[RFC PATCH v3 00/13] virtio/vsock: introduce SOCK_SEQPACKET support

@@ -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 +460,13 @@ 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->seqpacket_seq_send_len ||
+			    !new_transport->seqpacket_seq_get_len ||
+			    !new_transport->seqpacket_dequeue)
+				return -ENODEV;
+		}
 		break;
 	default:
 		return -ESOCKTNOSUPPORT;

@@ -684,6 +692,7 @@ 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);

@@ -1406,6 +1415,12 @@ static int vsock_stream_connect(struct socket *sock, struct sockaddr *addr,
 	return vsock_connect(sock, addr, addr_len, flags);
 }
 
+static int vsock_seqpacket_connect(struct socket *sock, struct sockaddr *addr,
+				   int addr_len, int flags)
+{
+	return vsock_connect(sock, addr, addr_len, flags);
+}
+
 static int vsock_accept(struct socket *sock, struct socket *newsock, int flags,
 			bool kern)
 {

@@ -1633,6 +1648,16 @@ static int vsock_stream_setsockopt(struct socket *sock,
 					    optlen);
 }
 
+static int vsock_seqpacket_setsockopt(struct socket *sock,
+				      int level,
+				      int optname,
+				      sockptr_t optval,
+				      unsigned int optlen)
+{
+	return vsock_connectible_setsockopt(sock, level, optname, optval,
+					    optlen);
+}
+
 static int vsock_connectible_getsockopt(struct socket *sock,
 					int level, int optname,
 					char __user *optval,

@@ -1713,6 +1738,15 @@ static int vsock_stream_getsockopt(struct socket *sock,
 					    optlen);
 }
 
+static int vsock_seqpacket_getsockopt(struct socket *sock,
+				      int level, int optname,
+				      char __user *optval,
+				      int __user *optlen)
+{
+	return vsock_connectible_getsockopt(sock, level, optname, optval,
+					    optlen);
+}
+
 static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 				     size_t len)
 {

@@ -1870,6 +1904,12 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	return vsock_connectible_sendmsg(sock, msg, len);
 }
 
+static int vsock_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg,
+				   size_t len)
+{
+	return vsock_connectible_sendmsg(sock, msg, len);
+}
+
 static int vsock_wait_data(struct sock *sk, struct wait_queue_entry *wait,
 			   long timeout,
 			   struct vsock_transport_recv_notify_data *recv_data,

@@ -2184,6 +2224,13 @@ vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	return vsock_connectible_recvmsg(sock, msg, len, flags);
 }
 
+static int
+vsock_seqpacket_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			int flags)
+{
+	return vsock_connectible_recvmsg(sock, msg, len, flags);
+}
+
 static const struct proto_ops vsock_stream_ops = {
 	.family = PF_VSOCK,
 	.owner = THIS_MODULE,

@@ -2205,6 +2252,27 @@ 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_seqpacket_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_seqpacket_setsockopt,
+	.getsockopt = vsock_seqpacket_getsockopt,
+	.sendmsg = vsock_seqpacket_sendmsg,
+	.recvmsg = vsock_seqpacket_recvmsg,
+	.mmap = sock_no_mmap,
+	.sendpage = sock_no_sendpage,
+};
+
 static int vsock_create(struct net *net, struct socket *sock,
 			int protocol, int kern)
 {

@@ -2225,6 +2293,9 @@ 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;
 	}

@@ -136,6 +136,7 @@ struct vsock_transport {
 	bool (*stream_allow)(u32 cid, u32 port);
 
 	/* SEQ_PACKET. */
+	bool (*seqpacket_seq_send_len)(struct vsock_sock *, size_t len);
 	size_t (*seqpacket_seq_get_len)(struct vsock_sock *);
 	ssize_t (*seqpacket_dequeue)(struct vsock_sock *, struct msghdr *,
 				     size_t len, int flags);

@@ -1767,6 +1767,12 @@ 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);
+		if (err < 0)
+			goto out;
+	}
+
 	while (total_written < len) {
 		ssize_t written;
 

