route.c 73.9 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		ROUTE - implementation of the IP router.
 *
 * Version:	$Id: route.c,v 1.103 2002/01/12 07:44:09 davem Exp $
 *
10
 * Authors:	Ross Biro
L
Linus Torvalds 已提交
11 12 13 14 15 16 17 18 19 20 21 22
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Alan Cox, <gw4pts@gw4pts.ampr.org>
 *		Linus Torvalds, <Linus.Torvalds@helsinki.fi>
 *		Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 * Fixes:
 *		Alan Cox	:	Verify area fixes.
 *		Alan Cox	:	cli() protects routing changes
 *		Rui Oliveira	:	ICMP routing table updates
 *		(rco@di.uminho.pt)	Routing table insertion and update
 *		Linus Torvalds	:	Rewrote bits to be sensible
 *		Alan Cox	:	Added BSD route gw semantics
23
 *		Alan Cox	:	Super /proc >4K
L
Linus Torvalds 已提交
24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40
 *		Alan Cox	:	MTU in route table
 *		Alan Cox	: 	MSS actually. Also added the window
 *					clamper.
 *		Sam Lantinga	:	Fixed route matching in rt_del()
 *		Alan Cox	:	Routing cache support.
 *		Alan Cox	:	Removed compatibility cruft.
 *		Alan Cox	:	RTF_REJECT support.
 *		Alan Cox	:	TCP irtt support.
 *		Jonathan Naylor	:	Added Metric support.
 *	Miquel van Smoorenburg	:	BSD API fixes.
 *	Miquel van Smoorenburg	:	Metrics.
 *		Alan Cox	:	Use __u32 properly
 *		Alan Cox	:	Aligned routing errors more closely with BSD
 *					our system is still very different.
 *		Alan Cox	:	Faster /proc handling
 *	Alexey Kuznetsov	:	Massive rework to support tree based routing,
 *					routing caches and better behaviour.
41
 *
L
Linus Torvalds 已提交
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56
 *		Olaf Erb	:	irtt wasn't being copied right.
 *		Bjorn Ekwall	:	Kerneld route support.
 *		Alan Cox	:	Multicast fixed (I hope)
 * 		Pavel Krauz	:	Limited broadcast fixed
 *		Mike McLagan	:	Routing by source
 *	Alexey Kuznetsov	:	End of old history. Split to fib.c and
 *					route.c and rewritten from scratch.
 *		Andi Kleen	:	Load-limit warning messages.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *	Vitaly E. Lavrov	:	Race condition in ip_route_input_slow.
 *	Tobias Ringstrom	:	Uninitialized res.type in ip_route_output_slow.
 *	Vladimir V. Ivanov	:	IP rule info (flowid) is really useful.
 *		Marc Boucher	:	routing by fwmark
 *	Robert Olsson		:	Added rt_cache statistics
 *	Arnaldo C. Melo		:	Convert proc stuff to seq_file
57
 *	Eric Dumazet		:	hashed spinlocks and rt_check_expire() fixes.
58 59
 * 	Ilia Sotnikov		:	Ignore TOS on PMTUD and Redirect
 * 	Ilia Sotnikov		:	Removed TOS from hash calculations
L
Linus Torvalds 已提交
60 61 62 63 64 65 66 67 68 69 70 71 72 73
 *
 *		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>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
74
#include <linux/bootmem.h>
L
Linus Torvalds 已提交
75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/pkt_sched.h>
#include <linux/mroute.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/arp.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
104
#include <net/netevent.h>
105
#include <net/rtnetlink.h>
L
Linus Torvalds 已提交
106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#define RT_FL_TOS(oldflp) \
    ((u32)(oldflp->fl4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))

#define IP_MAX_MTU	0xFFF0

#define RT_GC_TIMEOUT (300*HZ)

static int ip_rt_min_delay		= 2 * HZ;
static int ip_rt_max_delay		= 10 * HZ;
static int ip_rt_max_size;
static int ip_rt_gc_timeout		= RT_GC_TIMEOUT;
static int ip_rt_gc_interval		= 60 * HZ;
static int ip_rt_gc_min_interval	= HZ / 2;
static int ip_rt_redirect_number	= 9;
static int ip_rt_redirect_load		= HZ / 50;
static int ip_rt_redirect_silence	= ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost		= HZ;
static int ip_rt_error_burst		= 5 * HZ;
static int ip_rt_gc_elasticity		= 8;
static int ip_rt_mtu_expires		= 10 * 60 * HZ;
static int ip_rt_min_pmtu		= 512 + 20 + 20;
static int ip_rt_min_advmss		= 256;
static int ip_rt_secret_interval	= 10 * 60 * HZ;
static unsigned long rt_deadline;

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

static struct timer_list rt_flush_timer;
static struct timer_list rt_periodic_timer;
static struct timer_list rt_secret_timer;

/*
 *	Interface to generic destination cache.
 */

static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static void		 ipv4_dst_destroy(struct dst_entry *dst);
static void		 ipv4_dst_ifdown(struct dst_entry *dst,
					 struct net_device *dev, int how);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void		 ipv4_link_failure(struct sk_buff *skb);
static void		 ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
static int rt_garbage_collect(void);


static struct dst_ops ipv4_dst_ops = {
	.family =		AF_INET,
	.protocol =		__constant_htons(ETH_P_IP),
	.gc =			rt_garbage_collect,
	.check =		ipv4_dst_check,
	.destroy =		ipv4_dst_destroy,
	.ifdown =		ipv4_dst_ifdown,
	.negative_advice =	ipv4_negative_advice,
	.link_failure =		ipv4_link_failure,
	.update_pmtu =		ip_rt_update_pmtu,
	.entry_size =		sizeof(struct rtable),
};

#define ECN_OR_COST(class)	TC_PRIO_##class

170
const __u8 ip_tos2prio[16] = {
L
Linus Torvalds 已提交
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
	TC_PRIO_BESTEFFORT,
	ECN_OR_COST(FILLER),
	TC_PRIO_BESTEFFORT,
	ECN_OR_COST(BESTEFFORT),
	TC_PRIO_BULK,
	ECN_OR_COST(BULK),
	TC_PRIO_BULK,
	ECN_OR_COST(BULK),
	TC_PRIO_INTERACTIVE,
	ECN_OR_COST(INTERACTIVE),
	TC_PRIO_INTERACTIVE,
	ECN_OR_COST(INTERACTIVE),
	TC_PRIO_INTERACTIVE_BULK,
	ECN_OR_COST(INTERACTIVE_BULK),
	TC_PRIO_INTERACTIVE_BULK,
	ECN_OR_COST(INTERACTIVE_BULK)
};


/*
 * Route cache.
 */

/* The locking scheme is rather straight forward:
 *
 * 1) Read-Copy Update protects the buckets of the central route hash.
 * 2) Only writers remove entries, and they hold the lock
 *    as they look at rtable reference counts.
 * 3) Only readers acquire references to rtable entries,
 *    they do so with atomic increments and with the
 *    lock held.
 */

struct rt_hash_bucket {
	struct rtable	*chain;
206
};
207 208
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
	defined(CONFIG_PROVE_LOCKING)
209 210 211
/*
 * Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
 * The size of this table is a power of two and depends on the number of CPUS.
212
 * (on lockdep we have a quite big spinlock_t, so keep the size down there)
213
 */
214 215
#ifdef CONFIG_LOCKDEP
# define RT_HASH_LOCK_SZ	256
216
#else
217 218 219 220 221 222 223 224 225 226 227
# if NR_CPUS >= 32
#  define RT_HASH_LOCK_SZ	4096
# elif NR_CPUS >= 16
#  define RT_HASH_LOCK_SZ	2048
# elif NR_CPUS >= 8
#  define RT_HASH_LOCK_SZ	1024
# elif NR_CPUS >= 4
#  define RT_HASH_LOCK_SZ	512
# else
#  define RT_HASH_LOCK_SZ	256
# endif
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242
#endif

static spinlock_t	*rt_hash_locks;
# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
# define rt_hash_lock_init()	{ \
		int i; \
		rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ, GFP_KERNEL); \
		if (!rt_hash_locks) panic("IP: failed to allocate rt_hash_locks\n"); \
		for (i = 0; i < RT_HASH_LOCK_SZ; i++) \
			spin_lock_init(&rt_hash_locks[i]); \
		}
#else
# define rt_hash_lock_addr(slot) NULL
# define rt_hash_lock_init()
#endif
L
Linus Torvalds 已提交
243 244 245 246 247 248

static struct rt_hash_bucket 	*rt_hash_table;
static unsigned			rt_hash_mask;
static int			rt_hash_log;
static unsigned int		rt_hash_rnd;

249
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
250
#define RT_CACHE_STAT_INC(field) \
251
	(__raw_get_cpu_var(rt_cache_stat).field++)
L
Linus Torvalds 已提交
252 253 254 255

static int rt_intern_hash(unsigned hash, struct rtable *rth,
				struct rtable **res);

256
static unsigned int rt_hash_code(u32 daddr, u32 saddr)
L
Linus Torvalds 已提交
257
{
258
	return (jhash_2words(daddr, saddr, rt_hash_rnd)
L
Linus Torvalds 已提交
259 260 261
		& rt_hash_mask);
}

A
Al Viro 已提交
262 263 264 265
#define rt_hash(daddr, saddr, idx) \
	rt_hash_code((__force u32)(__be32)(daddr),\
		     (__force u32)(__be32)(saddr) ^ ((idx) << 5))

L
Linus Torvalds 已提交
266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
	int bucket;
};

static struct rtable *rt_cache_get_first(struct seq_file *seq)
{
	struct rtable *r = NULL;
	struct rt_cache_iter_state *st = seq->private;

	for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
		rcu_read_lock_bh();
		r = rt_hash_table[st->bucket].chain;
		if (r)
			break;
		rcu_read_unlock_bh();
	}
	return r;
}

static struct rtable *rt_cache_get_next(struct seq_file *seq, struct rtable *r)
{
	struct rt_cache_iter_state *st = rcu_dereference(seq->private);

290
	r = r->u.dst.rt_next;
L
Linus Torvalds 已提交
291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361
	while (!r) {
		rcu_read_unlock_bh();
		if (--st->bucket < 0)
			break;
		rcu_read_lock_bh();
		r = rt_hash_table[st->bucket].chain;
	}
	return r;
}

static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
{
	struct rtable *r = rt_cache_get_first(seq);

	if (r)
		while (pos && (r = rt_cache_get_next(seq, r)))
			--pos;
	return pos ? NULL : r;
}

static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
	return *pos ? rt_cache_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}

static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct rtable *r = NULL;

	if (v == SEQ_START_TOKEN)
		r = rt_cache_get_first(seq);
	else
		r = rt_cache_get_next(seq, v);
	++*pos;
	return r;
}

static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
	if (v && v != SEQ_START_TOKEN)
		rcu_read_unlock_bh();
}

static int rt_cache_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "%-127s\n",
			   "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
			   "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
			   "HHUptod\tSpecDst");
	else {
		struct rtable *r = v;
		char temp[256];

		sprintf(temp, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t"
			      "%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X",
			r->u.dst.dev ? r->u.dst.dev->name : "*",
			(unsigned long)r->rt_dst, (unsigned long)r->rt_gateway,
			r->rt_flags, atomic_read(&r->u.dst.__refcnt),
			r->u.dst.__use, 0, (unsigned long)r->rt_src,
			(dst_metric(&r->u.dst, RTAX_ADVMSS) ?
			     (int)dst_metric(&r->u.dst, RTAX_ADVMSS) + 40 : 0),
			dst_metric(&r->u.dst, RTAX_WINDOW),
			(int)((dst_metric(&r->u.dst, RTAX_RTT) >> 3) +
			      dst_metric(&r->u.dst, RTAX_RTTVAR)),
			r->fl.fl4_tos,
			r->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1,
			r->u.dst.hh ? (r->u.dst.hh->hh_output ==
				       dev_queue_xmit) : 0,
			r->rt_spec_dst);
		seq_printf(seq, "%-127s\n", temp);
362 363
	}
	return 0;
L
Linus Torvalds 已提交
364 365
}

366
static const struct seq_operations rt_cache_seq_ops = {
L
Linus Torvalds 已提交
367 368 369 370 371 372 373 374 375 376
	.start  = rt_cache_seq_start,
	.next   = rt_cache_seq_next,
	.stop   = rt_cache_seq_stop,
	.show   = rt_cache_seq_show,
};

static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	int rc = -ENOMEM;
377
	struct rt_cache_iter_state *s;
L
Linus Torvalds 已提交
378

