l2tp_ip6.c 19.8 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11
/*
 * L2TPv3 IP encapsulation support for IPv6
 *
 * Copyright (c) 2012 Katalix Systems Ltd
 *
 *	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.
 */

12 13
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

14 15 16 17 18 19 20 21 22 23 24 25 26 27
#include <linux/icmp.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/random.h>
#include <linux/socket.h>
#include <linux/l2tp.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/inet_common.h>
#include <net/inet_hashtables.h>
28
#include <net/inet6_hashtables.h>
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
#include <net/tcp_states.h>
#include <net/protocol.h>
#include <net/xfrm.h>

#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>

#include "l2tp_core.h"

struct l2tp_ip6_sock {
	/* inet_sock has to be the first member of l2tp_ip6_sock */
	struct inet_sock	inet;

	u32			conn_id;
	u32			peer_conn_id;

	/* ipv6_pinfo has to be the last member of l2tp_ip6_sock, see
	   inet6_sk_generic */
	struct ipv6_pinfo	inet6;
};

static DEFINE_RWLOCK(l2tp_ip6_lock);
static struct hlist_head l2tp_ip6_table;
static struct hlist_head l2tp_ip6_bind_table;

static inline struct l2tp_ip6_sock *l2tp_ip6_sk(const struct sock *sk)
{
	return (struct l2tp_ip6_sock *)sk;
}

60 61
static struct sock *__l2tp_ip6_bind_lookup(const struct net *net,
					   const struct in6_addr *laddr,
62
					   const struct in6_addr *raddr,
63 64 65 66
					   int dif, u32 tunnel_id)
{
	struct sock *sk;

67
	sk_for_each_bound(sk, &l2tp_ip6_bind_table) {
68
		const struct in6_addr *sk_laddr = inet6_rcv_saddr(sk);
69
		const struct in6_addr *sk_raddr = &sk->sk_v6_daddr;
70
		const struct l2tp_ip6_sock *l2tp = l2tp_ip6_sk(sk);
71

72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89
		if (!net_eq(sock_net(sk), net))
			continue;

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

		if (sk_laddr && !ipv6_addr_any(sk_laddr) &&
		    !ipv6_addr_any(laddr) && !ipv6_addr_equal(sk_laddr, laddr))
			continue;

		if (!ipv6_addr_any(sk_raddr) && raddr &&
		    !ipv6_addr_any(raddr) && !ipv6_addr_equal(sk_raddr, raddr))
			continue;

		if (l2tp->conn_id != tunnel_id)
			continue;

		goto found;
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
	}

	sk = NULL;
found:
	return sk;
}

/* When processing receive frames, there are two cases to
 * consider. Data frames consist of a non-zero session-id and an
 * optional cookie. Control frames consist of a regular L2TP header
 * preceded by 32-bits of zeros.
 *
 * L2TPv3 Session Header Over IP
 *
 *  0                   1                   2                   3
 *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |                           Session ID                          |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |               Cookie (optional, maximum 64 bits)...
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 *                                                                 |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 *
 * L2TPv3 Control Message Header Over IP
 *
 *  0                   1                   2                   3
 *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |                      (32 bits of zeros)                       |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |T|L|x|x|S|x|x|x|x|x|x|x|  Ver  |             Length            |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |                     Control Connection ID                     |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 * |               Ns              |               Nr              |
 * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
 *
 * All control frames are passed to userspace.
 */
static int l2tp_ip6_recv(struct sk_buff *skb)
{
132
	struct net *net = dev_net(skb->dev);
133 134 135 136 137 138
	struct sock *sk;
	u32 session_id;
	u32 tunnel_id;
	unsigned char *ptr, *optr;
	struct l2tp_session *session;
	struct l2tp_tunnel *tunnel = NULL;
139
	struct ipv6hdr *iph;
140 141 142 143 144
	int length;

	if (!pskb_may_pull(skb, 4))
		goto discard;

