udp.c 37.3 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 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		The User Datagram Protocol (UDP).
 *
 * Version:	$Id: udp.c,v 1.102 2002/02/01 22:01:04 davem Exp $
 *
 * Authors:	Ross Biro, <bir7@leland.Stanford.Edu>
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *		Alan Cox, <Alan.Cox@linux.org>
 *		Hirokazu Takahashi, <taka@valinux.co.jp>
 *
 * Fixes:
 *		Alan Cox	:	verify_area() calls
 *		Alan Cox	: 	stopped close while in use off icmp
 *					messages. Not a fix but a botch that
 *					for udp at least is 'valid'.
 *		Alan Cox	:	Fixed icmp handling properly
 *		Alan Cox	: 	Correct error for oversized datagrams
 *		Alan Cox	:	Tidied select() semantics. 
 *		Alan Cox	:	udp_err() fixed properly, also now 
 *					select and read wake correctly on errors
 *		Alan Cox	:	udp_send verify_area moved to avoid mem leak
 *		Alan Cox	:	UDP can count its memory
 *		Alan Cox	:	send to an unknown connection causes
 *					an ECONNREFUSED off the icmp, but
 *					does NOT close.
 *		Alan Cox	:	Switched to new sk_buff handlers. No more backlog!
 *		Alan Cox	:	Using generic datagram code. Even smaller and the PEEK
 *					bug no longer crashes it.
 *		Fred Van Kempen	: 	Net2e support for sk->broadcast.
 *		Alan Cox	:	Uses skb_free_datagram
 *		Alan Cox	:	Added get/set sockopt support.
 *		Alan Cox	:	Broadcasting without option set returns EACCES.
 *		Alan Cox	:	No wakeup calls. Instead we now use the callbacks.
 *		Alan Cox	:	Use ip_tos and ip_ttl
 *		Alan Cox	:	SNMP Mibs
 *		Alan Cox	:	MSG_DONTROUTE, and 0.0.0.0 support.
 *		Matt Dillon	:	UDP length checks.
 *		Alan Cox	:	Smarter af_inet used properly.
 *		Alan Cox	:	Use new kernel side addressing.
 *		Alan Cox	:	Incorrect return on truncated datagram receive.
 *	Arnt Gulbrandsen 	:	New udp_send and stuff
 *		Alan Cox	:	Cache last socket
 *		Alan Cox	:	Route cache
 *		Jon Peatfield	:	Minor efficiency fix to sendto().
 *		Mike Shaver	:	RFC1122 checks.
 *		Alan Cox	:	Nonblocking error fix.
 *	Willy Konynenberg	:	Transparent proxying support.
 *		Mike McLagan	:	Routing by source
 *		David S. Miller	:	New socket lookup architecture.
 *					Last socket cache retained as it
 *					does have a high hit rate.
 *		Olaf Kirch	:	Don't linearise iovec on sendmsg.
 *		Andi Kleen	:	Some cleanups, cache destination entry
 *					for connect. 
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *		Melvin Smith	:	Check msg_name not msg_namelen in sendto(),
 *					return ENOTCONN for unconnected sockets (POSIX)
 *		Janos Farkas	:	don't deliver multi/broadcasts to a different
 *					bound-to-device socket
 *	Hirokazu Takahashi	:	HW checksumming for outgoing UDP
 *					datagrams.
 *	Hirokazu Takahashi	:	sendfile() on UDP works now.
 *		Arnaldo C. Melo :	convert /proc/net/udp to seq_file
 *	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.
 *	Derek Atkins <derek@ihtfp.com>: Add Encapulation Support
 *
 *
 *		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 <asm/system.h>
#include <asm/uaccess.h>
#include <asm/ioctls.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/config.h>
#include <linux/inet.h>
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <net/snmp.h>
#include <net/tcp.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/sock.h>
#include <net/udp.h>
#include <net/icmp.h>
#include <net/route.h>
#include <net/inet_common.h>
#include <net/checksum.h>
#include <net/xfrm.h>

/*
 *	Snmp MIB for the UDP layer
 */

DEFINE_SNMP_STAT(struct udp_mib, udp_statistics);

struct hlist_head udp_hash[UDP_HTABLE_SIZE];
DEFINE_RWLOCK(udp_hash_lock);

