geneve.c 18.4 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17
/*
 * GENEVE: Generic Network Virtualization Encapsulation
 *
 * Copyright (c) 2015 Red Hat, Inc.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/hash.h>
18
#include <net/dst_metadata.h>
19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39
#include <net/rtnetlink.h>
#include <net/geneve.h>

#define GENEVE_NETDEV_VER	"0.6"

#define GENEVE_UDP_PORT		6081

#define GENEVE_N_VID		(1u << 24)
#define GENEVE_VID_MASK		(GENEVE_N_VID - 1)

#define VNI_HASH_BITS		10
#define VNI_HASH_SIZE		(1<<VNI_HASH_BITS)

static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");

/* per-network namespace private data for this module */
struct geneve_net {
	struct list_head  geneve_list;
	struct hlist_head vni_list[VNI_HASH_SIZE];
40
	struct geneve_dev __rcu *collect_md_tun;
41 42 43 44 45 46 47 48
};

/* Pseudo network device */
struct geneve_dev {
	struct hlist_node  hlist;	/* vni hash table */
	struct net	   *net;	/* netns for packet i/o */
	struct net_device  *dev;	/* netdev for geneve tunnel */
	struct geneve_sock *sock;	/* socket used for geneve tunnel */
49 50
	u8                 vni[3];	/* virtual network ID for tunnel */
	u8                 ttl;		/* TTL override */
51
	u8                 tos;		/* TOS override */
52 53
	struct sockaddr_in remote;	/* IPv4 address for link partner */
	struct list_head   next;	/* geneve's per namespace list */
54
	__be16		   dst_port;
55
	bool		   collect_md;
56 57 58 59 60 61 62 63 64 65 66 67
};

static int geneve_net_id;

static inline __u32 geneve_net_vni_hash(u8 vni[3])
{
	__u32 vnid;

	vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2];
	return hash_32(vnid, VNI_HASH_BITS);
}

68 69 70 71 72 73 74 75 76 77 78 79 80 81 82
static __be64 vni_to_tunnel_id(const __u8 *vni)
{
#ifdef __BIG_ENDIAN
	return (vni[0] << 16) | (vni[1] << 8) | vni[2];
#else
	return (__force __be64)(((__force u64)vni[0] << 40) |
				((__force u64)vni[1] << 48) |
				((__force u64)vni[2] << 56));
#endif
}

static struct geneve_dev *geneve_lookup(struct geneve_net *gn,
					struct geneve_sock *gs,
					struct iphdr *iph,
					struct genevehdr *gnvh)
83
{
84
	struct inet_sock *sk = inet_sk(gs->sock->sk);
85
	struct hlist_head *vni_list_head;
86
	struct geneve_dev *geneve;
87 88
	__u32 hash;

89 90 91
	geneve = rcu_dereference(gn->collect_md_tun);
	if (geneve)
		return geneve;
92 93 94 95

	/* Find the device for this VNI */
	hash = geneve_net_vni_hash(gnvh->vni);
	vni_list_head = &gn->vni_list[hash];
96 97 98 99 100
	hlist_for_each_entry_rcu(geneve, vni_list_head, hlist) {
		if (!memcmp(gnvh->vni, geneve->vni, sizeof(geneve->vni)) &&
		    iph->saddr == geneve->remote.sin_addr.s_addr &&
		    sk->inet_sport == geneve->dst_port) {
			return geneve;
101 102
		}
	}
103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119
	return NULL;
}

/* geneve receive/decap routine */
static void geneve_rx(struct geneve_sock *gs, struct sk_buff *skb)
{
	struct genevehdr *gnvh = geneve_hdr(skb);
	struct metadata_dst *tun_dst = NULL;
	struct geneve_dev *geneve = NULL;
	struct pcpu_sw_netstats *stats;
	struct geneve_net *gn;
	struct iphdr *iph;
	int err;

	iph = ip_hdr(skb); /* Still outer IP header... */
	gn = gs->rcv_data;
	geneve = geneve_lookup(gn, gs, iph, gnvh);
120 121 122
	if (!geneve)
		goto drop;

