1 files changed, 273 insertions, 224 deletions

diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index a827547aa102..432fcbbd14d4 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Hyper-V transport for vsock
  *
@@ -6,35 +7,29 @@
  * 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>
+#include <hyperv/hvhdk.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.
+/* Older (VMBUS version 'VERSION_WIN10' or before) Windows hosts have some
+ * stricter requirements on the hv_sock ring buffer size of six 4K pages.
+ * HV_HYP_PAGE_SIZE is defined as 4K. Newer hosts don't have this limitation;
+ * but, keep the defaults the same for compat.
  */
-#define PAGE_SIZE_4K		4096
-#define RINGBUFFER_HVS_RCV_SIZE (PAGE_SIZE_4K * 6)
-#define RINGBUFFER_HVS_SND_SIZE (PAGE_SIZE_4K * 6)
+#define RINGBUFFER_HVS_RCV_SIZE (HV_HYP_PAGE_SIZE * 6)
+#define RINGBUFFER_HVS_SND_SIZE (HV_HYP_PAGE_SIZE * 6)
+#define RINGBUFFER_HVS_MAX_SIZE (HV_HYP_PAGE_SIZE * 64)
 
 /* The MTU is 16KB per the host side's design */
 #define HVS_MTU_SIZE		(1024 * 16)
 
+/* How long to wait for graceful shutdown of a connection */
+#define HVS_CLOSE_TIMEOUT (8 * HZ)
+
 struct vmpipe_proto_header {
 	u32 pkt_type;
 	u32 data_size;
@@ -52,14 +47,16 @@ struct hvs_recv_buf {
 };
 
 /* 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.
+ * a smaller size, i.e. HVS_SEND_BUF_SIZE, to maximize concurrency between the
+ * guest and the host processing as one VMBUS packet is the smallest processing
+ * unit.
  *
  * 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))
+#define HVS_SEND_BUF_SIZE \
+		(HV_HYP_PAGE_SIZE - sizeof(struct vmpipe_proto_header))
 
 struct hvs_send_buf {
 	/* The header before the payload data */
@@ -81,12 +78,15 @@ struct hvs_send_buf {
 					 ALIGN((payload_len), 8) + \
 					 VMBUS_PKT_TRAILER_SIZE)
 
+/* Upper bound on the size of a VMbus packet for hv_sock */
+#define HVS_MAX_PKT_SIZE	HVS_PKT_LEN(HVS_MTU_SIZE)
+
 union hvs_service_id {
-	uuid_le	srv_id;
+	guid_t	srv_id;
 
 	struct {
 		unsigned int svm_port;
-		unsigned char b[sizeof(uuid_le) - sizeof(unsigned int)];
+		unsigned char b[sizeof(guid_t) - sizeof(unsigned int)];
 	};
 };
 
@@ -94,8 +94,8 @@ union hvs_service_id {
 struct hvsock {
 	struct vsock_sock *vsk;
 
-	uuid_le vm_srv_id;
-	uuid_le host_srv_id;
+	guid_t vm_srv_id;
+	guid_t host_srv_id;
 
 	struct vmbus_channel *chan;
 	struct vmpacket_descriptor *recv_desc;
@@ -141,94 +141,44 @@ struct hvsock {
  ****************************************************************************
  * 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].                                              *
+ * format: <port>-facb-11e6-bd58-64006a7986d3.                              *
  ****************************************************************************
  *
  * 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 const guid_t srv_id_template =
+	GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58,
+		  0x64, 0x00, 0x6a, 0x79, 0x86, 0xd3);
 
-static bool is_valid_srv_id(const uuid_le *id)
+static bool hvs_check_transport(struct vsock_sock *vsk);
+
+static bool is_valid_srv_id(const guid_t *id)
 {
-	return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(uuid_le) - 4);
+	return !memcmp(&id->b[4], &srv_id_template.b[4], sizeof(guid_t) - 4);
 }
 
-static unsigned int get_port_by_srv_id(const uuid_le *svr_id)
+static unsigned int get_port_by_srv_id(const guid_t *svr_id)
 {
 	return *((unsigned int *)svr_id);
 }
 
-static void hvs_addr_init(struct sockaddr_vm *addr, const uuid_le *svr_id)
+static void hvs_addr_init(struct sockaddr_vm *addr, const guid_t *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();
 }
 
@@ -278,14 +228,20 @@ static size_t hvs_channel_writable_bytes(struct vmbus_channel *chan)
 	return round_down(ret, 8);
 }
 