/* Shared by v4/v6 udp. */
int udp_port_rover;

static int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
	struct hlist_node *node;
	struct sock *sk2;
	struct inet_sock *inet = inet_sk(sk);

	write_lock_bh(&udp_hash_lock);
	if (snum == 0) {
		int best_size_so_far, best, result, i;

		if (udp_port_rover > sysctl_local_port_range[1] ||
		    udp_port_rover < sysctl_local_port_range[0])
			udp_port_rover = sysctl_local_port_range[0];
		best_size_so_far = 32767;
		best = result = udp_port_rover;
		for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
			struct hlist_head *list;
			int size;

			list = &udp_hash[result & (UDP_HTABLE_SIZE - 1)];
			if (hlist_empty(list)) {
				if (result > sysctl_local_port_range[1])
					result = sysctl_local_port_range[0] +
						((result - sysctl_local_port_range[0]) &
						 (UDP_HTABLE_SIZE - 1));
				goto gotit;
			}
			size = 0;
			sk_for_each(sk2, node, list)
				if (++size >= best_size_so_far)
					goto next;
			best_size_so_far = size;
			best = result;
		next:;
		}
		result = best;
		for(i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++, result += UDP_HTABLE_SIZE) {
			if (result > sysctl_local_port_range[1])
				result = sysctl_local_port_range[0]
					+ ((result - sysctl_local_port_range[0]) &
					   (UDP_HTABLE_SIZE - 1));
			if (!udp_lport_inuse(result))
				break;
		}
		if (i >= (1 << 16) / UDP_HTABLE_SIZE)
			goto fail;
gotit:
		udp_port_rover = snum = result;
	} else {
		sk_for_each(sk2, node,
			    &udp_hash[snum & (UDP_HTABLE_SIZE - 1)]) {
			struct inet_sock *inet2 = inet_sk(sk2);

			if (inet2->num == snum &&
			    sk2 != sk &&
			    !ipv6_only_sock(sk2) &&
			    (!sk2->sk_bound_dev_if ||
			     !sk->sk_bound_dev_if ||
			     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
			    (!inet2->rcv_saddr ||
			     !inet->rcv_saddr ||
			     inet2->rcv_saddr == inet->rcv_saddr) &&
			    (!sk2->sk_reuse || !sk->sk_reuse))
				goto fail;
		}
	}
	inet->num = snum;
	if (sk_unhashed(sk)) {
		struct hlist_head *h = &udp_hash[snum & (UDP_HTABLE_SIZE - 1)];

		sk_add_node(sk, h);
		sock_prot_inc_use(sk->sk_prot);
	}
	write_unlock_bh(&udp_hash_lock);
	return 0;

fail:
	write_unlock_bh(&udp_hash_lock);
	return 1;
}

static void udp_v4_hash(struct sock *sk)
{
	BUG();
}

static void udp_v4_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);
}

/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
 * harder than this. -DaveM
 */
static struct sock *udp_v4_lookup_longway(u32 saddr, u16 sport,
					  u32 daddr, u16 dport, int dif)
{
	struct sock *sk, *result = NULL;
	struct hlist_node *node;
	unsigned short hnum = ntohs(dport);
	int badness = -1;

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

		if (inet->num == hnum && !ipv6_only_sock(sk)) {
			int score = (sk->sk_family == PF_INET ? 1 : 0);
			if (inet->rcv_saddr) {
				if (inet->rcv_saddr != daddr)
					continue;
				score+=2;
			}
			if (inet->daddr) {
				if (inet->daddr != saddr)
					continue;
				score+=2;
			}
			if (inet->dport) {
				if (inet->dport != sport)
					continue;
				score+=2;
			}
			if (sk->sk_bound_dev_if) {
				if (sk->sk_bound_dev_if != dif)
					continue;
				score+=2;
			}
			if(score == 9) {
				result = sk;
				break;
			} else if(score > badness) {
				result = sk;
				badness = score;
			}
		}
	}
	return result;
}

static __inline__ struct sock *udp_v4_lookup(u32 saddr, u16 sport,
					     u32 daddr, u16 dport, int dif)
{
	struct sock *sk;

	read_lock(&udp_hash_lock);
	sk = udp_v4_lookup_longway(saddr, sport, daddr, dport, dif);
	if (sk)
		sock_hold(sk);
	read_unlock(&udp_hash_lock);
	return sk;
}

static inline struct sock *udp_v4_mcast_next(struct sock *sk,
					     u16 loc_port, u32 loc_addr,
					     u16 rmt_port, u32 rmt_addr,
					     int dif)
{
	struct hlist_node *node;
	struct sock *s = sk;
	unsigned short hnum = ntohs(loc_port);

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

		if (inet->num != hnum					||
		    (inet->daddr && inet->daddr != rmt_addr)		||
		    (inet->dport != rmt_port && inet->dport)		||
		    (inet->rcv_saddr && inet->rcv_saddr != loc_addr)	||
		    ipv6_only_sock(s)					||
		    (s->sk_bound_dev_if && s->sk_bound_dev_if != dif))
			continue;
		if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif))
			continue;
		goto found;
  	}
	s = NULL;
found:
  	return s;
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.  
 * Header points to the ip header of the error packet. We move
 * on past this. Then (as it used to claim before adjustment)
 * header points to the first 8 bytes of the udp header.  We need
 * to find the appropriate port.
 */

void udp_err(struct sk_buff *skb, u32 info)
{
	struct inet_sock *inet;
	struct iphdr *iph = (struct iphdr*)skb->data;
	struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;
	struct sock *sk;
	int harderr;
	int err;

	sk = udp_v4_lookup(iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex);
	if (sk == NULL) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
    	  	return;	/* No socket for error */
	}

	err = 0;
	harderr = 0;
	inet = inet_sk(sk);

	switch (type) {
	default:
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	case ICMP_SOURCE_QUENCH:
		goto out;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		harderr = 1;
		break;
	case ICMP_DEST_UNREACH:
		if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
			if (inet->pmtudisc != IP_PMTUDISC_DONT) {
				err = EMSGSIZE;
				harderr = 1;
				break;
			}
			goto out;
		}
		err = EHOSTUNREACH;
		if (code <= NR_ICMP_UNREACH) {
			harderr = icmp_err_convert[code].fatal;
			err = icmp_err_convert[code].errno;
		}
		break;
	}