123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
	if (ip_tunnel_collect_metadata() || geneve->collect_md) {
		__be16 flags;
		void *opts;

		flags = TUNNEL_KEY | TUNNEL_GENEVE_OPT |
			(gnvh->oam ? TUNNEL_OAM : 0) |
			(gnvh->critical ? TUNNEL_CRIT_OPT : 0);

		tun_dst = udp_tun_rx_dst(skb, AF_INET, flags,
					 vni_to_tunnel_id(gnvh->vni),
					 gnvh->opt_len * 4);
		if (!tun_dst)
			goto drop;

		/* Update tunnel dst according to Geneve options. */
		opts = ip_tunnel_info_opts(&tun_dst->u.tun_info,
					   gnvh->opt_len * 4);
		memcpy(opts, gnvh->options, gnvh->opt_len * 4);
	} else {
		/* Drop packets w/ critical options,
		 * since we don't support any...
		 */
		if (gnvh->critical)
			goto drop;
	}
148 149 150 151 152 153

	skb_reset_mac_header(skb);
	skb_scrub_packet(skb, !net_eq(geneve->net, dev_net(geneve->dev)));
	skb->protocol = eth_type_trans(skb, geneve->dev);
	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);

154 155 156
	if (tun_dst)
		skb_dst_set(skb, &tun_dst->dst);

157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210
	/* Ignore packet loops (and multicast echo) */
	if (ether_addr_equal(eth_hdr(skb)->h_source, geneve->dev->dev_addr))
		goto drop;

	skb_reset_network_header(skb);

	iph = ip_hdr(skb); /* Now inner IP header... */
	err = IP_ECN_decapsulate(iph, skb);

	if (unlikely(err)) {
		if (log_ecn_error)
			net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
					     &iph->saddr, iph->tos);
		if (err > 1) {
			++geneve->dev->stats.rx_frame_errors;
			++geneve->dev->stats.rx_errors;
			goto drop;
		}
	}

	stats = this_cpu_ptr(geneve->dev->tstats);
	u64_stats_update_begin(&stats->syncp);
	stats->rx_packets++;
	stats->rx_bytes += skb->len;
	u64_stats_update_end(&stats->syncp);

	netif_rx(skb);
	return;
drop:
	/* Consume bad packet */
	kfree_skb(skb);
}

/* Setup stats when device is created */
static int geneve_init(struct net_device *dev)
{
	dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
	if (!dev->tstats)
		return -ENOMEM;
	return 0;
}

static void geneve_uninit(struct net_device *dev)
{
	free_percpu(dev->tstats);
}

static int geneve_open(struct net_device *dev)
{
	struct geneve_dev *geneve = netdev_priv(dev);
	struct net *net = geneve->net;
	struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);
	struct geneve_sock *gs;

211
	gs = geneve_sock_add(net, geneve->dst_port, geneve_rx, gn,
212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230
	                     false, false);
	if (IS_ERR(gs))
		return PTR_ERR(gs);

	geneve->sock = gs;

	return 0;
}

static int geneve_stop(struct net_device *dev)
{
	struct geneve_dev *geneve = netdev_priv(dev);
	struct geneve_sock *gs = geneve->sock;

	geneve_sock_release(gs);

	return 0;
}

231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
static struct rtable *geneve_get_rt(struct sk_buff *skb,
				    struct net_device *dev,
				    struct flowi4 *fl4,
				    struct ip_tunnel_info *info)
{
	struct geneve_dev *geneve = netdev_priv(dev);
	struct rtable *rt = NULL;
	__u8 tos;

	memset(fl4, 0, sizeof(*fl4));
	fl4->flowi4_mark = skb->mark;
	fl4->flowi4_proto = IPPROTO_UDP;

	if (info) {
		fl4->daddr = info->key.u.ipv4.dst;
		fl4->saddr = info->key.u.ipv4.src;
		fl4->flowi4_tos = RT_TOS(info->key.tos);
	} else {
		tos = geneve->tos;
		if (tos == 1) {
			const struct iphdr *iip = ip_hdr(skb);

