forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
fib_frontend.c
1624 lines (1398 loc) · 38.6 KB
/
fib_frontend.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
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
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
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
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
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
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
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
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
675
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
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* IPv4 Forwarding Information Base: FIB frontend.
*
* Authors: Alexey Kuznetsov, <[email protected]>
*/
#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/nexthop.h>
#include <net/rtnetlink.h>
#include <net/xfrm.h>
#include <net/l3mdev.h>
#include <net/lwtunnel.h>
#include <trace/events/fib.h>
#ifndef CONFIG_IP_MULTIPLE_TABLES
static int __net_init fib4_rules_init(struct net *net)
{
struct fib_table *local_table, *main_table;
main_table = fib_trie_table(RT_TABLE_MAIN, NULL);
if (!main_table)
return -ENOMEM;
local_table = fib_trie_table(RT_TABLE_LOCAL, main_table);
if (!local_table)
goto fail;
hlist_add_head_rcu(&local_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
hlist_add_head_rcu(&main_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
return 0;
fail:
fib_free_table(main_table);
return -ENOMEM;
}
#else
struct fib_table *fib_new_table(struct net *net, u32 id)
{
struct fib_table *tb, *alias = NULL;
unsigned int h;
if (id == 0)
id = RT_TABLE_MAIN;
tb = fib_get_table(net, id);
if (tb)
return tb;
if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
alias = fib_new_table(net, RT_TABLE_MAIN);
tb = fib_trie_table(id, alias);
if (!tb)
return NULL;
switch (id) {
case RT_TABLE_MAIN:
rcu_assign_pointer(net->ipv4.fib_main, tb);
break;
case RT_TABLE_DEFAULT:
rcu_assign_pointer(net->ipv4.fib_default, tb);
break;
default:
break;
}
h = id & (FIB_TABLE_HASHSZ - 1);
hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]);
return tb;
}
EXPORT_SYMBOL_GPL(fib_new_table);
/* caller must hold either rtnl or rcu read lock */
struct fib_table *fib_get_table(struct net *net, u32 id)
{
struct fib_table *tb;
struct hlist_head *head;
unsigned int h;
if (id == 0)
id = RT_TABLE_MAIN;
h = id & (FIB_TABLE_HASHSZ - 1);
head = &net->ipv4.fib_table_hash[h];
hlist_for_each_entry_rcu(tb, head, tb_hlist,
lockdep_rtnl_is_held()) {
if (tb->tb_id == id)
return tb;
}
return NULL;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */
static void fib_replace_table(struct net *net, struct fib_table *old,
struct fib_table *new)
{
#ifdef CONFIG_IP_MULTIPLE_TABLES
switch (new->tb_id) {
case RT_TABLE_MAIN:
rcu_assign_pointer(net->ipv4.fib_main, new);
break;
case RT_TABLE_DEFAULT:
rcu_assign_pointer(net->ipv4.fib_default, new);
break;
default:
break;
}
#endif
/* replace the old table in the hlist */
hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist);
}
int fib_unmerge(struct net *net)
{
struct fib_table *old, *new, *main_table;
/* attempt to fetch local table if it has been allocated */
old = fib_get_table(net, RT_TABLE_LOCAL);
if (!old)
return 0;
new = fib_trie_unmerge(old);
if (!new)
return -ENOMEM;
/* table is already unmerged */
if (new == old)
return 0;
/* replace merged table with clean table */
fib_replace_table(net, old, new);
fib_free_table(old);
/* attempt to fetch main table if it has been allocated */
main_table = fib_get_table(net, RT_TABLE_MAIN);
if (!main_table)
return 0;
/* flush local entries from main table */
fib_table_flush_external(main_table);
return 0;
}
void fib_flush(struct net *net)
{
int flushed = 0;
unsigned int h;
for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
struct hlist_head *head = &net->ipv4.fib_table_hash[h];
struct hlist_node *tmp;
struct fib_table *tb;
hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
flushed += fib_table_flush(net, tb, false);
}
if (flushed)
rt_cache_flush(net);
}
/*
* Find address type as if only "dev" was present in the system. If
* on_dev is NULL then all interfaces are taken into consideration.
