	 * is not an error.  We may as well bail out now.
+	 */
+	if (!len) {
+		err = 0;
+		goto out;
+	}
+
+	err = __vsock_stream_recvmsg(sk, msg, len, flags);
+
+out:
+	release_sock(sk);
+	return err;
+}
+
 static const struct proto_ops vsock_stream_ops = {
 	.family = PF_VSOCK,
 	.owner = THIS_MODULE,

@@ -135,6 +135,11 @@ struct vsock_transport {
 	bool (*stream_is_active)(struct vsock_sock *);
 	bool (*stream_allow)(u32 cid, u32 port);
 
+	/* SEQ_PACKET. */
+	size_t (*seqpacket_seq_get_len)(struct vsock_sock *);
+	int (*seqpacket_dequeue)(struct vsock_sock *, struct msghdr *,
+				     int flags, bool *msg_ready);
+
 	/* Notification. */
 	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
 	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);

@@ -1977,6 +1977,97 @@ static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg,
 	return err;
 }
 
+static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
+				     size_t len, int flags)
+{
+	const struct vsock_transport *transport;
+	const struct iovec *orig_iov;
+	unsigned long orig_nr_segs;
+	bool msg_ready;
+	struct vsock_sock *vsk;
+	size_t record_len;
+	long timeout;
+	int err = 0;
+	DEFINE_WAIT(wait);
+
+	vsk = vsock_sk(sk);
+	transport = vsk->transport;
+
+	timeout = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+	orig_nr_segs = msg->msg_iter.nr_segs;
+	orig_iov = msg->msg_iter.iov;
+	msg_ready = false;
+	record_len = 0;
+
+	while (1) {
+		err = vsock_wait_data(sk, &wait, timeout, NULL, 0);
+
+		if (err <= 0) {
+			/* In case of any loop break(timeout, signal
+			 * interrupt or shutdown), we report user that
+			 * nothing was copied.
+			 */
+			err = 0;
+			break;
+		}
+
+		if (record_len == 0) {
+			record_len =
+				transport->seqpacket_seq_get_len(vsk);
+
+			if (record_len == 0)
+				continue;
+		}
+
+		err = transport->seqpacket_dequeue(vsk, msg,
+					flags, &msg_ready);
+		if (err < 0) {
+			if (err == -EAGAIN) {
+				iov_iter_init(&msg->msg_iter, READ,
+					      orig_iov, orig_nr_segs,
+					      len);
+				/* Clear 'MSG_EOR' here, because dequeue
+				 * callback above set it again if it was
+				 * set by sender. This 'MSG_EOR' is from
+				 * dropped record.
+				 */
+				msg->msg_flags &= ~MSG_EOR;
+				record_len = 0;
+				continue;
+			}
+
+			err = -ENOMEM;
+			break;
+		}
+
+		if (msg_ready)
+			break;
+	}
+
+	if (sk->sk_err)
+		err = -sk->sk_err;
+	else if (sk->sk_shutdown & RCV_SHUTDOWN)
+		err = 0;
+
+	if (msg_ready) {
+		/* User sets MSG_TRUNC, so return real length of
+		 * packet.
+		 */
+		if (flags & MSG_TRUNC)
+			err = record_len;
+		else
+			err = len - msg->msg_iter.count;
+
+		/* Always set MSG_TRUNC if real length of packet is
+		 * bigger than user's buffer.
+		 */
+		if (record_len > len)
+			msg->msg_flags |= MSG_TRUNC;
+	}
+
+	return err;
+}
+
 static int
 vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 			  int flags)

@@ -2032,7 +2123,10 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		goto out;
 	}
 
-	err = __vsock_stream_recvmsg(sk, msg, len, flags);
+	if (sk->sk_type == SOCK_STREAM)
+		err = __vsock_stream_recvmsg(sk, msg, len, flags);
+	else
+		err = __vsock_seqpacket_recvmsg(sk, msg, len, flags);
 
 out:
 	release_sock(sk);

