route.c 53.5 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
/*
 *	Linux INET6 implementation
 *	FIB front-end.
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	$Id: route.c,v 1.56 2001/10/31 21:55:55 davem Exp $
 *
 *	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.
 */

/*	Changes:
 *
 *	YOSHIFUJI Hideaki @USAGI
 *		reworked default router selection.
 *		- respect outgoing interface
 *		- select from (probably) reachable routers (i.e.
 *		routers in REACHABLE, STALE, DELAY or PROBE states).
 *		- always select the same router if it is (probably)
 *		reachable.  otherwise, round-robin the list.
 */

27
#include <linux/capability.h>
L
Linus Torvalds 已提交
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
#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/init.h>
#include <linux/netlink.h>
#include <linux/if_arp.h>

#ifdef 	CONFIG_PROC_FS
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#endif

#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>

#include <asm/uaccess.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

/* Set to 3 to get tracing. */
#define RT6_DEBUG 2

#if RT6_DEBUG >= 3
#define RDBG(x) printk x
#define RT6_TRACE(x...) printk(KERN_DEBUG x)
#else
#define RDBG(x)
#define RT6_TRACE(x...) do { ; } while (0)
#endif

75
#define CLONE_OFFLINK_ROUTE 0
L
Linus Torvalds 已提交
76

77 78 79
#define RT6_SELECT_F_IFACE	0x1
#define RT6_SELECT_F_REACHABLE	0x2

L
Linus Torvalds 已提交
80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100
static int ip6_rt_max_size = 4096;
static int ip6_rt_gc_min_interval = HZ / 2;
static int ip6_rt_gc_timeout = 60*HZ;
int ip6_rt_gc_interval = 30*HZ;
static int ip6_rt_gc_elasticity = 9;
static int ip6_rt_mtu_expires = 10*60*HZ;
static int ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void		ip6_dst_destroy(struct dst_entry *);
static void		ip6_dst_ifdown(struct dst_entry *,
				       struct net_device *dev, int how);
static int		 ip6_dst_gc(void);

static int		ip6_pkt_discard(struct sk_buff *skb);
static int		ip6_pkt_discard_out(struct sk_buff *skb);
static void		ip6_link_failure(struct sk_buff *skb);
static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);

101 102 103 104 105 106 107 108
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref);
static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex);
#endif

L
Linus Torvalds 已提交
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
static struct dst_ops ip6_dst_ops = {
	.family			=	AF_INET6,
	.protocol		=	__constant_htons(ETH_P_IPV6),
	.gc			=	ip6_dst_gc,
	.gc_thresh		=	1024,
	.check			=	ip6_dst_check,
	.destroy		=	ip6_dst_destroy,
	.ifdown			=	ip6_dst_ifdown,
	.negative_advice	=	ip6_negative_advice,
	.link_failure		=	ip6_link_failure,
	.update_pmtu		=	ip6_rt_update_pmtu,
	.entry_size		=	sizeof(struct rt6_info),
};

struct rt6_info ip6_null_entry = {
	.u = {
		.dst = {
			.__refcnt	= ATOMIC_INIT(1),
			.__use		= 1,
			.dev		= &loopback_dev,
			.obsolete	= -1,
			.error		= -ENETUNREACH,
			.metrics	= { [RTAX_HOPLIMIT - 1] = 255, },
			.input		= ip6_pkt_discard,
			.output		= ip6_pkt_discard_out,
			.ops		= &ip6_dst_ops,
			.path		= (struct dst_entry*)&ip6_null_entry,
		}
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

struct fib6_node ip6_routing_table = {
	.leaf		= &ip6_null_entry,
	.fn_flags	= RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO,
};

/* Protects all the ip6 fib */

DEFINE_RWLOCK(rt6_lock);


/* allocate dst with ip6_dst_ops */
static __inline__ struct rt6_info *ip6_dst_alloc(void)
{
	return (struct rt6_info *)dst_alloc(&ip6_dst_ops);
}

static void ip6_dst_destroy(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;

	if (idev != NULL) {
		rt->rt6i_idev = NULL;
		in6_dev_put(idev);
	}	
}

static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			   int how)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;

	if (dev != &loopback_dev && idev != NULL && idev->dev == dev) {
		struct inet6_dev *loopback_idev = in6_dev_get(&loopback_dev);
		if (loopback_idev != NULL) {
			rt->rt6i_idev = loopback_idev;
			in6_dev_put(idev);
		}
	}
}

static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
	return (rt->rt6i_flags & RTF_EXPIRES &&
		time_after(jiffies, rt->rt6i_expires));
}

/*
 *	Route lookup. Any rt6_lock is implied.
 */

static __inline__ struct rt6_info *rt6_device_match(struct rt6_info *rt,
						    int oif,
						    int strict)
{
	struct rt6_info *local = NULL;
	struct rt6_info *sprt;

	if (oif) {
		for (sprt = rt; sprt; sprt = sprt->u.next) {
			struct net_device *dev = sprt->rt6i_dev;
			if (dev->ifindex == oif)
				return sprt;
			if (dev->flags & IFF_LOOPBACK) {
				if (sprt->rt6i_idev == NULL ||
				    sprt->rt6i_idev->dev->ifindex != oif) {
					if (strict && oif)
						continue;
					if (local && (!oif || 
						      local->rt6i_idev->dev->ifindex == oif))
						continue;
				}
				local = sprt;
			}
		}

		if (local)
			return local;

		if (strict)
			return &ip6_null_entry;
	}
	return rt;
}

229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244
#ifdef CONFIG_IPV6_ROUTER_PREF
static void rt6_probe(struct rt6_info *rt)
{
	struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL;
	/*
	 * Okay, this does not seem to be appropriate
	 * for now, however, we need to check if it
	 * is really so; aka Router Reachability Probing.
	 *
	 * Router Reachability Probe MUST be rate-limited
	 * to no more than one per minute.
	 */
	if (!neigh || (neigh->nud_state & NUD_VALID))
		return;
	read_lock_bh(&neigh->lock);
	if (!(neigh->nud_state & NUD_VALID) &&
245
	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264
		struct in6_addr mcaddr;
		struct in6_addr *target;

		neigh->updated = jiffies;
		read_unlock_bh(&neigh->lock);

		target = (struct in6_addr *)&neigh->primary_key;
		addrconf_addr_solict_mult(target, &mcaddr);
		ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
	} else
		read_unlock_bh(&neigh->lock);
}
#else
static inline void rt6_probe(struct rt6_info *rt)
{
	return;
}
#endif

L
Linus Torvalds 已提交
265
/*
266
 * Default Router Selection (RFC 2461 6.3.6)
L
Linus Torvalds 已提交
267
 */
268 269 270 271 272 273 274 275 276 277
static int inline rt6_check_dev(struct rt6_info *rt, int oif)
{
	struct net_device *dev = rt->rt6i_dev;
	if (!oif || dev->ifindex == oif)
		return 2;
	if ((dev->flags & IFF_LOOPBACK) &&
	    rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
		return 1;
	return 0;
}
L
Linus Torvalds 已提交
278

279
static int inline rt6_check_neigh(struct rt6_info *rt)
L
Linus Torvalds 已提交
280
{
281 282
	struct neighbour *neigh = rt->rt6i_nexthop;
	int m = 0;
283 284 285 286
	if (rt->rt6i_flags & RTF_NONEXTHOP ||
	    !(rt->rt6i_flags & RTF_GATEWAY))
		m = 1;
	else if (neigh) {
287 288
		read_lock_bh(&neigh->lock);
		if (neigh->nud_state & NUD_VALID)
289
			m = 2;
290
		read_unlock_bh(&neigh->lock);
L
Linus Torvalds 已提交
291
	}
292
	return m;
L
Linus Torvalds 已提交
293 294
}

295 296
static int rt6_score_route(struct rt6_info *rt, int oif,
			   int strict)
L
Linus Torvalds 已提交
297
{
298 299 300
	int m, n;
		
	m = rt6_check_dev(rt, oif);
301 302
	if (!m && (strict & RT6_SELECT_F_IFACE))
		return -1;
303 304 305
#ifdef CONFIG_IPV6_ROUTER_PREF
	m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
#endif
306 307
	n = rt6_check_neigh(rt);
	if (n > 1)
308
		m |= 16;
309
	else if (!n && strict & RT6_SELECT_F_REACHABLE)
310 311 312 313 314 315 316 317 318 319 320
		return -1;
	return m;
}

static struct rt6_info *rt6_select(struct rt6_info **head, int oif,
				   int strict)
{
	struct rt6_info *match = NULL, *last = NULL;
	struct rt6_info *rt, *rt0 = *head;
	u32 metric;
	int mpri = -1;
L
Linus Torvalds 已提交
321