*/
static inline unsigned int __inet_dev_addr_type(struct net *net,
const struct net_device *dev,
__be32 addr, u32 tb_id)
{
struct flowi4 fl4 = { .daddr = addr };
struct fib_result res;
unsigned int ret = RTN_BROADCAST;
struct fib_table *table;
if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
return RTN_BROADCAST;
if (ipv4_is_multicast(addr))
return RTN_MULTICAST;
rcu_read_lock();
table = fib_get_table(net, tb_id);
if (table) {
ret = RTN_UNICAST;
if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) {
struct fib_nh_common *nhc = fib_info_nhc(res.fi, 0);
if (!dev || dev == nhc->nhc_dev)
ret = res.type;
}
}
rcu_read_unlock();
return ret;
}
unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id)
{
return __inet_dev_addr_type(net, NULL, addr, tb_id);
}
EXPORT_SYMBOL(inet_addr_type_table);
unsigned int inet_addr_type(struct net *net, __be32 addr)
{
return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL);
}
EXPORT_SYMBOL(inet_addr_type);
unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
__be32 addr)
{
u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
return __inet_dev_addr_type(net, dev, addr, rt_table);
}
EXPORT_SYMBOL(inet_dev_addr_type);
/* inet_addr_type with dev == NULL but using the table from a dev
* if one is associated
*/
unsigned int inet_addr_type_dev_table(struct net *net,
const struct net_device *dev,
__be32 addr)
{
u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;
return __inet_dev_addr_type(net, NULL, addr, rt_table);
}
EXPORT_SYMBOL(inet_addr_type_dev_table);
__be32 fib_compute_spec_dst(struct sk_buff *skb)
{
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct fib_result res;
struct rtable *rt;
struct net *net;
int scope;
rt = skb_rtable(skb);
if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) ==
RTCF_LOCAL)
return ip_hdr(skb)->daddr;
in_dev = __in_dev_get_rcu(dev);
net = dev_net(dev);
scope = RT_SCOPE_UNIVERSE;
if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
struct flowi4 fl4 = {
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
.daddr = ip_hdr(skb)->saddr,
.flowi4_tos = ip_hdr(skb)->tos & IPTOS_RT_MASK,
.flowi4_scope = scope,
.flowi4_mark = vmark ? skb->mark : 0,
};
if (!fib_lookup(net, &fl4, &res, 0))
return fib_result_prefsrc(net, &res);
} else {
scope = RT_SCOPE_LINK;
}
return inet_select_addr(dev, ip_hdr(skb)->saddr, scope);
}
bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev)
{
bool dev_match = false;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (unlikely(fi->nh)) {
dev_match = nexthop_uses_dev(fi->nh, dev);
} else {
int ret;
for (ret = 0; ret < fib_info_num_path(fi); ret++) {
const struct fib_nh_common *nhc = fib_info_nhc(fi, ret);
if (nhc_l3mdev_matches_dev(nhc, dev)) {
dev_match = true;
break;
}
}
}
#else
if (fib_info_nhc(fi, 0)->nhc_dev == dev)
dev_match = true;
#endif
return dev_match;
}
EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev);
/* Given (packet source, input interface) and optional (dst, oif, tos):
* - (main) check, that source is valid i.e. not broadcast or our local
* address.
* - figure out what "logical" interface this packet arrived
* and calculate "specific destination" address.
* - check, that packet arrived from expected physical interface.