379
	s = kzalloc(sizeof(*s), GFP_KERNEL);
L
Linus Torvalds 已提交
380 381 382 383 384 385 386 387 388 389 390 391 392 393
	if (!s)
		goto out;
	rc = seq_open(file, &rt_cache_seq_ops);
	if (rc)
		goto out_kfree;
	seq          = file->private_data;
	seq->private = s;
out:
	return rc;
out_kfree:
	kfree(s);
	goto out;
}

394
static const struct file_operations rt_cache_seq_fops = {
L
Linus Torvalds 已提交
395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413
	.owner	 = THIS_MODULE,
	.open	 = rt_cache_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release_private,
};


static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
	int cpu;

	if (*pos == 0)
		return SEQ_START_TOKEN;

	for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
414
		return &per_cpu(rt_cache_stat, cpu);
L
Linus Torvalds 已提交
415 416 417 418 419 420 421 422 423 424 425 426
	}
	return NULL;
}

static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	int cpu;

	for (cpu = *pos; cpu < NR_CPUS; ++cpu) {
		if (!cpu_possible(cpu))
			continue;
		*pos = cpu+1;
427
		return &per_cpu(rt_cache_stat, cpu);
L
Linus Torvalds 已提交
428 429
	}
	return NULL;
430

L
Linus Torvalds 已提交
431 432 433 434 435 436 437 438 439 440 441 442
}

static void rt_cpu_seq_stop(struct seq_file *seq, void *v)
{

}

static int rt_cpu_seq_show(struct seq_file *seq, void *v)
{
	struct rt_cache_stat *st = v;

	if (v == SEQ_START_TOKEN) {
443
		seq_printf(seq, "entries  in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src  out_hit out_slow_tot out_slow_mc  gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n");
L
Linus Torvalds 已提交
444 445
		return 0;
	}
446

L
Linus Torvalds 已提交
447 448 449 450 451 452 453 454 455 456 457 458 459
	seq_printf(seq,"%08x  %08x %08x %08x %08x %08x %08x %08x "
		   " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n",
		   atomic_read(&ipv4_dst_ops.entries),
		   st->in_hit,
		   st->in_slow_tot,
		   st->in_slow_mc,
		   st->in_no_route,
		   st->in_brd,
		   st->in_martian_dst,
		   st->in_martian_src,

		   st->out_hit,
		   st->out_slow_tot,
460
		   st->out_slow_mc,
L
Linus Torvalds 已提交
461 462 463 464 465 466 467 468 469 470 471

		   st->gc_total,
		   st->gc_ignored,
		   st->gc_goal_miss,
		   st->gc_dst_overflow,
		   st->in_hlist_search,
		   st->out_hlist_search
		);
	return 0;
}

472
static const struct seq_operations rt_cpu_seq_ops = {
L
Linus Torvalds 已提交
473 474 475 476 477 478 479 480 481 482 483 484
	.start  = rt_cpu_seq_start,
	.next   = rt_cpu_seq_next,
	.stop   = rt_cpu_seq_stop,
	.show   = rt_cpu_seq_show,
};


static int rt_cpu_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &rt_cpu_seq_ops);
}

485
static const struct file_operations rt_cpu_seq_fops = {
L
Linus Torvalds 已提交
486 487 488 489 490 491 492 493
	.owner	 = THIS_MODULE,
	.open	 = rt_cpu_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = seq_release,
};

#endif /* CONFIG_PROC_FS */
494

L
Linus Torvalds 已提交
495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510
static __inline__ void rt_free(struct rtable *rt)
{
	call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}

static __inline__ void rt_drop(struct rtable *rt)
{
	ip_rt_put(rt);
	call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}

static __inline__ int rt_fast_clean(struct rtable *rth)
{
	/* Kill broadcast/multicast entries very aggresively, if they
	   collide in hash table with more useful entries */
	return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
511
		rth->fl.iif && rth->u.dst.rt_next;
L
Linus Torvalds 已提交
512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
}

static __inline__ int rt_valuable(struct rtable *rth)
{
	return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
		rth->u.dst.expires;
}

static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
{
	unsigned long age;
	int ret = 0;

	if (atomic_read(&rth->u.dst.__refcnt))
		goto out;

	ret = 1;
	if (rth->u.dst.expires &&
	    time_after_eq(jiffies, rth->u.dst.expires))
		goto out;

	age = jiffies - rth->u.dst.lastuse;
	ret = 0;
	if ((age <= tmo1 && !rt_fast_clean(rth)) ||
	    (age <= tmo2 && rt_valuable(rth)))
		goto out;
	ret = 1;
out:	return ret;
}

/* Bits of score are:
 * 31: very valuable
 * 30: not quite useless
 * 29..0: usage counter
 */
static inline u32 rt_score(struct rtable *rt)
{
	u32 score = jiffies - rt->u.dst.lastuse;

	score = ~score & ~(3<<30);

	if (rt_valuable(rt))
		score |= (1<<31);

	if (!rt->fl.iif ||
	    !(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
		score |= (1<<30);

	return score;
}

static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
565 566
	return ((__force u32)((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
		(fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr)) |
567
		(fl1->mark ^ fl2->mark) |
568 569 570 571
		(*(u16 *)&fl1->nl_u.ip4_u.tos ^
		 *(u16 *)&fl2->nl_u.ip4_u.tos) |
		(fl1->oif ^ fl2->oif) |
		(fl1->iif ^ fl2->iif)) == 0;
L
Linus Torvalds 已提交
572 573 574 575 576
}

/* This runs via a timer and thus is always in BH context. */
static void rt_check_expire(unsigned long dummy)
{
577 578
	static unsigned int rover;
	unsigned int i = rover, goal;
L
Linus Torvalds 已提交
579 580
	struct rtable *rth, **rthp;
	unsigned long now = jiffies;
581 582 583 584 585 586 587 588
	u64 mult;

	mult = ((u64)ip_rt_gc_interval) << rt_hash_log;
	if (ip_rt_gc_timeout > 1)
		do_div(mult, ip_rt_gc_timeout);
	goal = (unsigned int)mult;
	if (goal > rt_hash_mask) goal = rt_hash_mask + 1;
	for (; goal > 0; goal--) {
L
Linus Torvalds 已提交
589 590 591 592 593
		unsigned long tmo = ip_rt_gc_timeout;

		i = (i + 1) & rt_hash_mask;
		rthp = &rt_hash_table[i].chain;

594 595
		if (*rthp == 0)
			continue;
596
		spin_lock(rt_hash_lock_addr(i));
L
Linus Torvalds 已提交
597 598 599 600 601
		while ((rth = *rthp) != NULL) {
			if (rth->u.dst.expires) {
				/* Entry is expired even if it is in use */
				if (time_before_eq(now, rth->u.dst.expires)) {
					tmo >>= 1;
602
					rthp = &rth->u.dst.rt_next;
L
Linus Torvalds 已提交
603 604 605 606
					continue;
				}
			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
				tmo >>= 1;
607
				rthp = &rth->u.dst.rt_next;
L
Linus Torvalds 已提交
608 609 610 611
				continue;
			}

			/* Cleanup aged off entries. */
612
			*rthp = rth->u.dst.rt_next;
613
			rt_free(rth);
L
Linus Torvalds 已提交
614
		}
615
		spin_unlock(rt_hash_lock_addr(i));
L
Linus Torvalds 已提交
616 617 618 619 620 621

		/* Fallback loop breaker. */
		if (time_after(jiffies, now))
			break;
	}
	rover = i;
622
	mod_timer(&rt_periodic_timer, jiffies + ip_rt_gc_interval);
L
Linus Torvalds 已提交
623 624 625 626 627 628 629 630 631 632 633 634 635 636 637
}

/* This can run from both BH and non-BH contexts, the latter
 * in the case of a forced flush event.
 */
static void rt_run_flush(unsigned long dummy)
{
	int i;
	struct rtable *rth, *next;

	rt_deadline = 0;

	get_random_bytes(&rt_hash_rnd, 4);

	for (i = rt_hash_mask; i >= 0; i--) {
638
		spin_lock_bh(rt_hash_lock_addr(i));
L
Linus Torvalds 已提交
639 640 641
		rth = rt_hash_table[i].chain;
		if (rth)
			rt_hash_table[i].chain = NULL;
642
		spin_unlock_bh(rt_hash_lock_addr(i));
L
Linus Torvalds 已提交
643 644

		for (; rth; rth = next) {
645
			next = rth->u.dst.rt_next;
L
Linus Torvalds 已提交
646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674
			rt_free(rth);
		}
	}
}

static DEFINE_SPINLOCK(rt_flush_lock);

void rt_cache_flush(int delay)
{
	unsigned long now = jiffies;
	int user_mode = !in_softirq();

	if (delay < 0)
		delay = ip_rt_min_delay;

	spin_lock_bh(&rt_flush_lock);

	if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) {
		long tmo = (long)(rt_deadline - now);

		/* If flush timer is already running
		   and flush request is not immediate (delay > 0):

		   if deadline is not achieved, prolongate timer to "delay",
		   otherwise fire it at deadline time.
		 */

		if (user_mode && tmo < ip_rt_max_delay-ip_rt_min_delay)
			tmo = 0;
675

L
Linus Torvalds 已提交
676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771
		if (delay > tmo)
			delay = tmo;
	}

	if (delay <= 0) {
		spin_unlock_bh(&rt_flush_lock);
		rt_run_flush(0);
		return;
	}

	if (rt_deadline == 0)
		rt_deadline = now + ip_rt_max_delay;

	mod_timer(&rt_flush_timer, now+delay);
	spin_unlock_bh(&rt_flush_lock);
}

static void rt_secret_rebuild(unsigned long dummy)
{
	unsigned long now = jiffies;

	rt_cache_flush(0);
	mod_timer(&rt_secret_timer, now + ip_rt_secret_interval);
}

/*
   Short description of GC goals.

   We want to build algorithm, which will keep routing cache
   at some equilibrium point, when number of aged off entries
   is kept approximately equal to newly generated ones.

   Current expiration strength is variable "expire".
   We try to adjust it dynamically, so that if networking
   is idle expires is large enough to keep enough of warm entries,
   and when load increases it reduces to limit cache size.
 */

static int rt_garbage_collect(void)
{
	static unsigned long expire = RT_GC_TIMEOUT;
	static unsigned long last_gc;
	static int rover;
	static int equilibrium;
	struct rtable *rth, **rthp;
	unsigned long now = jiffies;
	int goal;

	/*
	 * Garbage collection is pretty expensive,
	 * do not make it too frequently.
	 */

	RT_CACHE_STAT_INC(gc_total);

	if (now - last_gc < ip_rt_gc_min_interval &&
	    atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) {
		RT_CACHE_STAT_INC(gc_ignored);
		goto out;
	}

	/* Calculate number of entries, which we want to expire now. */
	goal = atomic_read(&ipv4_dst_ops.entries) -
		(ip_rt_gc_elasticity << rt_hash_log);
	if (goal <= 0) {
		if (equilibrium < ipv4_dst_ops.gc_thresh)
			equilibrium = ipv4_dst_ops.gc_thresh;
		goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
		if (goal > 0) {
			equilibrium += min_t(unsigned int, goal / 2, rt_hash_mask + 1);
			goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
		}
	} else {
		/* We are in dangerous area. Try to reduce cache really
		 * aggressively.
		 */
		goal = max_t(unsigned int, goal / 2, rt_hash_mask + 1);
		equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal;
	}

	if (now - last_gc >= ip_rt_gc_min_interval)
		last_gc = now;

	if (goal <= 0) {
		equilibrium += goal;
		goto work_done;
	}

	do {
		int i, k;

		for (i = rt_hash_mask, k = rover; i >= 0; i--) {
			unsigned long tmo = expire;

			k = (k + 1) & rt_hash_mask;
			rthp = &rt_hash_table[k].chain;
772
			spin_lock_bh(rt_hash_lock_addr(k));
L
Linus Torvalds 已提交
773 774 775
			while ((rth = *rthp) != NULL) {
				if (!rt_may_expire(rth, tmo, expire)) {
					tmo >>= 1;
776
					rthp = &rth->u.dst.rt_next;
L
Linus Torvalds 已提交
777 778
					continue;
				}
779
				*rthp = rth->u.dst.rt_next;
L
Linus Torvalds 已提交
780 781 782
				rt_free(rth);
				goal--;
			}
783
			spin_unlock_bh(rt_hash_lock_addr(k));
L
Linus Torvalds 已提交
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
			if (goal <= 0)
				break;
		}
		rover = k;

		if (goal <= 0)
			goto work_done;

		/* Goal is not achieved. We stop process if:

		   - if expire reduced to zero. Otherwise, expire is halfed.
		   - if table is not full.
		   - if we are called from interrupt.
		   - jiffies check is just fallback/debug loop breaker.
		     We will not spin here for long time in any case.
		 */

