forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
proto.c
1293 lines (1077 loc) · 30.6 KB
/
proto.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-only
/*
* net/dccp/proto.c
*
* An implementation of the DCCP protocol
* Arnaldo Carvalho de Melo <[email protected]>
*/
#include <linux/dccp.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/if_arp.h>
#include <linux/init.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <net/checksum.h>
#include <net/inet_sock.h>
#include <net/inet_common.h>
#include <net/sock.h>
#include <net/xfrm.h>
#include <asm/ioctls.h>
#include <linux/spinlock.h>
#include <linux/timer.h>
#include <linux/delay.h>
#include <linux/poll.h>
#include "ccid.h"
#include "dccp.h"
#include "feat.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
EXPORT_SYMBOL_GPL(dccp_statistics);
DEFINE_PER_CPU(unsigned int, dccp_orphan_count);
EXPORT_PER_CPU_SYMBOL_GPL(dccp_orphan_count);
struct inet_hashinfo dccp_hashinfo;
EXPORT_SYMBOL_GPL(dccp_hashinfo);
/* the maximum queue length for tx in packets. 0 is no limit */
int sysctl_dccp_tx_qlen __read_mostly = 5;
#ifdef CONFIG_IP_DCCP_DEBUG
static const char *dccp_state_name(const int state)
{
static const char *const dccp_state_names[] = {
[DCCP_OPEN] = "OPEN",
[DCCP_REQUESTING] = "REQUESTING",
[DCCP_PARTOPEN] = "PARTOPEN",
[DCCP_LISTEN] = "LISTEN",
[DCCP_RESPOND] = "RESPOND",
[DCCP_CLOSING] = "CLOSING",
[DCCP_ACTIVE_CLOSEREQ] = "CLOSEREQ",
[DCCP_PASSIVE_CLOSE] = "PASSIVE_CLOSE",
[DCCP_PASSIVE_CLOSEREQ] = "PASSIVE_CLOSEREQ",
[DCCP_TIME_WAIT] = "TIME_WAIT",
[DCCP_CLOSED] = "CLOSED",
};
if (state >= DCCP_MAX_STATES)
return "INVALID STATE!";
else
return dccp_state_names[state];
}
#endif
void dccp_set_state(struct sock *sk, const int state)
{
const int oldstate = sk->sk_state;
dccp_pr_debug("%s(%p) %s --> %s\n", dccp_role(sk), sk,
dccp_state_name(oldstate), dccp_state_name(state));
WARN_ON(state == oldstate);
switch (state) {
case DCCP_OPEN:
if (oldstate != DCCP_OPEN)
DCCP_INC_STATS(DCCP_MIB_CURRESTAB);
/* Client retransmits all Confirm options until entering OPEN */
if (oldstate == DCCP_PARTOPEN)
dccp_feat_list_purge(&dccp_sk(sk)->dccps_featneg);
break;
case DCCP_CLOSED:
if (oldstate == DCCP_OPEN || oldstate == DCCP_ACTIVE_CLOSEREQ ||
oldstate == DCCP_CLOSING)
DCCP_INC_STATS(DCCP_MIB_ESTABRESETS);
sk->sk_prot->unhash(sk);
if (inet_csk(sk)->icsk_bind_hash != NULL &&
!(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
inet_put_port(sk);
fallthrough;
default:
if (oldstate == DCCP_OPEN)
DCCP_DEC_STATS(DCCP_MIB_CURRESTAB);
}
/* Change state AFTER socket is unhashed to avoid closed
* socket sitting in hash tables.
*/
inet_sk_set_state(sk, state);
}
EXPORT_SYMBOL_GPL(dccp_set_state);
static void dccp_finish_passive_close(struct sock *sk)
{
switch (sk->sk_state) {
case DCCP_PASSIVE_CLOSE:
/* Node (client or server) has received Close packet. */
dccp_send_reset(sk, DCCP_RESET_CODE_CLOSED);
dccp_set_state(sk, DCCP_CLOSED);
break;
case DCCP_PASSIVE_CLOSEREQ:
/*
* Client received CloseReq. We set the `active' flag so that
* dccp_send_close() retransmits the Close as per RFC 4340, 8.3.
