xen-netfront.c

linux 内核源代码

		printk(KERN_WARNING "%s: add sysfs failed err=%d\n",
		       __func__, err);
		goto fail;
	}

	return 0;

 fail:
	free_netdev(netdev);
	dev->dev.driver_data = NULL;
	return err;
}

static void xennet_end_access(int ref, void *page)
{
	/* This frees the page as a side-effect */
	if (ref != GRANT_INVALID_REF)
		gnttab_end_foreign_access(ref, 0, (unsigned long)page);
}

static void xennet_disconnect_backend(struct netfront_info *info)
{
	/* Stop old i/f to prevent errors whilst we rebuild the state. */
	spin_lock_bh(&info->rx_lock);
	spin_lock_irq(&info->tx_lock);
	netif_carrier_off(info->netdev);
	spin_unlock_irq(&info->tx_lock);
	spin_unlock_bh(&info->rx_lock);

	if (info->netdev->irq)
		unbind_from_irqhandler(info->netdev->irq, info->netdev);
	info->evtchn = info->netdev->irq = 0;

	/* End access and free the pages */
	xennet_end_access(info->tx_ring_ref, info->tx.sring);
	xennet_end_access(info->rx_ring_ref, info->rx.sring);

	info->tx_ring_ref = GRANT_INVALID_REF;
	info->rx_ring_ref = GRANT_INVALID_REF;
	info->tx.sring = NULL;
	info->rx.sring = NULL;
}

/**
 * We are reconnecting to the backend, due to a suspend/resume, or a backend
 * driver restart.  We tear down our netif structure and recreate it, but
 * leave the device-layer structures intact so that this is transparent to the
 * rest of the kernel.
 */
static int netfront_resume(struct xenbus_device *dev)
{
	struct netfront_info *info = dev->dev.driver_data;

	dev_dbg(&dev->dev, "%s\n", dev->nodename);

	xennet_disconnect_backend(info);
	return 0;
}

static int xen_net_read_mac(struct xenbus_device *dev, u8 mac[])
{
	char *s, *e, *macstr;
	int i;

	macstr = s = xenbus_read(XBT_NIL, dev->nodename, "mac", NULL);
	if (IS_ERR(macstr))
		return PTR_ERR(macstr);

	for (i = 0; i < ETH_ALEN; i++) {
		mac[i] = simple_strtoul(s, &e, 16);
		if ((s == e) || (*e != ((i == ETH_ALEN-1) ? '\0' : ':'))) {
			kfree(macstr);
			return -ENOENT;
		}
		s = e+1;
	}

	kfree(macstr);
	return 0;
}

static irqreturn_t xennet_interrupt(int irq, void *dev_id)
{
	struct net_device *dev = dev_id;
	struct netfront_info *np = netdev_priv(dev);
	unsigned long flags;

	spin_lock_irqsave(&np->tx_lock, flags);

	if (likely(netif_carrier_ok(dev))) {
		xennet_tx_buf_gc(dev);
		/* Under tx_lock: protects access to rx shared-ring indexes. */
		if (RING_HAS_UNCONSUMED_RESPONSES(&np->rx))
			netif_rx_schedule(dev, &np->napi);
	}

	spin_unlock_irqrestore(&np->tx_lock, flags);

	return IRQ_HANDLED;
}

static int setup_netfront(struct xenbus_device *dev, struct netfront_info *info)
{
	struct xen_netif_tx_sring *txs;
	struct xen_netif_rx_sring *rxs;
	int err;
	struct net_device *netdev = info->netdev;

	info->tx_ring_ref = GRANT_INVALID_REF;
	info->rx_ring_ref = GRANT_INVALID_REF;
	info->rx.sring = NULL;
	info->tx.sring = NULL;
	netdev->irq = 0;

	err = xen_net_read_mac(dev, netdev->dev_addr);
	if (err) {
		xenbus_dev_fatal(dev, err, "parsing %s/mac", dev->nodename);
		goto fail;
	}

	txs = (struct xen_netif_tx_sring *)get_zeroed_page(GFP_KERNEL);
	if (!txs) {
		err = -ENOMEM;
		xenbus_dev_fatal(dev, err, "allocating tx ring page");
		goto fail;
	}
	SHARED_RING_INIT(txs);
	FRONT_RING_INIT(&info->tx, txs, PAGE_SIZE);

	err = xenbus_grant_ring(dev, virt_to_mfn(txs));
	if (err < 0) {
		free_page((unsigned long)txs);
		goto fail;
	}