+static int __hvs_send_data(struct vmbus_channel *chan,
+			   struct vmpipe_proto_header *hdr,
+			   size_t to_write)
+{
+	hdr->pkt_type = 1;
+	hdr->data_size = to_write;
+	return vmbus_sendpacket(chan, hdr, sizeof(*hdr) + to_write,
+				0, VM_PKT_DATA_INBAND, 0);
+}
+
 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);
+	return __hvs_send_data(chan, &send_buf->hdr, to_write);
 }
 
 static void hvs_channel_cb(void *ctx)
@@ -298,49 +254,62 @@ static void hvs_channel_cb(void *ctx)
 	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)
+static void hvs_do_close_lock_held(struct vsock_sock *vsk,
+				   bool cancel_timeout)
 {
-	struct sock *sk = get_per_channel_state(chan);
-	struct vsock_sock *vsk = vsock_sk(sk);
-
-	lock_sock(sk);
+	struct sock *sk = sk_vsock(vsk);
 
-	sk->sk_state = TCP_CLOSE;
 	sock_set_flag(sk, SOCK_DONE);
-	vsk->peer_shutdown |= SEND_SHUTDOWN | RCV_SHUTDOWN;
-
+	vsk->peer_shutdown = SHUTDOWN_MASK;
+	if (vsock_stream_has_data(vsk) <= 0)
+		sk->sk_state = TCP_CLOSING;
 	sk->sk_state_change(sk);
+	if (vsk->close_work_scheduled &&
+	    (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
+		vsk->close_work_scheduled = false;
+		vsock_remove_sock(vsk);
 
+		/* Release the reference taken while scheduling the timeout */
+		sock_put(sk);
+	}
+}
+
+static void hvs_close_connection(struct vmbus_channel *chan)
+{
+	struct sock *sk = get_per_channel_state(chan);
+
+	lock_sock(sk);
+	hvs_do_close_lock_held(vsock_sk(sk), true);
 	release_sock(sk);
+
+	/* Release the refcnt for the channel that's opened in
+	 * hvs_open_connection().
+	 */
+	sock_put(sk);
 }
 
 static void hvs_open_connection(struct vmbus_channel *chan)
 {
-	uuid_le *if_instance, *if_type;
+	guid_t *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;
+	struct vsock_sock *vnew = NULL;
+	struct hvsock *hvs = NULL;
+	struct hvsock *hvs_new = NULL;
+	int rcvbuf;
 	int ret;
+	int sndbuf;
 
 	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)
+	if (!is_valid_srv_id(if_type))
 		return;
 
 	hvs_addr_init(&addr, conn_from_host ? if_type : if_instance);
@@ -357,13 +326,27 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 		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);
+		new = vsock_create_connected(sk);
 		if (!new)
 			goto out;
 
 		new->sk_state = TCP_SYN_SENT;
 		vnew = vsock_sk(new);
+
+		hvs_addr_init(&vnew->local_addr, if_type);
+
+		/* Remote peer is always the host */
+		vsock_addr_init(&vnew->remote_addr,
+				VMADDR_CID_HOST, VMADDR_PORT_ANY);
+		vnew->remote_addr.svm_port = get_port_by_srv_id(if_instance);
+		ret = vsock_assign_transport(vnew, vsock_sk(sk));
+		/* Transport assigned (looking at remote_addr) must be the
+		 * same where we received the request.
+		 */
+		if (ret || !hvs_check_transport(vnew)) {
+			sock_put(new);
+			goto out;
+		}
 		hvs_new = vnew->trans;
 		hvs_new->chan = chan;
 	} else {
@@ -372,9 +355,36 @@ static void hvs_open_connection(struct vmbus_channel *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);
+
+	/* Use the socket buffer sizes as hints for the VMBUS ring size. For
+	 * server side sockets, 'sk' is the parent socket and thus, this will
+	 * allow the child sockets to inherit the size from the parent. Keep
+	 * the mins to the default value and align to page size as per VMBUS
+	 * requirements.
+	 * For the max, the socket core library will limit the socket buffer
+	 * size that can be set by the user, but, since currently, the hv_sock
+	 * VMBUS ring buffer is physically contiguous allocation, restrict it
+	 * further.
+	 * Older versions of hv_sock host side code cannot handle bigger VMBUS
+	 * ring buffer size. Use the version number to limit the change to newer
+	 * versions.
+	 */
+	if (vmbus_proto_version < VERSION_WIN10_V5) {
+		sndbuf = RINGBUFFER_HVS_SND_SIZE;
+		rcvbuf = RINGBUFFER_HVS_RCV_SIZE;
+	} else {
+		sndbuf = max_t(int, sk->sk_sndbuf, RINGBUFFER_HVS_SND_SIZE);
+		sndbuf = min_t(int, sndbuf, RINGBUFFER_HVS_MAX_SIZE);
+		sndbuf = ALIGN(sndbuf, HV_HYP_PAGE_SIZE);
+		rcvbuf = max_t(int, sk->sk_rcvbuf, RINGBUFFER_HVS_RCV_SIZE);
+		rcvbuf = min_t(int, rcvbuf, RINGBUFFER_HVS_MAX_SIZE);
+		rcvbuf = ALIGN(rcvbuf, HV_HYP_PAGE_SIZE);
+	}
+
+	chan->max_pkt_size = HVS_MAX_PKT_SIZE;
+
+	ret = vmbus_open(chan, sndbuf, rcvbuf, NULL, 0, hvs_channel_cb,
+			 conn_from_host ? new : sk);
 	if (ret != 0) {
 		if (conn_from_host) {
 			hvs_new->chan = NULL;
@@ -386,14 +396,21 @@ static void hvs_open_connection(struct vmbus_channel *chan)
 	}
 