@@ -1845,8 +1851,14 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 	}
 
 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;

@@ -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

@@ -477,10 +477,10 @@ 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);

@@ -657,9 +657,10 @@ 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);

@@ -950,10 +951,10 @@ 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;

@@ -1770,7 +1771,9 @@ static int vsock_connectible_sendmsg(struct socket *sock, struct msghdr *msg,
 
 	lock_sock(sk);
 
-	/* Callers should not provide a destination with stream sockets. */
+	/* Callers should not provide a destination with connect oriented
+	 * sockets.
+	 */
 	if (msg->msg_namelen) {
 		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EOPNOTSUPP;
 		goto out;

@@ -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 *);
+	ssize_t (*seqpacket_dequeue)(struct vsock_sock *, struct msghdr *,
+				     size_t len, int flags);
+
 	/* Notification. */
 	int (*notify_poll_in)(struct vsock_sock *, size_t, bool *);
 	int (*notify_poll_out)(struct vsock_sock *, size_t, bool *);

@@ -2006,7 +2006,107 @@ static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg,
 static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
 				     size_t len, int flags)
 {
-	return -1;
+	const struct vsock_transport *transport;
+	const struct iovec *orig_iov;
+	unsigned long orig_nr_segs;
+	ssize_t dequeued_total = 0;
+	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);
+	msg->msg_flags &= ~MSG_EOR;
+	orig_nr_segs = msg->msg_iter.nr_segs;
+	orig_iov = msg->msg_iter.iov;
+
+	while (1) {
+		ssize_t dequeued;
+		s64 ready;
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		ready = vsock_stream_has_data(vsk);
+
+		if (ready == 0) {
+			if (vsock_wait_data(sk, &wait, timeout, NULL, 0)) {
+				/* In case of any loop break(timeout, signal
+				 * interrupt or shutdown), we report user that
+				 * nothing was copied.
+				 */
+				dequeued_total = 0;
+				break;
+			}
+			continue;
+		}
+
+		finish_wait(sk_sleep(sk), &wait);
+
+		if (ready < 0) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		if (dequeued_total == 0) {
+			record_len =
+				transport->seqpacket_seq_get_len(vsk);
+
+			if (record_len == 0)
+				continue;
+		}
+
+		/* 'msg_iter.count' is number of unused bytes in iov.
+		 * On every copy to iov iterator it is decremented at
+		 * size of data.
+		 */
+		dequeued = transport->seqpacket_dequeue(vsk, msg,
+					msg->msg_iter.count, flags);
+
+		if (dequeued < 0) {
+			dequeued_total = 0;
+
+			if (dequeued == -EAGAIN) {
+				iov_iter_init(&msg->msg_iter, READ,
+					      orig_iov, orig_nr_segs,
+					      len);
+				msg->msg_flags &= ~MSG_EOR;
+				continue;
+			}
+
+			err = -ENOMEM;
+			break;
+		}
+
+		dequeued_total += dequeued;
+
+		if (dequeued_total >= record_len)
+			break;
+	}
+	if (sk->sk_err)
+		err = -sk->sk_err;
+	else if (sk->sk_shutdown & RCV_SHUTDOWN)
+		err = 0;
+
+	if (dequeued_total > 0) {
+		/* 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 that user buffer.
+		 */
+		if (record_len > len)
+			msg->msg_flags |= MSG_TRUNC;
+	}
+out:
+	return err;
 }
 
 static int

@@ -84,7 +84,14 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,
 			       size_t len, int flags);
 
+bool virtio_transport_seqpacket_seq_send_len(struct vsock_sock *vsk, size_t len);
 size_t virtio_transport_seqpacket_seq_get_len(struct vsock_sock *vsk);
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   size_t len,
+				   int type);
+
 s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
 

@@ -139,6 +139,7 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 		break;
 	case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
 	case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
+	case VIRTIO_VSOCK_OP_SEQ_BEGIN:
 		hdr->op = cpu_to_le16(AF_VSOCK_OP_CONTROL);
 		break;
 	default:

