fou.c 19.0 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
	u8 protocol;
	struct udp_port_cfg udp_config;
};

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

41
static void fou_recv_pull(struct sk_buff *skb, size_t len)
42 43 44 45
{
	struct iphdr *iph = ip_hdr(skb);

	/* Remove 'len' bytes from the packet (UDP header and
46
	 * FOU header if present).
47 48 49 50 51 52 53 54 55 56 57 58 59 60
	 */
	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);
}

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

	if (!fou)
		return 1;

61 62 63 64 65
	fou_recv_pull(skb, sizeof(struct udphdr));

	return -fou->protocol;
}

66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118
static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr,
				  void *data, int hdrlen, u8 ipproto)
{
	__be16 *pd = data;
	u16 start = ntohs(pd[0]);
	u16 offset = ntohs(pd[1]);
	u16 poffset = 0;
	u16 plen;
	__wsum csum, delta;
	__sum16 *psum;

	if (skb->remcsum_offload) {
		/* Already processed in GRO path */
		skb->remcsum_offload = 0;
		return guehdr;
	}

	if (start > skb->len - hdrlen ||
	    offset > skb->len - hdrlen - sizeof(u16))
		return NULL;

	if (unlikely(skb->ip_summed != CHECKSUM_COMPLETE))
		__skb_checksum_complete(skb);

	plen = hdrlen + offset + sizeof(u16);
	if (!pskb_may_pull(skb, plen))
		return NULL;
	guehdr = (struct guehdr *)&udp_hdr(skb)[1];

	if (ipproto == IPPROTO_IP && sizeof(struct iphdr) < plen) {
		struct iphdr *ip = (struct iphdr *)(skb->data + hdrlen);

		/* If next header happens to be IP we can skip that for the
		 * checksum calculation since the IP header checksum is zero
		 * if correct.
		 */
		poffset = ip->ihl * 4;
	}

	csum = csum_sub(skb->csum, skb_checksum(skb, poffset + hdrlen,
						start - poffset - hdrlen, 0));

	/* Set derived checksum in packet */
	psum = (__sum16 *)(skb->data + hdrlen + offset);
	delta = csum_sub(csum_fold(csum), *psum);
	*psum = csum_fold(csum);

	/* Adjust skb->csum since we changed the packet */
	skb->csum = csum_add(skb->csum, delta);

	return guehdr;
}

119 120 121 122 123
static int gue_control_message(struct sk_buff *skb, struct guehdr *guehdr)
{
	/* No support yet */
	kfree_skb(skb);
	return 0;
124 125
}

126 127 128
static int gue_udp_recv(struct sock *sk, struct sk_buff *skb)
{
	struct fou *fou = fou_from_sock(sk);
129
	size_t len, optlen, hdrlen;
130
	struct guehdr *guehdr;
131
	void *data;
132
	u16 doffset = 0;
133 134 135 136 137 138 139 140

	if (!fou)
		return 1;

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

141 142 143 144
	guehdr = (struct guehdr *)&udp_hdr(skb)[1];

	optlen = guehdr->hlen << 2;
	len += optlen;
145 146 147 148

	if (!pskb_may_pull(skb, len))
		goto drop;

149 150
	/* guehdr may change after pull */
	guehdr = (struct guehdr *)&udp_hdr(skb)[1];
151

152
	hdrlen = sizeof(struct guehdr) + optlen;
153

154
	if (guehdr->version != 0 || validate_gue_flags(guehdr, optlen))
155
		goto drop;
156

157 158 159 160 161 162 163 164 165 166 167
	hdrlen = sizeof(struct guehdr) + optlen;

	ip_hdr(skb)->tot_len = htons(ntohs(ip_hdr(skb)->tot_len) - len);

	/* Pull UDP header now, skb->data points to guehdr */
	__skb_pull(skb, sizeof(struct udphdr));

