udp.c 24.3 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
/*
 *	UDP over IPv6
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	Based on linux/ipv4/udp.c
 *
 *	$Id: udp.c,v 1.65 2002/02/01 22:01:04 davem Exp $
 *
 *	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.
 *      Kazunori MIYAZAWA @USAGI:       change process style to use ip6_append_data
 *      YOSHIFUJI Hideaki @USAGI:	convert /proc/net/udp6 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/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/sched.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
38
#include <linux/skbuff.h>
L
Linus Torvalds 已提交
39 40 41 42 43 44 45 46 47 48 49 50 51 52 53
#include <asm/uaccess.h>

#include <net/sock.h>
#include <net/snmp.h>

#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/ip.h>
#include <net/udp.h>
#include <net/raw.h>
#include <net/inet_common.h>
54
#include <net/tcp_states.h>
L
Linus Torvalds 已提交
55 56 57 58 59 60 61

#include <net/ip6_checksum.h>
#include <net/xfrm.h>

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

62
DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly;
L
Linus Torvalds 已提交
63

64
static inline int udp_v6_get_port(struct sock *sk, unsigned short snum)
L
Linus Torvalds 已提交
65
{
66
	return udp_get_port(sk, snum, ipv6_rcv_saddr_equal);
L
Linus Torvalds 已提交
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178
}

static void udp_v6_hash(struct sock *sk)
{
	BUG();
}

static void udp_v6_unhash(struct sock *sk)
{
 	write_lock_bh(&udp_hash_lock);
	if (sk_del_node_init(sk)) {
		inet_sk(sk)->num = 0;
		sock_prot_dec_use(sk->sk_prot);
	}
	write_unlock_bh(&udp_hash_lock);
}

static struct sock *udp_v6_lookup(struct in6_addr *saddr, u16 sport,
				  struct in6_addr *daddr, u16 dport, int dif)
{
	struct sock *sk, *result = NULL;
	struct hlist_node *node;
	unsigned short hnum = ntohs(dport);
	int badness = -1;

 	read_lock(&udp_hash_lock);
	sk_for_each(sk, node, &udp_hash[hnum & (UDP_HTABLE_SIZE - 1)]) {
		struct inet_sock *inet = inet_sk(sk);

		if (inet->num == hnum && sk->sk_family == PF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(sk);
			int score = 0;
			if (inet->dport) {
				if (inet->dport != sport)
					continue;
				score++;
			}
			if (!ipv6_addr_any(&np->rcv_saddr)) {
				if (!ipv6_addr_equal(&np->rcv_saddr, daddr))
					continue;
				score++;
			}
			if (!ipv6_addr_any(&np->daddr)) {
				if (!ipv6_addr_equal(&np->daddr, saddr))
					continue;
				score++;
			}
			if (sk->sk_bound_dev_if) {
				if (sk->sk_bound_dev_if != dif)
					continue;
				score++;
			}
			if(score == 4) {
				result = sk;
				break;
			} else if(score > badness) {
				result = sk;
				badness = score;
			}
		}
	}
	if (result)
		sock_hold(result);
 	read_unlock(&udp_hash_lock);
	return result;
}

/*
 *
 */

static void udpv6_close(struct sock *sk, long timeout)
{
	sk_common_release(sk);
}

/*
 * 	This should be easy, if there is something there we
 * 	return it, otherwise we block.
 */

static int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, 
		  struct msghdr *msg, size_t len,
		  int noblock, int flags, int *addr_len)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct inet_sock *inet = inet_sk(sk);
  	struct sk_buff *skb;
	size_t copied;
  	int err;

  	if (addr_len)
  		*addr_len=sizeof(struct sockaddr_in6);
  
	if (flags & MSG_ERRQUEUE)
		return ipv6_recv_error(sk, msg, len);

try_again:
	skb = skb_recv_datagram(sk, flags, noblock, &err);
	if (!skb)
		goto out;

 	copied = skb->len - sizeof(struct udphdr);
  	if (copied > len) {
  		copied = len;
  		msg->msg_flags |= MSG_TRUNC;
  	}

	if (skb->ip_summed==CHECKSUM_UNNECESSARY) {
		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
					      copied);
	} else if (msg->msg_flags&MSG_TRUNC) {
179
		if (__skb_checksum_complete(skb))
L
Linus Torvalds 已提交
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
			goto csum_copy_err;
		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov,
					      copied);
	} else {
		err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov);
		if (err == -EINVAL)
			goto csum_copy_err;
	}
	if (err)
		goto out_free;

	sock_recv_timestamp(msg, sk, skb);