@@ -157,6 +158,10 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque)
 
 void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
 {
+	/* TODO: implement tap support for SOCK_SEQPACKET. */
+	if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_SEQPACKET)
+		return;
+
 	if (pkt->tap_delivered)
 		return;
 

@@ -405,6 +410,19 @@ static u16 virtio_transport_get_type(struct sock *sk)
 		return VIRTIO_VSOCK_TYPE_SEQPACKET;
 }
 
+bool virtio_transport_seqpacket_seq_send_len(struct vsock_sock *vsk, size_t len)
+{
+	struct virtio_vsock_pkt_info info = {
+		.type = VIRTIO_VSOCK_TYPE_SEQPACKET,
+		.op = VIRTIO_VSOCK_OP_SEQ_BEGIN,
+		.vsk = vsk,
+		.flags = len
+	};
+
+	return virtio_transport_send_pkt_info(vsk, &info);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_seq_send_len);
+
 static inline void virtio_transport_del_n_free_pkt(struct virtio_vsock_pkt *pkt)
 {
 	list_del(&pkt->list);

@@ -576,6 +594,18 @@ virtio_transport_stream_dequeue(struct vsock_sock *vsk,
 }
 EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);
 
+ssize_t
+virtio_transport_seqpacket_dequeue(struct vsock_sock *vsk,
+				   struct msghdr *msg,
+				   size_t len, int flags)
+{
+	if (flags & MSG_PEEK)
+		return -EOPNOTSUPP;
+
+	return virtio_transport_seqpacket_do_dequeue(vsk, msg, len);
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_dequeue);
+
 int
 virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,

@@ -659,14 +689,15 @@ EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init);
 void virtio_transport_notify_buffer_size(struct vsock_sock *vsk, u64 *val)
 {
 	struct virtio_vsock_sock *vvs = vsk->trans;
+	int type;
 
 	if (*val > VIRTIO_VSOCK_MAX_BUF_SIZE)
 		*val = VIRTIO_VSOCK_MAX_BUF_SIZE;
 
 	vvs->buf_alloc = *val;
 
-	virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
-					    NULL);
+	type = virtio_transport_get_type(sk_vsock(vsk));
+	virtio_transport_send_credit_update(vsk, type, NULL);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_notify_buffer_size);
 

@@ -793,10 +824,11 @@ int virtio_transport_connect(struct vsock_sock *vsk)
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_REQUEST,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.vsk = vsk,
 	};
 
+	info.type = virtio_transport_get_type(sk_vsock(vsk));
+
 	return virtio_transport_send_pkt_info(vsk, &info);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_connect);

@@ -805,7 +837,6 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_SHUTDOWN,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.flags = (mode & RCV_SHUTDOWN ?
 			  VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
 			 (mode & SEND_SHUTDOWN ?

@@ -813,6 +844,8 @@ int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
 		.vsk = vsk,
 	};
 
+	info.type = virtio_transport_get_type(sk_vsock(vsk));
+
 	return virtio_transport_send_pkt_info(vsk, &info);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_shutdown);

@@ -834,12 +867,18 @@ virtio_transport_stream_enqueue(struct vsock_sock *vsk,
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RW,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.msg = msg,
 		.pkt_len = len,
 		.vsk = vsk,
+		.flags = 0,
 	};
 
+	info.type = virtio_transport_get_type(sk_vsock(vsk));
+
+	if (info.type == VIRTIO_VSOCK_TYPE_SEQPACKET &&
+	    msg->msg_flags & MSG_EOR)
+		info.flags |= VIRTIO_VSOCK_RW_EOR;
+
 	return virtio_transport_send_pkt_info(vsk, &info);
 }
 EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);

@@ -857,7 +896,6 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RST,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.reply = !!pkt,
 		.vsk = vsk,
 	};

