+ struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
+ unsigned uninitialized_var(in), log;
+ struct vhost_log *vq_log;
+ struct msghdr msg = {
+ .msg_name = NULL,
+ .msg_namelen = 0,
+ .msg_control = NULL, /* FIXME: get and handle RX aux data. */
+ .msg_controllen = 0,
+ .msg_iov = vq->iov,
+ .msg_flags = MSG_DONTWAIT,
+ };
+
+ struct virtio_net_hdr_mrg_rxbuf hdr = {
+ .hdr.flags = 0,
+ .hdr.gso_type = VIRTIO_NET_HDR_GSO_NONE
+ };
+
+ size_t total_len = 0;
+ int err, headcount;
+ size_t vhost_hlen, sock_hlen;
+ size_t vhost_len, sock_len;
+ struct socket *sock = rcu_dereference(vq->private_data);
+ if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
+ return;
+
+ use_mm(net->dev.mm);
+ mutex_lock(&vq->mutex);
+ vhost_disable_notify(vq);
+ vhost_hlen = vq->vhost_hlen;
+ sock_hlen = vq->sock_hlen;
+
+ vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
+ vq->log : NULL;
+
+ while ((sock_len = peek_head_len(sock->sk))) {
+ sock_len += sock_hlen;
+ vhost_len = sock_len + vhost_hlen;
+ headcount = get_rx_bufs(vq, vq->heads, vhost_len,
+ &in, vq_log, &log);
+ /* On error, stop handling until the next kick. */
+ if (unlikely(headcount < 0))
+ break;
+ /* OK, now we need to know about added descriptors. */
+ if (!headcount) {
+ if (unlikely(vhost_enable_notify(vq))) {
+ /* They have slipped one in as we were
+ * doing that: check again. */
+ vhost_disable_notify(vq);
+ continue;
+ }
+ /* Nothing new? Wait for eventfd to tell us
+ * they refilled. */
+ break;
+ }
+ /* We don't need to be notified again. */
+ if (unlikely((vhost_hlen)))
+ /* Skip header. TODO: support TSO. */
+ move_iovec_hdr(vq->iov, vq->hdr, vhost_hlen, in);
+ else
+ /* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
+ * needed because sendmsg can modify msg_iov. */
+ copy_iovec_hdr(vq->iov, vq->hdr, sock_hlen, in);
+ msg.msg_iovlen = in;
+ err = sock->ops->recvmsg(NULL, sock, &msg,
+ sock_len, MSG_DONTWAIT | MSG_TRUNC);
+ /* Userspace might have consumed the packet meanwhile:
+ * it's not supposed to do this usually, but might be hard
+ * to prevent. Discard data we got (if any) and keep going. */
+ if (unlikely(err != sock_len)) {
+ pr_debug("Discarded rx packet: "
+ " len %d, expected %zd\n", err, sock_len);
+ vhost_discard_vq_desc(vq, headcount);
+ continue;
+ }
+ if (unlikely(vhost_hlen) &&
+ memcpy_toiovecend(vq->hdr, (unsigned char *)&hdr, 0,
+ vhost_hlen)) {
+ vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
+ vq->iov->iov_base);
+ break;
+ }
+ /* TODO: Should check and handle checksum. */
+ if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF) &&
+ memcpy_toiovecend(vq->hdr, (unsigned char *)&headcount,
+ offsetof(typeof(hdr), num_buffers),
+ sizeof hdr.num_buffers)) {
+ vq_err(vq, "Failed num_buffers write");
+ vhost_discard_vq_desc(vq, headcount);
+ break;
+ }
+ vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+ headcount);
+ if (unlikely(vq_log))
+ vhost_log_write(vq, vq_log, log, vhost_len);
+ total_len += vhost_len;
+ if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+ vhost_poll_queue(&vq->poll);
+ break;
+ }
+ }
+
+ mutex_unlock(&vq->mutex);
+ unuse_mm(net->dev.mm);
+}
+
+static void handle_rx(struct vhost_net *net)
+{
+ if (vhost_has_feature(&net->dev, VIRTIO_NET_F_MRG_RXBUF))
+ handle_rx_mergeable(net);
+ else
+ handle_rx_big(net);
+}
+
+static void handle_tx_kick(struct vhost_work *work)
+{
+ struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
+ poll.work);
+ struct vhost_net *net = container_of(vq->dev, struct vhost_net, dev);
+