[PATCH v3 net-next 1/1] hv_sock: implements Hyper-V transport for Virtual Sockets (AF_VSOCK)

[Dexuan Cui]

Hyper-V Sockets (hv_sock) supplies a byte-stream based communication
mechanism between the host and the guest. It uses VMBus ringbuffer as the
transportation layer.

With hv_sock, applications between the host (Windows 10, Windows Server
2016 or newer) and the guest can talk with each other using the traditional
socket APIs.

More info about Hyper-V Sockets is available here:

"Make your own integration services":
https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/user-guide/make-integration-service

The patch implements the necessary support in Linux guest by introducing a new
vsock transport for AF_VSOCK.

Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
Cc: K. Y. Srinivasan <kys@xxxxxxxxxxxxx>
Cc: Haiyang Zhang <haiyangz@xxxxxxxxxxxxx>
Cc: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx>
Cc: Andy King <acking@xxxxxxxxxx>
Cc: Dmitry Torokhov <dtor@xxxxxxxxxx>
Cc: George Zhang <georgezhang@xxxxxxxxxx>
Cc: Jorgen Hansen <jhansen@xxxxxxxxxx>
Cc: Reilly Grant <grantr@xxxxxxxxxx>
Cc: Asias He <asias@xxxxxxxxxx>
Cc: Stefan Hajnoczi <stefanha@xxxxxxxxxx>
Cc: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Cc: Cathy Avery <cavery@xxxxxxxxxx>
Cc: Rolf Neugebauer <rolf.neugebauer@xxxxxxxxxx>
Cc: Marcelo Cerri <marcelo.cerri@xxxxxxxxxxxxx>

---

Changes in v2:
	fixed hvs_stream_allow() for cid and the comments
		Thanks Stefan Hajnoczi!

	added proper locking when using vsock_enqueue_accept()
		Thanks Stefan Hajnoczi and Jorgen Hansen!
		

	The previous v1 patch is not needed any more:
 	[PATCH net-next 2/3] vsock: fix vsock_dequeue/enqueue_accept race

	Another previous v1 patch is being discussed in another thread:
	    vsock: only load vmci transport on VMware hypervisor by default

Changes in v3 (addressed David Millers's comments):
	used better naming: VMBUS_PKT_TRAILER_SIZE
	better handled fin_sent: removed atomic
	removed "inline" tags
	better handled uuid service_id assignments: avoid pointers

 MAINTAINERS                      |   1 +
 net/vmw_vsock/Kconfig            |  12 +
 net/vmw_vsock/Makefile           |   3 +
 net/vmw_vsock/hyperv_transport.c | 904 +++++++++++++++++++++++++++++++++++++++
 4 files changed, 920 insertions(+)
 create mode 100644 net/vmw_vsock/hyperv_transport.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 2db0f8c..dae0573 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6279,6 +6279,7 @@ F:	drivers/net/hyperv/
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/uio/uio_hv_generic.c
 F:	drivers/video/fbdev/hyperv_fb.c
+F:	net/vmw_vsock/hyperv_transport.c
 F:	include/linux/hyperv.h
 F:	tools/hv/
 F:	Documentation/ABI/stable/sysfs-bus-vmbus
diff --git a/net/vmw_vsock/Kconfig b/net/vmw_vsock/Kconfig
index a7ae09d..3f52929 100644
--- a/net/vmw_vsock/Kconfig
+++ b/net/vmw_vsock/Kconfig
@@ -46,3 +46,15 @@ config VIRTIO_VSOCKETS_COMMON
 	  This option is selected by any driver which needs to access
 	  the virtio_vsock.  The module will be called
 	  vmw_vsock_virtio_transport_common.
+
+config HYPERV_VSOCKETS
+	tristate "Hyper-V transport for Virtual Sockets"
+	depends on VSOCKETS && HYPERV
+	help
+	  This module implements a Hyper-V transport for Virtual Sockets.
+
+	  Enable this transport if your Virtual Machine host supports Virtual
+	  Sockets over Hyper-V VMBus.
+
+	  To compile this driver as a module, choose M here: the module will be
+	  called hv_sock. If unsure, say N.
diff --git a/net/vmw_vsock/Makefile b/net/vmw_vsock/Makefile
index 09fc2eb..e63d574 100644
--- a/net/vmw_vsock/Makefile
+++ b/net/vmw_vsock/Makefile
@@ -2,6 +2,7 @@ obj-$(CONFIG_VSOCKETS) += vsock.o
 obj-$(CONFIG_VMWARE_VMCI_VSOCKETS) += vmw_vsock_vmci_transport.o
 obj-$(CONFIG_VIRTIO_VSOCKETS) += vmw_vsock_virtio_transport.o
 obj-$(CONFIG_VIRTIO_VSOCKETS_COMMON) += vmw_vsock_virtio_transport_common.o
+obj-$(CONFIG_HYPERV_VSOCKETS) += hv_sock.o
 
