fib_frontend.c 20.8 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
/*
 * 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.
 *
 *		IPv4 Forwarding Information Base: FIB frontend.
 *
 * Version:	$Id: fib_frontend.c,v 1.26 2001/10/31 21:55:54 davem Exp $
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */

#include <linux/module.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
22
#include <linux/capability.h>
L
Linus Torvalds 已提交
23 24 25 26 27 28 29 30 31
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
32
#include <linux/inetdevice.h>
L
Linus Torvalds 已提交
33
#include <linux/netdevice.h>
34
#include <linux/if_addr.h>
L
Linus Torvalds 已提交
35 36 37 38
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/netlink.h>
#include <linux/init.h>
39
#include <linux/list.h>
L
Linus Torvalds 已提交
40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56

#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/icmp.h>
#include <net/arp.h>
#include <net/ip_fib.h>

#define FFprint(a...) printk(KERN_DEBUG a)

#ifndef CONFIG_IP_MULTIPLE_TABLES

struct fib_table *ip_fib_local_table;
struct fib_table *ip_fib_main_table;

57 58
#define FIB_TABLE_HASHSZ 1
static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
L
Linus Torvalds 已提交
59

60
#else
L
Linus Torvalds 已提交
61

62 63
#define FIB_TABLE_HASHSZ 256
static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ];
L
Linus Torvalds 已提交
64

65
struct fib_table *fib_new_table(u32 id)
L
Linus Torvalds 已提交
66 67
{
	struct fib_table *tb;
68
	unsigned int h;
L
Linus Torvalds 已提交
69

70 71 72 73 74
	if (id == 0)
		id = RT_TABLE_MAIN;
	tb = fib_get_table(id);
	if (tb)
		return tb;
L
Linus Torvalds 已提交
75 76 77
	tb = fib_hash_init(id);
	if (!tb)
		return NULL;
78 79
	h = id & (FIB_TABLE_HASHSZ - 1);
	hlist_add_head_rcu(&tb->tb_hlist, &fib_table_hash[h]);
L
Linus Torvalds 已提交
80 81 82
	return tb;
}

83 84 85 86 87
struct fib_table *fib_get_table(u32 id)
{
	struct fib_table *tb;
	struct hlist_node *node;
	unsigned int h;
L
Linus Torvalds 已提交
88

89 90 91 92 93 94 95 96 97 98 99 100 101
	if (id == 0)
		id = RT_TABLE_MAIN;
	h = id & (FIB_TABLE_HASHSZ - 1);
	rcu_read_lock();
	hlist_for_each_entry_rcu(tb, node, &fib_table_hash[h], tb_hlist) {
		if (tb->tb_id == id) {
			rcu_read_unlock();
			return tb;
		}
	}
	rcu_read_unlock();
	return NULL;
}
L
Linus Torvalds 已提交
102 103 104 105 106 107
#endif /* CONFIG_IP_MULTIPLE_TABLES */

static void fib_flush(void)
{
	int flushed = 0;
	struct fib_table *tb;
108 109
	struct hlist_node *node;
	unsigned int h;
L
Linus Torvalds 已提交
110

111 112 113
	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
		hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist)
			flushed += tb->tb_flush(tb);
L
Linus Torvalds 已提交
114 115 116 117 118 119 120 121 122 123
	}

	if (flushed)
		rt_cache_flush(-1);
}

/*
 *	Find the first device with a given source address.
 */

A
Al Viro 已提交
124
struct net_device * ip_dev_find(__be32 addr)
L
Linus Torvalds 已提交
125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147
{
	struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
	struct fib_result res;
	struct net_device *dev = NULL;

#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r = NULL;
#endif

	if (!ip_fib_local_table ||
	    ip_fib_local_table->tb_lookup(ip_fib_local_table, &fl, &res))
		return NULL;
	if (res.type != RTN_LOCAL)
		goto out;
	dev = FIB_RES_DEV(res);

	if (dev)
		dev_hold(dev);
out:
	fib_res_put(&res);
	return dev;
}

A
Al Viro 已提交
148
unsigned inet_addr_type(__be32 addr)
L
Linus Torvalds 已提交
149 150 151 152 153 154 155 156 157 158 159 160 161
{
	struct flowi		fl = { .nl_u = { .ip4_u = { .daddr = addr } } };
	struct fib_result	res;
	unsigned ret = RTN_BROADCAST;

	if (ZERONET(addr) || BADCLASS(addr))
		return RTN_BROADCAST;
	if (MULTICAST(addr))
		return RTN_MULTICAST;

