[mirror_ubuntu-bionic-kernel.git] / drivers / net / veth.c

/*
 *  drivers/net/veth.c
 *
 *  Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc
 *
 * Author: Pavel Emelianov <xemul@openvz.org>
 * Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com>
 *
 */

#include <linux/netdevice.h>
#include <linux/slab.h>
#include <linux/ethtool.h>
#include <linux/etherdevice.h>
#include <linux/u64_stats_sync.h>

#include <net/dst.h>
#include <net/xfrm.h>
#include <linux/veth.h>
#include <linux/module.h>

#define DRV_NAME	"veth"
#define DRV_VERSION	"1.0"

#define MIN_MTU 68		/* Min L3 MTU */
#define MAX_MTU 65535		/* Max L3 MTU (arbitrary) */

struct pcpu_vstats {
	u64			packets;
	u64			bytes;
	struct u64_stats_sync	syncp;
};

struct veth_priv {
	struct net_device	*peer;
	atomic64_t		dropped;
};

/*
 * ethtool interface
 */

static struct {
	const char string[ETH_GSTRING_LEN];
} ethtool_stats_keys[] = {
	{ "peer_ifindex" },
};

static int veth_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
{
	cmd->supported		= 0;
	cmd->advertising	= 0;
	ethtool_cmd_speed_set(cmd, SPEED_10000);
	cmd->duplex		= DUPLEX_FULL;
	cmd->port		= PORT_TP;
	cmd->phy_address	= 0;
	cmd->transceiver	= XCVR_INTERNAL;
	cmd->autoneg		= AUTONEG_DISABLE;
	cmd->maxtxpkt		= 0;
	cmd->maxrxpkt		= 0;
	return 0;
}

static void veth_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info)
{
	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
}

static void veth_get_strings(struct net_device *dev, u32 stringset, u8 *buf)
{
	switch(stringset) {
	case ETH_SS_STATS:
		memcpy(buf, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
		break;
	}
}

static int veth_get_sset_count(struct net_device *dev, int sset)
{
	switch (sset) {
	case ETH_SS_STATS:
		return ARRAY_SIZE(ethtool_stats_keys);
	default:
		return -EOPNOTSUPP;
	}
}

static void veth_get_ethtool_stats(struct net_device *dev,
		struct ethtool_stats *stats, u64 *data)
{
	struct veth_priv *priv;

	priv = netdev_priv(dev);
	data[0] = priv->peer->ifindex;
}

static const struct ethtool_ops veth_ethtool_ops = {
	.get_settings		= veth_get_settings,
	.get_drvinfo		= veth_get_drvinfo,
	.get_link		= ethtool_op_get_link,
	.get_strings		= veth_get_strings,
	.get_sset_count		= veth_get_sset_count,
	.get_ethtool_stats	= veth_get_ethtool_stats,
};

static netdev_tx_t veth_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct veth_priv *priv = netdev_priv(dev);
	struct net_device *rcv = priv->peer;
	int length = skb->len;

	/* don't change ip_summed == CHECKSUM_PARTIAL, as that
	 * will cause bad checksum on forwarded packets
	 */
	if (skb->ip_summed == CHECKSUM_NONE &&
	    rcv->features & NETIF_F_RXCSUM)
		skb->ip_summed = CHECKSUM_UNNECESSARY;

	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
		struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);

		u64_stats_update_begin(&stats->syncp);
		stats->bytes += length;
		stats->packets++;
		u64_stats_update_end(&stats->syncp);
	} else {
		atomic64_inc(&priv->dropped);
	}

	return NETDEV_TX_OK;
}

/*
 * general routines
 */

static u64 veth_stats_one(struct pcpu_vstats *result, struct net_device *dev)
{
	struct veth_priv *priv = netdev_priv(dev);
	int cpu;

	result->packets = 0;
	result->bytes = 0;
	for_each_possible_cpu(cpu) {
		struct pcpu_vstats *stats = per_cpu_ptr(dev->vstats, cpu);
		u64 packets, bytes;
		unsigned int start;

		do {
			start = u64_stats_fetch_begin_bh(&stats->syncp);
			packets = stats->packets;
			bytes = stats->bytes;
		} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
		result->packets += packets;
		result->bytes += bytes;
	}
	return atomic64_read(&priv->dropped);
}