*/
dccp_send_close(sk, 1);
dccp_set_state(sk, DCCP_CLOSING);
}
}
void dccp_done(struct sock *sk)
{
dccp_set_state(sk, DCCP_CLOSED);
dccp_clear_xmit_timers(sk);
sk->sk_shutdown = SHUTDOWN_MASK;
if (!sock_flag(sk, SOCK_DEAD))
sk->sk_state_change(sk);
else
inet_csk_destroy_sock(sk);
}
EXPORT_SYMBOL_GPL(dccp_done);
const char *dccp_packet_name(const int type)
{
static const char *const dccp_packet_names[] = {
[DCCP_PKT_REQUEST] = "REQUEST",
[DCCP_PKT_RESPONSE] = "RESPONSE",
[DCCP_PKT_DATA] = "DATA",
[DCCP_PKT_ACK] = "ACK",
[DCCP_PKT_DATAACK] = "DATAACK",
[DCCP_PKT_CLOSEREQ] = "CLOSEREQ",
[DCCP_PKT_CLOSE] = "CLOSE",
[DCCP_PKT_RESET] = "RESET",
[DCCP_PKT_SYNC] = "SYNC",
[DCCP_PKT_SYNCACK] = "SYNCACK",
};
if (type >= DCCP_NR_PKT_TYPES)
return "INVALID";
else
return dccp_packet_names[type];
}
EXPORT_SYMBOL_GPL(dccp_packet_name);
void dccp_destruct_common(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk);
dp->dccps_hc_tx_ccid = NULL;
}
EXPORT_SYMBOL_GPL(dccp_destruct_common);
static void dccp_sk_destruct(struct sock *sk)
{
dccp_destruct_common(sk);
inet_sock_destruct(sk);
}
int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
{
struct dccp_sock *dp = dccp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
pr_warn_once("DCCP is deprecated and scheduled to be removed in 2025, "
"please contact the netdev mailing list\n");
icsk->icsk_rto = DCCP_TIMEOUT_INIT;
icsk->icsk_syn_retries = sysctl_dccp_request_retries;
sk->sk_state = DCCP_CLOSED;
sk->sk_write_space = dccp_write_space;
sk->sk_destruct = dccp_sk_destruct;
icsk->icsk_sync_mss = dccp_sync_mss;
dp->dccps_mss_cache = 536;
dp->dccps_rate_last = jiffies;
dp->dccps_role = DCCP_ROLE_UNDEFINED;
dp->dccps_service = DCCP_SERVICE_CODE_IS_ABSENT;
dp->dccps_tx_qlen = sysctl_dccp_tx_qlen;
dccp_init_xmit_timers(sk);
INIT_LIST_HEAD(&dp->dccps_featneg);
/* control socket doesn't need feat nego */
if (likely(ctl_sock_initialized))
return dccp_feat_init(sk);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_init_sock);
void dccp_destroy_sock(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
__skb_queue_purge(&sk->sk_write_queue);
if (sk->sk_send_head != NULL) {
kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
}
/* Clean up a referenced DCCP bind bucket. */
if (inet_csk(sk)->icsk_bind_hash != NULL)
inet_put_port(sk);
kfree(dp->dccps_service_list);
dp->dccps_service_list = NULL;
if (dp->dccps_hc_rx_ackvec != NULL) {
dccp_ackvec_free(dp->dccps_hc_rx_ackvec);
dp->dccps_hc_rx_ackvec = NULL;
}
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
dp->dccps_hc_rx_ccid = NULL;
/* clean up feature negotiation state */
dccp_feat_list_purge(&dp->dccps_featneg);
}
EXPORT_SYMBOL_GPL(dccp_destroy_sock);
static inline int dccp_need_reset(int state)
{
return state != DCCP_CLOSED && state != DCCP_LISTEN &&
state != DCCP_REQUESTING;
}
int dccp_disconnect(struct sock *sk, int flags)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct inet_sock *inet = inet_sk(sk);
struct dccp_sock *dp = dccp_sk(sk);
const int old_state = sk->sk_state;
if (old_state != DCCP_CLOSED)
dccp_set_state(sk, DCCP_CLOSED);
/*
* This corresponds to the ABORT function of RFC793, sec. 3.8
* TCP uses a RST segment, DCCP a Reset packet with Code 2, "Aborted".
*/
if (old_state == DCCP_LISTEN) {
inet_csk_listen_stop(sk);
} else if (dccp_need_reset(old_state)) {
dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
sk->sk_err = ECONNRESET;
} else if (old_state == DCCP_REQUESTING)
sk->sk_err = ECONNRESET;
dccp_clear_xmit_timers(sk);
ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk);
dp->dccps_hc_rx_ccid = NULL;
__skb_queue_purge(&sk->sk_receive_queue);
__skb_queue_purge(&sk->sk_write_queue);
if (sk->sk_send_head != NULL) {
__kfree_skb(sk->sk_send_head);
sk->sk_send_head = NULL;
}
inet->inet_dport = 0;
inet_bhash2_reset_saddr(sk);
sk->sk_shutdown = 0;
sock_reset_flag(sk, SOCK_DONE);
icsk->icsk_backoff = 0;
inet_csk_delack_init(sk);
__sk_dst_reset(sk);
WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);
sk_error_report(sk);
return 0;
}
EXPORT_SYMBOL_GPL(dccp_disconnect);
/*
* Wait for a DCCP event.