	/* Copy the address. */
	if (msg->msg_name) {
		struct sockaddr_in6 *sin6;
	  
		sin6 = (struct sockaddr_in6 *) msg->msg_name;
		sin6->sin6_family = AF_INET6;
		sin6->sin6_port = skb->h.uh->source;
		sin6->sin6_flowinfo = 0;
		sin6->sin6_scope_id = 0;

		if (skb->protocol == htons(ETH_P_IP))
			ipv6_addr_set(&sin6->sin6_addr, 0, 0,
				      htonl(0xffff), skb->nh.iph->saddr);
		else {
			ipv6_addr_copy(&sin6->sin6_addr, &skb->nh.ipv6h->saddr);
			if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL)
				sin6->sin6_scope_id = IP6CB(skb)->iif;
		}

	}
	if (skb->protocol == htons(ETH_P_IP)) {
		if (inet->cmsg_flags)
			ip_cmsg_recv(msg, skb);
	} else {
		if (np->rxopt.all)
			datagram_recv_ctl(sk, msg, skb);
  	}

	err = copied;
	if (flags & MSG_TRUNC)
		err = skb->len - sizeof(struct udphdr);

out_free:
	skb_free_datagram(sk, skb);
out:
	return err;

csum_copy_err:
231
	skb_kill_datagram(sk, skb, flags);
L
Linus Torvalds 已提交
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

	if (flags & MSG_DONTWAIT) {
		UDP6_INC_STATS_USER(UDP_MIB_INERRORS);
		return -EAGAIN;
	}
	goto try_again;
}

static void udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
	       int type, int code, int offset, __u32 info)
{
	struct ipv6_pinfo *np;
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	struct net_device *dev = skb->dev;
	struct in6_addr *saddr = &hdr->saddr;
	struct in6_addr *daddr = &hdr->daddr;
	struct udphdr *uh = (struct udphdr*)(skb->data+offset);
	struct sock *sk;
	int err;

	sk = udp_v6_lookup(daddr, uh->dest, saddr, uh->source, dev->ifindex);
   
	if (sk == NULL)
		return;

	np = inet6_sk(sk);

	if (!icmpv6_err_convert(type, code, &err) && !np->recverr)
		goto out;

	if (sk->sk_state != TCP_ESTABLISHED && !np->recverr)
		goto out;

	if (np->recverr)
		ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));

	sk->sk_err = err;
	sk->sk_error_report(sk);
out:
	sock_put(sk);
}

static inline int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
276 277
	int rc;

L
Linus Torvalds 已提交
278 279 280 281 282
	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
		kfree_skb(skb);
		return -1;
	}

283 284 285 286
	if (skb_checksum_complete(skb)) {
		UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
		kfree_skb(skb);
		return 0;
L
Linus Torvalds 已提交
287 288
	}

289 290 291
	if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) {
		/* Note that an ENOMEM error is charged twice */
		if (rc == -ENOMEM)
292
			UDP6_INC_STATS_BH(UDP_MIB_RCVBUFERRORS);
L
Linus Torvalds 已提交
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
		UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
		kfree_skb(skb);
		return 0;
	}
	UDP6_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
	return 0;
}

static struct sock *udp_v6_mcast_next(struct sock *sk,
				      u16 loc_port, struct in6_addr *loc_addr,
				      u16 rmt_port, struct in6_addr *rmt_addr,
				      int dif)
{
	struct hlist_node *node;
	struct sock *s = sk;
	unsigned short num = ntohs(loc_port);

