1 files changed, 363 insertions, 209 deletions

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 3fbc068eaa9b..0298ddc34824 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -1,11 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * vhost transport for vsock
  *
  * Copyright (C) 2013-2015 Red Hat, Inc.
  * Author: Asias He <asias@redhat.com>
  *         Stefan Hajnoczi <stefanha@redhat.com>
- *
- * This work is licensed under the terms of the GNU GPL, version 2.
  */
 #include <linux/miscdevice.h>
 #include <linux/atomic.h>
@@ -21,9 +20,25 @@
 #include "vhost.h"
 
 #define VHOST_VSOCK_DEFAULT_HOST_CID	2
+/* Max number of bytes transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others. */
+#define VHOST_VSOCK_WEIGHT 0x80000
+/* Max number of packets transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others with
+ * small pkts.
+ */
+#define VHOST_VSOCK_PKT_WEIGHT 256
+
+static const int vhost_vsock_bits[] = {
+	VHOST_FEATURES,
+	VIRTIO_F_ACCESS_PLATFORM,
+	VIRTIO_VSOCK_F_SEQPACKET
+};
+
+#define VHOST_VSOCK_FEATURES VHOST_FEATURES_U64(vhost_vsock_bits, 0)
 
 enum {
-	VHOST_VSOCK_FEATURES = VHOST_FEATURES,
+	VHOST_VSOCK_BACKEND_FEATURES = (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2)
 };
 
 /* Used to track all the vhost_vsock instances on the system. */
@@ -38,12 +53,12 @@ struct vhost_vsock {
 	struct hlist_node hash;
 
 	struct vhost_work send_pkt_work;
-	spinlock_t send_pkt_list_lock;
-	struct list_head send_pkt_list;	/* host->guest pending packets */
+	struct sk_buff_head send_pkt_queue; /* host->guest pending packets */
 
 	atomic_t queued_replies;
 
 	u32 guest_cid;
+	bool seqpacket_allow;
 };
 
 static u32 vhost_transport_get_local_cid(void)
@@ -78,51 +93,48 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			    struct vhost_virtqueue *vq)
 {
 	struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
+	int pkts = 0, total_len = 0;
 	bool added = false;
 	bool restart_tx = false;
 
 	mutex_lock(&vq->mutex);
 
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
+		goto out;
+
+	if (!vq_meta_prefetch(vq))
 		goto out;
 
 	/* Avoid further vmexits, we're already processing the virtqueue */
 	vhost_disable_notify(&vsock->dev, vq);
 
-	for (;;) {
-		struct virtio_vsock_pkt *pkt;
+	do {
+		struct virtio_vsock_hdr *hdr;
+		size_t iov_len, payload_len;
 		struct iov_iter iov_iter;
+		u32 flags_to_restore = 0;
+		struct sk_buff *skb;
 		unsigned out, in;
 		size_t nbytes;
-		size_t len;
+		u32 offset;
 		int head;
 
-		spin_lock_bh(&vsock->send_pkt_list_lock);
-		if (list_empty(&vsock->send_pkt_list)) {
-			spin_unlock_bh(&vsock->send_pkt_list_lock);
+		skb = virtio_vsock_skb_dequeue(&vsock->send_pkt_queue);
+
+		if (!skb) {
 			vhost_enable_notify(&vsock->dev, vq);
 			break;
 		}
 
-		pkt = list_first_entry(&vsock->send_pkt_list,
-				       struct virtio_vsock_pkt, list);
-		list_del_init(&pkt->list);
-		spin_unlock_bh(&vsock->send_pkt_list_lock);
-
 		head = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 					 &out, &in, NULL, NULL);
 		if (head < 0) {
-			spin_lock_bh(&vsock->send_pkt_list_lock);
-			list_add(&pkt->list, &vsock->send_pkt_list);
-			spin_unlock_bh(&vsock->send_pkt_list_lock);
+			virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
 			break;
 		}
 
 		if (head == vq->num) {
-			spin_lock_bh(&vsock->send_pkt_list_lock);
-			list_add(&pkt->list, &vsock->send_pkt_list);
-			spin_unlock_bh(&vsock->send_pkt_list_lock);
-
+			virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
 			/* We cannot finish yet if more buffers snuck in while
 			 * re-enabling notify.
 			 */
@@ -134,48 +146,109 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		}
 
 		if (out) {
-			virtio_transport_free_pkt(pkt);
+			kfree_skb(skb);
 			vq_err(vq, "Expected 0 output buffers, got %u\n", out);
 			break;
 		}
 