 vsock-y += af_vsock.o af_vsock_tap.o vsock_addr.o
 
@@ -11,3 +12,5 @@ vmw_vsock_vmci_transport-y += vmci_transport.o vmci_transport_notify.o \
 vmw_vsock_virtio_transport-y += virtio_transport.o
 
 vmw_vsock_virtio_transport_common-y += virtio_transport_common.o
+
+hv_sock-y += hyperv_transport.o
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
new file mode 100644
index 0000000..14ed5a3
--- /dev/null
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -0,0 +1,904 @@
+/*
+ * Hyper-V transport for vsock
+ *
+ * Hyper-V Sockets supplies a byte-stream based communication mechanism
+ * between the host and the VM. This driver implements the necessary
+ * support in the VM by introducing the new vsock transport.
+ *
+ * Copyright (c) 2017, Microsoft Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ *
+ */
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include <linux/hyperv.h>
+#include <net/sock.h>
+#include <net/af_vsock.h>
+
+/* The host side's design of the feature requires 6 exact 4KB pages for
+ * recv/send rings respectively -- this is suboptimal considering memory
+ * consumption, however unluckily we have to live with it, before the
+ * host comes up with a better design in the future.
+ */
+#define PAGE_SIZE_4K		4096
+#define RINGBUFFER_HVS_RCV_SIZE (PAGE_SIZE_4K * 6)
+#define RINGBUFFER_HVS_SND_SIZE (PAGE_SIZE_4K * 6)
+
+/* The MTU is 16KB per the host side's design */
+#define HVS_MTU_SIZE		(1024 * 16)
+
+struct vmpipe_proto_header {
+	u32 pkt_type;
+	u32 data_size;
+};
+
+/* For recv, we use the VMBus in-place packet iterator APIs to directly copy
+ * data from the ringbuffer into the userspace buffer.
+ */
+struct hvs_recv_buf {
+	/* The header before the payload data */
+	struct vmpipe_proto_header hdr;
+
+	/* The payload */
+	u8 data[HVS_MTU_SIZE];
+};
+
+/* We can send up to HVS_MTU_SIZE bytes of payload to the host, but let's use
+ * a small size, i.e. HVS_SEND_BUF_SIZE, to minimize the dynamically-allocated
+ * buffer, because tests show there is no significant performance difference.
+ *
+ * Note: the buffer can be eliminated in the future when we add new VMBus
+ * ringbuffer APIs that allow us to directly copy data from userspace buffer
+ * to VMBus ringbuffer.
+ */
+#define HVS_SEND_BUF_SIZE (PAGE_SIZE_4K - sizeof(struct vmpipe_proto_header))
+
+struct hvs_send_buf {
+	/* The header before the payload data */
+	struct vmpipe_proto_header hdr;
+
+	/* The payload */
+	u8 data[HVS_SEND_BUF_SIZE];
+};
+
+#define HVS_HEADER_LEN	(sizeof(struct vmpacket_descriptor) + \
+			 sizeof(struct vmpipe_proto_header))
+
+/* See 'prev_indices' in hv_ringbuffer_read(), hv_ringbuffer_write(), and
+ * __hv_pkt_iter_next().
+ */
+#define VMBUS_PKT_TRAILER_SIZE	(sizeof(u64))
+
+#define HVS_PKT_LEN(payload_len)	(HVS_HEADER_LEN + \
+					 ALIGN((payload_len), 8) + \
+					 VMBUS_PKT_TRAILER_SIZE)
+
+union hvs_service_id {
+	uuid_le	srv_id;
+
+	struct {
+		unsigned int svm_port;
+		unsigned char b[sizeof(uuid_le) - sizeof(unsigned int)];
+	};
+};
+
+/* Per-socket state (accessed via vsk->trans) */
+struct hvsock {
+	struct vsock_sock *vsk;
+
+	uuid_le vm_srv_id;
+	uuid_le host_srv_id;
+
+	struct vmbus_channel *chan;
+	struct vmpacket_descriptor *recv_desc;
+
+	/* The length of the payload not delivered to userland yet */
+	u32 recv_data_len;
+	/* The offset of the payload */
+	u32 recv_data_off;
+
