tcp_ipv6.c 54.7 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 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
/*
 *	TCP over IPv6
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	$Id: tcp_ipv6.c,v 1.144 2002/02/01 22:01:04 davem Exp $
 *
 *	Based on: 
 *	linux/net/ipv4/tcp.c
 *	linux/net/ipv4/tcp_input.c
 *	linux/net/ipv4/tcp_output.c
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 *	YOSHIFUJI Hideaki @USAGI:	convert /proc/net/tcp6 to seq_file.
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/module.h>
#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/jiffies.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/jhash.h>
#include <linux/ipsec.h>
#include <linux/times.h>

#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>

#include <net/tcp.h>
#include <net/ndisc.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <net/inet_ecn.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/addrconf.h>
#include <net/snmp.h>
#include <net/dsfield.h>

#include <asm/uaccess.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>

static void	tcp_v6_send_reset(struct sk_buff *skb);
68
static void	tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req);
L
Linus Torvalds 已提交
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141
static void	tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, 
				  struct sk_buff *skb);

static int	tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
static int	tcp_v6_xmit(struct sk_buff *skb, int ipfragok);

static struct tcp_func ipv6_mapped;
static struct tcp_func ipv6_specific;

/* I have no idea if this is a good hash for v6 or not. -DaveM */
static __inline__ int tcp_v6_hashfn(struct in6_addr *laddr, u16 lport,
				    struct in6_addr *faddr, u16 fport)
{
	int hashent = (lport ^ fport);

	hashent ^= (laddr->s6_addr32[3] ^ faddr->s6_addr32[3]);
	hashent ^= hashent>>16;
	hashent ^= hashent>>8;
	return (hashent & (tcp_ehash_size - 1));
}

static __inline__ int tcp_v6_sk_hashfn(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct in6_addr *laddr = &np->rcv_saddr;
	struct in6_addr *faddr = &np->daddr;
	__u16 lport = inet->num;
	__u16 fport = inet->dport;
	return tcp_v6_hashfn(laddr, lport, faddr, fport);
}

static inline int tcp_v6_bind_conflict(struct sock *sk,
				       struct tcp_bind_bucket *tb)
{
	struct sock *sk2;
	struct hlist_node *node;

	/* We must walk the whole port owner list in this case. -DaveM */
	sk_for_each_bound(sk2, node, &tb->owners) {
		if (sk != sk2 &&
		    (!sk->sk_bound_dev_if ||
		     !sk2->sk_bound_dev_if ||
		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if) &&
		    (!sk->sk_reuse || !sk2->sk_reuse ||
		     sk2->sk_state == TCP_LISTEN) &&
		     ipv6_rcv_saddr_equal(sk, sk2))
			break;
	}

	return node != NULL;
}

/* Grrr, addr_type already calculated by caller, but I don't want
 * to add some silly "cookie" argument to this method just for that.
 * But it doesn't matter, the recalculation is in the rarest path
 * this function ever takes.
 */
static int tcp_v6_get_port(struct sock *sk, unsigned short snum)
{
	struct tcp_bind_hashbucket *head;
	struct tcp_bind_bucket *tb;
	struct hlist_node *node;
	int ret;

	local_bh_disable();
	if (snum == 0) {
		int low = sysctl_local_port_range[0];
		int high = sysctl_local_port_range[1];
		int remaining = (high - low) + 1;
		int rover;

		spin_lock(&tcp_portalloc_lock);
142 143 144 145
		if (tcp_port_rover < low)
			rover = low;
		else
			rover = tcp_port_rover;
L
Linus Torvalds 已提交
146
		do {	rover++;
147
			if (rover > high)
L
Linus Torvalds 已提交
148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396
				rover = low;
			head = &tcp_bhash[tcp_bhashfn(rover)];
			spin_lock(&head->lock);
			tb_for_each(tb, node, &head->chain)
				if (tb->port == rover)
					goto next;
			break;
		next:
			spin_unlock(&head->lock);
		} while (--remaining > 0);
		tcp_port_rover = rover;
		spin_unlock(&tcp_portalloc_lock);

		/* Exhausted local port range during search? */
		ret = 1;
		if (remaining <= 0)
			goto fail;

		/* OK, here is the one we will use. */
		snum = rover;
	} else {
		head = &tcp_bhash[tcp_bhashfn(snum)];
		spin_lock(&head->lock);
		tb_for_each(tb, node, &head->chain)
			if (tb->port == snum)
				goto tb_found;
	}
	tb = NULL;
	goto tb_not_found;
tb_found:
	if (tb && !hlist_empty(&tb->owners)) {
		if (tb->fastreuse > 0 && sk->sk_reuse &&
		    sk->sk_state != TCP_LISTEN) {
			goto success;
		} else {
			ret = 1;
			if (tcp_v6_bind_conflict(sk, tb))
				goto fail_unlock;
		}
	}
tb_not_found:
	ret = 1;
	if (!tb && (tb = tcp_bucket_create(head, snum)) == NULL)
		goto fail_unlock;
	if (hlist_empty(&tb->owners)) {
		if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
			tb->fastreuse = 1;
		else
			tb->fastreuse = 0;
	} else if (tb->fastreuse &&
		   (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
		tb->fastreuse = 0;

success:
	if (!tcp_sk(sk)->bind_hash)
		tcp_bind_hash(sk, tb, snum);
	BUG_TRAP(tcp_sk(sk)->bind_hash == tb);
	ret = 0;

fail_unlock:
	spin_unlock(&head->lock);
fail:
	local_bh_enable();
	return ret;
}

static __inline__ void __tcp_v6_hash(struct sock *sk)
{
	struct hlist_head *list;
	rwlock_t *lock;

	BUG_TRAP(sk_unhashed(sk));

	if (sk->sk_state == TCP_LISTEN) {
		list = &tcp_listening_hash[tcp_sk_listen_hashfn(sk)];
		lock = &tcp_lhash_lock;
		tcp_listen_wlock();
	} else {
		sk->sk_hashent = tcp_v6_sk_hashfn(sk);
		list = &tcp_ehash[sk->sk_hashent].chain;
		lock = &tcp_ehash[sk->sk_hashent].lock;
		write_lock(lock);
	}

	__sk_add_node(sk, list);
	sock_prot_inc_use(sk->sk_prot);
	write_unlock(lock);
}


static void tcp_v6_hash(struct sock *sk)
{
	if (sk->sk_state != TCP_CLOSE) {
		struct tcp_sock *tp = tcp_sk(sk);

		if (tp->af_specific == &ipv6_mapped) {
			tcp_prot.hash(sk);
			return;
		}
		local_bh_disable();
		__tcp_v6_hash(sk);
		local_bh_enable();
	}
}

static struct sock *tcp_v6_lookup_listener(struct in6_addr *daddr, unsigned short hnum, int dif)
{
	struct sock *sk;
	struct hlist_node *node;
	struct sock *result = NULL;
	int score, hiscore;

	hiscore=0;
	read_lock(&tcp_lhash_lock);
	sk_for_each(sk, node, &tcp_listening_hash[tcp_lhashfn(hnum)]) {
		if (inet_sk(sk)->num == hnum && sk->sk_family == PF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(sk);
			
			score = 1;
			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
					continue;
				score++;
			}
			if (sk->sk_bound_dev_if) {
				if (sk->sk_bound_dev_if != dif)
					continue;
				score++;
			}
			if (score == 3) {
				result = sk;
				break;
			}
			if (score > hiscore) {
				hiscore = score;
				result = sk;
			}
		}
	}
	if (result)
		sock_hold(result);
	read_unlock(&tcp_lhash_lock);
	return result;
}

/* Sockets in TCP_CLOSE state are _always_ taken out of the hash, so
 * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM
 *
 * The sockhash lock must be held as a reader here.
 */

static inline struct sock *__tcp_v6_lookup_established(struct in6_addr *saddr, u16 sport,
						       struct in6_addr *daddr, u16 hnum,
						       int dif)
{
	struct tcp_ehash_bucket *head;
	struct sock *sk;
	struct hlist_node *node;
	__u32 ports = TCP_COMBINED_PORTS(sport, hnum);
	int hash;

