forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
udp.c
1783 lines (1533 loc) · 45.4 KB
/
udp.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
/*
* UDP over IPv6
* Linux INET6 implementation
*
* Authors:
* Pedro Roque <[email protected]>
*
* Based on linux/ipv4/udp.c
*
* Fixes:
* Hideaki YOSHIFUJI : sin6_scope_id support
* YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which
* Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind
* a single port at the same time.
* Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data
* YOSHIFUJI Hideaki @USAGI: convert /proc/net/udp6 to seq_file.
*/
#include <linux/bpf-cgroup.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/uaccess.h>
#include <linux/indirect_call_wrapper.h>
#include <net/addrconf.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/raw.h>
#include <net/seg6.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/ip6_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/busy_poll.h>
#include <net/sock_reuseport.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <trace/events/skb.h>
#include "udp_impl.h"
static u32 udp6_ehashfn(const struct net *net,
const struct in6_addr *laddr,
const u16 lport,
const struct in6_addr *faddr,
const __be16 fport)
{
static u32 udp6_ehash_secret __read_mostly;
static u32 udp_ipv6_hash_secret __read_mostly;
u32 lhash, fhash;
net_get_random_once(&udp6_ehash_secret,
sizeof(udp6_ehash_secret));
net_get_random_once(&udp_ipv6_hash_secret,
sizeof(udp_ipv6_hash_secret));
lhash = (__force u32)laddr->s6_addr32[3];
fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);
return __inet6_ehashfn(lhash, lport, fhash, fport,
udp_ipv6_hash_secret + net_hash_mix(net));
}
int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
unsigned int hash2_partial =
ipv6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
return udp_lib_get_port(sk, snum, hash2_nulladdr);
}
void udp_v6_rehash(struct sock *sk)
{
u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
&sk->sk_v6_rcv_saddr,
inet_sk(sk)->inet_num);
udp_lib_rehash(sk, new_hash);
}
static int compute_score(struct sock *sk, struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned short hnum,
int dif, int sdif)
{
int bound_dev_if, score;
struct inet_sock *inet;
bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
sk->sk_family != PF_INET6)
return -1;
if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
return -1;
score = 0;
inet = inet_sk(sk);
if (inet->inet_dport) {
if (inet->inet_dport != sport)
return -1;
score++;
}
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
return -1;
score++;
}
bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
dev_match = udp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif);
if (!dev_match)
return -1;
if (bound_dev_if)
score++;
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
return score;
}
static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb,
const struct in6_addr *saddr,
__be16 sport,
const struct in6_addr *daddr,
unsigned int hnum)
{
struct sock *reuse_sk = NULL;
u32 hash;
if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
hash = udp6_ehashfn(net, daddr, hnum, saddr, sport);
reuse_sk = reuseport_select_sock(sk, hash, skb,
sizeof(struct udphdr));
}
return reuse_sk;
}
/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, unsigned int hnum,
int dif, int sdif, struct udp_hslot *hslot2,
struct sk_buff *skb)
{
struct sock *sk, *result;
int score, badness;
result = NULL;
badness = -1;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
/* Fall back to scoring if group has connections */
if (result && !reuseport_has_conns(sk, false))
return result;
result = result ? : sk;
badness = score;
}
}
return result;
}
static inline struct sock *udp6_lookup_run_bpf(struct net *net,
struct udp_table *udptable,
struct sk_buff *skb,
const struct in6_addr *saddr,
__be16 sport,
const struct in6_addr *daddr,
u16 hnum, const int dif)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
if (udptable != &udp_table)
return NULL; /* only UDP is supported */
no_reuseport = bpf_sk_lookup_run_v6(net, IPPROTO_UDP, saddr, sport,
daddr, hnum, dif, &sk);
if (no_reuseport || IS_ERR_OR_NULL(sk))
return sk;
reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
if (reuse_sk)
sk = reuse_sk;
return sk;
}
/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(struct net *net,
const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport,
int dif, int sdif, struct udp_table *udptable,
struct sk_buff *skb)
{
unsigned short hnum = ntohs(dport);
unsigned int hash2, slot2;
struct udp_hslot *hslot2;
struct sock *result, *sk;
hash2 = ipv6_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
/* Lookup connected or non-wildcard sockets */
result = udp6_lib_lookup2(net, saddr, sport,
daddr, hnum, dif, sdif,
hslot2, skb);
if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
goto done;