322 323
	RT6_TRACE("%s(head=%p(*head=%p), oif=%d)\n",
		  __FUNCTION__, head, head ? *head : NULL, oif);
L
Linus Torvalds 已提交
324

325
	for (rt = rt0, metric = rt0->rt6i_metric;
326
	     rt && rt->rt6i_metric == metric && (!last || rt != rt0);
327 328
	     rt = rt->u.next) {
		int m;
L
Linus Torvalds 已提交
329

330
		if (rt6_check_expired(rt))
L
Linus Torvalds 已提交
331 332
			continue;

333 334 335 336
		last = rt;

		m = rt6_score_route(rt, oif, strict);
		if (m < 0)
L
Linus Torvalds 已提交
337 338
			continue;

339
		if (m > mpri) {
340
			rt6_probe(match);
341
			match = rt;
L
Linus Torvalds 已提交
342
			mpri = m;
343 344
		} else {
			rt6_probe(rt);
L
Linus Torvalds 已提交
345 346 347
		}
	}

348 349 350 351
	if (!match &&
	    (strict & RT6_SELECT_F_REACHABLE) &&
	    last && last != rt0) {
		/* no entries matched; do round-robin */
352 353
		static spinlock_t lock = SPIN_LOCK_UNLOCKED;
		spin_lock(&lock);
354 355 356
		*head = rt0->u.next;
		rt0->u.next = last->u.next;
		last->u.next = rt0;
357
		spin_unlock(&lock);
L
Linus Torvalds 已提交
358 359
	}

360 361
	RT6_TRACE("%s() => %p, score=%d\n",
		  __FUNCTION__, match, mpri);
L
Linus Torvalds 已提交
362

363
	return (match ? match : &ip6_null_entry);
L
Linus Torvalds 已提交
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
#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
		  struct in6_addr *gwaddr)
{
	struct route_info *rinfo = (struct route_info *) opt;
	struct in6_addr prefix_buf, *prefix;
	unsigned int pref;
	u32 lifetime;
	struct rt6_info *rt;

	if (len < sizeof(struct route_info)) {
		return -EINVAL;
	}

	/* Sanity check for prefix_len and length */
	if (rinfo->length > 3) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 128) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 64) {
		if (rinfo->length < 2) {
			return -EINVAL;
		}
	} else if (rinfo->prefix_len > 0) {
		if (rinfo->length < 1) {
			return -EINVAL;
		}
	}

	pref = rinfo->route_pref;
	if (pref == ICMPV6_ROUTER_PREF_INVALID)
		pref = ICMPV6_ROUTER_PREF_MEDIUM;

	lifetime = htonl(rinfo->lifetime);
	if (lifetime == 0xffffffff) {
		/* infinity */
	} else if (lifetime > 0x7fffffff/HZ) {
		/* Avoid arithmetic overflow */
		lifetime = 0x7fffffff/HZ - 1;
	}

	if (rinfo->length == 3)
		prefix = (struct in6_addr *)rinfo->prefix;
	else {
		/* this function is safe */
		ipv6_addr_prefix(&prefix_buf,
				 (struct in6_addr *)rinfo->prefix,
				 rinfo->prefix_len);
		prefix = &prefix_buf;
	}

	rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex);

	if (rt && !lifetime) {
		ip6_del_rt(rt, NULL, NULL, NULL);
		rt = NULL;
	}

	if (!rt && lifetime)
		rt = rt6_add_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
					pref);
	else if (rt)
		rt->rt6i_flags = RTF_ROUTEINFO |
				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);

	if (rt) {
		if (lifetime == 0xffffffff) {
			rt->rt6i_flags &= ~RTF_EXPIRES;
		} else {
			rt->rt6i_expires = jiffies + HZ * lifetime;
			rt->rt6i_flags |= RTF_EXPIRES;
		}
		dst_release(&rt->u.dst);
	}
	return 0;
}
#endif

L
Linus Torvalds 已提交
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
struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr,
			    int oif, int strict)
{
	struct fib6_node *fn;
	struct rt6_info *rt;

	read_lock_bh(&rt6_lock);
	fn = fib6_lookup(&ip6_routing_table, daddr, saddr);
	rt = rt6_device_match(fn->leaf, oif, strict);
	dst_hold(&rt->u.dst);
	rt->u.dst.__use++;
	read_unlock_bh(&rt6_lock);

	rt->u.dst.lastuse = jiffies;
	if (rt->u.dst.error == 0)
		return rt;
	dst_release(&rt->u.dst);
	return NULL;
}

/* ip6_ins_rt is called with FREE rt6_lock.
   It takes new route entry, the addition fails by any reason the
   route is freed. In any case, if caller does not hold it, it may
   be destroyed.
 */

470 471
int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh,
		void *_rtattr, struct netlink_skb_parms *req)
L
Linus Torvalds 已提交
472 473 474 475
{
	int err;

	write_lock_bh(&rt6_lock);
476
	err = fib6_add(&ip6_routing_table, rt, nlh, _rtattr, req);
L
Linus Torvalds 已提交
477 478 479 480 481
	write_unlock_bh(&rt6_lock);

	return err;
}

482 483
static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
				      struct in6_addr *saddr)
L
Linus Torvalds 已提交
484 485 486 487 488 489 490 491 492 493
{
	struct rt6_info *rt;

	/*
	 *	Clone the route.
	 */

	rt = ip6_rt_copy(ort);

	if (rt) {
494 495 496 497
		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
			if (rt->rt6i_dst.plen != 128 &&
			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
				rt->rt6i_flags |= RTF_ANYCAST;
L
Linus Torvalds 已提交
498
			ipv6_addr_copy(&rt->rt6i_gateway, daddr);
499
		}
L
Linus Torvalds 已提交
500

501
		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
L
Linus Torvalds 已提交
502 503 504 505 506 507 508 509 510 511 512 513 514
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->u.dst.flags |= DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
		if (rt->rt6i_src.plen && saddr) {
			ipv6_addr_copy(&rt->rt6i_src.addr, saddr);
			rt->rt6i_src.plen = 128;
		}
#endif

		rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);

515
	}
L
Linus Torvalds 已提交
516

517 518
	return rt;
}
L
Linus Torvalds 已提交
519

520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr)
{
	struct rt6_info *rt = ip6_rt_copy(ort);
	if (rt) {
		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		if (rt->rt6i_flags & RTF_REJECT)
			rt->u.dst.error = ort->u.dst.error;
		rt->u.dst.flags |= DST_HOST;
		rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop);
	}
	return rt;
}

L
Linus Torvalds 已提交
535
#define BACKTRACK() \
536
if (rt == &ip6_null_entry) { \
L
Linus Torvalds 已提交
537 538 539 540 541 542 543 544 545 546 547 548 549
       while ((fn = fn->parent) != NULL) { \
		if (fn->fn_flags & RTN_ROOT) { \
			goto out; \
		} \
		if (fn->fn_flags & RTN_RTINFO) \
			goto restart; \
	} \
}


void ip6_route_input(struct sk_buff *skb)
{
	struct fib6_node *fn;
550
	struct rt6_info *rt, *nrt;
L
Linus Torvalds 已提交
551 552
	int strict;
	int attempts = 3;
553
	int err;
554
	int reachable = RT6_SELECT_F_REACHABLE;
L
Linus Torvalds 已提交
555

556
	strict = ipv6_addr_type(&skb->nh.ipv6h->daddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0;
L
Linus Torvalds 已提交
557 558 559 560

relookup:
	read_lock_bh(&rt6_lock);

561
restart_2:
L
Linus Torvalds 已提交
562 563 564 565
	fn = fib6_lookup(&ip6_routing_table, &skb->nh.ipv6h->daddr,
			 &skb->nh.ipv6h->saddr);

restart:
566
	rt = rt6_select(&fn->leaf, skb->dev->ifindex, strict | reachable);
L
Linus Torvalds 已提交
567
	BACKTRACK();
568 569
	if (rt == &ip6_null_entry ||
	    rt->rt6i_flags & RTF_CACHE)
570
		goto out;
L
Linus Torvalds 已提交
571

572 573 574
	dst_hold(&rt->u.dst);
	read_unlock_bh(&rt6_lock);

575 576 577 578 579 580 581 582 583
	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, &skb->nh.ipv6h->daddr, &skb->nh.ipv6h->saddr);
	else {
#if CLONE_OFFLINK_ROUTE
		nrt = rt6_alloc_clone(rt, &skb->nh.ipv6h->daddr);
#else
		goto out2;
#endif
	}
584

