af_inet.c 35.2 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9
/*
 * 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.
 *
 *		PF_INET protocol family socket handler.
 *
 * Version:	$Id: af_inet.c,v 1.137 2002/02/01 22:01:03 davem Exp $
 *
10
 * Authors:	Ross Biro
L
Linus Torvalds 已提交
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
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Changes (see also sock.c)
 *
 *		piggy,
 *		Karl Knutson	:	Socket protocol table
 *		A.N.Kuznetsov	:	Socket death error in accept().
 *		John Richardson :	Fix non blocking error in connect()
 *					so sockets that fail to connect
 *					don't return -EINPROGRESS.
 *		Alan Cox	:	Asynchronous I/O support
 *		Alan Cox	:	Keep correct socket pointer on sock
 *					structures
 *					when accept() ed
 *		Alan Cox	:	Semantics of SO_LINGER aren't state
 *					moved to close when you look carefully.
 *					With this fixed and the accept bug fixed
 *					some RPC stuff seems happier.
 *		Niibe Yutaka	:	4.4BSD style write async I/O
 *		Alan Cox,
 *		Tony Gale 	:	Fixed reuse semantics.
 *		Alan Cox	:	bind() shouldn't abort existing but dead
 *					sockets. Stops FTP netin:.. I hope.
 *		Alan Cox	:	bind() works correctly for RAW sockets.
 *					Note that FreeBSD at least was broken
 *					in this respect so be careful with
 *					compatibility tests...
 *		Alan Cox	:	routing cache support
 *		Alan Cox	:	memzero the socket structure for
 *					compactness.
 *		Matt Day	:	nonblock connect error handler
 *		Alan Cox	:	Allow large numbers of pending sockets
 *					(eg for big web sites), but only if
 *					specifically application requested.
 *		Alan Cox	:	New buffering throughout IP. Used
 *					dumbly.
 *		Alan Cox	:	New buffering now used smartly.
 *		Alan Cox	:	BSD rather than common sense
 *					interpretation of listen.
 *		Germano Caronni	:	Assorted small races.
 *		Alan Cox	:	sendmsg/recvmsg basic support.
 *		Alan Cox	:	Only sendmsg/recvmsg now supported.
 *		Alan Cox	:	Locked down bind (see security list).
 *		Alan Cox	:	Loosened bind a little.
 *		Mike McLagan	:	ADD/DEL DLCI Ioctls
 *	Willy Konynenberg	:	Transparent proxying support.
 *		David S. Miller	:	New socket lookup architecture.
 *					Some other random speedups.
 *		Cyrus Durgin	:	Cleaned up file for kmod hacks.
 *		Andi Kleen	:	Fix inet_stream_connect TCP race.
 *
 *		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.
 */

H
Herbert Xu 已提交
70
#include <linux/err.h>
L
Linus Torvalds 已提交
71 72 73 74 75 76 77 78 79 80 81
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
82
#include <linux/capability.h>
L
Linus Torvalds 已提交
83 84 85 86 87 88 89
#include <linux/fcntl.h>
#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/stat.h>
#include <linux/init.h>
#include <linux/poll.h>
#include <linux/netfilter_ipv4.h>
90
#include <linux/random.h>
L
Linus Torvalds 已提交
91 92 93 94 95 96

#include <asm/uaccess.h>
#include <asm/system.h>

#include <linux/inet.h>
#include <linux/igmp.h>
97
#include <linux/inetdevice.h>
L
Linus Torvalds 已提交
98 99 100 101 102 103
#include <linux/netdevice.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/arp.h>
#include <net/route.h>
#include <net/ip_fib.h>
104
#include <net/inet_connection_sock.h>
L
Linus Torvalds 已提交
105 106
#include <net/tcp.h>
#include <net/udp.h>
107
#include <net/udplite.h>
L
Linus Torvalds 已提交
108 109 110 111 112 113 114 115 116 117 118
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <net/icmp.h>
#include <net/ipip.h>
#include <net/inet_common.h>
#include <net/xfrm.h>
#ifdef CONFIG_IP_MROUTE
#include <linux/mroute.h>
#endif

119
DEFINE_SNMP_STAT(struct linux_mib, net_statistics) __read_mostly;
L
Linus Torvalds 已提交
120 121 122 123 124 125 126 127 128

extern void ip_mc_drop_socket(struct sock *sk);

/* The inetsw table contains everything that inet_create needs to
 * build a new socket.
 */
static struct list_head inetsw[SOCK_MAX];
static DEFINE_SPINLOCK(inetsw_lock);

129 130 131 132
struct ipv4_config ipv4_config;

EXPORT_SYMBOL(ipv4_config);

L
Linus Torvalds 已提交
133 134 135 136 137 138 139 140 141
/* New destruction routine */

void inet_sock_destruct(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);

	__skb_queue_purge(&sk->sk_receive_queue);
	__skb_queue_purge(&sk->sk_error_queue);

H
Hideo Aoki 已提交
142 143
	sk_mem_reclaim(sk);

L
Linus Torvalds 已提交
144 145 146 147 148 149 150 151 152 153 154 155 156 157 158
	if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
		printk("Attempt to release TCP socket in state %d %p\n",
		       sk->sk_state, sk);
		return;
	}
	if (!sock_flag(sk, SOCK_DEAD)) {
		printk("Attempt to release alive inet socket %p\n", sk);
		return;
	}

	BUG_TRAP(!atomic_read(&sk->sk_rmem_alloc));
	BUG_TRAP(!atomic_read(&sk->sk_wmem_alloc));
	BUG_TRAP(!sk->sk_wmem_queued);
	BUG_TRAP(!sk->sk_forward_alloc);

J
Jesper Juhl 已提交
159
	kfree(inet->opt);
L
Linus Torvalds 已提交
160
	dst_release(sk->sk_dst_cache);
161
	sk_refcnt_debug_dec(sk);
L
Linus Torvalds 已提交
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
}

/*
 *	The routines beyond this point handle the behaviour of an AF_INET
 *	socket object. Mostly it punts to the subprotocols of IP to do
 *	the work.
 */