	/* Optimize here for direct hit, only listening connections can
	 * have wildcards anyways.
	 */
	hash = tcp_v6_hashfn(daddr, hnum, saddr, sport);
	head = &tcp_ehash[hash];
	read_lock(&head->lock);
	sk_for_each(sk, node, &head->chain) {
		/* For IPV6 do the cheaper port and family tests first. */
		if(TCP_IPV6_MATCH(sk, saddr, daddr, ports, dif))
			goto hit; /* You sunk my battleship! */
	}
	/* Must check for a TIME_WAIT'er before going to listener hash. */
	sk_for_each(sk, node, &(head + tcp_ehash_size)->chain) {
		/* FIXME: acme: check this... */
		struct tcp_tw_bucket *tw = (struct tcp_tw_bucket *)sk;

		if(*((__u32 *)&(tw->tw_dport))	== ports	&&
		   sk->sk_family		== PF_INET6) {
			if(ipv6_addr_equal(&tw->tw_v6_daddr, saddr)	&&
			   ipv6_addr_equal(&tw->tw_v6_rcv_saddr, daddr)	&&
			   (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif))
				goto hit;
		}
	}
	read_unlock(&head->lock);
	return NULL;

hit:
	sock_hold(sk);
	read_unlock(&head->lock);
	return sk;
}


static inline struct sock *__tcp_v6_lookup(struct in6_addr *saddr, u16 sport,
					   struct in6_addr *daddr, u16 hnum,
					   int dif)
{
	struct sock *sk;

	sk = __tcp_v6_lookup_established(saddr, sport, daddr, hnum, dif);

	if (sk)
		return sk;

	return tcp_v6_lookup_listener(daddr, hnum, dif);
}

inline struct sock *tcp_v6_lookup(struct in6_addr *saddr, u16 sport,
				  struct in6_addr *daddr, u16 dport,
				  int dif)
{
	struct sock *sk;

	local_bh_disable();
	sk = __tcp_v6_lookup(saddr, sport, daddr, ntohs(dport), dif);
	local_bh_enable();

	return sk;
}

EXPORT_SYMBOL_GPL(tcp_v6_lookup);


/*
 * Open request hash tables.
 */

static u32 tcp_v6_synq_hash(struct in6_addr *raddr, u16 rport, u32 rnd)
{
	u32 a, b, c;

	a = raddr->s6_addr32[0];
	b = raddr->s6_addr32[1];
	c = raddr->s6_addr32[2];

	a += JHASH_GOLDEN_RATIO;
	b += JHASH_GOLDEN_RATIO;
	c += rnd;
	__jhash_mix(a, b, c);

	a += raddr->s6_addr32[3];
	b += (u32) rport;
	__jhash_mix(a, b, c);

	return c & (TCP_SYNQ_HSIZE - 1);
}

397 398
static struct request_sock *tcp_v6_search_req(struct tcp_sock *tp,
					      struct request_sock ***prevp,
L
Linus Torvalds 已提交
399 400 401 402 403
					      __u16 rport,
					      struct in6_addr *raddr,
					      struct in6_addr *laddr,
					      int iif)
{
404
	struct listen_sock *lopt = tp->accept_queue.listen_opt;
405
	struct request_sock *req, **prev;  
L
Linus Torvalds 已提交
406 407 408 409

	for (prev = &lopt->syn_table[tcp_v6_synq_hash(raddr, rport, lopt->hash_rnd)];
	     (req = *prev) != NULL;
	     prev = &req->dl_next) {
410 411 412
		const struct tcp6_request_sock *treq = tcp6_rsk(req);

		if (inet_rsk(req)->rmt_port == rport &&
413
		    req->rsk_ops->family == AF_INET6 &&
414 415 416
		    ipv6_addr_equal(&treq->rmt_addr, raddr) &&
		    ipv6_addr_equal(&treq->loc_addr, laddr) &&
		    (!treq->iif || treq->iif == iif)) {
L
Linus Torvalds 已提交
417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910
			BUG_TRAP(req->sk == NULL);
			*prevp = prev;
			return req;
		}
	}

	return NULL;
}

static __inline__ u16 tcp_v6_check(struct tcphdr *th, int len,
				   struct in6_addr *saddr, 
				   struct in6_addr *daddr, 
				   unsigned long base)
{
	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
}

static __u32 tcp_v6_init_sequence(struct sock *sk, struct sk_buff *skb)
{
	if (skb->protocol == htons(ETH_P_IPV6)) {
		return secure_tcpv6_sequence_number(skb->nh.ipv6h->daddr.s6_addr32,
						    skb->nh.ipv6h->saddr.s6_addr32,
						    skb->h.th->dest,
						    skb->h.th->source);
	} else {
		return secure_tcp_sequence_number(skb->nh.iph->daddr,
						  skb->nh.iph->saddr,
						  skb->h.th->dest,
						  skb->h.th->source);
	}
}

static int __tcp_v6_check_established(struct sock *sk, __u16 lport,
				      struct tcp_tw_bucket **twp)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct in6_addr *daddr = &np->rcv_saddr;
	struct in6_addr *saddr = &np->daddr;
	int dif = sk->sk_bound_dev_if;
	u32 ports = TCP_COMBINED_PORTS(inet->dport, lport);
	int hash = tcp_v6_hashfn(daddr, inet->num, saddr, inet->dport);
	struct tcp_ehash_bucket *head = &tcp_ehash[hash];
	struct sock *sk2;
	struct hlist_node *node;
	struct tcp_tw_bucket *tw;

	write_lock(&head->lock);

	/* Check TIME-WAIT sockets first. */
	sk_for_each(sk2, node, &(head + tcp_ehash_size)->chain) {
		tw = (struct tcp_tw_bucket*)sk2;

		if(*((__u32 *)&(tw->tw_dport))	== ports	&&
		   sk2->sk_family		== PF_INET6	&&
		   ipv6_addr_equal(&tw->tw_v6_daddr, saddr)	&&
		   ipv6_addr_equal(&tw->tw_v6_rcv_saddr, daddr)	&&
		   sk2->sk_bound_dev_if == sk->sk_bound_dev_if) {
			struct tcp_sock *tp = tcp_sk(sk);

			if (tw->tw_ts_recent_stamp &&
			    (!twp || (sysctl_tcp_tw_reuse &&
				      xtime.tv_sec - 
				      tw->tw_ts_recent_stamp > 1))) {
				/* See comment in tcp_ipv4.c */
				tp->write_seq = tw->tw_snd_nxt + 65535 + 2;
				if (!tp->write_seq)
					tp->write_seq = 1;
				tp->rx_opt.ts_recent = tw->tw_ts_recent;
				tp->rx_opt.ts_recent_stamp = tw->tw_ts_recent_stamp;
				sock_hold(sk2);
				goto unique;
			} else
				goto not_unique;
		}
	}
	tw = NULL;

	/* And established part... */
	sk_for_each(sk2, node, &head->chain) {
		if(TCP_IPV6_MATCH(sk2, saddr, daddr, ports, dif))
			goto not_unique;
	}

unique:
	BUG_TRAP(sk_unhashed(sk));
	__sk_add_node(sk, &head->chain);
	sk->sk_hashent = hash;
	sock_prot_inc_use(sk->sk_prot);
	write_unlock(&head->lock);

	if (twp) {
		*twp = tw;
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
	} else if (tw) {
		/* Silly. Should hash-dance instead... */
		tcp_tw_deschedule(tw);
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);

		tcp_tw_put(tw);
	}
	return 0;

not_unique:
	write_unlock(&head->lock);
	return -EADDRNOTAVAIL;
}

static inline u32 tcpv6_port_offset(const struct sock *sk)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct ipv6_pinfo *np = inet6_sk(sk);

	return secure_tcpv6_port_ephemeral(np->rcv_saddr.s6_addr32,
					   np->daddr.s6_addr32,
					   inet->dport);
}

static int tcp_v6_hash_connect(struct sock *sk)
{
	unsigned short snum = inet_sk(sk)->num;
 	struct tcp_bind_hashbucket *head;
 	struct tcp_bind_bucket *tb;
	int ret;

 	if (!snum) {
 		int low = sysctl_local_port_range[0];
 		int high = sysctl_local_port_range[1];
		int range = high - low;
 		int i;
		int port;
		static u32 hint;
		u32 offset = hint + tcpv6_port_offset(sk);
		struct hlist_node *node;
 		struct tcp_tw_bucket *tw = NULL;

 		local_bh_disable();
		for (i = 1; i <= range; i++) {
			port = low + (i + offset) % range;
 			head = &tcp_bhash[tcp_bhashfn(port)];
 			spin_lock(&head->lock);