	/*
	 *      RFC1122: OK.  Passes ICMP errors back to application, as per 
	 *	4.1.3.3.
	 */
	if (!inet->recverr) {
		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
			goto out;
	} else {
		ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1));
	}
	sk->sk_err = err;
	sk->sk_error_report(sk);
out:
	sock_put(sk);
}

/*
 * Throw away all pending data and cancel the corking. Socket is locked.
 */
static void udp_flush_pending_frames(struct sock *sk)
{
	struct udp_sock *up = udp_sk(sk);

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

/*
 * Push out all pending data as one UDP datagram. Socket is locked.
 */
static int udp_push_pending_frames(struct sock *sk, struct udp_sock *up)
{
	struct inet_sock *inet = inet_sk(sk);
	struct flowi *fl = &inet->cork.fl;
	struct sk_buff *skb;
	struct udphdr *uh;
	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) {
		/*
		 * Only one fragment on the socket.
		 */
		if (skb->ip_summed == CHECKSUM_HW) {
			skb->csum = offsetof(struct udphdr, check);
			uh->check = ~csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst,
					up->len, IPPROTO_UDP, 0);
		} else {
			skb->csum = csum_partial((char *)uh,
					sizeof(struct udphdr), skb->csum);
			uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst,
					up->len, IPPROTO_UDP, skb->csum);
			if (uh->check == 0)
				uh->check = -1;
		}
	} else {
		unsigned int csum = 0;
		/*
		 * HW-checksum won't work as there are two or more 
		 * fragments on the socket so that all csums of sk_buffs
		 * should be together.
		 */
		if (skb->ip_summed == CHECKSUM_HW) {
			int offset = (unsigned char *)uh - skb->data;
			skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);

			skb->ip_summed = CHECKSUM_NONE;
		} else {
			skb->csum = csum_partial((char *)uh,
					sizeof(struct udphdr), skb->csum);
		}

		skb_queue_walk(&sk->sk_write_queue, skb) {
			csum = csum_add(csum, skb->csum);
		}
		uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst,
				up->len, IPPROTO_UDP, csum);
		if (uh->check == 0)
			uh->check = -1;
	}
send:
	err = ip_push_pending_frames(sk);
out:
	up->len = 0;
	up->pending = 0;
	return err;
}


static unsigned short udp_check(struct udphdr *uh, int len, unsigned long saddr, unsigned long daddr, unsigned long base)
{
	return(csum_tcpudp_magic(saddr, daddr, len, IPPROTO_UDP, base));
}

int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct udp_sock *up = udp_sk(sk);
	int ulen = len;
	struct ipcm_cookie ipc;
	struct rtable *rt = NULL;
	int free = 0;
	int connected = 0;
	u32 daddr, faddr, saddr;
	u16 dport;
	u8  tos;
	int err;
	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;

	if (len > 0xFFFF)
		return -EMSGSIZE;

	/* 
	 *	Check the flags.
	 */

	if (msg->msg_flags&MSG_OOB)	/* Mirror BSD error message compatibility */
		return -EOPNOTSUPP;

	ipc.opt = NULL;

	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_INET)) {
				release_sock(sk);
				return -EINVAL;
			}
 			goto do_append_data;
		}
		release_sock(sk);
	}
	ulen += sizeof(struct udphdr);

	/*
	 *	Get and verify the address. 
	 */
	if (msg->msg_name) {
		struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name;
		if (msg->msg_namelen < sizeof(*usin))
			return -EINVAL;
		if (usin->sin_family != AF_INET) {
			if (usin->sin_family != AF_UNSPEC)
				return -EAFNOSUPPORT;
		}

		daddr = usin->sin_addr.s_addr;
		dport = usin->sin_port;
		if (dport == 0)
			return -EINVAL;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;
		daddr = inet->daddr;
		dport = inet->dport;
		/* Open fast path for connected socket.
		   Route will not be used, if at least one option is set.
		 */
		connected = 1;
  	}
	ipc.addr = inet->saddr;

	ipc.oif = sk->sk_bound_dev_if;
	if (msg->msg_controllen) {
		err = ip_cmsg_send(msg, &ipc);
		if (err)
			return err;
		if (ipc.opt)
			free = 1;
		connected = 0;
	}
	if (!ipc.opt)
		ipc.opt = inet->opt;