	sk_for_each_from(s, node) {
		struct inet_sock *inet = inet_sk(s);

		if (inet->num == num && s->sk_family == PF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(s);
			if (inet->dport) {
				if (inet->dport != rmt_port)
					continue;
			}
			if (!ipv6_addr_any(&np->daddr) &&
			    !ipv6_addr_equal(&np->daddr, rmt_addr))
				continue;

			if (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)
				continue;

			if (!ipv6_addr_any(&np->rcv_saddr)) {
327 328
				if (!ipv6_addr_equal(&np->rcv_saddr, loc_addr))
					continue;
L
Linus Torvalds 已提交
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
			}
			if(!inet6_mc_check(s, loc_addr, rmt_addr))
				continue;
			return s;
		}
	}
	return NULL;
}

/*
 * Note: called only from the BH handler context,
 * so we don't need to lock the hashes.
 */
static void udpv6_mcast_deliver(struct udphdr *uh,
				struct in6_addr *saddr, struct in6_addr *daddr,
				struct sk_buff *skb)
{
	struct sock *sk, *sk2;
	int dif;

	read_lock(&udp_hash_lock);
	sk = sk_head(&udp_hash[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
	dif = skb->dev->ifindex;
	sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
	if (!sk) {
		kfree_skb(skb);
		goto out;
	}

	sk2 = sk;
	while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr,
					uh->source, saddr, dif))) {
		struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC);
		if (buff)
			udpv6_queue_rcv_skb(sk2, buff);
	}
	udpv6_queue_rcv_skb(sk, skb);
out:
	read_unlock(&udp_hash_lock);
}

370
static int udpv6_rcv(struct sk_buff **pskb)
L
Linus Torvalds 已提交
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
{
	struct sk_buff *skb = *pskb;
	struct sock *sk;
  	struct udphdr *uh;
	struct net_device *dev = skb->dev;
	struct in6_addr *saddr, *daddr;
	u32 ulen = 0;

	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto short_packet;

	saddr = &skb->nh.ipv6h->saddr;
	daddr = &skb->nh.ipv6h->daddr;
	uh = skb->h.uh;

	ulen = ntohs(uh->len);

	/* Check for jumbo payload */
	if (ulen == 0)
		ulen = skb->len;

	if (ulen > skb->len || ulen < sizeof(*uh))
		goto short_packet;

	if (uh->check == 0) {
		/* RFC 2460 section 8.1 says that we SHOULD log
		   this error. Well, it is reasonable.
		 */
399
		LIMIT_NETDEBUG(KERN_INFO "IPv6: udp checksum is 0\n");
L
Linus Torvalds 已提交
400 401 402 403
		goto discard;
	}

	if (ulen < skb->len) {
404
		if (pskb_trim_rcsum(skb, ulen))
L
Linus Torvalds 已提交
405 406 407 408 409 410
			goto discard;
		saddr = &skb->nh.ipv6h->saddr;
		daddr = &skb->nh.ipv6h->daddr;
		uh = skb->h.uh;
	}

411
	if (skb->ip_summed == CHECKSUM_COMPLETE &&
412
	    !csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, skb->csum))
L
Linus Torvalds 已提交
413
		skb->ip_summed = CHECKSUM_UNNECESSARY;
414

L
Linus Torvalds 已提交
415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437
	if (skb->ip_summed != CHECKSUM_UNNECESSARY)
		skb->csum = ~csum_ipv6_magic(saddr, daddr, ulen, IPPROTO_UDP, 0);

	/* 
	 *	Multicast receive code 
	 */
	if (ipv6_addr_is_multicast(daddr)) {
		udpv6_mcast_deliver(uh, saddr, daddr, skb);
		return 0;
	}

	/* Unicast */

	/* 
	 * check socket cache ... must talk to Alan about his plans
	 * for sock caches... i'll skip this for now.
	 */
	sk = udp_v6_lookup(saddr, uh->source, daddr, uh->dest, dev->ifindex);

	if (sk == NULL) {
		if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
			goto discard;