	info->tx_ring_ref = err;
	rxs = (struct xen_netif_rx_sring *)get_zeroed_page(GFP_KERNEL);
	if (!rxs) {
		err = -ENOMEM;
		xenbus_dev_fatal(dev, err, "allocating rx ring page");
		goto fail;
	}
	SHARED_RING_INIT(rxs);
	FRONT_RING_INIT(&info->rx, rxs, PAGE_SIZE);

	err = xenbus_grant_ring(dev, virt_to_mfn(rxs));
	if (err < 0) {
		free_page((unsigned long)rxs);
		goto fail;
	}
	info->rx_ring_ref = err;

	err = xenbus_alloc_evtchn(dev, &info->evtchn);
	if (err)
		goto fail;

	err = bind_evtchn_to_irqhandler(info->evtchn, xennet_interrupt,
					IRQF_SAMPLE_RANDOM, netdev->name,
					netdev);
	if (err < 0)
		goto fail;
	netdev->irq = err;
	return 0;

 fail:
	return err;
}

/* Common code used when first setting up, and when resuming. */
static int talk_to_backend(struct xenbus_device *dev,
			   struct netfront_info *info)
{
	const char *message;
	struct xenbus_transaction xbt;
	int err;

	/* Create shared ring, alloc event channel. */
	err = setup_netfront(dev, info);
	if (err)
		goto out;

again:
	err = xenbus_transaction_start(&xbt);
	if (err) {
		xenbus_dev_fatal(dev, err, "starting transaction");
		goto destroy_ring;
	}

	err = xenbus_printf(xbt, dev->nodename, "tx-ring-ref", "%u",
			    info->tx_ring_ref);
	if (err) {
		message = "writing tx ring-ref";
		goto abort_transaction;
	}
	err = xenbus_printf(xbt, dev->nodename, "rx-ring-ref", "%u",
			    info->rx_ring_ref);
	if (err) {
		message = "writing rx ring-ref";
		goto abort_transaction;
	}
	err = xenbus_printf(xbt, dev->nodename,
			    "event-channel", "%u", info->evtchn);
	if (err) {
		message = "writing event-channel";
		goto abort_transaction;
	}

	err = xenbus_printf(xbt, dev->nodename, "request-rx-copy", "%u",
			    1);
	if (err) {
		message = "writing request-rx-copy";
		goto abort_transaction;
	}

	err = xenbus_printf(xbt, dev->nodename, "feature-rx-notify", "%d", 1);
	if (err) {
		message = "writing feature-rx-notify";
		goto abort_transaction;
	}

	err = xenbus_printf(xbt, dev->nodename, "feature-sg", "%d", 1);
	if (err) {
		message = "writing feature-sg";
		goto abort_transaction;
	}

	err = xenbus_printf(xbt, dev->nodename, "feature-gso-tcpv4", "%d", 1);
	if (err) {
		message = "writing feature-gso-tcpv4";
		goto abort_transaction;
	}

	err = xenbus_transaction_end(xbt, 0);
	if (err) {
		if (err == -EAGAIN)
			goto again;
		xenbus_dev_fatal(dev, err, "completing transaction");
		goto destroy_ring;
	}

	return 0;

 abort_transaction:
	xenbus_transaction_end(xbt, 1);
	xenbus_dev_fatal(dev, err, "%s", message);
 destroy_ring:
	xennet_disconnect_backend(info);
 out:
	return err;
}

static int xennet_set_sg(struct net_device *dev, u32 data)
{
	if (data) {
		struct netfront_info *np = netdev_priv(dev);
		int val;

		if (xenbus_scanf(XBT_NIL, np->xbdev->otherend, "feature-sg",
				 "%d", &val) < 0)
			val = 0;
		if (!val)
			return -ENOSYS;
	} else if (dev->mtu > ETH_DATA_LEN)
		dev->mtu = ETH_DATA_LEN;

	return ethtool_op_set_sg(dev, data);
}

static int xennet_set_tso(struct net_device *dev, u32 data)
{
	if (data) {
		struct netfront_info *np = netdev_priv(dev);
		int val;

		if (xenbus_scanf(XBT_NIL, np->xbdev->otherend,
				 "feature-gso-tcpv4", "%d", &val) < 0)
			val = 0;
		if (!val)
			return -ENOSYS;
	}

	return ethtool_op_set_tso(dev, data);
}

static void xennet_set_features(struct net_device *dev)
{
	/* Turn off all GSO bits except ROBUST. */
	dev->features &= (1 << NETIF_F_GSO_SHIFT) - 1;
	dev->features |= NETIF_F_GSO_ROBUST;
	xennet_set_sg(dev, 0);

