fib_semantics.c 52.1 KB
Newer Older
1
// SPDX-License-Identifier: GPL-2.0-or-later
2
3
4
5
6
7
8
9
10
11
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		IPv4 Forwarding Information Base: semantics.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 */

12
#include <linux/uaccess.h>
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/slab.h>
31
#include <linux/netlink.h>
32
33
34
35
36
37
38
39

#include <net/arp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
40
#include <net/ip6_fib.h>
41
#include <net/nexthop.h>
42
#include <net/netlink.h>
43
#include <net/rtnh.h>
44
#include <net/lwtunnel.h>
45
#include <net/fib_notifier.h>
46
#include <net/addrconf.h>
47
48
49
50
51
52
53
54
55
56
57
58
59

#include "fib_lookup.h"

static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
static unsigned int fib_info_hash_size;
static unsigned int fib_info_cnt;

#define DEVINDEX_HASHBITS 8
#define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS)
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];

60
61
62
/* for_nexthops and change_nexthops only used when nexthop object
 * is not set in a fib_info. The logic within can reference fib_nh.
 */
63
64
65
66
67
#ifdef CONFIG_IP_ROUTE_MULTIPATH

#define for_nexthops(fi) {						\
	int nhsel; const struct fib_nh *nh;				\
	for (nhsel = 0, nh = (fi)->fib_nh;				\
68
	     nhsel < fib_info_num_path((fi));				\
69
70
71
72
73
	     nh++, nhsel++)

#define change_nexthops(fi) {						\
	int nhsel; struct fib_nh *nexthop_nh;				\
	for (nhsel = 0,	nexthop_nh = (struct fib_nh *)((fi)->fib_nh);	\
74
	     nhsel < fib_info_num_path((fi));				\
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
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
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
	     nexthop_nh++, nhsel++)

#else /* CONFIG_IP_ROUTE_MULTIPATH */

/* Hope, that gcc will optimize it to get rid of dummy loop */

#define for_nexthops(fi) {						\
	int nhsel; const struct fib_nh *nh = (fi)->fib_nh;		\
	for (nhsel = 0; nhsel < 1; nhsel++)

#define change_nexthops(fi) {						\
	int nhsel;							\
	struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh);	\
	for (nhsel = 0; nhsel < 1; nhsel++)

#endif /* CONFIG_IP_ROUTE_MULTIPATH */

#define endfor_nexthops(fi) }


const struct fib_prop fib_props[RTN_MAX + 1] = {
	[RTN_UNSPEC] = {
		.error	= 0,
		.scope	= RT_SCOPE_NOWHERE,
	},
	[RTN_UNICAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_LOCAL] = {
		.error	= 0,
		.scope	= RT_SCOPE_HOST,
	},
	[RTN_BROADCAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_LINK,
	},
	[RTN_ANYCAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_LINK,
	},
	[RTN_MULTICAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_BLACKHOLE] = {
		.error	= -EINVAL,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_UNREACHABLE] = {
		.error	= -EHOSTUNREACH,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_PROHIBIT] = {
		.error	= -EACCES,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_THROW] = {
		.error	= -EAGAIN,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_NAT] = {
		.error	= -EINVAL,
		.scope	= RT_SCOPE_NOWHERE,
	},
	[RTN_XRESOLVE] = {
		.error	= -EINVAL,
		.scope	= RT_SCOPE_NOWHERE,
	},
};

static void rt_fibinfo_free(struct rtable __rcu **rtp)
{
	struct rtable *rt = rcu_dereference_protected(*rtp, 1);

	if (!rt)
		return;

	/* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
	 * because we waited an RCU grace period before calling
	 * free_fib_info_rcu()
	 */

158
159
	dst_dev_put(&rt->dst);
	dst_release_immediate(&rt->dst);
160
161
}

162
static void free_nh_exceptions(struct fib_nh_common *nhc)
163
164
165
166
{
	struct fnhe_hash_bucket *hash;
	int i;

167
	hash = rcu_dereference_protected(nhc->nhc_exceptions, 1);
168
169
170
171
172
173
174
175
	if (!hash)
		return;
	for (i = 0; i < FNHE_HASH_SIZE; i++) {
		struct fib_nh_exception *fnhe;

		fnhe = rcu_dereference_protected(hash[i].chain, 1);
		while (fnhe) {
			struct fib_nh_exception *next;
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
			next = rcu_dereference_protected(fnhe->fnhe_next, 1);

			rt_fibinfo_free(&fnhe->fnhe_rth_input);
			rt_fibinfo_free(&fnhe->fnhe_rth_output);

			kfree(fnhe);

			fnhe = next;
		}
	}
	kfree(hash);
}

static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
{
	int cpu;

	if (!rtp)
		return;

	for_each_possible_cpu(cpu) {
		struct rtable *rt;

		rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
201
202
203
204
		if (rt) {
			dst_dev_put(&rt->dst);
			dst_release_immediate(&rt->dst);
		}
205
206
207
208
	}
	free_percpu(rtp);
}

209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
void fib_nh_common_release(struct fib_nh_common *nhc)
{
	if (nhc->nhc_dev)
		dev_put(nhc->nhc_dev);

	lwtstate_put(nhc->nhc_lwtstate);
	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
	rt_fibinfo_free(&nhc->nhc_rth_input);
	free_nh_exceptions(nhc);
}
EXPORT_SYMBOL_GPL(fib_nh_common_release);

void fib_nh_release(struct net *net, struct fib_nh *fib_nh)
{
#ifdef CONFIG_IP_ROUTE_CLASSID
	if (fib_nh->nh_tclassid)
		net->ipv4.fib_num_tclassid_users--;
#endif
	fib_nh_common_release(&fib_nh->nh_common);
}

230
231
232
233
234
/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
	struct fib_info *fi = container_of(head, struct fib_info, rcu);

235
236
237
238
239
240
241
	if (fi->nh) {
		nexthop_put(fi->nh);
	} else {
		change_nexthops(fi) {
			fib_nh_release(fi->fib_net, nexthop_nh);
		} endfor_nexthops(fi);
	}
242

243
244
	ip_fib_metrics_put(fi->fib_metrics);

245
246
247
248
249
250
251
252
253
254
	kfree(fi);
}

void free_fib_info(struct fib_info *fi)
{
	if (fi->fib_dead == 0) {
		pr_warn("Freeing alive fib_info %p\n", fi);
		return;
	}
	fib_info_cnt--;
255