585 586
	dst_release(&rt->u.dst);
	rt = nrt ? : &ip6_null_entry;
L
Linus Torvalds 已提交
587

588 589 590 591
	dst_hold(&rt->u.dst);
	if (nrt) {
		err = ip6_ins_rt(nrt, NULL, NULL, &NETLINK_CB(skb));
		if (!err)
L
Linus Torvalds 已提交
592 593 594
			goto out2;
	}

595 596 597 598 599 600 601 602 603 604 605
	if (--attempts <= 0)
		goto out2;

	/*
	 * Race condition! In the gap, when rt6_lock was
	 * released someone could insert this route.  Relookup.
	 */
	dst_release(&rt->u.dst);
	goto relookup;

out:
606 607 608 609
	if (reachable) {
		reachable = 0;
		goto restart_2;
	}
610 611
	dst_hold(&rt->u.dst);
	read_unlock_bh(&rt6_lock);
L
Linus Torvalds 已提交
612 613 614 615
out2:
	rt->u.dst.lastuse = jiffies;
	rt->u.dst.__use++;
	skb->dst = (struct dst_entry *) rt;
616
	return;
L
Linus Torvalds 已提交
617 618 619 620 621
}

struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl)
{
	struct fib6_node *fn;
622
	struct rt6_info *rt, *nrt;
L
Linus Torvalds 已提交
623 624
	int strict;
	int attempts = 3;
625
	int err;
626
	int reachable = RT6_SELECT_F_REACHABLE;
L
Linus Torvalds 已提交
627

628
	strict = ipv6_addr_type(&fl->fl6_dst) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL) ? RT6_SELECT_F_IFACE : 0;
L
Linus Torvalds 已提交
629 630 631 632

relookup:
	read_lock_bh(&rt6_lock);

633
restart_2:
L
Linus Torvalds 已提交
634 635 636
	fn = fib6_lookup(&ip6_routing_table, &fl->fl6_dst, &fl->fl6_src);

restart:
637
	rt = rt6_select(&fn->leaf, fl->oif, strict | reachable);
638
	BACKTRACK();
639 640
	if (rt == &ip6_null_entry ||
	    rt->rt6i_flags & RTF_CACHE)
L
Linus Torvalds 已提交
641 642
		goto out;

643 644 645
	dst_hold(&rt->u.dst);
	read_unlock_bh(&rt6_lock);

646
	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
647
		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
648 649 650 651 652 653 654
	else {
#if CLONE_OFFLINK_ROUTE
		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
#else
		goto out2;
#endif
	}
L
Linus Torvalds 已提交
655

656 657
	dst_release(&rt->u.dst);
	rt = nrt ? : &ip6_null_entry;
L
Linus Torvalds 已提交
658

659 660 661 662
	dst_hold(&rt->u.dst);
	if (nrt) {
		err = ip6_ins_rt(nrt, NULL, NULL, NULL);
		if (!err)
L
Linus Torvalds 已提交
663 664
			goto out2;
	}
665

666 667 668 669 670 671 672 673 674 675 676
	if (--attempts <= 0)
		goto out2;

	/*
	 * Race condition! In the gap, when rt6_lock was
	 * released someone could insert this route.  Relookup.
	 */
	dst_release(&rt->u.dst);
	goto relookup;

out:
677 678 679 680
	if (reachable) {
		reachable = 0;
		goto restart_2;
	}
681 682
	dst_hold(&rt->u.dst);
	read_unlock_bh(&rt6_lock);
L
Linus Torvalds 已提交
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
out2:
	rt->u.dst.lastuse = jiffies;
	rt->u.dst.__use++;
	return &rt->u.dst;
}


/*
 *	Destination cache support functions
 */

static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
	struct rt6_info *rt;

	rt = (struct rt6_info *) dst;

	if (rt && rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
		return dst;

	return NULL;
}

static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *) dst;

	if (rt) {
		if (rt->rt6i_flags & RTF_CACHE)
712
			ip6_del_rt(rt, NULL, NULL, NULL);
L
Linus Torvalds 已提交
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
		else
			dst_release(dst);
	}
	return NULL;
}

static void ip6_link_failure(struct sk_buff *skb)
{
	struct rt6_info *rt;

	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0, skb->dev);

	rt = (struct rt6_info *) skb->dst;
	if (rt) {
		if (rt->rt6i_flags&RTF_CACHE) {
			dst_set_expires(&rt->u.dst, 0);
			rt->rt6i_flags |= RTF_EXPIRES;
		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
			rt->rt6i_node->fn_sernum = -1;
	}
}

static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
	struct rt6_info *rt6 = (struct rt6_info*)dst;

	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
		rt6->rt6i_flags |= RTF_MODIFIED;
		if (mtu < IPV6_MIN_MTU) {
			mtu = IPV6_MIN_MTU;
			dst->metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
		}
		dst->metrics[RTAX_MTU-1] = mtu;
	}
}

/* Protected by rt6_lock.  */
static struct dst_entry *ndisc_dst_gc_list;
static int ipv6_get_mtu(struct net_device *dev);

static inline unsigned int ipv6_advmss(unsigned int mtu)
{
	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);

	if (mtu < ip6_rt_min_advmss)
		mtu = ip6_rt_min_advmss;

	/*
	 * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and 
	 * corresponding MSS is IPV6_MAXPLEN - tcp_header_size. 
	 * IPV6_MAXPLEN is also valid and means: "any MSS, 
	 * rely only on pmtu discovery"
	 */
	if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr))
		mtu = IPV6_MAXPLEN;
	return mtu;
}

struct dst_entry *ndisc_dst_alloc(struct net_device *dev, 
				  struct neighbour *neigh,
				  struct in6_addr *addr,
				  int (*output)(struct sk_buff *))
{
	struct rt6_info *rt;
	struct inet6_dev *idev = in6_dev_get(dev);

	if (unlikely(idev == NULL))
		return NULL;

	rt = ip6_dst_alloc();
	if (unlikely(rt == NULL)) {
		in6_dev_put(idev);
		goto out;
	}

	dev_hold(dev);
	if (neigh)
		neigh_hold(neigh);
	else
		neigh = ndisc_get_neigh(dev, addr);

	rt->rt6i_dev	  = dev;
	rt->rt6i_idev     = idev;
	rt->rt6i_nexthop  = neigh;
	atomic_set(&rt->u.dst.__refcnt, 1);
	rt->u.dst.metrics[RTAX_HOPLIMIT-1] = 255;
	rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
	rt->u.dst.output  = output;

#if 0	/* there's no chance to use these for ndisc */
	rt->u.dst.flags   = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST 
				? DST_HOST 
				: 0;
	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
#endif

	write_lock_bh(&rt6_lock);
	rt->u.dst.next = ndisc_dst_gc_list;
	ndisc_dst_gc_list = &rt->u.dst;
	write_unlock_bh(&rt6_lock);

	fib6_force_start_gc();

out:
	return (struct dst_entry *)rt;
}

int ndisc_dst_gc(int *more)
{
	struct dst_entry *dst, *next, **pprev;
	int freed;

	next = NULL;
	pprev = &ndisc_dst_gc_list;
	freed = 0;
	while ((dst = *pprev) != NULL) {
		if (!atomic_read(&dst->__refcnt)) {
			*pprev = dst->next;
			dst_free(dst);
			freed++;
		} else {
			pprev = &dst->next;
			(*more)++;
		}
	}

	return freed;
}

static int ip6_dst_gc(void)
{
	static unsigned expire = 30*HZ;
	static unsigned long last_gc;
	unsigned long now = jiffies;

	if (time_after(last_gc + ip6_rt_gc_min_interval, now) &&
	    atomic_read(&ip6_dst_ops.entries) <= ip6_rt_max_size)
		goto out;

	expire++;
	fib6_run_gc(expire);
	last_gc = now;
	if (atomic_read(&ip6_dst_ops.entries) < ip6_dst_ops.gc_thresh)
		expire = ip6_rt_gc_timeout>>1;

out:
	expire -= expire>>ip6_rt_gc_elasticity;
	return (atomic_read(&ip6_dst_ops.entries) > ip6_rt_max_size);
}

/* Clean host part of a prefix. Not necessary in radix tree,
   but results in cleaner routing tables.