#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r = NULL;
#endif
162

L
Linus Torvalds 已提交
163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181
	if (ip_fib_local_table) {
		ret = RTN_UNICAST;
		if (!ip_fib_local_table->tb_lookup(ip_fib_local_table,
						   &fl, &res)) {
			ret = res.type;
			fib_res_put(&res);
		}
	}
	return ret;
}

/* Given (packet source, input interface) and optional (dst, oif, tos):
   - (main) check, that source is valid i.e. not broadcast or our local
     address.
   - figure out what "logical" interface this packet arrived
     and calculate "specific destination" address.
   - check, that packet arrived from expected physical interface.
 */

182 183
int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
			struct net_device *dev, __be32 *spec_dst, u32 *itag)
L
Linus Torvalds 已提交
184 185 186 187 188 189 190 191 192 193 194 195 196
{
	struct in_device *in_dev;
	struct flowi fl = { .nl_u = { .ip4_u =
				      { .daddr = src,
					.saddr = dst,
					.tos = tos } },
			    .iif = oif };
	struct fib_result res;
	int no_addr, rpf;
	int ret;

	no_addr = rpf = 0;
	rcu_read_lock();
197
	in_dev = __in_dev_get_rcu(dev);
L
Linus Torvalds 已提交
198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254
	if (in_dev) {
		no_addr = in_dev->ifa_list == NULL;
		rpf = IN_DEV_RPFILTER(in_dev);
	}
	rcu_read_unlock();

	if (in_dev == NULL)
		goto e_inval;

	if (fib_lookup(&fl, &res))
		goto last_resort;
	if (res.type != RTN_UNICAST)
		goto e_inval_res;
	*spec_dst = FIB_RES_PREFSRC(res);
	fib_combine_itag(itag, &res);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1)
#else
	if (FIB_RES_DEV(res) == dev)
#endif
	{
		ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
		fib_res_put(&res);
		return ret;
	}
	fib_res_put(&res);
	if (no_addr)
		goto last_resort;
	if (rpf)
		goto e_inval;
	fl.oif = dev->ifindex;

	ret = 0;
	if (fib_lookup(&fl, &res) == 0) {
		if (res.type == RTN_UNICAST) {
			*spec_dst = FIB_RES_PREFSRC(res);
			ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST;
		}
		fib_res_put(&res);
	}
	return ret;

last_resort:
	if (rpf)
		goto e_inval;
	*spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
	*itag = 0;
	return 0;

e_inval_res:
	fib_res_put(&res);
e_inval:
	return -EINVAL;
}

#ifndef CONFIG_IP_NOSIOCRT

A
Al Viro 已提交
255
static inline __be32 sk_extract_addr(struct sockaddr *addr)
256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274
{
	return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
}

static int put_rtax(struct nlattr *mx, int len, int type, u32 value)
{
	struct nlattr *nla;

	nla = (struct nlattr *) ((char *) mx + len);
	nla->nla_type = type;
	nla->nla_len = nla_attr_size(4);
	*(u32 *) nla_data(nla) = value;

	return len + nla_total_size(4);
}

static int rtentry_to_fib_config(int cmd, struct rtentry *rt,
				 struct fib_config *cfg)
{
275
	__be32 addr;
276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
	int plen;

	memset(cfg, 0, sizeof(*cfg));

	if (rt->rt_dst.sa_family != AF_INET)
		return -EAFNOSUPPORT;

	/*
	 * Check mask for validity:
	 * a) it must be contiguous.
	 * b) destination must have all host bits clear.
	 * c) if application forgot to set correct family (AF_INET),
	 *    reject request unless it is absolutely clear i.e.
	 *    both family and mask are zero.
	 */
	plen = 32;
	addr = sk_extract_addr(&rt->rt_dst);
	if (!(rt->rt_flags & RTF_HOST)) {
A
Al Viro 已提交
294
		__be32 mask = sk_extract_addr(&rt->rt_genmask);
295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379

		if (rt->rt_genmask.sa_family != AF_INET) {
			if (mask || rt->rt_genmask.sa_family)
				return -EAFNOSUPPORT;
		}

		if (bad_mask(mask, addr))
			return -EINVAL;