256
257
	call_rcu(&fi->rcu, free_fib_info_rcu);
}
258
EXPORT_SYMBOL_GPL(free_fib_info);
259
260
261
262
263
264
265
266

void fib_release_info(struct fib_info *fi)
{
	spin_lock_bh(&fib_info_lock);
	if (fi && --fi->fib_treeref == 0) {
		hlist_del(&fi->fib_hash);
		if (fi->fib_prefsrc)
			hlist_del(&fi->fib_lhash);
267
268
269
270
271
272
273
274
275
		if (fi->nh) {
			list_del(&fi->nh_list);
		} else {
			change_nexthops(fi) {
				if (!nexthop_nh->fib_nh_dev)
					continue;
				hlist_del(&nexthop_nh->nh_hash);
			} endfor_nexthops(fi)
		}
276
277
278
279
280
281
		fi->fib_dead = 1;
		fib_info_put(fi);
	}
	spin_unlock_bh(&fib_info_lock);
}

282
static inline int nh_comp(struct fib_info *fi, struct fib_info *ofi)
283
{
284
285
286
287
288
289
290
	const struct fib_nh *onh;

	if (fi->nh || ofi->nh)
		return nexthop_cmp(fi->nh, ofi->nh) ? 0 : -1;

	if (ofi->fib_nhs == 0)
		return 0;
291
292

	for_nexthops(fi) {
293
294
		onh = fib_info_nh(ofi, nhsel);

295
296
297
		if (nh->fib_nh_oif != onh->fib_nh_oif ||
		    nh->fib_nh_gw_family != onh->fib_nh_gw_family ||
		    nh->fib_nh_scope != onh->fib_nh_scope ||
298
#ifdef CONFIG_IP_ROUTE_MULTIPATH
299
		    nh->fib_nh_weight != onh->fib_nh_weight ||
300
301
302
303
#endif
#ifdef CONFIG_IP_ROUTE_CLASSID
		    nh->nh_tclassid != onh->nh_tclassid ||
#endif
304
305
306
307
308
309
310
311
312
313
		    lwtunnel_cmp_encap(nh->fib_nh_lws, onh->fib_nh_lws) ||
		    ((nh->fib_nh_flags ^ onh->fib_nh_flags) & ~RTNH_COMPARE_MASK))
			return -1;

		if (nh->fib_nh_gw_family == AF_INET &&
		    nh->fib_nh_gw4 != onh->fib_nh_gw4)
			return -1;

		if (nh->fib_nh_gw_family == AF_INET6 &&
		    ipv6_addr_cmp(&nh->fib_nh_gw6, &onh->fib_nh_gw6))
314
315
316
317
318
319
320
321
322
323
324
325
326
327
			return -1;
	} endfor_nexthops(fi);
	return 0;
}

static inline unsigned int fib_devindex_hashfn(unsigned int val)
{
	unsigned int mask = DEVINDEX_HASHSIZE - 1;

	return (val ^
		(val >> DEVINDEX_HASHBITS) ^
		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
}

328
329
static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
				      u32 prefsrc, u32 priority)
330
{
331
	unsigned int val = init_val;
332

333
334
335
336
337
338
339
340
341
342
	val ^= (protocol << 8) | scope;
	val ^= prefsrc;
	val ^= priority;

	return val;
}

static unsigned int fib_info_hashfn_result(unsigned int val)
{
	unsigned int mask = (fib_info_hash_size - 1);
343
344
345
346

	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
}

347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
static inline unsigned int fib_info_hashfn(struct fib_info *fi)
{
	unsigned int val;

	val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol,
				fi->fib_scope, (__force u32)fi->fib_prefsrc,
				fi->fib_priority);

	if (fi->nh) {
		val ^= fib_devindex_hashfn(fi->nh->id);
	} else {
		for_nexthops(fi) {
			val ^= fib_devindex_hashfn(nh->fib_nh_oif);
		} endfor_nexthops(fi)
	}

	return fib_info_hashfn_result(val);
}

/* no metrics, only nexthop id */
static struct fib_info *fib_find_info_nh(struct net *net,
					 const struct fib_config *cfg)
{
	struct hlist_head *head;
	struct fib_info *fi;
	unsigned int hash;

	hash = fib_info_hashfn_1(fib_devindex_hashfn(cfg->fc_nh_id),
				 cfg->fc_protocol, cfg->fc_scope,
				 (__force u32)cfg->fc_prefsrc,
				 cfg->fc_priority);
	hash = fib_info_hashfn_result(hash);
	head = &fib_info_hash[hash];

	hlist_for_each_entry(fi, head, fib_hash) {
		if (!net_eq(fi->fib_net, net))
			continue;
		if (!fi->nh || fi->nh->id != cfg->fc_nh_id)
			continue;
		if (cfg->fc_protocol == fi->fib_protocol &&
		    cfg->fc_scope == fi->fib_scope &&
		    cfg->fc_prefsrc == fi->fib_prefsrc &&
		    cfg->fc_priority == fi->fib_priority &&
		    cfg->fc_type == fi->fib_type &&
		    cfg->fc_table == fi->fib_tb_id &&
		    !((cfg->fc_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK))
			return fi;
	}

	return NULL;
}

static struct fib_info *fib_find_info(struct fib_info *nfi)
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
{
	struct hlist_head *head;
	struct fib_info *fi;
	unsigned int hash;

	hash = fib_info_hashfn(nfi);
	head = &fib_info_hash[hash];

	hlist_for_each_entry(fi, head, fib_hash) {
		if (!net_eq(fi->fib_net, nfi->fib_net))
			continue;
		if (fi->fib_nhs != nfi->fib_nhs)
			continue;
		if (nfi->fib_protocol == fi->fib_protocol &&
		    nfi->fib_scope == fi->fib_scope &&
		    nfi->fib_prefsrc == fi->fib_prefsrc &&
		    nfi->fib_priority == fi->fib_priority &&
		    nfi->fib_type == fi->fib_type &&
		    memcmp(nfi->fib_metrics, fi->fib_metrics,
			   sizeof(u32) * RTAX_MAX) == 0 &&
		    !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) &&
421
		    nh_comp(fi, nfi) == 0)
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
			return fi;
	}

	return NULL;
}

/* Check, that the gateway is already configured.
 * Used only by redirect accept routine.
 */
int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
	struct hlist_head *head;
	struct fib_nh *nh;
	unsigned int hash;