-		len = iov_length(&vq->iov[out], in);
-		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, len);
+		iov_len = iov_length(&vq->iov[out], in);
+		if (iov_len < sizeof(*hdr)) {
+			kfree_skb(skb);
+			vq_err(vq, "Buffer len [%zu] too small\n", iov_len);
+			break;
+		}
+
+		iov_iter_init(&iov_iter, ITER_DEST, &vq->iov[out], in, iov_len);
+		offset = VIRTIO_VSOCK_SKB_CB(skb)->offset;
+		payload_len = skb->len - offset;
+		hdr = virtio_vsock_hdr(skb);
+
+		/* If the packet is greater than the space available in the
+		 * buffer, we split it using multiple buffers.
+		 */
+		if (payload_len > iov_len - sizeof(*hdr)) {
+			payload_len = iov_len - sizeof(*hdr);
+
+			/* As we are copying pieces of large packet's buffer to
+			 * small rx buffers, headers of packets in rx queue are
+			 * created dynamically and are initialized with header
+			 * of current packet(except length). But in case of
+			 * SOCK_SEQPACKET, we also must clear message delimeter
+			 * bit (VIRTIO_VSOCK_SEQ_EOM) and MSG_EOR bit
+			 * (VIRTIO_VSOCK_SEQ_EOR) if set. Otherwise,
+			 * there will be sequence of packets with these
+			 * bits set. After initialized header will be copied to
+			 * rx buffer, these required bits will be restored.
+			 */
+			if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOM) {
+				hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOM);
+				flags_to_restore |= VIRTIO_VSOCK_SEQ_EOM;
+
+				if (le32_to_cpu(hdr->flags) & VIRTIO_VSOCK_SEQ_EOR) {
+					hdr->flags &= ~cpu_to_le32(VIRTIO_VSOCK_SEQ_EOR);
+					flags_to_restore |= VIRTIO_VSOCK_SEQ_EOR;
+				}
+			}
+		}
+
+		/* Set the correct length in the header */
+		hdr->len = cpu_to_le32(payload_len);
 
-		nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
-		if (nbytes != sizeof(pkt->hdr)) {
-			virtio_transport_free_pkt(pkt);
+		nbytes = copy_to_iter(hdr, sizeof(*hdr), &iov_iter);
+		if (nbytes != sizeof(*hdr)) {
+			kfree_skb(skb);
 			vq_err(vq, "Faulted on copying pkt hdr\n");
 			break;
 		}
 
-		nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter);
-		if (nbytes != pkt->len) {
-			virtio_transport_free_pkt(pkt);
+		if (skb_copy_datagram_iter(skb,
+					   offset,
+					   &iov_iter,
+					   payload_len)) {
+			kfree_skb(skb);
 			vq_err(vq, "Faulted on copying pkt buf\n");
 			break;
 		}
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
-		added = true;
-
-		if (pkt->reply) {
-			int val;
+		/* Deliver to monitoring devices all packets that we
+		 * will transmit.
+		 */
+		virtio_transport_deliver_tap_pkt(skb);
 
-			val = atomic_dec_return(&vsock->queued_replies);
+		vhost_add_used(vq, head, sizeof(*hdr) + payload_len);
+		added = true;
 
-			/* Do we have resources to resume tx processing? */
-			if (val + 1 == tx_vq->num)
-				restart_tx = true;
-		}
+		VIRTIO_VSOCK_SKB_CB(skb)->offset += payload_len;
+		total_len += payload_len;
 
-		/* Deliver to monitoring devices all correctly transmitted
-		 * packets.
+		/* If we didn't send all the payload we can requeue the packet
+		 * to send it with the next available buffer.
 		 */
-		virtio_transport_deliver_tap_pkt(pkt);
+		if (VIRTIO_VSOCK_SKB_CB(skb)->offset < skb->len) {
+			hdr->flags |= cpu_to_le32(flags_to_restore);
 