438
		if (skb_checksum_complete(skb))
L
Linus Torvalds 已提交
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
			goto discard;
		UDP6_INC_STATS_BH(UDP_MIB_NOPORTS);

		icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0, dev);

		kfree_skb(skb);
		return(0);
	}
	
	/* deliver */
	
	udpv6_queue_rcv_skb(sk, skb);
	sock_put(sk);
	return(0);

short_packet:	
	if (net_ratelimit())
		printk(KERN_DEBUG "UDP: short packet: %d/%u\n", ulen, skb->len);

discard:
	UDP6_INC_STATS_BH(UDP_MIB_INERRORS);
	kfree_skb(skb);
	return(0);	
}
/*
 * Throw away all pending data and cancel the corking. Socket is locked.
 */
static void udp_v6_flush_pending_frames(struct sock *sk)
{
	struct udp_sock *up = udp_sk(sk);

	if (up->pending) {
		up->len = 0;
		up->pending = 0;
		ip6_flush_pending_frames(sk);
        }
}

/*
 *	Sending
 */

static int udp_v6_push_pending_frames(struct sock *sk, struct udp_sock *up)
{
	struct sk_buff *skb;
	struct udphdr *uh;
	struct inet_sock *inet = inet_sk(sk);
	struct flowi *fl = &inet->cork.fl;
	int err = 0;

	/* Grab the skbuff where UDP header space exists. */
	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	/*
	 * Create a UDP header
	 */
	uh = skb->h.uh;
	uh->source = fl->fl_ip_sport;
	uh->dest = fl->fl_ip_dport;
	uh->len = htons(up->len);
	uh->check = 0;

	if (sk->sk_no_check == UDP_CSUM_NOXMIT) {
		skb->ip_summed = CHECKSUM_NONE;
		goto send;
	}

	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		skb->csum = csum_partial((char *)uh,
				sizeof(struct udphdr), skb->csum);
		uh->check = csum_ipv6_magic(&fl->fl6_src,
					    &fl->fl6_dst,
					    up->len, fl->proto, skb->csum);
	} else {
		u32 tmp_csum = 0;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			tmp_csum = csum_add(tmp_csum, skb->csum);
		}
		tmp_csum = csum_partial((char *)uh,
				sizeof(struct udphdr), tmp_csum);
                tmp_csum = csum_ipv6_magic(&fl->fl6_src,
					   &fl->fl6_dst,
					   up->len, fl->proto, tmp_csum);
                uh->check = tmp_csum;

	}
	if (uh->check == 0)
		uh->check = -1;

send:
	err = ip6_push_pending_frames(sk);
out:
	up->len = 0;
	up->pending = 0;
	return err;
}

static int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, 
		  struct msghdr *msg, size_t len)
{
	struct ipv6_txoptions opt_space;
	struct udp_sock *up = udp_sk(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) msg->msg_name;
	struct in6_addr *daddr, *final_p = NULL, final;
	struct ipv6_txoptions *opt = NULL;
	struct ip6_flowlabel *flowlabel = NULL;
H
Herbert Xu 已提交
549
	struct flowi fl;
L
Linus Torvalds 已提交
550 551 552 553
	struct dst_entry *dst;
	int addr_len = msg->msg_namelen;
	int ulen = len;
	int hlimit = -1;
554
	int tclass = -1;
L
Linus Torvalds 已提交
555 556
	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
	int err;
557
	int connected = 0;
L
Linus Torvalds 已提交
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