static struct rtnl_link_stats64 *veth_get_stats64(struct net_device *dev,
						  struct rtnl_link_stats64 *tot)
{
	struct veth_priv *priv = netdev_priv(dev);
	struct pcpu_vstats one;

	tot->tx_dropped = veth_stats_one(&one, dev);
	tot->tx_bytes = one.bytes;
	tot->tx_packets = one.packets;

	tot->rx_dropped = veth_stats_one(&one, priv->peer);
	tot->rx_bytes = one.bytes;
	tot->rx_packets = one.packets;

	return tot;
}

static int veth_open(struct net_device *dev)
{
	struct veth_priv *priv;

	priv = netdev_priv(dev);
	if (priv->peer == NULL)
		return -ENOTCONN;

	if (priv->peer->flags & IFF_UP) {
		netif_carrier_on(dev);
		netif_carrier_on(priv->peer);
	}
	return 0;
}

static int veth_close(struct net_device *dev)
{
	struct veth_priv *priv = netdev_priv(dev);

	netif_carrier_off(dev);
	netif_carrier_off(priv->peer);

	return 0;
}

static int is_valid_veth_mtu(int new_mtu)
{
	return new_mtu >= MIN_MTU && new_mtu <= MAX_MTU;
}

static int veth_change_mtu(struct net_device *dev, int new_mtu)
{
	if (!is_valid_veth_mtu(new_mtu))
		return -EINVAL;
	dev->mtu = new_mtu;
	return 0;
}

static int veth_dev_init(struct net_device *dev)
{
	dev->vstats = alloc_percpu(struct pcpu_vstats);
	if (!dev->vstats)
		return -ENOMEM;

	return 0;
}

static void veth_dev_free(struct net_device *dev)
{
	free_percpu(dev->vstats);
	free_netdev(dev);
}

static const struct net_device_ops veth_netdev_ops = {
	.ndo_init            = veth_dev_init,
	.ndo_open            = veth_open,
	.ndo_stop            = veth_close,
	.ndo_start_xmit      = veth_xmit,
	.ndo_change_mtu      = veth_change_mtu,
	.ndo_get_stats64     = veth_get_stats64,
	.ndo_set_mac_address = eth_mac_addr,
};

#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_ALL_TSO |    \
		       NETIF_F_HW_CSUM | NETIF_F_RXCSUM | NETIF_F_HIGHDMA | \
		       NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX)

static void veth_setup(struct net_device *dev)
{
	ether_setup(dev);

	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;

	dev->netdev_ops = &veth_netdev_ops;
	dev->ethtool_ops = &veth_ethtool_ops;
	dev->features |= NETIF_F_LLTX;
	dev->features |= VETH_FEATURES;
	dev->destructor = veth_dev_free;

	dev->hw_features = VETH_FEATURES;
}

/*
 * netlink interface
 */

static int veth_validate(struct nlattr *tb[], struct nlattr *data[])
{
	if (tb[IFLA_ADDRESS]) {
		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
			return -EINVAL;
		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
			return -EADDRNOTAVAIL;
	}
	if (tb[IFLA_MTU]) {
		if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU])))
			return -EINVAL;
	}
	return 0;
}

static struct rtnl_link_ops veth_link_ops;

static int veth_newlink(struct net *src_net, struct net_device *dev,
			 struct nlattr *tb[], struct nlattr *data[])
{
	int err;
	struct net_device *peer;
	struct veth_priv *priv;
	char ifname[IFNAMSIZ];
	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp;
	struct ifinfomsg *ifmp;
	struct net *net;

	/*
	 * create and register peer first
	 */
	if (data != NULL && data[VETH_INFO_PEER] != NULL) {
		struct nlattr *nla_peer;

		nla_peer = data[VETH_INFO_PEER];
		ifmp = nla_data(nla_peer);
		err = nla_parse(peer_tb, IFLA_MAX,
				nla_data(nla_peer) + sizeof(struct ifinfomsg),
				nla_len(nla_peer) - sizeof(struct ifinfomsg),
				ifla_policy);
		if (err < 0)
			return err;

		err = veth_validate(peer_tb, NULL);
		if (err < 0)
			return err;

