forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 4
/
Copy pathroute.c
3764 lines (3222 loc) · 95.1 KB
/
route.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.
*
* ROUTE - implementation of the IP router.
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Alan Cox, <[email protected]>
* Linus Torvalds, <[email protected]>
* Alexey Kuznetsov, <[email protected]>
*
* Fixes:
* Alan Cox : Verify area fixes.
* Alan Cox : cli() protects routing changes
* Rui Oliveira : ICMP routing table updates
* ([email protected]) Routing table insertion and update
* Linus Torvalds : Rewrote bits to be sensible
* Alan Cox : Added BSD route gw semantics
* Alan Cox : Super /proc >4K
* 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.
*
* 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
* Eric Dumazet : hashed spinlocks and rt_check_expire() fixes.
* Ilia Sotnikov : Ignore TOS on PMTUD and Redirect
* Ilia Sotnikov : Removed TOS from hash calculations
*/
#define pr_fmt(fmt) "IPv4: " fmt
#include <linux/module.h>
#include <linux/bitops.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/memblock.h>
#include <linux/socket.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/rcupdate.h>
#include <linux/slab.h>
#include <linux/jhash.h>
#include <net/dst.h>
#include <net/dst_metadata.h>
#include <net/inet_dscp.h>
#include <net/net_namespace.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/nexthop.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <net/secure_seq.h>
#include <net/ip_tunnels.h>
#include "fib_lookup.h"
#define RT_GC_TIMEOUT (300*HZ)
#define DEFAULT_MIN_PMTU (512 + 20 + 20)
#define DEFAULT_MTU_EXPIRES (10 * 60 * HZ)
#define DEFAULT_MIN_ADVMSS 256
static int ip_rt_max_size;
static int ip_rt_redirect_number __read_mostly = 9;
static int ip_rt_redirect_load __read_mostly = HZ / 50;
static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
/*
* Interface to generic destination cache.
*/
INDIRECT_CALLABLE_SCOPE
struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
INDIRECT_CALLABLE_SCOPE
unsigned int ipv4_mtu(const struct dst_entry *dst);
static void ipv4_negative_advice(struct sock *sk,
struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb, u32 mtu,
bool confirm_neigh);
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk,
struct sk_buff *skb);
static void ipv4_dst_destroy(struct dst_entry *dst);
static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
{
WARN_ON(1);
return NULL;
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr);
static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr);
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
.redirect = ip_do_redirect,
.local_out = __ip_local_out,
.neigh_lookup = ipv4_neigh_lookup,
.confirm_neigh = ipv4_confirm_neigh,
};
#define ECN_OR_COST(class) TC_PRIO_##class
const __u8 ip_tos2prio[16] = {
TC_PRIO_BESTEFFORT,
ECN_OR_COST(BESTEFFORT),
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)
};
EXPORT_SYMBOL(ip_tos2prio);
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field)
#ifdef CONFIG_PROC_FS
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
if (*pos)
return NULL;
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
++*pos;
return NULL;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
}
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");
return 0;
}
static const struct seq_operations rt_cache_seq_ops = {
.start = rt_cache_seq_start,
.next = rt_cache_seq_next,
.stop = rt_cache_seq_stop,
.show = rt_cache_seq_show,
};
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_cpu_ids; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
}
static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int cpu;
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
(*pos)++;
return NULL;
}
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) {
seq_puts(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");
return 0;
}
seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x "
"%08x %08x %08x %08x %08x %08x "
"%08x %08x %08x %08x\n",
dst_entries_get_slow(&ipv4_dst_ops),
0, /* 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,
0, /* st->out_hit */
st->out_slow_tot,
st->out_slow_mc,
0, /* st->gc_total */