	spin_lock(&fib_info_lock);

	hash = fib_devindex_hashfn(dev->ifindex);
	head = &fib_info_devhash[hash];
	hlist_for_each_entry(nh, head, nh_hash) {
442
443
444
		if (nh->fib_nh_dev == dev &&
		    nh->fib_nh_gw4 == gw &&
		    !(nh->fib_nh_flags & RTNH_F_DEAD)) {
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
			spin_unlock(&fib_info_lock);
			return 0;
		}
	}

	spin_unlock(&fib_info_lock);

	return -1;
}

static inline size_t fib_nlmsg_size(struct fib_info *fi)
{
	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
			 + nla_total_size(4) /* RTA_TABLE */
			 + nla_total_size(4) /* RTA_DST */
			 + nla_total_size(4) /* RTA_PRIORITY */
			 + nla_total_size(4) /* RTA_PREFSRC */
			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */
463
	unsigned int nhs = fib_info_num_path(fi);
464
465
466
467

	/* space for nested metrics */
	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));

468
469
470
471
	if (fi->nh)
		payload += nla_total_size(4); /* RTA_NH_ID */

	if (nhs) {
472
		size_t nh_encapsize = 0;
473
		/* Also handles the special case nhs == 1 */
474
475
476

		/* each nexthop is packed in an attribute */
		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));
477
		unsigned int i;
478
479
480
481
482

		/* may contain flow and gateway attribute */
		nhsize += 2 * nla_total_size(4);

		/* grab encap info */
483
484
485
486
		for (i = 0; i < fib_info_num_path(fi); i++) {
			struct fib_nh_common *nhc = fib_info_nhc(fi, i);

			if (nhc->nhc_lwtstate) {
487
488
				/* RTA_ENCAP_TYPE */
				nh_encapsize += lwtunnel_get_encap_size(
489
						nhc->nhc_lwtstate);
490
491
492
				/* RTA_ENCAP */
				nh_encapsize +=  nla_total_size(2);
			}
493
		}
494
495

		/* all nexthops are packed in a nested attribute */
496
		payload += nla_total_size((nhs * nhsize) + nh_encapsize);
497
498
499
500
501
502
503
504
505
506

	}

	return payload;
}

void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
	       int dst_len, u32 tb_id, const struct nl_info *info,
	       unsigned int nlm_flags)
{
507
	struct fib_rt_info fri;
508
509
510
511
512
513
514
515
	struct sk_buff *skb;
	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
	int err = -ENOBUFS;

	skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
	if (!skb)
		goto errout;

516
517
518
519
520
521
522
523
524
	fri.fi = fa->fa_info;
	fri.tb_id = tb_id;
	fri.dst = key;
	fri.dst_len = dst_len;
	fri.tos = fa->fa_tos;
	fri.type = fa->fa_type;
	fri.offload = fa->offload;
	fri.trap = fa->trap;
	err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags);
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
	if (err < 0) {
		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE,
		    info->nlh, GFP_KERNEL);
	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
}

static int fib_detect_death(struct fib_info *fi, int order,
			    struct fib_info **last_resort, int *last_idx,
			    int dflt)
{
543
	const struct fib_nh_common *nhc = fib_info_nhc(fi, 0);
544
545
546
	struct neighbour *n;
	int state = NUD_NONE;

547
548
549
550
551
552
553
554
	if (likely(nhc->nhc_gw_family == AF_INET))
		n = neigh_lookup(&arp_tbl, &nhc->nhc_gw.ipv4, nhc->nhc_dev);
	else if (nhc->nhc_gw_family == AF_INET6)
		n = neigh_lookup(ipv6_stub->nd_tbl, &nhc->nhc_gw.ipv6,
				 nhc->nhc_dev);
	else
		n = NULL;

555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
	if (n) {
		state = n->nud_state;
		neigh_release(n);
	} else {
		return 0;
	}
	if (state == NUD_REACHABLE)
		return 0;
	if ((state & NUD_VALID) && order != dflt)
		return 0;
	if ((state & NUD_VALID) ||
	    (*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) {
		*last_resort = fi;
		*last_idx = order;
	}
	return 1;
}

573
574
575
int fib_nh_common_init(struct net *net, struct fib_nh_common *nhc,
		       struct nlattr *encap, u16 encap_type,
		       void *cfg, gfp_t gfp_flags,
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
		       struct netlink_ext_ack *extack)
{
	int err;

	nhc->nhc_pcpu_rth_output = alloc_percpu_gfp(struct rtable __rcu *,
						    gfp_flags);
	if (!nhc->nhc_pcpu_rth_output)
		return -ENOMEM;

	if (encap) {
		struct lwtunnel_state *lwtstate;

		if (encap_type == LWTUNNEL_ENCAP_NONE) {
			NL_SET_ERR_MSG(extack, "LWT encap type not specified");
			err = -EINVAL;
			goto lwt_failure;
		}
593
594
595
		err = lwtunnel_build_state(net, encap_type, encap,
					   nhc->nhc_family, cfg, &lwtstate,
					   extack);
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
		if (err)
			goto lwt_failure;

		nhc->nhc_lwtstate = lwtstate_get(lwtstate);
	}

	return 0;

lwt_failure:
	rt_fibinfo_free_cpus(nhc->nhc_pcpu_rth_output);
	nhc->nhc_pcpu_rth_output = NULL;
	return err;
}
EXPORT_SYMBOL_GPL(fib_nh_common_init);

int fib_nh_init(struct net *net, struct fib_nh *nh,
		struct fib_config *cfg, int nh_weight,
		struct netlink_ext_ack *extack)
{
	int err;

	nh->fib_nh_family = AF_INET;

619
	err = fib_nh_common_init(net, &nh->nh_common, cfg->fc_encap,
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
				 cfg->fc_encap_type, cfg, GFP_KERNEL, extack);
	if (err)
		return err;

	nh->fib_nh_oif = cfg->fc_oif;
	nh->fib_nh_gw_family = cfg->fc_gw_family;
	if (cfg->fc_gw_family == AF_INET)
		nh->fib_nh_gw4 = cfg->fc_gw4;
	else if (cfg->fc_gw_family == AF_INET6)
		nh->fib_nh_gw6 = cfg->fc_gw6;

	nh->fib_nh_flags = cfg->fc_flags;