+	/* Have we sent the zero-length packet (FIN)? */
+	bool fin_sent;
+};
+
+/* In the VM, we support Hyper-V Sockets with AF_VSOCK, and the endpoint is
+ * <cid, port> (see struct sockaddr_vm). Note: cid is not really used here:
+ * when we write apps to connect to the host, we can only use VMADDR_CID_ANY
+ * or VMADDR_CID_HOST (both are equivalent) as the remote cid, and when we
+ * write apps to bind() & listen() in the VM, we can only use VMADDR_CID_ANY
+ * as the local cid.
+ *
+ * On the host, Hyper-V Sockets are supported by Winsock AF_HYPERV:
+ * https://docs.microsoft.com/en-us/virtualization/hyper-v-on-windows/user-
+ * guide/make-integration-service, and the endpoint is <VmID, ServiceId> with
+ * the below sockaddr:
+ *
+ * struct SOCKADDR_HV
+ * {
+ *    ADDRESS_FAMILY Family;
+ *    USHORT Reserved;
+ *    GUID VmId;
+ *    GUID ServiceId;
+ * };
+ * Note: VmID is not used by Linux VM and actually it isn't transmitted via
+ * VMBus, because here it's obvious the host and the VM can easily identify
+ * each other. Though the VmID is useful on the host, especially in the case
+ * of Windows container, Linux VM doesn't need it at all.
+ *
+ * To make use of the AF_VSOCK infrastructure in Linux VM, we have to limit
+ * the available GUID space of SOCKADDR_HV so that we can create a mapping
+ * between AF_VSOCK port and SOCKADDR_HV Service GUID. The rule of writing
+ * Hyper-V Sockets apps on the host and in Linux VM is:
+ *
+ ****************************************************************************
+ * The only valid Service GUIDs, from the perspectives of both the host and *
+ * Linux VM, that can be connected by the other end, must conform to this   *
+ * format: <port>-facb-11e6-bd58-64006a7986d3, and the "port" must be in    *
+ * this range [0, 0x7FFFFFFF].                                              *
+ ****************************************************************************
+ *
+ * When we write apps on the host to connect(), the GUID ServiceID is used.
+ * When we write apps in Linux VM to connect(), we only need to specify the
+ * port and the driver will form the GUID and use that to request the host.
+ *
+ * From the perspective of Linux VM:
+ * 1. the local ephemeral port (i.e. the local auto-bound port when we call
+ * connect() without explicit bind()) is generated by __vsock_bind_stream(),
+ * and the range is [1024, 0xFFFFFFFF).
+ * 2. the remote ephemeral port (i.e. the auto-generated remote port for
+ * a connect request initiated by the host's connect()) is generated by
+ * hvs_remote_addr_init() and the range is [0x80000000, 0xFFFFFFFF).
+ */
+
+#define MAX_LISTEN_PORT			((u32)0x7FFFFFFF)
+#define MAX_VM_LISTEN_PORT		MAX_LISTEN_PORT
+#define MAX_HOST_LISTEN_PORT		MAX_LISTEN_PORT
+#define MIN_HOST_EPHEMERAL_PORT		(MAX_HOST_LISTEN_PORT + 1)
+
+/* 00000000-facb-11e6-bd58-64006a7986d3 */
+static const uuid_le srv_id_template =
+	UUID_LE(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
+		0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
+
+static bool is_valid_srv_id(const uuid_le *id)
+{
+	return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(uuid_le) - 4);
+}
+
+static unsigned int get_port_by_srv_id(const uuid_le *svr_id)
+{
+	return *((unsigned int *)svr_id);
+}
+
+static void hvs_addr_init(struct sockaddr_vm *addr, const uuid_le *svr_id)
+{
+	unsigned int port = get_port_by_srv_id(svr_id);
+
