sunvnet.c

来自「linux 内核源代码」· C语言 代码 · 共 1,295 行 · 第 1/2 页

	unsigned long flags;
	unsigned int len;
	void *tx_buf;
	int i, err;

	if (unlikely(!port))
		goto out_dropped;

	spin_lock_irqsave(&port->vio.lock, flags);

	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
		if (!netif_queue_stopped(dev)) {
			netif_stop_queue(dev);

			/* This is a hard error, log it. */
			printk(KERN_ERR PFX "%s: BUG! Tx Ring full when "
			       "queue awake!\n", dev->name);
			dev->stats.tx_errors++;
		}
		spin_unlock_irqrestore(&port->vio.lock, flags);
		return NETDEV_TX_BUSY;
	}

	d = vio_dring_cur(dr);

	tx_buf = port->tx_bufs[dr->prod].buf;
	skb_copy_from_linear_data(skb, tx_buf + VNET_PACKET_SKIP, skb->len);

	len = skb->len;
	if (len < ETH_ZLEN) {
		len = ETH_ZLEN;
		memset(tx_buf+VNET_PACKET_SKIP+skb->len, 0, len - skb->len);
	}

	d->hdr.ack = VIO_ACK_ENABLE;
	d->size = len;
	d->ncookies = port->tx_bufs[dr->prod].ncookies;
	for (i = 0; i < d->ncookies; i++)
		d->cookies[i] = port->tx_bufs[dr->prod].cookies[i];

	/* This has to be a non-SMP write barrier because we are writing
	 * to memory which is shared with the peer LDOM.
	 */
	wmb();

	d->hdr.state = VIO_DESC_READY;

	err = __vnet_tx_trigger(port);
	if (unlikely(err < 0)) {
		printk(KERN_INFO PFX "%s: TX trigger error %d\n",
		       dev->name, err);
		d->hdr.state = VIO_DESC_FREE;
		dev->stats.tx_carrier_errors++;
		goto out_dropped_unlock;
	}

	dev->stats.tx_packets++;
	dev->stats.tx_bytes += skb->len;

	dr->prod = (dr->prod + 1) & (VNET_TX_RING_SIZE - 1);
	if (unlikely(vnet_tx_dring_avail(dr) < 2)) {
		netif_stop_queue(dev);
		if (vnet_tx_dring_avail(dr) > VNET_TX_WAKEUP_THRESH(dr))
			netif_wake_queue(dev);
	}

	spin_unlock_irqrestore(&port->vio.lock, flags);

	dev_kfree_skb(skb);

	dev->trans_start = jiffies;
	return NETDEV_TX_OK;

out_dropped_unlock:
	spin_unlock_irqrestore(&port->vio.lock, flags);

out_dropped:
	dev_kfree_skb(skb);
	dev->stats.tx_dropped++;
	return NETDEV_TX_OK;
}

static void vnet_tx_timeout(struct net_device *dev)
{
	/* XXX Implement me XXX */
}

static int vnet_open(struct net_device *dev)
{
	netif_carrier_on(dev);
	netif_start_queue(dev);

	return 0;
}

static int vnet_close(struct net_device *dev)
{
	netif_stop_queue(dev);
	netif_carrier_off(dev);

	return 0;
}

static struct vnet_mcast_entry *__vnet_mc_find(struct vnet *vp, u8 *addr)
{
	struct vnet_mcast_entry *m;

	for (m = vp->mcast_list; m; m = m->next) {
		if (!memcmp(m->addr, addr, ETH_ALEN))
			return m;
	}
	return NULL;
}

static void __update_mc_list(struct vnet *vp, struct net_device *dev)
{
	struct dev_addr_list *p;

	for (p = dev->mc_list; p; p = p->next) {
		struct vnet_mcast_entry *m;