/* Lookup redirect from BPF */
if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
sk = udp6_lookup_run_bpf(net, udptable, skb,
saddr, sport, daddr, hnum, dif);
if (sk) {
result = sk;
goto done;
}
}
/* Got non-wildcard socket or error on first lookup */
if (result)
goto done;
/* Lookup wildcard sockets */
hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
result = udp6_lib_lookup2(net, saddr, sport,
&in6addr_any, hnum, dif, sdif,
hslot2, skb);
done:
if (IS_ERR(result))
return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__udp6_lib_lookup);
static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
inet6_sdif(skb), udptable, skb);
}
struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct ipv6hdr *iph = ipv6_hdr(skb);
return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
&iph->daddr, dport, inet6_iif(skb),
inet6_sdif(skb), &udp_table, NULL);
}
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
const struct in6_addr *daddr, __be16 dport, int dif)
{
struct sock *sk;
sk = __udp6_lib_lookup(net, saddr, sport, daddr, dport,
dif, 0, &udp_table, NULL);
if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
sk = NULL;
return sk;
}
EXPORT_SYMBOL_GPL(udp6_lib_lookup);
#endif
/* do not use the scratch area len for jumbogram: their length execeeds the
* scratch area space; note that the IP6CB flags is still in the first
* cacheline, so checking for jumbograms is cheap
*/
static int udp6_skb_len(struct sk_buff *skb)
{
return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb);
}
/*
* This should be easy, if there is something there we
* return it, otherwise we block.
*/
int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
int flags, int *addr_len)
{
struct ipv6_pinfo *np = inet6_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct sk_buff *skb;
unsigned int ulen, copied;
int off, err, peeking = flags & MSG_PEEK;
int is_udplite = IS_UDPLITE(sk);
struct udp_mib __percpu *mib;
bool checksum_valid = false;
int is_udp4;
if (flags & MSG_ERRQUEUE)
return ipv6_recv_error(sk, msg, len, addr_len);
if (np->rxpmtu && np->rxopt.bits.rxpmtu)
return ipv6_recv_rxpmtu(sk, msg, len, addr_len);
try_again:
off = sk_peek_offset(sk, flags);
skb = __skb_recv_udp(sk, flags, &off, &err);
if (!skb)
return err;
ulen = udp6_skb_len(skb);
copied = len;
if (copied > ulen - off)
copied = ulen - off;
else if (copied < ulen)
msg->msg_flags |= MSG_TRUNC;
is_udp4 = (skb->protocol == htons(ETH_P_IP));
mib = __UDPX_MIB(sk, is_udp4);
/*
* If checksum is needed at all, try to do it while copying the
* data. If the data is truncated, or if we only want a partial
* coverage checksum (UDP-Lite), do it before the copy.
*/
if (copied < ulen || peeking ||
(is_udplite && UDP_SKB_CB(skb)->partial_cov)) {
checksum_valid = udp_skb_csum_unnecessary(skb) ||
!__udp_lib_checksum_complete(skb);
if (!checksum_valid)
goto csum_copy_err;
}
if (checksum_valid || udp_skb_csum_unnecessary(skb)) {
if (udp_skb_is_linear(skb))
err = copy_linear_skb(skb, copied, off, &msg->msg_iter);
else
err = skb_copy_datagram_msg(skb, off, msg, copied);
} else {
err = skb_copy_and_csum_datagram_msg(skb, off, msg);
if (err == -EINVAL)
goto csum_copy_err;
}
if (unlikely(err)) {
if (!peeking) {
atomic_inc(&sk->sk_drops);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
return err;
}
if (!peeking)
SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);
sock_recv_cmsgs(msg, sk, skb);
/* Copy the address. */
if (msg->msg_name) {
DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
sin6->sin6_family = AF_INET6;
sin6->sin6_port = udp_hdr(skb)->source;
sin6->sin6_flowinfo = 0;
if (is_udp4) {
ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
&sin6->sin6_addr);
sin6->sin6_scope_id = 0;
} else {
sin6->sin6_addr = ipv6_hdr(skb)->saddr;
sin6->sin6_scope_id =
ipv6_iface_scope_id(&sin6->sin6_addr,
inet6_iif(skb));
}
*addr_len = sizeof(*sin6);
BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk,
(struct sockaddr *)sin6);
}
if (udp_sk(sk)->gro_enabled)
udp_cmsg_recv(msg, sk, skb);
if (np->rxopt.all)
ip6_datagram_recv_common_ctl(sk, msg, skb);
if (is_udp4) {
if (inet->cmsg_flags)
ip_cmsg_recv_offset(msg, sk, skb,
sizeof(struct udphdr), off);
} else {
if (np->rxopt.all)
ip6_datagram_recv_specific_ctl(sk, msg, skb);
}
err = copied;
if (flags & MSG_TRUNC)
err = ulen;
skb_consume_udp(sk, skb, peeking ? -err : err);
return err;
csum_copy_err:
if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
udp_skb_destructor)) {
SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
}
kfree_skb(skb);
/* starting over for a new packet, but check if we need to yield */
cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void)
{
static_branch_inc(&udpv6_encap_needed_key);
}
EXPORT_SYMBOL(udpv6_encap_enable);
/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
* through error handlers in encapsulations looking for a match.