@@ -205,6 +205,8 @@ void vsock_remove_sock(struct vsock_sock *vsk);
 void vsock_for_each_connected_socket(void (*fn)(struct sock *sk));
 int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk);
 bool vsock_find_cid(unsigned int cid);
+int vsock_wait_space(struct sock *sk, size_t space, int flags,
+		     struct vsock_transport_send_notify_data *send_data);
 
 /**** TAP ****/
 

@@ -1693,6 +1693,64 @@ static int vsock_connectible_getsockopt(struct socket *sock,
 	return 0;
 }
 
+int vsock_wait_space(struct sock *sk, size_t space, int flags,
+		     struct vsock_transport_send_notify_data *send_data)
+{
+	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	long timeout;
+	int err;
+
+	DEFINE_WAIT_FUNC(wait, woken_wake_function);
+
+	vsk = vsock_sk(sk);
+	transport = vsk->transport;
+	timeout = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
+	err = 0;
+
+	add_wait_queue(sk_sleep(sk), &wait);
+
+	while (vsock_stream_has_space(vsk) < space &&
+	       sk->sk_err == 0 &&
+	       !(sk->sk_shutdown & SEND_SHUTDOWN) &&
+	       !(vsk->peer_shutdown & RCV_SHUTDOWN)) {
+		/* Don't wait for non-blocking sockets. */
+		if (timeout == 0) {
+			err = -EAGAIN;
+			goto out_err;
+		}
+
+		if (send_data) {
+			err = transport->notify_send_pre_block(vsk, send_data);
+			if (err < 0)
+				goto out_err;
+		}
+
+		release_sock(sk);
+		timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
+		lock_sock(sk);
+		if (signal_pending(current)) {
+			err = sock_intr_errno(timeout);
+			goto out_err;
+		} else if (timeout == 0) {
+			err = -EAGAIN;
+			goto out_err;
+		}
+	}
+
+	if (sk->sk_err) {
+		err = -sk->sk_err;
+	} else if ((sk->sk_shutdown & SEND_SHUTDOWN) ||
+		   (vsk->peer_shutdown & RCV_SHUTDOWN)) {
+		err = -EPIPE;
+	}
+
+out_err:
+	remove_wait_queue(sk_sleep(sk), &wait);
+	return err;
+}
+EXPORT_SYMBOL_GPL(vsock_wait_space);
+
 static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 				     size_t len)
 {

@@ -1751,39 +1809,8 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 	while (total_written < len) {
 		ssize_t written;
 
-		add_wait_queue(sk_sleep(sk), &wait);
-		while (vsock_stream_has_space(vsk) == 0 &&
-		       sk->sk_err == 0 &&
-		       !(sk->sk_shutdown & SEND_SHUTDOWN) &&
-		       !(vsk->peer_shutdown & RCV_SHUTDOWN)) {
-
-			/* Don't wait for non-blocking sockets. */
-			if (timeout == 0) {
-				err = -EAGAIN;
-				remove_wait_queue(sk_sleep(sk), &wait);
-				goto out_err;
-			}
-
-			err = transport->notify_send_pre_block(vsk, &send_data);
-			if (err < 0) {
-				remove_wait_queue(sk_sleep(sk), &wait);
-				goto out_err;
-			}
-
-			release_sock(sk);
-			timeout = wait_woken(&wait, TASK_INTERRUPTIBLE, timeout);
-			lock_sock(sk);
-			if (signal_pending(current)) {
-				err = sock_intr_errno(timeout);
-				remove_wait_queue(sk_sleep(sk), &wait);
-				goto out_err;
-			} else if (timeout == 0) {
-				err = -EAGAIN;
-				remove_wait_queue(sk_sleep(sk), &wait);
-				goto out_err;
-			}
-		}
-		remove_wait_queue(sk_sleep(sk), &wait);
+		if (vsock_wait_space(sk, 1, msg->msg_flags, &send_data))
+			goto out_err;
 