		RT_CACHE_STAT_INC(gc_goal_miss);

		if (expire == 0)
			break;

		expire >>= 1;
#if RT_CACHE_DEBUG >= 2
		printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire,
				atomic_read(&ipv4_dst_ops.entries), goal, i);
#endif

		if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
			goto out;
	} while (!in_softirq() && time_before_eq(jiffies, now));

	if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
		goto out;
	if (net_ratelimit())
		printk(KERN_WARNING "dst cache overflow\n");
	RT_CACHE_STAT_INC(gc_dst_overflow);
	return 1;

work_done:
	expire += ip_rt_gc_min_interval;
	if (expire > ip_rt_gc_timeout ||
	    atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh)
		expire = ip_rt_gc_timeout;
#if RT_CACHE_DEBUG >= 2
	printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire,
			atomic_read(&ipv4_dst_ops.entries), goal, rover);
#endif
out:	return 0;
}

static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp)
{
	struct rtable	*rth, **rthp;
	unsigned long	now;
	struct rtable *cand, **candp;
	u32 		min_score;
	int		chain_length;
	int attempts = !in_softirq();

restart:
	chain_length = 0;
	min_score = ~(u32)0;
	cand = NULL;
	candp = NULL;
	now = jiffies;

	rthp = &rt_hash_table[hash].chain;

853
	spin_lock_bh(rt_hash_lock_addr(hash));
L
Linus Torvalds 已提交
854 855 856
	while ((rth = *rthp) != NULL) {
		if (compare_keys(&rth->fl, &rt->fl)) {
			/* Put it first */
857
			*rthp = rth->u.dst.rt_next;
L
Linus Torvalds 已提交
858 859 860 861 862
			/*
			 * Since lookup is lockfree, the deletion
			 * must be visible to another weakly ordered CPU before
			 * the insertion at the start of the hash chain.
			 */
863
			rcu_assign_pointer(rth->u.dst.rt_next,
L
Linus Torvalds 已提交
864 865 866 867 868 869 870 871 872 873
					   rt_hash_table[hash].chain);
			/*
			 * Since lookup is lockfree, the update writes
			 * must be ordered for consistency on SMP.
			 */
			rcu_assign_pointer(rt_hash_table[hash].chain, rth);

			rth->u.dst.__use++;
			dst_hold(&rth->u.dst);
			rth->u.dst.lastuse = now;
874
			spin_unlock_bh(rt_hash_lock_addr(hash));
L
Linus Torvalds 已提交
875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892

			rt_drop(rt);
			*rp = rth;
			return 0;
		}

		if (!atomic_read(&rth->u.dst.__refcnt)) {
			u32 score = rt_score(rth);

			if (score <= min_score) {
				cand = rth;
				candp = rthp;
				min_score = score;
			}
		}

		chain_length++;

893
		rthp = &rth->u.dst.rt_next;
L
Linus Torvalds 已提交
894 895 896 897 898 899 900 901 902 903
	}

	if (cand) {
		/* ip_rt_gc_elasticity used to be average length of chain
		 * length, when exceeded gc becomes really aggressive.
		 *
		 * The second limit is less certain. At the moment it allows
		 * only 2 entries per bucket. We will see.
		 */
		if (chain_length > ip_rt_gc_elasticity) {
904
			*candp = cand->u.dst.rt_next;
L
Linus Torvalds 已提交
905 906 907 908 909 910 911 912 913 914
			rt_free(cand);
		}
	}

	/* Try to bind route to arp only if it is output
	   route or unicast forwarding path.
	 */
	if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) {
		int err = arp_bind_neighbour(&rt->u.dst);
		if (err) {
915
			spin_unlock_bh(rt_hash_lock_addr(hash));
L
Linus Torvalds 已提交
916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943

			if (err != -ENOBUFS) {
				rt_drop(rt);
				return err;
			}

			/* Neighbour tables are full and nothing
			   can be released. Try to shrink route cache,
			   it is most likely it holds some neighbour records.
			 */
			if (attempts-- > 0) {
				int saved_elasticity = ip_rt_gc_elasticity;
				int saved_int = ip_rt_gc_min_interval;
				ip_rt_gc_elasticity	= 1;
				ip_rt_gc_min_interval	= 0;
				rt_garbage_collect();
				ip_rt_gc_min_interval	= saved_int;
				ip_rt_gc_elasticity	= saved_elasticity;
				goto restart;
			}

			if (net_ratelimit())
				printk(KERN_WARNING "Neighbour table overflow.\n");
			rt_drop(rt);
			return -ENOBUFS;
		}
	}

944
	rt->u.dst.rt_next = rt_hash_table[hash].chain;
L
Linus Torvalds 已提交
945
#if RT_CACHE_DEBUG >= 2
946
	if (rt->u.dst.rt_next) {
L
Linus Torvalds 已提交
947 948 949
		struct rtable *trt;
		printk(KERN_DEBUG "rt_cache @%02x: %u.%u.%u.%u", hash,
		       NIPQUAD(rt->rt_dst));
950
		for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next)
L
Linus Torvalds 已提交
951 952 953 954 955
			printk(" . %u.%u.%u.%u", NIPQUAD(trt->rt_dst));
		printk("\n");
	}
#endif
	rt_hash_table[hash].chain = rt;
956
	spin_unlock_bh(rt_hash_lock_addr(hash));
L
Linus Torvalds 已提交
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
	*rp = rt;
	return 0;
}

void rt_bind_peer(struct rtable *rt, int create)
{
	static DEFINE_SPINLOCK(rt_peer_lock);
	struct inet_peer *peer;

	peer = inet_getpeer(rt->rt_dst, create);

	spin_lock_bh(&rt_peer_lock);
	if (rt->peer == NULL) {
		rt->peer = peer;
		peer = NULL;
	}
	spin_unlock_bh(&rt_peer_lock);
	if (peer)
		inet_putpeer(peer);
}

/*
 * Peer allocation may fail only in serious out-of-memory conditions.  However
 * we still can generate some output.
 * Random ID selection looks a bit dangerous because we have no chances to
 * select ID being unique in a reasonable period of time.
 * But broken packet identifier may be better than no packet at all.
 */
static void ip_select_fb_ident(struct iphdr *iph)
{
	static DEFINE_SPINLOCK(ip_fb_id_lock);
	static u32 ip_fallback_id;
	u32 salt;

	spin_lock_bh(&ip_fb_id_lock);
992
	salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
L
Linus Torvalds 已提交
993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013
	iph->id = htons(salt & 0xFFFF);
	ip_fallback_id = salt;
	spin_unlock_bh(&ip_fb_id_lock);
}

void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
{
	struct rtable *rt = (struct rtable *) dst;

	if (rt) {
		if (rt->peer == NULL)
			rt_bind_peer(rt, 1);

		/* If peer is attached to destination, it is never detached,
		   so that we need not to grab a lock to dereference it.
		 */
		if (rt->peer) {
			iph->id = htons(inet_getid(rt->peer, more));
			return;
		}
	} else
1014
		printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
1015
		       __builtin_return_address(0));
L
Linus Torvalds 已提交
1016 1017 1018 1019 1020 1021 1022 1023

	ip_select_fb_ident(iph);
}

static void rt_del(unsigned hash, struct rtable *rt)
{
	struct rtable **rthp;

1024
	spin_lock_bh(rt_hash_lock_addr(hash));
L
Linus Torvalds 已提交
1025 1026
	ip_rt_put(rt);
	for (rthp = &rt_hash_table[hash].chain; *rthp;
1027
	     rthp = &(*rthp)->u.dst.rt_next)
L
Linus Torvalds 已提交
1028
		if (*rthp == rt) {
1029
			*rthp = rt->u.dst.rt_next;
L
Linus Torvalds 已提交
1030 1031 1032
			rt_free(rt);
			break;
		}
1033
	spin_unlock_bh(rt_hash_lock_addr(hash));
L
Linus Torvalds 已提交
1034 1035
}

A
Al Viro 已提交
1036 1037
void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
		    __be32 saddr, struct net_device *dev)
L
Linus Torvalds 已提交
1038 1039 1040 1041
{
	int i, k;
	struct in_device *in_dev = in_dev_get(dev);
	struct rtable *rth, **rthp;
A
Al Viro 已提交
1042
	__be32  skeys[2] = { saddr, 0 };
L
Linus Torvalds 已提交
1043
	int  ikeys[2] = { dev->ifindex, 0 };
1044
	struct netevent_redirect netevent;
L
Linus Torvalds 已提交
1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064

	if (!in_dev)
		return;

	if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
	    || MULTICAST(new_gw) || BADCLASS(new_gw) || ZERONET(new_gw))
		goto reject_redirect;

	if (!IN_DEV_SHARED_MEDIA(in_dev)) {
		if (!inet_addr_onlink(in_dev, new_gw, old_gw))
			goto reject_redirect;
		if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
			goto reject_redirect;
	} else {
		if (inet_addr_type(new_gw) != RTN_UNICAST)
			goto reject_redirect;
	}

	for (i = 0; i < 2; i++) {
		for (k = 0; k < 2; k++) {
A
Al Viro 已提交
1065
			unsigned hash = rt_hash(daddr, skeys[i], ikeys[k]);
L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076

			rthp=&rt_hash_table[hash].chain;

			rcu_read_lock();
			while ((rth = rcu_dereference(*rthp)) != NULL) {
				struct rtable *rt;

				if (rth->fl.fl4_dst != daddr ||
				    rth->fl.fl4_src != skeys[i] ||
				    rth->fl.oif != ikeys[k] ||
				    rth->fl.iif != 0) {
1077
					rthp = &rth->u.dst.rt_next;
L
Linus Torvalds 已提交
1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099
					continue;
				}

				if (rth->rt_dst != daddr ||
				    rth->rt_src != saddr ||
				    rth->u.dst.error ||
				    rth->rt_gateway != old_gw ||
				    rth->u.dst.dev != dev)
					break;

				dst_hold(&rth->u.dst);
				rcu_read_unlock();

				rt = dst_alloc(&ipv4_dst_ops);
				if (rt == NULL) {
					ip_rt_put(rth);
					in_dev_put(in_dev);
					return;
				}

				/* Copy all the information. */
				*rt = *rth;
1100
				INIT_RCU_HEAD(&rt->u.dst.rcu_head);
L
Linus Torvalds 已提交
1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134
				rt->u.dst.__use		= 1;
				atomic_set(&rt->u.dst.__refcnt, 1);
				rt->u.dst.child		= NULL;
				if (rt->u.dst.dev)
					dev_hold(rt->u.dst.dev);
				if (rt->idev)
					in_dev_hold(rt->idev);
				rt->u.dst.obsolete	= 0;
				rt->u.dst.lastuse	= jiffies;
				rt->u.dst.path		= &rt->u.dst;
				rt->u.dst.neighbour	= NULL;
				rt->u.dst.hh		= NULL;
				rt->u.dst.xfrm		= NULL;

				rt->rt_flags		|= RTCF_REDIRECTED;

				/* Gateway is different ... */
				rt->rt_gateway		= new_gw;

				/* Redirect received -> path was valid */
				dst_confirm(&rth->u.dst);

				if (rt->peer)
					atomic_inc(&rt->peer->refcnt);

				if (arp_bind_neighbour(&rt->u.dst) ||
				    !(rt->u.dst.neighbour->nud_state &
					    NUD_VALID)) {
					if (rt->u.dst.neighbour)
						neigh_event_send(rt->u.dst.neighbour, NULL);
					ip_rt_put(rth);
					rt_drop(rt);
					goto do_next;
				}
1135

1136 1137
				netevent.old = &rth->u.dst;
				netevent.new = &rt->u.dst;
1138 1139
				call_netevent_notifiers(NETEVENT_REDIRECT,
							&netevent);
L
Linus Torvalds 已提交
1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158

				rt_del(hash, rth);
				if (!rt_intern_hash(hash, rt, &rt))
					ip_rt_put(rt);
				goto do_next;
			}
			rcu_read_unlock();
		do_next:
			;
		}
	}
	in_dev_put(in_dev);
	return;

reject_redirect:
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
		printk(KERN_INFO "Redirect from %u.%u.%u.%u on %s about "
			"%u.%u.%u.%u ignored.\n"
1159
			"  Advised path = %u.%u.%u.%u -> %u.%u.%u.%u\n",
L
Linus Torvalds 已提交
1160
		       NIPQUAD(old_gw), dev->name, NIPQUAD(new_gw),
1161
		       NIPQUAD(saddr), NIPQUAD(daddr));
L
Linus Torvalds 已提交
1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176
#endif
	in_dev_put(in_dev);
}

static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
{
	struct rtable *rt = (struct rtable*)dst;
	struct dst_entry *ret = dst;

	if (rt) {
		if (dst->obsolete) {
			ip_rt_put(rt);
			ret = NULL;
		} else if ((rt->rt_flags & RTCF_REDIRECTED) ||
			   rt->u.dst.expires) {
A
Al Viro 已提交
1177 1178
			unsigned hash = rt_hash(rt->fl.fl4_dst, rt->fl.fl4_src,
						rt->fl.oif);
L
Linus Torvalds 已提交
1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234
#if RT_CACHE_DEBUG >= 1
			printk(KERN_DEBUG "ip_rt_advice: redirect to "
					  "%u.%u.%u.%u/%02x dropped\n",
				NIPQUAD(rt->rt_dst), rt->fl.fl4_tos);
#endif
			rt_del(hash, rt);
			ret = NULL;
		}
	}
	return ret;
}