		m = __vnet_mc_find(vp, p->dmi_addr);
		if (m) {
			m->hit = 1;
			continue;
		}

		if (!m) {
			m = kzalloc(sizeof(*m), GFP_ATOMIC);
			if (!m)
				continue;
			memcpy(m->addr, p->dmi_addr, ETH_ALEN);
			m->hit = 1;

			m->next = vp->mcast_list;
			vp->mcast_list = m;
		}
	}
}

static void __send_mc_list(struct vnet *vp, struct vnet_port *port)
{
	struct vio_net_mcast_info info;
	struct vnet_mcast_entry *m, **pp;
	int n_addrs;

	memset(&info, 0, sizeof(info));

	info.tag.type = VIO_TYPE_CTRL;
	info.tag.stype = VIO_SUBTYPE_INFO;
	info.tag.stype_env = VNET_MCAST_INFO;
	info.tag.sid = vio_send_sid(&port->vio);
	info.set = 1;

	n_addrs = 0;
	for (m = vp->mcast_list; m; m = m->next) {
		if (m->sent)
			continue;
		m->sent = 1;
		memcpy(&info.mcast_addr[n_addrs * ETH_ALEN],
		       m->addr, ETH_ALEN);
		if (++n_addrs == VNET_NUM_MCAST) {
			info.count = n_addrs;

			(void) vio_ldc_send(&port->vio, &info,
					    sizeof(info));
			n_addrs = 0;
		}
	}
	if (n_addrs) {
		info.count = n_addrs;
		(void) vio_ldc_send(&port->vio, &info, sizeof(info));
	}

	info.set = 0;

	n_addrs = 0;
	pp = &vp->mcast_list;
	while ((m = *pp) != NULL) {
		if (m->hit) {
			m->hit = 0;
			pp = &m->next;
			continue;
		}

		memcpy(&info.mcast_addr[n_addrs * ETH_ALEN],
		       m->addr, ETH_ALEN);
		if (++n_addrs == VNET_NUM_MCAST) {
			info.count = n_addrs;
			(void) vio_ldc_send(&port->vio, &info,
					    sizeof(info));
			n_addrs = 0;
		}

		*pp = m->next;
		kfree(m);
	}
	if (n_addrs) {
		info.count = n_addrs;
		(void) vio_ldc_send(&port->vio, &info, sizeof(info));
	}
}

static void vnet_set_rx_mode(struct net_device *dev)
{
	struct vnet *vp = netdev_priv(dev);
	struct vnet_port *port;
	unsigned long flags;

	spin_lock_irqsave(&vp->lock, flags);
	if (!list_empty(&vp->port_list)) {
		port = list_entry(vp->port_list.next, struct vnet_port, list);

		if (port->switch_port) {
			__update_mc_list(vp, dev);
			__send_mc_list(vp, port);
		}
	}
	spin_unlock_irqrestore(&vp->lock, flags);
}

static int vnet_change_mtu(struct net_device *dev, int new_mtu)
{
	if (new_mtu != ETH_DATA_LEN)
		return -EINVAL;

	dev->mtu = new_mtu;
	return 0;
}

static int vnet_set_mac_addr(struct net_device *dev, void *p)
{
	return -EINVAL;
}

static void vnet_get_drvinfo(struct net_device *dev,
			     struct ethtool_drvinfo *info)
{
	strcpy(info->driver, DRV_MODULE_NAME);
	strcpy(info->version, DRV_MODULE_VERSION);
}

static u32 vnet_get_msglevel(struct net_device *dev)
{
	struct vnet *vp = netdev_priv(dev);
	return vp->msg_enable;
}

static void vnet_set_msglevel(struct net_device *dev, u32 value)
{
	struct vnet *vp = netdev_priv(dev);
	vp->msg_enable = value;
}

static const struct ethtool_ops vnet_ethtool_ops = {
	.get_drvinfo		= vnet_get_drvinfo,
	.get_msglevel		= vnet_get_msglevel,
	.set_msglevel		= vnet_set_msglevel,
	.get_link		= ethtool_op_get_link,
};