*
* Note that we don't need to lock the socket, as the upper poll layers
* take care of normal races (between the test and the event) and we don't
* go look at any of the socket buffers directly.
*/
__poll_t dccp_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
struct sock *sk = sock->sk;
__poll_t mask;
u8 shutdown;
int state;
sock_poll_wait(file, sock, wait);
state = inet_sk_state_load(sk);
if (state == DCCP_LISTEN)
return inet_csk_listen_poll(sk);
/* Socket is not locked. We are protected from async events
by poll logic and correct handling of state changes
made by another threads is impossible in any case.
*/
mask = 0;
if (READ_ONCE(sk->sk_err))
mask = EPOLLERR;
shutdown = READ_ONCE(sk->sk_shutdown);
if (shutdown == SHUTDOWN_MASK || state == DCCP_CLOSED)
mask |= EPOLLHUP;
if (shutdown & RCV_SHUTDOWN)
mask |= EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
/* Connected? */
if ((1 << state) & ~(DCCPF_REQUESTING | DCCPF_RESPOND)) {
if (atomic_read(&sk->sk_rmem_alloc) > 0)
mask |= EPOLLIN | EPOLLRDNORM;
if (!(shutdown & SEND_SHUTDOWN)) {
if (sk_stream_is_writeable(sk)) {
mask |= EPOLLOUT | EPOLLWRNORM;
} else { /* send SIGIO later */
sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk);
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
/* Race breaker. If space is freed after
* wspace test but before the flags are set,
* IO signal will be lost.
*/
if (sk_stream_is_writeable(sk))
mask |= EPOLLOUT | EPOLLWRNORM;
}
}
}
return mask;
}
EXPORT_SYMBOL_GPL(dccp_poll);
int dccp_ioctl(struct sock *sk, int cmd, int *karg)
{
int rc = -ENOTCONN;
lock_sock(sk);
if (sk->sk_state == DCCP_LISTEN)
goto out;
switch (cmd) {
case SIOCOUTQ: {
*karg = sk_wmem_alloc_get(sk);
/* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and
* always 0, comparably to UDP.
*/
rc = 0;
}
break;
case SIOCINQ: {
struct sk_buff *skb;
*karg = 0;
skb = skb_peek(&sk->sk_receive_queue);
if (skb != NULL) {
/*
* We will only return the amount of this packet since
* that is all that will be read.
*/
*karg = skb->len;
}
rc = 0;
}
break;
default:
rc = -ENOIOCTLCMD;
break;
}
out:
release_sock(sk);
return rc;
}
EXPORT_SYMBOL_GPL(dccp_ioctl);
static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
sockptr_t optval, unsigned int optlen)
{
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_service_list *sl = NULL;
if (service == DCCP_SERVICE_INVALID_VALUE ||
optlen > DCCP_SERVICE_LIST_MAX_LEN * sizeof(u32))
return -EINVAL;
if (optlen > sizeof(service)) {
sl = kmalloc(optlen, GFP_KERNEL);
if (sl == NULL)
return -ENOMEM;
sl->dccpsl_nr = optlen / sizeof(u32) - 1;
if (copy_from_sockptr_offset(sl->dccpsl_list, optval,
sizeof(service), optlen - sizeof(service)) ||
dccp_list_has_service(sl, DCCP_SERVICE_INVALID_VALUE)) {
kfree(sl);
return -EFAULT;
}
}
lock_sock(sk);
dp->dccps_service = service;
kfree(dp->dccps_service_list);
dp->dccps_service_list = sl;
release_sock(sk);
return 0;
}
static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
{
u8 *list, len;
int i, rc;
if (cscov < 0 || cscov > 15)
return -EINVAL;
/*
* Populate a list of permissible values, in the range cscov...15. This
* is necessary since feature negotiation of single values only works if
* both sides incidentally choose the same value. Since the list starts
* lowest-value first, negotiation will pick the smallest shared value.