/*
 *	Automatically bind an unbound socket.
 */

static int inet_autobind(struct sock *sk)
{
	struct inet_sock *inet;
	/* We may need to bind the socket. */
	lock_sock(sk);
	inet = inet_sk(sk);
	if (!inet->num) {
		if (sk->sk_prot->get_port(sk, 0)) {
			release_sock(sk);
			return -EAGAIN;
		}
		inet->sport = htons(inet->num);
	}
	release_sock(sk);
	return 0;
}

/*
 *	Move a socket into listening state.
 */
int inet_listen(struct socket *sock, int backlog)
{
	struct sock *sk = sock->sk;
	unsigned char old_state;
	int err;

	lock_sock(sk);

	err = -EINVAL;
	if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM)
		goto out;

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

	/* Really, if the socket is already in listen state
	 * we can only allow the backlog to be adjusted.
	 */
	if (old_state != TCP_LISTEN) {
214
		err = inet_csk_listen_start(sk, backlog);
L
Linus Torvalds 已提交
215 216 217 218 219 220 221 222 223 224 225
		if (err)
			goto out;
	}
	sk->sk_max_ack_backlog = backlog;
	err = 0;

out:
	release_sock(sk);
	return err;
}

226
u32 inet_ehash_secret __read_mostly;
227 228
EXPORT_SYMBOL(inet_ehash_secret);

229 230 231 232
/*
 * inet_ehash_secret must be set exactly once
 * Instead of using a dedicated spinlock, we (ab)use inetsw_lock
 */
233 234
void build_ehash_secret(void)
{
235 236 237 238 239 240 241 242
	u32 rnd;
	do {
		get_random_bytes(&rnd, sizeof(rnd));
	} while (rnd == 0);
	spin_lock_bh(&inetsw_lock);
	if (!inet_ehash_secret)
		inet_ehash_secret = rnd;
	spin_unlock_bh(&inetsw_lock);
243 244 245
}
EXPORT_SYMBOL(build_ehash_secret);

L
Linus Torvalds 已提交
246 247 248 249
/*
 *	Create an inet socket.
 */

250
static int inet_create(struct net *net, struct socket *sock, int protocol)
L
Linus Torvalds 已提交
251 252 253 254 255 256 257 258
{
	struct sock *sk;
	struct list_head *p;
	struct inet_protosw *answer;
	struct inet_sock *inet;
	struct proto *answer_prot;
	unsigned char answer_flags;
	char answer_no_check;
259
	int try_loading_module = 0;
260
	int err;
L
Linus Torvalds 已提交
261

262 263 264
	if (net != &init_net)
		return -EAFNOSUPPORT;

265 266 267 268 269
	if (sock->type != SOCK_RAW &&
	    sock->type != SOCK_DGRAM &&
	    !inet_ehash_secret)
		build_ehash_secret();

L
Linus Torvalds 已提交
270 271 272 273
	sock->state = SS_UNCONNECTED;

	/* Look for the requested type/protocol pair. */
	answer = NULL;
274
lookup_protocol:
275
	err = -ESOCKTNOSUPPORT;
L
Linus Torvalds 已提交
276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292
	rcu_read_lock();
	list_for_each_rcu(p, &inetsw[sock->type]) {
		answer = list_entry(p, struct inet_protosw, list);

		/* Check the non-wild match. */
		if (protocol == answer->protocol) {
			if (protocol != IPPROTO_IP)
				break;
		} else {
			/* Check for the two wild cases. */
			if (IPPROTO_IP == protocol) {
				protocol = answer->protocol;
				break;
			}
			if (IPPROTO_IP == answer->protocol)
				break;
		}
293
		err = -EPROTONOSUPPORT;
L
Linus Torvalds 已提交
294 295 296
		answer = NULL;
	}

297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318
	if (unlikely(answer == NULL)) {
		if (try_loading_module < 2) {
			rcu_read_unlock();
			/*
			 * Be more specific, e.g. net-pf-2-proto-132-type-1
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP-type-SOCK_STREAM)
			 */
			if (++try_loading_module == 1)
				request_module("net-pf-%d-proto-%d-type-%d",
					       PF_INET, protocol, sock->type);
			/*
			 * Fall back to generic, e.g. net-pf-2-proto-132
			 * (net-pf-PF_INET-proto-IPPROTO_SCTP)
			 */
			else
				request_module("net-pf-%d-proto-%d",
					       PF_INET, protocol);
			goto lookup_protocol;
		} else
			goto out_rcu_unlock;
	}

L
Linus Torvalds 已提交
319 320 321 322 323 324 325 326 327 328 329 330 331
	err = -EPERM;
	if (answer->capability > 0 && !capable(answer->capability))
		goto out_rcu_unlock;

	sock->ops = answer->ops;
	answer_prot = answer->prot;
	answer_no_check = answer->no_check;
	answer_flags = answer->flags;
	rcu_read_unlock();

	BUG_TRAP(answer_prot->slab != NULL);

	err = -ENOBUFS;
332
	sk = sk_alloc(net, PF_INET, GFP_KERNEL, answer_prot);
L
Linus Torvalds 已提交
333 334 335 336 337 338 339 340 341
	if (sk == NULL)
		goto out;

	err = 0;
	sk->sk_no_check = answer_no_check;
	if (INET_PROTOSW_REUSE & answer_flags)
		sk->sk_reuse = 1;

	inet = inet_sk(sk);
342
	inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0;
L
Linus Torvalds 已提交
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 (SOCK_RAW == sock->type) {
		inet->num = protocol;
		if (IPPROTO_RAW == protocol)
			inet->hdrincl = 1;
	}

	if (ipv4_config.no_pmtu_disc)
		inet->pmtudisc = IP_PMTUDISC_DONT;
	else
		inet->pmtudisc = IP_PMTUDISC_WANT;

	inet->id = 0;

	sock_init_data(sock, sk);

	sk->sk_destruct	   = inet_sock_destruct;
	sk->sk_family	   = PF_INET;
	sk->sk_protocol	   = protocol;
	sk->sk_backlog_rcv = sk->sk_prot->backlog_rcv;

	inet->uc_ttl	= -1;
	inet->mc_loop	= 1;
	inet->mc_ttl	= 1;
	inet->mc_index	= 0;
	inet->mc_list	= NULL;