	/* destination address check */
	if (sin6) {
		if (addr_len < offsetof(struct sockaddr, sa_data))
			return -EINVAL;

		switch (sin6->sin6_family) {
		case AF_INET6:
			if (addr_len < SIN6_LEN_RFC2133)
				return -EINVAL;
			daddr = &sin6->sin6_addr;
			break;
		case AF_INET:
			goto do_udp_sendmsg;
		case AF_UNSPEC:
			msg->msg_name = sin6 = NULL;
			msg->msg_namelen = addr_len = 0;
			daddr = NULL;
			break;
		default:
			return -EINVAL;
		}
	} else if (!up->pending) {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;
		daddr = &np->daddr;
	} else 
		daddr = NULL;

	if (daddr) {
		if (ipv6_addr_type(daddr) == IPV6_ADDR_MAPPED) {
			struct sockaddr_in sin;
			sin.sin_family = AF_INET;
			sin.sin_port = sin6 ? sin6->sin6_port : inet->dport;
			sin.sin_addr.s_addr = daddr->s6_addr32[3];
			msg->msg_name = &sin;
			msg->msg_namelen = sizeof(sin);
do_udp_sendmsg:
			if (__ipv6_only_sock(sk))
				return -ENETUNREACH;
			return udp_sendmsg(iocb, sk, msg, len);
		}
	}

	if (up->pending == AF_INET)
		return udp_sendmsg(iocb, sk, msg, len);

	/* Rough check on arithmetic overflow,
	   better check is made in ip6_build_xmit
	   */
	if (len > INT_MAX - sizeof(struct udphdr))
		return -EMSGSIZE;
	
	if (up->pending) {
		/*
		 * There are pending frames.
		 * The socket lock must be held while it's corked.
		 */
		lock_sock(sk);
		if (likely(up->pending)) {
			if (unlikely(up->pending != AF_INET6)) {
				release_sock(sk);
				return -EAFNOSUPPORT;
			}
			dst = NULL;
			goto do_append_data;
		}
		release_sock(sk);
	}
	ulen += sizeof(struct udphdr);

H
Herbert Xu 已提交
629
	memset(&fl, 0, sizeof(fl));
L
Linus Torvalds 已提交
630 631 632 633 634

	if (sin6) {
		if (sin6->sin6_port == 0)
			return -EINVAL;

H
Herbert Xu 已提交
635
		fl.fl_ip_dport = sin6->sin6_port;
L
Linus Torvalds 已提交
636 637 638
		daddr = &sin6->sin6_addr;

		if (np->sndflow) {
H
Herbert Xu 已提交
639 640 641
			fl.fl6_flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
			if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
				flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
L
Linus Torvalds 已提交
642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658
				if (flowlabel == NULL)
					return -EINVAL;
				daddr = &flowlabel->dst;
			}
		}

		/*
		 * Otherwise it will be difficult to maintain
		 * sk->sk_dst_cache.
		 */
		if (sk->sk_state == TCP_ESTABLISHED &&
		    ipv6_addr_equal(daddr, &np->daddr))
			daddr = &np->daddr;

		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    sin6->sin6_scope_id &&
		    ipv6_addr_type(daddr)&IPV6_ADDR_LINKLOCAL)
H
Herbert Xu 已提交
659
			fl.oif = sin6->sin6_scope_id;
L
Linus Torvalds 已提交
660 661 662 663
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;

H
Herbert Xu 已提交
664
		fl.fl_ip_dport = inet->dport;
L
Linus Torvalds 已提交
665
		daddr = &np->daddr;
H
Herbert Xu 已提交
666
		fl.fl6_flowlabel = np->flow_label;
667
		connected = 1;
L
Linus Torvalds 已提交
668 669
	}

H
Herbert Xu 已提交
670 671
	if (!fl.oif)
		fl.oif = sk->sk_bound_dev_if;
L
Linus Torvalds 已提交
672 673 674 675 676 677

	if (msg->msg_controllen) {
		opt = &opt_space;
		memset(opt, 0, sizeof(struct ipv6_txoptions));
		opt->tot_len = sizeof(*opt);