/*
 * Algorithm:
 *	1. The first ip_rt_redirect_number redirects are sent
 *	   with exponential backoff, then we stop sending them at all,
 *	   assuming that the host ignores our redirects.
 *	2. If we did not see packets requiring redirects
 *	   during ip_rt_redirect_silence, we assume that the host
 *	   forgot redirected route and start to send redirects again.
 *
 * This algorithm is much cheaper and more intelligent than dumb load limiting
 * in icmp.c.
 *
 * NOTE. Do not forget to inhibit load limiting for redirects (redundant)
 * and "frag. need" (breaks PMTU discovery) in icmp.c.
 */

void ip_rt_send_redirect(struct sk_buff *skb)
{
	struct rtable *rt = (struct rtable*)skb->dst;
	struct in_device *in_dev = in_dev_get(rt->u.dst.dev);

	if (!in_dev)
		return;

	if (!IN_DEV_TX_REDIRECTS(in_dev))
		goto out;

	/* No redirected packets during ip_rt_redirect_silence;
	 * reset the algorithm.
	 */
	if (time_after(jiffies, rt->u.dst.rate_last + ip_rt_redirect_silence))
		rt->u.dst.rate_tokens = 0;

	/* Too many ignored redirects; do not send anything
	 * set u.dst.rate_last to the last seen redirected packet.
	 */
	if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) {
		rt->u.dst.rate_last = jiffies;
		goto out;
	}

	/* Check for load limit; set rate_last to the latest sent
	 * redirect.
	 */
1235 1236
	if (rt->u.dst.rate_tokens == 0 ||
	    time_after(jiffies,
L
Linus Torvalds 已提交
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252
		       (rt->u.dst.rate_last +
			(ip_rt_redirect_load << rt->u.dst.rate_tokens)))) {
		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
		rt->u.dst.rate_last = jiffies;
		++rt->u.dst.rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
		if (IN_DEV_LOG_MARTIANS(in_dev) &&
		    rt->u.dst.rate_tokens == ip_rt_redirect_number &&
		    net_ratelimit())
			printk(KERN_WARNING "host %u.%u.%u.%u/if%d ignores "
				"redirects for %u.%u.%u.%u to %u.%u.%u.%u.\n",
				NIPQUAD(rt->rt_src), rt->rt_iif,
				NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_gateway));
#endif
	}
out:
1253
	in_dev_put(in_dev);
L
Linus Torvalds 已提交
1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288
}

static int ip_error(struct sk_buff *skb)
{
	struct rtable *rt = (struct rtable*)skb->dst;
	unsigned long now;
	int code;

	switch (rt->u.dst.error) {
		case EINVAL:
		default:
			goto out;
		case EHOSTUNREACH:
			code = ICMP_HOST_UNREACH;
			break;
		case ENETUNREACH:
			code = ICMP_NET_UNREACH;
			break;
		case EACCES:
			code = ICMP_PKT_FILTERED;
			break;
	}

	now = jiffies;
	rt->u.dst.rate_tokens += now - rt->u.dst.rate_last;
	if (rt->u.dst.rate_tokens > ip_rt_error_burst)
		rt->u.dst.rate_tokens = ip_rt_error_burst;
	rt->u.dst.rate_last = now;
	if (rt->u.dst.rate_tokens >= ip_rt_error_cost) {
		rt->u.dst.rate_tokens -= ip_rt_error_cost;
		icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
	}

out:	kfree_skb(skb);
	return 0;
1289
}
L
Linus Torvalds 已提交
1290 1291 1292 1293 1294 1295

/*
 *	The last two values are not from the RFC but
 *	are needed for AMPRnet AX.25 paths.
 */

1296
static const unsigned short mtu_plateau[] =
L
Linus Torvalds 已提交
1297 1298 1299 1300 1301
{32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 };

static __inline__ unsigned short guess_mtu(unsigned short old_mtu)
{
	int i;
1302

L
Linus Torvalds 已提交
1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313
	for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++)
		if (old_mtu > mtu_plateau[i])
			return mtu_plateau[i];
	return 68;
}

unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
{
	int i;
	unsigned short old_mtu = ntohs(iph->tot_len);
	struct rtable *rth;
1314 1315
	__be32  skeys[2] = { iph->saddr, 0, };
	__be32  daddr = iph->daddr;
L
Linus Torvalds 已提交
1316 1317 1318 1319 1320 1321
	unsigned short est_mtu = 0;

	if (ipv4_config.no_pmtu_disc)
		return 0;

	for (i = 0; i < 2; i++) {
A
Al Viro 已提交
1322
		unsigned hash = rt_hash(daddr, skeys[i], 0);
L
Linus Torvalds 已提交
1323 1324 1325

		rcu_read_lock();
		for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
1326
		     rth = rcu_dereference(rth->u.dst.rt_next)) {
L
Linus Torvalds 已提交
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345
			if (rth->fl.fl4_dst == daddr &&
			    rth->fl.fl4_src == skeys[i] &&
			    rth->rt_dst  == daddr &&
			    rth->rt_src  == iph->saddr &&
			    rth->fl.iif == 0 &&
			    !(dst_metric_locked(&rth->u.dst, RTAX_MTU))) {
				unsigned short mtu = new_mtu;

				if (new_mtu < 68 || new_mtu >= old_mtu) {

					/* BSD 4.2 compatibility hack :-( */
					if (mtu == 0 &&
					    old_mtu >= rth->u.dst.metrics[RTAX_MTU-1] &&
					    old_mtu >= 68 + (iph->ihl << 2))
						old_mtu -= iph->ihl << 2;

					mtu = guess_mtu(old_mtu);
				}
				if (mtu <= rth->u.dst.metrics[RTAX_MTU-1]) {
1346
					if (mtu < rth->u.dst.metrics[RTAX_MTU-1]) {
L
Linus Torvalds 已提交
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
						dst_confirm(&rth->u.dst);
						if (mtu < ip_rt_min_pmtu) {
							mtu = ip_rt_min_pmtu;
							rth->u.dst.metrics[RTAX_LOCK-1] |=
								(1 << RTAX_MTU);
						}
						rth->u.dst.metrics[RTAX_MTU-1] = mtu;
						dst_set_expires(&rth->u.dst,
							ip_rt_mtu_expires);
					}
					est_mtu = mtu;
				}
			}
		}
		rcu_read_unlock();
	}
	return est_mtu ? : new_mtu;
}

static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
	if (dst->metrics[RTAX_MTU-1] > mtu && mtu >= 68 &&
	    !(dst_metric_locked(dst, RTAX_MTU))) {
		if (mtu < ip_rt_min_pmtu) {
			mtu = ip_rt_min_pmtu;
			dst->metrics[RTAX_LOCK-1] |= (1 << RTAX_MTU);
		}
		dst->metrics[RTAX_MTU-1] = mtu;
		dst_set_expires(dst, ip_rt_mtu_expires);
1376
		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
L
Linus Torvalds 已提交
1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429
	}
}

static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
	return NULL;
}

static void ipv4_dst_destroy(struct dst_entry *dst)
{
	struct rtable *rt = (struct rtable *) dst;
	struct inet_peer *peer = rt->peer;
	struct in_device *idev = rt->idev;

	if (peer) {
		rt->peer = NULL;
		inet_putpeer(peer);
	}

	if (idev) {
		rt->idev = NULL;
		in_dev_put(idev);
	}
}

static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			    int how)
{
	struct rtable *rt = (struct rtable *) dst;
	struct in_device *idev = rt->idev;
	if (dev != &loopback_dev && idev && idev->dev == dev) {
		struct in_device *loopback_idev = in_dev_get(&loopback_dev);
		if (loopback_idev) {
			rt->idev = loopback_idev;
			in_dev_put(idev);
		}
	}
}

static void ipv4_link_failure(struct sk_buff *skb)
{
	struct rtable *rt;

	icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);

	rt = (struct rtable *) skb->dst;
	if (rt)
		dst_set_expires(&rt->u.dst, 0);
}

static int ip_rt_bug(struct sk_buff *skb)
{
	printk(KERN_DEBUG "ip_rt_bug: %u.%u.%u.%u -> %u.%u.%u.%u, %s\n",
1430
		NIPQUAD(ip_hdr(skb)->saddr), NIPQUAD(ip_hdr(skb)->daddr),
L
Linus Torvalds 已提交
1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446
		skb->dev ? skb->dev->name : "?");
	kfree_skb(skb);
	return 0;
}

/*
   We do not cache source address of outgoing interface,
   because it is used only by IP RR, TS and SRR options,
   so that it out of fast path.

   BTW remember: "addr" is allowed to be not aligned
   in IP options!
 */

void ip_rt_get_source(u8 *addr, struct rtable *rt)
{
A
Al Viro 已提交
1447
	__be32 src;
L
Linus Torvalds 已提交
1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509
	struct fib_result res;

	if (rt->fl.iif == 0)
		src = rt->rt_src;
	else if (fib_lookup(&rt->fl, &res) == 0) {
		src = FIB_RES_PREFSRC(res);
		fib_res_put(&res);
	} else
		src = inet_select_addr(rt->u.dst.dev, rt->rt_gateway,
					RT_SCOPE_UNIVERSE);
	memcpy(addr, &src, 4);
}

#ifdef CONFIG_NET_CLS_ROUTE
static void set_class_tag(struct rtable *rt, u32 tag)
{
	if (!(rt->u.dst.tclassid & 0xFFFF))
		rt->u.dst.tclassid |= tag & 0xFFFF;
	if (!(rt->u.dst.tclassid & 0xFFFF0000))
		rt->u.dst.tclassid |= tag & 0xFFFF0000;
}
#endif

static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
{
	struct fib_info *fi = res->fi;

	if (fi) {
		if (FIB_RES_GW(*res) &&
		    FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
			rt->rt_gateway = FIB_RES_GW(*res);
		memcpy(rt->u.dst.metrics, fi->fib_metrics,
		       sizeof(rt->u.dst.metrics));
		if (fi->fib_mtu == 0) {
			rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu;
			if (rt->u.dst.metrics[RTAX_LOCK-1] & (1 << RTAX_MTU) &&
			    rt->rt_gateway != rt->rt_dst &&
			    rt->u.dst.dev->mtu > 576)
				rt->u.dst.metrics[RTAX_MTU-1] = 576;
		}
#ifdef CONFIG_NET_CLS_ROUTE
		rt->u.dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
	} else
		rt->u.dst.metrics[RTAX_MTU-1]= rt->u.dst.dev->mtu;

	if (rt->u.dst.metrics[RTAX_HOPLIMIT-1] == 0)
		rt->u.dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl;
	if (rt->u.dst.metrics[RTAX_MTU-1] > IP_MAX_MTU)
		rt->u.dst.metrics[RTAX_MTU-1] = IP_MAX_MTU;
	if (rt->u.dst.metrics[RTAX_ADVMSS-1] == 0)
		rt->u.dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->u.dst.dev->mtu - 40,
				       ip_rt_min_advmss);
	if (rt->u.dst.metrics[RTAX_ADVMSS-1] > 65535 - 40)
		rt->u.dst.metrics[RTAX_ADVMSS-1] = 65535 - 40;

#ifdef CONFIG_NET_CLS_ROUTE
#ifdef CONFIG_IP_MULTIPLE_TABLES
	set_class_tag(rt, fib_rules_tclass(res));
#endif
	set_class_tag(rt, itag);
#endif
1510
	rt->rt_type = res->type;
L
Linus Torvalds 已提交
1511 1512
}

A
Al Viro 已提交
1513
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
L
Linus Torvalds 已提交
1514 1515 1516 1517
				u8 tos, struct net_device *dev, int our)
{
	unsigned hash;
	struct rtable *rth;
A
Al Viro 已提交
1518
	__be32 spec_dst;
L
Linus Torvalds 已提交
1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546
	struct in_device *in_dev = in_dev_get(dev);
	u32 itag = 0;