   Remove it only when all the things will work!
 */

static int ipv6_get_mtu(struct net_device *dev)
{
	int mtu = IPV6_MIN_MTU;
	struct inet6_dev *idev;

	idev = in6_dev_get(dev);
	if (idev) {
		mtu = idev->cnf.mtu6;
		in6_dev_put(idev);
	}
	return mtu;
}

int ipv6_get_hoplimit(struct net_device *dev)
{
	int hoplimit = ipv6_devconf.hop_limit;
	struct inet6_dev *idev;

	idev = in6_dev_get(dev);
	if (idev) {
		hoplimit = idev->cnf.hop_limit;
		in6_dev_put(idev);
	}
	return hoplimit;
}

/*
 *
 */

901 902
int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, 
		void *_rtattr, struct netlink_skb_parms *req)
L
Linus Torvalds 已提交
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
{
	int err;
	struct rtmsg *r;
	struct rtattr **rta;
	struct rt6_info *rt = NULL;
	struct net_device *dev = NULL;
	struct inet6_dev *idev = NULL;
	int addr_type;

	rta = (struct rtattr **) _rtattr;

	if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128)
		return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
	if (rtmsg->rtmsg_src_len)
		return -EINVAL;
#endif
	if (rtmsg->rtmsg_ifindex) {
		err = -ENODEV;
		dev = dev_get_by_index(rtmsg->rtmsg_ifindex);
		if (!dev)
			goto out;
		idev = in6_dev_get(dev);
		if (!idev)
			goto out;
	}

	if (rtmsg->rtmsg_metric == 0)
		rtmsg->rtmsg_metric = IP6_RT_PRIO_USER;

	rt = ip6_dst_alloc();

	if (rt == NULL) {
		err = -ENOMEM;
		goto out;
	}

	rt->u.dst.obsolete = -1;
Y
YOSHIFUJI Hideaki 已提交
941
	rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info);
L
Linus Torvalds 已提交
942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 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
	if (nlh && (r = NLMSG_DATA(nlh))) {
		rt->rt6i_protocol = r->rtm_protocol;
	} else {
		rt->rt6i_protocol = RTPROT_BOOT;
	}

	addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst);

	if (addr_type & IPV6_ADDR_MULTICAST)
		rt->u.dst.input = ip6_mc_input;
	else
		rt->u.dst.input = ip6_forward;

	rt->u.dst.output = ip6_output;

	ipv6_addr_prefix(&rt->rt6i_dst.addr, 
			 &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len);
	rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len;
	if (rt->rt6i_dst.plen == 128)
	       rt->u.dst.flags = DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
	ipv6_addr_prefix(&rt->rt6i_src.addr, 
			 &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
	rt->rt6i_src.plen = rtmsg->rtmsg_src_len;
#endif

	rt->rt6i_metric = rtmsg->rtmsg_metric;

	/* We cannot add true routes via loopback here,
	   they would result in kernel looping; promote them to reject routes
	 */
	if ((rtmsg->rtmsg_flags&RTF_REJECT) ||
	    (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) {
		/* hold loopback dev/idev if we haven't done so. */
		if (dev != &loopback_dev) {
			if (dev) {
				dev_put(dev);
				in6_dev_put(idev);
			}
			dev = &loopback_dev;
			dev_hold(dev);
			idev = in6_dev_get(dev);
			if (!idev) {
				err = -ENODEV;
				goto out;
			}
		}
		rt->u.dst.output = ip6_pkt_discard_out;
		rt->u.dst.input = ip6_pkt_discard;
		rt->u.dst.error = -ENETUNREACH;
		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
		goto install_route;
	}

	if (rtmsg->rtmsg_flags & RTF_GATEWAY) {
		struct in6_addr *gw_addr;
		int gwa_type;

		gw_addr = &rtmsg->rtmsg_gateway;
		ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway);
		gwa_type = ipv6_addr_type(gw_addr);

		if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
			struct rt6_info *grt;

			/* IPv6 strictly inhibits using not link-local
			   addresses as nexthop address.
			   Otherwise, router will not able to send redirects.
			   It is very good, but in some (rare!) circumstances
			   (SIT, PtP, NBMA NOARP links) it is handy to allow
			   some exceptions. --ANK
			 */
			err = -EINVAL;
			if (!(gwa_type&IPV6_ADDR_UNICAST))
				goto out;

			grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1);

			err = -EHOSTUNREACH;
			if (grt == NULL)
				goto out;
			if (dev) {
				if (dev != grt->rt6i_dev) {
					dst_release(&grt->u.dst);
					goto out;
				}
			} else {
				dev = grt->rt6i_dev;
				idev = grt->rt6i_idev;
				dev_hold(dev);
				in6_dev_hold(grt->rt6i_idev);
			}
			if (!(grt->rt6i_flags&RTF_GATEWAY))
				err = 0;
			dst_release(&grt->u.dst);

			if (err)
				goto out;
		}
		err = -EINVAL;
		if (dev == NULL || (dev->flags&IFF_LOOPBACK))
			goto out;
	}

	err = -ENODEV;
	if (dev == NULL)
		goto out;

	if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) {
		rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
		if (IS_ERR(rt->rt6i_nexthop)) {
			err = PTR_ERR(rt->rt6i_nexthop);
			rt->rt6i_nexthop = NULL;
			goto out;
		}
	}

	rt->rt6i_flags = rtmsg->rtmsg_flags;

install_route:
	if (rta && rta[RTA_METRICS-1]) {
		int attrlen = RTA_PAYLOAD(rta[RTA_METRICS-1]);
		struct rtattr *attr = RTA_DATA(rta[RTA_METRICS-1]);

		while (RTA_OK(attr, attrlen)) {
			unsigned flavor = attr->rta_type;
			if (flavor) {
				if (flavor > RTAX_MAX) {
					err = -EINVAL;
					goto out;
				}
				rt->u.dst.metrics[flavor-1] =
					*(u32 *)RTA_DATA(attr);
			}
			attr = RTA_NEXT(attr, attrlen);
		}
	}

	if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0)
		rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
	if (!rt->u.dst.metrics[RTAX_MTU-1])
		rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(dev);
	if (!rt->u.dst.metrics[RTAX_ADVMSS-1])
		rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
	rt->u.dst.dev = dev;
	rt->rt6i_idev = idev;
1089
	return ip6_ins_rt(rt, nlh, _rtattr, req);
L
Linus Torvalds 已提交
1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100

out:
	if (dev)
		dev_put(dev);
	if (idev)
		in6_dev_put(idev);
	if (rt)
		dst_free((struct dst_entry *) rt);
	return err;
}

1101
int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
L
Linus Torvalds 已提交
1102 1103 1104 1105 1106
{
	int err;

	write_lock_bh(&rt6_lock);

1107
	err = fib6_del(rt, nlh, _rtattr, req);
L
Linus Torvalds 已提交
1108 1109 1110 1111 1112 1113 1114
	dst_release(&rt->u.dst);

	write_unlock_bh(&rt6_lock);

	return err;
}

1115
static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req)
L
Linus Torvalds 已提交
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
{
	struct fib6_node *fn;
	struct rt6_info *rt;
	int err = -ESRCH;

	read_lock_bh(&rt6_lock);

	fn = fib6_locate(&ip6_routing_table,
			 &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len,
			 &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len);
	
	if (fn) {
		for (rt = fn->leaf; rt; rt = rt->u.next) {
			if (rtmsg->rtmsg_ifindex &&
			    (rt->rt6i_dev == NULL ||
			     rt->rt6i_dev->ifindex != rtmsg->rtmsg_ifindex))
				continue;
			if (rtmsg->rtmsg_flags&RTF_GATEWAY &&
			    !ipv6_addr_equal(&rtmsg->rtmsg_gateway, &rt->rt6i_gateway))
				continue;
			if (rtmsg->rtmsg_metric &&
			    rtmsg->rtmsg_metric != rt->rt6i_metric)
				continue;
			dst_hold(&rt->u.dst);
			read_unlock_bh(&rt6_lock);

1142
			return ip6_del_rt(rt, nlh, _rtattr, req);
L
Linus Torvalds 已提交
1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155
		}
	}
	read_unlock_bh(&rt6_lock);

	return err;
}

/*
 *	Handle redirects
 */
void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr,
		  struct neighbour *neigh, u8 *lladdr, int on_link)
{
1156 1157 1158
	struct rt6_info *rt, *nrt = NULL;
	int strict;
	struct fib6_node *fn;
L
Linus Torvalds 已提交
1159 1160