 		/* These checks occur both as part of and after the loop
 		 * conditional since we need to check before and after

@@ -136,6 +136,8 @@ struct vsock_transport {
 	bool (*stream_allow)(u32 cid, u32 port);
 
 	/* SEQ_PACKET. */
+	int (*seqpacket_seq_send_len)(struct vsock_sock *, size_t len, int flags);
+	int (*seqpacket_seq_send_eor)(struct vsock_sock *, int flags);
 	size_t (*seqpacket_seq_get_len)(struct vsock_sock *);
 	int (*seqpacket_dequeue)(struct vsock_sock *, struct msghdr *,
 				     int flags, bool *msg_ready);

@@ -1806,6 +1806,12 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (err < 0)
 		goto out;
 
+	if (sk->sk_type == SOCK_SEQPACKET) {
+		err = transport->seqpacket_seq_send_len(vsk, len, msg->msg_flags);
+		if (err < 0)
+			goto out;
+	}
+
 	while (total_written < len) {
 		ssize_t written;
 

@@ -1852,9 +1858,21 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	}
 
+	if (sk->sk_type == SOCK_SEQPACKET) {
+		err = transport->seqpacket_seq_send_eor(vsk, msg->msg_flags);
+		if (err < 0)
+			goto out;
+	}
+
 out_err:
-	if (total_written > 0)
-		err = total_written;
+	if (total_written > 0) {
+		/* Return number of written bytes only if:
+		 * 1) SOCK_STREAM socket.
+		 * 2) SOCK_SEQPACKET socket when whole buffer is sent.
+		 */
+		if (sk->sk_type == SOCK_STREAM || total_written == len)
+			err = total_written;
+	}
 out:
 	release_sock(sk);
 	return err;

@@ -452,6 +452,7 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 		new_transport = transport_dgram;
 		break;
 	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
 		if (vsock_use_local_transport(remote_cid))
 			new_transport = transport_local;
 		else if (remote_cid <= VMADDR_CID_HOST || !transport_h2g ||

@@ -459,6 +460,15 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 			new_transport = transport_g2h;
 		else
 			new_transport = transport_h2g;
+
+		if (sk->sk_type == SOCK_SEQPACKET) {
+			if (!new_transport ||
+			    !new_transport->seqpacket_seq_send_len ||
+			    !new_transport->seqpacket_seq_send_eor ||
+			    !new_transport->seqpacket_seq_get_len ||
+			    !new_transport->seqpacket_dequeue)
+				return -ESOCKTNOSUPPORT;
+		}
 		break;
 	default:
 		return -ESOCKTNOSUPPORT;

@@ -684,6 +694,7 @@ static int __vsock_bind(struct sock *sk, struct sockaddr_vm *addr)
 
 	switch (sk->sk_socket->type) {
 	case SOCK_STREAM:
+	case SOCK_SEQPACKET:
 		spin_lock_bh(&vsock_table_lock);
 		retval = __vsock_bind_connectible(vsk, addr);
 		spin_unlock_bh(&vsock_table_lock);

@@ -769,7 +780,7 @@ static struct sock *__vsock_create(struct net *net,
 
 static bool sock_type_connectible(u16 type)
 {
-	return type == SOCK_STREAM;
+	return (type == SOCK_STREAM) || (type == SOCK_SEQPACKET);
 }
 
 static void __vsock_release(struct sock *sk, int level)

@@ -2199,6 +2210,27 @@ static const struct proto_ops vsock_stream_ops = {
 	.sendpage = sock_no_sendpage,
 };
 