H
Herbert Xu 已提交
678
		err = datagram_send_ctl(msg, &fl, opt, &hlimit, &tclass);
L
Linus Torvalds 已提交
679 680 681 682
		if (err < 0) {
			fl6_sock_release(flowlabel);
			return err;
		}
H
Herbert Xu 已提交
683 684
		if ((fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
L
Linus Torvalds 已提交
685 686 687 688 689
			if (flowlabel == NULL)
				return -EINVAL;
		}
		if (!(opt->opt_nflen|opt->opt_flen))
			opt = NULL;
690
		connected = 0;
L
Linus Torvalds 已提交
691 692 693
	}
	if (opt == NULL)
		opt = np->opt;
694 695 696
	if (flowlabel)
		opt = fl6_merge_options(&opt_space, flowlabel, opt);
	opt = ipv6_fixup_options(&opt_space, opt);
L
Linus Torvalds 已提交
697

H
Herbert Xu 已提交
698 699 700 701 702
	fl.proto = IPPROTO_UDP;
	ipv6_addr_copy(&fl.fl6_dst, daddr);
	if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr))
		ipv6_addr_copy(&fl.fl6_src, &np->saddr);
	fl.fl_ip_sport = inet->sport;
L
Linus Torvalds 已提交
703 704 705 706
	
	/* merge ip6_build_xmit from ip6_output */
	if (opt && opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
H
Herbert Xu 已提交
707 708
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
L
Linus Torvalds 已提交
709
		final_p = &final;
710
		connected = 0;
L
Linus Torvalds 已提交
711 712
	}

H
Herbert Xu 已提交
713 714
	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst)) {
		fl.oif = np->mcast_oif;
715 716
		connected = 0;
	}
L
Linus Torvalds 已提交
717

H
Herbert Xu 已提交
718
	security_sk_classify_flow(sk, &fl);
V
Venkat Yekkirala 已提交
719

H
Herbert Xu 已提交
720
	err = ip6_sk_dst_lookup(sk, &dst, &fl);
L
Linus Torvalds 已提交
721 722 723
	if (err)
		goto out;
	if (final_p)
H
Herbert Xu 已提交
724
		ipv6_addr_copy(&fl.fl6_dst, final_p);
L
Linus Torvalds 已提交
725

H
Herbert Xu 已提交
726
	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
L
Linus Torvalds 已提交
727 728 729
		goto out;

	if (hlimit < 0) {
H
Herbert Xu 已提交
730
		if (ipv6_addr_is_multicast(&fl.fl6_dst))
L
Linus Torvalds 已提交
731 732 733 734 735 736 737 738 739
			hlimit = np->mcast_hops;
		else
			hlimit = np->hop_limit;
		if (hlimit < 0)
			hlimit = dst_metric(dst, RTAX_HOPLIMIT);
		if (hlimit < 0)
			hlimit = ipv6_get_hoplimit(dst->dev);
	}

740 741 742 743 744 745
	if (tclass < 0) {
		tclass = np->tclass;
		if (tclass < 0)
			tclass = 0;
	}

L
Linus Torvalds 已提交
746 747 748 749 750 751 752 753 754 755
	if (msg->msg_flags&MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	lock_sock(sk);
	if (unlikely(up->pending)) {
		/* The socket is already corked while preparing it. */
		/* ... which is an evident application bug. --ANK */
		release_sock(sk);

756
		LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n");
L
Linus Torvalds 已提交
757 758 759 760 761 762 763 764
		err = -EINVAL;
		goto out;
	}

	up->pending = AF_INET6;

do_append_data:
	up->len += ulen;
765
	err = ip6_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen,
H
Herbert Xu 已提交
766
		sizeof(struct udphdr), hlimit, tclass, opt, &fl,
767 768
		(struct rt6_info*)dst,
		corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
L
Linus Torvalds 已提交
769 770 771 772
	if (err)
		udp_v6_flush_pending_frames(sk);
	else if (!corkreq)
		err = udp_v6_push_pending_frames(sk, up);
H
Herbert Xu 已提交
773 774
	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
		up->pending = 0;
L
Linus Torvalds 已提交
775

776 777 778
	if (dst) {
		if (connected) {
			ip6_dst_store(sk, dst,
H
Herbert Xu 已提交
779
				      ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ?
780 781
				      &np->daddr : NULL,
#ifdef CONFIG_IPV6_SUBTREES
H
Herbert Xu 已提交
782
				      ipv6_addr_equal(&fl.fl6_src, &np->saddr) ?
783 784 785
				      &np->saddr :
#endif
				      NULL);
786 787 788 789 790
		} else {
			dst_release(dst);
		}
	}