	saddr = ipc.addr;
	ipc.addr = faddr = daddr;

	if (ipc.opt && ipc.opt->srr) {
		if (!daddr)
			return -EINVAL;
		faddr = ipc.opt->faddr;
		connected = 0;
	}
	tos = RT_TOS(inet->tos);
	if (sock_flag(sk, SOCK_LOCALROUTE) ||
	    (msg->msg_flags & MSG_DONTROUTE) || 
	    (ipc.opt && ipc.opt->is_strictroute)) {
		tos |= RTO_ONLINK;
		connected = 0;
	}

	if (MULTICAST(daddr)) {
		if (!ipc.oif)
			ipc.oif = inet->mc_index;
		if (!saddr)
			saddr = inet->mc_addr;
		connected = 0;
	}

	if (connected)
		rt = (struct rtable*)sk_dst_check(sk, 0);

	if (rt == NULL) {
		struct flowi fl = { .oif = ipc.oif,
				    .nl_u = { .ip4_u =
					      { .daddr = faddr,
						.saddr = saddr,
						.tos = tos } },
				    .proto = IPPROTO_UDP,
				    .uli_u = { .ports =
					       { .sport = inet->sport,
						 .dport = dport } } };
		err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT));
		if (err)
			goto out;

		err = -EACCES;
		if ((rt->rt_flags & RTCF_BROADCAST) &&
		    !sock_flag(sk, SOCK_BROADCAST))
			goto out;
		if (connected)
			sk_dst_set(sk, dst_clone(&rt->u.dst));
	}

	if (msg->msg_flags&MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	saddr = rt->rt_src;
	if (!ipc.addr)
		daddr = ipc.addr = rt->rt_dst;

	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);

		NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "udp cork app bug 2\n"));
		err = -EINVAL;
		goto out;
	}
	/*
	 *	Now cork the socket to pend data.
	 */
	inet->cork.fl.fl4_dst = daddr;
	inet->cork.fl.fl_ip_dport = dport;
	inet->cork.fl.fl4_src = saddr;
	inet->cork.fl.fl_ip_sport = inet->sport;
	up->pending = AF_INET;

do_append_data:
	up->len += ulen;
	err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, ulen, 
			sizeof(struct udphdr), &ipc, rt, 
			corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
	if (err)
		udp_flush_pending_frames(sk);
	else if (!corkreq)
		err = udp_push_pending_frames(sk, up);
	release_sock(sk);

out:
	ip_rt_put(rt);
	if (free)
		kfree(ipc.opt);
	if (!err) {
		UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS);
		return len;
	}
	return err;

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

static int udp_sendpage(struct sock *sk, struct page *page, int offset,
			size_t size, int flags)
{
	struct udp_sock *up = udp_sk(sk);
	int ret;

	if (!up->pending) {
		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };

		/* Call udp_sendmsg to specify destination address which
		 * sendpage interface can't pass.
		 * This will succeed only when the socket is connected.
		 */
		ret = udp_sendmsg(NULL, sk, &msg, 0);
		if (ret < 0)
			return ret;
	}

	lock_sock(sk);

	if (unlikely(!up->pending)) {
		release_sock(sk);

		NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "udp cork app bug 3\n"));
		return -EINVAL;
	}

	ret = ip_append_page(sk, page, offset, size, flags);
	if (ret == -EOPNOTSUPP) {
		release_sock(sk);
		return sock_no_sendpage(sk->sk_socket, page, offset,
					size, flags);
	}
	if (ret < 0) {
		udp_flush_pending_frames(sk);
		goto out;
	}

	up->len += size;
	if (!(up->corkflag || (flags&MSG_MORE)))
		ret = udp_push_pending_frames(sk, up);
	if (!ret)
		ret = size;
out:
	release_sock(sk);
	return ret;
}

/*
 *	IOCTL requests applicable to the UDP protocol
 */
 
int udp_ioctl(struct sock *sk, int cmd, unsigned long arg)
{
	switch(cmd) 
	{
		case SIOCOUTQ:
		{
			int amount = atomic_read(&sk->sk_wmem_alloc);
			return put_user(amount, (int __user *)arg);
		}

		case SIOCINQ:
		{
			struct sk_buff *skb;
			unsigned long amount;

			amount = 0;
			spin_lock_irq(&sk->sk_receive_queue.lock);
			skb = skb_peek(&sk->sk_receive_queue);
			if (skb != NULL) {
				/*
				 * We will only return the amount
				 * of this packet since that is all
				 * that will be read.
				 */
				amount = skb->len - sizeof(struct udphdr);
			}
			spin_unlock_irq(&sk->sk_receive_queue.lock);
			return put_user(amount, (int __user *)arg);
		}

		default:
			return -ENOIOCTLCMD;
	}
	return(0);
}

static __inline__ int __udp_checksum_complete(struct sk_buff *skb)
{
	return (unsigned short)csum_fold(skb_checksum(skb, 0, skb->len, skb->csum));
}

static __inline__ int udp_checksum_complete(struct sk_buff *skb)
{
	return skb->ip_summed != CHECKSUM_UNNECESSARY &&
		__udp_checksum_complete(skb);
}