@@ -866,6 +904,8 @@ static int virtio_transport_reset(struct vsock_sock *vsk,
 	if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
 		return 0;
 
+	info.type = virtio_transport_get_type(sk_vsock(vsk));
+
 	return virtio_transport_send_pkt_info(vsk, &info);
 }
 

@@ -1177,13 +1217,14 @@ virtio_transport_send_response(struct vsock_sock *vsk,
 {
 	struct virtio_vsock_pkt_info info = {
 		.op = VIRTIO_VSOCK_OP_RESPONSE,
-		.type = VIRTIO_VSOCK_TYPE_STREAM,
 		.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
 		.remote_port = le32_to_cpu(pkt->hdr.src_port),
 		.reply = true,
 		.vsk = vsk,
 	};
 
+	info.type = virtio_transport_get_type(sk_vsock(vsk));
+
 	return virtio_transport_send_pkt_info(vsk, &info);
 }
 

@@ -84,6 +84,7 @@ virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
 			       struct msghdr *msg,
 			       size_t len, int flags);
 
+size_t virtio_transport_seqpacket_seq_get_len(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_data(struct vsock_sock *vsk);
 s64 virtio_transport_stream_has_space(struct vsock_sock *vsk);
 

@@ -420,6 +420,39 @@ static size_t virtio_transport_drop_until_seq_begin(struct virtio_vsock_sock *vv
 	return bytes_dropped;
 }
 
+size_t virtio_transport_seqpacket_seq_get_len(struct vsock_sock *vsk)
+{
+	struct virtio_vsock_sock *vvs = vsk->trans;
+	struct virtio_vsock_pkt *pkt;
+	size_t bytes_dropped;
+
+	spin_lock_bh(&vvs->rx_lock);
+
+	/* Fetch all orphaned 'RW', packets, and
+	 * send credit update.
+	 */
+	bytes_dropped = virtio_transport_drop_until_seq_begin(vvs);
+
+	if (list_empty(&vvs->rx_queue))
+		goto out;
+
+	pkt = list_first_entry(&vvs->rx_queue, struct virtio_vsock_pkt, list);
+
+	vvs->user_read_copied = 0;
+	vvs->user_read_seq_len = le32_to_cpu(pkt->hdr.flags);
+	virtio_transport_del_n_free_pkt(pkt);
+out:
+	spin_unlock_bh(&vvs->rx_lock);
+
+	if (bytes_dropped)
+		virtio_transport_send_credit_update(vsk,
+						    VIRTIO_VSOCK_TYPE_SEQPACKET,
+						    NULL);
+
+	return vvs->user_read_seq_len;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_seqpacket_seq_get_len);
+
 static ssize_t virtio_transport_seqpacket_do_dequeue(struct vsock_sock *vsk,
 						     struct msghdr *msg,
 						     size_t user_buf_len)

@@ -1858,65 +1858,69 @@ static int vsock_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 	return vsock_connectible_sendmsg(sock, msg, len);
 }
 
-
-static int
-vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
-			  int flags)
+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)
 {
-	struct sock *sk;
+	int err = 0;
 	struct vsock_sock *vsk;
 	const struct vsock_transport *transport;
-	int err;
-	size_t target;
-	ssize_t copied;
-	long timeout;
-	struct vsock_transport_recv_notify_data recv_data;
-
-	DEFINE_WAIT(wait);
 
-	sk = sock->sk;
 	vsk = vsock_sk(sk);
 	transport = vsk->transport;
-	err = 0;
-
-	lock_sock(sk);
-
-	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;
 
+	if (sk->sk_err != 0 ||
+	    (sk->sk_shutdown & RCV_SHUTDOWN) ||
+	    (vsk->peer_shutdown & SEND_SHUTDOWN)) {
+		err = -1;
 		goto out;
 	}
-
-	if (flags & MSG_OOB) {
-		err = -EOPNOTSUPP;
+	/* Don't wait for non-blocking sockets. */
+	if (timeout == 0) {
+		err = -EAGAIN;
 		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;
+	if (recv_data) {
+		err = transport->notify_recv_pre_block(vsk, target, recv_data);
+		if (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;
+	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;
 	}
 