L
Linus Torvalds 已提交
791 792 793 794 795 796 797 798 799
	if (err > 0)
		err = np->recverr ? net_xmit_errno(err) : 0;
	release_sock(sk);
out:
	fl6_sock_release(flowlabel);
	if (!err) {
		UDP6_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS);
		return len;
	}
800 801 802 803 804 805 806 807
	/*
	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
	 * ENOBUFS might not be good (it's not tunable per se), but otherwise
	 * we don't have a good statistic (IpOutDiscards but it can be too many
	 * things).  We could add another new stat but at least for now that
	 * seems like overkill.
	 */
	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) {
808
		UDP6_INC_STATS_USER(UDP_MIB_SNDBUFERRORS);
809
	}
L
Linus Torvalds 已提交
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833
	return err;

do_confirm:
	dst_confirm(dst);
	if (!(msg->msg_flags&MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto out;
}

static int udpv6_destroy_sock(struct sock *sk)
{
	lock_sock(sk);
	udp_v6_flush_pending_frames(sk);
	release_sock(sk);

	inet6_destroy_sock(sk);

	return 0;
}

/*
 *	Socket option code for UDP
 */
834
static int do_udpv6_setsockopt(struct sock *sk, int level, int optname,
L
Linus Torvalds 已提交
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
			  char __user *optval, int optlen)
{
	struct udp_sock *up = udp_sk(sk);
	int val;
	int err = 0;

	if(optlen<sizeof(int))
		return -EINVAL;

	if (get_user(val, (int __user *)optval))
		return -EFAULT;

	switch(optname) {
	case UDP_CORK:
		if (val != 0) {
			up->corkflag = 1;
		} else {
			up->corkflag = 0;
			lock_sock(sk);
			udp_v6_push_pending_frames(sk, up);
			release_sock(sk);
		}
		break;
		
	case UDP_ENCAP:
		switch (val) {
		case 0:
			up->encap_type = val;
			break;
		default:
			err = -ENOPROTOOPT;
			break;
		}
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	};

	return err;
}

878 879 880 881 882 883 884 885 886 887
static int udpv6_setsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int optlen)
{
	if (level != SOL_UDP)
		return ipv6_setsockopt(sk, level, optname, optval, optlen);
	return do_udpv6_setsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_udpv6_setsockopt(struct sock *sk, int level, int optname,
888
				   char __user *optval, int optlen)
889 890
{
	if (level != SOL_UDP)
891 892
		return compat_ipv6_setsockopt(sk, level, optname,
					      optval, optlen);
893 894 895 896 897
	return do_udpv6_setsockopt(sk, level, optname, optval, optlen);
}
#endif

static int do_udpv6_getsockopt(struct sock *sk, int level, int optname,
L
Linus Torvalds 已提交
898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930
			  char __user *optval, int __user *optlen)
{
	struct udp_sock *up = udp_sk(sk);
	int val, len;

	if(get_user(len,optlen))
		return -EFAULT;

	len = min_t(unsigned int, len, sizeof(int));
	
	if(len < 0)
		return -EINVAL;

	switch(optname) {
	case UDP_CORK:
		val = up->corkflag;
		break;

	case UDP_ENCAP:
		val = up->encap_type;
		break;

	default:
		return -ENOPROTOOPT;
	};

  	if(put_user(len, optlen))
  		return -EFAULT;
	if(copy_to_user(optval, &val,len))
		return -EFAULT;
  	return 0;
}

931 932 933 934 935 936 937 938 939 940
static int udpv6_getsockopt(struct sock *sk, int level, int optname,
			  char __user *optval, int __user *optlen)
{
	if (level != SOL_UDP)
		return ipv6_getsockopt(sk, level, optname, optval, optlen);
	return do_udpv6_getsockopt(sk, level, optname, optval, optlen);
}

