-
Notifications
You must be signed in to change notification settings - Fork 86
/
udp.c
3376 lines (2903 loc) · 84.4 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
/*
* 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.
*
* The User Datagram Protocol (UDP).
*
* Authors: Ross Biro
* Fred N. van Kempen, <[email protected]>
* Arnt Gulbrandsen, <[email protected]>
* Alan Cox, <[email protected]>
* Hirokazu Takahashi, <[email protected]>
*
* Fixes:
* Alan Cox : verify_area() calls
* Alan Cox : stopped close while in use off icmp
* messages. Not a fix but a botch that
* for udp at least is 'valid'.
* Alan Cox : Fixed icmp handling properly
* Alan Cox : Correct error for oversized datagrams
* Alan Cox : Tidied select() semantics.
* Alan Cox : udp_err() fixed properly, also now
* select and read wake correctly on errors
* Alan Cox : udp_send verify_area moved to avoid mem leak
* Alan Cox : UDP can count its memory
* Alan Cox : send to an unknown connection causes
* an ECONNREFUSED off the icmp, but
* does NOT close.
* Alan Cox : Switched to new sk_buff handlers. No more backlog!
* Alan Cox : Using generic datagram code. Even smaller and the PEEK
* bug no longer crashes it.
* Fred Van Kempen : Net2e support for sk->broadcast.
* Alan Cox : Uses skb_free_datagram
* Alan Cox : Added get/set sockopt support.
* Alan Cox : Broadcasting without option set returns EACCES.
* Alan Cox : No wakeup calls. Instead we now use the callbacks.
* Alan Cox : Use ip_tos and ip_ttl
* Alan Cox : SNMP Mibs
* Alan Cox : MSG_DONTROUTE, and 0.0.0.0 support.
* Matt Dillon : UDP length checks.
* Alan Cox : Smarter af_inet used properly.
* Alan Cox : Use new kernel side addressing.
* Alan Cox : Incorrect return on truncated datagram receive.
* Arnt Gulbrandsen : New udp_send and stuff
* Alan Cox : Cache last socket
* Alan Cox : Route cache
* Jon Peatfield : Minor efficiency fix to sendto().
* Mike Shaver : RFC1122 checks.
* Alan Cox : Nonblocking error fix.
* Willy Konynenberg : Transparent proxying support.
* Mike McLagan : Routing by source
* David S. Miller : New socket lookup architecture.
* Last socket cache retained as it
* does have a high hit rate.
* Olaf Kirch : Don't linearise iovec on sendmsg.
* Andi Kleen : Some cleanups, cache destination entry
* for connect.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Melvin Smith : Check msg_name not msg_namelen in sendto(),
* return ENOTCONN for unconnected sockets (POSIX)
* Janos Farkas : don't deliver multi/broadcasts to a different
* bound-to-device socket
* Hirokazu Takahashi : HW checksumming for outgoing UDP
* datagrams.
* Hirokazu Takahashi : sendfile() on UDP works now.
* Arnaldo C. Melo : convert /proc/net/udp to seq_file
* 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.
* Derek Atkins <[email protected]>: Add Encapulation Support
* James Chapman : Add L2TP encapsulation type.