370
	sk_refcnt_debug_inc(sk);
L
Linus Torvalds 已提交
371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428

	if (inet->num) {
		/* It assumes that any protocol which allows
		 * the user to assign a number at socket
		 * creation time automatically
		 * shares.
		 */
		inet->sport = htons(inet->num);
		/* Add to protocol hash chains. */
		sk->sk_prot->hash(sk);
	}

	if (sk->sk_prot->init) {
		err = sk->sk_prot->init(sk);
		if (err)
			sk_common_release(sk);
	}
out:
	return err;
out_rcu_unlock:
	rcu_read_unlock();
	goto out;
}


/*
 *	The peer socket should always be NULL (or else). When we call this
 *	function we are destroying the object and from then on nobody
 *	should refer to it.
 */
int inet_release(struct socket *sock)
{
	struct sock *sk = sock->sk;

	if (sk) {
		long timeout;

		/* Applications forget to leave groups before exiting */
		ip_mc_drop_socket(sk);

		/* If linger is set, we don't return until the close
		 * is complete.  Otherwise we return immediately. The
		 * actually closing is done the same either way.
		 *
		 * If the close is due to the process exiting, we never
		 * linger..
		 */
		timeout = 0;
		if (sock_flag(sk, SOCK_LINGER) &&
		    !(current->flags & PF_EXITING))
			timeout = sk->sk_lingertime;
		sock->sk = NULL;
		sk->sk_prot->close(sk, timeout);
	}
	return 0;
}

/* It is off by default, see below. */
429
int sysctl_ip_nonlocal_bind __read_mostly;
L
Linus Torvalds 已提交
430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448

int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
{
	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
	struct sock *sk = sock->sk;
	struct inet_sock *inet = inet_sk(sk);
	unsigned short snum;
	int chk_addr_ret;
	int err;

	/* If the socket has its own bind function then use it. (RAW) */
	if (sk->sk_prot->bind) {
		err = sk->sk_prot->bind(sk, uaddr, addr_len);
		goto out;
	}
	err = -EINVAL;
	if (addr_len < sizeof(struct sockaddr_in))
		goto out;

449
	chk_addr_ret = inet_addr_type(&init_net, addr->sin_addr.s_addr);
L
Linus Torvalds 已提交
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

	/* Not specified by any standard per-se, however it breaks too
	 * many applications when removed.  It is unfortunate since
	 * allowing applications to make a non-local bind solves
	 * several problems with systems using dynamic addressing.
	 * (ie. your servers still start up even if your ISDN link
	 *  is temporarily down)
	 */
	err = -EADDRNOTAVAIL;
	if (!sysctl_ip_nonlocal_bind &&
	    !inet->freebind &&
	    addr->sin_addr.s_addr != INADDR_ANY &&
	    chk_addr_ret != RTN_LOCAL &&
	    chk_addr_ret != RTN_MULTICAST &&
	    chk_addr_ret != RTN_BROADCAST)
		goto out;

	snum = ntohs(addr->sin_port);
	err = -EACCES;
	if (snum && snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
		goto out;

	/*      We keep a pair of addresses. rcv_saddr is the one
	 *      used by hash lookups, and saddr is used for transmit.
	 *
	 *      In the BSD API these are the same except where it
	 *      would be illegal to use them (multicast/broadcast) in
	 *      which case the sending device address is used.
	 */
	lock_sock(sk);

	/* Check these errors (active socket, double bind). */
	err = -EINVAL;
	if (sk->sk_state != TCP_CLOSE || inet->num)
		goto out_release_sock;

	inet->rcv_saddr = inet->saddr = addr->sin_addr.s_addr;
	if (chk_addr_ret == RTN_MULTICAST || chk_addr_ret == RTN_BROADCAST)
		inet->saddr = 0;  /* Use device */

	/* Make sure we are allowed to bind here. */
	if (sk->sk_prot->get_port(sk, snum)) {
		inet->saddr = inet->rcv_saddr = 0;
		err = -EADDRINUSE;
		goto out_release_sock;
	}

	if (inet->rcv_saddr)
		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
	if (snum)
		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
	inet->sport = htons(inet->num);
	inet->daddr = 0;
	inet->dport = 0;
	sk_dst_reset(sk);
	err = 0;
out_release_sock:
	release_sock(sk);
out:
	return err;
}

int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
		       int addr_len, int flags)
{
	struct sock *sk = sock->sk;

	if (uaddr->sa_family == AF_UNSPEC)
		return sk->sk_prot->disconnect(sk, flags);

	if (!inet_sk(sk)->num && inet_autobind(sk))
		return -EAGAIN;
	return sk->sk_prot->connect(sk, (struct sockaddr *)uaddr, addr_len);
}

static long inet_wait_for_connect(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);

	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

	/* Basic assumption: if someone sets sk->sk_err, he _must_
	 * change state of the socket from TCP_SYN_*.
	 * Connect() does not allow to get error notifications
	 * without closing the socket.
	 */
	while ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		if (signal_pending(current) || !timeo)
			break;
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
	}
	finish_wait(sk->sk_sleep, &wait);
	return timeo;
}

/*
 *	Connect to a remote host. There is regrettably still a little
 *	TCP 'magic' in here.
 */
int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
			int addr_len, int flags)
{
	struct sock *sk = sock->sk;
	int err;
	long timeo;

	lock_sock(sk);

	if (uaddr->sa_family == AF_UNSPEC) {
		err = sk->sk_prot->disconnect(sk, flags);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		goto out;
	}

	switch (sock->state) {
	default:
		err = -EINVAL;
		goto out;
	case SS_CONNECTED:
		err = -EISCONN;
		goto out;
	case SS_CONNECTING:
		err = -EALREADY;
		/* Fall out of switch with err, set for this state */
		break;
	case SS_UNCONNECTED:
		err = -EISCONN;
		if (sk->sk_state != TCP_CLOSE)
			goto out;

		err = sk->sk_prot->connect(sk, uaddr, addr_len);
		if (err < 0)
			goto out;