	/* Pull csum through the guehdr now . This can be used if
	 * there is a remote checksum offload.
	 */
	skb_postpull_rcsum(skb, udp_hdr(skb), len);
168 169 170 171

	data = &guehdr[1];

	if (guehdr->flags & GUE_FLAG_PRIV) {
172 173 174 175 176 177 178 179 180 181 182
		__be32 flags = *(__be32 *)(data + doffset);

		doffset += GUE_LEN_PRIV;

		if (flags & GUE_PFLAG_REMCSUM) {
			guehdr = gue_remcsum(skb, guehdr, data + doffset,
					     hdrlen, guehdr->proto_ctype);
			if (!guehdr)
				goto drop;

			data = &guehdr[1];
183

184 185
			doffset += GUE_PLEN_REMCSUM;
		}
186 187
	}

188 189 190
	if (unlikely(guehdr->control))
		return gue_control_message(skb, guehdr);

191 192 193
	__skb_pull(skb, hdrlen);
	skb_reset_transport_header(skb);

194 195
	return -guehdr->proto_ctype;

196 197 198 199 200
drop:
	kfree_skb(skb);
	return 0;
}

T
Tom Herbert 已提交
201
static struct sk_buff **fou_gro_receive(struct sk_buff **head,
202
					struct sk_buff *skb)
T
Tom Herbert 已提交
203 204 205 206
{
	const struct net_offload *ops;
	struct sk_buff **pp = NULL;
	u8 proto = NAPI_GRO_CB(skb)->proto;
207
	const struct net_offload **offloads;
T
Tom Herbert 已提交
208 209

	rcu_read_lock();
210
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
T
Tom Herbert 已提交
211 212 213 214 215 216 217 218 219 220 221 222
	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;
}

223
static int fou_gro_complete(struct sk_buff *skb, int nhoff)
T
Tom Herbert 已提交
224 225 226 227
{
	const struct net_offload *ops;
	u8 proto = NAPI_GRO_CB(skb)->proto;
	int err = -ENOSYS;
228
	const struct net_offload **offloads;
T
Tom Herbert 已提交
229

230 231
	udp_tunnel_gro_complete(skb, nhoff);

T
Tom Herbert 已提交
232
	rcu_read_lock();
233
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
T
Tom Herbert 已提交
234 235 236 237 238 239 240 241 242 243 244 245
	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;
}

246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305
static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off,
				      struct guehdr *guehdr, void *data,
				      size_t hdrlen, u8 ipproto)
{
	__be16 *pd = data;
	u16 start = ntohs(pd[0]);
	u16 offset = ntohs(pd[1]);
	u16 poffset = 0;
	u16 plen;
	void *ptr;
	__wsum csum, delta;
	__sum16 *psum;

	if (skb->remcsum_offload)
		return guehdr;

	if (start > skb_gro_len(skb) - hdrlen ||
	    offset > skb_gro_len(skb) - hdrlen - sizeof(u16) ||
	    !NAPI_GRO_CB(skb)->csum_valid || skb->remcsum_offload)
		return NULL;

	plen = hdrlen + offset + sizeof(u16);

	/* Pull checksum that will be written */
	if (skb_gro_header_hard(skb, off + plen)) {
		guehdr = skb_gro_header_slow(skb, off + plen, off);
		if (!guehdr)
			return NULL;
	}

	ptr = (void *)guehdr + hdrlen;

	if (ipproto == IPPROTO_IP &&
	    (hdrlen + sizeof(struct iphdr) < plen)) {
		struct iphdr *ip = (struct iphdr *)(ptr + hdrlen);

		/* If next header happens to be IP we can skip
		 * that for the checksum calculation since the
		 * IP header checksum is zero if correct.
		 */
		poffset = ip->ihl * 4;
	}

	csum = csum_sub(NAPI_GRO_CB(skb)->csum,
			csum_partial(ptr + poffset, start - poffset, 0));

	/* Set derived checksum in packet */
	psum = (__sum16 *)(ptr + offset);
	delta = csum_sub(csum_fold(csum), *psum);
	*psum = csum_fold(csum);