#ifdef CONFIG_IP_ROUTE_CLASSID
	nh->nh_tclassid = cfg->fc_flow;
	if (nh->nh_tclassid)
		net->ipv4.fib_num_tclassid_users++;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	nh->fib_nh_weight = nh_weight;
#endif
	return 0;
}

644
645
#ifdef CONFIG_IP_ROUTE_MULTIPATH

646
647
static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining,
			      struct netlink_ext_ack *extack)
648
649
650
651
652
653
654
655
656
{
	int nhs = 0;

	while (rtnh_ok(rtnh, remaining)) {
		nhs++;
		rtnh = rtnh_next(rtnh, &remaining);
	}

	/* leftover implies invalid nexthop configuration, discard it */
657
658
659
660
661
662
663
	if (remaining > 0) {
		NL_SET_ERR_MSG(extack,
			       "Invalid nexthop configuration - extra data after nexthops");
		nhs = 0;
	}

	return nhs;
664
665
}

666
/* only called when fib_nh is integrated into fib_info */
667
static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
668
669
		       int remaining, struct fib_config *cfg,
		       struct netlink_ext_ack *extack)
670
{
671
672
	struct net *net = fi->fib_net;
	struct fib_config fib_cfg;
673
	struct fib_nh *nh;
674
675
676
677
678
	int ret;

	change_nexthops(fi) {
		int attrlen;

679
680
		memset(&fib_cfg, 0, sizeof(fib_cfg));

681
682
683
		if (!rtnh_ok(rtnh, remaining)) {
			NL_SET_ERR_MSG(extack,
				       "Invalid nexthop configuration - extra data after nexthop");
684
			return -EINVAL;
685
		}
686

687
688
689
		if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) {
			NL_SET_ERR_MSG(extack,
				       "Invalid flags for nexthop - can not contain DEAD or LINKDOWN");
690
			return -EINVAL;
691
		}
692

693
694
		fib_cfg.fc_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
		fib_cfg.fc_oif = rtnh->rtnh_ifindex;
695
696
697

		attrlen = rtnh_attrlen(rtnh);
		if (attrlen > 0) {
698
			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
699
700

			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
701
702
703
704
705
706
			nlav = nla_find(attrs, attrlen, RTA_VIA);
			if (nla && nlav) {
				NL_SET_ERR_MSG(extack,
					       "Nexthop configuration can not contain both GATEWAY and VIA");
				return -EINVAL;
			}
707
			if (nla) {
708
709
710
711
712
				fib_cfg.fc_gw4 = nla_get_in_addr(nla);
				if (fib_cfg.fc_gw4)
					fib_cfg.fc_gw_family = AF_INET;
			} else if (nlav) {
				ret = fib_gw_from_via(&fib_cfg, nlav, extack);
713
714
715
				if (ret)
					goto errout;
			}
716
717
718
719
720
721
722
723
724

			nla = nla_find(attrs, attrlen, RTA_FLOW);
			if (nla)
				fib_cfg.fc_flow = nla_get_u32(nla);

			fib_cfg.fc_encap = nla_find(attrs, attrlen, RTA_ENCAP);
			nla = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
			if (nla)
				fib_cfg.fc_encap_type = nla_get_u16(nla);
725
726
		}

727
728
729
730
731
		ret = fib_nh_init(net, nexthop_nh, &fib_cfg,
				  rtnh->rtnh_hops + 1, extack);
		if (ret)
			goto errout;

732
733
734
735
		rtnh = rtnh_next(rtnh, &remaining);
	} endfor_nexthops(fi);

	ret = -EINVAL;
736
737
	nh = fib_info_nh(fi, 0);
	if (cfg->fc_oif && nh->fib_nh_oif != cfg->fc_oif) {
738
739
740
741
742
		NL_SET_ERR_MSG(extack,
			       "Nexthop device index does not match RTA_OIF");
		goto errout;
	}
	if (cfg->fc_gw_family) {
743
		if (cfg->fc_gw_family != nh->fib_nh_gw_family ||
744
		    (cfg->fc_gw_family == AF_INET &&
745
		     nh->fib_nh_gw4 != cfg->fc_gw4) ||
746
		    (cfg->fc_gw_family == AF_INET6 &&
747
		     ipv6_addr_cmp(&nh->fib_nh_gw6, &cfg->fc_gw6))) {
748
749
750
751
752
753
			NL_SET_ERR_MSG(extack,
				       "Nexthop gateway does not match RTA_GATEWAY or RTA_VIA");
			goto errout;
		}
	}
#ifdef CONFIG_IP_ROUTE_CLASSID
754
	if (cfg->fc_flow && nh->nh_tclassid != cfg->fc_flow) {
755
756
757
758
759
760
		NL_SET_ERR_MSG(extack,
			       "Nexthop class id does not match RTA_FLOW");
		goto errout;
	}
#endif
	ret = 0;
761
762
763
764
errout:
	return ret;
}

765
/* only called when fib_nh is integrated into fib_info */
766
767
768
769
770
static void fib_rebalance(struct fib_info *fi)
{
	int total;
	int w;

771
	if (fib_info_num_path(fi) < 2)
772
773
774
775
		return;

	total = 0;
	for_nexthops(fi) {
776
		if (nh->fib_nh_flags & RTNH_F_DEAD)
777
778
			continue;

779
780
		if (ip_ignore_linkdown(nh->fib_nh_dev) &&
		    nh->fib_nh_flags & RTNH_F_LINKDOWN)
781
782
			continue;

783
		total += nh->fib_nh_weight;
784
785
786
787
788
789
	} endfor_nexthops(fi);

	w = 0;
	change_nexthops(fi) {
		int upper_bound;

790
		if (nexthop_nh->fib_nh_flags & RTNH_F_DEAD) {
791
			upper_bound = -1;
792
793
		} else if (ip_ignore_linkdown(nexthop_nh->fib_nh_dev) &&
			   nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN) {
794
795
			upper_bound = -1;
		} else {
796
			w += nexthop_nh->fib_nh_weight;
797
798
799
800
			upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
							    total) - 1;
		}

801
		atomic_set(&nexthop_nh->fib_nh_upper_bound, upper_bound);
802
803
804
805
	} endfor_nexthops(fi);
}
#else /* CONFIG_IP_ROUTE_MULTIPATH */