	/* We need checksum offload to enable scatter/gather and TSO. */
	if (!(dev->features & NETIF_F_IP_CSUM))
		return;

	if (!xennet_set_sg(dev, 1))
		xennet_set_tso(dev, 1);
}

static int xennet_connect(struct net_device *dev)
{
	struct netfront_info *np = netdev_priv(dev);
	int i, requeue_idx, err;
	struct sk_buff *skb;
	grant_ref_t ref;
	struct xen_netif_rx_request *req;
	unsigned int feature_rx_copy;

	err = xenbus_scanf(XBT_NIL, np->xbdev->otherend,
			   "feature-rx-copy", "%u", &feature_rx_copy);
	if (err != 1)
		feature_rx_copy = 0;

	if (!feature_rx_copy) {
		dev_info(&dev->dev,
			 "backend does not support copying receive path\n");
		return -ENODEV;
	}

	err = talk_to_backend(np->xbdev, np);
	if (err)
		return err;

	xennet_set_features(dev);

	spin_lock_bh(&np->rx_lock);
	spin_lock_irq(&np->tx_lock);

	/* Step 1: Discard all pending TX packet fragments. */
	xennet_release_tx_bufs(np);

	/* Step 2: Rebuild the RX buffer freelist and the RX ring itself. */
	for (requeue_idx = 0, i = 0; i < NET_RX_RING_SIZE; i++) {
		if (!np->rx_skbs[i])
			continue;

		skb = np->rx_skbs[requeue_idx] = xennet_get_rx_skb(np, i);
		ref = np->grant_rx_ref[requeue_idx] = xennet_get_rx_ref(np, i);
		req = RING_GET_REQUEST(&np->rx, requeue_idx);

		gnttab_grant_foreign_access_ref(
			ref, np->xbdev->otherend_id,
			pfn_to_mfn(page_to_pfn(skb_shinfo(skb)->
					       frags->page)),
			0);
		req->gref = ref;
		req->id   = requeue_idx;

		requeue_idx++;
	}

	np->rx.req_prod_pvt = requeue_idx;

	/*
	 * Step 3: All public and private state should now be sane.  Get
	 * ready to start sending and receiving packets and give the driver
	 * domain a kick because we've probably just requeued some
	 * packets.
	 */
	netif_carrier_on(np->netdev);
	notify_remote_via_irq(np->netdev->irq);
	xennet_tx_buf_gc(dev);
	xennet_alloc_rx_buffers(dev);

	spin_unlock_irq(&np->tx_lock);
	spin_unlock_bh(&np->rx_lock);

	return 0;
}

/**
 * Callback received when the backend's state changes.
 */
static void backend_changed(struct xenbus_device *dev,
			    enum xenbus_state backend_state)
{
	struct netfront_info *np = dev->dev.driver_data;
	struct net_device *netdev = np->netdev;

	dev_dbg(&dev->dev, "%s\n", xenbus_strstate(backend_state));

	switch (backend_state) {
	case XenbusStateInitialising:
	case XenbusStateInitialised:
	case XenbusStateConnected:
	case XenbusStateUnknown:
	case XenbusStateClosed:
		break;

	case XenbusStateInitWait:
		if (dev->state != XenbusStateInitialising)
			break;
		if (xennet_connect(netdev) != 0)
			break;
		xenbus_switch_state(dev, XenbusStateConnected);
		break;

	case XenbusStateClosing:
		xenbus_frontend_closed(dev);
		break;
	}
}

static struct ethtool_ops xennet_ethtool_ops =
{
	.set_tx_csum = ethtool_op_set_tx_csum,
	.set_sg = xennet_set_sg,
	.set_tso = xennet_set_tso,
	.get_link = ethtool_op_get_link,
};

