fou.c 12.2 KB
Newer Older
1 2 3 4 5 6 7 8 9
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/socket.h>
#include <linux/skbuff.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <net/genetlink.h>
10
#include <net/gue.h>
11
#include <net/ip.h>
T
Tom Herbert 已提交
12
#include <net/protocol.h>
13 14 15 16 17 18 19 20 21 22 23 24 25
#include <net/udp.h>
#include <net/udp_tunnel.h>
#include <net/xfrm.h>
#include <uapi/linux/fou.h>
#include <uapi/linux/genetlink.h>

static DEFINE_SPINLOCK(fou_lock);
static LIST_HEAD(fou_list);

struct fou {
	struct socket *sock;
	u8 protocol;
	u16 port;
T
Tom Herbert 已提交
26
	struct udp_offload udp_offloads;
27 28 29 30
	struct list_head list;
};

struct fou_cfg {
31
	u16 type;
32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68
	u8 protocol;
	struct udp_port_cfg udp_config;
};

static inline struct fou *fou_from_sock(struct sock *sk)
{
	return sk->sk_user_data;
}

static int fou_udp_encap_recv_deliver(struct sk_buff *skb,
				      u8 protocol, size_t len)
{
	struct iphdr *iph = ip_hdr(skb);

	/* Remove 'len' bytes from the packet (UDP header and
	 * FOU header if present), modify the protocol to the one
	 * we found, and then call rcv_encap.
	 */
	iph->tot_len = htons(ntohs(iph->tot_len) - len);
	__skb_pull(skb, len);
	skb_postpull_rcsum(skb, udp_hdr(skb), len);
	skb_reset_transport_header(skb);

	return -protocol;
}

static int fou_udp_recv(struct sock *sk, struct sk_buff *skb)
{
	struct fou *fou = fou_from_sock(sk);

	if (!fou)
		return 1;

	return fou_udp_encap_recv_deliver(skb, fou->protocol,
					  sizeof(struct udphdr));
}

69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89
static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
{
	struct fou *fou = fou_from_sock(sk);
	size_t len;
	struct guehdr *guehdr;
	struct udphdr *uh;

	if (!fou)
		return 1;

	len = sizeof(struct udphdr) + sizeof(struct guehdr);
	if (!pskb_may_pull(skb, len))
		goto drop;

	uh = udp_hdr(skb);
	guehdr = (struct guehdr *)&uh[1];

	len += guehdr->hlen << 2;
	if (!pskb_may_pull(skb, len))
		goto drop;

90 91 92
	uh = udp_hdr(skb);
	guehdr = (struct guehdr *)&uh[1];

93 94 95 96 97 98 99 100 101 102 103 104 105 106
	if (guehdr->version != 0)
		goto drop;

	if (guehdr->flags) {
		/* No support yet */
		goto drop;
	}

	return fou_udp_encap_recv_deliver(skb, guehdr->next_hdr, len);
drop:
	kfree_skb(skb);
	return 0;
}

T
Tom Herbert 已提交
107
static struct sk_buff **fou_gro_receive(struct sk_buff **head,
108
					struct sk_buff *skb)
T
Tom Herbert 已提交
109 110 111 112
{
	const struct net_offload *ops;
	struct sk_buff **pp = NULL;
	u8 proto = NAPI_GRO_CB(skb)->proto;
113
	const struct net_offload **offloads;
T
Tom Herbert 已提交
114 115

	rcu_read_lock();
116
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
T
Tom Herbert 已提交
117 118 119 120 121 122 123 124 125 126 127 128
	ops = rcu_dereference(offloads[proto]);
	if (!ops || !ops->callbacks.gro_receive)
		goto out_unlock;

	pp = ops->callbacks.gro_receive(head, skb);

out_unlock:
	rcu_read_unlock();

	return pp;
}

129
static int fou_gro_complete(struct sk_buff *skb, int nhoff)
T
Tom Herbert 已提交
130 131 132 133
{
	const struct net_offload *ops;
	u8 proto = NAPI_GRO_CB(skb)->proto;
	int err = -ENOSYS;
134
	const struct net_offload **offloads;
T
Tom Herbert 已提交
135 136