-		virtio_transport_free_pkt(pkt);
-	}
+			/* We are queueing the same skb to handle
+			 * the remaining bytes, and we want to deliver it
+			 * to monitoring devices in the next iteration.
+			 */
+			virtio_vsock_skb_clear_tap_delivered(skb);
+			virtio_vsock_skb_queue_head(&vsock->send_pkt_queue, skb);
+		} else {
+			if (virtio_vsock_skb_reply(skb)) {
+				int val;
+
+				val = atomic_dec_return(&vsock->queued_replies);
+
+				/* Do we have resources to resume tx
+				 * processing?
+				 */
+				if (val + 1 == tx_vq->num)
+					restart_tx = true;
+			}
+
+			virtio_transport_consume_skb_sent(skb, true);
+		}
+	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
 		vhost_signal(&vsock->dev, vq);
 
@@ -198,29 +271,27 @@ static void vhost_transport_send_pkt_work(struct vhost_work *work)
 }
 
 static int
-vhost_transport_send_pkt(struct virtio_vsock_pkt *pkt)
+vhost_transport_send_pkt(struct sk_buff *skb)
 {
+	struct virtio_vsock_hdr *hdr = virtio_vsock_hdr(skb);
 	struct vhost_vsock *vsock;
-	int len = pkt->len;
+	int len = skb->len;
 
 	rcu_read_lock();
 
 	/* Find the vhost_vsock according to guest context id  */
-	vsock = vhost_vsock_get(le64_to_cpu(pkt->hdr.dst_cid));
+	vsock = vhost_vsock_get(le64_to_cpu(hdr->dst_cid));
 	if (!vsock) {
 		rcu_read_unlock();
-		virtio_transport_free_pkt(pkt);
+		kfree_skb(skb);
 		return -ENODEV;
 	}
 
-	if (pkt->reply)
+	if (virtio_vsock_skb_reply(skb))
 		atomic_inc(&vsock->queued_replies);
 
-	spin_lock_bh(&vsock->send_pkt_list_lock);
-	list_add_tail(&pkt->list, &vsock->send_pkt_list);
-	spin_unlock_bh(&vsock->send_pkt_list_lock);
-
-	vhost_work_queue(&vsock->dev, &vsock->send_pkt_work);
+	virtio_vsock_skb_queue_tail(&vsock->send_pkt_queue, skb);
+	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
 
 	rcu_read_unlock();
 	return len;
@@ -230,10 +301,8 @@ static int
 vhost_transport_cancel_pkt(struct vsock_sock *vsk)
 {
 	struct vhost_vsock *vsock;
-	struct virtio_vsock_pkt *pkt, *n;
 	int cnt = 0;
 	int ret = -ENODEV;
-	LIST_HEAD(freeme);
 
 	rcu_read_lock();
 
@@ -242,20 +311,7 @@ vhost_transport_cancel_pkt(struct vsock_sock *vsk)
 	if (!vsock)
 		goto out;
 
-	spin_lock_bh(&vsock->send_pkt_list_lock);
-	list_for_each_entry_safe(pkt, n, &vsock->send_pkt_list, list) {
-		if (pkt->vsk != vsk)
-			continue;
-		list_move(&pkt->list, &freeme);
-	}
-	spin_unlock_bh(&vsock->send_pkt_list_lock);
-
-	list_for_each_entry_safe(pkt, n, &freeme, list) {
-		if (pkt->reply)
-			cnt++;
-		list_del(&pkt->list);
-		virtio_transport_free_pkt(pkt);
-	}
+	cnt = virtio_transport_purge_skbs(vsk, &vsock->send_pkt_queue);
 
 	if (cnt) {
 		struct vhost_virtqueue *tx_vq = &vsock->vqs[VSOCK_VQ_TX];
@@ -272,12 +328,14 @@ out:
 	return ret;
 }
 
-static struct virtio_vsock_pkt *
-vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
+static struct sk_buff *
+vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 		      unsigned int out, unsigned int in)
 {
-	struct virtio_vsock_pkt *pkt;
+	struct virtio_vsock_hdr *hdr;
 	struct iov_iter iov_iter;
+	struct sk_buff *skb;
+	size_t payload_len;
 	size_t nbytes;
 	size_t len;
 
@@ -286,49 +344,49 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
-	pkt = kzalloc(sizeof(*pkt), GFP_KERNEL);
-	if (!pkt)
+	len = iov_length(vq->iov, out);
+
+	if (len < VIRTIO_VSOCK_SKB_HEADROOM ||
+	    len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM)
 		return NULL;
 