145 146
	/* Point to L2TP header */
	optr = ptr = skb->data;
147 148 149 150 151 152 153 154 155 156 157 158 159
	session_id = ntohl(*((__be32 *) ptr));
	ptr += 4;

	/* RFC3931: L2TP/IP packets have the first 4 bytes containing
	 * the session_id. If it is 0, the packet is a L2TP control
	 * frame and the session_id value can be discarded.
	 */
	if (session_id == 0) {
		__skb_pull(skb, 4);
		goto pass_up;
	}

	/* Ok, this is a data packet. Lookup the session. */
160 161
	session = l2tp_session_get(net, NULL, session_id, true);
	if (!session)
162 163 164
		goto discard;

	tunnel = session->tunnel;
165 166
	if (!tunnel)
		goto discard_sess;
167 168 169 170 171

	/* Trace packet contents, if enabled */
	if (tunnel->debug & L2TP_MSG_DATA) {
		length = min(32u, skb->len);
		if (!pskb_may_pull(skb, length))
172
			goto discard_sess;
173

174 175 176
		/* Point to L2TP header */
		optr = ptr = skb->data;
		ptr += 4;
177 178
		pr_debug("%s: ip recv\n", tunnel->name);
		print_hex_dump_bytes("", DUMP_PREFIX_OFFSET, ptr, length);
179 180 181 182
	}

	l2tp_recv_common(session, skb, ptr, optr, 0, skb->len,
			 tunnel->recv_payload_hook);
183 184
	l2tp_session_dec_refcount(session);

185 186 187 188 189 190 191 192 193 194 195
	return 0;

pass_up:
	/* Get the tunnel_id from the L2TP header */
	if (!pskb_may_pull(skb, 12))
		goto discard;

	if ((skb->data[0] & 0xc0) != 0xc0)
		goto discard;

	tunnel_id = ntohl(*(__be32 *) &skb->data[4]);
196 197 198 199 200 201
	iph = ipv6_hdr(skb);

	read_lock_bh(&l2tp_ip6_lock);
	sk = __l2tp_ip6_bind_lookup(net, &iph->daddr, &iph->saddr,
				    inet6_iif(skb), tunnel_id);
	if (!sk) {
202
		read_unlock_bh(&l2tp_ip6_lock);
203
		goto discard;
204
	}
205 206
	sock_hold(sk);
	read_unlock_bh(&l2tp_ip6_lock);
207 208 209 210 211 212 213 214

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

	nf_reset(skb);

	return sk_receive_skb(sk, skb, 1);

215 216 217 218 219 220
discard_sess:
	if (session->deref)
		session->deref(session);
	l2tp_session_dec_refcount(session);
	goto discard;

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
discard_put:
	sock_put(sk);

discard:
	kfree_skb(skb);
	return 0;
}

static int l2tp_ip6_open(struct sock *sk)
{
	/* Prevent autobind. We don't have ports. */
	inet_sk(sk)->inet_num = IPPROTO_L2TP;

	write_lock_bh(&l2tp_ip6_lock);
	sk_add_node(sk, &l2tp_ip6_table);
	write_unlock_bh(&l2tp_ip6_lock);

	return 0;
}

static void l2tp_ip6_close(struct sock *sk, long timeout)
{
	write_lock_bh(&l2tp_ip6_lock);
	hlist_del_init(&sk->sk_bind_node);
	sk_del_node_init(sk);
	write_unlock_bh(&l2tp_ip6_lock);

	sk_common_release(sk);
}

static void l2tp_ip6_destroy_sock(struct sock *sk)
{
253 254
	struct l2tp_tunnel *tunnel = l2tp_sock_to_tunnel(sk);

255 256 257 258
	lock_sock(sk);
	ip6_flush_pending_frames(sk);
	release_sock(sk);

259 260 261 262 263
	if (tunnel) {
		l2tp_tunnel_closeall(tunnel);
		sock_put(sk);
	}