	/* Primary sanity checks. */

	if (in_dev == NULL)
		return -EINVAL;

	if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr) ||
	    skb->protocol != htons(ETH_P_IP))
		goto e_inval;

	if (ZERONET(saddr)) {
		if (!LOCAL_MCAST(daddr))
			goto e_inval;
		spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
	} else if (fib_validate_source(saddr, 0, tos, 0,
					dev, &spec_dst, &itag) < 0)
		goto e_inval;

	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	rth->u.dst.output= ip_rt_bug;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
1547
	if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
L
Linus Torvalds 已提交
1548 1549 1550 1551
		rth->u.dst.flags |= DST_NOPOLICY;
	rth->fl.fl4_dst	= daddr;
	rth->rt_dst	= daddr;
	rth->fl.fl4_tos	= tos;
1552
	rth->fl.mark    = skb->mark;
L
Linus Torvalds 已提交
1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579
	rth->fl.fl4_src	= saddr;
	rth->rt_src	= saddr;
#ifdef CONFIG_NET_CLS_ROUTE
	rth->u.dst.tclassid = itag;
#endif
	rth->rt_iif	=
	rth->fl.iif	= dev->ifindex;
	rth->u.dst.dev	= &loopback_dev;
	dev_hold(rth->u.dst.dev);
	rth->idev	= in_dev_get(rth->u.dst.dev);
	rth->fl.oif	= 0;
	rth->rt_gateway	= daddr;
	rth->rt_spec_dst= spec_dst;
	rth->rt_type	= RTN_MULTICAST;
	rth->rt_flags	= RTCF_MULTICAST;
	if (our) {
		rth->u.dst.input= ip_local_deliver;
		rth->rt_flags |= RTCF_LOCAL;
	}

#ifdef CONFIG_IP_MROUTE
	if (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
		rth->u.dst.input = ip_mr_input;
#endif
	RT_CACHE_STAT_INC(in_slow_mc);

	in_dev_put(in_dev);
A
Al Viro 已提交
1580
	hash = rt_hash(daddr, saddr, dev->ifindex);
L
Linus Torvalds 已提交
1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595
	return rt_intern_hash(hash, rth, (struct rtable**) &skb->dst);

e_nobufs:
	in_dev_put(in_dev);
	return -ENOBUFS;

e_inval:
	in_dev_put(in_dev);
	return -EINVAL;
}


static void ip_handle_martian_source(struct net_device *dev,
				     struct in_device *in_dev,
				     struct sk_buff *skb,
A
Al Viro 已提交
1596 1597
				     __be32 daddr,
				     __be32 saddr)
L
Linus Torvalds 已提交
1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608
{
	RT_CACHE_STAT_INC(in_martian_src);
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) {
		/*
		 *	RFC1812 recommendation, if source is martian,
		 *	the only hint is MAC header.
		 */
		printk(KERN_WARNING "martian source %u.%u.%u.%u from "
			"%u.%u.%u.%u, on dev %s\n",
			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
1609
		if (dev->hard_header_len && skb_mac_header_was_set(skb)) {
L
Linus Torvalds 已提交
1610
			int i;
1611
			const unsigned char *p = skb_mac_header(skb);
L
Linus Torvalds 已提交
1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623
			printk(KERN_WARNING "ll header: ");
			for (i = 0; i < dev->hard_header_len; i++, p++) {
				printk("%02x", *p);
				if (i < (dev->hard_header_len - 1))
					printk(":");
			}
			printk("\n");
		}
	}
#endif
}

1624 1625 1626
static inline int __mkroute_input(struct sk_buff *skb,
				  struct fib_result* res,
				  struct in_device *in_dev,
A
Al Viro 已提交
1627
				  __be32 daddr, __be32 saddr, u32 tos,
1628
				  struct rtable **result)
L
Linus Torvalds 已提交
1629 1630 1631 1632 1633 1634
{

	struct rtable *rth;
	int err;
	struct in_device *out_dev;
	unsigned flags = 0;
1635 1636
	__be32 spec_dst;
	u32 itag;
L
Linus Torvalds 已提交
1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647

	/* get a working reference to the output device */
	out_dev = in_dev_get(FIB_RES_DEV(*res));
	if (out_dev == NULL) {
		if (net_ratelimit())
			printk(KERN_CRIT "Bug in ip_route_input" \
			       "_slow(). Please, report\n");
		return -EINVAL;
	}


1648
	err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res),
L
Linus Torvalds 已提交
1649 1650
				  in_dev->dev, &spec_dst, &itag);
	if (err < 0) {
1651
		ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
L
Linus Torvalds 已提交
1652
					 saddr);
1653

L
Linus Torvalds 已提交
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
		err = -EINVAL;
		goto cleanup;
	}

	if (err)
		flags |= RTCF_DIRECTSRC;

	if (out_dev == in_dev && err && !(flags & (RTCF_NAT | RTCF_MASQ)) &&
	    (IN_DEV_SHARED_MEDIA(out_dev) ||
	     inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
		flags |= RTCF_DOREDIRECT;

	if (skb->protocol != htons(ETH_P_IP)) {
		/* Not IP (i.e. ARP). Do not create route, if it is
		 * invalid for proxy arp. DNAT routes are always valid.
		 */
		if (out_dev == in_dev && !(flags & RTCF_DNAT)) {
			err = -EINVAL;
			goto cleanup;
		}
	}


	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth) {
		err = -ENOBUFS;
		goto cleanup;
	}

1683
	atomic_set(&rth->u.dst.__refcnt, 1);
L
Linus Torvalds 已提交
1684
	rth->u.dst.flags= DST_HOST;
1685
	if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
L
Linus Torvalds 已提交
1686
		rth->u.dst.flags |= DST_NOPOLICY;
1687
	if (IN_DEV_CONF_GET(out_dev, NOXFRM))
L
Linus Torvalds 已提交
1688 1689 1690 1691
		rth->u.dst.flags |= DST_NOXFRM;
	rth->fl.fl4_dst	= daddr;
	rth->rt_dst	= daddr;
	rth->fl.fl4_tos	= tos;
1692
	rth->fl.mark    = skb->mark;
L
Linus Torvalds 已提交
1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716
	rth->fl.fl4_src	= saddr;
	rth->rt_src	= saddr;
	rth->rt_gateway	= daddr;
	rth->rt_iif 	=
		rth->fl.iif	= in_dev->dev->ifindex;
	rth->u.dst.dev	= (out_dev)->dev;
	dev_hold(rth->u.dst.dev);
	rth->idev	= in_dev_get(rth->u.dst.dev);
	rth->fl.oif 	= 0;
	rth->rt_spec_dst= spec_dst;

	rth->u.dst.input = ip_forward;
	rth->u.dst.output = ip_output;

	rt_set_nexthop(rth, res, itag);

	rth->rt_flags = flags;

	*result = rth;
	err = 0;
 cleanup:
	/* release the working reference to the output device */
	in_dev_put(out_dev);
	return err;
1717
}
L
Linus Torvalds 已提交
1718

1719 1720 1721 1722 1723
static inline int ip_mkroute_input(struct sk_buff *skb,
				   struct fib_result* res,
				   const struct flowi *fl,
				   struct in_device *in_dev,
				   __be32 daddr, __be32 saddr, u32 tos)
L
Linus Torvalds 已提交
1724
{
C
Chuck Short 已提交
1725
	struct rtable* rth = NULL;
L
Linus Torvalds 已提交
1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739
	int err;
	unsigned hash;

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (res->fi && res->fi->fib_nhs > 1 && fl->oif == 0)
		fib_select_multipath(fl, res);
#endif

	/* create a routing cache entry */
	err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth);
	if (err)
		return err;

	/* put it into the cache */
A
Al Viro 已提交
1740
	hash = rt_hash(daddr, saddr, fl->iif);
1741
	return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
L
Linus Torvalds 已提交
1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753
}

/*
 *	NOTE. We drop all the packets that has local source
 *	addresses, because every properly looped back packet
 *	must have correct destination already attached by output routine.
 *
 *	Such approach solves two big problems:
 *	1. Not simplex devices are handled properly.
 *	2. IP spoofing attempts are filtered with 100% of guarantee.
 */

A
Al Viro 已提交
1754
static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
L
Linus Torvalds 已提交
1755 1756 1757 1758 1759 1760 1761 1762 1763 1764
			       u8 tos, struct net_device *dev)
{
	struct fib_result res;
	struct in_device *in_dev = in_dev_get(dev);
	struct flowi fl = { .nl_u = { .ip4_u =
				      { .daddr = daddr,
					.saddr = saddr,
					.tos = tos,
					.scope = RT_SCOPE_UNIVERSE,
				      } },
1765
			    .mark = skb->mark,
L
Linus Torvalds 已提交
1766 1767 1768 1769 1770
			    .iif = dev->ifindex };
	unsigned	flags = 0;
	u32		itag = 0;
	struct rtable * rth;
	unsigned	hash;
A
Al Viro 已提交
1771
	__be32		spec_dst;
L
Linus Torvalds 已提交
1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786
	int		err = -EINVAL;
	int		free_res = 0;

	/* IP on this device is disabled. */

	if (!in_dev)
		goto out;

	/* Check for the most weird martians, which can be not detected
	   by fib_lookup.
	 */

	if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr))
		goto martian_source;

1787
	if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0))
L
Linus Torvalds 已提交
1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803
		goto brd_input;

	/* Accept zero addresses only to limited broadcast;
	 * I even do not know to fix it or not. Waiting for complains :-)
	 */
	if (ZERONET(saddr))
		goto martian_source;

	if (BADCLASS(daddr) || ZERONET(daddr) || LOOPBACK(daddr))
		goto martian_destination;

	/*
	 *	Now we are ready to route packet.
	 */
	if ((err = fib_lookup(&fl, &res)) != 0) {
		if (!IN_DEV_FORWARD(in_dev))
1804
			goto e_hostunreach;
L
Linus Torvalds 已提交
1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827
		goto no_route;
	}
	free_res = 1;

	RT_CACHE_STAT_INC(in_slow_tot);

	if (res.type == RTN_BROADCAST)
		goto brd_input;

	if (res.type == RTN_LOCAL) {
		int result;
		result = fib_validate_source(saddr, daddr, tos,
					     loopback_dev.ifindex,
					     dev, &spec_dst, &itag);
		if (result < 0)
			goto martian_source;
		if (result)
			flags |= RTCF_DIRECTSRC;
		spec_dst = daddr;
		goto local_input;
	}

	if (!IN_DEV_FORWARD(in_dev))
1828
		goto e_hostunreach;
L
Linus Torvalds 已提交
1829 1830 1831 1832 1833 1834 1835 1836
	if (res.type != RTN_UNICAST)
		goto martian_destination;

	err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos);
	if (err == -ENOBUFS)
		goto e_nobufs;
	if (err == -EINVAL)
		goto e_inval;
1837

L
Linus Torvalds 已提交
1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870
done:
	in_dev_put(in_dev);
	if (free_res)
		fib_res_put(&res);
out:	return err;

brd_input:
	if (skb->protocol != htons(ETH_P_IP))
		goto e_inval;

	if (ZERONET(saddr))
		spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
	else {
		err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
					  &itag);
		if (err < 0)
			goto martian_source;
		if (err)
			flags |= RTCF_DIRECTSRC;
	}
	flags |= RTCF_BROADCAST;
	res.type = RTN_BROADCAST;
	RT_CACHE_STAT_INC(in_brd);

local_input:
	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	rth->u.dst.output= ip_rt_bug;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
1871
	if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
L
Linus Torvalds 已提交
1872 1873 1874 1875
		rth->u.dst.flags |= DST_NOPOLICY;
	rth->fl.fl4_dst	= daddr;
	rth->rt_dst	= daddr;
	rth->fl.fl4_tos	= tos;
1876
	rth->fl.mark    = skb->mark;
L
Linus Torvalds 已提交
1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896
	rth->fl.fl4_src	= saddr;
	rth->rt_src	= saddr;
#ifdef CONFIG_NET_CLS_ROUTE
	rth->u.dst.tclassid = itag;
#endif
	rth->rt_iif	=
	rth->fl.iif	= dev->ifindex;
	rth->u.dst.dev	= &loopback_dev;
	dev_hold(rth->u.dst.dev);
	rth->idev	= in_dev_get(rth->u.dst.dev);
	rth->rt_gateway	= daddr;
	rth->rt_spec_dst= spec_dst;
	rth->u.dst.input= ip_local_deliver;
	rth->rt_flags 	= flags|RTCF_LOCAL;
	if (res.type == RTN_UNREACHABLE) {
		rth->u.dst.input= ip_error;
		rth->u.dst.error= -err;
		rth->rt_flags 	&= ~RTCF_LOCAL;
	}
	rth->rt_type	= res.type;
A
Al Viro 已提交
1897
	hash = rt_hash(daddr, saddr, fl.iif);
L
Linus Torvalds 已提交
1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917
	err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
	goto done;

no_route:
	RT_CACHE_STAT_INC(in_no_route);
	spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
	res.type = RTN_UNREACHABLE;
	goto local_input;