	/* Adjust skb->csum since we changed the packet */
	skb->csum = csum_add(skb->csum, delta);
	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);

	skb->remcsum_offload = 1;

	return guehdr;
}

306 307 308 309 310 311 312 313
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;
	struct guehdr *guehdr;
314 315
	size_t len, optlen, hdrlen, off;
	void *data;
316
	u16 doffset = 0;
317 318 319
	int flush = 1;

	off = skb_gro_offset(skb);
320 321
	len = off + sizeof(*guehdr);

322
	guehdr = skb_gro_header_fast(skb, off);
323 324
	if (skb_gro_header_hard(skb, len)) {
		guehdr = skb_gro_header_slow(skb, len, off);
325 326 327 328
		if (unlikely(!guehdr))
			goto out;
	}

329 330
	optlen = guehdr->hlen << 2;
	len += optlen;
331

332 333 334 335 336
	if (skb_gro_header_hard(skb, len)) {
		guehdr = skb_gro_header_slow(skb, len, off);
		if (unlikely(!guehdr))
			goto out;
	}
337

338 339 340
	if (unlikely(guehdr->control) || guehdr->version != 0 ||
	    validate_gue_flags(guehdr, optlen))
		goto out;
341

342 343
	hdrlen = sizeof(*guehdr) + optlen;

344 345 346
	/* Adjust NAPI_GRO_CB(skb)->csum to account for guehdr,
	 * this is needed if there is a remote checkcsum offload.
	 */
347 348 349 350 351
	skb_gro_postpull_rcsum(skb, guehdr, hdrlen);

	data = &guehdr[1];

	if (guehdr->flags & GUE_FLAG_PRIV) {
352
		__be32 flags = *(__be32 *)(data + doffset);
353

354 355 356 357 358 359 360 361 362 363 364 365 366
		doffset += GUE_LEN_PRIV;

		if (flags & GUE_PFLAG_REMCSUM) {
			guehdr = gue_gro_remcsum(skb, off, guehdr,
						 data + doffset, hdrlen,
						 guehdr->proto_ctype);
			if (!guehdr)
				goto out;

			data = &guehdr[1];

			doffset += GUE_PLEN_REMCSUM;
		}
367 368
	}

369 370
	skb_gro_pull(skb, hdrlen);

371 372 373 374 375 376 377 378 379 380 381
	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
382
		 * hlen, version, proto_ctype, and flags.
383 384 385 386 387 388 389 390 391 392 393 394 395 396
		 */
		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;
		}
	}

397 398 399 400 401
	rcu_read_lock();
	offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
	ops = rcu_dereference(offloads[guehdr->proto_ctype]);
	if (WARN_ON(!ops || !ops->callbacks.gro_receive))
		goto out_unlock;
402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421

	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;

422
	proto = guehdr->proto_ctype;
423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438

	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;
}

439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473
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);
}

474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495
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;
}

496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517
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;

518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
	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;
	}
536 537 538 539 540 541 542 543 544 545 546

	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
547 548 549 550 551 552
	if (cfg->udp_config.family == AF_INET) {
		err = udp_add_offload(&fou->udp_offloads);
		if (err)
			goto error;
	}

553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578
	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
579
			udp_del_offload(&fou->udp_offloads);
580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602
			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, },
603
	[FOU_ATTR_TYPE] = { .type = NLA_U8, },
604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630
};

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]);

631 632 633
	if (info->attrs[FOU_ATTR_TYPE])
		cfg->type = nla_get_u8(info->attrs[FOU_ATTR_TYPE]);

634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
	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,
	},
};

673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696
size_t fou_encap_hlen(struct ip_tunnel_encap *e)
{
	return sizeof(struct udphdr);
}
EXPORT_SYMBOL(fou_encap_hlen);

size_t gue_encap_hlen(struct ip_tunnel_encap *e)
{
	size_t len;
	bool need_priv = false;

	len = sizeof(struct udphdr) + sizeof(struct guehdr);

	if (e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) {
		len += GUE_PLEN_REMCSUM;
		need_priv = true;
	}

	len += need_priv ? GUE_LEN_PRIV : 0;

	return len;
}
EXPORT_SYMBOL(gue_encap_hlen);