-	len = iov_length(vq->iov, out);
-	iov_iter_init(&iov_iter, WRITE, vq->iov, out, len);
+	/* len contains both payload and hdr */
+	skb = virtio_vsock_alloc_skb(len, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	iov_iter_init(&iov_iter, ITER_SOURCE, vq->iov, out, len);
 
-	nbytes = copy_from_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
-	if (nbytes != sizeof(pkt->hdr)) {
+	hdr = virtio_vsock_hdr(skb);
+	nbytes = copy_from_iter(hdr, sizeof(*hdr), &iov_iter);
+	if (nbytes != sizeof(*hdr)) {
 		vq_err(vq, "Expected %zu bytes for pkt->hdr, got %zu bytes\n",
-		       sizeof(pkt->hdr), nbytes);
-		kfree(pkt);
+		       sizeof(*hdr), nbytes);
+		kfree_skb(skb);
 		return NULL;
 	}
 
-	if (le16_to_cpu(pkt->hdr.type) == VIRTIO_VSOCK_TYPE_STREAM)
-		pkt->len = le32_to_cpu(pkt->hdr.len);
+	payload_len = le32_to_cpu(hdr->len);
 
 	/* No payload */
-	if (!pkt->len)
-		return pkt;
+	if (!payload_len)
+		return skb;
 
-	/* The pkt is too big */
-	if (pkt->len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
-		kfree(pkt);
+	/* The pkt is too big or the length in the header is invalid */
+	if (payload_len + sizeof(*hdr) > len) {
+		kfree_skb(skb);
 		return NULL;
 	}
 
-	pkt->buf = kmalloc(pkt->len, GFP_KERNEL);
-	if (!pkt->buf) {
-		kfree(pkt);
-		return NULL;
-	}
+	virtio_vsock_skb_put(skb, payload_len);
 
-	nbytes = copy_from_iter(pkt->buf, pkt->len, &iov_iter);
-	if (nbytes != pkt->len) {
-		vq_err(vq, "Expected %u byte payload, got %zu bytes\n",
-		       pkt->len, nbytes);
-		virtio_transport_free_pkt(pkt);
+	if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) {
+		vq_err(vq, "Failed to copy %zu byte payload\n", payload_len);
+		kfree_skb(skb);
 		return NULL;
 	}
 
-	return pkt;
+	return skb;
 }
 
 /* Is there space left for replies to rx packets? */
@@ -343,25 +401,105 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
 	return val < vq->num;
 }
 