264 265 266 267 268 269 270 271
	inet6_destroy_sock(sk);
}

static int l2tp_ip6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sockaddr_l2tpip6 *addr = (struct sockaddr_l2tpip6 *) uaddr;
272
	struct net *net = sock_net(sk);
273
	__be32 v4addr = 0;
274
	int bound_dev_if;
275 276 277
	int addr_type;
	int err;

278 279
	if (addr->l2tp_family != AF_INET6)
		return -EINVAL;
280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295
	if (addr_len < sizeof(*addr))
		return -EINVAL;

	addr_type = ipv6_addr_type(&addr->l2tp_addr);

	/* l2tp_ip6 sockets are IPv6 only */
	if (addr_type == IPV6_ADDR_MAPPED)
		return -EADDRNOTAVAIL;

	/* L2TP is point-point, not multicast */
	if (addr_type & IPV6_ADDR_MULTICAST)
		return -EADDRNOTAVAIL;

	lock_sock(sk);

	err = -EINVAL;
296 297 298
	if (!sock_flag(sk, SOCK_ZAPPED))
		goto out_unlock;

299 300 301
	if (sk->sk_state != TCP_CLOSE)
		goto out_unlock;

302 303
	bound_dev_if = sk->sk_bound_dev_if;

304 305 306 307 308 309
	/* Check if the address belongs to the host. */
	rcu_read_lock();
	if (addr_type != IPV6_ADDR_ANY) {
		struct net_device *dev = NULL;

		if (addr_type & IPV6_ADDR_LINKLOCAL) {
310 311
			if (addr->l2tp_scope_id)
				bound_dev_if = addr->l2tp_scope_id;
312 313

			/* Binding to link-local address requires an
314 315 316
			 * interface.
			 */
			if (!bound_dev_if)
317 318 319
				goto out_unlock_rcu;

			err = -ENODEV;
320
			dev = dev_get_by_index_rcu(sock_net(sk), bound_dev_if);
321 322 323 324 325 326 327 328 329 330 331 332 333 334
			if (!dev)
				goto out_unlock_rcu;
		}

		/* ipv4 addr of the socket is invalid.  Only the
		 * unspecified and mapped address have a v4 equivalent.
		 */
		v4addr = LOOPBACK4_IPV6;
		err = -EADDRNOTAVAIL;
		if (!ipv6_chk_addr(sock_net(sk), &addr->l2tp_addr, dev, 0))
			goto out_unlock_rcu;
	}
	rcu_read_unlock();

335
	write_lock_bh(&l2tp_ip6_lock);
336
	if (__l2tp_ip6_bind_lookup(net, &addr->l2tp_addr, NULL, bound_dev_if,
337 338 339 340 341 342 343 344 345
				   addr->l2tp_conn_id)) {
		write_unlock_bh(&l2tp_ip6_lock);
		err = -EADDRINUSE;
		goto out_unlock;
	}

	inet->inet_saddr = v4addr;
	inet->inet_rcv_saddr = v4addr;
	sk->sk_bound_dev_if = bound_dev_if;
346
	sk->sk_v6_rcv_saddr = addr->l2tp_addr;
347 348 349 350 351 352 353 354
	np->saddr = addr->l2tp_addr;

	l2tp_ip6_sk(sk)->conn_id = addr->l2tp_conn_id;

	sk_add_bind_node(sk, &l2tp_ip6_bind_table);
	sk_del_node_init(sk);
	write_unlock_bh(&l2tp_ip6_lock);

355
	sock_reset_flag(sk, SOCK_ZAPPED);
356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378
	release_sock(sk);
	return 0;

out_unlock_rcu:
	rcu_read_unlock();
out_unlock:
	release_sock(sk);

	return err;
}

static int l2tp_ip6_connect(struct sock *sk, struct sockaddr *uaddr,
			    int addr_len)
{
	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *) uaddr;
	struct sockaddr_in6	*usin = (struct sockaddr_in6 *) uaddr;
	struct in6_addr	*daddr;
	int	addr_type;
	int rc;

	if (addr_len < sizeof(*lsa))
		return -EINVAL;