#ifdef CONFIG_COMPAT
static int compat_udpv6_getsockopt(struct sock *sk, int level, int optname,
941
				   char __user *optval, int __user *optlen)
942 943
{
	if (level != SOL_UDP)
944 945
		return compat_ipv6_getsockopt(sk, level, optname,
					      optval, optlen);
946 947 948 949
	return do_udpv6_getsockopt(sk, level, optname, optval, optlen);
}
#endif

L
Linus Torvalds 已提交
950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022
static struct inet6_protocol udpv6_protocol = {
	.handler	=	udpv6_rcv,
	.err_handler	=	udpv6_err,
	.flags		=	INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
};

/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS

static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket)
{
	struct inet_sock *inet = inet_sk(sp);
	struct ipv6_pinfo *np = inet6_sk(sp);
	struct in6_addr *dest, *src;
	__u16 destp, srcp;

	dest  = &np->daddr;
	src   = &np->rcv_saddr;
	destp = ntohs(inet->dport);
	srcp  = ntohs(inet->sport);
	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\n",
		   bucket,
		   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, 
		   atomic_read(&sp->sk_wmem_alloc),
		   atomic_read(&sp->sk_rmem_alloc),
		   0, 0L, 0,
		   sock_i_uid(sp), 0,
		   sock_i_ino(sp),
		   atomic_read(&sp->sk_refcnt), sp);
}

static int udp6_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq,
			   "  sl  "
			   "local_address                         "
			   "remote_address                        "
			   "st tx_queue rx_queue tr tm->when retrnsmt"
			   "   uid  timeout inode\n");
	else
		udp6_sock_seq_show(seq, v, ((struct udp_iter_state *)seq->private)->bucket);
	return 0;
}

static struct file_operations udp6_seq_fops;
static struct udp_seq_afinfo udp6_seq_afinfo = {
	.owner		= THIS_MODULE,
	.name		= "udp6",
	.family		= AF_INET6,
	.seq_show	= udp6_seq_show,
	.seq_fops	= &udp6_seq_fops,
};

int __init udp6_proc_init(void)
{
	return udp_proc_register(&udp6_seq_afinfo);
}

void udp6_proc_exit(void) {
	udp_proc_unregister(&udp6_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */

/* ------------------------------------------------------------------------ */

struct proto udpv6_prot = {
1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038
	.name		   = "UDPv6",
	.owner		   = THIS_MODULE,
	.close		   = udpv6_close,
	.connect	   = ip6_datagram_connect,
	.disconnect	   = udp_disconnect,
	.ioctl		   = udp_ioctl,
	.destroy	   = udpv6_destroy_sock,
	.setsockopt	   = udpv6_setsockopt,
	.getsockopt	   = udpv6_getsockopt,
	.sendmsg	   = udpv6_sendmsg,
	.recvmsg	   = udpv6_recvmsg,
	.backlog_rcv	   = udpv6_queue_rcv_skb,
	.hash		   = udp_v6_hash,
	.unhash		   = udp_v6_unhash,
	.get_port	   = udp_v6_get_port,
	.obj_size	   = sizeof(struct udp6_sock),
1039
#ifdef CONFIG_COMPAT
1040 1041
	.compat_setsockopt = compat_udpv6_setsockopt,
	.compat_getsockopt = compat_udpv6_getsockopt,
1042
#endif
L
Linus Torvalds 已提交
1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061
};

static struct inet_protosw udpv6_protosw = {
	.type =      SOCK_DGRAM,
	.protocol =  IPPROTO_UDP,
	.prot =      &udpv6_prot,
	.ops =       &inet6_dgram_ops,
	.capability =-1,
	.no_check =  UDP_CSUM_DEFAULT,
	.flags =     INET_PROTOSW_PERMANENT,
};


void __init udpv6_init(void)
{
	if (inet6_add_protocol(&udpv6_protocol, IPPROTO_UDP) < 0)
		printk(KERN_ERR "udpv6_init: Could not register protocol\n");
	inet6_register_protosw(&udpv6_protosw);
}