#ifdef CONFIG_SYSFS
static ssize_t show_rxbuf_min(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct net_device *netdev = to_net_dev(dev);
	struct netfront_info *info = netdev_priv(netdev);

	return sprintf(buf, "%u\n", info->rx_min_target);
}

static ssize_t store_rxbuf_min(struct device *dev,
			       struct device_attribute *attr,
			       const char *buf, size_t len)
{
	struct net_device *netdev = to_net_dev(dev);
	struct netfront_info *np = netdev_priv(netdev);
	char *endp;
	unsigned long target;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	target = simple_strtoul(buf, &endp, 0);
	if (endp == buf)
		return -EBADMSG;

	if (target < RX_MIN_TARGET)
		target = RX_MIN_TARGET;
	if (target > RX_MAX_TARGET)
		target = RX_MAX_TARGET;

	spin_lock_bh(&np->rx_lock);
	if (target > np->rx_max_target)
		np->rx_max_target = target;
	np->rx_min_target = target;
	if (target > np->rx_target)
		np->rx_target = target;

	xennet_alloc_rx_buffers(netdev);

	spin_unlock_bh(&np->rx_lock);
	return len;
}

static ssize_t show_rxbuf_max(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct net_device *netdev = to_net_dev(dev);
	struct netfront_info *info = netdev_priv(netdev);

	return sprintf(buf, "%u\n", info->rx_max_target);
}

static ssize_t store_rxbuf_max(struct device *dev,
			       struct device_attribute *attr,
			       const char *buf, size_t len)
{
	struct net_device *netdev = to_net_dev(dev);
	struct netfront_info *np = netdev_priv(netdev);
	char *endp;
	unsigned long target;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	target = simple_strtoul(buf, &endp, 0);
	if (endp == buf)
		return -EBADMSG;

	if (target < RX_MIN_TARGET)
		target = RX_MIN_TARGET;
	if (target > RX_MAX_TARGET)
		target = RX_MAX_TARGET;

	spin_lock_bh(&np->rx_lock);
	if (target < np->rx_min_target)
		np->rx_min_target = target;
	np->rx_max_target = target;
	if (target < np->rx_target)
		np->rx_target = target;

	xennet_alloc_rx_buffers(netdev);

	spin_unlock_bh(&np->rx_lock);
	return len;
}

static ssize_t show_rxbuf_cur(struct device *dev,
			      struct device_attribute *attr, char *buf)
{
	struct net_device *netdev = to_net_dev(dev);
	struct netfront_info *info = netdev_priv(netdev);

	return sprintf(buf, "%u\n", info->rx_target);
}

static struct device_attribute xennet_attrs[] = {
	__ATTR(rxbuf_min, S_IRUGO|S_IWUSR, show_rxbuf_min, store_rxbuf_min),
	__ATTR(rxbuf_max, S_IRUGO|S_IWUSR, show_rxbuf_max, store_rxbuf_max),
	__ATTR(rxbuf_cur, S_IRUGO, show_rxbuf_cur, NULL),
};

static int xennet_sysfs_addif(struct net_device *netdev)
{
	int i;
	int err;

	for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++) {
		err = device_create_file(&netdev->dev,
					   &xennet_attrs[i]);
		if (err)
			goto fail;
	}
	return 0;

 fail:
	while (--i >= 0)
		device_remove_file(&netdev->dev, &xennet_attrs[i]);
	return err;
}

static void xennet_sysfs_delif(struct net_device *netdev)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(xennet_attrs); i++)
		device_remove_file(&netdev->dev, &xennet_attrs[i]);
}

#endif /* CONFIG_SYSFS */

static struct xenbus_device_id netfront_ids[] = {
	{ "vif" },
	{ "" }
};


static int __devexit xennet_remove(struct xenbus_device *dev)
{
	struct netfront_info *info = dev->dev.driver_data;

	dev_dbg(&dev->dev, "%s\n", dev->nodename);

	unregister_netdev(info->netdev);

	xennet_disconnect_backend(info);

	del_timer_sync(&info->rx_refill_timer);

	xennet_sysfs_delif(info->netdev);

	free_netdev(info->netdev);

	return 0;
}

static struct xenbus_driver netfront = {
	.name = "vif",
	.owner = THIS_MODULE,
	.ids = netfront_ids,
	.probe = netfront_probe,
	.remove = __devexit_p(xennet_remove),
	.resume = netfront_resume,
	.otherend_changed = backend_changed,
};

static int __init netif_init(void)
{
	if (!is_running_on_xen())
		return -ENODEV;

	if (is_initial_xendomain())
		return 0;

	printk(KERN_INFO "Initialising Xen virtual ethernet driver.\n");

	return xenbus_register_frontend(&netfront);
}
module_init(netif_init);


static void __exit netif_exit(void)
{
	if (is_initial_xendomain())
		return;

	return xenbus_unregister_driver(&netfront);
}
module_exit(netif_exit);

MODULE_DESCRIPTION("Xen virtual network device frontend");
MODULE_LICENSE("GPL");