 			/* Does not bother with rcv_saddr checks,
 			 * because the established check is already
 			 * unique enough.
 			 */
			tb_for_each(tb, node, &head->chain) {
 				if (tb->port == port) {
 					BUG_TRAP(!hlist_empty(&tb->owners));
 					if (tb->fastreuse >= 0)
 						goto next_port;
 					if (!__tcp_v6_check_established(sk,
									port,
									&tw))
 						goto ok;
 					goto next_port;
 				}
 			}

 			tb = tcp_bucket_create(head, port);
 			if (!tb) {
 				spin_unlock(&head->lock);
 				break;
 			}
 			tb->fastreuse = -1;
 			goto ok;

 		next_port:
 			spin_unlock(&head->lock);
 		}
 		local_bh_enable();

 		return -EADDRNOTAVAIL;

ok:
		hint += i;

 		/* Head lock still held and bh's disabled */
 		tcp_bind_hash(sk, tb, port);
		if (sk_unhashed(sk)) {
 			inet_sk(sk)->sport = htons(port);
 			__tcp_v6_hash(sk);
 		}
 		spin_unlock(&head->lock);

 		if (tw) {
 			tcp_tw_deschedule(tw);
 			tcp_tw_put(tw);
 		}

		ret = 0;
		goto out;
 	}

 	head  = &tcp_bhash[tcp_bhashfn(snum)];
 	tb  = tcp_sk(sk)->bind_hash;
	spin_lock_bh(&head->lock);

	if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
		__tcp_v6_hash(sk);
		spin_unlock_bh(&head->lock);
		return 0;
	} else {
		spin_unlock(&head->lock);
		/* No definite answer... Walk to established hash table */
		ret = __tcp_v6_check_established(sk, snum, NULL);
out:
		local_bh_enable();
		return ret;
	}
}

static __inline__ int tcp_v6_iif(struct sk_buff *skb)
{
	return IP6CB(skb)->iif;
}

static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 
			  int addr_len)
{
	struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct in6_addr *saddr = NULL, *final_p = NULL, final;
	struct flowi fl;
	struct dst_entry *dst;
	int addr_type;
	int err;

	if (addr_len < SIN6_LEN_RFC2133) 
		return -EINVAL;

	if (usin->sin6_family != AF_INET6) 
		return(-EAFNOSUPPORT);

	memset(&fl, 0, sizeof(fl));

	if (np->sndflow) {
		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
		IP6_ECN_flow_init(fl.fl6_flowlabel);
		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
			struct ip6_flowlabel *flowlabel;
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
			fl6_sock_release(flowlabel);
		}
	}

	/*
  	 *	connect() to INADDR_ANY means loopback (BSD'ism).
  	 */
  	
  	if(ipv6_addr_any(&usin->sin6_addr))
		usin->sin6_addr.s6_addr[15] = 0x1; 

	addr_type = ipv6_addr_type(&usin->sin6_addr);

	if(addr_type & IPV6_ADDR_MULTICAST)
		return -ENETUNREACH;

	if (addr_type&IPV6_ADDR_LINKLOCAL) {
		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    usin->sin6_scope_id) {
			/* If interface is set while binding, indices
			 * must coincide.
			 */
			if (sk->sk_bound_dev_if &&
			    sk->sk_bound_dev_if != usin->sin6_scope_id)
				return -EINVAL;

			sk->sk_bound_dev_if = usin->sin6_scope_id;
		}

		/* Connect to link-local address requires an interface */
		if (!sk->sk_bound_dev_if)
			return -EINVAL;
	}

	if (tp->rx_opt.ts_recent_stamp &&
	    !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
		tp->rx_opt.ts_recent = 0;
		tp->rx_opt.ts_recent_stamp = 0;
		tp->write_seq = 0;
	}

	ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
	np->flow_label = fl.fl6_flowlabel;

	/*
	 *	TCP over IPv4
	 */

	if (addr_type == IPV6_ADDR_MAPPED) {
		u32 exthdrlen = tp->ext_header_len;
		struct sockaddr_in sin;

		SOCK_DEBUG(sk, "connect: ipv4 mapped\n");

		if (__ipv6_only_sock(sk))
			return -ENETUNREACH;

		sin.sin_family = AF_INET;
		sin.sin_port = usin->sin6_port;
		sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];

		tp->af_specific = &ipv6_mapped;
		sk->sk_backlog_rcv = tcp_v4_do_rcv;

		err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));

		if (err) {
			tp->ext_header_len = exthdrlen;
			tp->af_specific = &ipv6_specific;
			sk->sk_backlog_rcv = tcp_v6_do_rcv;
			goto failure;
		} else {
			ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF),
				      inet->saddr);
			ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF),
				      inet->rcv_saddr);
		}

		return err;
	}

	if (!ipv6_addr_any(&np->rcv_saddr))
		saddr = &np->rcv_saddr;

	fl.proto = IPPROTO_TCP;
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
	ipv6_addr_copy(&fl.fl6_src,
		       (saddr ? saddr : &np->saddr));
	fl.oif = sk->sk_bound_dev_if;
	fl.fl_ip_dport = usin->sin6_port;
	fl.fl_ip_sport = inet->sport;

	if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
		final_p = &final;
	}

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto failure;
	if (final_p)
		ipv6_addr_copy(&fl.fl6_dst, final_p);

	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
		dst_release(dst);
		goto failure;
	}

	if (saddr == NULL) {
		saddr = &fl.fl6_src;
		ipv6_addr_copy(&np->rcv_saddr, saddr);
	}

	/* set the source address */
	ipv6_addr_copy(&np->saddr, saddr);
	inet->rcv_saddr = LOOPBACK4_IPV6;

	ip6_dst_store(sk, dst, NULL);
	sk->sk_route_caps = dst->dev->features &
		~(NETIF_F_IP_CSUM | NETIF_F_TSO);

	tp->ext_header_len = 0;
	if (np->opt)
		tp->ext_header_len = np->opt->opt_flen + np->opt->opt_nflen;

	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);

	inet->dport = usin->sin6_port;

	tcp_set_state(sk, TCP_SYN_SENT);
	err = tcp_v6_hash_connect(sk);
	if (err)
		goto late_failure;

	if (!tp->write_seq)
		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
							     np->daddr.s6_addr32,
							     inet->sport,
							     inet->dport);

	err = tcp_connect(sk);
	if (err)
		goto late_failure;

	return 0;

late_failure:
	tcp_set_state(sk, TCP_CLOSE);
	__sk_dst_reset(sk);
failure:
	inet->dport = 0;
	sk->sk_route_caps = 0;
	return err;
}

static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		int type, int code, int offset, __u32 info)
{
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
	struct ipv6_pinfo *np;
	struct sock *sk;
	int err;
	struct tcp_sock *tp; 
	__u32 seq;

	sk = tcp_v6_lookup(&hdr->daddr, th->dest, &hdr->saddr, th->source, skb->dev->ifindex);

	if (sk == NULL) {
		ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
		return;
	}

	if (sk->sk_state == TCP_TIME_WAIT) {
		tcp_tw_put((struct tcp_tw_bucket*)sk);
		return;
	}

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk))
		NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);

	if (sk->sk_state == TCP_CLOSE)
		goto out;

	tp = tcp_sk(sk);
	seq = ntohl(th->seq); 
	if (sk->sk_state != TCP_LISTEN &&
	    !between(seq, tp->snd_una, tp->snd_nxt)) {
		NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	np = inet6_sk(sk);

	if (type == ICMPV6_PKT_TOOBIG) {
		struct dst_entry *dst = NULL;

		if (sock_owned_by_user(sk))
			goto out;
		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
			goto out;

		/* icmp should have updated the destination cache entry */
		dst = __sk_dst_check(sk, np->dst_cookie);

		if (dst == NULL) {
			struct inet_sock *inet = inet_sk(sk);
			struct flowi fl;

			/* BUGGG_FUTURE: Again, it is not clear how
			   to handle rthdr case. Ignore this complexity
			   for now.
			 */
			memset(&fl, 0, sizeof(fl));
			fl.proto = IPPROTO_TCP;
			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
			fl.oif = sk->sk_bound_dev_if;
			fl.fl_ip_dport = inet->dport;
			fl.fl_ip_sport = inet->sport;

			if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
				sk->sk_err_soft = -err;
				goto out;
			}

			if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
				sk->sk_err_soft = -err;
				goto out;
			}