	/*
	 *	Do not cache martian addresses: they should be logged (RFC1812)
	 */
martian_destination:
	RT_CACHE_STAT_INC(in_martian_dst);
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
		printk(KERN_WARNING "martian destination %u.%u.%u.%u from "
			"%u.%u.%u.%u, dev %s\n",
			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
#endif
1918 1919

e_hostunreach:
1920 1921
	err = -EHOSTUNREACH;
	goto done;
1922

L
Linus Torvalds 已提交
1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935
e_inval:
	err = -EINVAL;
	goto done;

e_nobufs:
	err = -ENOBUFS;
	goto done;

martian_source:
	ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
	goto e_inval;
}

A
Al Viro 已提交
1936
int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
L
Linus Torvalds 已提交
1937 1938 1939 1940 1941 1942 1943
		   u8 tos, struct net_device *dev)
{
	struct rtable * rth;
	unsigned	hash;
	int iif = dev->ifindex;

	tos &= IPTOS_RT_MASK;
A
Al Viro 已提交
1944
	hash = rt_hash(daddr, saddr, iif);
L
Linus Torvalds 已提交
1945 1946 1947

	rcu_read_lock();
	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
1948
	     rth = rcu_dereference(rth->u.dst.rt_next)) {
L
Linus Torvalds 已提交
1949 1950 1951 1952
		if (rth->fl.fl4_dst == daddr &&
		    rth->fl.fl4_src == saddr &&
		    rth->fl.iif == iif &&
		    rth->fl.oif == 0 &&
1953
		    rth->fl.mark == skb->mark &&
L
Linus Torvalds 已提交
1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981
		    rth->fl.fl4_tos == tos) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			RT_CACHE_STAT_INC(in_hit);
			rcu_read_unlock();
			skb->dst = (struct dst_entry*)rth;
			return 0;
		}
		RT_CACHE_STAT_INC(in_hlist_search);
	}
	rcu_read_unlock();

	/* Multicast recognition logic is moved from route cache to here.
	   The problem was that too many Ethernet cards have broken/missing
	   hardware multicast filters :-( As result the host on multicasting
	   network acquires a lot of useless route cache entries, sort of
	   SDR messages from all the world. Now we try to get rid of them.
	   Really, provided software IP multicast filter is organized
	   reasonably (at least, hashed), it does not result in a slowdown
	   comparing with route cache reject entries.
	   Note, that multicast routers are not affected, because
	   route cache entry is created eventually.
	 */
	if (MULTICAST(daddr)) {
		struct in_device *in_dev;

		rcu_read_lock();
1982
		if ((in_dev = __in_dev_get_rcu(dev)) != NULL) {
L
Linus Torvalds 已提交
1983
			int our = ip_check_mc(in_dev, daddr, saddr,
1984
				ip_hdr(skb)->protocol);
L
Linus Torvalds 已提交
1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001
			if (our
#ifdef CONFIG_IP_MROUTE
			    || (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
#endif
			    ) {
				rcu_read_unlock();
				return ip_route_input_mc(skb, daddr, saddr,
							 tos, dev, our);
			}
		}
		rcu_read_unlock();
		return -EINVAL;
	}
	return ip_route_input_slow(skb, daddr, saddr, tos, dev);
}

static inline int __mkroute_output(struct rtable **result,
2002
				   struct fib_result* res,
L
Linus Torvalds 已提交
2003
				   const struct flowi *fl,
2004 2005 2006
				   const struct flowi *oldflp,
				   struct net_device *dev_out,
				   unsigned flags)
L
Linus Torvalds 已提交
2007 2008 2009 2010 2011 2012 2013 2014 2015
{
	struct rtable *rth;
	struct in_device *in_dev;
	u32 tos = RT_FL_TOS(oldflp);
	int err = 0;

	if (LOOPBACK(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK))
		return -EINVAL;

2016
	if (fl->fl4_dst == htonl(0xFFFFFFFF))
L
Linus Torvalds 已提交
2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038
		res->type = RTN_BROADCAST;
	else if (MULTICAST(fl->fl4_dst))
		res->type = RTN_MULTICAST;
	else if (BADCLASS(fl->fl4_dst) || ZERONET(fl->fl4_dst))
		return -EINVAL;

	if (dev_out->flags & IFF_LOOPBACK)
		flags |= RTCF_LOCAL;

	/* get work reference to inet device */
	in_dev = in_dev_get(dev_out);
	if (!in_dev)
		return -EINVAL;

	if (res->type == RTN_BROADCAST) {
		flags |= RTCF_BROADCAST | RTCF_LOCAL;
		if (res->fi) {
			fib_info_put(res->fi);
			res->fi = NULL;
		}
	} else if (res->type == RTN_MULTICAST) {
		flags |= RTCF_MULTICAST|RTCF_LOCAL;
2039
		if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src,
L
Linus Torvalds 已提交
2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056
				 oldflp->proto))
			flags &= ~RTCF_LOCAL;
		/* If multicast route do not exist use
		   default one, but do not gateway in this case.
		   Yes, it is hack.
		 */
		if (res->fi && res->prefixlen < 4) {
			fib_info_put(res->fi);
			res->fi = NULL;
		}
	}


	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth) {
		err = -ENOBUFS;
		goto cleanup;
2057
	}
L
Linus Torvalds 已提交
2058

2059
	atomic_set(&rth->u.dst.__refcnt, 1);
L
Linus Torvalds 已提交
2060
	rth->u.dst.flags= DST_HOST;
2061
	if (IN_DEV_CONF_GET(in_dev, NOXFRM))
L
Linus Torvalds 已提交
2062
		rth->u.dst.flags |= DST_NOXFRM;
2063
	if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
L
Linus Torvalds 已提交
2064 2065 2066 2067 2068 2069
		rth->u.dst.flags |= DST_NOPOLICY;

	rth->fl.fl4_dst	= oldflp->fl4_dst;
	rth->fl.fl4_tos	= tos;
	rth->fl.fl4_src	= oldflp->fl4_src;
	rth->fl.oif	= oldflp->oif;
2070
	rth->fl.mark    = oldflp->mark;
L
Linus Torvalds 已提交
2071 2072 2073
	rth->rt_dst	= fl->fl4_dst;
	rth->rt_src	= fl->fl4_src;
	rth->rt_iif	= oldflp->oif ? : dev_out->ifindex;
2074
	/* get references to the devices that are to be hold by the routing
L
Linus Torvalds 已提交
2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091
	   cache entry */
	rth->u.dst.dev	= dev_out;
	dev_hold(dev_out);
	rth->idev	= in_dev_get(dev_out);
	rth->rt_gateway = fl->fl4_dst;
	rth->rt_spec_dst= fl->fl4_src;

	rth->u.dst.output=ip_output;

	RT_CACHE_STAT_INC(out_slow_tot);

	if (flags & RTCF_LOCAL) {
		rth->u.dst.input = ip_local_deliver;
		rth->rt_spec_dst = fl->fl4_dst;
	}
	if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
		rth->rt_spec_dst = fl->fl4_src;
2092
		if (flags & RTCF_LOCAL &&
L
Linus Torvalds 已提交
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
		    !(dev_out->flags & IFF_LOOPBACK)) {
			rth->u.dst.output = ip_mc_output;
			RT_CACHE_STAT_INC(out_slow_mc);
		}
#ifdef CONFIG_IP_MROUTE
		if (res->type == RTN_MULTICAST) {
			if (IN_DEV_MFORWARD(in_dev) &&
			    !LOCAL_MCAST(oldflp->fl4_dst)) {
				rth->u.dst.input = ip_mr_input;
				rth->u.dst.output = ip_mc_output;
			}
		}
#endif
	}

	rt_set_nexthop(rth, res, 0);

	rth->rt_flags = flags;

	*result = rth;
 cleanup:
	/* release work reference to inet device */
	in_dev_put(in_dev);

	return err;
}

2120 2121 2122 2123 2124 2125
static inline int ip_mkroute_output(struct rtable **rp,
				    struct fib_result* res,
				    const struct flowi *fl,
				    const struct flowi *oldflp,
				    struct net_device *dev_out,
				    unsigned flags)
L
Linus Torvalds 已提交
2126
{
C
Chuck Short 已提交
2127
	struct rtable *rth = NULL;
L
Linus Torvalds 已提交
2128 2129 2130
	int err = __mkroute_output(&rth, res, fl, oldflp, dev_out, flags);
	unsigned hash;
	if (err == 0) {
A
Al Viro 已提交
2131
		hash = rt_hash(oldflp->fl4_dst, oldflp->fl4_src, oldflp->oif);
L
Linus Torvalds 已提交
2132 2133
		err = rt_intern_hash(hash, rth, rp);
	}
2134

L
Linus Torvalds 已提交
2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152
	return err;
}

/*
 * Major route resolver routine.
 */

static int ip_route_output_slow(struct rtable **rp, const struct flowi *oldflp)
{
	u32 tos	= RT_FL_TOS(oldflp);
	struct flowi fl = { .nl_u = { .ip4_u =
				      { .daddr = oldflp->fl4_dst,
					.saddr = oldflp->fl4_src,
					.tos = tos & IPTOS_RT_MASK,
					.scope = ((tos & RTO_ONLINK) ?
						  RT_SCOPE_LINK :
						  RT_SCOPE_UNIVERSE),
				      } },
2153
			    .mark = oldflp->mark,
L
Linus Torvalds 已提交
2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176
			    .iif = loopback_dev.ifindex,
			    .oif = oldflp->oif };
	struct fib_result res;
	unsigned flags = 0;
	struct net_device *dev_out = NULL;
	int free_res = 0;
	int err;


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

	if (oldflp->fl4_src) {
		err = -EINVAL;
		if (MULTICAST(oldflp->fl4_src) ||
		    BADCLASS(oldflp->fl4_src) ||
		    ZERONET(oldflp->fl4_src))
			goto out;

		/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
		dev_out = ip_dev_find(oldflp->fl4_src);
2177
		if (dev_out == NULL)
L
Linus Torvalds 已提交
2178 2179 2180 2181 2182 2183 2184 2185 2186 2187
			goto out;

		/* I removed check for oif == dev_out->oif here.
		   It was wrong for two reasons:
		   1. ip_dev_find(saddr) can return wrong iface, if saddr is
		      assigned to multiple interfaces.
		   2. Moreover, we are allowed to send packets with saddr
		      of another iface. --ANK
		 */

2188
		if (oldflp->oif == 0
2189
		    && (MULTICAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF))) {
L
Linus Torvalds 已提交
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
			/* Special hack: user can direct multicasts
			   and limited broadcast via necessary interface
			   without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
			   This hack is not just for fun, it allows
			   vic,vat and friends to work.
			   They bind socket to loopback, set ttl to zero
			   and expect that it will work.
			   From the viewpoint of routing cache they are broken,
			   because we are not allowed to build multicast path
			   with loopback source addr (look, routing cache
			   cannot know, that ttl is zero, so that packet
			   will not leave this host and route is valid).
			   Luckily, this hack is good workaround.
			 */

			fl.oif = dev_out->ifindex;
			goto make_route;
		}
		if (dev_out)
			dev_put(dev_out);
		dev_out = NULL;
	}


	if (oldflp->oif) {
		dev_out = dev_get_by_index(oldflp->oif);
		err = -ENODEV;
		if (dev_out == NULL)
			goto out;
2219 2220 2221

		/* RACE: Check return value of inet_select_addr instead. */
		if (__in_dev_get_rtnl(dev_out) == NULL) {
L
Linus Torvalds 已提交
2222 2223 2224 2225
			dev_put(dev_out);
			goto out;	/* Wrong error code */
		}

2226
		if (LOCAL_MCAST(oldflp->fl4_dst) || oldflp->fl4_dst == htonl(0xFFFFFFFF)) {
L
Linus Torvalds 已提交
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 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338
			if (!fl.fl4_src)
				fl.fl4_src = inet_select_addr(dev_out, 0,
							      RT_SCOPE_LINK);
			goto make_route;
		}
		if (!fl.fl4_src) {
			if (MULTICAST(oldflp->fl4_dst))
				fl.fl4_src = inet_select_addr(dev_out, 0,
							      fl.fl4_scope);
			else if (!oldflp->fl4_dst)
				fl.fl4_src = inet_select_addr(dev_out, 0,
							      RT_SCOPE_HOST);
		}
	}

	if (!fl.fl4_dst) {
		fl.fl4_dst = fl.fl4_src;
		if (!fl.fl4_dst)
			fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK);
		if (dev_out)
			dev_put(dev_out);
		dev_out = &loopback_dev;
		dev_hold(dev_out);
		fl.oif = loopback_dev.ifindex;
		res.type = RTN_LOCAL;
		flags |= RTCF_LOCAL;
		goto make_route;
	}

	if (fib_lookup(&fl, &res)) {
		res.fi = NULL;
		if (oldflp->oif) {
			/* Apparently, routing tables are wrong. Assume,
			   that the destination is on link.