+static const struct proto_ops vsock_seqpacket_ops = {
+	.family = PF_VSOCK,
+	.owner = THIS_MODULE,
+	.release = vsock_release,
+	.bind = vsock_bind,
+	.connect = vsock_connect,
+	.socketpair = sock_no_socketpair,
+	.accept = vsock_accept,
+	.getname = vsock_getname,
+	.poll = vsock_poll,
+	.ioctl = sock_no_ioctl,
+	.listen = vsock_listen,
+	.shutdown = vsock_shutdown,
+	.setsockopt = vsock_connectible_setsockopt,
+	.getsockopt = vsock_connectible_getsockopt,
+	.sendmsg = vsock_connectible_sendmsg,
+	.recvmsg = vsock_connectible_recvmsg,
+	.mmap = sock_no_mmap,
+	.sendpage = sock_no_sendpage,
+};
+
 static int vsock_create(struct net *net, struct socket *sock,
 			int protocol, int kern)
 {

@@ -2219,6 +2251,9 @@ static int vsock_create(struct net *net, struct socket *sock,
 	case SOCK_STREAM:
 		sock->ops = &vsock_stream_ops;
 		break;
+	case SOCK_SEQPACKET:
+		sock->ops = &vsock_seqpacket_ops;
+		break;
 	default:
 		return -ESOCKTNOSUPPORT;
 	}

@@ -415,8 +415,8 @@ static void vsock_deassign_transport(struct vsock_sock *vsk)
 
 /* Assign a transport to a socket and call the .init transport callback.
  *
- * Note: for stream socket this must be called when vsk->remote_addr is set
- * (e.g. during the connect() or when a connection request on a listener
+ * Note: for connect oriented socket this must be called when vsk->remote_addr
+ * is set (e.g. during the connect() or when a connection request on a listener
  * socket is received).
  * The vsk->remote_addr is used to decide which transport to use:
  *  - remote CID == VMADDR_CID_LOCAL or g2h->local_cid or VMADDR_CID_HOST if

@@ -479,10 +479,10 @@ int vsock_assign_transport(struct vsock_sock *vsk, struct vsock_sock *psk)
 			return 0;
 
 		/* transport->release() must be called with sock lock acquired.
-		 * This path can only be taken during vsock_stream_connect(),
-		 * where we have already held the sock lock.
-		 * In the other cases, this function is called on a new socket
-		 * which is not assigned to any transport.
+		 * This path can only be taken during vsock_connect(), where we
+		 * have already held the sock lock. In the other cases, this
+		 * function is called on a new socket which is not assigned to
+		 * any transport.
 		 */
 		vsk->transport->release(vsk);
 		vsock_deassign_transport(vsk);

@@ -659,9 +659,10 @@ static int __vsock_bind_connectible(struct vsock_sock *vsk,
 
 	vsock_addr_init(&vsk->local_addr, new_addr.svm_cid, new_addr.svm_port);
 
-	/* Remove stream sockets from the unbound list and add them to the hash
-	 * table for easy lookup by its address.  The unbound list is simply an
-	 * extra entry at the end of the hash table, a trick used by AF_UNIX.
+	/* Remove connect oriented sockets from the unbound list and add them
+	 * to the hash table for easy lookup by its address.  The unbound list
+	 * is simply an extra entry at the end of the hash table, a trick used
+	 * by AF_UNIX.
 	 */
 	__vsock_remove_bound(vsk);
 	__vsock_insert_bound(vsock_bound_sockets(&vsk->local_addr), vsk);

@@ -952,10 +953,10 @@ static int vsock_shutdown(struct socket *sock, int mode)
 	if ((mode & ~SHUTDOWN_MASK) || !mode)
 		return -EINVAL;
 
-	/* If this is a STREAM socket and it is not connected then bail out
-	 * immediately.  If it is a DGRAM socket then we must first kick the
-	 * socket so that it wakes up from any sleeping calls, for example
-	 * recv(), and then afterwards return the error.
+	/* If this is a connect oriented socket and it is not connected then
+	 * bail out immediately.  If it is a DGRAM socket then we must first
+	 * kick the socket so that it wakes up from any sleeping calls, for
+	 * example recv(), and then afterwards return the error.
 	 */
 
 	sk = sock->sk;