	/*
1161 1162 1163 1164 1165 1166 1167 1168
	 * Get the "current" route for this destination and
	 * check if the redirect has come from approriate router.
	 *
	 * RFC 2461 specifies that redirects should only be
	 * accepted if they come from the nexthop to the target.
	 * Due to the way the routes are chosen, this notion
	 * is a bit fuzzy and one might need to check all possible
	 * routes.
L
Linus Torvalds 已提交
1169
	 */
1170
	strict = ipv6_addr_type(dest) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL);
L
Linus Torvalds 已提交
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
	read_lock_bh(&rt6_lock);
	fn = fib6_lookup(&ip6_routing_table, dest, NULL);
restart:
	for (rt = fn->leaf; rt; rt = rt->u.next) {
		/*
		 * Current route is on-link; redirect is always invalid.
		 *
		 * Seems, previous statement is not true. It could
		 * be node, which looks for us as on-link (f.e. proxy ndisc)
		 * But then router serving it might decide, that we should
		 * know truth 8)8) --ANK (980726).
		 */
		if (rt6_check_expired(rt))
			continue;
		if (!(rt->rt6i_flags & RTF_GATEWAY))
			continue;
		if (neigh->dev != rt->rt6i_dev)
			continue;
		if (!ipv6_addr_equal(saddr, &rt->rt6i_gateway))
			continue;
		break;
	}
	if (rt)
		dst_hold(&rt->u.dst);
	else if (strict) {
		while ((fn = fn->parent) != NULL) {
			if (fn->fn_flags & RTN_ROOT)
				break;
			if (fn->fn_flags & RTN_RTINFO)
				goto restart;
L
Linus Torvalds 已提交
1202
		}
1203 1204 1205 1206
	}
	read_unlock_bh(&rt6_lock);

	if (!rt) {
L
Linus Torvalds 已提交
1207 1208 1209
		if (net_ratelimit())
			printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
			       "for redirect target\n");
1210
		return;
L
Linus Torvalds 已提交
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
	}

	/*
	 *	We have finally decided to accept it.
	 */

	neigh_update(neigh, lladdr, NUD_STALE, 
		     NEIGH_UPDATE_F_WEAK_OVERRIDE|
		     NEIGH_UPDATE_F_OVERRIDE|
		     (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
				     NEIGH_UPDATE_F_ISROUTER))
		     );

	/*
	 * Redirect received -> path was valid.
	 * Look, redirects are sent only in response to data packets,
	 * so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->u.dst);

	/* Duplicate redirect: silently ignore. */
	if (neigh == rt->u.dst.neighbour)
		goto out;

	nrt = ip6_rt_copy(rt);
	if (nrt == NULL)
		goto out;

	nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
	if (on_link)
		nrt->rt6i_flags &= ~RTF_GATEWAY;

	ipv6_addr_copy(&nrt->rt6i_dst.addr, dest);
	nrt->rt6i_dst.plen = 128;
	nrt->u.dst.flags |= DST_HOST;

	ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
	nrt->rt6i_nexthop = neigh_clone(neigh);
	/* Reset pmtu, it may be better */
	nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev);
	nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst));

1253
	if (ip6_ins_rt(nrt, NULL, NULL, NULL))
L
Linus Torvalds 已提交
1254 1255 1256
		goto out;

	if (rt->rt6i_flags&RTF_CACHE) {
1257
		ip6_del_rt(rt, NULL, NULL, NULL);
L
Linus Torvalds 已提交
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
		return;
	}

out:
        dst_release(&rt->u.dst);
	return;
}

/*
 *	Handle ICMP "packet too big" messages
 *	i.e. Path MTU discovery
 */

void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
			struct net_device *dev, u32 pmtu)
{
	struct rt6_info *rt, *nrt;
	int allfrag = 0;

	rt = rt6_lookup(daddr, saddr, dev->ifindex, 0);
	if (rt == NULL)
		return;

	if (pmtu >= dst_mtu(&rt->u.dst))
		goto out;

	if (pmtu < IPV6_MIN_MTU) {
		/*
		 * According to RFC2460, PMTU is set to the IPv6 Minimum Link 
		 * MTU (1280) and a fragment header should always be included
		 * after a node receiving Too Big message reporting PMTU is
		 * less than the IPv6 Minimum Link MTU.
		 */
		pmtu = IPV6_MIN_MTU;
		allfrag = 1;
	}

	/* New mtu received -> path was valid.
	   They are sent only in response to data packets,
	   so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->u.dst);

	/* Host route. If it is static, it would be better
	   not to override it, but add new one, so that
	   when cache entry will expire old pmtu
	   would return automatically.
	 */
	if (rt->rt6i_flags & RTF_CACHE) {
		rt->u.dst.metrics[RTAX_MTU-1] = pmtu;
		if (allfrag)
			rt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;
		dst_set_expires(&rt->u.dst, ip6_rt_mtu_expires);
		rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
		goto out;
	}

	/* Network route.
	   Two cases are possible:
	   1. It is connected route. Action: COW
	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
	 */
1320
	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
1321
		nrt = rt6_alloc_cow(rt, daddr, saddr);
1322 1323
	else
		nrt = rt6_alloc_clone(rt, daddr);
1324

1325
	if (nrt) {
1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339
		nrt->u.dst.metrics[RTAX_MTU-1] = pmtu;
		if (allfrag)
			nrt->u.dst.metrics[RTAX_FEATURES-1] |= RTAX_FEATURE_ALLFRAG;

		/* According to RFC 1981, detecting PMTU increase shouldn't be
		 * happened within 5 mins, the recommended timer is 10 mins.
		 * Here this route expiration time is set to ip6_rt_mtu_expires
		 * which is 10 mins. After 10 mins the decreased pmtu is expired
		 * and detecting PMTU increase will be automatically happened.
		 */
		dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires);
		nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;

		ip6_ins_rt(nrt, NULL, NULL, NULL);
L
Linus Torvalds 已提交
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
	}
out:
	dst_release(&rt->u.dst);
}

/*
 *	Misc support functions
 */

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
	struct rt6_info *rt = ip6_dst_alloc();

	if (rt) {
		rt->u.dst.input = ort->u.dst.input;
		rt->u.dst.output = ort->u.dst.output;

		memcpy(rt->u.dst.metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));
		rt->u.dst.dev = ort->u.dst.dev;
		if (rt->u.dst.dev)
			dev_hold(rt->u.dst.dev);
		rt->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->u.dst.lastuse = jiffies;
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		rt->rt6i_metric = 0;

		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
		memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
	}
	return rt;
}

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
#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex)
{
	struct fib6_node *fn;
	struct rt6_info *rt = NULL;

	write_lock_bh(&rt6_lock);
	fn = fib6_locate(&ip6_routing_table, prefix ,prefixlen, NULL, 0);
	if (!fn)
		goto out;

	for (rt = fn->leaf; rt; rt = rt->u.next) {
		if (rt->rt6i_dev->ifindex != ifindex)
			continue;
		if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
			continue;
		if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
			continue;
		dst_hold(&rt->u.dst);
		break;
	}
out:
	write_unlock_bh(&rt6_lock);
	return rt;
}

static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref)
{
	struct in6_rtmsg rtmsg;

	memset(&rtmsg, 0, sizeof(rtmsg));
	rtmsg.rtmsg_type = RTMSG_NEWROUTE;
	ipv6_addr_copy(&rtmsg.rtmsg_dst, prefix);
	rtmsg.rtmsg_dst_len = prefixlen;
	ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr);
	rtmsg.rtmsg_metric = 1024;
	rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref);
1419 1420 1421
	/* We should treat it as a default route if prefix length is 0. */
	if (!prefixlen)
		rtmsg.rtmsg_flags |= RTF_DEFAULT;
1422 1423 1424 1425 1426 1427 1428 1429
	rtmsg.rtmsg_ifindex = ifindex;

	ip6_route_add(&rtmsg, NULL, NULL, NULL);

	return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex);
}
#endif

L
Linus Torvalds 已提交
1430 1431 1432 1433 1434 1435 1436 1437 1438 1439
struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
{	
	struct rt6_info *rt;
	struct fib6_node *fn;

	fn = &ip6_routing_table;

	write_lock_bh(&rt6_lock);
	for (rt = fn->leaf; rt; rt=rt->u.next) {
		if (dev == rt->rt6i_dev &&
1440
		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
L
Linus Torvalds 已提交
1441 1442 1443 1444 1445 1446 1447 1448 1449 1450
		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
			break;
	}
	if (rt)
		dst_hold(&rt->u.dst);
	write_unlock_bh(&rt6_lock);
	return rt;
}

struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
1451 1452
				     struct net_device *dev,
				     unsigned int pref)
L
Linus Torvalds 已提交
1453 1454 1455 1456 1457 1458 1459
{
	struct in6_rtmsg rtmsg;

	memset(&rtmsg, 0, sizeof(struct in6_rtmsg));
	rtmsg.rtmsg_type = RTMSG_NEWROUTE;
	ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr);
	rtmsg.rtmsg_metric = 1024;
1460 1461
	rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES |
			    RTF_PREF(pref);
L
Linus Torvalds 已提交
1462 1463 1464

	rtmsg.rtmsg_ifindex = dev->ifindex;