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

static int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		       size_t len, int noblock, int flags, int *addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
  	struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
  	struct sk_buff *skb;
  	int copied, err;

	/*
	 *	Check any passed addresses
	 */
	if (addr_len)
		*addr_len=sizeof(*sin);

	if (flags & MSG_ERRQUEUE)
		return ip_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) {
		if (__udp_checksum_complete(skb))
			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 (sin)
	{
		sin->sin_family = AF_INET;
		sin->sin_port = skb->h.uh->source;
		sin->sin_addr.s_addr = skb->nh.iph->saddr;
		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
  	}
	if (inet->cmsg_flags)
		ip_cmsg_recv(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:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS);

	/* Clear queue. */
	if (flags&MSG_PEEK) {
		int clear = 0;
		spin_lock_irq(&sk->sk_receive_queue.lock);
		if (skb == skb_peek(&sk->sk_receive_queue)) {
			__skb_unlink(skb, &sk->sk_receive_queue);
			clear = 1;
		}
		spin_unlock_irq(&sk->sk_receive_queue.lock);
		if (clear)
			kfree_skb(skb);
	}

	skb_free_datagram(sk, skb);

	if (noblock)
		return -EAGAIN;	
	goto try_again;
}


int udp_disconnect(struct sock *sk, int flags)
{
	struct inet_sock *inet = inet_sk(sk);
	/*
	 *	1003.1g - break association.
	 */
	 
	sk->sk_state = TCP_CLOSE;
	inet->daddr = 0;
	inet->dport = 0;
	sk->sk_bound_dev_if = 0;
	if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
		inet_reset_saddr(sk);

	if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) {
		sk->sk_prot->unhash(sk);
		inet->sport = 0;
	}
	sk_dst_reset(sk);
	return 0;
}

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

/* return:
 * 	1  if the the UDP system should process it
 *	0  if we should drop this packet
 * 	-1 if it should get processed by xfrm4_rcv_encap
 */
static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
{
#ifndef CONFIG_XFRM
	return 1; 
#else
	struct udp_sock *up = udp_sk(sk);
  	struct udphdr *uh = skb->h.uh;
	struct iphdr *iph;
	int iphlen, len;
  
	__u8 *udpdata = (__u8 *)uh + sizeof(struct udphdr);
	__u32 *udpdata32 = (__u32 *)udpdata;
	__u16 encap_type = up->encap_type;

	/* if we're overly short, let UDP handle it */
	if (udpdata > skb->tail)
		return 1;

	/* if this is not encapsulated socket, then just return now */
	if (!encap_type)
		return 1;

	len = skb->tail - udpdata;

	switch (encap_type) {
	default:
	case UDP_ENCAP_ESPINUDP:
		/* Check if this is a keepalive packet.  If so, eat it. */
		if (len == 1 && udpdata[0] == 0xff) {
			return 0;
		} else if (len > sizeof(struct ip_esp_hdr) && udpdata32[0] != 0 ) {
			/* ESP Packet without Non-ESP header */
			len = sizeof(struct udphdr);
		} else
			/* Must be an IKE packet.. pass it through */
			return 1;
		break;
	case UDP_ENCAP_ESPINUDP_NON_IKE:
		/* Check if this is a keepalive packet.  If so, eat it. */
		if (len == 1 && udpdata[0] == 0xff) {
			return 0;
		} else if (len > 2 * sizeof(u32) + sizeof(struct ip_esp_hdr) &&
			   udpdata32[0] == 0 && udpdata32[1] == 0) {
			
			/* ESP Packet with Non-IKE marker */
			len = sizeof(struct udphdr) + 2 * sizeof(u32);
		} else
			/* Must be an IKE packet.. pass it through */
			return 1;
		break;
	}

	/* At this point we are sure that this is an ESPinUDP packet,
	 * so we need to remove 'len' bytes from the packet (the UDP
	 * header and optional ESP marker bytes) and then modify the
	 * protocol to ESP, and then call into the transform receiver.
	 */
958 959
	if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
		return 0;
L
Linus Torvalds 已提交
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 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 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 1226 1227 1228 1229 1230 1231 1232 1233 1234 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 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 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 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 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 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 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

	/* Now we can update and verify the packet length... */
	iph = skb->nh.iph;
	iphlen = iph->ihl << 2;
	iph->tot_len = htons(ntohs(iph->tot_len) - len);
	if (skb->len < iphlen + len) {
		/* packet is too small!?! */
		return 0;
	}

	/* pull the data buffer up to the ESP header and set the
	 * transport header to point to ESP.  Keep UDP on the stack
	 * for later.
	 */
	skb->h.raw = skb_pull(skb, len);

	/* modify the protocol (it's ESP!) */
	iph->protocol = IPPROTO_ESP;

	/* and let the caller know to send this into the ESP processor... */
	return -1;
#endif
}

