ipoib_main.c

linux内核源码

	return 0;
}

int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	/* Allocate RX/TX "rings" to hold queued skbs */
	priv->rx_ring =	kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring,
				GFP_KERNEL);
	if (!priv->rx_ring) {
		printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
		       ca->name, ipoib_recvq_size);
		goto out;
	}

	priv->tx_ring = kzalloc(ipoib_sendq_size * sizeof *priv->tx_ring,
				GFP_KERNEL);
	if (!priv->tx_ring) {
		printk(KERN_WARNING "%s: failed to allocate TX ring (%d entries)\n",
		       ca->name, ipoib_sendq_size);
		goto out_rx_ring_cleanup;
	}

	/* priv->tx_head, tx_tail & tx_outstanding are already 0 */

	if (ipoib_ib_dev_init(dev, ca, port))
		goto out_tx_ring_cleanup;

	return 0;

out_tx_ring_cleanup:
	kfree(priv->tx_ring);

out_rx_ring_cleanup:
	kfree(priv->rx_ring);

out:
	return -ENOMEM;
}

void ipoib_dev_cleanup(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev), *cpriv, *tcpriv;

	ipoib_delete_debug_files(dev);

	/* Delete any child interfaces first */
	list_for_each_entry_safe(cpriv, tcpriv, &priv->child_intfs, list) {
		unregister_netdev(cpriv->dev);
		ipoib_dev_cleanup(cpriv->dev);
		free_netdev(cpriv->dev);
	}

	ipoib_ib_dev_cleanup(dev);

	kfree(priv->rx_ring);
	kfree(priv->tx_ring);

	priv->rx_ring = NULL;
	priv->tx_ring = NULL;
}

static const struct header_ops ipoib_header_ops = {
	.create	= ipoib_hard_header,
};

static void ipoib_setup(struct net_device *dev)
{
	struct ipoib_dev_priv *priv = netdev_priv(dev);

	dev->open 		 = ipoib_open;
	dev->stop 		 = ipoib_stop;
	dev->change_mtu 	 = ipoib_change_mtu;
	dev->hard_start_xmit 	 = ipoib_start_xmit;
	dev->tx_timeout 	 = ipoib_timeout;
	dev->header_ops 	 = &ipoib_header_ops;
	dev->set_multicast_list  = ipoib_set_mcast_list;
	dev->neigh_setup         = ipoib_neigh_setup_dev;

	netif_napi_add(dev, &priv->napi, ipoib_poll, 100);

	dev->watchdog_timeo 	 = HZ;

	dev->flags              |= IFF_BROADCAST | IFF_MULTICAST;

	/*
	 * We add in INFINIBAND_ALEN to allow for the destination
	 * address "pseudoheader" for skbs without neighbour struct.
	 */
	dev->hard_header_len 	 = IPOIB_ENCAP_LEN + INFINIBAND_ALEN;
	dev->addr_len 		 = INFINIBAND_ALEN;
	dev->type 		 = ARPHRD_INFINIBAND;
	dev->tx_queue_len 	 = ipoib_sendq_size * 2;
	dev->features            = NETIF_F_VLAN_CHALLENGED | NETIF_F_LLTX;

	/* MTU will be reset when mcast join happens */
	dev->mtu 		 = IPOIB_PACKET_SIZE - IPOIB_ENCAP_LEN;
	priv->mcast_mtu 	 = priv->admin_mtu = dev->mtu;

	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);

	netif_carrier_off(dev);

	priv->dev = dev;

	spin_lock_init(&priv->lock);
	spin_lock_init(&priv->tx_lock);

	mutex_init(&priv->mcast_mutex);
	mutex_init(&priv->vlan_mutex);

	INIT_LIST_HEAD(&priv->path_list);
	INIT_LIST_HEAD(&priv->child_intfs);
	INIT_LIST_HEAD(&priv->dead_ahs);
	INIT_LIST_HEAD(&priv->multicast_list);