static void vnet_port_free_tx_bufs(struct vnet_port *port)
{
	struct vio_dring_state *dr;
	int i;

	dr = &port->vio.drings[VIO_DRIVER_TX_RING];
	if (dr->base) {
		ldc_free_exp_dring(port->vio.lp, dr->base,
				   (dr->entry_size * dr->num_entries),
				   dr->cookies, dr->ncookies);
		dr->base = NULL;
		dr->entry_size = 0;
		dr->num_entries = 0;
		dr->pending = 0;
		dr->ncookies = 0;
	}

	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
		void *buf = port->tx_bufs[i].buf;

		if (!buf)
			continue;

		ldc_unmap(port->vio.lp,
			  port->tx_bufs[i].cookies,
			  port->tx_bufs[i].ncookies);

		kfree(buf);
		port->tx_bufs[i].buf = NULL;
	}
}

static int __devinit vnet_port_alloc_tx_bufs(struct vnet_port *port)
{
	struct vio_dring_state *dr;
	unsigned long len;
	int i, err, ncookies;
	void *dring;

	for (i = 0; i < VNET_TX_RING_SIZE; i++) {
		void *buf = kzalloc(ETH_FRAME_LEN + 8, GFP_KERNEL);
		int map_len = (ETH_FRAME_LEN + 7) & ~7;

		err = -ENOMEM;
		if (!buf) {
			printk(KERN_ERR "TX buffer allocation failure\n");
			goto err_out;
		}
		err = -EFAULT;
		if ((unsigned long)buf & (8UL - 1)) {
			printk(KERN_ERR "TX buffer misaligned\n");
			kfree(buf);
			goto err_out;
		}

		err = ldc_map_single(port->vio.lp, buf, map_len,
				     port->tx_bufs[i].cookies, 2,
				     (LDC_MAP_SHADOW |
				      LDC_MAP_DIRECT |
				      LDC_MAP_RW));
		if (err < 0) {
			kfree(buf);
			goto err_out;
		}
		port->tx_bufs[i].buf = buf;
		port->tx_bufs[i].ncookies = err;
	}

	dr = &port->vio.drings[VIO_DRIVER_TX_RING];

	len = (VNET_TX_RING_SIZE *
	       (sizeof(struct vio_net_desc) +
		(sizeof(struct ldc_trans_cookie) * 2)));

	ncookies = VIO_MAX_RING_COOKIES;
	dring = ldc_alloc_exp_dring(port->vio.lp, len,
				    dr->cookies, &ncookies,
				    (LDC_MAP_SHADOW |
				     LDC_MAP_DIRECT |
				     LDC_MAP_RW));
	if (IS_ERR(dring)) {
		err = PTR_ERR(dring);
		goto err_out;
	}

	dr->base = dring;
	dr->entry_size = (sizeof(struct vio_net_desc) +
			  (sizeof(struct ldc_trans_cookie) * 2));
	dr->num_entries = VNET_TX_RING_SIZE;
	dr->prod = dr->cons = 0;
	dr->pending = VNET_TX_RING_SIZE;
	dr->ncookies = ncookies;

	return 0;

err_out:
	vnet_port_free_tx_bufs(port);

	return err;
}

static LIST_HEAD(vnet_list);
static DEFINE_MUTEX(vnet_list_mutex);

static struct vnet * __devinit vnet_new(const u64 *local_mac)
{
	struct net_device *dev;
	struct vnet *vp;
	int err, i;

	dev = alloc_etherdev(sizeof(*vp));
	if (!dev) {
		printk(KERN_ERR PFX "Etherdev alloc failed, aborting.\n");
		return ERR_PTR(-ENOMEM);
	}

	for (i = 0; i < ETH_ALEN; i++)
		dev->dev_addr[i] = (*local_mac >> (5 - i) * 8) & 0xff;

	memcpy(dev->perm_addr, dev->dev_addr, dev->addr_len);

	vp = netdev_priv(dev);

	spin_lock_init(&vp->lock);
	vp->dev = dev;