		plen = inet_mask_len(mask);
	}

	cfg->fc_dst_len = plen;
	cfg->fc_dst = addr;

	if (cmd != SIOCDELRT) {
		cfg->fc_nlflags = NLM_F_CREATE;
		cfg->fc_protocol = RTPROT_BOOT;
	}

	if (rt->rt_metric)
		cfg->fc_priority = rt->rt_metric - 1;

	if (rt->rt_flags & RTF_REJECT) {
		cfg->fc_scope = RT_SCOPE_HOST;
		cfg->fc_type = RTN_UNREACHABLE;
		return 0;
	}

	cfg->fc_scope = RT_SCOPE_NOWHERE;
	cfg->fc_type = RTN_UNICAST;

	if (rt->rt_dev) {
		char *colon;
		struct net_device *dev;
		char devname[IFNAMSIZ];

		if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1))
			return -EFAULT;

		devname[IFNAMSIZ-1] = 0;
		colon = strchr(devname, ':');
		if (colon)
			*colon = 0;
		dev = __dev_get_by_name(devname);
		if (!dev)
			return -ENODEV;
		cfg->fc_oif = dev->ifindex;
		if (colon) {
			struct in_ifaddr *ifa;
			struct in_device *in_dev = __in_dev_get_rtnl(dev);
			if (!in_dev)
				return -ENODEV;
			*colon = ':';
			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
				if (strcmp(ifa->ifa_label, devname) == 0)
					break;
			if (ifa == NULL)
				return -ENODEV;
			cfg->fc_prefsrc = ifa->ifa_local;
		}
	}

	addr = sk_extract_addr(&rt->rt_gateway);
	if (rt->rt_gateway.sa_family == AF_INET && addr) {
		cfg->fc_gw = addr;
		if (rt->rt_flags & RTF_GATEWAY &&
		    inet_addr_type(addr) == RTN_UNICAST)
			cfg->fc_scope = RT_SCOPE_UNIVERSE;
	}

	if (cmd == SIOCDELRT)
		return 0;

	if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw)
		return -EINVAL;

	if (cfg->fc_scope == RT_SCOPE_NOWHERE)
		cfg->fc_scope = RT_SCOPE_LINK;

	if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) {
		struct nlattr *mx;
		int len = 0;

		mx = kzalloc(3 * nla_total_size(4), GFP_KERNEL);
380
		if (mx == NULL)
381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398
			return -ENOMEM;

		if (rt->rt_flags & RTF_MTU)
			len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40);

		if (rt->rt_flags & RTF_WINDOW)
			len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window);

		if (rt->rt_flags & RTF_IRTT)
			len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3);

		cfg->fc_mx = mx;
		cfg->fc_mx_len = len;
	}

	return 0;
}

L
Linus Torvalds 已提交
399 400 401
/*
 *	Handle IP routing ioctl calls. These are used to manipulate the routing tables
 */
402

L
Linus Torvalds 已提交
403 404
int ip_rt_ioctl(unsigned int cmd, void __user *arg)
{
405 406
	struct fib_config cfg;
	struct rtentry rt;
L
Linus Torvalds 已提交
407 408 409 410 411 412 413
	int err;

	switch (cmd) {
	case SIOCADDRT:		/* Add a route */
	case SIOCDELRT:		/* Delete a route */
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
414 415

		if (copy_from_user(&rt, arg, sizeof(rt)))
L
Linus Torvalds 已提交
416
			return -EFAULT;
417

L
Linus Torvalds 已提交
418
		rtnl_lock();
419
		err = rtentry_to_fib_config(cmd, &rt, &cfg);
L
Linus Torvalds 已提交
420
		if (err == 0) {
421 422
			struct fib_table *tb;

L
Linus Torvalds 已提交
423
			if (cmd == SIOCDELRT) {
424
				tb = fib_get_table(cfg.fc_table);
L
Linus Torvalds 已提交
425
				if (tb)
426 427 428
					err = tb->tb_delete(tb, &cfg);
				else
					err = -ESRCH;
L
Linus Torvalds 已提交
429
			} else {
430
				tb = fib_new_table(cfg.fc_table);
L
Linus Torvalds 已提交
431
				if (tb)
432 433 434
					err = tb->tb_insert(tb, &cfg);
				else
					err = -ENOBUFS;
L
Linus Torvalds 已提交
435
			}
436 437 438