587
		sock->state = SS_CONNECTING;
L
Linus Torvalds 已提交
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

		/* Just entered SS_CONNECTING state; the only
		 * difference is that return value in non-blocking
		 * case is EINPROGRESS, rather than EALREADY.
		 */
		err = -EINPROGRESS;
		break;
	}

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);

	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		/* Error code is set above */
		if (!timeo || !inet_wait_for_connect(sk, timeo))
			goto out;

		err = sock_intr_errno(timeo);
		if (signal_pending(current))
			goto out;
	}

	/* Connection was closed by RST, timeout, ICMP error
	 * or another process disconnected us.
	 */
	if (sk->sk_state == TCP_CLOSE)
		goto sock_error;

	/* sk->sk_err may be not zero now, if RECVERR was ordered by user
	 * and error was received after socket entered established state.
	 * Hence, it is handled normally after connect() return successfully.
	 */

	sock->state = SS_CONNECTED;
	err = 0;
out:
	release_sock(sk);
	return err;

sock_error:
	err = sock_error(sk) ? : -ECONNABORTED;
	sock->state = SS_UNCONNECTED;
	if (sk->sk_prot->disconnect(sk, flags))
		sock->state = SS_DISCONNECTING;
	goto out;
}

/*
 *	Accept a pending connection. The TCP layer now gives BSD semantics.
 */

int inet_accept(struct socket *sock, struct socket *newsock, int flags)
{
	struct sock *sk1 = sock->sk;
	int err = -EINVAL;
	struct sock *sk2 = sk1->sk_prot->accept(sk1, flags, &err);

	if (!sk2)
		goto do_err;

	lock_sock(sk2);

	BUG_TRAP((1 << sk2->sk_state) &
		 (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT | TCPF_CLOSE));

	sock_graft(sk2, newsock);

	newsock->state = SS_CONNECTED;
	err = 0;
	release_sock(sk2);
do_err:
	return err;
}


/*
 *	This does both peername and sockname.
 */
int inet_getname(struct socket *sock, struct sockaddr *uaddr,
			int *uaddr_len, int peer)
{
	struct sock *sk		= sock->sk;
	struct inet_sock *inet	= inet_sk(sk);
	struct sockaddr_in *sin	= (struct sockaddr_in *)uaddr;

	sin->sin_family = AF_INET;
	if (peer) {
		if (!inet->dport ||
		    (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) &&
		     peer == 1))
			return -ENOTCONN;
		sin->sin_port = inet->dport;
		sin->sin_addr.s_addr = inet->daddr;
	} else {
681
		__be32 addr = inet->rcv_saddr;
L
Linus Torvalds 已提交
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
		if (!addr)
			addr = inet->saddr;
		sin->sin_port = inet->sport;
		sin->sin_addr.s_addr = addr;
	}
	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
	*uaddr_len = sizeof(*sin);
	return 0;
}

int inet_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
		 size_t size)
{
	struct sock *sk = sock->sk;

	/* We may need to bind the socket. */
	if (!inet_sk(sk)->num && inet_autobind(sk))
		return -EAGAIN;

	return sk->sk_prot->sendmsg(iocb, sk, msg, size);
}


static ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
	struct sock *sk = sock->sk;

	/* We may need to bind the socket. */
	if (!inet_sk(sk)->num && inet_autobind(sk))
		return -EAGAIN;

	if (sk->sk_prot->sendpage)
		return sk->sk_prot->sendpage(sk, page, offset, size, flags);
	return sock_no_sendpage(sock, page, offset, size, flags);
}


int inet_shutdown(struct socket *sock, int how)
{
	struct sock *sk = sock->sk;
	int err = 0;

	/* This should really check to make sure
	 * the socket is a TCP socket. (WHY AC...)
	 */
	how++; /* maps 0->1 has the advantage of making bit 1 rcvs and
		       1->2 bit 2 snds.
		       2->3 */
	if ((how & ~SHUTDOWN_MASK) || !how)	/* MAXINT->0 */
		return -EINVAL;

	lock_sock(sk);
	if (sock->state == SS_CONNECTING) {
		if ((1 << sk->sk_state) &
		    (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_CLOSE))
			sock->state = SS_DISCONNECTING;
		else
			sock->state = SS_CONNECTED;
	}

	switch (sk->sk_state) {
	case TCP_CLOSE:
		err = -ENOTCONN;
		/* Hack to wake up other listeners, who can poll for
		   POLLHUP, even on eg. unconnected UDP sockets -- RR */
	default:
		sk->sk_shutdown |= how;
		if (sk->sk_prot->shutdown)
			sk->sk_prot->shutdown(sk, how);
		break;

	/* Remaining two branches are temporary solution for missing
	 * close() in multithreaded environment. It is _not_ a good idea,
	 * but we have no choice until close() is repaired at VFS level.
	 */
	case TCP_LISTEN:
		if (!(how & RCV_SHUTDOWN))
			break;
		/* Fall through */
	case TCP_SYN_SENT:
		err = sk->sk_prot->disconnect(sk, O_NONBLOCK);
		sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
		break;
	}

	/* Wake up anyone sleeping in poll. */
	sk->sk_state_change(sk);
	release_sock(sk);
	return err;
}