		} else
			dst_hold(dst);

		if (tp->pmtu_cookie > dst_mtu(dst)) {
			tcp_sync_mss(sk, dst_mtu(dst));
			tcp_simple_retransmit(sk);
		} /* else let the usual retransmit timer handle it */
		dst_release(dst);
		goto out;
	}

	icmpv6_err_convert(type, code, &err);

911
	/* Might be for an request_sock */
L
Linus Torvalds 已提交
912
	switch (sk->sk_state) {
913
		struct request_sock *req, **prev;
L
Linus Torvalds 已提交
914 915 916 917 918 919 920 921 922 923 924 925 926 927
	case TCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = tcp_v6_search_req(tp, &prev, th->dest, &hdr->daddr,
					&hdr->saddr, tcp_v6_iif(skb));
		if (!req)
			goto out;

		/* ICMPs are not backlogged, hence we cannot get
		 * an established socket here.
		 */
		BUG_TRAP(req->sk == NULL);

928
		if (seq != tcp_rsk(req)->snt_isn) {
L
Linus Torvalds 已提交
929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961
			NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}

		tcp_synq_drop(sk, req, prev);
		goto out;

	case TCP_SYN_SENT:
	case TCP_SYN_RECV:  /* Cannot happen.
			       It can, it SYNs are crossed. --ANK */ 
		if (!sock_owned_by_user(sk)) {
			TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
			sk->sk_err = err;
			sk->sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */

			tcp_done(sk);
		} else
			sk->sk_err_soft = err;
		goto out;
	}

	if (!sock_owned_by_user(sk) && np->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else
		sk->sk_err_soft = err;

out:
	bh_unlock_sock(sk);
	sock_put(sk);
}


962
static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
L
Linus Torvalds 已提交
963 964
			      struct dst_entry *dst)
{
965
	struct tcp6_request_sock *treq = tcp6_rsk(req);
L
Linus Torvalds 已提交
966 967 968 969 970 971 972 973 974
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff * skb;
	struct ipv6_txoptions *opt = NULL;
	struct in6_addr * final_p = NULL, final;
	struct flowi fl;
	int err = -1;

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_TCP;
975 976
	ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
L
Linus Torvalds 已提交
977
	fl.fl6_flowlabel = 0;
978 979
	fl.oif = treq->iif;
	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
L
Linus Torvalds 已提交
980 981 982 983 984 985
	fl.fl_ip_sport = inet_sk(sk)->sport;

	if (dst == NULL) {
		opt = np->opt;
		if (opt == NULL &&
		    np->rxopt.bits.srcrt == 2 &&
986 987
		    treq->pktopts) {
			struct sk_buff *pktopts = treq->pktopts;
L
Linus Torvalds 已提交
988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
			struct inet6_skb_parm *rxopt = IP6CB(pktopts);
			if (rxopt->srcrt)
				opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(pktopts->nh.raw + rxopt->srcrt));
		}

		if (opt && opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}

		err = ip6_dst_lookup(sk, &dst, &fl);
		if (err)
			goto done;
		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);
		if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
			goto done;
	}

	skb = tcp_make_synack(sk, dst, req);
	if (skb) {
		struct tcphdr *th = skb->h.th;

		th->check = tcp_v6_check(th, skb->len,
1014
					 &treq->loc_addr, &treq->rmt_addr,
L
Linus Torvalds 已提交
1015 1016
					 csum_partial((char *)th, skb->len, skb->csum));

1017
		ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
L
Linus Torvalds 已提交
1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029
		err = ip6_xmit(sk, skb, &fl, opt, 0);
		if (err == NET_XMIT_CN)
			err = 0;
	}

done:
	dst_release(dst);
        if (opt && opt != np->opt)
		sock_kfree_s(sk, opt, opt->tot_len);
	return err;
}

1030
static void tcp_v6_reqsk_destructor(struct request_sock *req)
L
Linus Torvalds 已提交
1031
{
1032 1033
	if (tcp6_rsk(req)->pktopts)
		kfree_skb(tcp6_rsk(req)->pktopts);
L
Linus Torvalds 已提交
1034 1035
}

1036
static struct request_sock_ops tcp6_request_sock_ops = {
L
Linus Torvalds 已提交
1037
	.family		=	AF_INET6,
1038
	.obj_size	=	sizeof(struct tcp6_request_sock),
L
Linus Torvalds 已提交
1039
	.rtx_syn_ack	=	tcp_v6_send_synack,
1040 1041
	.send_ack	=	tcp_v6_reqsk_send_ack,
	.destructor	=	tcp_v6_reqsk_destructor,
L
Linus Torvalds 已提交
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225
	.send_reset	=	tcp_v6_send_reset
};

static int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct inet6_skb_parm *opt = IP6CB(skb);

	if (np->rxopt.all) {
		if ((opt->hop && np->rxopt.bits.hopopts) ||
		    ((IPV6_FLOWINFO_MASK&*(u32*)skb->nh.raw) &&
		     np->rxopt.bits.rxflow) ||
		    (opt->srcrt && np->rxopt.bits.srcrt) ||
		    ((opt->dst1 || opt->dst0) && np->rxopt.bits.dstopts))
			return 1;
	}
	return 0;
}


static void tcp_v6_send_check(struct sock *sk, struct tcphdr *th, int len, 
			      struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);

	if (skb->ip_summed == CHECKSUM_HW) {
		th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP,  0);
		skb->csum = offsetof(struct tcphdr, check);
	} else {
		th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 
					    csum_partial((char *)th, th->doff<<2, 
							 skb->csum));
	}
}


static void tcp_v6_send_reset(struct sk_buff *skb)
{
	struct tcphdr *th = skb->h.th, *t1; 
	struct sk_buff *buff;
	struct flowi fl;

	if (th->rst)
		return;

	if (!ipv6_unicast_destination(skb))
		return; 

	/*
	 * We need to grab some memory, and put together an RST,
	 * and then put it into the queue to be sent.
	 */

	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr),
			 GFP_ATOMIC);
	if (buff == NULL) 
	  	return;

	skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr));

	t1 = (struct tcphdr *) skb_push(buff,sizeof(struct tcphdr));

	/* Swap the send and the receive. */
	memset(t1, 0, sizeof(*t1));
	t1->dest = th->source;
	t1->source = th->dest;
	t1->doff = sizeof(*t1)/4;
	t1->rst = 1;
  
	if(th->ack) {
	  	t1->seq = th->ack_seq;
	} else {
		t1->ack = 1;
		t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin
				    + skb->len - (th->doff<<2));
	}

	buff->csum = csum_partial((char *)t1, sizeof(*t1), 0);

	memset(&fl, 0, sizeof(fl));
	ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
	ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr);

	t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst,
				    sizeof(*t1), IPPROTO_TCP,
				    buff->csum);

	fl.proto = IPPROTO_TCP;
	fl.oif = tcp_v6_iif(skb);
	fl.fl_ip_dport = t1->dest;
	fl.fl_ip_sport = t1->source;

	/* sk = NULL, but it is safe for now. RST socket required. */
	if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {

		if ((xfrm_lookup(&buff->dst, &fl, NULL, 0)) < 0) {
			dst_release(buff->dst);
			return;
		}

		ip6_xmit(NULL, buff, &fl, NULL, 0);
		TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
		TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
		return;
	}

	kfree_skb(buff);
}

static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts)
{
	struct tcphdr *th = skb->h.th, *t1;
	struct sk_buff *buff;
	struct flowi fl;
	int tot_len = sizeof(struct tcphdr);

	if (ts)
		tot_len += 3*4;

	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
			 GFP_ATOMIC);
	if (buff == NULL)
		return;

	skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);

	t1 = (struct tcphdr *) skb_push(buff,tot_len);