		tbp = peer_tb;
	} else {
		ifmp = NULL;
		tbp = tb;
	}

	if (tbp[IFLA_IFNAME])
		nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
	else
		snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");

	net = rtnl_link_get_net(src_net, tbp);
	if (IS_ERR(net))
		return PTR_ERR(net);

	peer = rtnl_create_link(net, ifname, &veth_link_ops, tbp);
	if (IS_ERR(peer)) {
		put_net(net);
		return PTR_ERR(peer);
	}

	if (tbp[IFLA_ADDRESS] == NULL)
		eth_hw_addr_random(peer);

	if (ifmp && (dev->ifindex != 0))
		peer->ifindex = ifmp->ifi_index;

	err = register_netdevice(peer);
	put_net(net);
	net = NULL;
	if (err < 0)
		goto err_register_peer;

	netif_carrier_off(peer);

	err = rtnl_configure_link(peer, ifmp);
	if (err < 0)
		goto err_configure_peer;

	/*
	 * register dev last
	 *
	 * note, that since we've registered new device the dev's name
	 * should be re-allocated
	 */

	if (tb[IFLA_ADDRESS] == NULL)
		eth_hw_addr_random(dev);

	if (tb[IFLA_IFNAME])
		nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
	else
		snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");

	if (strchr(dev->name, '%')) {
		err = dev_alloc_name(dev, dev->name);
		if (err < 0)
			goto err_alloc_name;
	}

	err = register_netdevice(dev);
	if (err < 0)
		goto err_register_dev;

	netif_carrier_off(dev);

	/*
	 * tie the deviced together
	 */

	priv = netdev_priv(dev);
	priv->peer = peer;

	priv = netdev_priv(peer);
	priv->peer = dev;
	return 0;

err_register_dev:
	/* nothing to do */
err_alloc_name:
err_configure_peer:
	unregister_netdevice(peer);
	return err;

err_register_peer:
	free_netdev(peer);
	return err;
}

static void veth_dellink(struct net_device *dev, struct list_head *head)
{
	struct veth_priv *priv;
	struct net_device *peer;

	priv = netdev_priv(dev);
	peer = priv->peer;

	unregister_netdevice_queue(dev, head);
	unregister_netdevice_queue(peer, head);
}

static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
	[VETH_INFO_PEER]	= { .len = sizeof(struct ifinfomsg) },
};

static struct rtnl_link_ops veth_link_ops = {
	.kind		= DRV_NAME,
	.priv_size	= sizeof(struct veth_priv),
	.setup		= veth_setup,
	.validate	= veth_validate,
	.newlink	= veth_newlink,
	.dellink	= veth_dellink,
	.policy		= veth_policy,
	.maxtype	= VETH_INFO_MAX,
};

/*
 * init/fini
 */

static __init int veth_init(void)
{
	return rtnl_link_register(&veth_link_ops);
}

static __exit void veth_exit(void)
{
	rtnl_link_unregister(&veth_link_ops);
}

module_init(veth_init);
module_exit(veth_exit);