+out:
+	finish_wait(sk_sleep(sk), wait);
+	return err;
+}
+
+static int __vsock_stream_recvmsg(struct sock *sk, struct msghdr *msg,
+				  size_t len, int flags)
+{
+	struct vsock_transport_recv_notify_data recv_data;
+	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	ssize_t copied;
+	size_t target;
+	long timeout;
+	int err;
+
+	DEFINE_WAIT(wait);
+
+	vsk = vsock_sk(sk);
+	transport = vsk->transport;
+
 	/* 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

@@ -1937,85 +1941,53 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 
 
 	while (1) {
+		ssize_t read;
 		s64 ready;
 
 		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);
+			if (vsock_wait_data(sk, &wait, timeout, &recv_data, target))
 				break;
-			}
-		} else {
-			ssize_t read;
+			continue;
+		}
 
-			finish_wait(sk_sleep(sk), &wait);
+		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.
-				*/
+		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 = -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);
 
-			read = transport->stream_dequeue(
-					vsk, msg,
-					len - copied, flags);
-			if (read < 0) {
-				err = -ENOMEM;
-				break;
-			}
+		if (read < 0) {
+			err = -ENOMEM;
+			break;
+		}
 
-			copied += read;
+		copied += read;
 
-			err = transport->notify_recv_post_dequeue(
-					vsk, target, read,
+		err = transport->notify_recv_post_dequeue(vsk,
+					target, read,
 					!(flags & MSG_PEEK), &recv_data);
-			if (err < 0)
-				goto out;
+		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)

@@ -2031,6 +2003,68 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 	return err;
 }
 
+static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
+				     size_t len, int flags)
+{
+	return -1;
+}
+
+static int
+vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+			  int flags)
+{
+	const struct vsock_transport *transport;
+	struct vsock_sock *vsk;
+	struct sock *sk;
+	int err = 0;
+
+	sk = sock->sk;
+
+	lock_sock(sk);
+
+	vsk = vsock_sk(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 = -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)
+		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)
+		goto out;
+
+	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);
+	return err;
+}
+
 static int
 vsock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
 		     int flags)

@@ -469,6 +469,10 @@ static struct virtio_transport virtio_transport = {
 		.stream_is_active         = virtio_transport_stream_is_active,
 		.stream_allow             = virtio_transport_stream_allow,
 
+		.seqpacket_seq_send_len	  = virtio_transport_seqpacket_seq_send_len,
+		.seqpacket_seq_get_len	  = virtio_transport_seqpacket_seq_get_len,
+		.seqpacket_dequeue        = virtio_transport_seqpacket_dequeue,
+
 		.notify_poll_in           = virtio_transport_notify_poll_in,
 		.notify_poll_out          = virtio_transport_notify_poll_out,
 		.notify_recv_init         = virtio_transport_notify_recv_init,

@@ -354,8 +354,7 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
-	if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM)
-		pkt->len = le32_to_cpu(pkt->hdr.len);
+	pkt->len = le32_to_cpu(pkt->hdr.len);
 
 	/* No payload */
 	if (!pkt->len)

@@ -424,6 +423,10 @@ static struct virtio_transport vhost_transport = {
 		.stream_is_active         = virtio_transport_stream_is_active,
 		.stream_allow             = virtio_transport_stream_allow,
 
+		.seqpacket_seq_send_len	  = virtio_transport_seqpacket_seq_send_len,
+		.seqpacket_seq_get_len	  = virtio_transport_seqpacket_seq_get_len,
+		.seqpacket_dequeue        = virtio_transport_seqpacket_dequeue,
+
 		.notify_poll_in           = virtio_transport_notify_poll_in,
 		.notify_poll_out          = virtio_transport_notify_poll_out,
 		.notify_recv_init         = virtio_transport_notify_recv_init,

@@ -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;