+static bool vhost_transport_msgzerocopy_allow(void)
+{
+	return true;
+}
+
+static bool vhost_transport_seqpacket_allow(u32 remote_cid);
+
+static struct virtio_transport vhost_transport = {
+	.transport = {
+		.module                   = THIS_MODULE,
+
+		.get_local_cid            = vhost_transport_get_local_cid,
+
+		.init                     = virtio_transport_do_socket_init,
+		.destruct                 = virtio_transport_destruct,
+		.release                  = virtio_transport_release,
+		.connect                  = virtio_transport_connect,
+		.shutdown                 = virtio_transport_shutdown,
+		.cancel_pkt               = vhost_transport_cancel_pkt,
+
+		.dgram_enqueue            = virtio_transport_dgram_enqueue,
+		.dgram_dequeue            = virtio_transport_dgram_dequeue,
+		.dgram_bind               = virtio_transport_dgram_bind,
+		.dgram_allow              = virtio_transport_dgram_allow,
+
+		.stream_enqueue           = virtio_transport_stream_enqueue,
+		.stream_dequeue           = virtio_transport_stream_dequeue,
+		.stream_has_data          = virtio_transport_stream_has_data,
+		.stream_has_space         = virtio_transport_stream_has_space,
+		.stream_rcvhiwat          = virtio_transport_stream_rcvhiwat,
+		.stream_is_active         = virtio_transport_stream_is_active,
+		.stream_allow             = virtio_transport_stream_allow,
+
+		.seqpacket_dequeue        = virtio_transport_seqpacket_dequeue,
+		.seqpacket_enqueue        = virtio_transport_seqpacket_enqueue,
+		.seqpacket_allow          = vhost_transport_seqpacket_allow,
+		.seqpacket_has_data       = virtio_transport_seqpacket_has_data,
+
+		.msgzerocopy_allow        = vhost_transport_msgzerocopy_allow,
+
+		.notify_poll_in           = virtio_transport_notify_poll_in,
+		.notify_poll_out          = virtio_transport_notify_poll_out,
+		.notify_recv_init         = virtio_transport_notify_recv_init,
+		.notify_recv_pre_block    = virtio_transport_notify_recv_pre_block,
+		.notify_recv_pre_dequeue  = virtio_transport_notify_recv_pre_dequeue,
+		.notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
+		.notify_send_init         = virtio_transport_notify_send_init,
+		.notify_send_pre_block    = virtio_transport_notify_send_pre_block,
+		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
+		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
+		.notify_buffer_size       = virtio_transport_notify_buffer_size,
+		.notify_set_rcvlowat      = virtio_transport_notify_set_rcvlowat,
+
+		.unsent_bytes             = virtio_transport_unsent_bytes,
+
+		.read_skb = virtio_transport_read_skb,
+	},
+
+	.send_pkt = vhost_transport_send_pkt,
+};
+
+static bool vhost_transport_seqpacket_allow(u32 remote_cid)
+{
+	struct vhost_vsock *vsock;
+	bool seqpacket_allow = false;
+
+	rcu_read_lock();
+	vsock = vhost_vsock_get(remote_cid);
+
+	if (vsock)
+		seqpacket_allow = vsock->seqpacket_allow;
+
+	rcu_read_unlock();
+
+	return seqpacket_allow;
+}
+
 static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 {
 	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
 						  poll.work);
 	struct vhost_vsock *vsock = container_of(vq->dev, struct vhost_vsock,
 						 dev);
-	struct virtio_vsock_pkt *pkt;
-	int head;
+	int head, pkts = 0, total_len = 0;
 	unsigned int out, in;
+	struct sk_buff *skb;
 	bool added = false;
 
 	mutex_lock(&vq->mutex);
 
-	if (!vq->private_data)
+	if (!vhost_vq_get_backend(vq))
+		goto out;
+
+	if (!vq_meta_prefetch(vq))
 		goto out;
 
 	vhost_disable_notify(&vsock->dev, vq);
-	for (;;) {
-		u32 len;
+	do {
+		struct virtio_vsock_hdr *hdr;
 
 		if (!vhost_vsock_more_replies(vsock)) {
 			/* Stop tx until the device processes already
@@ -384,26 +522,30 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 			break;
 		}
 
-		pkt = vhost_vsock_alloc_pkt(vq, out, in);
-		if (!pkt) {
+		skb = vhost_vsock_alloc_skb(vq, out, in);
+		if (!skb) {
 			vq_err(vq, "Faulted on pkt\n");
 			continue;
 		}
 
-		len = pkt->len;
+		total_len += sizeof(*hdr) + skb->len;
 
 		/* Deliver to monitoring devices all received packets */
-		virtio_transport_deliver_tap_pkt(pkt);
+		virtio_transport_deliver_tap_pkt(skb);
+
+		hdr = virtio_vsock_hdr(skb);
 
 		/* Only accept correctly addressed packets */
-		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
-			virtio_transport_recv_pkt(pkt);
+		if (le64_to_cpu(hdr->src_cid) == vsock->guest_cid &&
+		    le64_to_cpu(hdr->dst_cid) ==
+		    vhost_transport_get_local_cid())
+			virtio_transport_recv_pkt(&vhost_transport, skb);
 		else
-			virtio_transport_free_pkt(pkt);
+			kfree_skb(skb);
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + len);
+		vhost_add_used(vq, head, 0);
 		added = true;
-	}
+	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 
 no_more_replies:
 	if (added)
@@ -445,8 +587,8 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 			goto err_vq;
 		}
 
-		if (!vq->private_data) {
-			vq->private_data = vsock;
+		if (!vhost_vq_get_backend(vq)) {
+			vhost_vq_set_backend(vq, vsock);
 			ret = vhost_vq_init_access(vq);
 			if (ret)
 				goto err_vq;
@@ -455,18 +597,23 @@ static int vhost_vsock_start(struct vhost_vsock *vsock)
 		mutex_unlock(&vq->mutex);
 	}
 