*/
#define pr_fmt(fmt) "UDP: " fmt
#include <linux/uaccess.h>
#include <asm/ioctls.h>
#include <linux/memblock.h>
#include <linux/highmem.h>
#include <linux/swap.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
#include <linux/inetdevice.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/slab.h>
#include <net/tcp_states.h>
#include <linux/skbuff.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <net/net_namespace.h>
#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/ip_tunnels.h>
#include <net/route.h>
#include <net/checksum.h>
#include <net/xfrm.h>
#include <trace/events/udp.h>
#include <linux/static_key.h>
#include <linux/btf_ids.h>
#include <trace/events/skb.h>
#include <net/busy_poll.h>
#include "udp_impl.h"
#include <net/sock_reuseport.h>
#include <net/addrconf.h>
#include <net/udp_tunnel.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6_stubs.h>
#endif
struct udp_table udp_table __read_mostly;
EXPORT_SYMBOL(udp_table);
long sysctl_udp_mem[3] __read_mostly;
EXPORT_SYMBOL(sysctl_udp_mem);
atomic_long_t udp_memory_allocated;
EXPORT_SYMBOL(udp_memory_allocated);
#define MAX_UDP_PORTS 65536
#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN)
static int udp_lib_lport_inuse(struct net *net, __u16 num,
const struct udp_hslot *hslot,
unsigned long *bitmap,
struct sock *sk, unsigned int log)
{
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
sk_for_each(sk2, &hslot->head) {
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
(bitmap || udp_sk(sk2)->udp_port_hash == num) &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
inet_rcv_saddr_equal(sk, sk2, true)) {
if (sk2->sk_reuseport && sk->sk_reuseport &&
!rcu_access_pointer(sk->sk_reuseport_cb) &&
uid_eq(uid, sock_i_uid(sk2))) {
if (!bitmap)
return 0;
} else {
if (!bitmap)
return 1;
__set_bit(udp_sk(sk2)->udp_port_hash >> log,
bitmap);
}
}
}
return 0;
}
/*
* Note: we still hold spinlock of primary hash chain, so no other writer
* can insert/delete a socket with local_port == num
*/
static int udp_lib_lport_inuse2(struct net *net, __u16 num,
struct udp_hslot *hslot2,
struct sock *sk)
{
struct sock *sk2;
kuid_t uid = sock_i_uid(sk);
int res = 0;
spin_lock(&hslot2->lock);
udp_portaddr_for_each_entry(sk2, &hslot2->head) {
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
(udp_sk(sk2)->udp_port_hash == num) &&
(!sk2->sk_reuse || !sk->sk_reuse) &&
(!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
inet_rcv_saddr_equal(sk, sk2, true)) {
if (sk2->sk_reuseport && sk->sk_reuseport &&
!rcu_access_pointer(sk->sk_reuseport_cb) &&
uid_eq(uid, sock_i_uid(sk2))) {
res = 0;
} else {
res = 1;
}
break;
}
}
spin_unlock(&hslot2->lock);
return res;
}
static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
{
struct net *net = sock_net(sk);
kuid_t uid = sock_i_uid(sk);
struct sock *sk2;
sk_for_each(sk2, &hslot->head) {
if (net_eq(sock_net(sk2), net) &&
sk2 != sk &&
sk2->sk_family == sk->sk_family &&
ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
(udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) &&
(sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
inet_rcv_saddr_equal(sk, sk2, false)) {
return reuseport_add_sock(sk, sk2,
inet_rcv_saddr_any(sk));
}
}
return reuseport_alloc(sk, inet_rcv_saddr_any(sk));
}
/**
* udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6
*
* @sk: socket struct in question
* @snum: port number to look up
* @hash2_nulladdr: AF-dependent hash value in secondary hash chains,
* with NULL address
*/
int udp_lib_get_port(struct sock *sk, unsigned short snum,
unsigned int hash2_nulladdr)
{
struct udp_hslot *hslot, *hslot2;
struct udp_table *udptable = sk->sk_prot->h.udp_table;
int error = 1;
struct net *net = sock_net(sk);
if (!snum) {
int low, high, remaining;
unsigned int rand;
unsigned short first, last;
DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);
inet_get_local_port_range(net, &low, &high);
remaining = (high - low) + 1;
rand = prandom_u32();
first = reciprocal_scale(rand, remaining) + low;
/*
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
rand = (rand | 1) * (udptable->mask + 1);
last = first + udptable->mask + 1;
do {
hslot = udp_hashslot(udptable, net, first);
bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
udptable->log);
snum = first;
/*
* Iterate on all possible values of snum for this hash.
* Using steps of an odd multiple of UDP_HTABLE_SIZE
* give us randomization and full range coverage.