	/* Swap the send and the receive. */
	memset(t1, 0, sizeof(*t1));
	t1->dest = th->source;
	t1->source = th->dest;
	t1->doff = tot_len/4;
	t1->seq = htonl(seq);
	t1->ack_seq = htonl(ack);
	t1->ack = 1;
	t1->window = htons(win);
	
	if (ts) {
		u32 *ptr = (u32*)(t1 + 1);
		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
			       (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
		*ptr++ = htonl(tcp_time_stamp);
		*ptr = htonl(ts);
	}

	buff->csum = csum_partial((char *)t1, tot_len, 0);

	memset(&fl, 0, sizeof(fl));
	ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
	ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr);

	t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst,
				    tot_len, IPPROTO_TCP,
				    buff->csum);

	fl.proto = IPPROTO_TCP;
	fl.oif = tcp_v6_iif(skb);
	fl.fl_ip_dport = t1->dest;
	fl.fl_ip_sport = t1->source;

	if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
		if ((xfrm_lookup(&buff->dst, &fl, NULL, 0)) < 0) {
			dst_release(buff->dst);
			return;
		}
		ip6_xmit(NULL, buff, &fl, NULL, 0);
		TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
		return;
	}

	kfree_skb(buff);
}

static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_tw_bucket *tw = (struct tcp_tw_bucket *)sk;

	tcp_v6_send_ack(skb, tw->tw_snd_nxt, tw->tw_rcv_nxt,
			tw->tw_rcv_wnd >> tw->tw_rcv_wscale, tw->tw_ts_recent);

	tcp_tw_put(tw);
}

1226
static void tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
L
Linus Torvalds 已提交
1227
{
1228
	tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent);
L
Linus Torvalds 已提交
1229 1230 1231 1232 1233
}


static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
{
1234
	struct request_sock *req, **prev;
L
Linus Torvalds 已提交
1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266
	struct tcphdr *th = skb->h.th;
	struct tcp_sock *tp = tcp_sk(sk);
	struct sock *nsk;

	/* Find possible connection requests. */
	req = tcp_v6_search_req(tp, &prev, th->source, &skb->nh.ipv6h->saddr,
				&skb->nh.ipv6h->daddr, tcp_v6_iif(skb));
	if (req)
		return tcp_check_req(sk, skb, req, prev);

	nsk = __tcp_v6_lookup_established(&skb->nh.ipv6h->saddr,
					  th->source,
					  &skb->nh.ipv6h->daddr,
					  ntohs(th->dest),
					  tcp_v6_iif(skb));

	if (nsk) {
		if (nsk->sk_state != TCP_TIME_WAIT) {
			bh_lock_sock(nsk);
			return nsk;
		}
		tcp_tw_put((struct tcp_tw_bucket*)nsk);
		return NULL;
	}

#if 0 /*def CONFIG_SYN_COOKIES*/
	if (!th->rst && !th->syn && th->ack)
		sk = cookie_v6_check(sk, skb, &(IPCB(skb)->opt));
#endif
	return sk;
}

1267
static void tcp_v6_synq_add(struct sock *sk, struct request_sock *req)
L
Linus Torvalds 已提交
1268 1269
{
	struct tcp_sock *tp = tcp_sk(sk);
1270
	struct listen_sock *lopt = tp->accept_queue.listen_opt;
1271
	u32 h = tcp_v6_synq_hash(&tcp6_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd);
L
Linus Torvalds 已提交
1272

1273
	reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT);
L
Linus Torvalds 已提交
1274 1275 1276 1277 1278 1279 1280 1281 1282
	tcp_synq_added(sk);
}


/* FIXME: this is substantially similar to the ipv4 code.
 * Can some kind of merge be done? -- erics
 */
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
1283
	struct tcp6_request_sock *treq;
L
Linus Torvalds 已提交
1284 1285 1286
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcp_options_received tmp_opt;
	struct tcp_sock *tp = tcp_sk(sk);
1287
	struct request_sock *req = NULL;
L
Linus Torvalds 已提交
1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307
	__u32 isn = TCP_SKB_CB(skb)->when;

	if (skb->protocol == htons(ETH_P_IP))
		return tcp_v4_conn_request(sk, skb);

	if (!ipv6_unicast_destination(skb))
		goto drop; 

	/*
	 *	There are no SYN attacks on IPv6, yet...	
	 */
	if (tcp_synq_is_full(sk) && !isn) {
		if (net_ratelimit())
			printk(KERN_INFO "TCPv6: dropping request, synflood is possible\n");
		goto drop;		
	}

	if (sk_acceptq_is_full(sk) && tcp_synq_young(sk) > 1)
		goto drop;

1308
	req = reqsk_alloc(&tcp6_request_sock_ops);
L
Linus Torvalds 已提交
1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320
	if (req == NULL)
		goto drop;

	tcp_clear_options(&tmp_opt);
	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
	tmp_opt.user_mss = tp->rx_opt.user_mss;

	tcp_parse_options(skb, &tmp_opt, 0);

	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
	tcp_openreq_init(req, &tmp_opt, skb);

1321 1322 1323
	treq = tcp6_rsk(req);
	ipv6_addr_copy(&treq->rmt_addr, &skb->nh.ipv6h->saddr);
	ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr);
L
Linus Torvalds 已提交
1324
	TCP_ECN_create_request(req, skb->h.th);
1325
	treq->pktopts = NULL;
L
Linus Torvalds 已提交
1326 1327 1328 1329
	if (ipv6_opt_accepted(sk, skb) ||
	    np->rxopt.bits.rxinfo ||
	    np->rxopt.bits.rxhlim) {
		atomic_inc(&skb->users);
1330
		treq->pktopts = skb;
L
Linus Torvalds 已提交
1331
	}
1332
	treq->iif = sk->sk_bound_dev_if;
L
Linus Torvalds 已提交
1333 1334 1335

	/* So that link locals have meaning */
	if (!sk->sk_bound_dev_if &&
1336 1337
	    ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
		treq->iif = tcp_v6_iif(skb);
L
Linus Torvalds 已提交
1338 1339 1340 1341

	if (isn == 0) 
		isn = tcp_v6_init_sequence(sk,skb);

1342
	tcp_rsk(req)->snt_isn = isn;
L
Linus Torvalds 已提交
1343 1344 1345 1346 1347 1348 1349 1350 1351 1352

	if (tcp_v6_send_synack(sk, req, NULL))
		goto drop;

	tcp_v6_synq_add(sk, req);

	return 0;

drop:
	if (req)
1353
		reqsk_free(req);
L
Linus Torvalds 已提交
1354 1355 1356 1357 1358 1359

	TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
	return 0; /* don't send reset */
}

static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
1360
					  struct request_sock *req,
L
Linus Torvalds 已提交
1361 1362
					  struct dst_entry *dst)
{
1363
	struct tcp6_request_sock *treq = tcp6_rsk(req);
L
Linus Torvalds 已提交
1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426
	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
	struct tcp6_sock *newtcp6sk;
	struct inet_sock *newinet;
	struct tcp_sock *newtp;
	struct sock *newsk;
	struct ipv6_txoptions *opt;

	if (skb->protocol == htons(ETH_P_IP)) {
		/*
		 *	v6 mapped
		 */

		newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst);

		if (newsk == NULL) 
			return NULL;

		newtcp6sk = (struct tcp6_sock *)newsk;
		inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;

		newinet = inet_sk(newsk);
		newnp = inet6_sk(newsk);
		newtp = tcp_sk(newsk);

		memcpy(newnp, np, sizeof(struct ipv6_pinfo));

		ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF),
			      newinet->daddr);

		ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF),
			      newinet->saddr);

		ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);

		newtp->af_specific = &ipv6_mapped;
		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
		newnp->pktoptions  = NULL;
		newnp->opt	   = NULL;
		newnp->mcast_oif   = tcp_v6_iif(skb);
		newnp->mcast_hops  = skb->nh.ipv6h->hop_limit;

		/* Charge newly allocated IPv6 socket. Though it is mapped,
		 * it is IPv6 yet.
		 */
#ifdef INET_REFCNT_DEBUG
		atomic_inc(&inet6_sock_nr);
#endif

