Linux kernel Vhost-net 和 Virtio-net代码详解

场景

Host上运行qemu kvm虚拟机，其中虚拟机的网卡类型为virtio-net，而Host上virtio-net backend使用vhost-net

数据包进入虚拟机代码分析

首先看vhost-net模块注册，主要使用linux内核提供的内存注册机制，这部分开发过linux kernel的人都应该

很了解啦

static struct miscdevice vhost_net_misc = {
	.minor = VHOST_NET_MINOR,
	.name = "vhost-net",
	.fops = &vhost_net_fops,
};

static int vhost_net_init(void)
{
	if (experimental_zcopytx)
		vhost_net_enable_zcopy(VHOST_NET_VQ_TX);
	return misc_register(&vhost_net_misc);
}
module_init(vhost_net_init);

static void vhost_net_exit(void)
{
	misc_deregister(&vhost_net_misc);
}
module_exit(vhost_net_exit);

MODULE_VERSION("0.0.1");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Michael S. Tsirkin");
MODULE_DESCRIPTION("Host kernel accelerator for virtio net");
MODULE_ALIAS_MISCDEV(VHOST_NET_MINOR);
MODULE_ALIAS("devname:vhost-net");

其中vhost_net_fops代表字符设备支持的用户态接口。字符设备为/dev/vhost-net

static const struct file_operations vhost_net_fops = {
	.owner          = THIS_MODULE,
	.release        = vhost_net_release,
	.unlocked_ioctl = vhost_net_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl   = vhost_net_compat_ioctl,
#endif
	.open           = vhost_net_open,
	.llseek		= noop_llseek,
};

当用户态进行使用open系统调用的使用，则执行vhost_net_open函数，该函数主要对该

字符设备进行初始化

static int vhost_net_open(struct inode *inode, struct file *f)
{
	struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
	struct vhost_dev *dev;
	struct vhost_virtqueue **vqs;
	int r, i;

	if (!n)
		return -ENOMEM;
	vqs = kmalloc(VHOST_NET_VQ_MAX * sizeof(*vqs), GFP_KERNEL);
	if (!vqs) {
		kfree(n);
		return -ENOMEM;
	}

	dev = &n->dev;
	vqs[VHOST_NET_VQ_TX] = &n->vqs[VHOST_NET_VQ_TX].vq;
	vqs[VHOST_NET_VQ_RX] = &n->vqs[VHOST_NET_VQ_RX].vq;
	n->vqs[VHOST_NET_VQ_TX].vq.handle_kick = handle_tx_kick;
	n->vqs[VHOST_NET_VQ_RX].vq.handle_kick = handle_rx_kick;
	for (i = 0; i < VHOST_NET_VQ_MAX; i++) {
		n->vqs[i].ubufs = NULL;
		n->vqs[i].ubuf_info = NULL;
		n->vqs[i].upend_idx = 0;
		n->vqs[i].done_idx = 0;
		n->vqs[i].vhost_hlen = 0;
		n->vqs[i].sock_hlen = 0;
	}
	r = vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX);
	if (r < 0) {
		kfree(n);
		kfree(vqs);
		return r;
	}

	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT, dev);
	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN, dev);

	f->private_data = n;

	return 0;
}

从上述代码中可以看出vhost-net模块的核心数据结果关系图如下

为了获取tap设备的数据包，vhost-net模块注册了该设备的tun scoket

static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
{

	sock = get_socket(fd);
	if (IS_ERR(sock)) {
		r = PTR_ERR(sock);
		goto err_vq;
	}

        vq->private_data = sock;

}

tun socket的收发包函数为

static const struct proto_ops tun_socket_ops = {
	.sendmsg = tun_sendmsg,
	.recvmsg = tun_recvmsg,
	.release = tun_release,
};

　　

当tap获取到数据包的时候，vhost-net会调用

static void handle_rx(struct vhost_net *net)
{
	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_RX];
	struct vhost_virtqueue *vq = &nvq->vq;
	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, mergeable;
	s16 headcount;
	size_t vhost_hlen, sock_hlen;
	size_t vhost_len, sock_len;
	struct socket *sock;

	mutex_lock(&vq->mutex);
	sock = vq->private_data;
	if (!sock)
		goto out;
	vhost_disable_notify(&net->dev, vq);

	vhost_hlen = nvq->vhost_hlen;
	sock_hlen = nvq->sock_hlen;

	vq_log = unlikely(vhost_has_feature(vq, VHOST_F_LOG_ALL)) ?
		vq->log : NULL;
	mergeable = vhost_has_feature(vq, VIRTIO_NET_F_MRG_RXBUF);