+	vsock_addr_init(addr, VMADDR_CID_ANY, port);
+}
+
+static void hvs_remote_addr_init(struct sockaddr_vm *remote,
+				 struct sockaddr_vm *local)
+{
+	static u32 host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
+	struct sock *sk;
+
+	vsock_addr_init(remote, VMADDR_CID_ANY, VMADDR_PORT_ANY);
+
+	while (1) {
+		/* Wrap around ? */
+		if (host_ephemeral_port < MIN_HOST_EPHEMERAL_PORT ||
+		    host_ephemeral_port == VMADDR_PORT_ANY)
+			host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT;
+
+		remote->svm_port = host_ephemeral_port++;
+
+		sk = vsock_find_connected_socket(remote, local);
+		if (!sk) {
+			/* Found an available ephemeral port */
+			return;
+		}
+
+		/* Release refcnt got in vsock_find_connected_socket */
+		sock_put(sk);
+	}
+}
+
+static void hvs_set_channel_pending_send_size(struct vmbus_channel *chan)
+{
+	set_channel_pending_send_size(chan,
+				      HVS_PKT_LEN(HVS_SEND_BUF_SIZE));
+
+	/* See hvs_stream_has_space(): we must make sure the host has seen
+	 * the new pending send size, before we can re-check the writable
+	 * bytes.
+	 */
+	virt_mb();
+}
+
+static void hvs_clear_channel_pending_send_size(struct vmbus_channel *chan)
+{
+	set_channel_pending_send_size(chan, 0);
+
+	/* Ditto */
+	virt_mb();
+}
+
+static bool hvs_channel_readable(struct vmbus_channel *chan)
+{
+	u32 readable = hv_get_bytes_to_read(&chan->inbound);
+
+	/* 0-size payload means FIN */
+	return readable >= HVS_PKT_LEN(0);
+}
+
+static int hvs_channel_readable_payload(struct vmbus_channel *chan)
+{
+	u32 readable = hv_get_bytes_to_read(&chan->inbound);
+
+	if (readable > HVS_PKT_LEN(0)) {
+		/* At least we have 1 byte to read. We don't need to return
+		 * the exact readable bytes: see vsock_stream_recvmsg() ->
+		 * vsock_stream_has_data().
+		 */
+		return 1;
+	}
+
+	if (readable == HVS_PKT_LEN(0)) {
+		/* 0-size payload means FIN */
+		return 0;
+	}
+
+	/* No payload or FIN */
+	return -1;
+}
+
+static size_t hvs_channel_writable_bytes(struct vmbus_channel *chan)
+{
+	u32 writeable = hv_get_bytes_to_write(&chan->outbound);
+	size_t ret;
+
+	/* The ringbuffer mustn't be 100% full, and we should reserve a
+	 * zero-length-payload packet for the FIN: see hv_ringbuffer_write()
+	 * and hvs_shutdown().
+	 */
+	if (writeable <= HVS_PKT_LEN(1) + HVS_PKT_LEN(0))
+		return 0;
+
+	ret = writeable - HVS_PKT_LEN(1) - HVS_PKT_LEN(0);
+
+	return round_down(ret, 8);
+}
+
+static int hvs_send_data(struct vmbus_channel *chan,
+			 struct hvs_send_buf *send_buf, size_t to_write)
+{
+	send_buf->hdr.pkt_type = 1;
+	send_buf->hdr.data_size = to_write;
+	return vmbus_sendpacket(chan, &send_buf->hdr,
+				sizeof(send_buf->hdr) + to_write,
+				0, VM_PKT_DATA_INBAND, 0);
+}
+
+static void hvs_channel_cb(void *ctx)
+{
+	struct sock *sk = (struct sock *)ctx;
+	struct vsock_sock *vsk = vsock_sk(sk);
+	struct hvsock *hvs = vsk->trans;
+	struct vmbus_channel *chan = hvs->chan;
+
+	if (hvs_channel_readable(chan))
+		sk->sk_data_ready(sk);
+
+	/* See hvs_stream_has_space(): when we reach here, the writable bytes
+	 * may be already less than HVS_PKT_LEN(HVS_SEND_BUF_SIZE).
+	 */
+	if (hv_get_bytes_to_write(&chan->outbound) > 0)
+		sk->sk_write_space(sk);
+}
+
+static void hvs_close_connection(struct vmbus_channel *chan)
+{
+	struct sock *sk = get_per_channel_state(chan);
+	struct vsock_sock *vsk = vsock_sk(sk);
+
+	sk->sk_state = SS_UNCONNECTED;