	INIT_DELAYED_WORK(&priv->pkey_poll_task, ipoib_pkey_poll);
	INIT_WORK(&priv->pkey_event_task, ipoib_pkey_event);
	INIT_DELAYED_WORK(&priv->mcast_task,   ipoib_mcast_join_task);
	INIT_WORK(&priv->flush_task,   ipoib_ib_dev_flush);
	INIT_WORK(&priv->restart_task, ipoib_mcast_restart_task);
	INIT_DELAYED_WORK(&priv->ah_reap_task, ipoib_reap_ah);
}

struct ipoib_dev_priv *ipoib_intf_alloc(const char *name)
{
	struct net_device *dev;

	dev = alloc_netdev((int) sizeof (struct ipoib_dev_priv), name,
			   ipoib_setup);
	if (!dev)
		return NULL;

	return netdev_priv(dev);
}

static ssize_t show_pkey(struct device *dev,
			 struct device_attribute *attr, char *buf)
{
	struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));

	return sprintf(buf, "0x%04x\n", priv->pkey);
}
static DEVICE_ATTR(pkey, S_IRUGO, show_pkey, NULL);

static ssize_t show_umcast(struct device *dev,
			   struct device_attribute *attr, char *buf)
{
	struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));

	return sprintf(buf, "%d\n", test_bit(IPOIB_FLAG_UMCAST, &priv->flags));
}

static ssize_t set_umcast(struct device *dev,
			  struct device_attribute *attr,
			  const char *buf, size_t count)
{
	struct ipoib_dev_priv *priv = netdev_priv(to_net_dev(dev));
	unsigned long umcast_val = simple_strtoul(buf, NULL, 0);

	if (umcast_val > 0) {
		set_bit(IPOIB_FLAG_UMCAST, &priv->flags);
		ipoib_warn(priv, "ignoring multicast groups joined directly "
				"by userspace\n");
	} else
		clear_bit(IPOIB_FLAG_UMCAST, &priv->flags);

	return count;
}
static DEVICE_ATTR(umcast, S_IWUSR | S_IRUGO, show_umcast, set_umcast);

int ipoib_add_umcast_attr(struct net_device *dev)
{
	return device_create_file(&dev->dev, &dev_attr_umcast);
}

static ssize_t create_child(struct device *dev,
			    struct device_attribute *attr,
			    const char *buf, size_t count)
{
	int pkey;
	int ret;

	if (sscanf(buf, "%i", &pkey) != 1)
		return -EINVAL;

	if (pkey < 0 || pkey > 0xffff)
		return -EINVAL;

	/*
	 * Set the full membership bit, so that we join the right
	 * broadcast group, etc.
	 */
	pkey |= 0x8000;

	ret = ipoib_vlan_add(to_net_dev(dev), pkey);

	return ret ? ret : count;
}
static DEVICE_ATTR(create_child, S_IWUGO, NULL, create_child);

static ssize_t delete_child(struct device *dev,
			    struct device_attribute *attr,
			    const char *buf, size_t count)
{
	int pkey;
	int ret;

	if (sscanf(buf, "%i", &pkey) != 1)
		return -EINVAL;

	if (pkey < 0 || pkey > 0xffff)
		return -EINVAL;

	ret = ipoib_vlan_delete(to_net_dev(dev), pkey);

	return ret ? ret : count;

}
static DEVICE_ATTR(delete_child, S_IWUGO, NULL, delete_child);

int ipoib_add_pkey_attr(struct net_device *dev)
{
	return device_create_file(&dev->dev, &dev_attr_pkey);
}

static struct net_device *ipoib_add_port(const char *format,
					 struct ib_device *hca, u8 port)
{
	struct ipoib_dev_priv *priv;
	int result = -ENOMEM;

	priv = ipoib_intf_alloc(format);
	if (!priv)
		goto alloc_mem_failed;

	SET_NETDEV_DEV(priv->dev, hca->dma_device);

	result = ib_query_pkey(hca, port, 0, &priv->pkey);
	if (result) {
		printk(KERN_WARNING "%s: ib_query_pkey port %d failed (ret = %d)\n",
		       hca->name, port, result);
		goto device_init_failed;
	}

	/*
	 * Set the full membership bit, so that we join the right
	 * broadcast group, etc.
	 */
	priv->pkey |= 0x8000;

	priv->dev->broadcast[8] = priv->pkey >> 8;
	priv->dev->broadcast[9] = priv->pkey & 0xff;

	result = ib_query_gid(hca, port, 0, &priv->local_gid);
	if (result) {
		printk(KERN_WARNING "%s: ib_query_gid port %d failed (ret = %d)\n",
		       hca->name, port, result);
		goto device_init_failed;
	} else
		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));


	result = ipoib_dev_init(priv->dev, hca, port);
	if (result < 0) {
		printk(KERN_WARNING "%s: failed to initialize port %d (ret = %d)\n",
		       hca->name, port, result);
		goto device_init_failed;
	}