+	/* Some packets may have been queued before the device was started,
+	 * let's kick the send worker to send them.
+	 */
+	vhost_vq_work_queue(&vsock->vqs[VSOCK_VQ_RX], &vsock->send_pkt_work);
+
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
 
 err_vq:
-	vq->private_data = NULL;
+	vhost_vq_set_backend(vq, NULL);
 	mutex_unlock(&vq->mutex);
 
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
 		vq = &vsock->vqs[i];
 
 		mutex_lock(&vq->mutex);
-		vq->private_data = NULL;
+		vhost_vq_set_backend(vq, NULL);
 		mutex_unlock(&vq->mutex);
 	}
 err:
@@ -474,22 +621,24 @@ err:
 	return ret;
 }
 
-static int vhost_vsock_stop(struct vhost_vsock *vsock)
+static int vhost_vsock_stop(struct vhost_vsock *vsock, bool check_owner)
 {
 	size_t i;
-	int ret;
+	int ret = 0;
 
 	mutex_lock(&vsock->dev.mutex);
 
-	ret = vhost_dev_check_owner(&vsock->dev);
-	if (ret)
-		goto err;
+	if (check_owner) {
+		ret = vhost_dev_check_owner(&vsock->dev);
+		if (ret)
+			goto err;
+	}
 
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
 		struct vhost_virtqueue *vq = &vsock->vqs[i];
 
 		mutex_lock(&vq->mutex);
-		vq->private_data = NULL;
+		vhost_vq_set_backend(vq, NULL);
 		mutex_unlock(&vq->mutex);
 	}
 
@@ -523,6 +672,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	}
 
 	vsock->guest_cid = 0; /* no CID assigned yet */
+	vsock->seqpacket_allow = false;
 
 	atomic_set(&vsock->queued_replies, 0);
 
@@ -531,11 +681,12 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 	vsock->vqs[VSOCK_VQ_TX].handle_kick = vhost_vsock_handle_tx_kick;
 	vsock->vqs[VSOCK_VQ_RX].handle_kick = vhost_vsock_handle_rx_kick;
 
-	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs));
+	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs),
+		       UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT,
+		       VHOST_VSOCK_WEIGHT, true, NULL);
 
 	file->private_data = vsock;
-	spin_lock_init(&vsock->send_pkt_list_lock);
-	INIT_LIST_HEAD(&vsock->send_pkt_list);
+	skb_queue_head_init(&vsock->send_pkt_queue);
 	vhost_work_init(&vsock->send_pkt_work, vhost_transport_send_pkt_work);
 	return 0;
 
@@ -546,12 +697,7 @@ out:
 
 static void vhost_vsock_flush(struct vhost_vsock *vsock)
 {
-	int i;
-
-	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++)
-		if (vsock->vqs[i].handle_kick)
-			vhost_poll_flush(&vsock->vqs[i].poll);
-	vhost_work_flush(&vsock->dev, &vsock->send_pkt_work);
+	vhost_dev_flush(&vsock->dev);
 }
 
 static void vhost_vsock_reset_orphans(struct sock *sk)
@@ -577,7 +723,7 @@ static void vhost_vsock_reset_orphans(struct sock *sk)
 	vsk->peer_shutdown = SHUTDOWN_MASK;
 	sk->sk_state = SS_UNCONNECTED;
 	sk->sk_err = ECONNRESET;
-	sk->sk_error_report(sk);
+	sk_error_report(sk);
 }
 
 static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
@@ -594,22 +740,19 @@ static int vhost_vsock_dev_release(struct inode *inode, struct file *file)
 
 	/* Iterating over all connections for all CIDs to find orphans is
 	 * inefficient.  Room for improvement here. */
-	vsock_for_each_connected_socket(vhost_vsock_reset_orphans);
+	vsock_for_each_connected_socket(&vhost_transport.transport,
+					vhost_vsock_reset_orphans);
 
-	vhost_vsock_stop(vsock);
+	/* Don't check the owner, because we are in the release path, so we
+	 * need to stop the vsock device in any case.
+	 * vhost_vsock_stop() can not fail in this case, so we don't need to
+	 * check the return code.
+	 */
+	vhost_vsock_stop(vsock, false);
 	vhost_vsock_flush(vsock);
 	vhost_dev_stop(&vsock->dev);
 