	INIT_LIST_HEAD(&vp->port_list);
	for (i = 0; i < VNET_PORT_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&vp->port_hash[i]);
	INIT_LIST_HEAD(&vp->list);
	vp->local_mac = *local_mac;

	dev->open = vnet_open;
	dev->stop = vnet_close;
	dev->set_multicast_list = vnet_set_rx_mode;
	dev->set_mac_address = vnet_set_mac_addr;
	dev->tx_timeout = vnet_tx_timeout;
	dev->ethtool_ops = &vnet_ethtool_ops;
	dev->watchdog_timeo = VNET_TX_TIMEOUT;
	dev->change_mtu = vnet_change_mtu;
	dev->hard_start_xmit = vnet_start_xmit;

	err = register_netdev(dev);
	if (err) {
		printk(KERN_ERR PFX "Cannot register net device, "
		       "aborting.\n");
		goto err_out_free_dev;
	}

	printk(KERN_INFO "%s: Sun LDOM vnet ", dev->name);

	for (i = 0; i < 6; i++)
		printk("%2.2x%c", dev->dev_addr[i], i == 5 ? '\n' : ':');

	list_add(&vp->list, &vnet_list);

	return vp;

err_out_free_dev:
	free_netdev(dev);

	return ERR_PTR(err);
}

static struct vnet * __devinit vnet_find_or_create(const u64 *local_mac)
{
	struct vnet *iter, *vp;

	mutex_lock(&vnet_list_mutex);
	vp = NULL;
	list_for_each_entry(iter, &vnet_list, list) {
		if (iter->local_mac == *local_mac) {
			vp = iter;
			break;
		}
	}
	if (!vp)
		vp = vnet_new(local_mac);
	mutex_unlock(&vnet_list_mutex);

	return vp;
}

static const char *local_mac_prop = "local-mac-address";

static struct vnet * __devinit vnet_find_parent(struct mdesc_handle *hp,
						u64 port_node)
{
	const u64 *local_mac = NULL;
	u64 a;

	mdesc_for_each_arc(a, hp, port_node, MDESC_ARC_TYPE_BACK) {
		u64 target = mdesc_arc_target(hp, a);
		const char *name;

		name = mdesc_get_property(hp, target, "name", NULL);
		if (!name || strcmp(name, "network"))
			continue;

		local_mac = mdesc_get_property(hp, target,
					       local_mac_prop, NULL);
		if (local_mac)
			break;
	}
	if (!local_mac)
		return ERR_PTR(-ENODEV);

	return vnet_find_or_create(local_mac);
}

static struct ldc_channel_config vnet_ldc_cfg = {
	.event		= vnet_event,
	.mtu		= 64,
	.mode		= LDC_MODE_UNRELIABLE,
};

static struct vio_driver_ops vnet_vio_ops = {
	.send_attr		= vnet_send_attr,
	.handle_attr		= vnet_handle_attr,
	.handshake_complete	= vnet_handshake_complete,
};

static void print_version(void)
{
	static int version_printed;

	if (version_printed++ == 0)
		printk(KERN_INFO "%s", version);
}

const char *remote_macaddr_prop = "remote-mac-address";

static int __devinit vnet_port_probe(struct vio_dev *vdev,
				     const struct vio_device_id *id)
{
	struct mdesc_handle *hp;
	struct vnet_port *port;
	unsigned long flags;
	struct vnet *vp;
	const u64 *rmac;
	int len, i, err, switch_port;

	print_version();

	hp = mdesc_grab();

	vp = vnet_find_parent(hp, vdev->mp);
	if (IS_ERR(vp)) {
		printk(KERN_ERR PFX "Cannot find port parent vnet.\n");
		err = PTR_ERR(vp);
		goto err_out_put_mdesc;
	}