 	set_per_channel_state(chan, conn_from_host ? new : sk);
+
+	/* This reference will be dropped by hvs_close_connection(). */
+	sock_hold(conn_from_host ? new : sk);
 	vmbus_set_chn_rescind_callback(chan, hvs_close_connection);
 
+	/* Set the pending send size to max packet size to always get
+	 * notifications from the host when there is enough writable space.
+	 * The host is optimized to send notifications only when the pending
+	 * size boundary is crossed, and not always.
+	 */
+	hvs_set_channel_pending_send_size(chan);
+
 	if (conn_from_host) {
 		new->sk_state = TCP_ESTABLISHED;
-		sk->sk_ack_backlog++;
-
-		hvs_addr_init(&vnew->local_addr, if_type);
-		hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr);
+		sk_acceptq_added(sk);
 
 		hvs_new->vm_srv_id = *if_type;
 		hvs_new->host_srv_id = *if_instance;
@@ -425,6 +442,7 @@ static u32 hvs_get_local_cid(void)
 static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk)
 {
 	struct hvsock *hvs;
+	struct sock *sk = sk_vsock(vsk);
 
 	hvs = kzalloc(sizeof(*hvs), GFP_KERNEL);
 	if (!hvs)
@@ -432,7 +450,8 @@ static int hvs_sock_init(struct vsock_sock *vsk, struct vsock_sock *psk)
 
 	vsk->trans = hvs;
 	hvs->vsk = vsk;
-
+	sk->sk_sndbuf = RINGBUFFER_HVS_SND_SIZE;
+	sk->sk_rcvbuf = RINGBUFFER_HVS_RCV_SIZE;
 	return 0;
 }
 
@@ -452,50 +471,73 @@ static int hvs_connect(struct vsock_sock *vsk)
 	return vmbus_send_tl_connect_request(&h->vm_srv_id, &h->host_srv_id);
 }
 
-static int hvs_shutdown(struct vsock_sock *vsk, int mode)
+static void hvs_shutdown_lock_held(struct hvsock *hvs, int mode)
 {
-	struct sock *sk = sk_vsock(vsk);
 	struct vmpipe_proto_header hdr;
-	struct hvs_send_buf *send_buf;
-	struct hvsock *hvs;
 
+	if (hvs->fin_sent || !hvs->chan)
+		return;
+
+	/* It can't fail: see hvs_channel_writable_bytes(). */
+	(void)__hvs_send_data(hvs->chan, &hdr, 0);
+	hvs->fin_sent = true;
+}
+
+static int hvs_shutdown(struct vsock_sock *vsk, int mode)
+{
 	if (!(mode & SEND_SHUTDOWN))
 		return 0;
 
-	lock_sock(sk);
-
-	hvs = vsk->trans;
-	if (hvs->fin_sent)
-		goto out;
+	hvs_shutdown_lock_held(vsk->trans, mode);
+	return 0;
+}
 
-	send_buf = (struct hvs_send_buf *)&hdr;
+static void hvs_close_timeout(struct work_struct *work)
+{
+	struct vsock_sock *vsk =
+		container_of(work, struct vsock_sock, close_work.work);
+	struct sock *sk = sk_vsock(vsk);
 
-	/* It can't fail: see hvs_channel_writable_bytes(). */
-	(void)hvs_send_data(hvs->chan, send_buf, 0);
+	sock_hold(sk);
+	lock_sock(sk);
+	if (!sock_flag(sk, SOCK_DONE))
+		hvs_do_close_lock_held(vsk, false);
 