		/* It is tricky place. Until this moment IPv4 tcp
		   worked with IPv6 af_tcp.af_specific.
		   Sync it now.
		 */
		tcp_sync_mss(newsk, newtp->pmtu_cookie);

		return newsk;
	}

	opt = np->opt;

	if (sk_acceptq_is_full(sk))
		goto out_overflow;

	if (np->rxopt.bits.srcrt == 2 &&
1427 1428
	    opt == NULL && treq->pktopts) {
		struct inet6_skb_parm *rxopt = IP6CB(treq->pktopts);
L
Linus Torvalds 已提交
1429
		if (rxopt->srcrt)
1430
			opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(treq->pktopts->nh.raw + rxopt->srcrt));
L
Linus Torvalds 已提交
1431 1432 1433 1434 1435 1436 1437 1438
	}

	if (dst == NULL) {
		struct in6_addr *final_p = NULL, final;
		struct flowi fl;

		memset(&fl, 0, sizeof(fl));
		fl.proto = IPPROTO_TCP;
1439
		ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
L
Linus Torvalds 已提交
1440 1441 1442 1443 1444 1445
		if (opt && opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}
1446
		ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
L
Linus Torvalds 已提交
1447
		fl.oif = sk->sk_bound_dev_if;
1448
		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
L
Linus Torvalds 已提交
1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482
		fl.fl_ip_sport = inet_sk(sk)->sport;

		if (ip6_dst_lookup(sk, &dst, &fl))
			goto out;

		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);

		if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0)
			goto out;
	} 

	newsk = tcp_create_openreq_child(sk, req, skb);
	if (newsk == NULL)
		goto out;

	/* Charge newly allocated IPv6 socket */
#ifdef INET_REFCNT_DEBUG
	atomic_inc(&inet6_sock_nr);
#endif

	ip6_dst_store(newsk, dst, NULL);
	newsk->sk_route_caps = dst->dev->features &
		~(NETIF_F_IP_CSUM | NETIF_F_TSO);

	newtcp6sk = (struct tcp6_sock *)newsk;
	inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;

	newtp = tcp_sk(newsk);
	newinet = inet_sk(newsk);
	newnp = inet6_sk(newsk);

	memcpy(newnp, np, sizeof(struct ipv6_pinfo));

1483 1484 1485 1486
	ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr);
	ipv6_addr_copy(&newnp->saddr, &treq->loc_addr);
	ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr);
	newsk->sk_bound_dev_if = treq->iif;
L
Linus Torvalds 已提交
1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498

	/* Now IPv6 options... 

	   First: no IPv4 options.
	 */
	newinet->opt = NULL;

	/* Clone RX bits */
	newnp->rxopt.all = np->rxopt.all;

	/* Clone pktoptions received with SYN */
	newnp->pktoptions = NULL;
1499 1500 1501 1502
	if (treq->pktopts != NULL) {
		newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC);
		kfree_skb(treq->pktopts);
		treq->pktopts = NULL;
L
Linus Torvalds 已提交
1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027
		if (newnp->pktoptions)
			skb_set_owner_r(newnp->pktoptions, newsk);
	}
	newnp->opt	  = NULL;
	newnp->mcast_oif  = tcp_v6_iif(skb);
	newnp->mcast_hops = skb->nh.ipv6h->hop_limit;

	/* Clone native IPv6 options from listening socket (if any)

	   Yes, keeping reference count would be much more clever,
	   but we make one more one thing there: reattach optmem
	   to newsk.
	 */
	if (opt) {
		newnp->opt = ipv6_dup_options(newsk, opt);
		if (opt != np->opt)
			sock_kfree_s(sk, opt, opt->tot_len);
	}

	newtp->ext_header_len = 0;
	if (newnp->opt)
		newtp->ext_header_len = newnp->opt->opt_nflen +
					newnp->opt->opt_flen;

	tcp_sync_mss(newsk, dst_mtu(dst));
	newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
	tcp_initialize_rcv_mss(newsk);

	newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;

	__tcp_v6_hash(newsk);
	tcp_inherit_port(sk, newsk);

	return newsk;

out_overflow:
	NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
out:
	NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
	if (opt && opt != np->opt)
		sock_kfree_s(sk, opt, opt->tot_len);
	dst_release(dst);
	return NULL;
}

static int tcp_v6_checksum_init(struct sk_buff *skb)
{
	if (skb->ip_summed == CHECKSUM_HW) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
		if (!tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr,
				  &skb->nh.ipv6h->daddr,skb->csum))
			return 0;
		LIMIT_NETDEBUG(printk(KERN_DEBUG "hw tcp v6 csum failed\n"));
	}
	if (skb->len <= 76) {
		if (tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr,
				 &skb->nh.ipv6h->daddr,skb_checksum(skb, 0, skb->len, 0)))
			return -1;
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else {
		skb->csum = ~tcp_v6_check(skb->h.th,skb->len,&skb->nh.ipv6h->saddr,
					  &skb->nh.ipv6h->daddr,0);
	}
	return 0;
}

/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcp_sock *tp;
	struct sk_buff *opt_skb = NULL;

	/* Imagine: socket is IPv6. IPv4 packet arrives,
	   goes to IPv4 receive handler and backlogged.
	   From backlog it always goes here. Kerboom...
	   Fortunately, tcp_rcv_established and rcv_established
	   handle them correctly, but it is not case with
	   tcp_v6_hnd_req and tcp_v6_send_reset().   --ANK
	 */

	if (skb->protocol == htons(ETH_P_IP))
		return tcp_v4_do_rcv(sk, skb);

	if (sk_filter(sk, skb, 0))
		goto discard;

	/*
	 *	socket locking is here for SMP purposes as backlog rcv
	 *	is currently called with bh processing disabled.
	 */

	/* Do Stevens' IPV6_PKTOPTIONS.

	   Yes, guys, it is the only place in our code, where we
	   may make it not affecting IPv4.
	   The rest of code is protocol independent,
	   and I do not like idea to uglify IPv4.

	   Actually, all the idea behind IPV6_PKTOPTIONS
	   looks not very well thought. For now we latch
	   options, received in the last packet, enqueued
	   by tcp. Feel free to propose better solution.
	                                       --ANK (980728)
	 */
	if (np->rxopt.all)
		opt_skb = skb_clone(skb, GFP_ATOMIC);

	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
		TCP_CHECK_TIMER(sk);
		if (tcp_rcv_established(sk, skb, skb->h.th, skb->len))
			goto reset;
		TCP_CHECK_TIMER(sk);
		if (opt_skb)
			goto ipv6_pktoptions;
		return 0;
	}

	if (skb->len < (skb->h.th->doff<<2) || tcp_checksum_complete(skb))
		goto csum_err;

	if (sk->sk_state == TCP_LISTEN) { 
		struct sock *nsk = tcp_v6_hnd_req(sk, skb);
		if (!nsk)
			goto discard;

		/*
		 * Queue it on the new socket if the new socket is active,
		 * otherwise we just shortcircuit this and continue with
		 * the new socket..
		 */
 		if(nsk != sk) {
			if (tcp_child_process(sk, nsk, skb))
				goto reset;
			if (opt_skb)
				__kfree_skb(opt_skb);
			return 0;
		}
	}

	TCP_CHECK_TIMER(sk);
	if (tcp_rcv_state_process(sk, skb, skb->h.th, skb->len))
		goto reset;
	TCP_CHECK_TIMER(sk);
	if (opt_skb)
		goto ipv6_pktoptions;
	return 0;

reset:
	tcp_v6_send_reset(skb);
discard:
	if (opt_skb)
		__kfree_skb(opt_skb);
	kfree_skb(skb);
	return 0;
csum_err:
	TCP_INC_STATS_BH(TCP_MIB_INERRS);
	goto discard;


ipv6_pktoptions:
	/* Do you ask, what is it?