1465
	ip6_route_add(&rtmsg, NULL, NULL, NULL);
L
Linus Torvalds 已提交
1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480
	return rt6_get_dflt_router(gwaddr, dev);
}

void rt6_purge_dflt_routers(void)
{
	struct rt6_info *rt;

restart:
	read_lock_bh(&rt6_lock);
	for (rt = ip6_routing_table.leaf; rt; rt = rt->u.next) {
		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
			dst_hold(&rt->u.dst);

			read_unlock_bh(&rt6_lock);

1481
			ip6_del_rt(rt, NULL, NULL, NULL);
L
Linus Torvalds 已提交
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

			goto restart;
		}
	}
	read_unlock_bh(&rt6_lock);
}

int ipv6_route_ioctl(unsigned int cmd, void __user *arg)
{
	struct in6_rtmsg rtmsg;
	int err;

	switch(cmd) {
	case SIOCADDRT:		/* Add a route */
	case SIOCDELRT:		/* Delete a route */
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		err = copy_from_user(&rtmsg, arg,
				     sizeof(struct in6_rtmsg));
		if (err)
			return -EFAULT;
			
		rtnl_lock();
		switch (cmd) {
		case SIOCADDRT:
1507
			err = ip6_route_add(&rtmsg, NULL, NULL, NULL);
L
Linus Torvalds 已提交
1508 1509
			break;
		case SIOCDELRT:
1510
			err = ip6_route_del(&rtmsg, NULL, NULL, NULL);
L
Linus Torvalds 已提交
1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526
			break;
		default:
			err = -EINVAL;
		}
		rtnl_unlock();

		return err;
	};

	return -EINVAL;
}

/*
 *	Drop the packet on the floor
 */

1527
static int ip6_pkt_discard(struct sk_buff *skb)
L
Linus Torvalds 已提交
1528 1529 1530 1531 1532 1533 1534
{
	IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_NOROUTE, 0, skb->dev);
	kfree_skb(skb);
	return 0;
}

1535
static int ip6_pkt_discard_out(struct sk_buff *skb)
L
Linus Torvalds 已提交
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
{
	skb->dev = skb->dst->dev;
	return ip6_pkt_discard(skb);
}

/*
 *	Allocate a dst for local (unicast / anycast) address.
 */

struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
				    const struct in6_addr *addr,
				    int anycast)
{
	struct rt6_info *rt = ip6_dst_alloc();

	if (rt == NULL)
		return ERR_PTR(-ENOMEM);

	dev_hold(&loopback_dev);
	in6_dev_hold(idev);

	rt->u.dst.flags = DST_HOST;
	rt->u.dst.input = ip6_input;
	rt->u.dst.output = ip6_output;
	rt->rt6i_dev = &loopback_dev;
	rt->rt6i_idev = idev;
	rt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(rt->rt6i_dev);
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&rt->u.dst));
	rt->u.dst.metrics[RTAX_HOPLIMIT-1] = -1;
	rt->u.dst.obsolete = -1;

	rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
1568 1569 1570
	if (anycast)
		rt->rt6i_flags |= RTF_ANYCAST;
	else
L
Linus Torvalds 已提交
1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705
		rt->rt6i_flags |= RTF_LOCAL;
	rt->rt6i_nexthop = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
	if (rt->rt6i_nexthop == NULL) {
		dst_free((struct dst_entry *) rt);
		return ERR_PTR(-ENOMEM);
	}

	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;

	atomic_set(&rt->u.dst.__refcnt, 1);

	return rt;
}

static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
	if (((void*)rt->rt6i_dev == arg || arg == NULL) &&
	    rt != &ip6_null_entry) {
		RT6_TRACE("deleted by ifdown %p\n", rt);
		return -1;
	}
	return 0;
}

void rt6_ifdown(struct net_device *dev)
{
	write_lock_bh(&rt6_lock);
	fib6_clean_tree(&ip6_routing_table, fib6_ifdown, 0, dev);
	write_unlock_bh(&rt6_lock);
}

struct rt6_mtu_change_arg
{
	struct net_device *dev;
	unsigned mtu;
};

static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
	struct inet6_dev *idev;

	/* In IPv6 pmtu discovery is not optional,
	   so that RTAX_MTU lock cannot disable it.
	   We still use this lock to block changes
	   caused by addrconf/ndisc.
	*/

	idev = __in6_dev_get(arg->dev);
	if (idev == NULL)
		return 0;

	/* For administrative MTU increase, there is no way to discover
	   IPv6 PMTU increase, so PMTU increase should be updated here.
	   Since RFC 1981 doesn't include administrative MTU increase
	   update PMTU increase is a MUST. (i.e. jumbo frame)
	 */
	/*
	   If new MTU is less than route PMTU, this new MTU will be the
	   lowest MTU in the path, update the route PMTU to reflect PMTU
	   decreases; if new MTU is greater than route PMTU, and the
	   old MTU is the lowest MTU in the path, update the route PMTU
	   to reflect the increase. In this case if the other nodes' MTU
	   also have the lowest MTU, TOO BIG MESSAGE will be lead to
	   PMTU discouvery.
	 */
	if (rt->rt6i_dev == arg->dev &&
	    !dst_metric_locked(&rt->u.dst, RTAX_MTU) &&
            (dst_mtu(&rt->u.dst) > arg->mtu ||
             (dst_mtu(&rt->u.dst) < arg->mtu &&
	      dst_mtu(&rt->u.dst) == idev->cnf.mtu6)))
		rt->u.dst.metrics[RTAX_MTU-1] = arg->mtu;
	rt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(arg->mtu);
	return 0;
}

void rt6_mtu_change(struct net_device *dev, unsigned mtu)
{
	struct rt6_mtu_change_arg arg;

	arg.dev = dev;
	arg.mtu = mtu;
	read_lock_bh(&rt6_lock);
	fib6_clean_tree(&ip6_routing_table, rt6_mtu_change_route, 0, &arg);
	read_unlock_bh(&rt6_lock);
}

static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta,
			      struct in6_rtmsg *rtmsg)
{
	memset(rtmsg, 0, sizeof(*rtmsg));

	rtmsg->rtmsg_dst_len = r->rtm_dst_len;
	rtmsg->rtmsg_src_len = r->rtm_src_len;
	rtmsg->rtmsg_flags = RTF_UP;
	if (r->rtm_type == RTN_UNREACHABLE)
		rtmsg->rtmsg_flags |= RTF_REJECT;

	if (rta[RTA_GATEWAY-1]) {
		if (rta[RTA_GATEWAY-1]->rta_len != RTA_LENGTH(16))
			return -EINVAL;
		memcpy(&rtmsg->rtmsg_gateway, RTA_DATA(rta[RTA_GATEWAY-1]), 16);
		rtmsg->rtmsg_flags |= RTF_GATEWAY;
	}
	if (rta[RTA_DST-1]) {
		if (RTA_PAYLOAD(rta[RTA_DST-1]) < ((r->rtm_dst_len+7)>>3))
			return -EINVAL;
		memcpy(&rtmsg->rtmsg_dst, RTA_DATA(rta[RTA_DST-1]), ((r->rtm_dst_len+7)>>3));
	}
	if (rta[RTA_SRC-1]) {
		if (RTA_PAYLOAD(rta[RTA_SRC-1]) < ((r->rtm_src_len+7)>>3))
			return -EINVAL;
		memcpy(&rtmsg->rtmsg_src, RTA_DATA(rta[RTA_SRC-1]), ((r->rtm_src_len+7)>>3));
	}
	if (rta[RTA_OIF-1]) {
		if (rta[RTA_OIF-1]->rta_len != RTA_LENGTH(sizeof(int)))
			return -EINVAL;
		memcpy(&rtmsg->rtmsg_ifindex, RTA_DATA(rta[RTA_OIF-1]), sizeof(int));
	}
	if (rta[RTA_PRIORITY-1]) {
		if (rta[RTA_PRIORITY-1]->rta_len != RTA_LENGTH(4))
			return -EINVAL;
		memcpy(&rtmsg->rtmsg_metric, RTA_DATA(rta[RTA_PRIORITY-1]), 4);
	}
	return 0;
}

int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtmsg *r = NLMSG_DATA(nlh);
	struct in6_rtmsg rtmsg;

	if (inet6_rtm_to_rtmsg(r, arg, &rtmsg))
		return -EINVAL;
1706
	return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb));
L
Linus Torvalds 已提交
1707 1708 1709 1710 1711 1712 1713 1714 1715
}

int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtmsg *r = NLMSG_DATA(nlh);
	struct in6_rtmsg rtmsg;

	if (inet6_rtm_to_rtmsg(r, arg, &rtmsg))
		return -EINVAL;
1716
	return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb));
L
Linus Torvalds 已提交
1717 1718 1719 1720 1721 1722 1723 1724 1725
}

struct rt6_rtnl_dump_arg
{
	struct sk_buff *skb;
	struct netlink_callback *cb;
};

static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt,
1726 1727 1728
			 struct in6_addr *dst, struct in6_addr *src,
			 int iif, int type, u32 pid, u32 seq,
			 int prefix, unsigned int flags)
L
Linus Torvalds 已提交
1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741
{
	struct rtmsg *rtm;
	struct nlmsghdr  *nlh;
	unsigned char	 *b = skb->tail;
	struct rta_cacheinfo ci;

	if (prefix) {	/* user wants prefix routes only */
		if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
			/* success since this is not a prefix route */
			return 1;
		}
	}