MODULE_DESCRIPTION("Virtual Ethernet Tunnel");
MODULE_LICENSE("GPL v2");
MODULE_ALIAS_RTNL_LINK(DRV_NAME);
Commit	Line	Data
e314dbdc PE	1	/*
	2	* drivers/net/veth.c
	3	*
	4	* Copyright (C) 2007 OpenVZ http://openvz.org, SWsoft Inc
	5	*
	6	* Author: Pavel Emelianov <xemul@openvz.org>
	7	* Ethtool interface from: Eric W. Biederman <ebiederm@xmission.com>
	8	*
	9	*/
	10
e314dbdc	11	#include <linux/netdevice.h>
5a0e3ad6	12	#include <linux/slab.h>
e314dbdc PE	13	#include <linux/ethtool.h>
e314dbdc PE	14	#include <linux/etherdevice.h>
cf05c700	15	#include <linux/u64_stats_sync.h>
e314dbdc PE	16
	17	#include <net/dst.h>
	18	#include <net/xfrm.h>
ecef969e	19	#include <linux/veth.h>
9d9779e7	20	#include <linux/module.h>
e314dbdc PE	21
	22	#define DRV_NAME "veth"
	23	#define DRV_VERSION "1.0"
	24
38d40815 EB	25	#define MIN_MTU 68 /* Min L3 MTU */
38d40815 EB	26	#define MAX_MTU 65535 /* Max L3 MTU (arbitrary) */
38d40815	27
2681128f ED	28	struct pcpu_vstats {
	29	u64 packets;
	30	u64 bytes;
cf05c700	31	struct u64_stats_sync syncp;
e314dbdc PE	32	};
	33
	34	struct veth_priv {
2681128f ED	35	struct net_device *peer;
2681128f ED	36	atomic64_t dropped;
e314dbdc PE	37	};
e314dbdc PE	38
e314dbdc PE	39	/*
	40	* ethtool interface
	41	*/
	42
	43	static struct {
	44	const char string[ETH_GSTRING_LEN];
	45	} ethtool_stats_keys[] = {
	46	{ "peer_ifindex" },
	47	};
	48
	49	static int veth_get_settings(struct net_device dev, struct ethtool_cmd cmd)
	50	{
	51	cmd->supported = 0;
	52	cmd->advertising = 0;
70739497	53	ethtool_cmd_speed_set(cmd, SPEED_10000);
e314dbdc PE	54	cmd->duplex = DUPLEX_FULL;
	55	cmd->port = PORT_TP;
	56	cmd->phy_address = 0;
	57	cmd->transceiver = XCVR_INTERNAL;
	58	cmd->autoneg = AUTONEG_DISABLE;
	59	cmd->maxtxpkt = 0;
	60	cmd->maxrxpkt = 0;
	61	return 0;
	62	}
	63
	64	static void veth_get_drvinfo(struct net_device dev, struct ethtool_drvinfo info)
	65	{
33a5ba14 RJ	66	strlcpy(info->driver, DRV_NAME, sizeof(info->driver));
33a5ba14 RJ	67	strlcpy(info->version, DRV_VERSION, sizeof(info->version));
e314dbdc PE	68	}
	69
	70	static void veth_get_strings(struct net_device dev, u32 stringset, u8 buf)
	71	{
	72	switch(stringset) {
	73	case ETH_SS_STATS:
	74	memcpy(buf, &ethtool_stats_keys, sizeof(ethtool_stats_keys));
	75	break;
	76	}
	77	}
	78
b9f2c044	79	static int veth_get_sset_count(struct net_device *dev, int sset)
e314dbdc	80	{
b9f2c044 JG	81	switch (sset) {
	82	case ETH_SS_STATS:
	83	return ARRAY_SIZE(ethtool_stats_keys);
	84	default:
	85	return -EOPNOTSUPP;
	86	}
e314dbdc PE	87	}
	88
	89	static void veth_get_ethtool_stats(struct net_device *dev,
	90	struct ethtool_stats stats, u64 data)
	91	{
	92	struct veth_priv *priv;
	93
	94	priv = netdev_priv(dev);
	95	data[0] = priv->peer->ifindex;
	96	}
	97
0fc0b732	98	static const struct ethtool_ops veth_ethtool_ops = {
e314dbdc PE	99	.get_settings = veth_get_settings,
	100	.get_drvinfo = veth_get_drvinfo,
	101	.get_link = ethtool_op_get_link,
e314dbdc	102	.get_strings = veth_get_strings,
b9f2c044	103	.get_sset_count = veth_get_sset_count,
e314dbdc PE	104	.get_ethtool_stats = veth_get_ethtool_stats,
	105	};
	106
424efe9c	107	static netdev_tx_t veth_xmit(struct sk_buff skb, struct net_device dev)
e314dbdc	108	{
2681128f ED	109	struct veth_priv *priv = netdev_priv(dev);