			tos = ip_tunnel_get_dsfield(iip, skb);
		}

		fl4->flowi4_tos = RT_TOS(tos);
		fl4->daddr = geneve->remote.sin_addr.s_addr;
	}

	rt = ip_route_output_key(geneve->net, fl4);
	if (IS_ERR(rt)) {
		netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr);
		dev->stats.tx_carrier_errors++;
		return rt;
	}
	if (rt->dst.dev == dev) { /* is this necessary? */
		netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr);
		dev->stats.collisions++;
		ip_rt_put(rt);
		return ERR_PTR(-EINVAL);
	}

	return rt;
}

/* Convert 64 bit tunnel ID to 24 bit VNI. */
static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
{
#ifdef __BIG_ENDIAN
	vni[0] = (__force __u8)(tun_id >> 16);
	vni[1] = (__force __u8)(tun_id >> 8);
	vni[2] = (__force __u8)tun_id;
#else
	vni[0] = (__force __u8)((__force u64)tun_id >> 40);
	vni[1] = (__force __u8)((__force u64)tun_id >> 48);
	vni[2] = (__force __u8)((__force u64)tun_id >> 56);
#endif
}

290 291 292 293
static netdev_tx_t geneve_xmit(struct sk_buff *skb, struct net_device *dev)
{
	struct geneve_dev *geneve = netdev_priv(dev);
	struct geneve_sock *gs = geneve->sock;
294
	struct ip_tunnel_info *info = NULL;
295 296 297
	struct rtable *rt = NULL;
	const struct iphdr *iip; /* interior IP header */
	struct flowi4 fl4;
298
	__u8 tos, ttl;
299 300 301
	__be16 sport;
	bool xnet;
	int err;
302

303
	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
304

305 306 307 308 309 310 311
	if (geneve->collect_md) {
		info = skb_tunnel_info(skb);
		if (unlikely(info && info->mode != IP_TUNNEL_INFO_TX)) {
			netdev_dbg(dev, "no tunnel metadata\n");
			goto tx_error;
		}
	}
312

313
	rt = geneve_get_rt(skb, dev, &fl4, info);
314 315 316 317 318
	if (IS_ERR(rt)) {
		netdev_dbg(dev, "no route to %pI4\n", &fl4.daddr);
		dev->stats.tx_carrier_errors++;
		goto tx_error;
	}
319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354
	skb_reset_mac_header(skb);
	xnet = !net_eq(geneve->net, dev_net(geneve->dev));

	if (info) {
		const struct ip_tunnel_key *key = &info->key;
		bool udp_csum;
		u8 *opts = NULL;
		u8 vni[3];
		__be16 df;

		tunnel_id_to_vni(key->tun_id, vni);
		df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
		udp_csum = !!(key->tun_flags & TUNNEL_CSUM);

		if (key->tun_flags & TUNNEL_GENEVE_OPT)
			opts = ip_tunnel_info_opts(info, info->options_len);

		err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr,
				      key->tos, key->ttl, df,
				      sport, geneve->dst_port,
				      key->tun_flags, vni,
				      info->options_len, opts, udp_csum, xnet);
	} else {
		iip = ip_hdr(skb);
		tos = ip_tunnel_ecn_encap(fl4.flowi4_tos, iip, skb);

		ttl = geneve->ttl;
		if (!ttl && IN_MULTICAST(ntohl(fl4.daddr)))
			ttl = 1;

		ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);

		/* no need to handle local destination and encap bypass...yet... */
		err = geneve_xmit_skb(gs, rt, skb, fl4.saddr, fl4.daddr, tos,
				      ttl, 0, sport, geneve->dst_port, 0,
				      geneve->vni, 0, NULL, false, xnet);
355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420
	}
	if (err < 0)
		ip_rt_put(rt);

	iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
	return NETDEV_TX_OK;

tx_error:
	dev->stats.tx_errors++;
	dev_kfree_skb(skb);
	return NETDEV_TX_OK;
}

static const struct net_device_ops geneve_netdev_ops = {
	.ndo_init		= geneve_init,
	.ndo_uninit		= geneve_uninit,
	.ndo_open		= geneve_open,
	.ndo_stop		= geneve_stop,
	.ndo_start_xmit		= geneve_xmit,
	.ndo_get_stats64	= ip_tunnel_get_stats64,
	.ndo_change_mtu		= eth_change_mtu,
	.ndo_validate_addr	= eth_validate_addr,
	.ndo_set_mac_address	= eth_mac_addr,
};

static void geneve_get_drvinfo(struct net_device *dev,
			       struct ethtool_drvinfo *drvinfo)
{
	strlcpy(drvinfo->version, GENEVE_NETDEV_VER, sizeof(drvinfo->version));
	strlcpy(drvinfo->driver, "geneve", sizeof(drvinfo->driver));
}

static const struct ethtool_ops geneve_ethtool_ops = {
	.get_drvinfo	= geneve_get_drvinfo,
	.get_link	= ethtool_op_get_link,
};