806
807
808
809
810
811
812
813
814
static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
		       int remaining, struct fib_config *cfg,
		       struct netlink_ext_ack *extack)
{
	NL_SET_ERR_MSG(extack, "Multipath support not enabled in kernel");

	return -EINVAL;
}

815
816
817
818
#define fib_rebalance(fi) do { } while (0)

#endif /* CONFIG_IP_ROUTE_MULTIPATH */

819
static int fib_encap_match(struct net *net, u16 encap_type,
820
			   struct nlattr *encap,
821
			   const struct fib_nh *nh,
822
823
			   const struct fib_config *cfg,
			   struct netlink_ext_ack *extack)
824
825
826
827
828
829
830
{
	struct lwtunnel_state *lwtstate;
	int ret, result = 0;

	if (encap_type == LWTUNNEL_ENCAP_NONE)
		return 0;

831
	ret = lwtunnel_build_state(net, encap_type, encap, AF_INET,
832
				   cfg, &lwtstate, extack);
833
	if (!ret) {
834
		result = lwtunnel_cmp_encap(lwtstate, nh->fib_nh_lws);
835
836
837
838
839
840
		lwtstate_free(lwtstate);
	}

	return result;
}

841
int fib_nh_match(struct net *net, struct fib_config *cfg, struct fib_info *fi,
842
		 struct netlink_ext_ack *extack)
843
844
845
846
847
848
849
850
851
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	struct rtnexthop *rtnh;
	int remaining;
#endif

	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
		return 1;

852
853
854
855
856
857
	if (cfg->fc_nh_id) {
		if (fi->nh && cfg->fc_nh_id == fi->nh->id)
			return 0;
		return 1;
	}

858
	if (cfg->fc_oif || cfg->fc_gw_family) {
859
860
		struct fib_nh *nh = fib_info_nh(fi, 0);

861
		if (cfg->fc_encap) {
862
863
			if (fib_encap_match(net, cfg->fc_encap_type,
					    cfg->fc_encap, nh, cfg, extack))
864
				return 1;
865
		}
866
867
#ifdef CONFIG_IP_ROUTE_CLASSID
		if (cfg->fc_flow &&
868
		    cfg->fc_flow != nh->nh_tclassid)
869
870
			return 1;
#endif
871
		if ((cfg->fc_oif && cfg->fc_oif != nh->fib_nh_oif) ||
872
		    (cfg->fc_gw_family &&
873
		     cfg->fc_gw_family != nh->fib_nh_gw_family))
874
875
876
			return 1;

		if (cfg->fc_gw_family == AF_INET &&
877
		    cfg->fc_gw4 != nh->fib_nh_gw4)
878
879
880
			return 1;

		if (cfg->fc_gw_family == AF_INET6 &&
881
		    ipv6_addr_cmp(&cfg->fc_gw6, &nh->fib_nh_gw6))
882
883
884
			return 1;

		return 0;
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (!cfg->fc_mp)
		return 0;

	rtnh = cfg->fc_mp;
	remaining = cfg->fc_mp_len;

	for_nexthops(fi) {
		int attrlen;

		if (!rtnh_ok(rtnh, remaining))
			return -EINVAL;

900
		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->fib_nh_oif)
901
902
903
904
			return 1;

		attrlen = rtnh_attrlen(rtnh);
		if (attrlen > 0) {
905
			struct nlattr *nla, *nlav, *attrs = rtnh_attrs(rtnh);
906
907

			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
			nlav = nla_find(attrs, attrlen, RTA_VIA);
			if (nla && nlav) {
				NL_SET_ERR_MSG(extack,
					       "Nexthop configuration can not contain both GATEWAY and VIA");
				return -EINVAL;
			}

			if (nla) {
				if (nh->fib_nh_gw_family != AF_INET ||
				    nla_get_in_addr(nla) != nh->fib_nh_gw4)
					return 1;
			} else if (nlav) {
				struct fib_config cfg2;
				int err;

				err = fib_gw_from_via(&cfg2, nlav, extack);
				if (err)
					return err;

				switch (nh->fib_nh_gw_family) {
				case AF_INET:
					if (cfg2.fc_gw_family != AF_INET ||
					    cfg2.fc_gw4 != nh->fib_nh_gw4)
						return 1;
					break;
				case AF_INET6:
					if (cfg2.fc_gw_family != AF_INET6 ||
					    ipv6_addr_cmp(&cfg2.fc_gw6,
							  &nh->fib_nh_gw6))
						return 1;
					break;
				}
			}

942
943
944
945
946
947
948
949
950
951
952
953
954
#ifdef CONFIG_IP_ROUTE_CLASSID
			nla = nla_find(attrs, attrlen, RTA_FLOW);
			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
				return 1;
#endif
		}

		rtnh = rtnh_next(rtnh, &remaining);
	} endfor_nexthops(fi);
#endif
	return 0;
}

955
956
957
958
959
960
961
962
963
964
bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
{
	struct nlattr *nla;
	int remaining;

	if (!cfg->fc_mx)
		return true;

	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
		int type = nla_type(nla);
965
		u32 fi_val, val;
966
967
968
969
970
971
972
973
974
975
976

		if (!type)
			continue;
		if (type > RTAX_MAX)
			return false;

		if (type == RTAX_CC_ALGO) {
			char tmp[TCP_CA_NAME_MAX];
			bool ecn_ca = false;

			nla_strlcpy(tmp, nla, sizeof(tmp));
977
			val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
978
		} else {
979
980
			if (nla_len(nla) != sizeof(u32))
				return false;
981
982
983
			val = nla_get_u32(nla);
		}

984
985
986
987
988
		fi_val = fi->fib_metrics->metrics[type - 1];
		if (type == RTAX_FEATURES)
			fi_val &= ~DST_FEATURE_ECN_CA;

		if (fi_val != val)
989
990
991
992
993
994
			return false;
	}

	return true;
}

995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
static int fib_check_nh_v6_gw(struct net *net, struct fib_nh *nh,
			      u32 table, struct netlink_ext_ack *extack)
{
	struct fib6_config cfg = {
		.fc_table = table,
		.fc_flags = nh->fib_nh_flags | RTF_GATEWAY,
		.fc_ifindex = nh->fib_nh_oif,
		.fc_gateway = nh->fib_nh_gw6,
	};
	struct fib6_nh fib6_nh = {};
	int err;