	110	struct net_device *rcv = priv->peer;
	111	int length = skb->len;
e314dbdc	112
0b796750	113	/* don't change ip_summed == CHECKSUM_PARTIAL, as that
2681128f ED	114	* will cause bad checksum on forwarded packets
2681128f ED	115	*/
a2c725fa MM	116	if (skb->ip_summed == CHECKSUM_NONE &&
	117	rcv->features & NETIF_F_RXCSUM)
	118	skb->ip_summed = CHECKSUM_UNNECESSARY;
e314dbdc	119
2681128f ED	120	if (likely(dev_forward_skb(rcv, skb) == NET_RX_SUCCESS)) {
2681128f ED	121	struct pcpu_vstats *stats = this_cpu_ptr(dev->vstats);
e314dbdc	122
2681128f ED	123	u64_stats_update_begin(&stats->syncp);
	124	stats->bytes += length;
	125	stats->packets++;
	126	u64_stats_update_end(&stats->syncp);
	127	} else {
	128	atomic64_inc(&priv->dropped);
	129	}
e314dbdc	130
6ed10654	131	return NETDEV_TX_OK;
e314dbdc PE	132	}
	133
	134	/*
	135	* general routines
	136	*/
	137
2681128f	138	static u64 veth_stats_one(struct pcpu_vstats result, struct net_device dev)
e314dbdc	139	{
cf05c700	140	struct veth_priv *priv = netdev_priv(dev);
11687a10	141	int cpu;
e314dbdc	142
2681128f ED	143	result->packets = 0;
2681128f ED	144	result->bytes = 0;
2b1c8b0f	145	for_each_possible_cpu(cpu) {
2681128f ED	146	struct pcpu_vstats *stats = per_cpu_ptr(dev->vstats, cpu);
2681128f ED	147	u64 packets, bytes;
cf05c700 ED	148	unsigned int start;
	149
	150	do {
	151	start = u64_stats_fetch_begin_bh(&stats->syncp);
2681128f ED	152	packets = stats->packets;
2681128f ED	153	bytes = stats->bytes;
cf05c700	154	} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
2681128f ED	155	result->packets += packets;
2681128f ED	156	result->bytes += bytes;
11687a10	157	}
2681128f ED	158	return atomic64_read(&priv->dropped);
	159	}
	160
	161	static struct rtnl_link_stats64 veth_get_stats64(struct net_device dev,
	162	struct rtnl_link_stats64 *tot)
	163	{
	164	struct veth_priv *priv = netdev_priv(dev);
	165	struct pcpu_vstats one;
	166
	167	tot->tx_dropped = veth_stats_one(&one, dev);
	168	tot->tx_bytes = one.bytes;
	169	tot->tx_packets = one.packets;
	170
	171	tot->rx_dropped = veth_stats_one(&one, priv->peer);
	172	tot->rx_bytes = one.bytes;
	173	tot->rx_packets = one.packets;
6311cc44	174
6311cc44	175	return tot;
e314dbdc PE	176	}
	177
	178	static int veth_open(struct net_device *dev)
	179	{
	180	struct veth_priv *priv;
	181
	182	priv = netdev_priv(dev);
	183	if (priv->peer == NULL)
	184	return -ENOTCONN;
	185
	186	if (priv->peer->flags & IFF_UP) {
	187	netif_carrier_on(dev);
	188	netif_carrier_on(priv->peer);
	189	}
	190	return 0;
	191	}
	192
2cf48a10 EB	193	static int veth_close(struct net_device *dev)
	194	{
	195	struct veth_priv *priv = netdev_priv(dev);
	196
	197	netif_carrier_off(dev);
	198	netif_carrier_off(priv->peer);
	199
	200	return 0;
	201	}
	202
38d40815 EB	203	static int is_valid_veth_mtu(int new_mtu)
38d40815 EB	204	{
807540ba	205	return new_mtu >= MIN_MTU && new_mtu <= MAX_MTU;
38d40815 EB	206	}
	207
	208	static int veth_change_mtu(struct net_device *dev, int new_mtu)
	209	{
	210	if (!is_valid_veth_mtu(new_mtu))
	211	return -EINVAL;
	212	dev->mtu = new_mtu;
	213	return 0;
	214	}
	215
e314dbdc PE	216	static int veth_dev_init(struct net_device *dev)
e314dbdc PE	217	{
2681128f ED	218	dev->vstats = alloc_percpu(struct pcpu_vstats);