0, /* st->gc_ignored */
0, /* st->gc_goal_miss */
0, /* st->gc_dst_overflow */
0, /* st->in_hlist_search */
0 /* st->out_hlist_search */
);
return 0;
}
static const struct seq_operations rt_cpu_seq_ops = {
.start = rt_cpu_seq_start,
.next = rt_cpu_seq_next,
.stop = rt_cpu_seq_stop,
.show = rt_cpu_seq_show,
};
#ifdef CONFIG_IP_ROUTE_CLASSID
static int rt_acct_proc_show(struct seq_file *m, void *v)
{
struct ip_rt_acct *dst, *src;
unsigned int i, j;
dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL);
if (!dst)
return -ENOMEM;
for_each_possible_cpu(i) {
src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i);
for (j = 0; j < 256; j++) {
dst[j].o_bytes += src[j].o_bytes;
dst[j].o_packets += src[j].o_packets;
dst[j].i_bytes += src[j].i_bytes;
dst[j].i_packets += src[j].i_packets;
}
}
seq_write(m, dst, 256 * sizeof(struct ip_rt_acct));
kfree(dst);
return 0;
}
#endif
static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
pde = proc_create_seq("rt_cache", 0444, net->proc_net,
&rt_cache_seq_ops);
if (!pde)
goto err1;
pde = proc_create_seq("rt_cache", 0444, net->proc_net_stat,
&rt_cpu_seq_ops);
if (!pde)
goto err2;
#ifdef CONFIG_IP_ROUTE_CLASSID
pde = proc_create_single("rt_acct", 0, net->proc_net,
rt_acct_proc_show);
if (!pde)
goto err3;
#endif
return 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
err3:
remove_proc_entry("rt_cache", net->proc_net_stat);
#endif
err2:
remove_proc_entry("rt_cache", net->proc_net);
err1:
return -ENOMEM;
}
static void __net_exit ip_rt_do_proc_exit(struct net *net)
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
#ifdef CONFIG_IP_ROUTE_CLASSID
remove_proc_entry("rt_acct", net->proc_net);
#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
.init = ip_rt_do_proc_init,
.exit = ip_rt_do_proc_exit,
};
static int __init ip_rt_proc_init(void)
{
return register_pernet_subsys(&ip_rt_proc_ops);
}
#else
static inline int ip_rt_proc_init(void)
{
return 0;
}
#endif /* CONFIG_PROC_FS */
static inline bool rt_is_expired(const struct rtable *rth)
{
return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev));
}
void rt_cache_flush(struct net *net)
{
rt_genid_bump_ipv4(net);
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
struct sk_buff *skb,
const void *daddr)
{
const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
struct neighbour *n;
rcu_read_lock();
if (likely(rt->rt_gw_family == AF_INET)) {
n = ip_neigh_gw4(dev, rt->rt_gw4);
} else if (rt->rt_gw_family == AF_INET6) {
n = ip_neigh_gw6(dev, &rt->rt_gw6);
} else {
__be32 pkey;
pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr);
n = ip_neigh_gw4(dev, pkey);
}
if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt))
n = NULL;
rcu_read_unlock();
return n;
}
static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr)
{
const struct rtable *rt = container_of(dst, struct rtable, dst);
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
if (rt->rt_gw_family == AF_INET) {
pkey = (const __be32 *)&rt->rt_gw4;
} else if (rt->rt_gw_family == AF_INET6) {
return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6);
} else if (!daddr ||
(rt->rt_flags &
(RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) {
return;
}
__ipv4_confirm_neigh(dev, *(__force u32 *)pkey);
}
/* Hash tables of size 2048..262144 depending on RAM size.
* Each bucket uses 8 bytes.
*/
static u32 ip_idents_mask __read_mostly;
static atomic_t *ip_idents __read_mostly;
static u32 *ip_tstamps __read_mostly;
/* In order to protect privacy, we add a perturbation to identifiers
* if one generator is seldom used. This makes hard for an attacker
* to infer how many packets were sent between two points in time.
*/
static u32 ip_idents_reserve(u32 hash, int segs)
{
u32 bucket, old, now = (u32)jiffies;
atomic_t *p_id;
u32 *p_tstamp;
u32 delta = 0;
bucket = hash & ip_idents_mask;
p_tstamp = ip_tstamps + bucket;
p_id = ip_idents + bucket;
old = READ_ONCE(*p_tstamp);
if (old != now && cmpxchg(p_tstamp, old, now) == old)
delta = get_random_u32_below(now - old);
/* If UBSAN reports an error there, please make sure your compiler
* supports -fno-strict-overflow before reporting it that was a bug
* in UBSAN, and it has been fixed in GCC-8.