*/
do {
if (low <= snum && snum <= high &&
!test_bit(snum >> udptable->log, bitmap) &&
!inet_is_local_reserved_port(net, snum))
goto found;
snum += rand;
} while (snum != first);
spin_unlock_bh(&hslot->lock);
cond_resched();
} while (++first != last);
goto fail;
} else {
hslot = udp_hashslot(udptable, net, snum);
spin_lock_bh(&hslot->lock);
if (hslot->count > 10) {
int exist;
unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
slot2 &= udptable->mask;
hash2_nulladdr &= udptable->mask;
hslot2 = udp_hashslot2(udptable, slot2);
if (hslot->count < hslot2->count)
goto scan_primary_hash;
exist = udp_lib_lport_inuse2(net, snum, hslot2, sk);
if (!exist && (hash2_nulladdr != slot2)) {
hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
exist = udp_lib_lport_inuse2(net, snum, hslot2,
sk);
}
if (exist)
goto fail_unlock;
else
goto found;
}
scan_primary_hash:
if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0))
goto fail_unlock;
}
found:
inet_sk(sk)->inet_num = snum;
udp_sk(sk)->udp_port_hash = snum;
udp_sk(sk)->udp_portaddr_hash ^= snum;
if (sk_unhashed(sk)) {
if (sk->sk_reuseport &&
udp_reuseport_add_sock(sk, hslot)) {
inet_sk(sk)->inet_num = 0;
udp_sk(sk)->udp_port_hash = 0;
udp_sk(sk)->udp_portaddr_hash ^= snum;
goto fail_unlock;
}
sk_add_node_rcu(sk, &hslot->head);
hslot->count++;
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
spin_lock(&hslot2->lock);
if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
sk->sk_family == AF_INET6)
hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
&hslot2->head);
else
hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
&hslot2->head);
hslot2->count++;
spin_unlock(&hslot2->lock);
}
sock_set_flag(sk, SOCK_RCU_FREE);
error = 0;
fail_unlock:
spin_unlock_bh(&hslot->lock);
fail:
return error;
}
EXPORT_SYMBOL(udp_lib_get_port);
int udp_v4_get_port(struct sock *sk, unsigned short snum)
{
unsigned int hash2_nulladdr =
ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);
unsigned int hash2_partial =
ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);
/* precompute partial secondary hash */
udp_sk(sk)->udp_portaddr_hash = hash2_partial;
return udp_lib_get_port(sk, snum, hash2_nulladdr);
}
static int compute_score(struct sock *sk, struct net *net,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned short hnum,
int dif, int sdif)
{
int score;
struct inet_sock *inet;
bool dev_match;
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
ipv6_only_sock(sk))
return -1;
if (sk->sk_rcv_saddr != daddr)
return -1;
score = (sk->sk_family == PF_INET) ? 2 : 1;
inet = inet_sk(sk);
if (inet->inet_daddr) {
if (inet->inet_daddr != saddr)
return -1;
score += 4;
}
if (inet->inet_dport) {
if (inet->inet_dport != sport)
return -1;
score += 4;
}
dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
dif, sdif);
if (!dev_match)
return -1;
if (sk->sk_bound_dev_if)
score += 4;
if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())
score++;
return score;
}
static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
const __u16 lport, const __be32 faddr,
const __be16 fport)
{
static u32 udp_ehash_secret __read_mostly;
net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret));
return __inet_ehashfn(laddr, lport, faddr, fport,
udp_ehash_secret + net_hash_mix(net));
}
static struct sock *lookup_reuseport(struct net *net, struct sock *sk,
struct sk_buff *skb,
__be32 saddr, __be16 sport,
__be32 daddr, unsigned short hnum)
{
struct sock *reuse_sk = NULL;
u32 hash;
if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) {
hash = udp_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 *udp4_lib_lookup2(struct net *net,
__be32 saddr, __be16 sport,
__be32 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 = 0;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
score = compute_score(sk, net, saddr, sport,