* called with rcu_read_lock()
*/
static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
int rpf, struct in_device *idev, u32 *itag)
{
struct net *net = dev_net(dev);
struct flow_keys flkeys;
int ret, no_addr;
struct fib_result res;
struct flowi4 fl4;
bool dev_match;
fl4.flowi4_oif = 0;
fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev);
if (!fl4.flowi4_iif)
fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX;
fl4.daddr = src;
fl4.saddr = dst;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.flowi4_tun_key.tun_id = 0;
fl4.flowi4_flags = 0;
fl4.flowi4_uid = sock_net_uid(net, NULL);
fl4.flowi4_multipath_hash = 0;
no_addr = idev->ifa_list == NULL;
fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) {
fl4.flowi4_proto = 0;
fl4.fl4_sport = 0;
fl4.fl4_dport = 0;
}
if (fib_lookup(net, &fl4, &res, 0))
goto last_resort;
if (res.type != RTN_UNICAST &&
(res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
goto e_inval;
fib_combine_itag(itag, &res);
dev_match = fib_info_nh_uses_dev(res.fi, dev);
/* This is not common, loopback packets retain skb_dst so normally they
* would not even hit this slow path.
*/
dev_match = dev_match || (res.type == RTN_LOCAL &&
dev == net->loopback_dev);
if (dev_match) {
ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
return ret;
}
if (no_addr)
goto last_resort;
if (rpf == 1)
goto e_rpf;
fl4.flowi4_oif = dev->ifindex;
ret = 0;
if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
if (res.type == RTN_UNICAST)
ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
}
return ret;
last_resort:
if (rpf)
goto e_rpf;
*itag = 0;
return 0;
e_inval:
return -EINVAL;
e_rpf:
return -EXDEV;
}
/* Ignore rp_filter for packets protected by IPsec. */
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
u8 tos, int oif, struct net_device *dev,
struct in_device *idev, u32 *itag)
{
int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
struct net *net = dev_net(dev);
if (!r && !fib_num_tclassid_users(net) &&
(dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
if (IN_DEV_ACCEPT_LOCAL(idev))
goto ok;
/* with custom local routes in place, checking local addresses
* only will be too optimistic, with custom rules, checking
* local addresses only can be too strict, e.g. due to vrf
*/
if (net->ipv4.fib_has_custom_local_routes ||
fib4_has_custom_rules(net))
goto full_check;
if (inet_lookup_ifaddr_rcu(net, src))
return -EINVAL;
ok:
*itag = 0;
return 0;
}
full_check:
return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
}
static inline __be32 sk_extract_addr(struct sockaddr *addr)
{
return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
}
static int put_rtax(struct nlattr *mx, int len, int type, u32 value)
{
struct nlattr *nla;
nla = (struct nlattr *) ((char *) mx + len);
nla->nla_type = type;
nla->nla_len = nla_attr_size(4);
*(u32 *) nla_data(nla) = value;
return len + nla_total_size(4);
}
static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
struct fib_config *cfg)
{
__be32 addr;
int plen;
memset(cfg, 0, sizeof(*cfg));
cfg->fc_nlinfo.nl_net = net;
if (rt->rt_dst.sa_family != AF_INET)
return -EAFNOSUPPORT;
/*
* Check mask for validity:
* a) it must be contiguous.
* b) destination must have all host bits clear.
* c) if application forgot to set correct family (AF_INET),
* reject request unless it is absolutely clear i.e.
* both family and mask are zero.