379 380 381
	if (usin->sin6_family != AF_INET6)
		return -EINVAL;

382 383 384 385 386 387 388 389 390 391 392 393
	addr_type = ipv6_addr_type(&usin->sin6_addr);
	if (addr_type & IPV6_ADDR_MULTICAST)
		return -EINVAL;

	if (addr_type & IPV6_ADDR_MAPPED) {
		daddr = &usin->sin6_addr;
		if (ipv4_is_multicast(daddr->s6_addr32[3]))
			return -EINVAL;
	}

	lock_sock(sk);

394 395 396 397 398 399 400 401 402 403
	 /* Must bind first - autobinding does not work */
	if (sock_flag(sk, SOCK_ZAPPED)) {
		rc = -EINVAL;
		goto out_sk;
	}

	rc = __ip6_datagram_connect(sk, uaddr, addr_len);
	if (rc < 0)
		goto out_sk;

404 405 406 407 408 409 410
	l2tp_ip6_sk(sk)->peer_conn_id = lsa->l2tp_conn_id;

	write_lock_bh(&l2tp_ip6_lock);
	hlist_del_init(&sk->sk_bind_node);
	sk_add_bind_node(sk, &l2tp_ip6_bind_table);
	write_unlock_bh(&l2tp_ip6_lock);

411
out_sk:
412 413 414 415 416
	release_sock(sk);

	return rc;
}

417 418 419 420 421
static int l2tp_ip6_disconnect(struct sock *sk, int flags)
{
	if (sock_flag(sk, SOCK_ZAPPED))
		return 0;

422
	return __udp_disconnect(sk, flags);
423 424
}

425 426 427 428 429 430 431 432 433 434 435
static int l2tp_ip6_getname(struct socket *sock, struct sockaddr *uaddr,
			    int *uaddr_len, int peer)
{
	struct sockaddr_l2tpip6 *lsa = (struct sockaddr_l2tpip6 *)uaddr;
	struct sock *sk = sock->sk;
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct l2tp_ip6_sock *lsk = l2tp_ip6_sk(sk);

	lsa->l2tp_family = AF_INET6;
	lsa->l2tp_flowinfo = 0;
	lsa->l2tp_scope_id = 0;
436
	lsa->l2tp_unused = 0;
437 438 439 440
	if (peer) {
		if (!lsk->peer_conn_id)
			return -ENOTCONN;
		lsa->l2tp_conn_id = lsk->peer_conn_id;
441
		lsa->l2tp_addr = sk->sk_v6_daddr;
442 443 444
		if (np->sndflow)
			lsa->l2tp_flowinfo = np->flow_label;
	} else {
445
		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
446 447
			lsa->l2tp_addr = np->saddr;
		else
448
			lsa->l2tp_addr = sk->sk_v6_rcv_saddr;
449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469

		lsa->l2tp_conn_id = lsk->conn_id;
	}
	if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
		lsa->l2tp_scope_id = sk->sk_bound_dev_if;
	*uaddr_len = sizeof(*lsa);
	return 0;
}

static int l2tp_ip6_backlog_recv(struct sock *sk, struct sk_buff *skb)
{
	int rc;