2681128f ED	219	if (!dev->vstats)
e314dbdc PE	220	return -ENOMEM;
e314dbdc PE	221
e314dbdc PE	222	return 0;
	223	}
	224
11687a10 DM	225	static void veth_dev_free(struct net_device *dev)
11687a10 DM	226	{
2681128f	227	free_percpu(dev->vstats);
11687a10 DM	228	free_netdev(dev);
	229	}
	230
4456e7bd	231	static const struct net_device_ops veth_netdev_ops = {
ee923623 DL	232	.ndo_init = veth_dev_init,
ee923623 DL	233	.ndo_open = veth_open,
2cf48a10	234	.ndo_stop = veth_close,
ee923623	235	.ndo_start_xmit = veth_xmit,
38d40815	236	.ndo_change_mtu = veth_change_mtu,
6311cc44	237	.ndo_get_stats64 = veth_get_stats64,
ee923623	238	.ndo_set_mac_address = eth_mac_addr,
4456e7bd SH	239	};
4456e7bd SH	240
8093315a ED	241	#define VETH_FEATURES (NETIF_F_SG \| NETIF_F_FRAGLIST \| NETIF_F_ALL_TSO \| \
	242	NETIF_F_HW_CSUM \| NETIF_F_RXCSUM \| NETIF_F_HIGHDMA \| \
	243	NETIF_F_HW_VLAN_TX \| NETIF_F_HW_VLAN_RX)
	244
e314dbdc PE	245	static void veth_setup(struct net_device *dev)
	246	{
	247	ether_setup(dev);
	248
550fd08c	249	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
23ea5a96	250	dev->priv_flags \|= IFF_LIVE_ADDR_CHANGE;
550fd08c	251
4456e7bd	252	dev->netdev_ops = &veth_netdev_ops;
e314dbdc PE	253	dev->ethtool_ops = &veth_ethtool_ops;
e314dbdc PE	254	dev->features \|= NETIF_F_LLTX;
8093315a	255	dev->features \|= VETH_FEATURES;
11687a10	256	dev->destructor = veth_dev_free;
a2c725fa	257
8093315a	258	dev->hw_features = VETH_FEATURES;
e314dbdc PE	259	}
	260
	261	/*
	262	* netlink interface
	263	*/
	264
	265	static int veth_validate(struct nlattr tb[], struct nlattr data[])
	266	{
	267	if (tb[IFLA_ADDRESS]) {
	268	if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN)
	269	return -EINVAL;
	270	if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS])))
	271	return -EADDRNOTAVAIL;
	272	}
38d40815 EB	273	if (tb[IFLA_MTU]) {
	274	if (!is_valid_veth_mtu(nla_get_u32(tb[IFLA_MTU])))
	275	return -EINVAL;
	276	}
e314dbdc PE	277	return 0;
	278	}
	279
	280	static struct rtnl_link_ops veth_link_ops;
	281
81adee47	282	static int veth_newlink(struct net src_net, struct net_device dev,
e314dbdc PE	283	struct nlattr tb[], struct nlattr data[])
	284	{
	285	int err;
	286	struct net_device *peer;
	287	struct veth_priv *priv;
	288	char ifname[IFNAMSIZ];
	289	struct nlattr peer_tb[IFLA_MAX + 1], *tbp;
3729d502	290	struct ifinfomsg *ifmp;
81adee47	291	struct net *net;
e314dbdc PE	292
	293	/*
	294	* create and register peer first
e314dbdc	295	*/
e314dbdc PE	296	if (data != NULL && data[VETH_INFO_PEER] != NULL) {
	297	struct nlattr *nla_peer;
	298
	299	nla_peer = data[VETH_INFO_PEER];
3729d502	300	ifmp = nla_data(nla_peer);
e314dbdc PE	301	err = nla_parse(peer_tb, IFLA_MAX,
	302	nla_data(nla_peer) + sizeof(struct ifinfomsg),
	303	nla_len(nla_peer) - sizeof(struct ifinfomsg),
	304	ifla_policy);
	305	if (err < 0)
	306	return err;
	307
	308	err = veth_validate(peer_tb, NULL);
	309	if (err < 0)
	310	return err;
	311
	312	tbp = peer_tb;
3729d502 PM	313	} else {
3729d502 PM	314	ifmp = NULL;
e314dbdc	315	tbp = tb;
3729d502	316	}
e314dbdc PE	317
	318	if (tbp[IFLA_IFNAME])
	319	nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ);
	320	else
	321	snprintf(ifname, IFNAMSIZ, DRV_NAME "%%d");
	322
81adee47 EB	323	net = rtnl_link_get_net(src_net, tbp);