/* Info for udev, that this is a virtual tunnel endpoint */
static struct device_type geneve_type = {
	.name = "geneve",
};

/* Initialize the device structure. */
static void geneve_setup(struct net_device *dev)
{
	ether_setup(dev);

	dev->netdev_ops = &geneve_netdev_ops;
	dev->ethtool_ops = &geneve_ethtool_ops;
	dev->destructor = free_netdev;

	SET_NETDEV_DEVTYPE(dev, &geneve_type);

	dev->features    |= NETIF_F_LLTX;
	dev->features    |= NETIF_F_SG | NETIF_F_HW_CSUM;
	dev->features    |= NETIF_F_RXCSUM;
	dev->features    |= NETIF_F_GSO_SOFTWARE;

	dev->vlan_features = dev->features;
	dev->features    |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;

	dev->hw_features |= NETIF_F_SG | NETIF_F_HW_CSUM | NETIF_F_RXCSUM;
	dev->hw_features |= NETIF_F_GSO_SOFTWARE;
	dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;

	netif_keep_dst(dev);
421
	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
422
	eth_hw_addr_random(dev);
423 424 425 426 427
}

static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
	[IFLA_GENEVE_ID]		= { .type = NLA_U32 },
	[IFLA_GENEVE_REMOTE]		= { .len = FIELD_SIZEOF(struct iphdr, daddr) },
428
	[IFLA_GENEVE_TTL]		= { .type = NLA_U8 },
429
	[IFLA_GENEVE_TOS]		= { .type = NLA_U8 },
430
	[IFLA_GENEVE_PORT]		= { .type = NLA_U16 },
431
	[IFLA_GENEVE_COLLECT_METADATA]	= { .type = NLA_FLAG },
432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456
};

static int geneve_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 (!data)
		return -EINVAL;

	if (data[IFLA_GENEVE_ID]) {
		__u32 vni =  nla_get_u32(data[IFLA_GENEVE_ID]);

		if (vni >= GENEVE_VID_MASK)
			return -ERANGE;
	}

	return 0;
}

457 458 459
static int geneve_configure(struct net *net, struct net_device *dev,
			    __be32 rem_addr, __u32 vni, __u8 ttl, __u8 tos,
			    __u16 dst_port, bool metadata)
460 461 462 463 464
{
	struct geneve_net *gn = net_generic(net, geneve_net_id);
	struct geneve_dev *dummy, *geneve = netdev_priv(dev);
	struct hlist_head *vni_list_head;
	struct sockaddr_in remote;	/* IPv4 address for link partner */
465
	__u32 hash;
466 467
	int err;

468 469 470 471 472 473 474 475 476
	if (metadata) {
		if (rtnl_dereference(gn->collect_md_tun))
			return -EEXIST;
		if (!list_empty(&gn->geneve_list))
			return -EPERM;
	} else {
		if (rtnl_dereference(gn->collect_md_tun))
			return -EPERM;
	}
477 478 479 480 481 482 483 484

	geneve->net = net;
	geneve->dev = dev;

	geneve->vni[0] = (vni & 0x00ff0000) >> 16;
	geneve->vni[1] = (vni & 0x0000ff00) >> 8;
	geneve->vni[2] =  vni & 0x000000ff;

485
	geneve->remote.sin_addr.s_addr = rem_addr;
486 487 488 489
	if (IN_MULTICAST(ntohl(geneve->remote.sin_addr.s_addr)))
		return -EINVAL;

	remote = geneve->remote;
490 491 492 493 494
	if (metadata) {
		if (rem_addr || vni || tos || ttl)
			return -EINVAL;
	}