-	hvs->fin_sent = true;
-out:
+	vsk->close_work_scheduled = false;
 	release_sock(sk);
-	return 0;
+	sock_put(sk);
 }
 
-static void hvs_release(struct vsock_sock *vsk)
+/* Returns true, if it is safe to remove socket; false otherwise */
+static bool hvs_close_lock_held(struct vsock_sock *vsk)
 {
 	struct sock *sk = sk_vsock(vsk);
-	struct hvsock *hvs = vsk->trans;
-	struct vmbus_channel *chan;
 
-	lock_sock(sk);
+	if (!(sk->sk_state == TCP_ESTABLISHED ||
+	      sk->sk_state == TCP_CLOSING))
+		return true;
 
-	sk->sk_state = TCP_CLOSING;
-	vsock_remove_sock(vsk);
+	if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
+		hvs_shutdown_lock_held(vsk->trans, SHUTDOWN_MASK);
 
-	release_sock(sk);
+	if (sock_flag(sk, SOCK_DONE))
+		return true;
 
-	chan = hvs->chan;
-	if (chan)
-		hvs_shutdown(vsk, RCV_SHUTDOWN | SEND_SHUTDOWN);
+	/* This reference will be dropped by the delayed close routine */
+	sock_hold(sk);
+	INIT_DELAYED_WORK(&vsk->close_work, hvs_close_timeout);
+	vsk->close_work_scheduled = true;
+	schedule_delayed_work(&vsk->close_work, HVS_CLOSE_TIMEOUT);
+	return false;
+}
+
+static void hvs_release(struct vsock_sock *vsk)
+{
+	bool remove_sock;
 
+	remove_sock = hvs_close_lock_held(vsk);
+	if (remove_sock)
+		vsock_remove_sock(vsk);
 }
 
 static void hvs_destruct(struct vsock_sock *vsk)
@@ -507,6 +549,7 @@ static void hvs_destruct(struct vsock_sock *vsk)
 		vmbus_hvsock_device_unregister(chan);
 
 	kfree(hvs);
+	vsk->trans = NULL;
 }
 
 static int hvs_dgram_bind(struct vsock_sock *vsk, struct sockaddr_vm *addr)
@@ -535,12 +578,18 @@ static bool hvs_dgram_allow(u32 cid, u32 port)
 static int hvs_update_recv_data(struct hvsock *hvs)
 {
 	struct hvs_recv_buf *recv_buf;
-	u32 payload_len;
+	u32 pkt_len, payload_len;
+
+	pkt_len = hv_pkt_len(hvs->recv_desc);
+
+	if (pkt_len < HVS_HEADER_LEN)
+		return -EIO;
 
 	recv_buf = (struct hvs_recv_buf *)(hvs->recv_desc + 1);
 	payload_len = recv_buf->hdr.data_size;
 
-	if (payload_len > HVS_MTU_SIZE)
+	if (payload_len > pkt_len - HVS_HEADER_LEN ||
+	    payload_len > HVS_MTU_SIZE)
 		return -EIO;
 
 	if (payload_len == 0)
@@ -566,6 +615,8 @@ static ssize_t hvs_stream_dequeue(struct vsock_sock *vsk, struct msghdr *msg,
 
 	if (need_refill) {
 		hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
+		if (!hvs->recv_desc)
+			return -ENOBUFS;
 		ret = hvs_update_recv_data(hvs);
 		if (ret)
 			return ret;
@@ -598,28 +649,44 @@ static ssize_t hvs_stream_enqueue(struct vsock_sock *vsk, struct msghdr *msg,
 	struct hvsock *hvs = vsk->trans;
 	struct vmbus_channel *chan = hvs->chan;
 	struct hvs_send_buf *send_buf;
-	ssize_t to_write, max_writable, ret;
+	ssize_t to_write, max_writable;
+	ssize_t ret = 0;
+	ssize_t bytes_written = 0;
 
-	BUILD_BUG_ON(sizeof(*send_buf) != PAGE_SIZE_4K);
+	BUILD_BUG_ON(sizeof(*send_buf) != HV_HYP_PAGE_SIZE);
 
 	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;
+	/* Reader(s) could be draining data from the channel as we write.
+	 * Maximize bandwidth, by iterating until the channel is found to be
+	 * full.
+	 */
+	while (len) {
+		max_writable = hvs_channel_writable_bytes(chan);
+		if (!max_writable)
+			break;
+		to_write = min_t(ssize_t, len, max_writable);
+		to_write = min_t(ssize_t, to_write, HVS_SEND_BUF_SIZE);
+		/* memcpy_from_msg is safe for loop as it advances the offsets
+		 * within the message iterator.
+		 */
+		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 = hvs_send_data(hvs->chan, send_buf, to_write);
+		if (ret < 0)
+			goto out;
 