*/
plen = 32;
addr = sk_extract_addr(&rt->rt_dst);
if (!(rt->rt_flags & RTF_HOST)) {
__be32 mask = sk_extract_addr(&rt->rt_genmask);
if (rt->rt_genmask.sa_family != AF_INET) {
if (mask || rt->rt_genmask.sa_family)
return -EAFNOSUPPORT;
}
if (bad_mask(mask, addr))
return -EINVAL;
plen = inet_mask_len(mask);
}
cfg->fc_dst_len = plen;
cfg->fc_dst = addr;
if (cmd != SIOCDELRT) {
cfg->fc_nlflags = NLM_F_CREATE;
cfg->fc_protocol = RTPROT_BOOT;
}
if (rt->rt_metric)
cfg->fc_priority = rt->rt_metric - 1;
if (rt->rt_flags & RTF_REJECT) {
cfg->fc_scope = RT_SCOPE_HOST;
cfg->fc_type = RTN_UNREACHABLE;
return 0;
}
cfg->fc_scope = RT_SCOPE_NOWHERE;
cfg->fc_type = RTN_UNICAST;
if (rt->rt_dev) {
char *colon;
struct net_device *dev;
char devname[IFNAMSIZ];
if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1))
return -EFAULT;
devname[IFNAMSIZ-1] = 0;
colon = strchr(devname, ':');
if (colon)
*colon = 0;
dev = __dev_get_by_name(net, devname);
if (!dev)
return -ENODEV;
cfg->fc_oif = dev->ifindex;
cfg->fc_table = l3mdev_fib_table(dev);
if (colon) {
const struct in_ifaddr *ifa;
struct in_device *in_dev;
in_dev = __in_dev_get_rtnl(dev);
if (!in_dev)
return -ENODEV;
*colon = ':';
rcu_read_lock();
in_dev_for_each_ifa_rcu(ifa, in_dev) {
if (strcmp(ifa->ifa_label, devname) == 0)
break;
}
rcu_read_unlock();
if (!ifa)
return -ENODEV;
cfg->fc_prefsrc = ifa->ifa_local;
}
}
addr = sk_extract_addr(&rt->rt_gateway);
if (rt->rt_gateway.sa_family == AF_INET && addr) {
unsigned int addr_type;
cfg->fc_gw4 = addr;
cfg->fc_gw_family = AF_INET;
addr_type = inet_addr_type_table(net, addr, cfg->fc_table);
if (rt->rt_flags & RTF_GATEWAY &&
addr_type == RTN_UNICAST)
cfg->fc_scope = RT_SCOPE_UNIVERSE;
}
if (cmd == SIOCDELRT)
return 0;
if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family)
return -EINVAL;
if (cfg->fc_scope == RT_SCOPE_NOWHERE)
cfg->fc_scope = RT_SCOPE_LINK;
if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) {
struct nlattr *mx;
int len = 0;
mx = kcalloc(3, nla_total_size(4), GFP_KERNEL);
if (!mx)
return -ENOMEM;
if (rt->rt_flags & RTF_MTU)
len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40);
if (rt->rt_flags & RTF_WINDOW)
len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window);
if (rt->rt_flags & RTF_IRTT)
len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3);
cfg->fc_mx = mx;
cfg->fc_mx_len = len;
}
return 0;
}
/*
* Handle IP routing ioctl calls.
* These are used to manipulate the routing tables
*/
int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
{
struct fib_config cfg;
int err;
switch (cmd) {
case SIOCADDRT: /* Add a route */
case SIOCDELRT: /* Delete a route */
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
rtnl_lock();
err = rtentry_to_fib_config(net, cmd, rt, &cfg);
if (err == 0) {
struct fib_table *tb;
if (cmd == SIOCDELRT) {
tb = fib_get_table(net, cfg.fc_table);
if (tb)
err = fib_table_delete(net, tb, &cfg,
NULL);
else
err = -ESRCH;
} else {
tb = fib_new_table(net, cfg.fc_table);
if (tb)
err = fib_table_insert(net, tb,
&cfg, NULL);
else
err = -ENOBUFS;
}
/* allocated by rtentry_to_fib_config() */
kfree(cfg.fc_mx);
}
rtnl_unlock();
return err;
}
return -EINVAL;
}
const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
[RTA_UNSPEC] = { .strict_start_type = RTA_DPORT + 1 },
[RTA_DST] = { .type = NLA_U32 },
[RTA_SRC] = { .type = NLA_U32 },
[RTA_IIF] = { .type = NLA_U32 },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_GATEWAY] = { .type = NLA_U32 },
[RTA_PRIORITY] = { .type = NLA_U32 },
[RTA_PREFSRC] = { .type = NLA_U32 },
[RTA_METRICS] = { .type = NLA_NESTED },
[RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) },
[RTA_FLOW] = { .type = NLA_U32 },