	   1. skb was enqueued by tcp.
	   2. skb is added to tail of read queue, rather than out of order.
	   3. socket is not in passive state.
	   4. Finally, it really contains options, which user wants to receive.
	 */
	tp = tcp_sk(sk);
	if (TCP_SKB_CB(opt_skb)->end_seq == tp->rcv_nxt &&
	    !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) {
		if (np->rxopt.bits.rxinfo)
			np->mcast_oif = tcp_v6_iif(opt_skb);
		if (np->rxopt.bits.rxhlim)
			np->mcast_hops = opt_skb->nh.ipv6h->hop_limit;
		if (ipv6_opt_accepted(sk, opt_skb)) {
			skb_set_owner_r(opt_skb, sk);
			opt_skb = xchg(&np->pktoptions, opt_skb);
		} else {
			__kfree_skb(opt_skb);
			opt_skb = xchg(&np->pktoptions, NULL);
		}
	}

	if (opt_skb)
		kfree_skb(opt_skb);
	return 0;
}

static int tcp_v6_rcv(struct sk_buff **pskb, unsigned int *nhoffp)
{
	struct sk_buff *skb = *pskb;
	struct tcphdr *th;	
	struct sock *sk;
	int ret;

	if (skb->pkt_type != PACKET_HOST)
		goto discard_it;

	/*
	 *	Count it even if it's bad.
	 */
	TCP_INC_STATS_BH(TCP_MIB_INSEGS);

	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
		goto discard_it;

	th = skb->h.th;

	if (th->doff < sizeof(struct tcphdr)/4)
		goto bad_packet;
	if (!pskb_may_pull(skb, th->doff*4))
		goto discard_it;

	if ((skb->ip_summed != CHECKSUM_UNNECESSARY &&
	     tcp_v6_checksum_init(skb) < 0))
		goto bad_packet;

	th = skb->h.th;
	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
				    skb->len - th->doff*4);
	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
	TCP_SKB_CB(skb)->when = 0;
	TCP_SKB_CB(skb)->flags = ipv6_get_dsfield(skb->nh.ipv6h);
	TCP_SKB_CB(skb)->sacked = 0;

	sk = __tcp_v6_lookup(&skb->nh.ipv6h->saddr, th->source,
			     &skb->nh.ipv6h->daddr, ntohs(th->dest), tcp_v6_iif(skb));

	if (!sk)
		goto no_tcp_socket;

process:
	if (sk->sk_state == TCP_TIME_WAIT)
		goto do_time_wait;

	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;

	if (sk_filter(sk, skb, 0))
		goto discard_and_relse;

	skb->dev = NULL;

	bh_lock_sock(sk);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
		if (!tcp_prequeue(sk, skb))
			ret = tcp_v6_do_rcv(sk, skb);
	} else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);

	sock_put(sk);
	return ret ? -1 : 0;

no_tcp_socket:
	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
bad_packet:
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
	} else {
		tcp_v6_send_reset(skb);
	}

discard_it:

	/*
	 *	Discard frame
	 */

	kfree_skb(skb);
	return 0;

discard_and_relse:
	sock_put(sk);
	goto discard_it;

do_time_wait:
	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		tcp_tw_put((struct tcp_tw_bucket *) sk);
		goto discard_it;
	}

	if (skb->len < (th->doff<<2) || tcp_checksum_complete(skb)) {
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
		tcp_tw_put((struct tcp_tw_bucket *) sk);
		goto discard_it;
	}

	switch(tcp_timewait_state_process((struct tcp_tw_bucket *)sk,
					  skb, th, skb->len)) {
	case TCP_TW_SYN:
	{
		struct sock *sk2;

		sk2 = tcp_v6_lookup_listener(&skb->nh.ipv6h->daddr, ntohs(th->dest), tcp_v6_iif(skb));
		if (sk2 != NULL) {
			tcp_tw_deschedule((struct tcp_tw_bucket *)sk);
			tcp_tw_put((struct tcp_tw_bucket *)sk);
			sk = sk2;
			goto process;
		}
		/* Fall through to ACK */
	}
	case TCP_TW_ACK:
		tcp_v6_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		goto no_tcp_socket;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

static int tcp_v6_rebuild_header(struct sock *sk)
{
	int err;
	struct dst_entry *dst;
	struct ipv6_pinfo *np = inet6_sk(sk);

	dst = __sk_dst_check(sk, np->dst_cookie);

	if (dst == NULL) {
		struct inet_sock *inet = inet_sk(sk);
		struct in6_addr *final_p = NULL, final;
		struct flowi fl;

		memset(&fl, 0, sizeof(fl));
		fl.proto = IPPROTO_TCP;
		ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
		fl.fl6_flowlabel = np->flow_label;
		fl.oif = sk->sk_bound_dev_if;
		fl.fl_ip_dport = inet->dport;
		fl.fl_ip_sport = inet->sport;

		if (np->opt && np->opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}

		err = ip6_dst_lookup(sk, &dst, &fl);
		if (err) {
			sk->sk_route_caps = 0;
			return err;
		}
		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);

		if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
			sk->sk_err_soft = -err;
			dst_release(dst);
			return err;
		}

		ip6_dst_store(sk, dst, NULL);
		sk->sk_route_caps = dst->dev->features &
			~(NETIF_F_IP_CSUM | NETIF_F_TSO);
	}

	return 0;
}

static int tcp_v6_xmit(struct sk_buff *skb, int ipfragok)
{
	struct sock *sk = skb->sk;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct flowi fl;
	struct dst_entry *dst;
	struct in6_addr *final_p = NULL, final;

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_TCP;
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
	ipv6_addr_copy(&fl.fl6_src, &np->saddr);
	fl.fl6_flowlabel = np->flow_label;
	IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel);
	fl.oif = sk->sk_bound_dev_if;
	fl.fl_ip_sport = inet->sport;
	fl.fl_ip_dport = inet->dport;

	if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) np->opt->srcrt;
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
		final_p = &final;
	}

	dst = __sk_dst_check(sk, np->dst_cookie);

	if (dst == NULL) {
		int err = ip6_dst_lookup(sk, &dst, &fl);

		if (err) {
			sk->sk_err_soft = -err;
			return err;
		}

		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);

		if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
			sk->sk_route_caps = 0;
			dst_release(dst);
			return err;
		}

		ip6_dst_store(sk, dst, NULL);
		sk->sk_route_caps = dst->dev->features &
			~(NETIF_F_IP_CSUM | NETIF_F_TSO);
	}

	skb->dst = dst_clone(dst);

	/* Restore final destination back after routing done */
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);

	return ip6_xmit(sk, skb, &fl, np->opt, 0);
}

static void v6_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;

	sin6->sin6_family = AF_INET6;
	ipv6_addr_copy(&sin6->sin6_addr, &np->daddr);
	sin6->sin6_port	= inet_sk(sk)->dport;
	/* We do not store received flowlabel for TCP */
	sin6->sin6_flowinfo = 0;
	sin6->sin6_scope_id = 0;
	if (sk->sk_bound_dev_if &&
	    ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
		sin6->sin6_scope_id = sk->sk_bound_dev_if;
}

static int tcp_v6_remember_stamp(struct sock *sk)
{
	/* Alas, not yet... */
	return 0;
}

static struct tcp_func ipv6_specific = {
	.queue_xmit	=	tcp_v6_xmit,
	.send_check	=	tcp_v6_send_check,
	.rebuild_header	=	tcp_v6_rebuild_header,
	.conn_request	=	tcp_v6_conn_request,
	.syn_recv_sock	=	tcp_v6_syn_recv_sock,
	.remember_stamp	=	tcp_v6_remember_stamp,
	.net_header_len	=	sizeof(struct ipv6hdr),

	.setsockopt	=	ipv6_setsockopt,
	.getsockopt	=	ipv6_getsockopt,
	.addr2sockaddr	=	v6_addr2sockaddr,
	.sockaddr_len	=	sizeof(struct sockaddr_in6)
};

/*
 *	TCP over IPv4 via INET6 API
 */

static struct tcp_func ipv6_mapped = {
	.queue_xmit	=	ip_queue_xmit,
	.send_check	=	tcp_v4_send_check,
	.rebuild_header	=	tcp_v4_rebuild_header,
	.conn_request	=	tcp_v6_conn_request,
	.syn_recv_sock	=	tcp_v6_syn_recv_sock,
	.remember_stamp	=	tcp_v4_remember_stamp,
	.net_header_len	=	sizeof(struct iphdr),

	.setsockopt	=	ipv6_setsockopt,
	.getsockopt	=	ipv6_getsockopt,
	.addr2sockaddr	=	v6_addr2sockaddr,
	.sockaddr_len	=	sizeof(struct sockaddr_in6)
};



/* NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */
static int tcp_v6_init_sock(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	skb_queue_head_init(&tp->out_of_order_queue);
	tcp_init_xmit_timers(sk);
	tcp_prequeue_init(tp);

	tp->rto  = TCP_TIMEOUT_INIT;
	tp->mdev = TCP_TIMEOUT_INIT;

	/* So many TCP implementations out there (incorrectly) count the
	 * initial SYN frame in their delayed-ACK and congestion control
	 * algorithms that we must have the following bandaid to talk
	 * efficiently to them.  -DaveM
	 */
	tp->snd_cwnd = 2;