-	spin_lock_bh(&vsock->send_pkt_list_lock);
-	while (!list_empty(&vsock->send_pkt_list)) {
-		struct virtio_vsock_pkt *pkt;
-
-		pkt = list_first_entry(&vsock->send_pkt_list,
-				struct virtio_vsock_pkt, list);
-		list_del_init(&pkt->list);
-		virtio_transport_free_pkt(pkt);
-	}
-	spin_unlock_bh(&vsock->send_pkt_list_lock);
+	virtio_vsock_skb_queue_purge(&vsock->send_pkt_queue);
 
 	vhost_dev_cleanup(&vsock->dev);
 	kfree(vsock->dev.vqs);
@@ -630,6 +773,12 @@ static int vhost_vsock_set_cid(struct vhost_vsock *vsock, u64 guest_cid)
 	if (guest_cid > U32_MAX)
 		return -EINVAL;
 
+	/* Refuse if CID is assigned to the guest->host transport (i.e. nested
+	 * VM), to make the loopback work.
+	 */
+	if (vsock_find_cid(guest_cid))
+		return -EADDRINUSE;
+
 	/* Refuse if CID is already in use */
 	mutex_lock(&vhost_vsock_mutex);
 	other = vhost_vsock_get(guest_cid);
@@ -659,10 +808,16 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
 	mutex_lock(&vsock->dev.mutex);
 	if ((features & (1 << VHOST_F_LOG_ALL)) &&
 	    !vhost_log_access_ok(&vsock->dev)) {
-		mutex_unlock(&vsock->dev.mutex);
-		return -EFAULT;
+		goto err;
+	}
+
+	if ((features & (1ULL << VIRTIO_F_ACCESS_PLATFORM))) {
+		if (vhost_init_device_iotlb(&vsock->dev))
+			goto err;
 	}
 
+	vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET);
+
 	for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
 		vq = &vsock->vqs[i];
 		mutex_lock(&vq->mutex);
@@ -671,6 +826,10 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
 	}
 	mutex_unlock(&vsock->dev.mutex);
 	return 0;
+
+err:
+	mutex_unlock(&vsock->dev.mutex);
+	return -EFAULT;
 }
 
 static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
@@ -694,7 +853,7 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 		if (start)
 			return vhost_vsock_start(vsock);
 		else
-			return vhost_vsock_stop(vsock);
+			return vhost_vsock_stop(vsock, true);
 	case VHOST_GET_FEATURES:
 		features = VHOST_VSOCK_FEATURES;
 		if (copy_to_user(argp, &features, sizeof(features)))
@@ -704,6 +863,18 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 		if (copy_from_user(&features, argp, sizeof(features)))
 			return -EFAULT;
 		return vhost_vsock_set_features(vsock, features);
+	case VHOST_GET_BACKEND_FEATURES:
+		features = VHOST_VSOCK_BACKEND_FEATURES;
+		if (copy_to_user(argp, &features, sizeof(features)))
+			return -EFAULT;
+		return 0;
+	case VHOST_SET_BACKEND_FEATURES:
+		if (copy_from_user(&features, argp, sizeof(features)))
+			return -EFAULT;
+		if (features & ~VHOST_VSOCK_BACKEND_FEATURES)
+			return -EOPNOTSUPP;
+		vhost_set_backend_features(&vsock->dev, features);
+		return 0;
 	default:
 		mutex_lock(&vsock->dev.mutex);
 		r = vhost_dev_ioctl(&vsock->dev, ioctl, argp);
@@ -716,13 +887,33 @@ static long vhost_vsock_dev_ioctl(struct file *f, unsigned int ioctl,
 	}
 }
 
-#ifdef CONFIG_COMPAT
-static long vhost_vsock_dev_compat_ioctl(struct file *f, unsigned int ioctl,
-					 unsigned long arg)
+static ssize_t vhost_vsock_chr_read_iter(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+	int noblock = file->f_flags & O_NONBLOCK;
+
+	return vhost_chr_read_iter(dev, to, noblock);
+}
+
+static ssize_t vhost_vsock_chr_write_iter(struct kiocb *iocb,
+					struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+
+	return vhost_chr_write_iter(dev, from);
+}
+
+static __poll_t vhost_vsock_chr_poll(struct file *file, poll_table *wait)
 {
-	return vhost_vsock_dev_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
+	struct vhost_vsock *vsock = file->private_data;
+	struct vhost_dev *dev = &vsock->dev;
+
+	return vhost_chr_poll(file, dev, wait);
 }
-#endif
 