daddr, hnum, dif, sdif);
if (score > badness) {
badness = score;
result = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum);
if (!result) {
result = sk;
continue;
}
/* Fall back to scoring if group has connections */
if (!reuseport_has_conns(sk))
return result;
/* Reuseport logic returned an error, keep original score. */
if (IS_ERR(result))
continue;
badness = compute_score(result, net, saddr, sport,
daddr, hnum, dif, sdif);
}
}
return result;
}
static struct sock *udp4_lookup_run_bpf(struct net *net,
struct udp_table *udptable,
struct sk_buff *skb,
__be32 saddr, __be16 sport,
__be32 daddr, u16 hnum)
{
struct sock *sk, *reuse_sk;
bool no_reuseport;
if (udptable != &udp_table)
return NULL; /* only UDP is supported */
no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP,
saddr, sport, daddr, hnum, &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;
}
/* UDP is nearly always wildcards out the wazoo, it makes no sense to try
* harder than this. -DaveM
*/
struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
__be16 sport, __be32 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 = ipv4_portaddr_hash(net, daddr, hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
/* Lookup connected or non-wildcard socket */
result = udp4_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 = udp4_lookup_run_bpf(net, udptable, skb,
saddr, sport, daddr, hnum);
if (sk) {
result = sk;
goto done;
}
}
/* Got non-wildcard socket or error on first lookup */
if (result)
goto done;
/* Lookup wildcard sockets */
hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
slot2 = hash2 & udptable->mask;
hslot2 = &udptable->hash2[slot2];
result = udp4_lib_lookup2(net, saddr, sport,
htonl(INADDR_ANY), hnum, dif, sdif,
hslot2, skb);
done:
if (IS_ERR(result))
return NULL;
return result;
}
EXPORT_SYMBOL_GPL(__udp4_lib_lookup);
static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
__be16 sport, __be16 dport,
struct udp_table *udptable)
{
const struct iphdr *iph = ip_hdr(skb);
return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
inet_sdif(skb), udptable, skb);
}
struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
__be16 sport, __be16 dport)
{
const struct iphdr *iph = ip_hdr(skb);
return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
iph->daddr, dport, inet_iif(skb),
inet_sdif(skb), &udp_table, NULL);
}
/* Must be called under rcu_read_lock().
* Does increment socket refcount.
*/
#if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4)
struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
__be32 daddr, __be16 dport, int dif)
{
struct sock *sk;
sk = __udp4_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(udp4_lib_lookup);
#endif
static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
__be16 loc_port, __be32 loc_addr,
__be16 rmt_port, __be32 rmt_addr,
int dif, int sdif, unsigned short hnum)
{
struct inet_sock *inet = inet_sk(sk);
if (!net_eq(sock_net(sk), net) ||
udp_sk(sk)->udp_port_hash != hnum ||
(inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
(inet->inet_dport != rmt_port && inet->inet_dport) ||
(inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
ipv6_only_sock(sk) ||
!udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))
return false;
if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif))
return false;
return true;
}
DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
void udp_encap_enable(void)
{
static_branch_inc(&udp_encap_needed_key);
}
EXPORT_SYMBOL(udp_encap_enable);
void udp_encap_disable(void)
{
static_branch_dec(&udp_encap_needed_key);
}
EXPORT_SYMBOL(udp_encap_disable);
/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
* through error handlers in encapsulations looking for a match.