/*
 *	ioctl() calls you can issue on an INET socket. Most of these are
 *	device configuration and stuff and very rarely used. Some ioctls
 *	pass on to the socket itself.
 *
 *	NOTE: I like the idea of a module for the config stuff. ie ifconfig
 *	loads the devconfigure module does its configuring and unloads it.
 *	There's a good 20K of config code hanging around the kernel.
 */

int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	struct sock *sk = sock->sk;
	int err = 0;
787
	struct net *net = sk->sk_net;
L
Linus Torvalds 已提交
788 789 790 791 792

	switch (cmd) {
		case SIOCGSTAMP:
			err = sock_get_timestamp(sk, (struct timeval __user *)arg);
			break;
793 794 795
		case SIOCGSTAMPNS:
			err = sock_get_timestampns(sk, (struct timespec __user *)arg);
			break;
L
Linus Torvalds 已提交
796 797 798
		case SIOCADDRT:
		case SIOCDELRT:
		case SIOCRTMSG:
799
			err = ip_rt_ioctl(net, cmd, (void __user *)arg);
L
Linus Torvalds 已提交
800 801 802 803
			break;
		case SIOCDARP:
		case SIOCGARP:
		case SIOCSARP:
804
			err = arp_ioctl(net, cmd, (void __user *)arg);
L
Linus Torvalds 已提交
805 806 807 808 809 810 811 812 813 814 815 816
			break;
		case SIOCGIFADDR:
		case SIOCSIFADDR:
		case SIOCGIFBRDADDR:
		case SIOCSIFBRDADDR:
		case SIOCGIFNETMASK:
		case SIOCSIFNETMASK:
		case SIOCGIFDSTADDR:
		case SIOCSIFDSTADDR:
		case SIOCSIFPFLAGS:
		case SIOCGIFPFLAGS:
		case SIOCSIFFLAGS:
817
			err = devinet_ioctl(net, cmd, (void __user *)arg);
L
Linus Torvalds 已提交
818 819
			break;
		default:
820 821 822 823
			if (sk->sk_prot->ioctl)
				err = sk->sk_prot->ioctl(sk, cmd, arg);
			else
				err = -ENOIOCTLCMD;
L
Linus Torvalds 已提交
824 825 826 827 828
			break;
	}
	return err;
}

829
const struct proto_ops inet_stream_ops = {
830 831 832 833 834 835 836 837 838 839 840 841 842 843
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_stream_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = inet_accept,
	.getname	   = inet_getname,
	.poll		   = tcp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = inet_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
844
	.sendmsg	   = tcp_sendmsg,
845 846 847
	.recvmsg	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = tcp_sendpage,
J
Jens Axboe 已提交
848
	.splice_read	   = tcp_splice_read,
849
#ifdef CONFIG_COMPAT
850 851
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
852
#endif
L
Linus Torvalds 已提交
853 854
};

855
const struct proto_ops inet_dgram_ops = {
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = udp_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
874
#ifdef CONFIG_COMPAT
875 876
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
877
#endif
L
Linus Torvalds 已提交
878 879 880 881 882 883
};

/*
 * For SOCK_RAW sockets; should be the same as inet_dgram_ops but without
 * udp_poll
 */
884
static const struct proto_ops inet_sockraw_ops = {
885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902
	.family		   = PF_INET,
	.owner		   = THIS_MODULE,
	.release	   = inet_release,
	.bind		   = inet_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = inet_getname,
	.poll		   = datagram_poll,
	.ioctl		   = inet_ioctl,
	.listen		   = sock_no_listen,
	.shutdown	   = inet_shutdown,
	.setsockopt	   = sock_common_setsockopt,
	.getsockopt	   = sock_common_getsockopt,
	.sendmsg	   = inet_sendmsg,
	.recvmsg	   = sock_common_recvmsg,
	.mmap		   = sock_no_mmap,
	.sendpage	   = inet_sendpage,
903
#ifdef CONFIG_COMPAT
904 905
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
906
#endif
L
Linus Torvalds 已提交
907 908 909 910 911 912 913 914 915 916 917 918 919
};

static struct net_proto_family inet_family_ops = {
	.family = PF_INET,
	.create = inet_create,
	.owner	= THIS_MODULE,
};

/* Upon startup we insert all the elements in inetsw_array[] into
 * the linked list inetsw.
 */
static struct inet_protosw inetsw_array[] =
{
920 921 922 923 924 925 926 927
	{
		.type =       SOCK_STREAM,
		.protocol =   IPPROTO_TCP,
		.prot =       &tcp_prot,
		.ops =        &inet_stream_ops,
		.capability = -1,
		.no_check =   0,
		.flags =      INET_PROTOSW_PERMANENT |
928
			      INET_PROTOSW_ICSK,
929 930 931 932 933 934 935 936 937 938
	},

	{
		.type =       SOCK_DGRAM,
		.protocol =   IPPROTO_UDP,
		.prot =       &udp_prot,
		.ops =        &inet_dgram_ops,
		.capability = -1,
		.no_check =   UDP_CSUM_DEFAULT,
		.flags =      INET_PROTOSW_PERMANENT,
L
Linus Torvalds 已提交
939
       },
940

L
Linus Torvalds 已提交
941 942

       {
943 944 945 946 947 948 949
	       .type =       SOCK_RAW,
	       .protocol =   IPPROTO_IP,	/* wild card */
	       .prot =       &raw_prot,
	       .ops =        &inet_sockraw_ops,
	       .capability = CAP_NET_RAW,
	       .no_check =   UDP_CSUM_DEFAULT,
	       .flags =      INET_PROTOSW_REUSE,
L
Linus Torvalds 已提交
950 951 952
       }
};

953
#define INETSW_ARRAY_LEN ARRAY_SIZE(inetsw_array)
L
Linus Torvalds 已提交
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

void inet_register_protosw(struct inet_protosw *p)
{
	struct list_head *lh;
	struct inet_protosw *answer;
	int protocol = p->protocol;
	struct list_head *last_perm;

	spin_lock_bh(&inetsw_lock);

	if (p->type >= SOCK_MAX)
		goto out_illegal;

	/* If we are trying to override a permanent protocol, bail. */
	answer = NULL;
	last_perm = &inetsw[p->type];
	list_for_each(lh, &inetsw[p->type]) {
		answer = list_entry(lh, struct inet_protosw, list);

		/* Check only the non-wild match. */
		if (INET_PROTOSW_PERMANENT & answer->flags) {
			if (protocol == answer->protocol)
				break;
			last_perm = lh;
		}

		answer = NULL;
	}
	if (answer)
		goto out_permanent;