1742
	nlh = NLMSG_NEW(skb, pid, seq, type, sizeof(*rtm), flags);
L
Linus Torvalds 已提交
1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827
	rtm = NLMSG_DATA(nlh);
	rtm->rtm_family = AF_INET6;
	rtm->rtm_dst_len = rt->rt6i_dst.plen;
	rtm->rtm_src_len = rt->rt6i_src.plen;
	rtm->rtm_tos = 0;
	rtm->rtm_table = RT_TABLE_MAIN;
	if (rt->rt6i_flags&RTF_REJECT)
		rtm->rtm_type = RTN_UNREACHABLE;
	else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
		rtm->rtm_type = RTN_LOCAL;
	else
		rtm->rtm_type = RTN_UNICAST;
	rtm->rtm_flags = 0;
	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
	rtm->rtm_protocol = rt->rt6i_protocol;
	if (rt->rt6i_flags&RTF_DYNAMIC)
		rtm->rtm_protocol = RTPROT_REDIRECT;
	else if (rt->rt6i_flags & RTF_ADDRCONF)
		rtm->rtm_protocol = RTPROT_KERNEL;
	else if (rt->rt6i_flags&RTF_DEFAULT)
		rtm->rtm_protocol = RTPROT_RA;

	if (rt->rt6i_flags&RTF_CACHE)
		rtm->rtm_flags |= RTM_F_CLONED;

	if (dst) {
		RTA_PUT(skb, RTA_DST, 16, dst);
	        rtm->rtm_dst_len = 128;
	} else if (rtm->rtm_dst_len)
		RTA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
	if (src) {
		RTA_PUT(skb, RTA_SRC, 16, src);
	        rtm->rtm_src_len = 128;
	} else if (rtm->rtm_src_len)
		RTA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
#endif
	if (iif)
		RTA_PUT(skb, RTA_IIF, 4, &iif);
	else if (dst) {
		struct in6_addr saddr_buf;
		if (ipv6_get_saddr(&rt->u.dst, dst, &saddr_buf) == 0)
			RTA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
	}
	if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
		goto rtattr_failure;
	if (rt->u.dst.neighbour)
		RTA_PUT(skb, RTA_GATEWAY, 16, &rt->u.dst.neighbour->primary_key);
	if (rt->u.dst.dev)
		RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->rt6i_dev->ifindex);
	RTA_PUT(skb, RTA_PRIORITY, 4, &rt->rt6i_metric);
	ci.rta_lastuse = jiffies_to_clock_t(jiffies - rt->u.dst.lastuse);
	if (rt->rt6i_expires)
		ci.rta_expires = jiffies_to_clock_t(rt->rt6i_expires - jiffies);
	else
		ci.rta_expires = 0;
	ci.rta_used = rt->u.dst.__use;
	ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt);
	ci.rta_error = rt->u.dst.error;
	ci.rta_id = 0;
	ci.rta_ts = 0;
	ci.rta_tsage = 0;
	RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci);
	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

static int rt6_dump_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
	int prefix;

	if (arg->cb->nlh->nlmsg_len >= NLMSG_LENGTH(sizeof(struct rtmsg))) {
		struct rtmsg *rtm = NLMSG_DATA(arg->cb->nlh);
		prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0;
	} else
		prefix = 0;

	return rt6_fill_node(arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
		     NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq,
1828
		     prefix, NLM_F_MULTI);
L
Linus Torvalds 已提交
1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857
}

static int fib6_dump_node(struct fib6_walker_t *w)
{
	int res;
	struct rt6_info *rt;

	for (rt = w->leaf; rt; rt = rt->u.next) {
		res = rt6_dump_route(rt, w->args);
		if (res < 0) {
			/* Frame is full, suspend walking */
			w->leaf = rt;
			return 1;
		}
		BUG_TRAP(res!=0);
	}
	w->leaf = NULL;
	return 0;
}

static void fib6_dump_end(struct netlink_callback *cb)
{
	struct fib6_walker_t *w = (void*)cb->args[0];

	if (w) {
		cb->args[0] = 0;
		fib6_walker_unlink(w);
		kfree(w);
	}
1858 1859
	cb->done = (void*)cb->args[1];
	cb->args[1] = 0;
L
Linus Torvalds 已提交
1860 1861 1862 1863 1864
}

static int fib6_dump_done(struct netlink_callback *cb)
{
	fib6_dump_end(cb);
1865
	return cb->done ? cb->done(cb) : 0;
L
Linus Torvalds 已提交
1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888
}

int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct rt6_rtnl_dump_arg arg;
	struct fib6_walker_t *w;
	int res;

	arg.skb = skb;
	arg.cb = cb;

	w = (void*)cb->args[0];
	if (w == NULL) {
		/* New dump:
		 * 
		 * 1. hook callback destructor.
		 */
		cb->args[1] = (long)cb->done;
		cb->done = fib6_dump_done;

		/*
		 * 2. allocate and initialize walker.
		 */
1889
		w = kzalloc(sizeof(*w), GFP_ATOMIC);
L
Linus Torvalds 已提交
1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972
		if (w == NULL)
			return -ENOMEM;
		RT6_TRACE("dump<%p", w);
		w->root = &ip6_routing_table;
		w->func = fib6_dump_node;
		w->args = &arg;
		cb->args[0] = (long)w;
		read_lock_bh(&rt6_lock);
		res = fib6_walk(w);
		read_unlock_bh(&rt6_lock);
	} else {
		w->args = &arg;
		read_lock_bh(&rt6_lock);
		res = fib6_walk_continue(w);
		read_unlock_bh(&rt6_lock);
	}
#if RT6_DEBUG >= 3
	if (res <= 0 && skb->len == 0)
		RT6_TRACE("%p>dump end\n", w);
#endif
	res = res < 0 ? res : skb->len;
	/* res < 0 is an error. (really, impossible)
	   res == 0 means that dump is complete, but skb still can contain data.
	   res > 0 dump is not complete, but frame is full.
	 */
	/* Destroy walker, if dump of this table is complete. */
	if (res <= 0)
		fib6_dump_end(cb);
	return res;
}

int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtattr **rta = arg;
	int iif = 0;
	int err = -ENOBUFS;
	struct sk_buff *skb;
	struct flowi fl;
	struct rt6_info *rt;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (skb == NULL)
		goto out;

	/* Reserve room for dummy headers, this skb can pass
	   through good chunk of routing engine.
	 */
	skb->mac.raw = skb->data;
	skb_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));

	memset(&fl, 0, sizeof(fl));
	if (rta[RTA_SRC-1])
		ipv6_addr_copy(&fl.fl6_src,
			       (struct in6_addr*)RTA_DATA(rta[RTA_SRC-1]));
	if (rta[RTA_DST-1])
		ipv6_addr_copy(&fl.fl6_dst,
			       (struct in6_addr*)RTA_DATA(rta[RTA_DST-1]));

	if (rta[RTA_IIF-1])
		memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));

	if (iif) {
		struct net_device *dev;
		dev = __dev_get_by_index(iif);
		if (!dev) {
			err = -ENODEV;
			goto out_free;
		}
	}

	fl.oif = 0;
	if (rta[RTA_OIF-1])
		memcpy(&fl.oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int));

	rt = (struct rt6_info*)ip6_route_output(NULL, &fl);

	skb->dst = &rt->u.dst;

	NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;
	err = rt6_fill_node(skb, rt, 
			    &fl.fl6_dst, &fl.fl6_src,
			    iif,
			    RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
1973
			    nlh->nlmsg_seq, 0, 0);
L
Linus Torvalds 已提交
1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988
	if (err < 0) {
		err = -EMSGSIZE;
		goto out_free;
	}

	err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
	if (err > 0)
		err = 0;
out:
	return err;
out_free:
	kfree_skb(skb);
	goto out;	
}