+	sock_set_flag(sk, SOCK_DONE);
+	vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN;
+
+	sk->sk_state_change(sk);
+}
+
+static void hvs_open_connection(struct vmbus_channel *chan)
+{
+	uuid_le *if_instance, *if_type;
+	unsigned char conn_from_host;
+
+	struct sockaddr_vm addr;
+	struct sock *sk, *new = NULL;
+	struct vsock_sock *vnew;
+	struct hvsock *hvs, *hvs_new;
+	int ret;
+
+	if_type = &chan->offermsg.offer.if_type;
+	if_instance = &chan->offermsg.offer.if_instance;
+	conn_from_host = chan->offermsg.offer.u.pipe.user_def[0];
+
+	/* The host or the VM should only listen on a port in
+	 * [0, MAX_LISTEN_PORT]
+	 */
+	if (!is_valid_srv_id(if_type) ||
+	    get_port_by_srv_id(if_type) > MAX_LISTEN_PORT)
+		return;
+
+	hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
+	sk = vsock_find_bound_socket(&addr);
+	if (!sk)
+		return;
+
+	if ((conn_from_host && sk->sk_state != VSOCK_SS_LISTEN) ||
+	    (!conn_from_host && sk->sk_state != SS_CONNECTING))
+		goto out;
+
+	if (conn_from_host) {
+		if (sk->sk_ack_backlog >= sk->sk_max_ack_backlog)
+			goto out;
+
+		new = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
+				     sk->sk_type, 0);
+		if (!new)
+			goto out;
+
+		new->sk_state = SS_CONNECTING;
+		vnew = vsock_sk(new);
+		hvs_new = vnew->trans;
+		hvs_new->chan = chan;
+	} else {
+		hvs = vsock_sk(sk)->trans;
+		hvs->chan = chan;
+	}
+
+	set_channel_read_mode(chan, HV_CALL_DIRECT);
+	ret = vmbus_open(chan, RINGBUFFER_HVS_SND_SIZE,
+			 RINGBUFFER_HVS_RCV_SIZE, NULL, 0,
+			 hvs_channel_cb, conn_from_host ? new : sk);
+	if (ret != 0) {
+		if (conn_from_host) {
+			hvs_new->chan = NULL;
+			sock_put(new);
+		} else {
+			hvs->chan = NULL;
+		}
+		goto out;
+	}
+
+	set_per_channel_state(chan, conn_from_host ? new : sk);
+	vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
+
+	if (conn_from_host) {
+		new->sk_state = SS_CONNECTED;
+		sk->sk_ack_backlog++;
+
+		hvs_addr_init(&vnew->local_addr, if_type);
+		hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
+
+		hvs_new->vm_srv_id = *if_type;
+		hvs_new->host_srv_id = *if_instance;
+
+		vsock_insert_connected(vnew);
+
+		lock_sock(sk);
+		vsock_enqueue_accept(sk, new);
+		release_sock(sk);
+	} else {
+		sk->sk_state = SS_CONNECTED;
+		sk->sk_socket->state = SS_CONNECTED;
+
+		vsock_insert_connected(vsock_sk(sk));
+	}
+
+	sk->sk_state_change(sk);
+
+out:
+	/* Release refcnt obtained when we called vsock_find_bound_socket() */
+	sock_put(sk);
+}
+
+static u32 hvs_get_local_cid(void)
+{
+	return VMADDR_CID_ANY;
+}
+
+static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk)
+{
+	struct hvsock *hvs;
+
+	hvs = kzalloc(sizeof(*hvs), GFP_KERNEL);
+	if (!hvs)
+		return -ENOMEM;
+
+	vsk->trans = hvs;
+	hvs->vsk = vsk;
+
+	return 0;
+}
+
+static int hvs_connect(struct vsock_sock *vsk)
+{
+	union hvs_service_id vm, host;
+	struct hvsock *h = vsk->trans;
+
+	vm.srv_id = srv_id_template;
+	vm.svm_port = vsk->local_addr.svm_port;
+	h->vm_srv_id = vm.srv_id;
+
+	host.srv_id = srv_id_template;
+	host.svm_port = vsk->remote_addr.svm_port;
+	h->host_srv_id = host.srv_id;
+
+	return vmbus_send_tl_connect_request(&h->vm_srv_id, &h->host_srv_id);
+}
+
+static int hvs_shutdown(struct vsock_sock *vsk, int mode)
+{
+	struct sock *sk = sk_vsock(vsk);
+	struct vmpipe_proto_header hdr;
+	struct hvs_send_buf *send_buf;
+	struct hvsock *hvs;
+
+	if (!(mode & SEND_SHUTDOWN))
+		return 0;
+