/* returns:
 *  -1: error
 *   0: success
 *  >0: "udp encap" protocol resubmission
 *
 * Note that in the success and error cases, the skb is assumed to
 * have either been requeued or freed.
 */
static int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb)
{
	struct udp_sock *up = udp_sk(sk);

	/*
	 *	Charge it to the socket, dropping if the queue is full.
	 */
	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
		kfree_skb(skb);
		return -1;
	}

	if (up->encap_type) {
		/*
		 * This is an encapsulation socket, so let's see if this is
		 * an encapsulated packet.
		 * If it's a keepalive packet, then just eat it.
		 * If it's an encapsulateed packet, then pass it to the
		 * IPsec xfrm input and return the response
		 * appropriately.  Otherwise, just fall through and
		 * pass this up the UDP socket.
		 */
		int ret;

		ret = udp_encap_rcv(sk, skb);
		if (ret == 0) {
			/* Eat the packet .. */
			kfree_skb(skb);
			return 0;
		}
		if (ret < 0) {
			/* process the ESP packet */
			ret = xfrm4_rcv_encap(skb, up->encap_type);
			UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
			return -ret;
		}
		/* FALLTHROUGH -- it's a UDP Packet */
	}

	if (sk->sk_filter && skb->ip_summed != CHECKSUM_UNNECESSARY) {
		if (__udp_checksum_complete(skb)) {
			UDP_INC_STATS_BH(UDP_MIB_INERRORS);
			kfree_skb(skb);
			return -1;
		}
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	if (sock_queue_rcv_skb(sk,skb)<0) {
		UDP_INC_STATS_BH(UDP_MIB_INERRORS);
		kfree_skb(skb);
		return -1;
	}
	UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS);
	return 0;
}

/*
 *	Multicasts and broadcasts go to each listener.
 *
 *	Note: called only from the BH handler context,
 *	so we don't need to lock the hashes.
 */
static int udp_v4_mcast_deliver(struct sk_buff *skb, struct udphdr *uh,
				 u32 saddr, u32 daddr)
{
	struct sock *sk;
	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_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
	if (sk) {
		struct sock *sknext = NULL;

		do {
			struct sk_buff *skb1 = skb;

			sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
						   uh->source, saddr, dif);
			if(sknext)
				skb1 = skb_clone(skb, GFP_ATOMIC);

			if(skb1) {
				int ret = udp_queue_rcv_skb(sk, skb1);
				if (ret > 0)
					/* we should probably re-process instead
					 * of dropping packets here. */
					kfree_skb(skb1);
			}
			sk = sknext;
		} while(sknext);
	} else
		kfree_skb(skb);
	read_unlock(&udp_hash_lock);
	return 0;
}

/* Initialize UDP checksum. If exited with zero value (success),
 * CHECKSUM_UNNECESSARY means, that no more checks are required.
 * Otherwise, csum completion requires chacksumming packet body,
 * including udp header and folding it to skb->csum.
 */
static int udp_checksum_init(struct sk_buff *skb, struct udphdr *uh,
			     unsigned short ulen, u32 saddr, u32 daddr)
{
	if (uh->check == 0) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else if (skb->ip_summed == CHECKSUM_HW) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
		if (!udp_check(uh, ulen, saddr, daddr, skb->csum))
			return 0;
		NETDEBUG(if (net_ratelimit()) printk(KERN_DEBUG "udp v4 hw csum failure.\n"));
		skb->ip_summed = CHECKSUM_NONE;
	}
	if (skb->ip_summed != CHECKSUM_UNNECESSARY)
		skb->csum = csum_tcpudp_nofold(saddr, daddr, ulen, IPPROTO_UDP, 0);
	/* Probably, we should checksum udp header (it should be in cache
	 * in any case) and data in tiny packets (< rx copybreak).
	 */
	return 0;
}

/*
 *	All we need to do is get the socket, and then do a checksum. 
 */
 
int udp_rcv(struct sk_buff *skb)
{
  	struct sock *sk;
  	struct udphdr *uh;
	unsigned short ulen;
	struct rtable *rt = (struct rtable*)skb->dst;
	u32 saddr = skb->nh.iph->saddr;
	u32 daddr = skb->nh.iph->daddr;
	int len = skb->len;

	/*
	 *	Validate the packet and the UDP length.
	 */
	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto no_header;

	uh = skb->h.uh;

	ulen = ntohs(uh->len);

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

	if (pskb_trim(skb, ulen))
		goto short_packet;

	if (udp_checksum_init(skb, uh, ulen, saddr, daddr) < 0)
		goto csum_error;

	if(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST))
		return udp_v4_mcast_deliver(skb, uh, saddr, daddr);

	sk = udp_v4_lookup(saddr, uh->source, daddr, uh->dest, skb->dev->ifindex);

	if (sk != NULL) {
		int ret = udp_queue_rcv_skb(sk, skb);
		sock_put(sk);

		/* a return value > 0 means to resubmit the input, but
		 * it it wants the return to be -protocol, or 0
		 */
		if (ret > 0)
			return -ret;
		return 0;
	}