*/
static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info)
{
int i;
for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info);
const struct ip6_tnl_encap_ops *encap;
encap = rcu_dereference(ip6tun_encaps[i]);
if (!encap)
continue;
handler = encap->err_handler;
if (handler && !handler(skb, opt, type, code, offset, info))
return 0;
}
return -ENOENT;
}
/* Try to match ICMP errors to UDP tunnels by looking up a socket without
* reversing source and destination port: this will match tunnels that force the
* same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
* lwtunnels might actually break this assumption by being configured with
* different destination ports on endpoints, in this case we won't be able to
* trace ICMP messages back to them.
*
* If this doesn't match any socket, probe tunnels with arbitrary destination
* ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
* we've sent packets to won't necessarily match the local destination port.
*
* Then ask the tunnel implementation to match the error against a valid
* association.
*
* Return an error if we can't find a match, the socket if we need further
* processing, zero otherwise.
*/
static struct sock *__udp6_lib_err_encap(struct net *net,
const struct ipv6hdr *hdr, int offset,
struct udphdr *uh,
struct udp_table *udptable,
struct sock *sk,
struct sk_buff *skb,
struct inet6_skb_parm *opt,
u8 type, u8 code, __be32 info)
{
int (*lookup)(struct sock *sk, struct sk_buff *skb);
int network_offset, transport_offset;
struct udp_sock *up;
network_offset = skb_network_offset(skb);
transport_offset = skb_transport_offset(skb);
/* Network header needs to point to the outer IPv6 header inside ICMP */
skb_reset_network_header(skb);
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, offset);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (lookup && lookup(sk, skb))
sk = NULL;
goto out;
}
sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
&hdr->saddr, uh->dest,
inet6_iif(skb), 0, udptable, skb);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (!lookup || lookup(sk, skb))
sk = NULL;
}
out:
if (!sk) {
sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
offset, info));
}
skb_set_transport_header(skb, transport_offset);
skb_set_network_header(skb, network_offset);
return sk;
}
int __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info,
struct udp_table *udptable)
{
struct ipv6_pinfo *np;
const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
const struct in6_addr *saddr = &hdr->saddr;
const struct in6_addr *daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr;
struct udphdr *uh = (struct udphdr *)(skb->data+offset);
bool tunnel = false;
struct sock *sk;
int harderr;
int err;
struct net *net = dev_net(skb->dev);
sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
inet6_iif(skb), inet6_sdif(skb), udptable, NULL);
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
if (static_branch_unlikely(&udpv6_encap_needed_key)) {
sk = __udp6_lib_err_encap(net, hdr, offset, uh,
udptable, sk, skb,
opt, type, code, info);
if (!sk)
return 0;
} else
sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
ICMP6_MIB_INERRORS);
return PTR_ERR(sk);
}
tunnel = true;
}
harderr = icmpv6_err_convert(type, code, &err);
np = inet6_sk(sk);
if (type == ICMPV6_PKT_TOOBIG) {
if (!ip6_sk_accept_pmtu(sk))
goto out;
ip6_sk_update_pmtu(skb, sk, info);
if (np->pmtudisc != IPV6_PMTUDISC_DONT)
harderr = 1;
}
if (type == NDISC_REDIRECT) {
if (tunnel) {
ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
sk->sk_mark, sk->sk_uid);
} else {
ip6_sk_redirect(skb, sk);
}
goto out;
}
/* Tunnels don't have an application socket: don't pass errors back */
if (tunnel)
goto out;
if (!np->recverr) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));
}
sk->sk_err = err;
sk_error_report(sk);
out:
return 0;
}
static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
int rc;
if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
sk_incoming_cpu_update(sk);
} else {
sk_mark_napi_id_once(sk, skb);
}
rc = __udp_enqueue_schedule_skb(sk, skb);
if (rc < 0) {
int is_udplite = IS_UDPLITE(sk);
/* Note that an ENOMEM error is charged twice */
if (rc == -ENOMEM)
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_RCVBUFERRORS, is_udplite);
else
UDP6_INC_STATS(sock_net(sk),
UDP_MIB_MEMERRORS, is_udplite);
UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
kfree_skb(skb);
return -1;
}
return 0;
}
static __inline__ int udpv6_err(struct sk_buff *skb,
struct inet6_skb_parm *opt, u8 type,
u8 code, int offset, __be32 info)
{
return __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table);
}
static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
struct udp_sock *up = udp_sk(sk);
int is_udplite = IS_UDPLITE(sk);
if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb))
goto drop;
if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) {
int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);
/*
* This is an encapsulation socket so pass the skb to
* the socket's udp_encap_rcv() hook. Otherwise, just
* fall through and pass this up the UDP socket.