495 496 497 498
	hash = geneve_net_vni_hash(geneve->vni);
	vni_list_head = &gn->vni_list[hash];
	hlist_for_each_entry_rcu(dummy, vni_list_head, hlist) {
		if (!memcmp(geneve->vni, dummy->vni, sizeof(dummy->vni)) &&
499
		    !memcmp(&remote, &dummy->remote, sizeof(dummy->remote)) &&
500
		    htons(dst_port) == dummy->dst_port) {
501
			return -EBUSY;
502
		}
503 504
	}

505 506 507 508 509
	geneve->ttl = ttl;
	geneve->tos = tos;
	geneve->dst_port = htons(dst_port);
	geneve->collect_md = metadata;

510 511 512 513
	err = register_netdevice(dev);
	if (err)
		return err;

514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536
	list_add(&geneve->next, &gn->geneve_list);
	hlist_add_head_rcu(&geneve->hlist, &gn->vni_list[hash]);

	if (geneve->collect_md)
		rcu_assign_pointer(gn->collect_md_tun, geneve);
	return 0;
}

static int geneve_newlink(struct net *net, struct net_device *dev,
			  struct nlattr *tb[], struct nlattr *data[])
{
	__u16 dst_port = GENEVE_UDP_PORT;
	__u8 ttl = 0, tos = 0;
	bool metadata = false;
	__be32 rem_addr;
	__u32 vni;

	if (!data[IFLA_GENEVE_ID] || !data[IFLA_GENEVE_REMOTE])
		return -EINVAL;

	vni = nla_get_u32(data[IFLA_GENEVE_ID]);
	rem_addr = nla_get_in_addr(data[IFLA_GENEVE_REMOTE]);

537
	if (data[IFLA_GENEVE_TTL])
538
		ttl = nla_get_u8(data[IFLA_GENEVE_TTL]);
539

540
	if (data[IFLA_GENEVE_TOS])
541
		tos = nla_get_u8(data[IFLA_GENEVE_TOS]);
542

543 544
	if (data[IFLA_GENEVE_PORT])
		dst_port = nla_get_u16(data[IFLA_GENEVE_PORT]);
545

546 547
	if (data[IFLA_GENEVE_COLLECT_METADATA])
		metadata = true;
548

549 550
	return geneve_configure(net, dev, rem_addr, vni,
				ttl, tos, dst_port, metadata);
551 552 553 554 555 556
}

static void geneve_dellink(struct net_device *dev, struct list_head *head)
{
	struct geneve_dev *geneve = netdev_priv(dev);

557 558 559 560 561 562
	if (geneve->collect_md) {
		struct geneve_net *gn = net_generic(geneve->net, geneve_net_id);

		rcu_assign_pointer(gn->collect_md_tun, NULL);
	}

563 564 565 566 567 568 569 570 571 572 573
	if (!hlist_unhashed(&geneve->hlist))
		hlist_del_rcu(&geneve->hlist);

	list_del(&geneve->next);
	unregister_netdevice_queue(dev, head);
}

static size_t geneve_get_size(const struct net_device *dev)
{
	return nla_total_size(sizeof(__u32)) +	/* IFLA_GENEVE_ID */
		nla_total_size(sizeof(struct in_addr)) + /* IFLA_GENEVE_REMOTE */
574
		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TTL */
575
		nla_total_size(sizeof(__u8)) +  /* IFLA_GENEVE_TOS */
576
		nla_total_size(sizeof(__u16)) +  /* IFLA_GENEVE_PORT */
577
		nla_total_size(0) +	 /* IFLA_GENEVE_COLLECT_METADATA */
578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593
		0;
}

static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
{
	struct geneve_dev *geneve = netdev_priv(dev);
	__u32 vni;

	vni = (geneve->vni[0] << 16) | (geneve->vni[1] << 8) | geneve->vni[2];
	if (nla_put_u32(skb, IFLA_GENEVE_ID, vni))
		goto nla_put_failure;

	if (nla_put_in_addr(skb, IFLA_GENEVE_REMOTE,
			    geneve->remote.sin_addr.s_addr))
		goto nla_put_failure;