			/* allocated by rtentry_to_fib_config() */
			kfree(cfg.fc_mx);
L
Linus Torvalds 已提交
439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454
		}
		rtnl_unlock();
		return err;
	}
	return -EINVAL;
}

#else

int ip_rt_ioctl(unsigned int cmd, void *arg)
{
	return -EINVAL;
}

#endif

455
struct nla_policy rtm_ipv4_policy[RTA_MAX+1] __read_mostly = {
456 457 458 459 460 461 462 463
	[RTA_DST]		= { .type = NLA_U32 },
	[RTA_SRC]		= { .type = NLA_U32 },
	[RTA_IIF]		= { .type = NLA_U32 },
	[RTA_OIF]		= { .type = NLA_U32 },
	[RTA_GATEWAY]		= { .type = NLA_U32 },
	[RTA_PRIORITY]		= { .type = NLA_U32 },
	[RTA_PREFSRC]		= { .type = NLA_U32 },
	[RTA_METRICS]		= { .type = NLA_NESTED },
464
	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
465 466 467 468 469 470 471
	[RTA_PROTOINFO]		= { .type = NLA_U32 },
	[RTA_FLOW]		= { .type = NLA_U32 },
	[RTA_MP_ALGO]		= { .type = NLA_U32 },
};

static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh,
			     struct fib_config *cfg)
L
Linus Torvalds 已提交
472
{
473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495
	struct nlattr *attr;
	int err, remaining;
	struct rtmsg *rtm;

	err = nlmsg_validate(nlh, sizeof(*rtm), RTA_MAX, rtm_ipv4_policy);
	if (err < 0)
		goto errout;

	memset(cfg, 0, sizeof(*cfg));

	rtm = nlmsg_data(nlh);
	cfg->fc_dst_len = rtm->rtm_dst_len;
	cfg->fc_tos = rtm->rtm_tos;
	cfg->fc_table = rtm->rtm_table;
	cfg->fc_protocol = rtm->rtm_protocol;
	cfg->fc_scope = rtm->rtm_scope;
	cfg->fc_type = rtm->rtm_type;
	cfg->fc_flags = rtm->rtm_flags;
	cfg->fc_nlflags = nlh->nlmsg_flags;

	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
	cfg->fc_nlinfo.nlh = nlh;

496 497 498 499 500
	if (cfg->fc_type > RTN_MAX) {
		err = -EINVAL;
		goto errout;
	}

501 502 503
	nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
		switch (attr->nla_type) {
		case RTA_DST:
504
			cfg->fc_dst = nla_get_be32(attr);
505 506 507 508 509
			break;
		case RTA_OIF:
			cfg->fc_oif = nla_get_u32(attr);
			break;
		case RTA_GATEWAY:
510
			cfg->fc_gw = nla_get_be32(attr);
511 512 513 514 515
			break;
		case RTA_PRIORITY:
			cfg->fc_priority = nla_get_u32(attr);
			break;
		case RTA_PREFSRC:
516
			cfg->fc_prefsrc = nla_get_be32(attr);
517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534
			break;
		case RTA_METRICS:
			cfg->fc_mx = nla_data(attr);
			cfg->fc_mx_len = nla_len(attr);
			break;
		case RTA_MULTIPATH:
			cfg->fc_mp = nla_data(attr);
			cfg->fc_mp_len = nla_len(attr);
			break;
		case RTA_FLOW:
			cfg->fc_flow = nla_get_u32(attr);
			break;
		case RTA_MP_ALGO:
			cfg->fc_mp_alg = nla_get_u32(attr);
			break;
		case RTA_TABLE:
			cfg->fc_table = nla_get_u32(attr);
			break;
L
Linus Torvalds 已提交
535 536
		}
	}
537

L
Linus Torvalds 已提交
538
	return 0;
539 540
errout:
	return err;
L
Linus Torvalds 已提交
541 542 543 544
}

int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
545 546 547
	struct fib_config cfg;
	struct fib_table *tb;
	int err;
L
Linus Torvalds 已提交
548

549 550 551
	err = rtm_to_fib_config(skb, nlh, &cfg);
	if (err < 0)
		goto errout;
L
Linus Torvalds 已提交
552