	INIT_IB_EVENT_HANDLER(&priv->event_handler,
			      priv->ca, ipoib_event);
	result = ib_register_event_handler(&priv->event_handler);
	if (result < 0) {
		printk(KERN_WARNING "%s: ib_register_event_handler failed for "
		       "port %d (ret = %d)\n",
		       hca->name, port, result);
		goto event_failed;
	}

	result = register_netdev(priv->dev);
	if (result) {
		printk(KERN_WARNING "%s: couldn't register ipoib port %d; error %d\n",
		       hca->name, port, result);
		goto register_failed;
	}

	ipoib_create_debug_files(priv->dev);

	if (ipoib_cm_add_mode_attr(priv->dev))
		goto sysfs_failed;
	if (ipoib_add_pkey_attr(priv->dev))
		goto sysfs_failed;
	if (ipoib_add_umcast_attr(priv->dev))
		goto sysfs_failed;
	if (device_create_file(&priv->dev->dev, &dev_attr_create_child))
		goto sysfs_failed;
	if (device_create_file(&priv->dev->dev, &dev_attr_delete_child))
		goto sysfs_failed;

	return priv->dev;

sysfs_failed:
	ipoib_delete_debug_files(priv->dev);
	unregister_netdev(priv->dev);

register_failed:
	ib_unregister_event_handler(&priv->event_handler);
	flush_scheduled_work();

event_failed:
	ipoib_dev_cleanup(priv->dev);

device_init_failed:
	free_netdev(priv->dev);

alloc_mem_failed:
	return ERR_PTR(result);
}

static void ipoib_add_one(struct ib_device *device)
{
	struct list_head *dev_list;
	struct net_device *dev;
	struct ipoib_dev_priv *priv;
	int s, e, p;

	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
		return;

	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
	if (!dev_list)
		return;

	INIT_LIST_HEAD(dev_list);

	if (device->node_type == RDMA_NODE_IB_SWITCH) {
		s = 0;
		e = 0;
	} else {
		s = 1;
		e = device->phys_port_cnt;
	}

	for (p = s; p <= e; ++p) {
		dev = ipoib_add_port("ib%d", device, p);
		if (!IS_ERR(dev)) {
			priv = netdev_priv(dev);
			list_add_tail(&priv->list, dev_list);
		}
	}

	ib_set_client_data(device, &ipoib_client, dev_list);
}

static void ipoib_remove_one(struct ib_device *device)
{
	struct ipoib_dev_priv *priv, *tmp;
	struct list_head *dev_list;

	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
		return;

	dev_list = ib_get_client_data(device, &ipoib_client);

	list_for_each_entry_safe(priv, tmp, dev_list, list) {
		ib_unregister_event_handler(&priv->event_handler);
		flush_scheduled_work();

		unregister_netdev(priv->dev);
		ipoib_dev_cleanup(priv->dev);
		free_netdev(priv->dev);
	}

	kfree(dev_list);
}

static int __init ipoib_init_module(void)
{
	int ret;

	ipoib_recvq_size = roundup_pow_of_two(ipoib_recvq_size);
	ipoib_recvq_size = min(ipoib_recvq_size, IPOIB_MAX_QUEUE_SIZE);
	ipoib_recvq_size = max(ipoib_recvq_size, IPOIB_MIN_QUEUE_SIZE);

	ipoib_sendq_size = roundup_pow_of_two(ipoib_sendq_size);
	ipoib_sendq_size = min(ipoib_sendq_size, IPOIB_MAX_QUEUE_SIZE);
	ipoib_sendq_size = max(ipoib_sendq_size, IPOIB_MIN_QUEUE_SIZE);

	ret = ipoib_register_debugfs();
	if (ret)
		return ret;

	/*
	 * We create our own workqueue mainly because we want to be
	 * able to flush it when devices are being removed.  We can't
	 * use schedule_work()/flush_scheduled_work() because both
	 * unregister_netdev() and linkwatch_event take the rtnl lock,
	 * so flush_scheduled_work() can deadlock during device
	 * removal.
	 */
	ipoib_workqueue = create_singlethread_workqueue("ipoib");
	if (!ipoib_workqueue) {
		ret = -ENOMEM;
		goto err_fs;
	}

	ib_sa_register_client(&ipoib_sa_client);

	ret = ib_register_client(&ipoib_client);
	if (ret)
		goto err_sa;

	return 0;

err_sa:
	ib_sa_unregister_client(&ipoib_sa_client);
	destroy_workqueue(ipoib_workqueue);

err_fs:
	ipoib_unregister_debugfs();

	return ret;
}

static void __exit ipoib_cleanup_module(void)
{
	ib_unregister_client(&ipoib_client);
	ib_sa_unregister_client(&ipoib_sa_client);
	ipoib_unregister_debugfs();
	destroy_workqueue(ipoib_workqueue);
}

module_init(ipoib_init_module);
module_exit(ipoib_cleanup_module);