	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,
					likely(mergeable) ? UIO_MAXIOV : 1);
		/* On error, stop handling until the next kick. */
		if (unlikely(headcount < 0))
			break;
		/* On overrun, truncate and discard */
		if (unlikely(headcount > UIO_MAXIOV)) {
			msg.msg_iovlen = 1;
			err = sock->ops->recvmsg(NULL, sock, &msg,
						 1, MSG_DONTWAIT | MSG_TRUNC);
			pr_debug("Discarded rx packet: len %zd
", sock_len);
			continue;
		}
		/* OK, now we need to know about added descriptors. */
		if (!headcount) {
			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
				/* They have slipped one in as we were
				 * doing that: check again. */
				vhost_disable_notify(&net->dev, 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, nvq->hdr, vhost_hlen, in);
		else
			/* Copy the header for use in VIRTIO_NET_F_MRG_RXBUF:
			 * needed because recvmsg can modify msg_iov. */
			copy_iovec_hdr(vq->iov, nvq->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
", err, sock_len);
			vhost_discard_vq_desc(vq, headcount);
			continue;
		}
		if (unlikely(vhost_hlen) &&
		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&hdr, 0,
				      vhost_hlen)) {
			vq_err(vq, "Unable to write vnet_hdr at addr %p
",
			       vq->iov->iov_base);
			break;
		}
		/* TODO: Should check and handle checksum. */

		hdr.num_buffers = cpu_to_vhost16(vq, headcount);
		if (likely(mergeable) &&
		    memcpy_toiovecend(nvq->hdr, (void *)&hdr.num_buffers,
				      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;
		}
	}
out:
	mutex_unlock(&vq->mutex);
}

从上述代码中可以看出

sock->ops->recvmsg会执行tun socket ops的tun_recvmsg函数，把tap收到的skb，放到virt_queue结构体中然后通过qemu kvm，以中断的形式唤醒virtio-net驱动的收报函数，注意vhost-net的收发包队列与virtio-net的收发包队列

是共享的

static int virtnet_poll(struct napi_struct *napi, int budget)
{
    struct receive_queue *rq =
        container_of(napi, struct receive_queue, napi);
    struct virtnet_info *vi = rq->vq->vdev->priv;
    void *buf;
    unsigned int r, len, received = 0;

again:
    while (received < budget &&
           (buf = virtqueue_get_buf(rq->vq, &len)) != NULL) {
        receive_buf(vi, rq, buf, len);
        --rq->num;
        received++;
    }

    if (rq->num < rq->max / 2) {
        if (!try_fill_recv(vi, rq, GFP_ATOMIC))
            schedule_delayed_work(&vi->refill, 0);
    }

    /* Out of packets? */
    if (received < budget) {
        r = virtqueue_enable_cb_prepare(rq->vq);
        napi_complete(napi);
        if (unlikely(virtqueue_poll(rq->vq, r)) &&
            napi_schedule_prep(napi)) {
            virtqueue_disable_cb(rq->vq);
            __napi_schedule(napi);
            goto again;
        }
    }

    return received;
}

　　

该函数receive_buf会调用linux kernel标准的协议栈收报函数netif_receive_skb，至此数据包就通过tap到vhost-net

最终送到了虚拟机中

虚拟机向外发包

虚拟机向外发送数据包，首先会走linux 协议栈，协议栈发包最终都会调用网卡的xmit函数，对于

virtio-net网卡其xmit函数为

static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct virtnet_info *vi = netdev_priv(dev);
	int qnum = skb_get_queue_mapping(skb);
	struct send_queue *sq = &vi->sq[qnum];
	int err;
	struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
	bool kick = !skb->xmit_more;

	/* Free up any pending old buffers before queueing new ones. */
	free_old_xmit_skbs(sq);

	/* Try to transmit */
	err = xmit_skb(sq, skb);

	/* This should not happen! */
	if (unlikely(err)) {
		dev->stats.tx_fifo_errors++;
		if (net_ratelimit())
			dev_warn(&dev->dev,
				 "Unexpected TXQ (%d) queue failure: %d
", qnum, err);
		dev->stats.tx_dropped++;
		kfree_skb(skb);
		return NETDEV_TX_OK;
	}

	/* Don't wait up for transmitted skbs to be freed. */
	skb_orphan(skb);
	nf_reset(skb);

	/* Apparently nice girls don't return TX_BUSY; stop the queue
	 * before it gets out of hand.  Naturally, this wastes entries. */
	if (sq->vq->num_free < 2+MAX_SKB_FRAGS) {
		netif_stop_subqueue(dev, qnum);
		if (unlikely(!virtqueue_enable_cb_delayed(sq->vq))) {
			/* More just got used, free them then recheck. */
			free_old_xmit_skbs(sq);
			if (sq->vq->num_free >= 2+MAX_SKB_FRAGS) {
				netif_start_subqueue(dev, qnum);
				virtqueue_disable_cb(sq->vq);
			}
		}
	}

	if (kick || netif_xmit_stopped(txq))
		virtqueue_kick(sq->vq);