553 554 555 556 557 558 559 560 561
	tb = fib_get_table(cfg.fc_table);
	if (tb == NULL) {
		err = -ESRCH;
		goto errout;
	}

	err = tb->tb_delete(tb, &cfg);
errout:
	return err;
L
Linus Torvalds 已提交
562 563 564 565
}

int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
566 567 568
	struct fib_config cfg;
	struct fib_table *tb;
	int err;
L
Linus Torvalds 已提交
569

570 571 572
	err = rtm_to_fib_config(skb, nlh, &cfg);
	if (err < 0)
		goto errout;
L
Linus Torvalds 已提交
573

574 575 576 577 578 579 580 581 582
	tb = fib_new_table(cfg.fc_table);
	if (tb == NULL) {
		err = -ENOBUFS;
		goto errout;
	}

	err = tb->tb_insert(tb, &cfg);
errout:
	return err;
L
Linus Torvalds 已提交
583 584 585 586
}

int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
587 588
	unsigned int h, s_h;
	unsigned int e = 0, s_e;
L
Linus Torvalds 已提交
589
	struct fib_table *tb;
590 591
	struct hlist_node *node;
	int dumped = 0;
L
Linus Torvalds 已提交
592

593 594
	if (nlmsg_len(cb->nlh) >= sizeof(struct rtmsg) &&
	    ((struct rtmsg *) nlmsg_data(cb->nlh))->rtm_flags & RTM_F_CLONED)
L
Linus Torvalds 已提交
595 596
		return ip_rt_dump(skb, cb);

597 598 599 600 601 602 603 604 605 606
	s_h = cb->args[0];
	s_e = cb->args[1];

	for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
		e = 0;
		hlist_for_each_entry(tb, node, &fib_table_hash[h], tb_hlist) {
			if (e < s_e)
				goto next;
			if (dumped)
				memset(&cb->args[2], 0, sizeof(cb->args) -
607
						 2 * sizeof(cb->args[0]));
608 609 610 611 612 613
			if (tb->tb_dump(tb, skb, cb) < 0)
				goto out;
			dumped = 1;
next:
			e++;
		}
L
Linus Torvalds 已提交
614
	}
615 616 617
out:
	cb->args[1] = e;
	cb->args[0] = h;
L
Linus Torvalds 已提交
618 619 620 621 622 623 624 625 626 627 628

	return skb->len;
}

/* Prepare and feed intra-kernel routing request.
   Really, it should be netlink message, but :-( netlink
   can be not configured, so that we feed it directly
   to fib engine. It is legal, because all events occur
   only when netlink is already locked.
 */

A
Al Viro 已提交
629
static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa)
L
Linus Torvalds 已提交
630
{
631 632 633 634 635 636 637 638 639 640
	struct fib_table *tb;
	struct fib_config cfg = {
		.fc_protocol = RTPROT_KERNEL,
		.fc_type = type,
		.fc_dst = dst,
		.fc_dst_len = dst_len,
		.fc_prefsrc = ifa->ifa_local,
		.fc_oif = ifa->ifa_dev->dev->ifindex,
		.fc_nlflags = NLM_F_CREATE | NLM_F_APPEND,
	};
L
Linus Torvalds 已提交
641 642 643 644 645 646 647 648 649

	if (type == RTN_UNICAST)
		tb = fib_new_table(RT_TABLE_MAIN);
	else
		tb = fib_new_table(RT_TABLE_LOCAL);

	if (tb == NULL)
		return;

650
	cfg.fc_table = tb->tb_id;
L
Linus Torvalds 已提交
651

652 653 654 655
	if (type != RTN_LOCAL)
		cfg.fc_scope = RT_SCOPE_LINK;
	else
		cfg.fc_scope = RT_SCOPE_HOST;
L
Linus Torvalds 已提交
656 657

	if (cmd == RTM_NEWROUTE)
658
		tb->tb_insert(tb, &cfg);
L
Linus Torvalds 已提交
659
	else
660
		tb->tb_delete(tb, &cfg);
L
Linus Torvalds 已提交
661 662
}

663
void fib_add_ifaddr(struct in_ifaddr *ifa)
L
Linus Torvalds 已提交
664 665 666 667
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;
	struct in_ifaddr *prim = ifa;
A
Al Viro 已提交
668 669 670
	__be32 mask = ifa->ifa_mask;
	__be32 addr = ifa->ifa_local;
	__be32 prefix = ifa->ifa_address&mask;
L
Linus Torvalds 已提交
671 672 673 674 675 676 677 678 679 680 681 682 683 684 685

	if (ifa->ifa_flags&IFA_F_SECONDARY) {
		prim = inet_ifa_byprefix(in_dev, prefix, mask);
		if (prim == NULL) {
			printk(KERN_DEBUG "fib_add_ifaddr: bug: prim == NULL\n");
			return;
		}
	}

	fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim);

	if (!(dev->flags&IFF_UP))
		return;