 static const struct file_operations vhost_vsock_fops = {
 	.owner          = THIS_MODULE,
@@ -730,9 +921,10 @@ static const struct file_operations vhost_vsock_fops = {
 	.release        = vhost_vsock_dev_release,
 	.llseek		= noop_llseek,
 	.unlocked_ioctl = vhost_vsock_dev_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl   = vhost_vsock_dev_compat_ioctl,
-#endif
+	.compat_ioctl   = compat_ptr_ioctl,
+	.read_iter      = vhost_vsock_chr_read_iter,
+	.write_iter     = vhost_vsock_chr_write_iter,
+	.poll           = vhost_vsock_chr_poll,
 };
 
 static struct miscdevice vhost_vsock_misc = {
@@ -741,66 +933,28 @@ static struct miscdevice vhost_vsock_misc = {
 	.fops = &vhost_vsock_fops,
 };
 
-static struct virtio_transport vhost_transport = {
-	.transport = {
-		.get_local_cid            = vhost_transport_get_local_cid,
-
-		.init                     = virtio_transport_do_socket_init,
-		.destruct                 = virtio_transport_destruct,
-		.release                  = virtio_transport_release,
-		.connect                  = virtio_transport_connect,
-		.shutdown                 = virtio_transport_shutdown,
-		.cancel_pkt               = vhost_transport_cancel_pkt,
-
-		.dgram_enqueue            = virtio_transport_dgram_enqueue,
-		.dgram_dequeue            = virtio_transport_dgram_dequeue,
-		.dgram_bind               = virtio_transport_dgram_bind,
-		.dgram_allow              = virtio_transport_dgram_allow,
-
-		.stream_enqueue           = virtio_transport_stream_enqueue,
-		.stream_dequeue           = virtio_transport_stream_dequeue,
-		.stream_has_data          = virtio_transport_stream_has_data,
-		.stream_has_space         = virtio_transport_stream_has_space,
-		.stream_rcvhiwat          = virtio_transport_stream_rcvhiwat,
-		.stream_is_active         = virtio_transport_stream_is_active,
-		.stream_allow             = virtio_transport_stream_allow,
-
-		.notify_poll_in           = virtio_transport_notify_poll_in,
-		.notify_poll_out          = virtio_transport_notify_poll_out,
-		.notify_recv_init         = virtio_transport_notify_recv_init,
-		.notify_recv_pre_block    = virtio_transport_notify_recv_pre_block,
-		.notify_recv_pre_dequeue  = virtio_transport_notify_recv_pre_dequeue,
-		.notify_recv_post_dequeue = virtio_transport_notify_recv_post_dequeue,
-		.notify_send_init         = virtio_transport_notify_send_init,
-		.notify_send_pre_block    = virtio_transport_notify_send_pre_block,
-		.notify_send_pre_enqueue  = virtio_transport_notify_send_pre_enqueue,
-		.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
-
-		.set_buffer_size          = virtio_transport_set_buffer_size,
-		.set_min_buffer_size      = virtio_transport_set_min_buffer_size,
-		.set_max_buffer_size      = virtio_transport_set_max_buffer_size,
-		.get_buffer_size          = virtio_transport_get_buffer_size,
-		.get_min_buffer_size      = virtio_transport_get_min_buffer_size,
-		.get_max_buffer_size      = virtio_transport_get_max_buffer_size,
-	},
-
-	.send_pkt = vhost_transport_send_pkt,
-};
-
 static int __init vhost_vsock_init(void)
 {
 	int ret;
 
-	ret = vsock_core_init(&vhost_transport.transport);
+	ret = vsock_core_register(&vhost_transport.transport,
+				  VSOCK_TRANSPORT_F_H2G);
 	if (ret < 0)
 		return ret;
-	return misc_register(&vhost_vsock_misc);
+
+	ret = misc_register(&vhost_vsock_misc);
+	if (ret) {
+		vsock_core_unregister(&vhost_transport.transport);
+		return ret;
+	}
+
+	return 0;
 };
 
 static void __exit vhost_vsock_exit(void)
 {
 	misc_deregister(&vhost_vsock_misc);
-	vsock_core_exit();
+	vsock_core_unregister(&vhost_transport.transport);
 };
 
 module_init(vhost_vsock_init);