1 files changed, 107 insertions, 79 deletions

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 6a50e1d0529c..c2d7d57e98cf 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -102,7 +102,7 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 		struct iov_iter iov_iter;
 		unsigned out, in;
 		size_t nbytes;
-		size_t len;
+		size_t iov_len, payload_len;
 		int head;
 
 		spin_lock_bh(&vsock->send_pkt_list_lock);
@@ -147,8 +147,24 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			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(pkt->hdr)) {
+			virtio_transport_free_pkt(pkt);
+			vq_err(vq, "Buffer len [%zu] too small\n", iov_len);
+			break;
+		}
+
+		iov_iter_init(&iov_iter, READ, &vq->iov[out], in, iov_len);
+		payload_len = pkt->len - pkt->off;
+
+		/* If the packet is greater than the space available in the
+		 * buffer, we split it using multiple buffers.
+		 */
+		if (payload_len > iov_len - sizeof(pkt->hdr))
+			payload_len = iov_len - sizeof(pkt->hdr);
+
+		/* Set the correct length in the header */
+		pkt->hdr.len = cpu_to_le32(payload_len);
 
 		nbytes = copy_to_iter(&pkt->hdr, sizeof(pkt->hdr), &iov_iter);
 		if (nbytes != sizeof(pkt->hdr)) {
@@ -157,33 +173,47 @@ vhost_transport_do_send_pkt(struct vhost_vsock *vsock,
 			break;
 		}
 
-		nbytes = copy_to_iter(pkt->buf, pkt->len, &iov_iter);
-		if (nbytes != pkt->len) {
+		nbytes = copy_to_iter(pkt->buf + pkt->off, payload_len,
+				      &iov_iter);
+		if (nbytes != payload_len) {
 			virtio_transport_free_pkt(pkt);
 			vq_err(vq, "Faulted on copying pkt buf\n");
 			break;
 		}
 
-		vhost_add_used(vq, head, sizeof(pkt->hdr) + pkt->len);
+		vhost_add_used(vq, head, sizeof(pkt->hdr) + payload_len);
 		added = true;
 
-		if (pkt->reply) {
-			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;
-		}
-
 		/* Deliver to monitoring devices all correctly transmitted
 		 * packets.
 		 */
 		virtio_transport_deliver_tap_pkt(pkt);
 
-		total_len += pkt->len;
-		virtio_transport_free_pkt(pkt);
+		pkt->off += payload_len;
+		total_len += payload_len;
+
+		/* If we didn't send all the payload we can requeue the packet
+		 * to send it with the next available buffer.
+		 */
+		if (pkt->off < pkt->len) {
+			spin_lock_bh(&vsock->send_pkt_list_lock);
+			list_add(&pkt->list, &vsock->send_pkt_list);
+			spin_unlock_bh(&vsock->send_pkt_list_lock);
+		} else {
+			if (pkt->reply) {
+				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_free_pkt(pkt);
+		}
 	} while(likely(!vhost_exceeds_weight(vq, ++pkts, total_len)));
 	if (added)
 		vhost_signal(&vsock->dev, vq);
@@ -329,6 +359,8 @@ vhost_vsock_alloc_pkt(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
+	pkt->buf_len = pkt->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",
@@ -352,6 +384,49 @@ static bool vhost_vsock_more_replies(struct vhost_vsock *vsock)
 	return val < vq->num;
 }
 
+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,
+
+		.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,
+
+	},
+
+	.send_pkt = vhost_transport_send_pkt,
+};
+
 static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 {
 	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
@@ -405,8 +480,10 @@ static void vhost_vsock_handle_tx_kick(struct vhost_work *work)
 		virtio_transport_deliver_tap_pkt(pkt);
 
 		/* 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(pkt->hdr.src_cid) == vsock->guest_cid &&
+		    le64_to_cpu(pkt->hdr.dst_cid) ==
+		    vhost_transport_get_local_cid())
+			virtio_transport_recv_pkt(&vhost_transport, pkt);
 		else
 			virtio_transport_free_pkt(pkt);
 
@@ -643,6 +720,12 @@ 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);
@@ -729,23 +812,13 @@ 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)
-{
-	return vhost_vsock_dev_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
-}
-#endif
-
 static const struct file_operations vhost_vsock_fops = {
 	.owner          = THIS_MODULE,
 	.open           = vhost_vsock_dev_open,
 	.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,
 };
 
 static struct miscdevice vhost_vsock_misc = {
@@ -754,57 +827,12 @@ 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);
@@ -813,7 +841,7 @@ static int __init vhost_vsock_init(void)
 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);