	/* Charge it to the socket, dropping if the queue is full. */
	rc = sock_queue_rcv_skb(sk, skb);
	if (rc < 0)
		goto drop;

	return 0;

drop:
470
	IP_INC_STATS(sock_net(sk), IPSTATS_MIB_INDISCARDS);
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
	kfree_skb(skb);
	return -1;
}

static int l2tp_ip6_push_pending_frames(struct sock *sk)
{
	struct sk_buff *skb;
	__be32 *transhdr = NULL;
	int err = 0;

	skb = skb_peek(&sk->sk_write_queue);
	if (skb == NULL)
		goto out;

	transhdr = (__be32 *)skb_transport_header(skb);
	*transhdr = 0;

	err = ip6_push_pending_frames(sk);

out:
	return err;
}

/* Userspace will call sendmsg() on the tunnel socket to send L2TP
 * control frames.
 */
497
static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
498 499
{
	struct ipv6_txoptions opt_space;
500
	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
501 502
	struct in6_addr *daddr, *final_p, final;
	struct ipv6_pinfo *np = inet6_sk(sk);
503
	struct ipv6_txoptions *opt_to_free = NULL;
504 505 506 507
	struct ipv6_txoptions *opt = NULL;
	struct ip6_flowlabel *flowlabel = NULL;
	struct dst_entry *dst = NULL;
	struct flowi6 fl6;
508
	struct sockcm_cookie sockc_unused = {0};
W
Wei Wang 已提交
509
	struct ipcm6_cookie ipc6;
510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530
	int addr_len = msg->msg_namelen;
	int transhdrlen = 4; /* zero session-id */
	int ulen = len + transhdrlen;
	int err;

	/* Rough check on arithmetic overflow,
	   better check is made in ip6_append_data().
	 */
	if (len > INT_MAX)
		return -EMSGSIZE;

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

	/*
	 *	Get and verify the address.
	 */
	memset(&fl6, 0, sizeof(fl6));

	fl6.flowi6_mark = sk->sk_mark;
531
	fl6.flowi6_uid = sk->sk_uid;
532

W
Wei Wang 已提交
533 534 535 536
	ipc6.hlimit = -1;
	ipc6.tclass = -1;
	ipc6.dontfrag = -1;

537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558
	if (lsa) {
		if (addr_len < SIN6_LEN_RFC2133)
			return -EINVAL;

		if (lsa->l2tp_family && lsa->l2tp_family != AF_INET6)
			return -EAFNOSUPPORT;

		daddr = &lsa->l2tp_addr;
		if (np->sndflow) {
			fl6.flowlabel = lsa->l2tp_flowinfo & IPV6_FLOWINFO_MASK;
			if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) {
				flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
				if (flowlabel == NULL)
					return -EINVAL;
			}
		}

		/*
		 * Otherwise it will be difficult to maintain
		 * sk->sk_dst_cache.
		 */
		if (sk->sk_state == TCP_ESTABLISHED &&
559 560
		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
			daddr = &sk->sk_v6_daddr;
561 562 563 564 565 566 567 568 569

		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    lsa->l2tp_scope_id &&
		    ipv6_addr_type(daddr) & IPV6_ADDR_LINKLOCAL)
			fl6.flowi6_oif = lsa->l2tp_scope_id;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;

570
		daddr = &sk->sk_v6_daddr;
571 572 573 574 575 576 577 578 579 580
		fl6.flowlabel = np->flow_label;
	}

	if (fl6.flowi6_oif == 0)
		fl6.flowi6_oif = sk->sk_bound_dev_if;

	if (msg->msg_controllen) {
		opt = &opt_space;
		memset(opt, 0, sizeof(struct ipv6_txoptions));
		opt->tot_len = sizeof(struct ipv6_txoptions);
W
Wei Wang 已提交
581
		ipc6.opt = opt;
582

W
Wei Wang 已提交
583 584 585
		err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6,
					    &sockc_unused);
		if (err < 0) {
586 587 588 589 590 591 592 593 594 595 596 597
			fl6_sock_release(flowlabel);
			return err;
		}
		if ((fl6.flowlabel & IPV6_FLOWLABEL_MASK) && !flowlabel) {
			flowlabel = fl6_sock_lookup(sk, fl6.flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
		}
		if (!(opt->opt_nflen|opt->opt_flen))
			opt = NULL;
	}