	/* Add the new entry after the last permanent entry if any, so that
	 * the new entry does not override a permanent entry when matched with
	 * a wild-card protocol. But it is allowed to override any existing
988
	 * non-permanent entry.  This means that when we remove this entry, the
L
Linus Torvalds 已提交
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
	 * system automatically returns to the old behavior.
	 */
	list_add_rcu(&p->list, last_perm);
out:
	spin_unlock_bh(&inetsw_lock);

	synchronize_net();

	return;

out_permanent:
	printk(KERN_ERR "Attempt to override permanent protocol %d.\n",
	       protocol);
	goto out;

out_illegal:
	printk(KERN_ERR
	       "Ignoring attempt to register invalid socket type %d.\n",
	       p->type);
	goto out;
}

void inet_unregister_protosw(struct inet_protosw *p)
{
	if (INET_PROTOSW_PERMANENT & p->flags) {
		printk(KERN_ERR
		       "Attempt to unregister permanent protocol %d.\n",
		       p->protocol);
	} else {
		spin_lock_bh(&inetsw_lock);
		list_del_rcu(&p->list);
		spin_unlock_bh(&inetsw_lock);

		synchronize_net();
	}
}

1026 1027 1028 1029
/*
 *      Shall we try to damage output packets if routing dev changes?
 */

1030
int sysctl_ip_dynaddr __read_mostly;
1031 1032 1033 1034 1035 1036

static int inet_sk_reselect_saddr(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	int err;
	struct rtable *rt;
1037 1038
	__be32 old_saddr = inet->saddr;
	__be32 new_saddr;
1039
	__be32 daddr = inet->daddr;
1040 1041 1042 1043 1044 1045 1046 1047 1048

	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;

	/* Query new route. */
	err = ip_route_connect(&rt, daddr, 0,
			       RT_CONN_FLAGS(sk),
			       sk->sk_bound_dev_if,
			       sk->sk_protocol,
1049
			       inet->sport, inet->dport, sk, 0);
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
	if (err)
		return err;

	sk_setup_caps(sk, &rt->u.dst);

	new_saddr = rt->rt_src;

	if (new_saddr == old_saddr)
		return 0;

	if (sysctl_ip_dynaddr > 1) {
		printk(KERN_INFO "%s(): shifting inet->"
				 "saddr from %d.%d.%d.%d to %d.%d.%d.%d\n",
		       __FUNCTION__,
		       NIPQUAD(old_saddr),
		       NIPQUAD(new_saddr));
	}

	inet->saddr = inet->rcv_saddr = new_saddr;

	/*
	 * XXX The only one ugly spot where we need to
	 * XXX really change the sockets identity after
	 * XXX it has entered the hashes. -DaveM
	 *
	 * Besides that, it does not check for connection
	 * uniqueness. Wait for troubles.
	 */
	__sk_prot_rehash(sk);
	return 0;
}

int inet_sk_rebuild_header(struct sock *sk)
{
	struct inet_sock *inet = inet_sk(sk);
	struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
A
Al Viro 已提交
1086
	__be32 daddr;
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
	int err;

	/* Route is OK, nothing to do. */
	if (rt)
		return 0;

	/* Reroute. */
	daddr = inet->daddr;
	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;
{
	struct flowi fl = {
		.oif = sk->sk_bound_dev_if,
		.nl_u = {
			.ip4_u = {
				.daddr	= daddr,
				.saddr	= inet->saddr,
				.tos	= RT_CONN_FLAGS(sk),
			},
		},
		.proto = sk->sk_protocol,
		.uli_u = {
			.ports = {
				.sport = inet->sport,
				.dport = inet->dport,
			},
		},
	};
1115

V
Venkat Yekkirala 已提交
1116
	security_sk_classify_flow(sk, &fl);
1117
	err = ip_route_output_flow(&init_net, &rt, &fl, sk, 0);
1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139
}
	if (!err)
		sk_setup_caps(sk, &rt->u.dst);
	else {
		/* Routing failed... */
		sk->sk_route_caps = 0;
		/*
		 * Other protocols have to map its equivalent state to TCP_SYN_SENT.
		 * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
		 */
		if (!sysctl_ip_dynaddr ||
		    sk->sk_state != TCP_SYN_SENT ||
		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
		    (err = inet_sk_reselect_saddr(sk)) != 0)
			sk->sk_err_soft = -err;
	}

	return err;
}

EXPORT_SYMBOL(inet_sk_rebuild_header);

1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150
static int inet_gso_send_check(struct sk_buff *skb)
{
	struct iphdr *iph;
	struct net_protocol *ops;
	int proto;
	int ihl;
	int err = -EINVAL;

	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
		goto out;

1151
	iph = ip_hdr(skb);
1152 1153 1154 1155 1156 1157 1158
	ihl = iph->ihl * 4;
	if (ihl < sizeof(*iph))
		goto out;

	if (unlikely(!pskb_may_pull(skb, ihl)))
		goto out;

1159 1160
	__skb_pull(skb, ihl);
	skb_reset_transport_header(skb);
1161
	iph = ip_hdr(skb);
1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174
	proto = iph->protocol & (MAX_INET_PROTOS - 1);
	err = -EPROTONOSUPPORT;

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
	if (likely(ops && ops->gso_send_check))
		err = ops->gso_send_check(skb);
	rcu_read_unlock();

out:
	return err;
}

1175
static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features)
H
Herbert Xu 已提交
1176 1177 1178 1179 1180 1181 1182 1183
{
	struct sk_buff *segs = ERR_PTR(-EINVAL);
	struct iphdr *iph;
	struct net_protocol *ops;
	int proto;
	int ihl;
	int id;

1184 1185 1186
	if (!(features & NETIF_F_V4_CSUM))
		features &= ~NETIF_F_SG;

1187 1188 1189 1190 1191 1192 1193 1194 1195
	if (unlikely(skb_shinfo(skb)->gso_type &
		     ~(SKB_GSO_TCPV4 |
		       SKB_GSO_UDP |
		       SKB_GSO_DODGY |
		       SKB_GSO_TCP_ECN |
		       0)))
		goto out;

	if (unlikely(!pskb_may_pull(skb, sizeof(*iph))))
H
Herbert Xu 已提交
1196 1197
		goto out;