	err = ipv6_stub->fib6_nh_init(net, &fib6_nh, &cfg, GFP_KERNEL, extack);
	if (!err) {
		nh->fib_nh_dev = fib6_nh.fib_nh_dev;
		dev_hold(nh->fib_nh_dev);
		nh->fib_nh_oif = nh->fib_nh_dev->ifindex;
		nh->fib_nh_scope = RT_SCOPE_LINK;

		ipv6_stub->fib6_nh_release(&fib6_nh);
	}

	return err;
}
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062

/*
 * Picture
 * -------
 *
 * Semantics of nexthop is very messy by historical reasons.
 * We have to take into account, that:
 * a) gateway can be actually local interface address,
 *    so that gatewayed route is direct.
 * b) gateway must be on-link address, possibly
 *    described not by an ifaddr, but also by a direct route.
 * c) If both gateway and interface are specified, they should not
 *    contradict.
 * d) If we use tunnel routes, gateway could be not on-link.
 *
 * Attempt to reconcile all of these (alas, self-contradictory) conditions
 * results in pretty ugly and hairy code with obscure logic.
 *
 * I chose to generalized it instead, so that the size
 * of code does not increase practically, but it becomes
 * much more general.
 * Every prefix is assigned a "scope" value: "host" is local address,
 * "link" is direct route,
 * [ ... "site" ... "interior" ... ]
 * and "universe" is true gateway route with global meaning.
 *
 * Every prefix refers to a set of "nexthop"s (gw, oif),
 * where gw must have narrower scope. This recursion stops
 * when gw has LOCAL scope or if "nexthop" is declared ONLINK,
 * which means that gw is forced to be on link.
 *
 * Code is still hairy, but now it is apparently logically
 * consistent and very flexible. F.e. as by-product it allows
 * to co-exists in peace independent exterior and interior
 * routing processes.
 *
 * Normally it looks as following.
 *
 * {universe prefix}  -> (gw, oif) [scope link]
 *		  |
 *		  |-> {link prefix} -> (gw, oif) [scope local]
 *					|
 *					|-> {local prefix} (terminal node)
 */
1063
1064
static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table,
			      u8 scope, struct netlink_ext_ack *extack)
1065
1066
{
	struct net_device *dev;
1067
1068
	struct fib_result res;
	int err = 0;
1069

1070
1071
	if (nh->fib_nh_flags & RTNH_F_ONLINK) {
		unsigned int addr_type;
1072

1073
1074
1075
		if (scope >= RT_SCOPE_LINK) {
			NL_SET_ERR_MSG(extack, "Nexthop has invalid scope");
			return -EINVAL;
1076
		}
1077
1078
1079
1080
		dev = __dev_get_by_index(net, nh->fib_nh_oif);
		if (!dev) {
			NL_SET_ERR_MSG(extack, "Nexthop device required for onlink");
			return -ENODEV;
1081
		}
1082
1083
1084
		if (!(dev->flags & IFF_UP)) {
			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
			return -ENETDOWN;
1085
		}
1086
1087
1088
1089
		addr_type = inet_addr_type_dev_table(net, dev, nh->fib_nh_gw4);
		if (addr_type != RTN_UNICAST) {
			NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
			return -EINVAL;
1090
		}
1091
		if (!netif_carrier_ok(dev))
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
			nh->fib_nh_flags |= RTNH_F_LINKDOWN;
		nh->fib_nh_dev = dev;
		dev_hold(dev);
		nh->fib_nh_scope = RT_SCOPE_LINK;
		return 0;
	}
	rcu_read_lock();
	{
		struct fib_table *tbl = NULL;
		struct flowi4 fl4 = {
			.daddr = nh->fib_nh_gw4,
			.flowi4_scope = scope + 1,
			.flowi4_oif = nh->fib_nh_oif,
			.flowi4_iif = LOOPBACK_IFINDEX,
		};

		/* It is not necessary, but requires a bit of thinking */
		if (fl4.flowi4_scope < RT_SCOPE_LINK)
			fl4.flowi4_scope = RT_SCOPE_LINK;

1112
		if (table && table != RT_TABLE_MAIN)
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
			tbl = fib_get_table(net, table);

		if (tbl)
			err = fib_table_lookup(tbl, &fl4, &res,
					       FIB_LOOKUP_IGNORE_LINKSTATE |
					       FIB_LOOKUP_NOREF);

		/* on error or if no table given do full lookup. This
		 * is needed for example when nexthops are in the local
		 * table rather than the given table
		 */
		if (!tbl || err) {
			err = fib_lookup(net, &fl4, &res,
					 FIB_LOOKUP_IGNORE_LINKSTATE);
1127
		}
1128
1129
1130

		if (err) {
			NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
1131
			goto out;
1132
		}
1133
	}
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151

	err = -EINVAL;
	if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) {
		NL_SET_ERR_MSG(extack, "Nexthop has invalid gateway");
		goto out;
	}
	nh->fib_nh_scope = res.scope;
	nh->fib_nh_oif = FIB_RES_OIF(res);
	nh->fib_nh_dev = dev = FIB_RES_DEV(res);
	if (!dev) {
		NL_SET_ERR_MSG(extack,
			       "No egress device for nexthop gateway");
		goto out;
	}
	dev_hold(dev);
	if (!netif_carrier_ok(dev))
		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
	err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
1152
1153
1154
1155
1156
out:
	rcu_read_unlock();
	return err;
}

1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
			      struct netlink_ext_ack *extack)
{
	struct in_device *in_dev;
	int err;

	if (nh->fib_nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) {
		NL_SET_ERR_MSG(extack,
			       "Invalid flags for nexthop - PERVASIVE and ONLINK can not be set");
		return -EINVAL;
	}

	rcu_read_lock();

	err = -ENODEV;
	in_dev = inetdev_by_index(net, nh->fib_nh_oif);
	if (!in_dev)
		goto out;
	err = -ENETDOWN;
	if (!(in_dev->dev->flags & IFF_UP)) {
		NL_SET_ERR_MSG(extack, "Device for nexthop is not up");
		goto out;
	}

	nh->fib_nh_dev = in_dev->dev;
	dev_hold(nh->fib_nh_dev);
	nh->fib_nh_scope = RT_SCOPE_HOST;
	if (!netif_carrier_ok(nh->fib_nh_dev))
		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
	err = 0;
out:
	rcu_read_unlock();
	return err;
}