598 599 600 601
	if (!opt) {
		opt = txopt_get(np);
		opt_to_free = opt;
	}
602 603 604
	if (flowlabel)
		opt = fl6_merge_options(&opt_space, flowlabel, opt);
	opt = ipv6_fixup_options(&opt_space, opt);
W
Wei Wang 已提交
605
	ipc6.opt = opt;
606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623

	fl6.flowi6_proto = sk->sk_protocol;
	if (!ipv6_addr_any(daddr))
		fl6.daddr = *daddr;
	else
		fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */
	if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr))
		fl6.saddr = np->saddr;

	final_p = fl6_update_dst(&fl6, opt, &final);

	if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
		fl6.flowi6_oif = np->mcast_oif;
	else if (!fl6.flowi6_oif)
		fl6.flowi6_oif = np->ucast_oif;

	security_sk_classify_flow(sk, flowi6_to_flowi(&fl6));

624 625 626 627 628
	if (ipc6.tclass < 0)
		ipc6.tclass = np->tclass;

	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);

629
	dst = ip6_dst_lookup_flow(sk, &fl6, final_p);
630 631 632 633 634
	if (IS_ERR(dst)) {
		err = PTR_ERR(dst);
		goto out;
	}

W
Wei Wang 已提交
635 636
	if (ipc6.hlimit < 0)
		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
637

W
Wei Wang 已提交
638 639
	if (ipc6.dontfrag < 0)
		ipc6.dontfrag = np->dontfrag;
640 641 642 643 644 645

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

back_from_confirm:
	lock_sock(sk);
646
	err = ip6_append_data(sk, ip_generic_getfrag, msg,
W
Wei Wang 已提交
647
			      ulen, transhdrlen, &ipc6,
648
			      &fl6, (struct rt6_info *)dst,
W
Wei Wang 已提交
649
			      msg->msg_flags, &sockc_unused);
650 651 652 653 654 655 656 657 658
	if (err)
		ip6_flush_pending_frames(sk);
	else if (!(msg->msg_flags & MSG_MORE))
		err = l2tp_ip6_push_pending_frames(sk);
	release_sock(sk);
done:
	dst_release(dst);
out:
	fl6_sock_release(flowlabel);
659
	txopt_put(opt_to_free);
660 661 662 663

	return err < 0 ? err : len;

do_confirm:
664 665
	if (msg->msg_flags & MSG_PROBE)
		dst_confirm_neigh(dst, &fl6.daddr);
666 667 668 669 670 671
	if (!(msg->msg_flags & MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto done;
}

672 673
static int l2tp_ip6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
			    int noblock, int flags, int *addr_len)
674
{
675
	struct ipv6_pinfo *np = inet6_sk(sk);
676
	DECLARE_SOCKADDR(struct sockaddr_l2tpip6 *, lsa, msg->msg_name);
677 678 679 680 681 682 683 684 685 686 687
	size_t copied = 0;
	int err = -EOPNOTSUPP;
	struct sk_buff *skb;

	if (flags & MSG_OOB)
		goto out;

	if (addr_len)
		*addr_len = sizeof(*lsa);

	if (flags & MSG_ERRQUEUE)
688
		return ipv6_recv_error(sk, msg, len, addr_len);
689 690 691 692 693 694 695 696 697 698 699

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

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

700
	err = skb_copy_datagram_msg(skb, 0, msg, copied);
701 702 703 704 705 706 707 708 709 710 711 712
	if (err)
		goto done;

	sock_recv_timestamp(msg, sk, skb);

	/* Copy the address. */
	if (lsa) {
		lsa->l2tp_family = AF_INET6;
		lsa->l2tp_unused = 0;
		lsa->l2tp_addr = ipv6_hdr(skb)->saddr;
		lsa->l2tp_flowinfo = 0;
		lsa->l2tp_scope_id = 0;
713
		lsa->l2tp_conn_id = 0;
714
		if (ipv6_addr_type(&lsa->l2tp_addr) & IPV6_ADDR_LINKLOCAL)
715
			lsa->l2tp_scope_id = inet6_iif(skb);
716 717
	}