1989 1990
void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh, 
			struct netlink_skb_parms *req)
L
Linus Torvalds 已提交
1991 1992 1993
{
	struct sk_buff *skb;
	int size = NLMSG_SPACE(sizeof(struct rtmsg)+256);
1994 1995
	u32 pid = current->pid;
	u32 seq = 0;
L
Linus Torvalds 已提交
1996

1997 1998 1999 2000 2001
	if (req)
		pid = req->pid;
	if (nlh)
		seq = nlh->nlmsg_seq;
	
L
Linus Torvalds 已提交
2002 2003
	skb = alloc_skb(size, gfp_any());
	if (!skb) {
2004
		netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, ENOBUFS);
L
Linus Torvalds 已提交
2005 2006
		return;
	}
2007
	if (rt6_fill_node(skb, rt, NULL, NULL, 0, event, pid, seq, 0, 0) < 0) {
L
Linus Torvalds 已提交
2008
		kfree_skb(skb);
2009
		netlink_set_err(rtnl, 0, RTNLGRP_IPV6_ROUTE, EINVAL);
L
Linus Torvalds 已提交
2010 2011
		return;
	}
2012 2013
	NETLINK_CB(skb).dst_group = RTNLGRP_IPV6_ROUTE;
	netlink_broadcast(rtnl, skb, 0, RTNLGRP_IPV6_ROUTE, gfp_any());
L
Linus Torvalds 已提交
2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161
}

/*
 *	/proc
 */

#ifdef CONFIG_PROC_FS

#define RT6_INFO_LEN (32 + 4 + 32 + 4 + 32 + 40 + 5 + 1)

struct rt6_proc_arg
{
	char *buffer;
	int offset;
	int length;
	int skip;
	int len;
};

static int rt6_info_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_proc_arg *arg = (struct rt6_proc_arg *) p_arg;
	int i;

	if (arg->skip < arg->offset / RT6_INFO_LEN) {
		arg->skip++;
		return 0;
	}

	if (arg->len >= arg->length)
		return 0;

	for (i=0; i<16; i++) {
		sprintf(arg->buffer + arg->len, "%02x",
			rt->rt6i_dst.addr.s6_addr[i]);
		arg->len += 2;
	}
	arg->len += sprintf(arg->buffer + arg->len, " %02x ",
			    rt->rt6i_dst.plen);

#ifdef CONFIG_IPV6_SUBTREES
	for (i=0; i<16; i++) {
		sprintf(arg->buffer + arg->len, "%02x",
			rt->rt6i_src.addr.s6_addr[i]);
		arg->len += 2;
	}
	arg->len += sprintf(arg->buffer + arg->len, " %02x ",
			    rt->rt6i_src.plen);
#else
	sprintf(arg->buffer + arg->len,
		"00000000000000000000000000000000 00 ");
	arg->len += 36;
#endif

	if (rt->rt6i_nexthop) {
		for (i=0; i<16; i++) {
			sprintf(arg->buffer + arg->len, "%02x",
				rt->rt6i_nexthop->primary_key[i]);
			arg->len += 2;
		}
	} else {
		sprintf(arg->buffer + arg->len,
			"00000000000000000000000000000000");
		arg->len += 32;
	}
	arg->len += sprintf(arg->buffer + arg->len,
			    " %08x %08x %08x %08x %8s\n",
			    rt->rt6i_metric, atomic_read(&rt->u.dst.__refcnt),
			    rt->u.dst.__use, rt->rt6i_flags, 
			    rt->rt6i_dev ? rt->rt6i_dev->name : "");
	return 0;
}

static int rt6_proc_info(char *buffer, char **start, off_t offset, int length)
{
	struct rt6_proc_arg arg;
	arg.buffer = buffer;
	arg.offset = offset;
	arg.length = length;
	arg.skip = 0;
	arg.len = 0;

	read_lock_bh(&rt6_lock);
	fib6_clean_tree(&ip6_routing_table, rt6_info_route, 0, &arg);
	read_unlock_bh(&rt6_lock);

	*start = buffer;
	if (offset)
		*start += offset % RT6_INFO_LEN;

	arg.len -= offset % RT6_INFO_LEN;

	if (arg.len > length)
		arg.len = length;
	if (arg.len < 0)
		arg.len = 0;

	return arg.len;
}

static int rt6_stats_seq_show(struct seq_file *seq, void *v)
{
	seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n",
		      rt6_stats.fib_nodes, rt6_stats.fib_route_nodes,
		      rt6_stats.fib_rt_alloc, rt6_stats.fib_rt_entries,
		      rt6_stats.fib_rt_cache,
		      atomic_read(&ip6_dst_ops.entries),
		      rt6_stats.fib_discarded_routes);

	return 0;
}

static int rt6_stats_seq_open(struct inode *inode, struct file *file)
{
	return single_open(file, rt6_stats_seq_show, NULL);
}

static struct file_operations rt6_stats_seq_fops = {
	.owner	 = THIS_MODULE,
	.open	 = rt6_stats_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = single_release,
};
#endif	/* CONFIG_PROC_FS */

#ifdef CONFIG_SYSCTL

static int flush_delay;

static
int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
			      void __user *buffer, size_t *lenp, loff_t *ppos)
{
	if (write) {
		proc_dointvec(ctl, write, filp, buffer, lenp, ppos);
		fib6_run_gc(flush_delay <= 0 ? ~0UL : (unsigned long)flush_delay);
		return 0;
	} else
		return -EINVAL;
}

ctl_table ipv6_route_table[] = {
        {
		.ctl_name	=	NET_IPV6_ROUTE_FLUSH, 
		.procname	=	"flush",
         	.data		=	&flush_delay,
		.maxlen		=	sizeof(int),
2162
		.mode		=	0200,
L
Linus Torvalds 已提交
2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285
         	.proc_handler	=	&ipv6_sysctl_rtcache_flush
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_THRESH,
		.procname	=	"gc_thresh",
         	.data		=	&ip6_dst_ops.gc_thresh,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_MAX_SIZE,
		.procname	=	"max_size",
         	.data		=	&ip6_rt_max_size,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_MIN_INTERVAL,
		.procname	=	"gc_min_interval",
         	.data		=	&ip6_rt_gc_min_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_jiffies,
		.strategy	=	&sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_TIMEOUT,
		.procname	=	"gc_timeout",
         	.data		=	&ip6_rt_gc_timeout,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_jiffies,
		.strategy	=	&sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_INTERVAL,
		.procname	=	"gc_interval",
         	.data		=	&ip6_rt_gc_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_jiffies,
		.strategy	=	&sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_ELASTICITY,
		.procname	=	"gc_elasticity",
         	.data		=	&ip6_rt_gc_elasticity,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_jiffies,
		.strategy	=	&sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_MTU_EXPIRES,
		.procname	=	"mtu_expires",
         	.data		=	&ip6_rt_mtu_expires,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_jiffies,
		.strategy	=	&sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_MIN_ADVMSS,
		.procname	=	"min_adv_mss",
         	.data		=	&ip6_rt_min_advmss,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_jiffies,
		.strategy	=	&sysctl_jiffies,
	},
	{
		.ctl_name	=	NET_IPV6_ROUTE_GC_MIN_INTERVAL_MS,
		.procname	=	"gc_min_interval_ms",
         	.data		=	&ip6_rt_gc_min_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
         	.proc_handler	=	&proc_dointvec_ms_jiffies,
		.strategy	=	&sysctl_ms_jiffies,
	},
	{ .ctl_name = 0 }
};

#endif

void __init ip6_route_init(void)
{
	struct proc_dir_entry *p;

	ip6_dst_ops.kmem_cachep = kmem_cache_create("ip6_dst_cache",
						     sizeof(struct rt6_info),
						     0, SLAB_HWCACHE_ALIGN,
						     NULL, NULL);
	if (!ip6_dst_ops.kmem_cachep)
		panic("cannot create ip6_dst_cache");

	fib6_init();
#ifdef 	CONFIG_PROC_FS
	p = proc_net_create("ipv6_route", 0, rt6_proc_info);
	if (p)
		p->owner = THIS_MODULE;

	proc_net_fops_create("rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
#endif
#ifdef CONFIG_XFRM
	xfrm6_init();
#endif
}

void ip6_route_cleanup(void)
{
#ifdef CONFIG_PROC_FS
	proc_net_remove("ipv6_route");
	proc_net_remove("rt6_stats");
#endif
#ifdef CONFIG_XFRM
	xfrm6_fini();
#endif
	rt6_ifdown(NULL);
	fib6_gc_cleanup();
	kmem_cache_destroy(ip6_dst_ops.kmem_cachep);
}