	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto drop;

	/* No socket. Drop packet silently, if checksum is wrong */
	if (udp_checksum_complete(skb))
		goto csum_error;

	UDP_INC_STATS_BH(UDP_MIB_NOPORTS);
	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);

	/*
	 * Hmm.  We got an UDP packet to a port to which we
	 * don't wanna listen.  Ignore it.
	 */
	kfree_skb(skb);
	return(0);

short_packet:
	NETDEBUG(if (net_ratelimit())
		printk(KERN_DEBUG "UDP: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n",
			NIPQUAD(saddr),
			ntohs(uh->source),
			ulen,
			len,
			NIPQUAD(daddr),
			ntohs(uh->dest)));
no_header:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS);
	kfree_skb(skb);
	return(0);

csum_error:
	/* 
	 * RFC1122: OK.  Discards the bad packet silently (as far as 
	 * the network is concerned, anyway) as per 4.1.3.4 (MUST). 
	 */
	NETDEBUG(if (net_ratelimit())
		 printk(KERN_DEBUG "UDP: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n",
			NIPQUAD(saddr),
			ntohs(uh->source),
			NIPQUAD(daddr),
			ntohs(uh->dest),
			ulen));
drop:
	UDP_INC_STATS_BH(UDP_MIB_INERRORS);
	kfree_skb(skb);
	return(0);
}

static int udp_destroy_sock(struct sock *sk)
{
	lock_sock(sk);
	udp_flush_pending_frames(sk);
	release_sock(sk);
	return 0;
}

/*
 *	Socket option code for UDP
 */
static int udp_setsockopt(struct sock *sk, int level, int optname, 
			  char __user *optval, int optlen)
{
	struct udp_sock *up = udp_sk(sk);
	int val;
	int err = 0;

	if (level != SOL_UDP)
		return ip_setsockopt(sk, level, optname, optval, optlen);

	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_push_pending_frames(sk, up);
			release_sock(sk);
		}
		break;
		
	case UDP_ENCAP:
		switch (val) {
		case 0:
		case UDP_ENCAP_ESPINUDP:
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			up->encap_type = val;
			break;
		default:
			err = -ENOPROTOOPT;
			break;
		}
		break;

	default:
		err = -ENOPROTOOPT;
		break;
	};

	return err;
}

static int udp_getsockopt(struct sock *sk, int level, int optname, 
			  char __user *optval, int __user *optlen)
{
	struct udp_sock *up = udp_sk(sk);
	int val, len;

	if (level != SOL_UDP)
		return ip_getsockopt(sk, level, optname, optval, optlen);

	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;
}

/**
 * 	udp_poll - wait for a UDP event.
 *	@file - file struct
 *	@sock - socket
 *	@wait - poll table
 *
 *	This is same as datagram poll, except for the special case of 
 *	blocking sockets. If application is using a blocking fd
 *	and a packet with checksum error is in the queue;
 *	then it could get return from select indicating data available
 *	but then block when reading it. Add special case code
 *	to work around these arguably broken applications.
 */
unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
	unsigned int mask = datagram_poll(file, sock, wait);
	struct sock *sk = sock->sk;
	
	/* Check for false positives due to checksum errors */
	if ( (mask & POLLRDNORM) &&
	     !(file->f_flags & O_NONBLOCK) &&
	     !(sk->sk_shutdown & RCV_SHUTDOWN)){
		struct sk_buff_head *rcvq = &sk->sk_receive_queue;
		struct sk_buff *skb;

		spin_lock_irq(&rcvq->lock);
		while ((skb = skb_peek(rcvq)) != NULL) {
			if (udp_checksum_complete(skb)) {
				UDP_INC_STATS_BH(UDP_MIB_INERRORS);
				__skb_unlink(skb, rcvq);
				kfree_skb(skb);
			} else {
				skb->ip_summed = CHECKSUM_UNNECESSARY;
				break;
			}
		}
		spin_unlock_irq(&rcvq->lock);

		/* nothing to see, move along */
		if (skb == NULL)
			mask &= ~(POLLIN | POLLRDNORM);
	}

	return mask;
	
}

struct proto udp_prot = {
 	.name =		"UDP",
	.owner =	THIS_MODULE,
	.close =	udp_close,
	.connect =	ip4_datagram_connect,
	.disconnect =	udp_disconnect,
	.ioctl =	udp_ioctl,
	.destroy =	udp_destroy_sock,
	.setsockopt =	udp_setsockopt,
	.getsockopt =	udp_getsockopt,
	.sendmsg =	udp_sendmsg,
	.recvmsg =	udp_recvmsg,
	.sendpage =	udp_sendpage,
	.backlog_rcv =	udp_queue_rcv_skb,
	.hash =		udp_v4_hash,
	.unhash =	udp_v4_unhash,
	.get_port =	udp_v4_get_port,
	.obj_size =	sizeof(struct udp_sock),
};