*/
return atomic_add_return(segs + delta, p_id) - segs;
}
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs)
{
u32 hash, id;
/* Note the following code is not safe, but this is okay. */
if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key)))
get_random_bytes(&net->ipv4.ip_id_key,
sizeof(net->ipv4.ip_id_key));
hash = siphash_3u32((__force u32)iph->daddr,
(__force u32)iph->saddr,
iph->protocol,
&net->ipv4.ip_id_key);
id = ip_idents_reserve(hash, segs);
iph->id = htons(id);
}
EXPORT_SYMBOL(__ip_select_ident);
static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
const struct sock *sk, const struct iphdr *iph,
int oif, __u8 tos, u8 prot, u32 mark,
int flow_flags)
{
__u8 scope = RT_SCOPE_UNIVERSE;
if (sk) {
oif = sk->sk_bound_dev_if;
mark = READ_ONCE(sk->sk_mark);
tos = ip_sock_rt_tos(sk);
scope = ip_sock_rt_scope(sk);
prot = inet_test_bit(HDRINCL, sk) ? IPPROTO_RAW :
sk->sk_protocol;
}
flowi4_init_output(fl4, oif, mark, tos & INET_DSCP_MASK, scope,
prot, flow_flags, iph->daddr, iph->saddr, 0, 0,
sock_net_uid(net, sk));
}
static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb,
const struct sock *sk)
{
const struct net *net = dev_net(skb->dev);
const struct iphdr *iph = ip_hdr(skb);
int oif = skb->dev->ifindex;
u8 prot = iph->protocol;
u32 mark = skb->mark;
__u8 tos = iph->tos;
__build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0);
}
static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
const struct ip_options_rcu *inet_opt;
__be32 daddr = inet->inet_daddr;
rcu_read_lock();
inet_opt = rcu_dereference(inet->inet_opt);
if (inet_opt && inet_opt->opt.srr)
daddr = inet_opt->opt.faddr;
flowi4_init_output(fl4, sk->sk_bound_dev_if, READ_ONCE(sk->sk_mark),
ip_sock_rt_tos(sk),
ip_sock_rt_scope(sk),
inet_test_bit(HDRINCL, sk) ?
IPPROTO_RAW : sk->sk_protocol,
inet_sk_flowi_flags(sk),
daddr, inet->inet_saddr, 0, 0, sk->sk_uid);
rcu_read_unlock();
}
static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk,
const struct sk_buff *skb)
{
if (skb)
build_skb_flow_key(fl4, skb, sk);
else
build_sk_flow_key(fl4, sk);
}
static DEFINE_SPINLOCK(fnhe_lock);
static void fnhe_flush_routes(struct fib_nh_exception *fnhe)
{
struct rtable *rt;
rt = rcu_dereference(fnhe->fnhe_rth_input);
if (rt) {
RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL);
dst_dev_put(&rt->dst);
dst_release(&rt->dst);
}
rt = rcu_dereference(fnhe->fnhe_rth_output);
if (rt) {
RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL);
dst_dev_put(&rt->dst);
dst_release(&rt->dst);
}
}
static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash)
{
struct fib_nh_exception __rcu **fnhe_p, **oldest_p;
struct fib_nh_exception *fnhe, *oldest = NULL;
for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) {
fnhe = rcu_dereference_protected(*fnhe_p,
lockdep_is_held(&fnhe_lock));
if (!fnhe)
break;
if (!oldest ||
time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) {
oldest = fnhe;
oldest_p = fnhe_p;
}
}
fnhe_flush_routes(oldest);
*oldest_p = oldest->fnhe_next;
kfree_rcu(oldest, rcu);
}
static u32 fnhe_hashfun(__be32 daddr)
{
static siphash_aligned_key_t fnhe_hash_key;
u64 hval;
net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key));
hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key);
return hash_64(hval, FNHE_HASH_SHIFT);
}
static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
{
rt->rt_pmtu = fnhe->fnhe_pmtu;
rt->rt_mtu_locked = fnhe->fnhe_mtu_locked;
rt->dst.expires = fnhe->fnhe_expires;
if (fnhe->fnhe_gw) {
rt->rt_flags |= RTCF_REDIRECTED;
rt->rt_uses_gateway = 1;
rt->rt_gw_family = AF_INET;
rt->rt_gw4 = fnhe->fnhe_gw;
}
}
static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr,
__be32 gw, u32 pmtu, bool lock,
unsigned long expires)
{