	rcu_read_lock();
137
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
T
Tom Herbert 已提交
138 139 140 141 142 143 144 145 146 147 148 149
	ops = rcu_dereference(offloads[proto]);
	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
		goto out_unlock;

	err = ops->callbacks.gro_complete(skb, nhoff);

out_unlock:
	rcu_read_unlock();

	return err;
}

150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255
static struct sk_buff **gue_gro_receive(struct sk_buff **head,
					struct sk_buff *skb)
{
	const struct net_offload **offloads;
	const struct net_offload *ops;
	struct sk_buff **pp = NULL;
	struct sk_buff *p;
	u8 proto;
	struct guehdr *guehdr;
	unsigned int hlen, guehlen;
	unsigned int off;
	int flush = 1;

	off = skb_gro_offset(skb);
	hlen = off + sizeof(*guehdr);
	guehdr = skb_gro_header_fast(skb, off);
	if (skb_gro_header_hard(skb, hlen)) {
		guehdr = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!guehdr))
			goto out;
	}

	proto = guehdr->next_hdr;

	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[proto]);
	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
		goto out_unlock;

	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);

	hlen = off + guehlen;
	if (skb_gro_header_hard(skb, hlen)) {
		guehdr = skb_gro_header_slow(skb, hlen, off);
		if (unlikely(!guehdr))
			goto out_unlock;
	}

	flush = 0;

	for (p = *head; p; p = p->next) {
		const struct guehdr *guehdr2;

		if (!NAPI_GRO_CB(p)->same_flow)
			continue;

		guehdr2 = (struct guehdr *)(p->data + off);

		/* Compare base GUE header to be equal (covers
		 * hlen, version, next_hdr, and flags.
		 */
		if (guehdr->word != guehdr2->word) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}

		/* Compare optional fields are the same. */
		if (guehdr->hlen && memcmp(&guehdr[1], &guehdr2[1],
					   guehdr->hlen << 2)) {
			NAPI_GRO_CB(p)->same_flow = 0;
			continue;
		}
	}

	skb_gro_pull(skb, guehlen);

	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
	skb_gro_postpull_rcsum(skb, guehdr, guehlen);

	pp = ops->callbacks.gro_receive(head, skb);

out_unlock:
	rcu_read_unlock();
out:
	NAPI_GRO_CB(skb)->flush |= flush;

	return pp;
}

static int gue_gro_complete(struct sk_buff *skb, int nhoff)
{
	const struct net_offload **offloads;
	struct guehdr *guehdr = (struct guehdr *)(skb->data + nhoff);
	const struct net_offload *ops;
	unsigned int guehlen;
	u8 proto;
	int err = -ENOENT;

	proto = guehdr->next_hdr;

	guehlen = sizeof(*guehdr) + (guehdr->hlen << 2);

	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[proto]);
	if (WARN_ON(!ops || !ops->callbacks.gro_complete))
		goto out_unlock;

	err = ops->callbacks.gro_complete(skb, nhoff + guehlen);

out_unlock:
	rcu_read_unlock();
	return err;
}

256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290
static int fou_add_to_port_list(struct fou *fou)
{
	struct fou *fout;

	spin_lock(&fou_lock);
	list_for_each_entry(fout, &fou_list, list) {
		if (fou->port == fout->port) {
			spin_unlock(&fou_lock);
			return -EALREADY;
		}
	}

	list_add(&fou->list, &fou_list);
	spin_unlock(&fou_lock);

	return 0;
}

static void fou_release(struct fou *fou)
{
	struct socket *sock = fou->sock;
	struct sock *sk = sock->sk;

	udp_del_offload(&fou->udp_offloads);

	list_del(&fou->list);