[RTA_ENCAP_TYPE] = { .type = NLA_U16 },
[RTA_ENCAP] = { .type = NLA_NESTED },
[RTA_UID] = { .type = NLA_U32 },
[RTA_MARK] = { .type = NLA_U32 },
[RTA_TABLE] = { .type = NLA_U32 },
[RTA_IP_PROTO] = { .type = NLA_U8 },
[RTA_SPORT] = { .type = NLA_U16 },
[RTA_DPORT] = { .type = NLA_U16 },
[RTA_NH_ID] = { .type = NLA_U32 },
};
int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
struct netlink_ext_ack *extack)
{
struct rtvia *via;
int alen;
if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) {
NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA");
return -EINVAL;
}
via = nla_data(nla);
alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr);
switch (via->rtvia_family) {
case AF_INET:
if (alen != sizeof(__be32)) {
NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA");
return -EINVAL;
}
cfg->fc_gw_family = AF_INET;
cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
break;
case AF_INET6:
#if IS_ENABLED(CONFIG_IPV6)
if (alen != sizeof(struct in6_addr)) {
NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
return -EINVAL;
}
cfg->fc_gw_family = AF_INET6;
cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr);
#else
NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
return -EINVAL;
#endif
break;
default:
NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA");
return -EINVAL;
}
return 0;
}
static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
struct nlmsghdr *nlh, struct fib_config *cfg,
struct netlink_ext_ack *extack)
{
bool has_gw = false, has_via = false;
struct nlattr *attr;
int err, remaining;
struct rtmsg *rtm;
err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX,
rtm_ipv4_policy, extack);
if (err < 0)
goto errout;
memset(cfg, 0, sizeof(*cfg));
rtm = nlmsg_data(nlh);
cfg->fc_dst_len = rtm->rtm_dst_len;
cfg->fc_tos = rtm->rtm_tos;
cfg->fc_table = rtm->rtm_table;
cfg->fc_protocol = rtm->rtm_protocol;
cfg->fc_scope = rtm->rtm_scope;
cfg->fc_type = rtm->rtm_type;
cfg->fc_flags = rtm->rtm_flags;
cfg->fc_nlflags = nlh->nlmsg_flags;
cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
cfg->fc_nlinfo.nlh = nlh;
cfg->fc_nlinfo.nl_net = net;
if (cfg->fc_type > RTN_MAX) {
NL_SET_ERR_MSG(extack, "Invalid route type");
err = -EINVAL;
goto errout;
}
nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
switch (nla_type(attr)) {
case RTA_DST:
cfg->fc_dst = nla_get_be32(attr);
break;
case RTA_OIF:
cfg->fc_oif = nla_get_u32(attr);
break;
case RTA_GATEWAY:
has_gw = true;
cfg->fc_gw4 = nla_get_be32(attr);
if (cfg->fc_gw4)
cfg->fc_gw_family = AF_INET;
break;
case RTA_VIA:
has_via = true;
err = fib_gw_from_via(cfg, attr, extack);
if (err)
goto errout;
break;
case RTA_PRIORITY:
cfg->fc_priority = nla_get_u32(attr);
break;
case RTA_PREFSRC:
cfg->fc_prefsrc = nla_get_be32(attr);
break;
case RTA_METRICS:
cfg->fc_mx = nla_data(attr);
cfg->fc_mx_len = nla_len(attr);
break;
case RTA_MULTIPATH:
err = lwtunnel_valid_encap_type_attr(nla_data(attr),
nla_len(attr),
extack);
if (err < 0)
goto errout;
cfg->fc_mp = nla_data(attr);
cfg->fc_mp_len = nla_len(attr);
break;
case RTA_FLOW:
cfg->fc_flow = nla_get_u32(attr);
break;
case RTA_TABLE:
cfg->fc_table = nla_get_u32(attr);
break;
case RTA_ENCAP:
cfg->fc_encap = attr;
break;
case RTA_ENCAP_TYPE:
cfg->fc_encap_type = nla_get_u16(attr);
err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
extack);
if (err < 0)
goto errout;
break;
case RTA_NH_ID:
cfg->fc_nh_id = nla_get_u32(attr);
break;
}
}
if (cfg->fc_nh_id) {
if (cfg->fc_oif || cfg->fc_gw_family ||
cfg->fc_encap || cfg->fc_mp) {
NL_SET_ERR_MSG(extack,
"Nexthop specification and nexthop id are mutually exclusive");
return -EINVAL;
}
}
if (has_gw && has_via) {