1192
1193
int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
		 struct netlink_ext_ack *extack)
1194
1195
1196
1197
{
	int err;

	if (nh->fib_nh_gw_family == AF_INET)
1198
		err = fib_check_nh_v4_gw(net, nh, table, scope, extack);
1199
1200
1201
1202
1203
1204
1205
1206
	else if (nh->fib_nh_gw_family == AF_INET6)
		err = fib_check_nh_v6_gw(net, nh, table, extack);
	else
		err = fib_check_nh_nongw(net, nh, extack);

	return err;
}

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
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
static inline unsigned int fib_laddr_hashfn(__be32 val)
{
	unsigned int mask = (fib_info_hash_size - 1);

	return ((__force u32)val ^
		((__force u32)val >> 7) ^
		((__force u32)val >> 14)) & mask;
}

static struct hlist_head *fib_info_hash_alloc(int bytes)
{
	if (bytes <= PAGE_SIZE)
		return kzalloc(bytes, GFP_KERNEL);
	else
		return (struct hlist_head *)
			__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					 get_order(bytes));
}

static void fib_info_hash_free(struct hlist_head *hash, int bytes)
{
	if (!hash)
		return;

	if (bytes <= PAGE_SIZE)
		kfree(hash);
	else
		free_pages((unsigned long) hash, get_order(bytes));
}

static void fib_info_hash_move(struct hlist_head *new_info_hash,
			       struct hlist_head *new_laddrhash,
			       unsigned int new_size)
{
	struct hlist_head *old_info_hash, *old_laddrhash;
	unsigned int old_size = fib_info_hash_size;
	unsigned int i, bytes;

	spin_lock_bh(&fib_info_lock);
	old_info_hash = fib_info_hash;
	old_laddrhash = fib_info_laddrhash;
	fib_info_hash_size = new_size;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *head = &fib_info_hash[i];
		struct hlist_node *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, n, head, fib_hash) {
			struct hlist_head *dest;
			unsigned int new_hash;

			new_hash = fib_info_hashfn(fi);
			dest = &new_info_hash[new_hash];
			hlist_add_head(&fi->fib_hash, dest);
		}
	}
	fib_info_hash = new_info_hash;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *lhead = &fib_info_laddrhash[i];
		struct hlist_node *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
			struct hlist_head *ldest;
			unsigned int new_hash;

			new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
			ldest = &new_laddrhash[new_hash];
			hlist_add_head(&fi->fib_lhash, ldest);
		}
	}
	fib_info_laddrhash = new_laddrhash;

	spin_unlock_bh(&fib_info_lock);

	bytes = old_size * sizeof(struct hlist_head *);
	fib_info_hash_free(old_info_hash, bytes);
	fib_info_hash_free(old_laddrhash, bytes);
}

1289
1290
__be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
				 unsigned char scope)
1291
{
1292
1293
1294
1295
1296
1297
1298
	struct fib_nh *nh;

	if (nhc->nhc_family != AF_INET)
		return inet_select_addr(nhc->nhc_dev, 0, scope);

	nh = container_of(nhc, struct fib_nh, nh_common);
	nh->nh_saddr = inet_select_addr(nh->fib_nh_dev, nh->fib_nh_gw4, scope);
1299
1300
1301
1302
1303
	nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);

	return nh->nh_saddr;
}

1304
1305
1306
1307
1308
1309
1310
__be32 fib_result_prefsrc(struct net *net, struct fib_result *res)
{
	struct fib_nh_common *nhc = res->nhc;

	if (res->fi->fib_prefsrc)
		return res->fi->fib_prefsrc;

1311
1312
1313
1314
1315
1316
1317
	if (nhc->nhc_family == AF_INET) {
		struct fib_nh *nh;

		nh = container_of(nhc, struct fib_nh, nh_common);
		if (nh->nh_saddr_genid == atomic_read(&net->ipv4.dev_addr_genid))
			return nh->nh_saddr;
	}
1318

1319
	return fib_info_update_nhc_saddr(net, nhc, res->fi->fib_scope);
1320
1321
}

1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
{
	if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
	    fib_prefsrc != cfg->fc_dst) {
		u32 tb_id = cfg->fc_table;
		int rc;

		if (tb_id == RT_TABLE_MAIN)
			tb_id = RT_TABLE_LOCAL;

		rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
					  fib_prefsrc, tb_id);

		if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) {
			rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
						  fib_prefsrc, RT_TABLE_LOCAL);
		}

		if (rc != RTN_LOCAL)
			return false;
	}
	return true;
}

1346
1347
struct fib_info *fib_create_info(struct fib_config *cfg,
				 struct netlink_ext_ack *extack)
1348
1349
1350
{
	int err;
	struct fib_info *fi = NULL;
1351
	struct nexthop *nh = NULL;
1352
1353
1354
1355
1356
1357
1358
1359
	struct fib_info *ofi;
	int nhs = 1;
	struct net *net = cfg->fc_nlinfo.nl_net;

	if (cfg->fc_type > RTN_MAX)
		goto err_inval;

	/* Fast check to catch the most weird cases */
1360
1361
	if (fib_props[cfg->fc_type].scope > cfg->fc_scope) {
		NL_SET_ERR_MSG(extack, "Invalid scope");
1362
		goto err_inval;
1363
	}
1364

1365
1366
1367
	if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) {
		NL_SET_ERR_MSG(extack,
			       "Invalid rtm_flags - can not contain DEAD or LINKDOWN");
1368
		goto err_inval;
1369
	}
1370

1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
	if (cfg->fc_nh_id) {
		if (!cfg->fc_mx) {
			fi = fib_find_info_nh(net, cfg);
			if (fi) {
				fi->fib_treeref++;
				return fi;
			}
		}

		nh = nexthop_find_by_id(net, cfg->fc_nh_id);
		if (!nh) {
			NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
			goto err_inval;
		}
		nhs = 0;
	}

1388
1389
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (cfg->fc_mp) {
1390
		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len, extack);
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
		if (nhs == 0)
			goto err_inval;
	}
#endif

	err = -ENOBUFS;
	if (fib_info_cnt >= fib_info_hash_size) {
		unsigned int new_size = fib_info_hash_size << 1;
		struct hlist_head *new_info_hash;
		struct hlist_head *new_laddrhash;
		unsigned int bytes;

		if (!new_size)
			new_size = 16;
		bytes = new_size * sizeof(struct hlist_head *);
		new_info_hash = fib_info_hash_alloc(bytes);
		new_laddrhash = fib_info_hash_alloc(bytes);
		if (!new_info_hash || !new_laddrhash) {
			fib_info_hash_free(new_info_hash, bytes);
			fib_info_hash_free(new_laddrhash, bytes);
		} else
			fib_info_hash_move(new_info_hash, new_laddrhash, new_size);

		if (!fib_info_hash_size)
			goto failure;
	}

1418
	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
1419
1420
	if (!fi)
		goto failure;
1421
1422
	fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
					      cfg->fc_mx_len, extack);
1423
	if (IS_ERR(fi->fib_metrics)) {
1424
1425
1426
		err = PTR_ERR(fi->fib_metrics);
		kfree(fi);
		return ERR_PTR(err);
1427
	}
1428