+	lock_sock(sk);
+
+	hvs = vsk->trans;
+	if (hvs->fin_sent)
+		goto out;
+
+	send_buf = (struct hvs_send_buf *)&hdr;
+
+	/* It can't fail: see hvs_channel_writable_bytes(). */
+	(void)hvs_send_data(hvs->chan, send_buf, 0);
+
+	hvs->fin_sent = true;
+out:
+	release_sock(sk);
+	return 0;
+}
+
+static void hvs_release(struct vsock_sock *vsk)
+{
+	struct hvsock *hvs = vsk->trans;
+	struct vmbus_channel *chan = hvs->chan;
+
+	if (chan)
+		hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN);
+
+	vsock_remove_sock(vsk);
+}
+
+static void hvs_destruct(struct vsock_sock *vsk)
+{
+	struct hvsock *hvs = vsk->trans;
+	struct vmbus_channel *chan = hvs->chan;
+
+	if (chan)
+		vmbus_hvsock_device_unregister(chan);
+
+	kfree(hvs);
+}
+
+static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hvs_dgram_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
+			     size_t len, int flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static int hvs_dgram_enqueue(struct vsock_sock *vsk,
+			     struct sockaddr_vm *remote, struct msghdr *msg,
+			     size_t dgram_len)
+{
+	return -EOPNOTSUPP;
+}
+
+static bool hvs_dgram_allow(u32 cid, u32 port)
+{
+	return false;
+}
+
+static int hvs_update_recv_data(struct hvsock *hvs)
+{
+	struct hvs_recv_buf *recv_buf;
+	u32 payload_len;
+
+	recv_buf = (struct hvs_recv_buf *)(hvs->recv_desc + 1);
+	payload_len = recv_buf->hdr.data_size;
+
+	if (payload_len > HVS_MTU_SIZE)
+		return -EIO;
+
+	if (payload_len == 0)
+		hvs->vsk->peer_shutdown |= SEND_SHUTDOWN;
+
+	hvs->recv_data_len = payload_len;
+	hvs->recv_data_off = 0;
+
+	return 0;
+}
+
+static ssize_t hvs_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
+				  size_t len, int flags)
+{
+	struct hvsock *hvs = vsk->trans;
+	bool need_refill = !hvs->recv_desc;
+	struct hvs_recv_buf *recv_buf;
+	u32 to_read;
+	int ret;
+
+	if (flags & MSG_PEEK)
+		return -EOPNOTSUPP;
+
+	if (need_refill) {
+		hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
+		ret = hvs_update_recv_data(hvs);
+		if (ret)
+			return ret;
+	}
+
+	recv_buf = (struct hvs_recv_buf *)(hvs->recv_desc + 1);
+	to_read = min_t(u32, len, hvs->recv_data_len);
+	ret = memcpy_to_msg(msg, recv_buf->data + hvs->recv_data_off, to_read);
+	if (ret != 0)
+		return ret;
+
+	hvs->recv_data_len -= to_read;
+	if (hvs->recv_data_len == 0) {
+		hvs->recv_desc = hv_pkt_iter_next(hvs->chan, hvs->recv_desc);
+		if (hvs->recv_desc) {
+			ret = hvs_update_recv_data(hvs);
+			if (ret)
+				return ret;
+		}
+	} else {
+		hvs->recv_data_off += to_read;
+	}
+
+	return to_read;
+}
+
+static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
+				  size_t len)
+{
+	struct hvsock *hvs = vsk->trans;
+	struct vmbus_channel *chan = hvs->chan;
+	struct hvs_send_buf *send_buf;
+	ssize_t to_write, max_writable, ret;
+
+	BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K);
+
+	send_buf = kmalloc(sizeof(*send_buf), GFP_KERNEL);
+	if (!send_buf)
+		return -ENOMEM;
+
+	max_writable = hvs_channel_writable_bytes(chan);
+	to_write = min_t(ssize_t, len, max_writable);
+	to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE);
+
+	ret = memcpy_from_msg(send_buf->data, msg, to_write);
+	if (ret < 0)
+		goto out;
+
+	ret = hvs_send_data(hvs->chan, send_buf, to_write);
+	if (ret < 0)
+		goto out;
+
+	ret = to_write;
+out:
+	kfree(send_buf);
+	return ret;
+}
+
+static s64 hvs_stream_has_data(struct vsock_sock *vsk)
+{