*/
static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
{
int i;
for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
int (*handler)(struct sk_buff *skb, u32 info);
const struct ip_tunnel_encap_ops *encap;
encap = rcu_dereference(iptun_encaps[i]);
if (!encap)
continue;
handler = encap->err_handler;
if (handler && !handler(skb, 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 *__udp4_lib_err_encap(struct net *net,
const struct iphdr *iph,
struct udphdr *uh,
struct udp_table *udptable,
struct sock *sk,
struct sk_buff *skb, u32 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 IPv4 header inside ICMP */
skb_reset_network_header(skb);
/* Transport header needs to point to the UDP header */
skb_set_transport_header(skb, iph->ihl << 2);
if (sk) {
up = udp_sk(sk);
lookup = READ_ONCE(up->encap_err_lookup);
if (lookup && lookup(sk, skb))
sk = NULL;
goto out;
}
sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
iph->saddr, uh->dest, skb->dev->ifindex, 0,
udptable, NULL);
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(__udp4_lib_err_encap_no_sk(skb, info));
skb_set_transport_header(skb, transport_offset);
skb_set_network_header(skb, network_offset);
return sk;
}
/*
* This routine is called by the ICMP module when it gets some
* sort of error condition. If err < 0 then the socket should
* be closed and the error returned to the user. If err > 0
* it's just the icmp type << 8 | icmp code.
* Header points to the ip header of the error packet. We move
* on past this. Then (as it used to claim before adjustment)
* header points to the first 8 bytes of the udp header. We need
* to find the appropriate port.
*/
int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
{
struct inet_sock *inet;
const struct iphdr *iph = (const struct iphdr *)skb->data;
struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
bool tunnel = false;
struct sock *sk;
int harderr;
int err;
struct net *net = dev_net(skb->dev);
sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
iph->saddr, uh->source, skb->dev->ifindex,
inet_sdif(skb), udptable, NULL);
if (!sk || udp_sk(sk)->encap_type) {
/* No socket for error: try tunnels before discarding */
if (static_branch_unlikely(&udp_encap_needed_key)) {
sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb,
info);
if (!sk)
return 0;
} else
sk = ERR_PTR(-ENOENT);
if (IS_ERR(sk)) {
__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
return PTR_ERR(sk);
}
tunnel = true;
}
err = 0;
harderr = 0;
inet = inet_sk(sk);
switch (type) {
default:
case ICMP_TIME_EXCEEDED:
err = EHOSTUNREACH;
break;
case ICMP_SOURCE_QUENCH:
goto out;
case ICMP_PARAMETERPROB:
err = EPROTO;
harderr = 1;
break;
case ICMP_DEST_UNREACH:
if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
ipv4_sk_update_pmtu(skb, sk, info);
if (inet->pmtudisc != IP_PMTUDISC_DONT) {
err = EMSGSIZE;
harderr = 1;
break;
}
goto out;
}
err = EHOSTUNREACH;
if (code <= NR_ICMP_UNREACH) {
harderr = icmp_err_convert[code].fatal;
err = icmp_err_convert[code].errno;
}
break;
case ICMP_REDIRECT:
ipv4_sk_redirect(skb, sk);
goto out;
}
/*
* RFC1122: OK. Passes ICMP errors back to application, as per
* 4.1.3.3.
*/
if (tunnel) {
/* ...not for tunnels though: we don't have a sending socket */
if (udp_sk(sk)->encap_err_rcv)
udp_sk(sk)->encap_err_rcv(sk, skb, iph->ihl << 2);
goto out;
}
if (!inet->recverr) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else
ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1));
sk->sk_err = err;
sk_error_report(sk);
out:
return 0;
}
int udp_err(struct sk_buff *skb, u32 info)
{
return __udp4_lib_err(skb, info, &udp_table);
}
/*
* Throw away all pending data and cancel the corking. Socket is locked.
*/
void udp_flush_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
if (up->pending) {
up->len = 0;
up->pending = 0;
ip_flush_pending_frames(sk);
}
}
EXPORT_SYMBOL(udp_flush_pending_frames);
/**
* udp4_hwcsum - handle outgoing HW checksumming
* @skb: sk_buff containing the filled-in UDP header
* (checksum field must be zeroed out)
* @src: source IP address
* @dst: destination IP address
*/
void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
{
struct udphdr *uh = udp_hdr(skb);
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
int hlen = len;
__wsum csum = 0;
if (!skb_has_frag_list(skb)) {
/*
* Only one fragment on the socket.