1198
	iph = ip_hdr(skb);
H
Herbert Xu 已提交
1199 1200 1201 1202
	ihl = iph->ihl * 4;
	if (ihl < sizeof(*iph))
		goto out;

1203
	if (unlikely(!pskb_may_pull(skb, ihl)))
H
Herbert Xu 已提交
1204 1205
		goto out;

1206 1207
	__skb_pull(skb, ihl);
	skb_reset_transport_header(skb);
1208
	iph = ip_hdr(skb);
H
Herbert Xu 已提交
1209 1210 1211 1212 1213 1214
	id = ntohs(iph->id);
	proto = iph->protocol & (MAX_INET_PROTOS - 1);
	segs = ERR_PTR(-EPROTONOSUPPORT);

	rcu_read_lock();
	ops = rcu_dereference(inet_protos[proto]);
1215
	if (likely(ops && ops->gso_segment))
1216
		segs = ops->gso_segment(skb, features);
H
Herbert Xu 已提交
1217 1218
	rcu_read_unlock();

1219
	if (!segs || unlikely(IS_ERR(segs)))
H
Herbert Xu 已提交
1220 1221 1222 1223
		goto out;

	skb = segs;
	do {
1224
		iph = ip_hdr(skb);
H
Herbert Xu 已提交
1225 1226 1227
		iph->id = htons(id++);
		iph->tot_len = htons(skb->len - skb->mac_len);
		iph->check = 0;
1228
		iph->check = ip_fast_csum(skb_network_header(skb), iph->ihl);
H
Herbert Xu 已提交
1229 1230 1231 1232 1233 1234
	} while ((skb = skb->next));

out:
	return segs;
}

1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247
unsigned long snmp_fold_field(void *mib[], int offt)
{
	unsigned long res = 0;
	int i;

	for_each_possible_cpu(i) {
		res += *(((unsigned long *) per_cpu_ptr(mib[0], i)) + offt);
		res += *(((unsigned long *) per_cpu_ptr(mib[1], i)) + offt);
	}
	return res;
}
EXPORT_SYMBOL_GPL(snmp_fold_field);

1248
int snmp_mib_init(void *ptr[2], size_t mibsize)
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
{
	BUG_ON(ptr == NULL);
	ptr[0] = __alloc_percpu(mibsize);
	if (!ptr[0])
		goto err0;
	ptr[1] = __alloc_percpu(mibsize);
	if (!ptr[1])
		goto err1;
	return 0;
err1:
	free_percpu(ptr[0]);
	ptr[0] = NULL;
err0:
	return -ENOMEM;
}
EXPORT_SYMBOL_GPL(snmp_mib_init);

void snmp_mib_free(void *ptr[2])
{
	BUG_ON(ptr == NULL);
	free_percpu(ptr[0]);
	free_percpu(ptr[1]);
	ptr[0] = ptr[1] = NULL;
}
EXPORT_SYMBOL_GPL(snmp_mib_free);

L
Linus Torvalds 已提交
1275 1276 1277 1278 1279 1280 1281 1282 1283
#ifdef CONFIG_IP_MULTICAST
static struct net_protocol igmp_protocol = {
	.handler =	igmp_rcv,
};
#endif

static struct net_protocol tcp_protocol = {
	.handler =	tcp_v4_rcv,
	.err_handler =	tcp_v4_err,
1284
	.gso_send_check = tcp_v4_gso_send_check,
H
Herbert Xu 已提交
1285
	.gso_segment =	tcp_tso_segment,
L
Linus Torvalds 已提交
1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296
	.no_policy =	1,
};

static struct net_protocol udp_protocol = {
	.handler =	udp_rcv,
	.err_handler =	udp_err,
	.no_policy =	1,
};

static struct net_protocol icmp_protocol = {
	.handler =	icmp_rcv,
1297
	.no_policy =	1,
L
Linus Torvalds 已提交
1298 1299 1300 1301
};

static int __init init_ipv4_mibs(void)
{
1302
	if (snmp_mib_init((void **)net_statistics,
1303
			  sizeof(struct linux_mib)) < 0)
1304 1305
		goto err_net_mib;
	if (snmp_mib_init((void **)ip_statistics,
1306
			  sizeof(struct ipstats_mib)) < 0)
1307 1308
		goto err_ip_mib;
	if (snmp_mib_init((void **)icmp_statistics,
1309
			  sizeof(struct icmp_mib)) < 0)
1310
		goto err_icmp_mib;
1311
	if (snmp_mib_init((void **)icmpmsg_statistics,
1312
			  sizeof(struct icmpmsg_mib)) < 0)
1313
		goto err_icmpmsg_mib;
1314
	if (snmp_mib_init((void **)tcp_statistics,
1315
			  sizeof(struct tcp_mib)) < 0)
1316 1317
		goto err_tcp_mib;
	if (snmp_mib_init((void **)udp_statistics,
1318
			  sizeof(struct udp_mib)) < 0)
1319 1320
		goto err_udp_mib;
	if (snmp_mib_init((void **)udplite_statistics,
1321
			  sizeof(struct udp_mib)) < 0)
1322 1323 1324
		goto err_udplite_mib;

	tcp_mib_init();
L
Linus Torvalds 已提交
1325 1326

	return 0;
1327 1328 1329 1330 1331 1332

err_udplite_mib:
	snmp_mib_free((void **)udp_statistics);
err_udp_mib:
	snmp_mib_free((void **)tcp_statistics);
err_tcp_mib:
1333 1334
	snmp_mib_free((void **)icmpmsg_statistics);
err_icmpmsg_mib:
1335 1336 1337 1338 1339 1340 1341
	snmp_mib_free((void **)icmp_statistics);
err_icmp_mib:
	snmp_mib_free((void **)ip_statistics);
err_ip_mib:
	snmp_mib_free((void **)net_statistics);
err_net_mib:
	return -ENOMEM;
L
Linus Torvalds 已提交
1342 1343 1344 1345
}

static int ipv4_proc_init(void);