struct fnhe_hash_bucket *hash;
struct fib_nh_exception *fnhe;
struct rtable *rt;
u32 genid, hval;
unsigned int i;
int depth;
genid = fnhe_genid(dev_net(nhc->nhc_dev));
hval = fnhe_hashfun(daddr);
spin_lock_bh(&fnhe_lock);
hash = rcu_dereference(nhc->nhc_exceptions);
if (!hash) {
hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC);
if (!hash)
goto out_unlock;
rcu_assign_pointer(nhc->nhc_exceptions, hash);
}
hash += hval;
depth = 0;
for (fnhe = rcu_dereference(hash->chain); fnhe;
fnhe = rcu_dereference(fnhe->fnhe_next)) {
if (fnhe->fnhe_daddr == daddr)
break;
depth++;
}
if (fnhe) {
if (fnhe->fnhe_genid != genid)
fnhe->fnhe_genid = genid;
if (gw)
fnhe->fnhe_gw = gw;
if (pmtu) {
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_mtu_locked = lock;
}
fnhe->fnhe_expires = max(1UL, expires);
/* Update all cached dsts too */
rt = rcu_dereference(fnhe->fnhe_rth_input);
if (rt)
fill_route_from_fnhe(rt, fnhe);
rt = rcu_dereference(fnhe->fnhe_rth_output);
if (rt)
fill_route_from_fnhe(rt, fnhe);
} else {
/* Randomize max depth to avoid some side channels attacks. */
int max_depth = FNHE_RECLAIM_DEPTH +
get_random_u32_below(FNHE_RECLAIM_DEPTH);
while (depth > max_depth) {
fnhe_remove_oldest(hash);
depth--;
}
fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC);
if (!fnhe)
goto out_unlock;
fnhe->fnhe_next = hash->chain;
fnhe->fnhe_genid = genid;
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_mtu_locked = lock;
fnhe->fnhe_expires = max(1UL, expires);
rcu_assign_pointer(hash->chain, fnhe);
/* Exception created; mark the cached routes for the nexthop
* stale, so anyone caching it rechecks if this exception
* applies to them.
*/
rt = rcu_dereference(nhc->nhc_rth_input);
if (rt)
rt->dst.obsolete = DST_OBSOLETE_KILL;
for_each_possible_cpu(i) {
struct rtable __rcu **prt;
prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i);
rt = rcu_dereference(*prt);
if (rt)
rt->dst.obsolete = DST_OBSOLETE_KILL;
}
}
fnhe->fnhe_stamp = jiffies;
out_unlock:
spin_unlock_bh(&fnhe_lock);
}
static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4,
bool kill_route)
{
__be32 new_gw = icmp_hdr(skb)->un.gateway;
__be32 old_gw = ip_hdr(skb)->saddr;
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct fib_result res;
struct neighbour *n;
struct net *net;
switch (icmp_hdr(skb)->code & 7) {
case ICMP_REDIR_NET:
case ICMP_REDIR_NETTOS:
case ICMP_REDIR_HOST:
case ICMP_REDIR_HOSTTOS:
break;
default:
return;
}
if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw)
return;
in_dev = __in_dev_get_rcu(dev);
if (!in_dev)
return;
net = dev_net(dev);
if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) ||
ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) ||
ipv4_is_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(net, new_gw) != RTN_UNICAST)
goto reject_redirect;
}
n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw);
if (!n)
n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev);
if (!IS_ERR(n)) {
if (!(READ_ONCE(n->nud_state) & NUD_VALID)) {
neigh_event_send(n, NULL);
} else {
if (fib_lookup(net, fl4, &res, 0) == 0) {
struct fib_nh_common *nhc;
fib_select_path(net, &res, fl4, skb);
nhc = FIB_RES_NHC(res);
update_or_create_fnhe(nhc, fl4->daddr, new_gw,
0, false,
jiffies + ip_rt_gc_timeout);
}
if (kill_route)
rt->dst.obsolete = DST_OBSOLETE_KILL;
call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
}
neigh_release(n);
}
return;
reject_redirect:
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev)) {
const struct iphdr *iph = (const struct iphdr *) skb->data;
__be32 daddr = iph->daddr;
__be32 saddr = iph->saddr;
net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n"
" Advised path = %pI4 -> %pI4\n",
&old_gw, dev->name, &new_gw,
&saddr, &daddr);
}
#endif
;
}