+	struct hvsock *hvs = vsk->trans;
+	s64 ret;
+
+	if (hvs->recv_data_len > 0)
+		return 1;
+
+	switch (hvs_channel_readable_payload(hvs->chan)) {
+	case 1:
+		ret = 1;
+		break;
+	case 0:
+		vsk->peer_shutdown |= SEND_SHUTDOWN;
+		ret = 0;
+		break;
+	default: /* -1 */
+		ret = 0;
+		break;
+	}
+
+	return ret;
+}
+
+static s64 hvs_stream_has_space(struct vsock_sock *vsk)
+{
+	struct hvsock *hvs = vsk->trans;
+	struct vmbus_channel *chan = hvs->chan;
+	s64 ret;
+
+	ret = hvs_channel_writable_bytes(chan);
+	if (ret > 0)  {
+		hvs_clear_channel_pending_send_size(chan);
+	} else {
+		/* See hvs_channel_cb() */
+		hvs_set_channel_pending_send_size(chan);
+
+		/* Re-check the writable bytes to avoid race */
+		ret = hvs_channel_writable_bytes(chan);
+		if (ret > 0)
+			hvs_clear_channel_pending_send_size(chan);
+	}
+
+	return ret;
+}
+
+static u64 hvs_stream_rcvhiwat(struct vsock_sock *vsk)
+{
+	return HVS_MTU_SIZE + 1;
+}
+
+static bool hvs_stream_is_active(struct vsock_sock *vsk)
+{
+	struct hvsock *hvs = vsk->trans;
+
+	return hvs->chan != NULL;
+}
+
+static bool hvs_stream_allow(u32 cid, u32 port)
+{
+	/* The host's port range [MIN_HOST_EPHEMERAL_PORT, 0xFFFFFFFF) is
+	 * reserved as ephemeral ports, which are used as the host's ports
+	 * when the host initiates connections.
+	 *
+	 * Perform this check in the guest so an immediate error is produced
+	 * instead of a timeout.
+	 */
+	if (port > MAX_HOST_LISTEN_PORT)
+		return false;
+
+	if (cid == VMADDR_CID_HOST)
+		return true;
+
+	return false;
+}
+
+static
+int hvs_notify_poll_in(struct vsock_sock *vsk, size_t target, bool *readable)
+{
+	struct hvsock *hvs = vsk->trans;
+
+	*readable = hvs_channel_readable(hvs->chan);
+	return 0;
+}
+
+static
+int hvs_notify_poll_out(struct vsock_sock *vsk, size_t target, bool *writable)
+{
+	*writable = hvs_stream_has_space(vsk) > 0;
+
+	return 0;
+}
+
+static
+int hvs_notify_recv_init(struct vsock_sock *vsk, size_t target,
+			 struct vsock_transport_recv_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_recv_pre_block(struct vsock_sock *vsk, size_t target,
+			      struct vsock_transport_recv_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_recv_pre_dequeue(struct vsock_sock *vsk, size_t target,
+				struct vsock_transport_recv_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_recv_post_dequeue(struct vsock_sock *vsk, size_t target,
+				 ssize_t copied, bool data_read,
+				 struct vsock_transport_recv_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_send_init(struct vsock_sock *vsk,
+			 struct vsock_transport_send_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_send_pre_block(struct vsock_sock *vsk,
+			      struct vsock_transport_send_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_send_pre_enqueue(struct vsock_sock *vsk,
+				struct vsock_transport_send_notify_data *d)
+{
+	return 0;
+}
+
+static
+int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
+				 struct vsock_transport_send_notify_data *d)
+{
+	return 0;
+}
+
+static void hvs_set_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+	/* Ignored. */
+}
+
+static void hvs_set_min_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+	/* Ignored. */
+}
+
+static void hvs_set_max_buffer_size(struct vsock_sock *vsk, u64 val)
+{
+	/* Ignored. */
+}
+
+static u64 hvs_get_buffer_size(struct vsock_sock *vsk)
+{
+	return -ENOPROTOOPT;
+}
+