-	ret = to_write;
+		bytes_written += to_write;
+		len -= to_write;
+	}
 out:
+	/* If any data has been sent, return that */
+	if (bytes_written)
+		ret = bytes_written;
 	kfree(send_buf);
 	return ret;
 }
@@ -627,15 +694,26 @@ out:
 static s64 hvs_stream_has_data(struct vsock_sock *vsk)
 {
 	struct hvsock *hvs = vsk->trans;
+	bool need_refill;
 	s64 ret;
 
 	if (hvs->recv_data_len > 0)
-		return 1;
+		return hvs->recv_data_len;
 
 	switch (hvs_channel_readable_payload(hvs->chan)) {
 	case 1:
-		ret = 1;
-		break;
+		need_refill = !hvs->recv_desc;
+		if (!need_refill)
+			return -EIO;
+
+		hvs->recv_desc = hv_pkt_iter_first(hvs->chan);
+		if (!hvs->recv_desc)
+			return -ENOBUFS;
+
+		ret = hvs_update_recv_data(hvs);
+		if (ret)
+			return ret;
+		return hvs->recv_data_len;
 	case 0:
 		vsk->peer_shutdown |= SEND_SHUTDOWN;
 		ret = 0;
@@ -651,23 +729,8 @@ static s64 hvs_stream_has_data(struct vsock_sock *vsk)
 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;
+	return hvs_channel_writable_bytes(hvs->chan);
 }
 
 static u64 hvs_stream_rcvhiwat(struct vsock_sock *vsk)
@@ -684,16 +747,6 @@ static bool hvs_stream_is_active(struct vsock_sock *vsk)
 
 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;
 
@@ -774,37 +827,15 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
 	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)
+static
+int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
 {
-	return -ENOPROTOOPT;
+	return -EOPNOTSUPP;
 }
 
 static struct vsock_transport hvs_transport = {
+	.module                   = THIS_MODULE,
+
 	.get_local_cid            = hvs_get_local_cid,
 
 	.init                     = hvs_sock_init,
@@ -837,14 +868,14 @@ static struct vsock_transport hvs_transport = {
 	.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,
+	.notify_set_rcvlowat      = hvs_notify_set_rcvlowat
 };
 
+static bool hvs_check_transport(struct vsock_sock *vsk)
+{
+	return vsk->transport == &hvs_transport;
+}
+
 static int hvs_probe(struct hv_device *hdev,
 		     const struct hv_vmbus_device_id *dev_id)
 {
@@ -860,12 +891,28 @@ static int hvs_probe(struct hv_device *hdev,
 	return 0;
 }
 
-static int hvs_remove(struct hv_device *hdev)
+static void hvs_remove(struct hv_device *hdev)
 {
 	struct vmbus_channel *chan = hdev->channel;
 
 	vmbus_close(chan);
+}
+
+/* hv_sock connections can not persist across hibernation, and all the hv_sock
+ * channels are forced to be rescinded before hibernation: see
+ * vmbus_bus_suspend(). Here the dummy hvs_suspend() and hvs_resume()
+ * are only needed because hibernation requires that every vmbus device's
+ * driver should have a .suspend and .resume callback: see vmbus_suspend().
+ */
+static int hvs_suspend(struct hv_device *hv_dev)
+{
+	/* Dummy */
+	return 0;
+}
 
+static int hvs_resume(struct hv_device *dev)
+{
+	/* Dummy */
 	return 0;
 }
 
@@ -880,6 +927,8 @@ static struct hv_driver hvs_drv = {
 	.id_table	= id_table,
 	.probe		= hvs_probe,
 	.remove		= hvs_remove,
+	.suspend	= hvs_suspend,
+	.resume		= hvs_resume,
 };
 
 static int __init hvs_init(void)
@@ -893,7 +942,7 @@ static int __init hvs_init(void)
 	if (ret != 0)
 		return ret;
 
-	ret = vsock_core_init(&hvs_transport);
+	ret = vsock_core_register(&hvs_transport, VSOCK_TRANSPORT_F_G2H);
 	if (ret) {
 		vmbus_driver_unregister(&hvs_drv);
 		return ret;
@@ -904,7 +953,7 @@ static int __init hvs_init(void)
 
 static void __exit hvs_exit(void)
 {
-	vsock_core_exit();
+	vsock_core_unregister(&hvs_transport);
 	vmbus_driver_unregister(&hvs_drv);
 }