697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742
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;
743
	size_t hdrlen, optlen = 0;
744
	__be16 sport;
745 746 747
	void *data;
	bool need_priv = false;

748 749 750 751 752 753 754 755
	if ((e->flags & TUNNEL_ENCAP_FLAG_REMCSUM) &&
	    skb->ip_summed == CHECKSUM_PARTIAL) {
		csum = false;
		optlen += GUE_PLEN_REMCSUM;
		type |= SKB_GSO_TUNNEL_REMCSUM;
		need_priv = true;
	}

756
	optlen += need_priv ? GUE_LEN_PRIV : 0;
757 758 759 760 761 762 763 764 765 766

	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);

767 768 769
	hdrlen = sizeof(struct guehdr) + optlen;

	skb_push(skb, hdrlen);
770 771 772

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

773
	guehdr->control = 0;
774
	guehdr->version = 0;
775
	guehdr->hlen = optlen >> 2;
776
	guehdr->flags = 0;
777 778 779 780 781 782 783 784 785 786 787
	guehdr->proto_ctype = *protocol;

	data = &guehdr[1];

	if (need_priv) {
		__be32 *flags = data;

		guehdr->flags |= GUE_FLAG_PRIV;
		*flags = 0;
		data += GUE_LEN_PRIV;

788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807
		if (type & SKB_GSO_TUNNEL_REMCSUM) {
			u16 csum_start = skb_checksum_start_offset(skb);
			__be16 *pd = data;

			if (csum_start < hdrlen)
				return -EINVAL;

			csum_start -= hdrlen;
			pd[0] = htons(csum_start);
			pd[1] = htons(csum_start + skb->csum_offset);

			if (!skb_is_gso(skb)) {
				skb->ip_summed = CHECKSUM_NONE;
				skb->encapsulation = 0;
			}

			*flags |= GUE_PFLAG_REMCSUM;
			data += GUE_PLEN_REMCSUM;
		}

808
	}
809 810 811 812 813 814 815

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

	return 0;
}
EXPORT_SYMBOL(gue_build_header);

816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860
#ifdef CONFIG_NET_FOU_IP_TUNNELS

static const struct ip_tunnel_encap_ops __read_mostly fou_iptun_ops = {
	.encap_hlen = fou_encap_hlen,
	.build_header = fou_build_header,
};

static const struct ip_tunnel_encap_ops __read_mostly gue_iptun_ops = {
	.encap_hlen = gue_encap_hlen,
	.build_header = gue_build_header,
};

static int ip_tunnel_encap_add_fou_ops(void)
{
	int ret;

	ret = ip_tunnel_encap_add_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
	if (ret < 0) {
		pr_err("can't add fou ops\n");
		return ret;
	}

	ret = ip_tunnel_encap_add_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
	if (ret < 0) {
		pr_err("can't add gue ops\n");
		ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
		return ret;
	}

	return 0;
}

static void ip_tunnel_encap_del_fou_ops(void)
{
	ip_tunnel_encap_del_ops(&fou_iptun_ops, TUNNEL_ENCAP_FOU);
	ip_tunnel_encap_del_ops(&gue_iptun_ops, TUNNEL_ENCAP_GUE);
}

#else

static int ip_tunnel_encap_add_fou_ops(void)
{
	return 0;
}

861
static void ip_tunnel_encap_del_fou_ops(void)
862 863 864 865 866
{
}

#endif

867 868 869 870 871 872 873
static int __init fou_init(void)
{
	int ret;

	ret = genl_register_family_with_ops(&fou_nl_family,
					    fou_nl_ops);

874 875 876 877 878 879 880 881
	if (ret < 0)
		goto exit;

	ret = ip_tunnel_encap_add_fou_ops();
	if (ret < 0)
		genl_unregister_family(&fou_nl_family);

exit:
882 883 884 885 886 887 888
	return ret;
}

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

889 890
	ip_tunnel_encap_del_fou_ops();

891 892 893 894 895 896 897 898 899 900 901 902 903 904
	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");