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

static struct sock *udp_get_first(struct seq_file *seq)
{
	struct sock *sk;
	struct udp_iter_state *state = seq->private;

	for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) {
		struct hlist_node *node;
		sk_for_each(sk, node, &udp_hash[state->bucket]) {
			if (sk->sk_family == state->family)
				goto found;
		}
	}
	sk = NULL;
found:
	return sk;
}

static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
{
	struct udp_iter_state *state = seq->private;

	do {
		sk = sk_next(sk);
try_again:
		;
	} while (sk && sk->sk_family != state->family);

	if (!sk && ++state->bucket < UDP_HTABLE_SIZE) {
		sk = sk_head(&udp_hash[state->bucket]);
		goto try_again;
	}
	return sk;
}

static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos)
{
	struct sock *sk = udp_get_first(seq);

	if (sk)
		while(pos && (sk = udp_get_next(seq, sk)) != NULL)
			--pos;
	return pos ? NULL : sk;
}

static void *udp_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&udp_hash_lock);
	return *pos ? udp_get_idx(seq, *pos-1) : (void *)1;
}

static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct sock *sk;

	if (v == (void *)1)
		sk = udp_get_idx(seq, 0);
	else
		sk = udp_get_next(seq, v);

	++*pos;
	return sk;
}

static void udp_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&udp_hash_lock);
}

static int udp_seq_open(struct inode *inode, struct file *file)
{
	struct udp_seq_afinfo *afinfo = PDE(inode)->data;
	struct seq_file *seq;
	int rc = -ENOMEM;
	struct udp_iter_state *s = kmalloc(sizeof(*s), GFP_KERNEL);

	if (!s)
		goto out;
	memset(s, 0, sizeof(*s));
	s->family		= afinfo->family;
	s->seq_ops.start	= udp_seq_start;
	s->seq_ops.next		= udp_seq_next;
	s->seq_ops.show		= afinfo->seq_show;
	s->seq_ops.stop		= udp_seq_stop;

	rc = seq_open(file, &s->seq_ops);
	if (rc)
		goto out_kfree;

	seq	     = file->private_data;
	seq->private = s;
out:
	return rc;
out_kfree:
	kfree(s);
	goto out;
}

/* ------------------------------------------------------------------------ */
int udp_proc_register(struct udp_seq_afinfo *afinfo)
{
	struct proc_dir_entry *p;
	int rc = 0;

	if (!afinfo)
		return -EINVAL;
	afinfo->seq_fops->owner		= afinfo->owner;
	afinfo->seq_fops->open		= udp_seq_open;
	afinfo->seq_fops->read		= seq_read;
	afinfo->seq_fops->llseek	= seq_lseek;
	afinfo->seq_fops->release	= seq_release_private;

	p = proc_net_fops_create(afinfo->name, S_IRUGO, afinfo->seq_fops);
	if (p)
		p->data = afinfo;
	else
		rc = -ENOMEM;
	return rc;
}

void udp_proc_unregister(struct udp_seq_afinfo *afinfo)
{
	if (!afinfo)
		return;
	proc_net_remove(afinfo->name);
	memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops));
}

/* ------------------------------------------------------------------------ */
static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket)
{
	struct inet_sock *inet = inet_sk(sp);
	unsigned int dest = inet->daddr;
	unsigned int src  = inet->rcv_saddr;
	__u16 destp	  = ntohs(inet->dport);
	__u16 srcp	  = ntohs(inet->sport);

	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p",
		bucket, src, srcp, dest, 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 udp4_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "%-127s\n",
			   "  sl  local_address rem_address   st tx_queue "
			   "rx_queue tr tm->when retrnsmt   uid  timeout "
			   "inode");
	else {
		char tmpbuf[129];
		struct udp_iter_state *state = seq->private;

		udp4_format_sock(v, tmpbuf, state->bucket);
		seq_printf(seq, "%-127s\n", tmpbuf);
	}
	return 0;
}

/* ------------------------------------------------------------------------ */
static struct file_operations udp4_seq_fops;
static struct udp_seq_afinfo udp4_seq_afinfo = {
	.owner		= THIS_MODULE,
	.name		= "udp",
	.family		= AF_INET,
	.seq_show	= udp4_seq_show,
	.seq_fops	= &udp4_seq_fops,
};

int __init udp4_proc_init(void)
{
	return udp_proc_register(&udp4_seq_afinfo);
}

void udp4_proc_exit(void)
{
	udp_proc_unregister(&udp4_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */

EXPORT_SYMBOL(udp_disconnect);
EXPORT_SYMBOL(udp_hash);
EXPORT_SYMBOL(udp_hash_lock);
EXPORT_SYMBOL(udp_ioctl);
EXPORT_SYMBOL(udp_port_rover);
EXPORT_SYMBOL(udp_prot);
EXPORT_SYMBOL(udp_sendmsg);
EXPORT_SYMBOL(udp_poll);

#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(udp_proc_register);
EXPORT_SYMBOL(udp_proc_unregister);
#endif