	/* Remove hooks into tunnel socket */
	sk->sk_user_data = NULL;

	sock_release(sock);

	kfree(fou);
}

291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312
static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
{
	udp_sk(sk)->encap_rcv = fou_udp_recv;
	fou->protocol = cfg->protocol;
	fou->udp_offloads.callbacks.gro_receive = fou_gro_receive;
	fou->udp_offloads.callbacks.gro_complete = fou_gro_complete;
	fou->udp_offloads.port = cfg->udp_config.local_udp_port;
	fou->udp_offloads.ipproto = cfg->protocol;

	return 0;
}

static int gue_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
{
	udp_sk(sk)->encap_rcv = gue_udp_recv;
	fou->udp_offloads.callbacks.gro_receive = gue_gro_receive;
	fou->udp_offloads.callbacks.gro_complete = gue_gro_complete;
	fou->udp_offloads.port = cfg->udp_config.local_udp_port;

	return 0;
}

313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334
static int fou_create(struct net *net, struct fou_cfg *cfg,
		      struct socket **sockp)
{
	struct fou *fou = NULL;
	int err;
	struct socket *sock = NULL;
	struct sock *sk;

	/* Open UDP socket */
	err = udp_sock_create(net, &cfg->udp_config, &sock);
	if (err < 0)
		goto error;

	/* Allocate FOU port structure */
	fou = kzalloc(sizeof(*fou), GFP_KERNEL);
	if (!fou) {
		err = -ENOMEM;
		goto error;
	}

	sk = sock->sk;

335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352
	fou->port = cfg->udp_config.local_udp_port;

	/* Initial for fou type */
	switch (cfg->type) {
	case FOU_ENCAP_DIRECT:
		err = fou_encap_init(sk, fou, cfg);
		if (err)
			goto error;
		break;
	case FOU_ENCAP_GUE:
		err = gue_encap_init(sk, fou, cfg);
		if (err)
			goto error;
		break;
	default:
		err = -EINVAL;
		goto error;
	}
353 354 355 356 357 358 359 360 361 362 363

	udp_sk(sk)->encap_type = 1;
	udp_encap_enable();

	sk->sk_user_data = fou;
	fou->sock = sock;

	udp_set_convert_csum(sk, true);

	sk->sk_allocation = GFP_ATOMIC;

T
Tom Herbert 已提交
364 365 366 367 368 369
	if (cfg->udp_config.family == AF_INET) {
		err = udp_add_offload(&fou->udp_offloads);
		if (err)
			goto error;
	}

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
	err = fou_add_to_port_list(fou);
	if (err)
		goto error;

	if (sockp)
		*sockp = sock;

	return 0;

error:
	kfree(fou);
	if (sock)
		sock_release(sock);

	return err;
}

static int fou_destroy(struct net *net, struct fou_cfg *cfg)
{
	struct fou *fou;
	u16 port = cfg->udp_config.local_udp_port;
	int err = -EINVAL;

	spin_lock(&fou_lock);
	list_for_each_entry(fou, &fou_list, list) {
		if (fou->port == port) {
T
Tom Herbert 已提交
396
			udp_del_offload(&fou->udp_offloads);
397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
			fou_release(fou);
			err = 0;
			break;
		}
	}
	spin_unlock(&fou_lock);

	return err;
}

static struct genl_family fou_nl_family = {
	.id		= GENL_ID_GENERATE,
	.hdrsize	= 0,
	.name		= FOU_GENL_NAME,
	.version	= FOU_GENL_VERSION,
	.maxattr	= FOU_ATTR_MAX,
	.netnsok	= true,
};

static struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = {
	[FOU_ATTR_PORT] = { .type = NLA_U16, },
	[FOU_ATTR_AF] = { .type = NLA_U8, },
	[FOU_ATTR_IPPROTO] = { .type = NLA_U8, },
420
	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447
};

static int parse_nl_config(struct genl_info *info,
			   struct fou_cfg *cfg)
{
	memset(cfg, 0, sizeof(*cfg));

	cfg->udp_config.family = AF_INET;

	if (info->attrs[FOU_ATTR_AF]) {
		u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]);

		if (family != AF_INET && family != AF_INET6)
			return -EINVAL;

		cfg->udp_config.family = family;
	}

	if (info->attrs[FOU_ATTR_PORT]) {
		u16 port = nla_get_u16(info->attrs[FOU_ATTR_PORT]);

		cfg->udp_config.local_udp_port = port;
	}

	if (info->attrs[FOU_ATTR_IPPROTO])
		cfg->protocol = nla_get_u8(info->attrs[FOU_ATTR_IPPROTO]);