static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb)
{
struct rtable *rt;
struct flowi4 fl4;
const struct iphdr *iph = (const struct iphdr *) skb->data;
struct net *net = dev_net(skb->dev);
int oif = skb->dev->ifindex;
u8 prot = iph->protocol;
u32 mark = skb->mark;
__u8 tos = iph->tos;
rt = dst_rtable(dst);
__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
__ip_do_redirect(rt, skb, &fl4, true);
}
static void ipv4_negative_advice(struct sock *sk,
struct dst_entry *dst)
{
struct rtable *rt = dst_rtable(dst);
if ((dst->obsolete > 0) ||
(rt->rt_flags & RTCF_REDIRECTED) ||
rt->dst.expires)
sk_dst_reset(sk);
}
/*
* 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 = skb_rtable(skb);
struct in_device *in_dev;
struct inet_peer *peer;
struct net *net;
int log_martians;
int vif;
rcu_read_lock();
in_dev = __in_dev_get_rcu(rt->dst.dev);
if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
rcu_read_unlock();
return;
}
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
vif = l3mdev_master_ifindex_rcu(rt->dst.dev);
rcu_read_unlock();
net = dev_net(rt->dst.dev);
peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1);
if (!peer) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST,
rt_nexthop(rt, ip_hdr(skb)->daddr));
return;
}
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) {
peer->rate_tokens = 0;
peer->n_redirects = 0;
}
/* Too many ignored redirects; do not send anything
* set dst.rate_last to the last seen redirected packet.
*/
if (peer->n_redirects >= ip_rt_redirect_number) {
peer->rate_last = jiffies;
goto out_put_peer;
}
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
if (peer->n_redirects == 0 ||
time_after(jiffies,
(peer->rate_last +
(ip_rt_redirect_load << peer->n_redirects)))) {
__be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr);
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw);
peer->rate_last = jiffies;
++peer->n_redirects;
if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians &&
peer->n_redirects == ip_rt_redirect_number)
net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n",
&ip_hdr(skb)->saddr, inet_iif(skb),
&ip_hdr(skb)->daddr, &gw);
}
out_put_peer:
inet_putpeer(peer);
}
static int ip_error(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct net_device *dev = skb->dev;
struct in_device *in_dev;
struct inet_peer *peer;
unsigned long now;
struct net *net;
SKB_DR(reason);
bool send;
int code;
if (netif_is_l3_master(skb->dev)) {
dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
if (!dev)
goto out;
}
in_dev = __in_dev_get_rcu(dev);
/* IP on this device is disabled. */
if (!in_dev)
goto out;
net = dev_net(rt->dst.dev);
if (!IN_DEV_FORWARD(in_dev)) {
switch (rt->dst.error) {
case EHOSTUNREACH:
SKB_DR_SET(reason, IP_INADDRERRORS);
__IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS);
break;
case ENETUNREACH:
SKB_DR_SET(reason, IP_INNOROUTES);
__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
break;
}
goto out;
}
switch (rt->dst.error) {
case EINVAL:
default:
goto out;
case EHOSTUNREACH:
code = ICMP_HOST_UNREACH;
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
SKB_DR_SET(reason, IP_INNOROUTES);
__IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
break;
}
peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr,
l3mdev_master_ifindex(skb->dev), 1);
send = true;
if (peer) {
now = jiffies;
peer->rate_tokens += now - peer->rate_last;
if (peer->rate_tokens > ip_rt_error_burst)
peer->rate_tokens = ip_rt_error_burst;
peer->rate_last = now;
if (peer->rate_tokens >= ip_rt_error_cost)
peer->rate_tokens -= ip_rt_error_cost;
else
send = false;
inet_putpeer(peer);
}
if (send)
icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
out: kfree_skb_reason(skb, reason);
return 0;
}