NL_SET_ERR_MSG(extack,
"Nexthop configuration can not contain both GATEWAY and VIA");
return -EINVAL;
}
return 0;
errout:
return err;
}
static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
struct fib_table *tb;
int err;
err = rtm_to_fib_config(net, skb, nlh, &cfg, extack);
if (err < 0)
goto errout;
if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) {
NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
err = -EINVAL;
goto errout;
}
tb = fib_get_table(net, cfg.fc_table);
if (!tb) {
NL_SET_ERR_MSG(extack, "FIB table does not exist");
err = -ESRCH;
goto errout;
}
err = fib_table_delete(net, tb, &cfg, extack);
errout:
return err;
}
static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
struct netlink_ext_ack *extack)
{
struct net *net = sock_net(skb->sk);
struct fib_config cfg;
struct fib_table *tb;
int err;
err = rtm_to_fib_config(net, skb, nlh, &cfg, extack);
if (err < 0)
goto errout;
tb = fib_new_table(net, cfg.fc_table);
if (!tb) {
err = -ENOBUFS;
goto errout;
}
err = fib_table_insert(net, tb, &cfg, extack);
if (!err && cfg.fc_type == RTN_LOCAL)
net->ipv4.fib_has_custom_local_routes = true;
errout:
return err;
}
int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
struct fib_dump_filter *filter,
struct netlink_callback *cb)
{
struct netlink_ext_ack *extack = cb->extack;
struct nlattr *tb[RTA_MAX + 1];
struct rtmsg *rtm;
int err, i;
ASSERT_RTNL();
if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request");
return -EINVAL;
}
rtm = nlmsg_data(nlh);
if (rtm->rtm_dst_len || rtm->rtm_src_len || rtm->rtm_tos ||
rtm->rtm_scope) {
NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request");
return -EINVAL;
}
if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) {
NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request");
return -EINVAL;
}
if (rtm->rtm_flags & RTM_F_CLONED)
filter->dump_routes = false;
else
filter->dump_exceptions = false;
filter->flags = rtm->rtm_flags;
filter->protocol = rtm->rtm_protocol;
filter->rt_type = rtm->rtm_type;
filter->table_id = rtm->rtm_table;
err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
rtm_ipv4_policy, extack);
if (err < 0)
return err;
for (i = 0; i <= RTA_MAX; ++i) {
int ifindex;
if (!tb[i])
continue;
switch (i) {
case RTA_TABLE:
filter->table_id = nla_get_u32(tb[i]);
break;
case RTA_OIF:
ifindex = nla_get_u32(tb[i]);
filter->dev = __dev_get_by_index(net, ifindex);
if (!filter->dev)
return -ENODEV;
break;
default:
NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request");
return -EINVAL;
}
}
if (filter->flags || filter->protocol || filter->rt_type ||
filter->table_id || filter->dev) {
filter->filter_set = 1;
cb->answer_flags = NLM_F_DUMP_FILTERED;
}
return 0;
}
EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req);
static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
struct fib_dump_filter filter = { .dump_routes = true,
.dump_exceptions = true };
const struct nlmsghdr *nlh = cb->nlh;
struct net *net = sock_net(skb->sk);
unsigned int h, s_h;
unsigned int e = 0, s_e;
struct fib_table *tb;
struct hlist_head *head;
int dumped = 0, err;
if (cb->strict_check) {
err = ip_valid_fib_dump_req(net, nlh, &filter, cb);
if (err < 0)
return err;
} else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) {
struct rtmsg *rtm = nlmsg_data(nlh);
filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED);
}
/* ipv4 does not use prefix flag */
if (filter.flags & RTM_F_PREFIX)
return skb->len;
if (filter.table_id) {
tb = fib_get_table(net, filter.table_id);
if (!tb) {
if (rtnl_msg_family(cb->nlh) != PF_INET)
return skb->len;
NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
return -ENOENT;
}