			   WHY? DW.
			   Because we are allowed to send to iface
			   even if it has NO routes and NO assigned
			   addresses. When oif is specified, routing
			   tables are looked up with only one purpose:
			   to catch if destination is gatewayed, rather than
			   direct. Moreover, if MSG_DONTROUTE is set,
			   we send packet, ignoring both routing tables
			   and ifaddr state. --ANK


			   We could make it even if oif is unknown,
			   likely IPv6, but we do not.
			 */

			if (fl.fl4_src == 0)
				fl.fl4_src = inet_select_addr(dev_out, 0,
							      RT_SCOPE_LINK);
			res.type = RTN_UNICAST;
			goto make_route;
		}
		if (dev_out)
			dev_put(dev_out);
		err = -ENETUNREACH;
		goto out;
	}
	free_res = 1;

	if (res.type == RTN_LOCAL) {
		if (!fl.fl4_src)
			fl.fl4_src = fl.fl4_dst;
		if (dev_out)
			dev_put(dev_out);
		dev_out = &loopback_dev;
		dev_hold(dev_out);
		fl.oif = dev_out->ifindex;
		if (res.fi)
			fib_info_put(res.fi);
		res.fi = NULL;
		flags |= RTCF_LOCAL;
		goto make_route;
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (res.fi->fib_nhs > 1 && fl.oif == 0)
		fib_select_multipath(&fl, &res);
	else
#endif
	if (!res.prefixlen && res.type == RTN_UNICAST && !fl.oif)
		fib_select_default(&fl, &res);

	if (!fl.fl4_src)
		fl.fl4_src = FIB_RES_PREFSRC(res);

	if (dev_out)
		dev_put(dev_out);
	dev_out = FIB_RES_DEV(res);
	dev_hold(dev_out);
	fl.oif = dev_out->ifindex;


make_route:
	err = ip_mkroute_output(rp, &res, &fl, oldflp, dev_out, flags);


	if (free_res)
		fib_res_put(&res);
	if (dev_out)
		dev_put(dev_out);
out:	return err;
}

int __ip_route_output_key(struct rtable **rp, const struct flowi *flp)
{
	unsigned hash;
	struct rtable *rth;

A
Al Viro 已提交
2339
	hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif);
L
Linus Torvalds 已提交
2340 2341 2342

	rcu_read_lock_bh();
	for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
2343
		rth = rcu_dereference(rth->u.dst.rt_next)) {
L
Linus Torvalds 已提交
2344 2345 2346 2347
		if (rth->fl.fl4_dst == flp->fl4_dst &&
		    rth->fl.fl4_src == flp->fl4_src &&
		    rth->fl.iif == 0 &&
		    rth->fl.oif == flp->oif &&
2348
		    rth->fl.mark == flp->mark &&
L
Linus Torvalds 已提交
2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365
		    !((rth->fl.fl4_tos ^ flp->fl4_tos) &
			    (IPTOS_RT_MASK | RTO_ONLINK))) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			RT_CACHE_STAT_INC(out_hit);
			rcu_read_unlock_bh();
			*rp = rth;
			return 0;
		}
		RT_CACHE_STAT_INC(out_hlist_search);
	}
	rcu_read_unlock_bh();

	return ip_route_output_slow(rp, flp);
}

2366 2367
EXPORT_SYMBOL_GPL(__ip_route_output_key);

2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}

static struct dst_ops ipv4_dst_blackhole_ops = {
	.family			=	AF_INET,
	.protocol		=	__constant_htons(ETH_P_IP),
	.destroy		=	ipv4_dst_destroy,
	.check			=	ipv4_dst_check,
	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
	.entry_size		=	sizeof(struct rtable),
};


static int ipv4_blackhole_output(struct sk_buff *skb)
{
	kfree_skb(skb);
	return 0;
}

static int ipv4_dst_blackhole(struct rtable **rp, struct flowi *flp, struct sock *sk)
{
	struct rtable *ort = *rp;
	struct rtable *rt = (struct rtable *)
		dst_alloc(&ipv4_dst_blackhole_ops);

	if (rt) {
		struct dst_entry *new = &rt->u.dst;

		atomic_set(&new->__refcnt, 1);
		new->__use = 1;
		new->input = ipv4_blackhole_output;
		new->output = ipv4_blackhole_output;
		memcpy(new->metrics, ort->u.dst.metrics, RTAX_MAX*sizeof(u32));

		new->dev = ort->u.dst.dev;
		if (new->dev)
			dev_hold(new->dev);

		rt->fl = ort->fl;

		rt->idev = ort->idev;
		if (rt->idev)
			in_dev_hold(rt->idev);
		rt->rt_flags = ort->rt_flags;
		rt->rt_type = ort->rt_type;
		rt->rt_dst = ort->rt_dst;
		rt->rt_src = ort->rt_src;
		rt->rt_iif = ort->rt_iif;
		rt->rt_gateway = ort->rt_gateway;
		rt->rt_spec_dst = ort->rt_spec_dst;
		rt->peer = ort->peer;
		if (rt->peer)
			atomic_inc(&rt->peer->refcnt);

		dst_free(new);
	}

	dst_release(&(*rp)->u.dst);
	*rp = rt;
	return (rt ? 0 : -ENOMEM);
}

L
Linus Torvalds 已提交
2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442
int ip_route_output_flow(struct rtable **rp, struct flowi *flp, struct sock *sk, int flags)
{
	int err;

	if ((err = __ip_route_output_key(rp, flp)) != 0)
		return err;

	if (flp->proto) {
		if (!flp->fl4_src)
			flp->fl4_src = (*rp)->rt_src;
		if (!flp->fl4_dst)
			flp->fl4_dst = (*rp)->rt_dst;
2443 2444 2445 2446 2447
		err = __xfrm_lookup((struct dst_entry **)rp, flp, sk, flags);
		if (err == -EREMOTE)
			err = ipv4_dst_blackhole(rp, flp, sk);

		return err;
L
Linus Torvalds 已提交
2448 2449 2450 2451 2452
	}

	return 0;
}

2453 2454
EXPORT_SYMBOL_GPL(ip_route_output_flow);

L
Linus Torvalds 已提交
2455 2456 2457 2458 2459 2460
int ip_route_output_key(struct rtable **rp, struct flowi *flp)
{
	return ip_route_output_flow(rp, flp, NULL, 0);
}

static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
2461
			int nowait, unsigned int flags)
L
Linus Torvalds 已提交
2462 2463 2464
{
	struct rtable *rt = (struct rtable*)skb->dst;
	struct rtmsg *r;
2465
	struct nlmsghdr *nlh;
2466 2467
	long expires;
	u32 id = 0, ts = 0, tsage = 0, error;
2468 2469 2470

	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
	if (nlh == NULL)
2471
		return -EMSGSIZE;
2472 2473

	r = nlmsg_data(nlh);
L
Linus Torvalds 已提交
2474 2475 2476 2477 2478
	r->rtm_family	 = AF_INET;
	r->rtm_dst_len	= 32;
	r->rtm_src_len	= 0;
	r->rtm_tos	= rt->fl.fl4_tos;
	r->rtm_table	= RT_TABLE_MAIN;
2479
	NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN);
L
Linus Torvalds 已提交
2480 2481 2482 2483 2484 2485
	r->rtm_type	= rt->rt_type;
	r->rtm_scope	= RT_SCOPE_UNIVERSE;
	r->rtm_protocol = RTPROT_UNSPEC;
	r->rtm_flags	= (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
	if (rt->rt_flags & RTCF_NOTIFY)
		r->rtm_flags |= RTM_F_NOTIFY;
2486

2487
	NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
2488

L
Linus Torvalds 已提交
2489 2490
	if (rt->fl.fl4_src) {
		r->rtm_src_len = 32;
2491
		NLA_PUT_BE32(skb, RTA_SRC, rt->fl.fl4_src);
L
Linus Torvalds 已提交
2492 2493
	}
	if (rt->u.dst.dev)
2494
		NLA_PUT_U32(skb, RTA_OIF, rt->u.dst.dev->ifindex);
L
Linus Torvalds 已提交
2495 2496
#ifdef CONFIG_NET_CLS_ROUTE
	if (rt->u.dst.tclassid)
2497
		NLA_PUT_U32(skb, RTA_FLOW, rt->u.dst.tclassid);
L
Linus Torvalds 已提交
2498 2499
#endif
	if (rt->fl.iif)
2500
		NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
L
Linus Torvalds 已提交
2501
	else if (rt->rt_src != rt->fl.fl4_src)
2502
		NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
2503

L
Linus Torvalds 已提交
2504
	if (rt->rt_dst != rt->rt_gateway)
2505
		NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway);
2506

L
Linus Torvalds 已提交
2507
	if (rtnetlink_put_metrics(skb, rt->u.dst.metrics) < 0)
2508 2509
		goto nla_put_failure;

2510 2511
	error = rt->u.dst.error;
	expires = rt->u.dst.expires ? rt->u.dst.expires - jiffies : 0;
L
Linus Torvalds 已提交
2512
	if (rt->peer) {
2513
		id = rt->peer->ip_id_count;
L
Linus Torvalds 已提交
2514
		if (rt->peer->tcp_ts_stamp) {
2515
			ts = rt->peer->tcp_ts;
2516
			tsage = get_seconds() - rt->peer->tcp_ts_stamp;
L
Linus Torvalds 已提交
2517 2518
		}
	}
2519

L
Linus Torvalds 已提交
2520 2521
	if (rt->fl.iif) {
#ifdef CONFIG_IP_MROUTE
2522
		__be32 dst = rt->rt_dst;
L
Linus Torvalds 已提交
2523 2524

		if (MULTICAST(dst) && !LOCAL_MCAST(dst) &&
2525
		    IPV4_DEVCONF_ALL(MC_FORWARDING)) {
L
Linus Torvalds 已提交
2526 2527 2528 2529 2530
			int err = ipmr_get_route(skb, r, nowait);
			if (err <= 0) {
				if (!nowait) {
					if (err == 0)
						return 0;
2531
					goto nla_put_failure;
L
Linus Torvalds 已提交
2532 2533
				} else {
					if (err == -EMSGSIZE)
2534
						goto nla_put_failure;
2535
					error = err;
L
Linus Torvalds 已提交
2536 2537 2538 2539
				}
			}
		} else
#endif
2540
			NLA_PUT_U32(skb, RTA_IIF, rt->fl.iif);
L
Linus Torvalds 已提交
2541 2542
	}

2543 2544 2545
	if (rtnl_put_cacheinfo(skb, &rt->u.dst, id, ts, tsage,
			       expires, error) < 0)
		goto nla_put_failure;
2546 2547

	return nlmsg_end(skb, nlh);
L
Linus Torvalds 已提交
2548

2549
nla_put_failure:
2550 2551
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
L
Linus Torvalds 已提交
2552 2553
}

2554
static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
L
Linus Torvalds 已提交
2555
{
2556 2557
	struct rtmsg *rtm;
	struct nlattr *tb[RTA_MAX+1];
L
Linus Torvalds 已提交
2558
	struct rtable *rt = NULL;
A
Al Viro 已提交
2559 2560 2561
	__be32 dst = 0;
	__be32 src = 0;
	u32 iif;
2562
	int err;
L
Linus Torvalds 已提交
2563 2564
	struct sk_buff *skb;

2565 2566 2567 2568 2569 2570
	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
	if (err < 0)
		goto errout;

	rtm = nlmsg_data(nlh);

L
Linus Torvalds 已提交
2571
	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
2572 2573 2574 2575
	if (skb == NULL) {
		err = -ENOBUFS;
		goto errout;
	}
L
Linus Torvalds 已提交
2576 2577 2578 2579

	/* Reserve room for dummy headers, this skb can pass
	   through good chunk of routing engine.
	 */
2580
	skb_reset_mac_header(skb);
2581
	skb_reset_network_header(skb);
2582 2583