1346 1347 1348 1349 1350 1351 1352
/*
 *	IP protocol layer initialiser
 */

static struct packet_type ip_packet_type = {
	.type = __constant_htons(ETH_P_IP),
	.func = ip_rcv,
1353
	.gso_send_check = inet_gso_send_check,
H
Herbert Xu 已提交
1354
	.gso_segment = inet_gso_segment,
1355 1356
};

L
Linus Torvalds 已提交
1357 1358 1359 1360 1361 1362 1363
static int __init inet_init(void)
{
	struct sk_buff *dummy_skb;
	struct inet_protosw *q;
	struct list_head *r;
	int rc = -EINVAL;

1364
	BUILD_BUG_ON(sizeof(struct inet_skb_parm) > sizeof(dummy_skb->cb));
L
Linus Torvalds 已提交
1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378

	rc = proto_register(&tcp_prot, 1);
	if (rc)
		goto out;

	rc = proto_register(&udp_prot, 1);
	if (rc)
		goto out_unregister_tcp_proto;

	rc = proto_register(&raw_prot, 1);
	if (rc)
		goto out_unregister_udp_proto;

	/*
1379
	 *	Tell SOCKET that we are alive...
L
Linus Torvalds 已提交
1380 1381
	 */

1382
	(void)sock_register(&inet_family_ops);
L
Linus Torvalds 已提交
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

	/*
	 *	Add all the base protocols.
	 */

	if (inet_add_protocol(&icmp_protocol, IPPROTO_ICMP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add ICMP protocol\n");
	if (inet_add_protocol(&udp_protocol, IPPROTO_UDP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add UDP protocol\n");
	if (inet_add_protocol(&tcp_protocol, IPPROTO_TCP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add TCP protocol\n");
#ifdef CONFIG_IP_MULTICAST
	if (inet_add_protocol(&igmp_protocol, IPPROTO_IGMP) < 0)
		printk(KERN_CRIT "inet_init: Cannot add IGMP protocol\n");
#endif

	/* Register the socket-side information for inet_create. */
	for (r = &inetsw[0]; r < &inetsw[SOCK_MAX]; ++r)
		INIT_LIST_HEAD(r);

	for (q = inetsw_array; q < &inetsw_array[INETSW_ARRAY_LEN]; ++q)
		inet_register_protosw(q);

	/*
	 *	Set the ARP module up
	 */

	arp_init();

1412 1413 1414
	/*
	 *	Set the IP module up
	 */
L
Linus Torvalds 已提交
1415 1416 1417

	ip_init();

1418
	tcp_v4_init();
L
Linus Torvalds 已提交
1419 1420 1421 1422

	/* Setup TCP slab cache for open requests. */
	tcp_init();

H
Hideo Aoki 已提交
1423 1424 1425
	/* Setup UDP memory threshold */
	udp_init();

1426 1427
	/* Add UDP-Lite (RFC 3828) */
	udplite4_register();
L
Linus Torvalds 已提交
1428 1429 1430 1431 1432

	/*
	 *	Set the ICMP layer up
	 */

1433
	icmp_init();
L
Linus Torvalds 已提交
1434 1435 1436 1437 1438 1439 1440 1441 1442

	/*
	 *	Initialise the multicast router
	 */
#if defined(CONFIG_IP_MROUTE)
	ip_mr_init();
#endif
	/*
	 *	Initialise per-cpu ipv4 mibs
1443
	 */
L
Linus Torvalds 已提交
1444

S
Stephen Hemminger 已提交
1445
	if (init_ipv4_mibs())
L
Linus Torvalds 已提交
1446
		printk(KERN_CRIT "inet_init: Cannot init ipv4 mibs\n"); ;
1447

L
Linus Torvalds 已提交
1448 1449 1450 1451
	ipv4_proc_init();

	ipfrag_init();

1452 1453
	dev_add_pack(&ip_packet_type);

L
Linus Torvalds 已提交
1454 1455 1456 1457 1458
	rc = 0;
out:
	return rc;
out_unregister_udp_proto:
	proto_unregister(&udp_prot);
1459 1460
out_unregister_tcp_proto:
	proto_unregister(&tcp_prot);
L
Linus Torvalds 已提交
1461 1462 1463
	goto out;
}

1464
fs_initcall(inet_init);
L
Linus Torvalds 已提交
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

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

#ifdef CONFIG_PROC_FS
static int __init ipv4_proc_init(void)
{
	int rc = 0;

	if (raw_proc_init())
		goto out_raw;
	if (tcp4_proc_init())
		goto out_tcp;
	if (udp4_proc_init())
		goto out_udp;
	if (ip_misc_proc_init())
		goto out_misc;
out:
	return rc;
out_misc:
	udp4_proc_exit();
out_udp:
	tcp4_proc_exit();
out_tcp:
	raw_proc_exit();
out_raw:
	rc = -ENOMEM;
	goto out;
}

#else /* CONFIG_PROC_FS */
static int __init ipv4_proc_init(void)
{
	return 0;
}
#endif /* CONFIG_PROC_FS */

MODULE_ALIAS_NETPROTO(PF_INET);

EXPORT_SYMBOL(inet_accept);
EXPORT_SYMBOL(inet_bind);
EXPORT_SYMBOL(inet_dgram_connect);
EXPORT_SYMBOL(inet_dgram_ops);
EXPORT_SYMBOL(inet_getname);
EXPORT_SYMBOL(inet_ioctl);
EXPORT_SYMBOL(inet_listen);
EXPORT_SYMBOL(inet_register_protosw);
EXPORT_SYMBOL(inet_release);
EXPORT_SYMBOL(inet_sendmsg);
EXPORT_SYMBOL(inet_shutdown);
EXPORT_SYMBOL(inet_sock_destruct);
EXPORT_SYMBOL(inet_stream_connect);
EXPORT_SYMBOL(inet_stream_ops);
EXPORT_SYMBOL(inet_unregister_protosw);
EXPORT_SYMBOL(net_statistics);
1519
EXPORT_SYMBOL(sysctl_ip_nonlocal_bind);