* up->encap_rcv() returns the following value:
* =0 if skb was successfully passed to the encap
* handler or was discarded by it.
* >0 if skb should be passed on to UDP.
* <0 if skb should be resubmitted as proto -N
*/
/* if we're overly short, let UDP handle it */
encap_rcv = READ_ONCE(up->encap_rcv);
if (encap_rcv) {
int ret;
/* Verify checksum before giving to encap */
if (udp_lib_checksum_complete(skb))
goto csum_error;
ret = encap_rcv(sk, skb);
if (ret <= 0) {
__UDP6_INC_STATS(sock_net(sk),
UDP_MIB_INDATAGRAMS,
is_udplite);
return -ret;
}
}
/* FALLTHROUGH -- it's a UDP Packet */
}
/*
* UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c).
*/
if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) {
if (up->pcrlen == 0) { /* full coverage was set */
net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n",
UDP_SKB_CB(skb)->cscov, skb->len);
goto drop;
}
if (UDP_SKB_CB(skb)->cscov < up->pcrlen) {
net_dbg_ratelimited("UDPLITE6: coverage %d too small, need min %d\n",
UDP_SKB_CB(skb)->cscov, up->pcrlen);
goto drop;
}
}
prefetch(&sk->sk_rmem_alloc);
if (rcu_access_pointer(sk->sk_filter) &&
udp_lib_checksum_complete(skb))
goto csum_error;
if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr)))
goto drop;
udp_csum_pull_header(skb);
skb_dst_drop(skb);
return __udpv6_queue_rcv_skb(sk, skb);
csum_error:
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
drop:
__UDP6_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
atomic_inc(&sk->sk_drops);
kfree_skb(skb);
return -1;
}
static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
struct sk_buff *next, *segs;
int ret;
if (likely(!udp_unexpected_gso(sk, skb)))
return udpv6_queue_rcv_one_skb(sk, skb);
__skb_push(skb, -skb_mac_offset(skb));
segs = udp_rcv_segment(sk, skb, false);
skb_list_walk_safe(segs, skb, next) {
__skb_pull(skb, skb_transport_offset(skb));
udp_post_segment_fix_csum(skb);
ret = udpv6_queue_rcv_one_skb(sk, skb);
if (ret > 0)
ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
true);
}
return 0;
}
static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, const struct in6_addr *loc_addr,
__be16 rmt_port, const struct in6_addr *rmt_addr,
int dif, int sdif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net))
return false;
if (udp_sk(sk)->udp_port_hash != hnum ||
sk->sk_family != PF_INET6 ||
(inet->inet_dport && inet->inet_dport != rmt_port) ||
(!ipv6_addr_any(&sk->sk_v6_daddr) &&
!ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
!udp_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif) ||
(!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
return false;
if (!inet6_mc_check(sk, loc_addr, rmt_addr))
return false;
return true;
}
static void udp6_csum_zero_error(struct sk_buff *skb)
{
/* RFC 2460 section 8.1 says that we SHOULD log
* this error. Well, it is reasonable.
*/
net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
&ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
&ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
}
/*
* Note: called only from the BH handler context,
* so we don't need to lock the hashes.