	return NETDEV_TX_OK;
}

从代码中看就是把skb发到virtqueue中，然后调用virtqueue_kick通知qemu kvm，kvm 会把该数据包

送给vhost-net，vhost-net会调用

static void handle_tx(struct vhost_net *net)
{
	struct vhost_net_virtqueue *nvq = &net->vqs[VHOST_NET_VQ_TX];
	struct vhost_virtqueue *vq = &nvq->vq;
	unsigned out, in, s;
	int head;
	struct msghdr msg = {
		.msg_name = NULL,
		.msg_namelen = 0,
		.msg_control = NULL,
		.msg_controllen = 0,
		.msg_iov = vq->iov,
		.msg_flags = MSG_DONTWAIT,
	};
	size_t len, total_len = 0;
	int err;
	size_t hdr_size;
	struct socket *sock;
	struct vhost_net_ubuf_ref *uninitialized_var(ubufs);
	bool zcopy, zcopy_used;

	mutex_lock(&vq->mutex);
	sock = vq->private_data;
	if (!sock)
		goto out;

	vhost_disable_notify(&net->dev, vq);

	hdr_size = nvq->vhost_hlen;
	zcopy = nvq->ubufs;

	for (;;) {
		/* Release DMAs done buffers first */
		if (zcopy)
			vhost_zerocopy_signal_used(net, vq);

		/* If more outstanding DMAs, queue the work.
		 * Handle upend_idx wrap around
		 */
		if (unlikely((nvq->upend_idx + vq->num - VHOST_MAX_PEND)
			      % UIO_MAXIOV == nvq->done_idx))
			break;

		head = vhost_get_vq_desc(vq, vq->iov,
					 ARRAY_SIZE(vq->iov),
					 &out, &in,
					 NULL, NULL);
		/* On error, stop handling until the next kick. */
		if (unlikely(head < 0))
			break;
		/* Nothing new?  Wait for eventfd to tell us they refilled. */
		if (head == vq->num) {
			if (unlikely(vhost_enable_notify(&net->dev, vq))) {
				vhost_disable_notify(&net->dev, vq);
				continue;
			}
			break;
		}
		if (in) {
			vq_err(vq, "Unexpected descriptor format for TX: "
			       "out %d, int %d
", out, in);
			break;
		}
		/* Skip header. TODO: support TSO. */
		s = move_iovec_hdr(vq->iov, nvq->hdr, hdr_size, out);
		msg.msg_iovlen = out;
		len = iov_length(vq->iov, out);
		/* Sanity check */
		if (!len) {
			vq_err(vq, "Unexpected header len for TX: "
			       "%zd expected %zd
",
			       iov_length(nvq->hdr, s), hdr_size);
			break;
		}
		zcopy_used = zcopy && (len >= VHOST_GOODCOPY_LEN ||
				       nvq->upend_idx != nvq->done_idx);

		/* use msg_control to pass vhost zerocopy ubuf info to skb */
		if (zcopy_used) {
			vq->heads[nvq->upend_idx].id = cpu_to_vhost32(vq, head);
			if (!vhost_net_tx_select_zcopy(net) ||
			    len < VHOST_GOODCOPY_LEN) {
				/* copy don't need to wait for DMA done */
				vq->heads[nvq->upend_idx].len =
							VHOST_DMA_DONE_LEN;
				msg.msg_control = NULL;
				msg.msg_controllen = 0;
				ubufs = NULL;
			} else {
				struct ubuf_info *ubuf;
				ubuf = nvq->ubuf_info + nvq->upend_idx;

				vq->heads[nvq->upend_idx].len =
					VHOST_DMA_IN_PROGRESS;
				ubuf->callback = vhost_zerocopy_callback;
				ubuf->ctx = nvq->ubufs;
				ubuf->desc = nvq->upend_idx;
				msg.msg_control = ubuf;
				msg.msg_controllen = sizeof(ubuf);
				ubufs = nvq->ubufs;
				atomic_inc(&ubufs->refcount);
			}
			nvq->upend_idx = (nvq->upend_idx + 1) % UIO_MAXIOV;
		} else
			msg.msg_control = NULL;
		/* TODO: Check specific error and bomb out unless ENOBUFS? */
		err = sock->ops->sendmsg(NULL, sock, &msg, len);
		if (unlikely(err < 0)) {
			if (zcopy_used) {
				if (ubufs)
					vhost_net_ubuf_put(ubufs);
				nvq->upend_idx = ((unsigned)nvq->upend_idx - 1)
					% UIO_MAXIOV;
			}
			vhost_discard_vq_desc(vq, 1);
			break;
		}
		if (err != len)
			pr_debug("Truncated TX packet: "
				 " len %d != %zd
", err, len);
		if (!zcopy_used)
			vhost_add_used_and_signal(&net->dev, vq, head, 0);
		else
			vhost_zerocopy_signal_used(net, vq);
		total_len += len;
		vhost_net_tx_packet(net);
		if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
			vhost_poll_queue(&vq->poll);
			break;
		}
	}
out:
	mutex_unlock(&vq->mutex);
}

在该函数中会调用sock->ops->sendmsg，也就是tun_sendmsg,在该函数中最终会调用

netif_rx,该函数就是协议栈网卡的收报函数，代表tap网卡已经收到数据包了，然后就可以通过

linux协议的briage把数据包发送出去啦