	/* Add broadcast address, if it is explicitly assigned. */
A
Al Viro 已提交
686
	if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
L
Linus Torvalds 已提交
687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707
		fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);

	if (!ZERONET(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) &&
	    (prefix != addr || ifa->ifa_prefixlen < 32)) {
		fib_magic(RTM_NEWROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL :
			  RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim);

		/* Add network specific broadcasts, when it takes a sense */
		if (ifa->ifa_prefixlen < 31) {
			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim);
			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix|~mask, 32, prim);
		}
	}
}

static void fib_del_ifaddr(struct in_ifaddr *ifa)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;
	struct in_ifaddr *ifa1;
	struct in_ifaddr *prim = ifa;
A
Al Viro 已提交
708 709
	__be32 brd = ifa->ifa_address|~ifa->ifa_mask;
	__be32 any = ifa->ifa_address&ifa->ifa_mask;
L
Linus Torvalds 已提交
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
#define LOCAL_OK	1
#define BRD_OK		2
#define BRD0_OK		4
#define BRD1_OK		8
	unsigned ok = 0;

	if (!(ifa->ifa_flags&IFA_F_SECONDARY))
		fib_magic(RTM_DELROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL :
			  RTN_UNICAST, any, ifa->ifa_prefixlen, prim);
	else {
		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
		if (prim == NULL) {
			printk(KERN_DEBUG "fib_del_ifaddr: bug: prim == NULL\n");
			return;
		}
	}

	/* Deletion is more complicated than add.
	   We should take care of not to delete too much :-)

	   Scan address list to be sure that addresses are really gone.
	 */

	for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
		if (ifa->ifa_local == ifa1->ifa_local)
			ok |= LOCAL_OK;
		if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
			ok |= BRD_OK;
		if (brd == ifa1->ifa_broadcast)
			ok |= BRD1_OK;
		if (any == ifa1->ifa_broadcast)
			ok |= BRD0_OK;
	}

	if (!(ok&BRD_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
	if (!(ok&BRD1_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim);
	if (!(ok&BRD0_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim);
	if (!(ok&LOCAL_OK)) {
		fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim);

		/* Check, that this local address finally disappeared. */
		if (inet_addr_type(ifa->ifa_local) != RTN_LOCAL) {
			/* And the last, but not the least thing.
			   We must flush stray FIB entries.

			   First of all, we scan fib_info list searching
			   for stray nexthop entries, then ignite fib_flush.
			*/
			if (fib_sync_down(ifa->ifa_local, NULL, 0))
				fib_flush();
		}
	}
#undef LOCAL_OK
#undef BRD_OK
#undef BRD0_OK
#undef BRD1_OK
}

771 772
static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb )
{
773

774
	struct fib_result       res;
775
	struct flowi            fl = { .mark = frn->fl_mark,
776
				       .nl_u = { .ip4_u = { .daddr = frn->fl_addr,
777 778
							    .tos = frn->fl_tos,
							    .scope = frn->fl_scope } } };
779 780

	frn->err = -ENOENT;
781 782 783 784 785 786 787 788 789 790 791
	if (tb) {
		local_bh_disable();

		frn->tb_id = tb->tb_id;
		frn->err = tb->tb_lookup(tb, &fl, &res);

		if (!frn->err) {
			frn->prefixlen = res.prefixlen;
			frn->nh_sel = res.nh_sel;
			frn->type = res.type;
			frn->scope = res.scope;
792
			fib_res_put(&res);
793 794 795 796 797 798 799 800
		}
		local_bh_enable();
	}
}

static void nl_fib_input(struct sock *sk, int len)
{
	struct sk_buff *skb = NULL;
801
	struct nlmsghdr *nlh = NULL;
802
	struct fib_result_nl *frn;
803
	u32 pid;
804
	struct fib_table *tb;
805

806
	skb = skb_dequeue(&sk->sk_receive_queue);
807 808 809
	if (skb == NULL)
		return;