	/* See draft-stevens-tcpca-spec-01 for discussion of the
	 * initialization of these values.
	 */
	tp->snd_ssthresh = 0x7fffffff;
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache_std = tp->mss_cache = 536;

	tp->reordering = sysctl_tcp_reordering;

	sk->sk_state = TCP_CLOSE;

	tp->af_specific = &ipv6_specific;
2028
	tp->ca_ops = &tcp_init_congestion_ops;
L
Linus Torvalds 已提交
2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049
	sk->sk_write_space = sk_stream_write_space;
	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);

	sk->sk_sndbuf = sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sysctl_tcp_rmem[1];

	atomic_inc(&tcp_sockets_allocated);

	return 0;
}

static int tcp_v6_destroy_sock(struct sock *sk)
{
	extern int tcp_v4_destroy_sock(struct sock *sk);

	tcp_v4_destroy_sock(sk);
	return inet6_destroy_sock(sk);
}

/* Proc filesystem TCPv6 sock list dumping. */
static void get_openreq6(struct seq_file *seq, 
2050
			 struct sock *sk, struct request_sock *req, int i, int uid)
L
Linus Torvalds 已提交
2051 2052 2053 2054 2055 2056 2057
{
	struct in6_addr *dest, *src;
	int ttd = req->expires - jiffies;

	if (ttd < 0)
		ttd = 0;

2058 2059
	src = &tcp6_rsk(req)->loc_addr;
	dest = &tcp6_rsk(req)->rmt_addr;
L
Linus Torvalds 已提交
2060 2061 2062 2063 2064 2065 2066 2067 2068
	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3],
		   ntohs(inet_sk(sk)->sport),
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3],
2069
		   ntohs(inet_rsk(req)->rmt_port),
L
Linus Torvalds 已提交
2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238
		   TCP_SYN_RECV,
		   0,0, /* could print option size, but that is af dependent. */
		   1,   /* timers active (only the expire timer) */  
		   jiffies_to_clock_t(ttd), 
		   req->retrans,
		   uid,
		   0,  /* non standard timer */  
		   0, /* open_requests have no inode */
		   0, req);
}

static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i)
{
	struct in6_addr *dest, *src;
	__u16 destp, srcp;
	int timer_active;
	unsigned long timer_expires;
	struct inet_sock *inet = inet_sk(sp);
	struct tcp_sock *tp = tcp_sk(sp);
	struct ipv6_pinfo *np = inet6_sk(sp);

	dest  = &np->daddr;
	src   = &np->rcv_saddr;
	destp = ntohs(inet->dport);
	srcp  = ntohs(inet->sport);
	if (tp->pending == TCP_TIME_RETRANS) {
		timer_active	= 1;
		timer_expires	= tp->timeout;
	} else if (tp->pending == TCP_TIME_PROBE0) {
		timer_active	= 4;
		timer_expires	= tp->timeout;
	} else if (timer_pending(&sp->sk_timer)) {
		timer_active	= 2;
		timer_expires	= sp->sk_timer.expires;
	} else {
		timer_active	= 0;
		timer_expires = jiffies;
	}

	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %u %u %u %u %d\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3], srcp,
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
		   sp->sk_state, 
		   tp->write_seq-tp->snd_una, tp->rcv_nxt-tp->copied_seq,
		   timer_active,
		   jiffies_to_clock_t(timer_expires - jiffies),
		   tp->retransmits,
		   sock_i_uid(sp),
		   tp->probes_out,
		   sock_i_ino(sp),
		   atomic_read(&sp->sk_refcnt), sp,
		   tp->rto, tp->ack.ato, (tp->ack.quick<<1)|tp->ack.pingpong,
		   tp->snd_cwnd, tp->snd_ssthresh>=0xFFFF?-1:tp->snd_ssthresh
		   );
}

static void get_timewait6_sock(struct seq_file *seq, 
			       struct tcp_tw_bucket *tw, int i)
{
	struct in6_addr *dest, *src;
	__u16 destp, srcp;
	int ttd = tw->tw_ttd - jiffies;

	if (ttd < 0)
		ttd = 0;

	dest  = &tw->tw_v6_daddr;
	src   = &tw->tw_v6_rcv_saddr;
	destp = ntohs(tw->tw_dport);
	srcp  = ntohs(tw->tw_sport);

	seq_printf(seq,
		   "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X "
		   "%02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p\n",
		   i,
		   src->s6_addr32[0], src->s6_addr32[1],
		   src->s6_addr32[2], src->s6_addr32[3], srcp,
		   dest->s6_addr32[0], dest->s6_addr32[1],
		   dest->s6_addr32[2], dest->s6_addr32[3], destp,
		   tw->tw_substate, 0, 0,
		   3, jiffies_to_clock_t(ttd), 0, 0, 0, 0,
		   atomic_read(&tw->tw_refcnt), tw);
}

#ifdef CONFIG_PROC_FS
static int tcp6_seq_show(struct seq_file *seq, void *v)
{
	struct tcp_iter_state *st;

	if (v == SEQ_START_TOKEN) {
		seq_puts(seq,
			 "  sl  "
			 "local_address                         "
			 "remote_address                        "
			 "st tx_queue rx_queue tr tm->when retrnsmt"
			 "   uid  timeout inode\n");
		goto out;
	}
	st = seq->private;

	switch (st->state) {
	case TCP_SEQ_STATE_LISTENING:
	case TCP_SEQ_STATE_ESTABLISHED:
		get_tcp6_sock(seq, v, st->num);
		break;
	case TCP_SEQ_STATE_OPENREQ:
		get_openreq6(seq, st->syn_wait_sk, v, st->num, st->uid);
		break;
	case TCP_SEQ_STATE_TIME_WAIT:
		get_timewait6_sock(seq, v, st->num);
		break;
	}
out:
	return 0;
}

static struct file_operations tcp6_seq_fops;
static struct tcp_seq_afinfo tcp6_seq_afinfo = {
	.owner		= THIS_MODULE,
	.name		= "tcp6",
	.family		= AF_INET6,
	.seq_show	= tcp6_seq_show,
	.seq_fops	= &tcp6_seq_fops,
};

int __init tcp6_proc_init(void)
{
	return tcp_proc_register(&tcp6_seq_afinfo);
}

void tcp6_proc_exit(void)
{
	tcp_proc_unregister(&tcp6_seq_afinfo);
}
#endif

struct proto tcpv6_prot = {
	.name			= "TCPv6",
	.owner			= THIS_MODULE,
	.close			= tcp_close,
	.connect		= tcp_v6_connect,
	.disconnect		= tcp_disconnect,
	.accept			= tcp_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v6_init_sock,
	.destroy		= tcp_v6_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.sendmsg		= tcp_sendmsg,
	.recvmsg		= tcp_recvmsg,
	.backlog_rcv		= tcp_v6_do_rcv,
	.hash			= tcp_v6_hash,
	.unhash			= tcp_unhash,
	.get_port		= tcp_v6_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.sockets_allocated	= &tcp_sockets_allocated,
	.memory_allocated	= &tcp_memory_allocated,
	.memory_pressure	= &tcp_memory_pressure,
	.sysctl_mem		= sysctl_tcp_mem,
	.sysctl_wmem		= sysctl_tcp_wmem,
	.sysctl_rmem		= sysctl_tcp_rmem,
	.max_header		= MAX_TCP_HEADER,
	.obj_size		= sizeof(struct tcp6_sock),
2239
	.rsk_prot		= &tcp6_request_sock_ops,
L
Linus Torvalds 已提交
2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266
};

static struct inet6_protocol tcpv6_protocol = {
	.handler	=	tcp_v6_rcv,
	.err_handler	=	tcp_v6_err,
	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};

extern struct proto_ops inet6_stream_ops;

static struct inet_protosw tcpv6_protosw = {
	.type		=	SOCK_STREAM,
	.protocol	=	IPPROTO_TCP,
	.prot		=	&tcpv6_prot,
	.ops		=	&inet6_stream_ops,
	.capability	=	-1,
	.no_check	=	0,
	.flags		=	INET_PROTOSW_PERMANENT,
};

void __init tcpv6_init(void)
{
	/* register inet6 protocol */
	if (inet6_add_protocol(&tcpv6_protocol, IPPROTO_TCP) < 0)
		printk(KERN_ERR "tcpv6_init: Could not register protocol\n");
	inet6_register_protosw(&tcpv6_protosw);
}