*/
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
uh->check = ~csum_tcpudp_magic(src, dst, len,
IPPROTO_UDP, 0);
} else {
struct sk_buff *frags;
/*
* HW-checksum won't work as there are two or more
* fragments on the socket so that all csums of sk_buffs
* should be together
*/
skb_walk_frags(skb, frags) {
csum = csum_add(csum, frags->csum);
hlen -= frags->len;
}
csum = skb_checksum(skb, offset, hlen, csum);
skb->ip_summed = CHECKSUM_NONE;
uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
}
}
EXPORT_SYMBOL_GPL(udp4_hwcsum);
/* Function to set UDP checksum for an IPv4 UDP packet. This is intended
* for the simple case like when setting the checksum for a UDP tunnel.
*/
void udp_set_csum(bool nocheck, struct sk_buff *skb,
__be32 saddr, __be32 daddr, int len)
{
struct udphdr *uh = udp_hdr(skb);
if (nocheck) {
uh->check = 0;
} else if (skb_is_gso(skb)) {
uh->check = ~udp_v4_check(len, saddr, daddr, 0);
} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
uh->check = 0;
uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb));
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
} else {
skb->ip_summed = CHECKSUM_PARTIAL;
skb->csum_start = skb_transport_header(skb) - skb->head;
skb->csum_offset = offsetof(struct udphdr, check);
uh->check = ~udp_v4_check(len, saddr, daddr, 0);
}
}
EXPORT_SYMBOL(udp_set_csum);
static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
struct inet_cork *cork)
{
struct sock *sk = skb->sk;
struct inet_sock *inet = inet_sk(sk);
struct udphdr *uh;
int err;
int is_udplite = IS_UDPLITE(sk);
int offset = skb_transport_offset(skb);
int len = skb->len - offset;
int datalen = len - sizeof(*uh);
__wsum csum = 0;
/*
* Create a UDP header
*/
uh = udp_hdr(skb);
uh->source = inet->inet_sport;
uh->dest = fl4->fl4_dport;
uh->len = htons(len);
uh->check = 0;
if (cork->gso_size) {
const int hlen = skb_network_header_len(skb) +
sizeof(struct udphdr);
if (hlen + cork->gso_size > cork->fragsize) {
kfree_skb(skb);
return -EINVAL;
}
if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
kfree_skb(skb);
return -EINVAL;
}
if (sk->sk_no_check_tx) {
kfree_skb(skb);
return -EINVAL;
}
if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||
dst_xfrm(skb_dst(skb))) {
kfree_skb(skb);
return -EIO;
}
if (datalen > cork->gso_size) {
skb_shinfo(skb)->gso_size = cork->gso_size;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
cork->gso_size);
}
goto csum_partial;
}
if (is_udplite) /* UDP-Lite */
csum = udplite_csum(skb);
else if (sk->sk_no_check_tx) { /* UDP csum off */
skb->ip_summed = CHECKSUM_NONE;
goto send;
} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
csum_partial:
udp4_hwcsum(skb, fl4->saddr, fl4->daddr);
goto send;
} else
csum = udp_csum(skb);
/* add protocol-dependent pseudo-header */
uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len,
sk->sk_protocol, csum);
if (uh->check == 0)
uh->check = CSUM_MANGLED_0;
send:
err = ip_send_skb(sock_net(sk), skb);
if (err) {
if (err == -ENOBUFS && !inet->recverr) {
UDP_INC_STATS(sock_net(sk),
UDP_MIB_SNDBUFERRORS, is_udplite);
err = 0;
}
} else
UDP_INC_STATS(sock_net(sk),
UDP_MIB_OUTDATAGRAMS, is_udplite);
return err;
}
/*
* Push out all pending data as one UDP datagram. Socket is locked.
*/
int udp_push_pending_frames(struct sock *sk)
{
struct udp_sock *up = udp_sk(sk);
struct inet_sock *inet = inet_sk(sk);
struct flowi4 *fl4 = &inet->cork.fl.u.ip4;
struct sk_buff *skb;