810
	nlh = (struct nlmsghdr *)skb->data;
811 812 813 814 815
	if (skb->len < NLMSG_SPACE(0) || skb->len < nlh->nlmsg_len ||
	    nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*frn))) {
		kfree_skb(skb);
		return;
	}
816

817 818 819 820
	frn = (struct fib_result_nl *) NLMSG_DATA(nlh);
	tb = fib_get_table(frn->tb_id_in);

	nl_fib_lookup(frn, tb);
821

822
	pid = NETLINK_CB(skb).pid;       /* pid of sending process */
823
	NETLINK_CB(skb).pid = 0;         /* from kernel */
824
	NETLINK_CB(skb).dst_group = 0;  /* unicast */
825
	netlink_unicast(sk, skb, pid, MSG_DONTWAIT);
826
}
827 828 829

static void nl_fib_lookup_init(void)
{
830
      netlink_kernel_create(NETLINK_FIB_LOOKUP, 0, nl_fib_input, THIS_MODULE);
831 832
}

L
Linus Torvalds 已提交
833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854
static void fib_disable_ip(struct net_device *dev, int force)
{
	if (fib_sync_down(0, dev, force))
		fib_flush();
	rt_cache_flush(0);
	arp_ifdown(dev);
}

static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct in_ifaddr *ifa = (struct in_ifaddr*)ptr;

	switch (event) {
	case NETDEV_UP:
		fib_add_ifaddr(ifa);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		fib_sync_up(ifa->ifa_dev->dev);
#endif
		rt_cache_flush(-1);
		break;
	case NETDEV_DOWN:
		fib_del_ifaddr(ifa);
855
		if (ifa->ifa_dev->ifa_list == NULL) {
L
Linus Torvalds 已提交
856 857 858 859 860 861 862 863 864 865 866 867 868 869 870
			/* Last address was deleted from this interface.
			   Disable IP.
			 */
			fib_disable_ip(ifa->ifa_dev->dev, 1);
		} else {
			rt_cache_flush(-1);
		}
		break;
	}
	return NOTIFY_DONE;
}

static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *dev = ptr;
871
	struct in_device *in_dev = __in_dev_get_rtnl(dev);
L
Linus Torvalds 已提交
872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911

	if (event == NETDEV_UNREGISTER) {
		fib_disable_ip(dev, 2);
		return NOTIFY_DONE;
	}

	if (!in_dev)
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_UP:
		for_ifa(in_dev) {
			fib_add_ifaddr(ifa);
		} endfor_ifa(in_dev);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		fib_sync_up(dev);
#endif
		rt_cache_flush(-1);
		break;
	case NETDEV_DOWN:
		fib_disable_ip(dev, 0);
		break;
	case NETDEV_CHANGEMTU:
	case NETDEV_CHANGE:
		rt_cache_flush(0);
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block fib_inetaddr_notifier = {
	.notifier_call =fib_inetaddr_event,
};

static struct notifier_block fib_netdev_notifier = {
	.notifier_call =fib_netdev_event,
};

void __init ip_fib_init(void)
{
912 913 914 915
	unsigned int i;

	for (i = 0; i < FIB_TABLE_HASHSZ; i++)
		INIT_HLIST_HEAD(&fib_table_hash[i]);
L
Linus Torvalds 已提交
916 917
#ifndef CONFIG_IP_MULTIPLE_TABLES
	ip_fib_local_table = fib_hash_init(RT_TABLE_LOCAL);
918
	hlist_add_head_rcu(&ip_fib_local_table->tb_hlist, &fib_table_hash[0]);
L
Linus Torvalds 已提交
919
	ip_fib_main_table  = fib_hash_init(RT_TABLE_MAIN);
920
	hlist_add_head_rcu(&ip_fib_main_table->tb_hlist, &fib_table_hash[0]);
L
Linus Torvalds 已提交
921
#else
922
	fib4_rules_init();
L
Linus Torvalds 已提交
923 924 925 926
#endif

	register_netdevice_notifier(&fib_netdev_notifier);
	register_inetaddr_notifier(&fib_inetaddr_notifier);
927
	nl_fib_lookup_init();
L
Linus Torvalds 已提交
928 929 930
}

EXPORT_SYMBOL(inet_addr_type);
S
Sean Hefty 已提交
931
EXPORT_SYMBOL(ip_dev_find);