*/
static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
const struct in6_addr *saddr, const struct in6_addr *daddr,
struct udp_table *udptable, int proto)
{
struct sock *sk, *first = NULL;
const struct udphdr *uh = udp_hdr(skb);
unsigned short hnum = ntohs(uh->dest);
struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum);
unsigned int offset = offsetof(typeof(*sk), sk_node);
unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10);
int dif = inet6_iif(skb);
int sdif = inet6_sdif(skb);
struct hlist_node *node;
struct sk_buff *nskb;
if (use_hash2) {
hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) &
udptable->mask;
hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
hslot = &udptable->hash2[hash2];
offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
}
sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
uh->source, saddr, dif, sdif,
hnum))
continue;
/* If zero checksum and no_check is not on for
* the socket then skip it.
*/
if (!uh->check && !udp_sk(sk)->no_check6_rx)
continue;
if (!first) {
first = sk;
continue;
}
nskb = skb_clone(skb, GFP_ATOMIC);
if (unlikely(!nskb)) {
atomic_inc(&sk->sk_drops);
__UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS,
IS_UDPLITE(sk));
__UDP6_INC_STATS(net, UDP_MIB_INERRORS,
IS_UDPLITE(sk));
continue;
}
if (udpv6_queue_rcv_skb(sk, nskb) > 0)
consume_skb(nskb);
}
/* Also lookup *:port if we are using hash2 and haven't done so yet. */
if (use_hash2 && hash2 != hash2_any) {
hash2 = hash2_any;
goto start_lookup;
}
if (first) {
if (udpv6_queue_rcv_skb(first, skb) > 0)
consume_skb(skb);
} else {
kfree_skb(skb);
__UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI,
proto == IPPROTO_UDPLITE);
}
return 0;
}
static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
{
if (udp_sk_rx_dst_set(sk, dst)) {
const struct rt6_info *rt = (const struct rt6_info *)dst;
sk->sk_rx_dst_cookie = rt6_get_cookie(rt);
}
}
/* wrapper for udp_queue_rcv_skb tacking care of csum conversion and
* return code conversion for ip layer consumption
*/
static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
struct udphdr *uh)
{
int ret;
if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk))
skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo);
ret = udpv6_queue_rcv_skb(sk, skb);
/* a return value > 0 means to resubmit the input */
if (ret > 0)
return ret;
return 0;
}
int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
int proto)
{
enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
const struct in6_addr *saddr, *daddr;
struct net *net = dev_net(skb->dev);
struct udphdr *uh;
struct sock *sk;
bool refcounted;
u32 ulen = 0;
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto discard;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
uh = udp_hdr(skb);
ulen = ntohs(uh->len);
if (ulen > skb->len)
goto short_packet;
if (proto == IPPROTO_UDP) {
/* UDP validates ulen. */
/* Check for jumbo payload */
if (ulen == 0)
ulen = skb->len;
if (ulen < sizeof(*uh))
goto short_packet;
if (ulen < skb->len) {
if (pskb_trim_rcsum(skb, ulen))
goto short_packet;
saddr = &ipv6_hdr(skb)->saddr;
daddr = &ipv6_hdr(skb)->daddr;
uh = udp_hdr(skb);
}
}
if (udp6_csum_init(skb, uh, proto))
goto csum_error;
/* Check if the socket is already available, e.g. due to early demux */
sk = skb_steal_sock(skb, &refcounted);
if (sk) {
struct dst_entry *dst = skb_dst(skb);
int ret;
if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp6_sk_rx_dst_set(sk, dst);
if (!uh->check && !udp_sk(sk)->no_check6_rx) {
if (refcounted)
sock_put(sk);
goto report_csum_error;
}
ret = udp6_unicast_rcv_skb(sk, skb, uh);
if (refcounted)
sock_put(sk);
return ret;
}
/*
* Multicast receive code
*/
if (ipv6_addr_is_multicast(daddr))
return __udp6_lib_mcast_deliver(net, skb,
saddr, daddr, udptable, proto);
/* Unicast */
sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest, udptable);
if (sk) {
if (!uh->check && !udp_sk(sk)->no_check6_rx)
goto report_csum_error;
return udp6_unicast_rcv_skb(sk, skb, uh);
}
reason = SKB_DROP_REASON_NO_SOCKET;
if (!uh->check)
goto report_csum_error;
if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
goto discard;