718 719
	if (np->rxopt.all)
		ip6_datagram_recv_ctl(sk, msg, skb);
720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735

	if (flags & MSG_TRUNC)
		copied = skb->len;
done:
	skb_free_datagram(sk, skb);
out:
	return err ? err : copied;
}

static struct proto l2tp_ip6_prot = {
	.name		   = "L2TP/IPv6",
	.owner		   = THIS_MODULE,
	.init		   = l2tp_ip6_open,
	.close		   = l2tp_ip6_close,
	.bind		   = l2tp_ip6_bind,
	.connect	   = l2tp_ip6_connect,
736
	.disconnect	   = l2tp_ip6_disconnect,
E
Eric Dumazet 已提交
737
	.ioctl		   = l2tp_ioctl,
738 739 740 741 742 743
	.destroy	   = l2tp_ip6_destroy_sock,
	.setsockopt	   = ipv6_setsockopt,
	.getsockopt	   = ipv6_getsockopt,
	.sendmsg	   = l2tp_ip6_sendmsg,
	.recvmsg	   = l2tp_ip6_recvmsg,
	.backlog_rcv	   = l2tp_ip6_backlog_recv,
744
	.hash		   = inet6_hash,
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
	.unhash		   = inet_unhash,
	.obj_size	   = sizeof(struct l2tp_ip6_sock),
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ipv6_setsockopt,
	.compat_getsockopt = compat_ipv6_getsockopt,
#endif
};

static const struct proto_ops l2tp_ip6_ops = {
	.family		   = PF_INET6,
	.owner		   = THIS_MODULE,
	.release	   = inet6_release,
	.bind		   = inet6_bind,
	.connect	   = inet_dgram_connect,
	.socketpair	   = sock_no_socketpair,
	.accept		   = sock_no_accept,
	.getname	   = l2tp_ip6_getname,
	.poll		   = datagram_poll,
	.ioctl		   = inet6_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	   = sock_no_sendpage,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_sock_common_setsockopt,
	.compat_getsockopt = compat_sock_common_getsockopt,
#endif
};

static struct inet_protosw l2tp_ip6_protosw = {
	.type		= SOCK_DGRAM,
	.protocol	= IPPROTO_L2TP,
	.prot		= &l2tp_ip6_prot,
	.ops		= &l2tp_ip6_ops,
};

static struct inet6_protocol l2tp_ip6_protocol __read_mostly = {
	.handler	= l2tp_ip6_recv,
};

static int __init l2tp_ip6_init(void)
{
	int err;

793
	pr_info("L2TP IP encapsulation support for IPv6 (L2TPv3)\n");
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

	err = proto_register(&l2tp_ip6_prot, 1);
	if (err != 0)
		goto out;

	err = inet6_add_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
	if (err)
		goto out1;

	inet6_register_protosw(&l2tp_ip6_protosw);
	return 0;

out1:
	proto_unregister(&l2tp_ip6_prot);
out:
	return err;
}

static void __exit l2tp_ip6_exit(void)
{
	inet6_unregister_protosw(&l2tp_ip6_protosw);
	inet6_del_protocol(&l2tp_ip6_protocol, IPPROTO_L2TP);
	proto_unregister(&l2tp_ip6_prot);
}

module_init(l2tp_ip6_init);
module_exit(l2tp_ip6_exit);

MODULE_LICENSE("GPL");
MODULE_AUTHOR("Chris Elston <celston@katalix.com>");
MODULE_DESCRIPTION("L2TP IP encapsulation for IPv6");
MODULE_VERSION("1.0");

/* Use the value of SOCK_DGRAM (2) directory, because __stringify doesn't like
 * enums
 */
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_INET6, 2, IPPROTO_L2TP);
S
stephen hemminger 已提交
831
MODULE_ALIAS_NET_PF_PROTO(PF_INET6, IPPROTO_L2TP);