	rmac = mdesc_get_property(hp, vdev->mp, remote_macaddr_prop, &len);
	err = -ENODEV;
	if (!rmac) {
		printk(KERN_ERR PFX "Port lacks %s property.\n",
		       remote_macaddr_prop);
		goto err_out_put_mdesc;
	}

	port = kzalloc(sizeof(*port), GFP_KERNEL);
	err = -ENOMEM;
	if (!port) {
		printk(KERN_ERR PFX "Cannot allocate vnet_port.\n");
		goto err_out_put_mdesc;
	}

	for (i = 0; i < ETH_ALEN; i++)
		port->raddr[i] = (*rmac >> (5 - i) * 8) & 0xff;

	port->vp = vp;

	err = vio_driver_init(&port->vio, vdev, VDEV_NETWORK,
			      vnet_versions, ARRAY_SIZE(vnet_versions),
			      &vnet_vio_ops, vp->dev->name);
	if (err)
		goto err_out_free_port;

	err = vio_ldc_alloc(&port->vio, &vnet_ldc_cfg, port);
	if (err)
		goto err_out_free_port;

	err = vnet_port_alloc_tx_bufs(port);
	if (err)
		goto err_out_free_ldc;

	INIT_HLIST_NODE(&port->hash);
	INIT_LIST_HEAD(&port->list);

	switch_port = 0;
	if (mdesc_get_property(hp, vdev->mp, "switch-port", NULL) != NULL)
		switch_port = 1;
	port->switch_port = switch_port;

	spin_lock_irqsave(&vp->lock, flags);
	if (switch_port)
		list_add(&port->list, &vp->port_list);
	else
		list_add_tail(&port->list, &vp->port_list);
	hlist_add_head(&port->hash, &vp->port_hash[vnet_hashfn(port->raddr)]);
	spin_unlock_irqrestore(&vp->lock, flags);

	dev_set_drvdata(&vdev->dev, port);

	printk(KERN_INFO "%s: PORT ( remote-mac ", vp->dev->name);
	for (i = 0; i < 6; i++)
		printk("%2.2x%c", port->raddr[i], i == 5 ? ' ' : ':');
	if (switch_port)
		printk("switch-port ");
	printk(")\n");

	vio_port_up(&port->vio);

	mdesc_release(hp);

	return 0;

err_out_free_ldc:
	vio_ldc_free(&port->vio);

err_out_free_port:
	kfree(port);

err_out_put_mdesc:
	mdesc_release(hp);
	return err;
}

static int vnet_port_remove(struct vio_dev *vdev)
{
	struct vnet_port *port = dev_get_drvdata(&vdev->dev);

	if (port) {
		struct vnet *vp = port->vp;
		unsigned long flags;

		del_timer_sync(&port->vio.timer);

		spin_lock_irqsave(&vp->lock, flags);
		list_del(&port->list);
		hlist_del(&port->hash);
		spin_unlock_irqrestore(&vp->lock, flags);

		vnet_port_free_tx_bufs(port);
		vio_ldc_free(&port->vio);

		dev_set_drvdata(&vdev->dev, NULL);

		kfree(port);
	}
	return 0;
}

static struct vio_device_id vnet_port_match[] = {
	{
		.type = "vnet-port",
	},
	{},
};
MODULE_DEVICE_TABLE(vio, vnet_port_match);

static struct vio_driver vnet_port_driver = {
	.id_table	= vnet_port_match,
	.probe		= vnet_port_probe,
	.remove		= vnet_port_remove,
	.driver		= {
		.name	= "vnet_port",
		.owner	= THIS_MODULE,
	}
};

static int __init vnet_init(void)
{
	return vio_register_driver(&vnet_port_driver);
}

static void __exit vnet_exit(void)
{
	vio_unregister_driver(&vnet_port_driver);
}

module_init(vnet_init);
module_exit(vnet_exit);