	/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
2584
	ip_hdr(skb)->protocol = IPPROTO_ICMP;
L
Linus Torvalds 已提交
2585 2586
	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));

2587 2588
	src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0;
	dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
2589
	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
L
Linus Torvalds 已提交
2590 2591

	if (iif) {
2592 2593 2594 2595 2596 2597 2598 2599
		struct net_device *dev;

		dev = __dev_get_by_index(iif);
		if (dev == NULL) {
			err = -ENODEV;
			goto errout_free;
		}

L
Linus Torvalds 已提交
2600 2601 2602 2603 2604
		skb->protocol	= htons(ETH_P_IP);
		skb->dev	= dev;
		local_bh_disable();
		err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
		local_bh_enable();
2605 2606 2607

		rt = (struct rtable*) skb->dst;
		if (err == 0 && rt->u.dst.error)
L
Linus Torvalds 已提交
2608 2609
			err = -rt->u.dst.error;
	} else {
2610 2611 2612 2613 2614 2615 2616 2617 2618 2619
		struct flowi fl = {
			.nl_u = {
				.ip4_u = {
					.daddr = dst,
					.saddr = src,
					.tos = rtm->rtm_tos,
				},
			},
			.oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
		};
L
Linus Torvalds 已提交
2620 2621
		err = ip_route_output_key(&rt, &fl);
	}
2622

L
Linus Torvalds 已提交
2623
	if (err)
2624
		goto errout_free;
L
Linus Torvalds 已提交
2625 2626 2627 2628 2629 2630

	skb->dst = &rt->u.dst;
	if (rtm->rtm_flags & RTM_F_NOTIFY)
		rt->rt_flags |= RTCF_NOTIFY;

	err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
2631
				RTM_NEWROUTE, 0, 0);
2632 2633
	if (err <= 0)
		goto errout_free;
L
Linus Torvalds 已提交
2634

2635
	err = rtnl_unicast(skb, NETLINK_CB(in_skb).pid);
2636
errout:
2637
	return err;
L
Linus Torvalds 已提交
2638

2639
errout_free:
L
Linus Torvalds 已提交
2640
	kfree_skb(skb);
2641
	goto errout;
L
Linus Torvalds 已提交
2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657
}

int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
{
	struct rtable *rt;
	int h, s_h;
	int idx, s_idx;

	s_h = cb->args[0];
	s_idx = idx = cb->args[1];
	for (h = 0; h <= rt_hash_mask; h++) {
		if (h < s_h) continue;
		if (h > s_h)
			s_idx = 0;
		rcu_read_lock_bh();
		for (rt = rcu_dereference(rt_hash_table[h].chain), idx = 0; rt;
2658
		     rt = rcu_dereference(rt->u.dst.rt_next), idx++) {
L
Linus Torvalds 已提交
2659 2660 2661 2662
			if (idx < s_idx)
				continue;
			skb->dst = dst_clone(&rt->u.dst);
			if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
2663
					 cb->nlh->nlmsg_seq, RTM_NEWROUTE,
2664
					 1, NLM_F_MULTI) <= 0) {
L
Linus Torvalds 已提交
2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695
				dst_release(xchg(&skb->dst, NULL));
				rcu_read_unlock_bh();
				goto done;
			}
			dst_release(xchg(&skb->dst, NULL));
		}
		rcu_read_unlock_bh();
	}

done:
	cb->args[0] = h;
	cb->args[1] = idx;
	return skb->len;
}

void ip_rt_multicast_event(struct in_device *in_dev)
{
	rt_cache_flush(0);
}

#ifdef CONFIG_SYSCTL
static int flush_delay;

static int ipv4_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);
		rt_cache_flush(flush_delay);
		return 0;
2696
	}
L
Linus Torvalds 已提交
2697 2698 2699 2700 2701 2702 2703 2704 2705 2706

	return -EINVAL;
}

static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table,
						int __user *name,
						int nlen,
						void __user *oldval,
						size_t __user *oldlenp,
						void __user *newval,
2707
						size_t newlen)
L
Linus Torvalds 已提交
2708 2709 2710 2711 2712
{
	int delay;
	if (newlen != sizeof(int))
		return -EINVAL;
	if (get_user(delay, (int __user *)newval))
2713 2714
		return -EFAULT;
	rt_cache_flush(delay);
L
Linus Torvalds 已提交
2715 2716 2717 2718
	return 0;
}

ctl_table ipv4_route_table[] = {
2719
	{
L
Linus Torvalds 已提交
2720 2721 2722 2723
		.ctl_name 	= NET_IPV4_ROUTE_FLUSH,
		.procname	= "flush",
		.data		= &flush_delay,
		.maxlen		= sizeof(int),
2724
		.mode		= 0200,
L
Linus Torvalds 已提交
2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763
		.proc_handler	= &ipv4_sysctl_rtcache_flush,
		.strategy	= &ipv4_sysctl_rtcache_flush_strategy,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_MIN_DELAY,
		.procname	= "min_delay",
		.data		= &ip_rt_min_delay,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_MAX_DELAY,
		.procname	= "max_delay",
		.data		= &ip_rt_max_delay,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_GC_THRESH,
		.procname	= "gc_thresh",
		.data		= &ipv4_dst_ops.gc_thresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_MAX_SIZE,
		.procname	= "max_size",
		.data		= &ip_rt_max_size,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		/*  Deprecated. Use gc_min_interval_ms */
2764

L
Linus Torvalds 已提交
2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923
		.ctl_name	= NET_IPV4_ROUTE_GC_MIN_INTERVAL,
		.procname	= "gc_min_interval",
		.data		= &ip_rt_gc_min_interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS,
		.procname	= "gc_min_interval_ms",
		.data		= &ip_rt_gc_min_interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_ms_jiffies,
		.strategy	= &sysctl_ms_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_GC_TIMEOUT,
		.procname	= "gc_timeout",
		.data		= &ip_rt_gc_timeout,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_GC_INTERVAL,
		.procname	= "gc_interval",
		.data		= &ip_rt_gc_interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_REDIRECT_LOAD,
		.procname	= "redirect_load",
		.data		= &ip_rt_redirect_load,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_REDIRECT_NUMBER,
		.procname	= "redirect_number",
		.data		= &ip_rt_redirect_number,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_REDIRECT_SILENCE,
		.procname	= "redirect_silence",
		.data		= &ip_rt_redirect_silence,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_ERROR_COST,
		.procname	= "error_cost",
		.data		= &ip_rt_error_cost,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_ERROR_BURST,
		.procname	= "error_burst",
		.data		= &ip_rt_error_burst,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_GC_ELASTICITY,
		.procname	= "gc_elasticity",
		.data		= &ip_rt_gc_elasticity,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_MTU_EXPIRES,
		.procname	= "mtu_expires",
		.data		= &ip_rt_mtu_expires,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_MIN_PMTU,
		.procname	= "min_pmtu",
		.data		= &ip_rt_min_pmtu,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_MIN_ADVMSS,
		.procname	= "min_adv_mss",
		.data		= &ip_rt_min_advmss,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_ROUTE_SECRET_INTERVAL,
		.procname	= "secret_interval",
		.data		= &ip_rt_secret_interval,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
		.strategy	= &sysctl_jiffies,
	},
	{ .ctl_name = 0 }
};
#endif

#ifdef CONFIG_NET_CLS_ROUTE
struct ip_rt_acct *ip_rt_acct;

/* This code sucks.  But you should have seen it before! --RR */

/* IP route accounting ptr for this logical cpu number. */
#define IP_RT_ACCT_CPU(i) (ip_rt_acct + i * 256)

#ifdef CONFIG_PROC_FS
static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
			   int length, int *eof, void *data)
{
	unsigned int i;

	if ((offset & 3) || (length & 3))
		return -EIO;

	if (offset >= sizeof(struct ip_rt_acct) * 256) {
		*eof = 1;
		return 0;
	}

	if (offset + length >= sizeof(struct ip_rt_acct) * 256) {
		length = sizeof(struct ip_rt_acct) * 256 - offset;
		*eof = 1;
	}

	offset /= sizeof(u32);

	if (length > 0) {
		u32 *src = ((u32 *) IP_RT_ACCT_CPU(0)) + offset;
		u32 *dst = (u32 *) buffer;

		/* Copy first cpu. */
		*start = buffer;
		memcpy(dst, src, length);

		/* Add the other cpus in, one int at a time */
2924
		for_each_possible_cpu(i) {
L
Linus Torvalds 已提交
2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949
			unsigned int j;

			src = ((u32 *) IP_RT_ACCT_CPU(i)) + offset;

			for (j = 0; j < length/4; j++)
				dst[j] += src[j];
		}
	}
	return length;
}
#endif /* CONFIG_PROC_FS */
#endif /* CONFIG_NET_CLS_ROUTE */

static __initdata unsigned long rhash_entries;
static int __init set_rhash_entries(char *str)
{
	if (!str)
		return 0;
	rhash_entries = simple_strtoul(str, &str, 0);
	return 1;
}
__setup("rhash_entries=", set_rhash_entries);

int __init ip_rt_init(void)
{
2950
	int rc = 0;
L
Linus Torvalds 已提交
2951 2952 2953 2954 2955

	rt_hash_rnd = (int) ((num_physpages ^ (num_physpages>>8)) ^
			     (jiffies ^ (jiffies >> 7)));

#ifdef CONFIG_NET_CLS_ROUTE
2956 2957
	{
	int order;
L
Linus Torvalds 已提交
2958 2959 2960 2961 2962 2963 2964
	for (order = 0;
	     (PAGE_SIZE << order) < 256 * sizeof(struct ip_rt_acct) * NR_CPUS; order++)
		/* NOTHING */;
	ip_rt_acct = (struct ip_rt_acct *)__get_free_pages(GFP_KERNEL, order);
	if (!ip_rt_acct)
		panic("IP: failed to allocate ip_rt_acct\n");
	memset(ip_rt_acct, 0, PAGE_SIZE << order);
2965
	}
L
Linus Torvalds 已提交
2966 2967
#endif

A
Alexey Dobriyan 已提交
2968 2969
	ipv4_dst_ops.kmem_cachep =
		kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0,
2970
				  SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
L
Linus Torvalds 已提交
2971

2972 2973
	ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep;

2974 2975 2976 2977 2978
	rt_hash_table = (struct rt_hash_bucket *)
		alloc_large_system_hash("IP route cache",
					sizeof(struct rt_hash_bucket),
					rhash_entries,
					(num_physpages >= 128 * 1024) ?
2979
					15 : 17,
2980
					0,
2981 2982 2983
					&rt_hash_log,
					&rt_hash_mask,
					0);
2984 2985
	memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
	rt_hash_lock_init();
L
Linus Torvalds 已提交
2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014

	ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
	ip_rt_max_size = (rt_hash_mask + 1) * 16;

	devinet_init();
	ip_fib_init();

	init_timer(&rt_flush_timer);
	rt_flush_timer.function = rt_run_flush;
	init_timer(&rt_periodic_timer);
	rt_periodic_timer.function = rt_check_expire;
	init_timer(&rt_secret_timer);
	rt_secret_timer.function = rt_secret_rebuild;

	/* All the timers, started at system startup tend
	   to synchronize. Perturb it a bit.
	 */
	rt_periodic_timer.expires = jiffies + net_random() % ip_rt_gc_interval +
					ip_rt_gc_interval;
	add_timer(&rt_periodic_timer);

	rt_secret_timer.expires = jiffies + net_random() % ip_rt_secret_interval +
		ip_rt_secret_interval;
	add_timer(&rt_secret_timer);

#ifdef CONFIG_PROC_FS
	{
	struct proc_dir_entry *rtstat_pde = NULL; /* keep gcc happy */
	if (!proc_net_fops_create("rt_cache", S_IRUGO, &rt_cache_seq_fops) ||
3015 3016
	    !(rtstat_pde = create_proc_entry("rt_cache", S_IRUGO,
					     proc_net_stat))) {
L
Linus Torvalds 已提交
3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028
		return -ENOMEM;
	}
	rtstat_pde->proc_fops = &rt_cpu_seq_fops;
	}
#ifdef CONFIG_NET_CLS_ROUTE
	create_proc_read_entry("rt_acct", 0, proc_net, ip_rt_acct_read, NULL);
#endif
#endif
#ifdef CONFIG_XFRM
	xfrm_init();
	xfrm4_init();
#endif
3029 3030
	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL);

L
Linus Torvalds 已提交
3031 3032 3033 3034 3035 3036
	return rc;
}

EXPORT_SYMBOL(__ip_select_ident);
EXPORT_SYMBOL(ip_route_input);
EXPORT_SYMBOL(ip_route_output_key);