1429
	fib_info_cnt++;
1430
1431
1432
1433
1434
1435
1436
	fi->fib_net = net;
	fi->fib_protocol = cfg->fc_protocol;
	fi->fib_scope = cfg->fc_scope;
	fi->fib_flags = cfg->fc_flags;
	fi->fib_priority = cfg->fc_priority;
	fi->fib_prefsrc = cfg->fc_prefsrc;
	fi->fib_type = cfg->fc_type;
1437
	fi->fib_tb_id = cfg->fc_table;
1438
1439

	fi->fib_nhs = nhs;
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
	if (nh) {
		if (!nexthop_get(nh)) {
			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
			err = -EINVAL;
		} else {
			err = 0;
			fi->nh = nh;
		}
	} else {
		change_nexthops(fi) {
			nexthop_nh->nh_parent = fi;
		} endfor_nexthops(fi)
1452

1453
1454
1455
1456
1457
1458
		if (cfg->fc_mp)
			err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg,
					  extack);
		else
			err = fib_nh_init(net, fi->fib_nh, cfg, 1, extack);
	}
1459

1460
1461
	if (err != 0)
		goto failure;
1462
1463

	if (fib_props[cfg->fc_type].error) {
1464
		if (cfg->fc_gw_family || cfg->fc_oif || cfg->fc_mp) {
1465
1466
			NL_SET_ERR_MSG(extack,
				       "Gateway, device and multipath can not be specified for this route type");
1467
			goto err_inval;
1468
		}
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
		goto link_it;
	} else {
		switch (cfg->fc_type) {
		case RTN_UNICAST:
		case RTN_LOCAL:
		case RTN_BROADCAST:
		case RTN_ANYCAST:
		case RTN_MULTICAST:
			break;
		default:
1479
			NL_SET_ERR_MSG(extack, "Invalid route type");
1480
1481
1482
1483
			goto err_inval;
		}
	}

1484
1485
	if (cfg->fc_scope > RT_SCOPE_HOST) {
		NL_SET_ERR_MSG(extack, "Invalid scope");
1486
		goto err_inval;
1487
	}
1488

1489
1490
1491
1492
1493
	if (fi->nh) {
		err = fib_check_nexthop(fi->nh, cfg->fc_scope, extack);
		if (err)
			goto failure;
	} else if (cfg->fc_scope == RT_SCOPE_HOST) {
1494
1495
1496
		struct fib_nh *nh = fi->fib_nh;

		/* Local address is added. */
1497
1498
1499
1500
1501
		if (nhs != 1) {
			NL_SET_ERR_MSG(extack,
				       "Route with host scope can not have multiple nexthops");
			goto err_inval;
		}
1502
		if (nh->fib_nh_gw_family) {
1503
1504
			NL_SET_ERR_MSG(extack,
				       "Route with host scope can not have a gateway");
1505
			goto err_inval;
1506
		}
1507
		nh->fib_nh_scope = RT_SCOPE_NOWHERE;
1508
		nh->fib_nh_dev = dev_get_by_index(net, nh->fib_nh_oif);
1509
		err = -ENODEV;
1510
		if (!nh->fib_nh_dev)
1511
1512
1513
1514
1515
			goto failure;
	} else {
		int linkdown = 0;

		change_nexthops(fi) {
1516
1517
1518
			err = fib_check_nh(cfg->fc_nlinfo.nl_net, nexthop_nh,
					   cfg->fc_table, cfg->fc_scope,
					   extack);
1519
1520
			if (err != 0)
				goto failure;
1521
			if (nexthop_nh->fib_nh_flags & RTNH_F_LINKDOWN)
1522
1523
1524
1525
1526
1527
				linkdown++;
		} endfor_nexthops(fi)
		if (linkdown == fi->fib_nhs)
			fi->fib_flags |= RTNH_F_LINKDOWN;
	}

1528
1529
	if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) {
		NL_SET_ERR_MSG(extack, "Invalid prefsrc address");
1530
		goto err_inval;
1531
	}
1532

1533
1534
1535
1536
1537
1538
1539
	if (!fi->nh) {
		change_nexthops(fi) {
			fib_info_update_nhc_saddr(net, &nexthop_nh->nh_common,
						  fi->fib_scope);
			if (nexthop_nh->fib_nh_gw_family == AF_INET6)
				fi->fib_nh_is_v6 = true;
		} endfor_nexthops(fi)
1540

1541
1542
		fib_rebalance(fi);
	}
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553

link_it:
	ofi = fib_find_info(fi);
	if (ofi) {
		fi->fib_dead = 1;
		free_fib_info(fi);
		ofi->fib_treeref++;
		return ofi;
	}

	fi->fib_treeref++;
1554
	refcount_set(&fi->fib_clntref, 1);
1555
1556
1557
1558
1559
1560
1561
1562
1563
	spin_lock_bh(&fib_info_lock);
	hlist_add_head(&fi->fib_hash,
		       &fib_info_hash[fib_info_hashfn(fi)]);
	if (fi->fib_prefsrc) {
		struct hlist_head *head;

		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
		hlist_add_head(&fi->fib_lhash, head);
	}
1564
1565
1566
1567
1568
1569
	if (fi->nh) {
		list_add(&fi->nh_list, &nh->fi_list);
	} else {
		change_nexthops(fi) {
			struct hlist_head *head;
			unsigned int hash;
1570

1571
1572
1573
1574
1575
1576
1577
			if (!nexthop_nh->fib_nh_dev)
				continue;
			hash = fib_devindex_hashfn(nexthop_nh->fib_nh_dev->ifindex);
			head = &fib_info_devhash[hash];
			hlist_add_head(&nexthop_nh->nh_hash, head);
		} endfor_nexthops(fi)
	}
1578
1579
1580
1581
1582
1583
1584
1585