	324	if (IS_ERR(net))
	325	return PTR_ERR(net);
	326
c0713563	327	peer = rtnl_create_link(net, ifname, &veth_link_ops, tbp);
81adee47 EB	328	if (IS_ERR(peer)) {
81adee47 EB	329	put_net(net);
e314dbdc	330	return PTR_ERR(peer);
81adee47	331	}
e314dbdc PE	332
e314dbdc PE	333	if (tbp[IFLA_ADDRESS] == NULL)
f2cedb63	334	eth_hw_addr_random(peer);
e6f8f1a7 PE	335
	336	if (ifmp && (dev->ifindex != 0))
	337	peer->ifindex = ifmp->ifi_index;
e314dbdc PE	338
e314dbdc PE	339	err = register_netdevice(peer);
81adee47 EB	340	put_net(net);
81adee47 EB	341	net = NULL;
e314dbdc PE	342	if (err < 0)
	343	goto err_register_peer;
	344
	345	netif_carrier_off(peer);
	346
3729d502 PM	347	err = rtnl_configure_link(peer, ifmp);
	348	if (err < 0)
	349	goto err_configure_peer;
	350
e314dbdc PE	351	/*
	352	* register dev last
	353	*
	354	* note, that since we've registered new device the dev's name
	355	* should be re-allocated
	356	*/
	357
	358	if (tb[IFLA_ADDRESS] == NULL)
f2cedb63	359	eth_hw_addr_random(dev);
e314dbdc	360
6c8c4446 JP	361	if (tb[IFLA_IFNAME])
	362	nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ);
	363	else
	364	snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");
	365
	366	if (strchr(dev->name, '%')) {
	367	err = dev_alloc_name(dev, dev->name);
	368	if (err < 0)
	369	goto err_alloc_name;
	370	}
	371
e314dbdc PE	372	err = register_netdevice(dev);
	373	if (err < 0)
	374	goto err_register_dev;
	375
	376	netif_carrier_off(dev);
	377
	378	/*
	379	* tie the deviced together
	380	*/
	381
	382	priv = netdev_priv(dev);
e314dbdc	383	priv->peer = peer;
e314dbdc PE	384
e314dbdc PE	385	priv = netdev_priv(peer);
e314dbdc	386	priv->peer = dev;
e314dbdc PE	387	return 0;
	388
	389	err_register_dev:
	390	/* nothing to do */
6c8c4446	391	err_alloc_name:
3729d502	392	err_configure_peer:
e314dbdc PE	393	unregister_netdevice(peer);
	394	return err;
	395
	396	err_register_peer:
	397	free_netdev(peer);
	398	return err;
	399	}
	400
23289a37	401	static void veth_dellink(struct net_device dev, struct list_head head)
e314dbdc PE	402	{
	403	struct veth_priv *priv;
	404	struct net_device *peer;
	405
	406	priv = netdev_priv(dev);
	407	peer = priv->peer;
	408
24540535 ED	409	unregister_netdevice_queue(dev, head);
24540535 ED	410	unregister_netdevice_queue(peer, head);
e314dbdc PE	411	}
e314dbdc PE	412
23711438 TG	413	static const struct nla_policy veth_policy[VETH_INFO_MAX + 1] = {
	414	[VETH_INFO_PEER] = { .len = sizeof(struct ifinfomsg) },
	415	};
e314dbdc PE	416
	417	static struct rtnl_link_ops veth_link_ops = {
	418	.kind = DRV_NAME,
	419	.priv_size = sizeof(struct veth_priv),
	420	.setup = veth_setup,
	421	.validate = veth_validate,
	422	.newlink = veth_newlink,
	423	.dellink = veth_dellink,
	424	.policy = veth_policy,
	425	.maxtype = VETH_INFO_MAX,
	426	};
	427
	428	/*
	429	* init/fini
	430	*/
	431
	432	static __init int veth_init(void)
	433	{
	434	return rtnl_link_register(&veth_link_ops);
	435	}
	436
	437	static __exit void veth_exit(void)
	438	{
68365458	439	rtnl_link_unregister(&veth_link_ops);
e314dbdc PE	440	}
	441
	442	module_init(veth_init);
	443	module_exit(veth_exit);
	444
	445	MODULE_DESCRIPTION("Virtual Ethernet Tunnel");
	446	MODULE_LICENSE("GPL v2");
	447	MODULE_ALIAS_RTNL_LINK(DRV_NAME);