448 449 450
	if (info->attrs[FOU_ATTR_TYPE])
		cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);

451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489
	return 0;
}

static int fou_nl_cmd_add_port(struct sk_buff *skb, struct genl_info *info)
{
	struct fou_cfg cfg;
	int err;

	err = parse_nl_config(info, &cfg);
	if (err)
		return err;

	return fou_create(&init_net, &cfg, NULL);
}

static int fou_nl_cmd_rm_port(struct sk_buff *skb, struct genl_info *info)
{
	struct fou_cfg cfg;

	parse_nl_config(info, &cfg);

	return fou_destroy(&init_net, &cfg);
}

static const struct genl_ops fou_nl_ops[] = {
	{
		.cmd = FOU_CMD_ADD,
		.doit = fou_nl_cmd_add_port,
		.policy = fou_nl_policy,
		.flags = GENL_ADMIN_PERM,
	},
	{
		.cmd = FOU_CMD_DEL,
		.doit = fou_nl_cmd_rm_port,
		.policy = fou_nl_policy,
		.flags = GENL_ADMIN_PERM,
	},
};

490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562
static void fou_build_udp(struct sk_buff *skb, struct ip_tunnel_encap *e,
			  struct flowi4 *fl4, u8 *protocol, __be16 sport)
{
	struct udphdr *uh;

	skb_push(skb, sizeof(struct udphdr));
	skb_reset_transport_header(skb);

	uh = udp_hdr(skb);

	uh->dest = e->dport;
	uh->source = sport;
	uh->len = htons(skb->len);
	uh->check = 0;
	udp_set_csum(!(e->flags & TUNNEL_ENCAP_FLAG_CSUM), skb,
		     fl4->saddr, fl4->daddr, skb->len);

	*protocol = IPPROTO_UDP;
}

int fou_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
		     u8 *protocol, struct flowi4 *fl4)
{
	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
	__be16 sport;

	skb = iptunnel_handle_offloads(skb, csum, type);

	if (IS_ERR(skb))
		return PTR_ERR(skb);

	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
					       skb, 0, 0, false);
	fou_build_udp(skb, e, fl4, protocol, sport);

	return 0;
}
EXPORT_SYMBOL(fou_build_header);

int gue_build_header(struct sk_buff *skb, struct ip_tunnel_encap *e,
		     u8 *protocol, struct flowi4 *fl4)
{
	bool csum = !!(e->flags & TUNNEL_ENCAP_FLAG_CSUM);
	int type = csum ? SKB_GSO_UDP_TUNNEL_CSUM : SKB_GSO_UDP_TUNNEL;
	struct guehdr *guehdr;
	size_t hdr_len = sizeof(struct guehdr);
	__be16 sport;

	skb = iptunnel_handle_offloads(skb, csum, type);

	if (IS_ERR(skb))
		return PTR_ERR(skb);

	/* Get source port (based on flow hash) before skb_push */
	sport = e->sport ? : udp_flow_src_port(dev_net(skb->dev),
					       skb, 0, 0, false);

	skb_push(skb, hdr_len);

	guehdr = (struct guehdr *)skb->data;

	guehdr->version = 0;
	guehdr->hlen = 0;
	guehdr->flags = 0;
	guehdr->next_hdr = *protocol;

	fou_build_udp(skb, e, fl4, protocol, sport);

	return 0;
}
EXPORT_SYMBOL(gue_build_header);

563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590
static int __init fou_init(void)
{
	int ret;

	ret = genl_register_family_with_ops(&fou_nl_family,
					    fou_nl_ops);

	return ret;
}

static void __exit fou_fini(void)
{
	struct fou *fou, *next;

	genl_unregister_family(&fou_nl_family);

	/* Close all the FOU sockets */

	spin_lock(&fou_lock);
	list_for_each_entry_safe(fou, next, &fou_list, list)
		fou_release(fou);
	spin_unlock(&fou_lock);
}

module_init(fou_init);
module_exit(fou_fini);
MODULE_AUTHOR("Tom Herbert <therbert@google.com>");
MODULE_LICENSE("GPL");