594 595
	if (nla_put_u8(skb, IFLA_GENEVE_TTL, geneve->ttl) ||
	    nla_put_u8(skb, IFLA_GENEVE_TOS, geneve->tos))
596 597
		goto nla_put_failure;

598 599 600
	if (nla_put_u16(skb, IFLA_GENEVE_PORT, ntohs(geneve->dst_port)))
		goto nla_put_failure;

601 602 603 604 605
	if (geneve->collect_md) {
		if (nla_put_flag(skb, IFLA_GENEVE_COLLECT_METADATA))
			goto nla_put_failure;
	}

606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624
	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static struct rtnl_link_ops geneve_link_ops __read_mostly = {
	.kind		= "geneve",
	.maxtype	= IFLA_GENEVE_MAX,
	.policy		= geneve_policy,
	.priv_size	= sizeof(struct geneve_dev),
	.setup		= geneve_setup,
	.validate	= geneve_validate,
	.newlink	= geneve_newlink,
	.dellink	= geneve_dellink,
	.get_size	= geneve_get_size,
	.fill_info	= geneve_fill_info,
};

625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646
struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
					u8 name_assign_type, u16 dst_port)
{
	struct nlattr *tb[IFLA_MAX + 1];
	struct net_device *dev;
	int err;

	memset(tb, 0, sizeof(tb));
	dev = rtnl_create_link(net, name, name_assign_type,
			       &geneve_link_ops, tb);
	if (IS_ERR(dev))
		return dev;

	err = geneve_configure(net, dev, 0, 0, 0, 0, dst_port, true);
	if (err) {
		free_netdev(dev);
		return ERR_PTR(err);
	}
	return dev;
}
EXPORT_SYMBOL_GPL(geneve_dev_create_fb);

647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726
static __net_init int geneve_init_net(struct net *net)
{
	struct geneve_net *gn = net_generic(net, geneve_net_id);
	unsigned int h;

	INIT_LIST_HEAD(&gn->geneve_list);

	for (h = 0; h < VNI_HASH_SIZE; ++h)
		INIT_HLIST_HEAD(&gn->vni_list[h]);

	return 0;
}

static void __net_exit geneve_exit_net(struct net *net)
{
	struct geneve_net *gn = net_generic(net, geneve_net_id);
	struct geneve_dev *geneve, *next;
	struct net_device *dev, *aux;
	LIST_HEAD(list);

	rtnl_lock();

	/* gather any geneve devices that were moved into this ns */
	for_each_netdev_safe(net, dev, aux)
		if (dev->rtnl_link_ops == &geneve_link_ops)
			unregister_netdevice_queue(dev, &list);

	/* now gather any other geneve devices that were created in this ns */
	list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) {
		/* If geneve->dev is in the same netns, it was already added
		 * to the list by the previous loop.
		 */
		if (!net_eq(dev_net(geneve->dev), net))
			unregister_netdevice_queue(geneve->dev, &list);
	}

	/* unregister the devices gathered above */
	unregister_netdevice_many(&list);
	rtnl_unlock();
}

static struct pernet_operations geneve_net_ops = {
	.init = geneve_init_net,
	.exit = geneve_exit_net,
	.id   = &geneve_net_id,
	.size = sizeof(struct geneve_net),
};

static int __init geneve_init_module(void)
{
	int rc;

	rc = register_pernet_subsys(&geneve_net_ops);
	if (rc)
		goto out1;

	rc = rtnl_link_register(&geneve_link_ops);
	if (rc)
		goto out2;

	return 0;
out2:
	unregister_pernet_subsys(&geneve_net_ops);
out1:
	return rc;
}
late_initcall(geneve_init_module);

static void __exit geneve_cleanup_module(void)
{
	rtnl_link_unregister(&geneve_link_ops);
	unregister_pernet_subsys(&geneve_net_ops);
}
module_exit(geneve_cleanup_module);

MODULE_LICENSE("GPL");
MODULE_VERSION(GENEVE_NETDEV_VER);
MODULE_AUTHOR("John W. Linville <linville@tuxdriver.com>");
MODULE_DESCRIPTION("Interface driver for GENEVE encapsulated traffic");
MODULE_ALIAS_RTNL_LINK("geneve");