+static u64 hvs_get_min_buffer_size(struct vsock_sock *vsk)
+{
+	return -ENOPROTOOPT;
+}
+
+static u64 hvs_get_max_buffer_size(struct vsock_sock *vsk)
+{
+	return -ENOPROTOOPT;
+}
+
+static struct vsock_transport hvs_transport = {
+	.get_local_cid            = hvs_get_local_cid,
+
+	.init                     = hvs_sock_init,
+	.destruct                 = hvs_destruct,
+	.release                  = hvs_release,
+	.connect                  = hvs_connect,
+	.shutdown                 = hvs_shutdown,
+
+	.dgram_bind               = hvs_dgram_bind,
+	.dgram_dequeue            = hvs_dgram_dequeue,
+	.dgram_enqueue            = hvs_dgram_enqueue,
+	.dgram_allow              = hvs_dgram_allow,
+
+	.stream_dequeue           = hvs_stream_dequeue,
+	.stream_enqueue           = hvs_stream_enqueue,
+	.stream_has_data          = hvs_stream_has_data,
+	.stream_has_space         = hvs_stream_has_space,
+	.stream_rcvhiwat          = hvs_stream_rcvhiwat,
+	.stream_is_active         = hvs_stream_is_active,
+	.stream_allow             = hvs_stream_allow,
+
+	.notify_poll_in           = hvs_notify_poll_in,
+	.notify_poll_out          = hvs_notify_poll_out,
+	.notify_recv_init         = hvs_notify_recv_init,
+	.notify_recv_pre_block    = hvs_notify_recv_pre_block,
+	.notify_recv_pre_dequeue  = hvs_notify_recv_pre_dequeue,
+	.notify_recv_post_dequeue = hvs_notify_recv_post_dequeue,
+	.notify_send_init         = hvs_notify_send_init,
+	.notify_send_pre_block    = hvs_notify_send_pre_block,
+	.notify_send_pre_enqueue  = hvs_notify_send_pre_enqueue,
+	.notify_send_post_enqueue = hvs_notify_send_post_enqueue,
+
+	.set_buffer_size          = hvs_set_buffer_size,
+	.set_min_buffer_size      = hvs_set_min_buffer_size,
+	.set_max_buffer_size      = hvs_set_max_buffer_size,
+	.get_buffer_size          = hvs_get_buffer_size,
+	.get_min_buffer_size      = hvs_get_min_buffer_size,
+	.get_max_buffer_size      = hvs_get_max_buffer_size,
+};
+
+static int hvs_probe(struct hv_device *hdev,
+		     const struct hv_vmbus_device_id *dev_id)
+{
+	struct vmbus_channel *chan = hdev->channel;
+
+	hvs_open_connection(chan);
+
+	/* Always return success to suppress the unnecessary error message
+	 * in vmbus_probe(): on error the host will rescind the device in
+	 * 30 seconds and we can do cleanup at that time in
+	 * vmbus_onoffer_rescind().
+	 */
+	return 0;
+}
+
+static int hvs_remove(struct hv_device *hdev)
+{
+	struct vmbus_channel *chan = hdev->channel;
+
+	vmbus_close(chan);
+
+	return 0;
+}
+
+/* This isn't really used. See vmbus_match() and vmbus_probe() */
+static const struct hv_vmbus_device_id id_table[] = {
+	{},
+};
+
+static struct hv_driver hvs_drv = {
+	.name		= "hv_sock",
+	.hvsock		= true,
+	.id_table	= id_table,
+	.probe		= hvs_probe,
+	.remove		= hvs_remove,
+};
+
+static int __init hvs_init(void)
+{
+	int ret;
+
+	if (vmbus_proto_version < VERSION_WIN10)
+		return -ENODEV;
+
+	ret = vmbus_driver_register(&hvs_drv);
+	if (ret != 0)
+		return ret;
+
+	ret = vsock_core_init(&hvs_transport);
+	if (ret) {
+		vmbus_driver_unregister(&hvs_drv);
+		return ret;
+	}
+
+	return 0;
+}
+
+static void __exit hvs_exit(void)
+{
+	vsock_core_exit();
+	vmbus_driver_unregister(&hvs_drv);
+}
+
+module_init(hvs_init);
+module_exit(hvs_exit);
+
+MODULE_DESCRIPTION("Hyper-V Sockets");
+MODULE_VERSION("1.0.0");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NETPROTO(PF_VSOCK);
-- 
2.7.4