*/
if (cscov == 0)
return 0;
len = 16 - cscov;
list = kmalloc(len, GFP_KERNEL);
if (list == NULL)
return -ENOBUFS;
for (i = 0; i < len; i++)
list[i] = cscov++;
rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len);
if (rc == 0) {
if (rx)
dccp_sk(sk)->dccps_pcrlen = cscov;
else
dccp_sk(sk)->dccps_pcslen = cscov;
}
kfree(list);
return rc;
}
static int dccp_setsockopt_ccid(struct sock *sk, int type,
sockptr_t optval, unsigned int optlen)
{
u8 *val;
int rc = 0;
if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
return -EINVAL;
val = memdup_sockptr(optval, optlen);
if (IS_ERR(val))
return PTR_ERR(val);
lock_sock(sk);
if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID)
rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen);
if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID))
rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen);
release_sock(sk);
kfree(val);
return rc;
}
static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
sockptr_t optval, unsigned int optlen)
{
struct dccp_sock *dp = dccp_sk(sk);
int val, err = 0;
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_CHANGE_L:
case DCCP_SOCKOPT_CHANGE_R:
DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_CCID:
case DCCP_SOCKOPT_RX_CCID:
case DCCP_SOCKOPT_TX_CCID:
return dccp_setsockopt_ccid(sk, optname, optval, optlen);
}
if (optlen < (int)sizeof(int))
return -EINVAL;
if (copy_from_sockptr(&val, optval, sizeof(int)))
return -EFAULT;
if (optname == DCCP_SOCKOPT_SERVICE)
return dccp_setsockopt_service(sk, val, optval, optlen);
lock_sock(sk);
switch (optname) {
case DCCP_SOCKOPT_SERVER_TIMEWAIT:
if (dp->dccps_role != DCCP_ROLE_SERVER)
err = -EOPNOTSUPP;
else
dp->dccps_server_timewait = (val != 0);
break;
case DCCP_SOCKOPT_SEND_CSCOV:
err = dccp_setsockopt_cscov(sk, val, false);
break;
case DCCP_SOCKOPT_RECV_CSCOV:
err = dccp_setsockopt_cscov(sk, val, true);
break;
case DCCP_SOCKOPT_QPOLICY_ID:
if (sk->sk_state != DCCP_CLOSED)
err = -EISCONN;
else if (val < 0 || val >= DCCPQ_POLICY_MAX)
err = -EINVAL;
else
dp->dccps_qpolicy = val;
break;
case DCCP_SOCKOPT_QPOLICY_TXQLEN:
if (val < 0)
err = -EINVAL;
else
dp->dccps_tx_qlen = val;
break;
default:
err = -ENOPROTOOPT;
break;
}
release_sock(sk);
return err;
}
int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
unsigned int optlen)
{
if (level != SOL_DCCP)
return inet_csk(sk)->icsk_af_ops->setsockopt(sk, level,
optname, optval,
optlen);
return do_dccp_setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL_GPL(dccp_setsockopt);
static int dccp_getsockopt_service(struct sock *sk, int len,
__be32 __user *optval,
int __user *optlen)
{
const struct dccp_sock *dp = dccp_sk(sk);
const struct dccp_service_list *sl;
int err = -ENOENT, slen = 0, total_len = sizeof(u32);
lock_sock(sk);
if ((sl = dp->dccps_service_list) != NULL) {
slen = sl->dccpsl_nr * sizeof(u32);
total_len += slen;
}
err = -EINVAL;
if (total_len > len)
goto out;
err = 0;
if (put_user(total_len, optlen) ||
put_user(dp->dccps_service, optval) ||
(sl != NULL && copy_to_user(optval + 1, sl->dccpsl_list, slen)))
err = -EFAULT;
out:
release_sock(sk);
return err;
}
static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
struct dccp_sock *dp;
int val, len;
if (get_user(len, optlen))
return -EFAULT;
if (len < (int)sizeof(int))
return -EINVAL;
dp = dccp_sk(sk);
switch (optname) {
case DCCP_SOCKOPT_PACKET_SIZE:
DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
return 0;
case DCCP_SOCKOPT_SERVICE:
return dccp_getsockopt_service(sk, len,
(__be32 __user *)optval, optlen);
case DCCP_SOCKOPT_GET_CUR_MPS:
val = READ_ONCE(dp->dccps_mss_cache);
break;
case DCCP_SOCKOPT_AVAILABLE_CCIDS:
return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
case DCCP_SOCKOPT_TX_CCID:
val = ccid_get_current_tx_ccid(dp);
if (val < 0)
return -ENOPROTOOPT;
break;
case DCCP_SOCKOPT_RX_CCID:
val = ccid_get_current_rx_ccid(dp);
if (val < 0)
return -ENOPROTOOPT;
break;
case DCCP_SOCKOPT_SERVER_TIMEWAIT:
val = dp->dccps_server_timewait;
break;
case DCCP_SOCKOPT_SEND_CSCOV:
val = dp->dccps_pcslen;
break;
case DCCP_SOCKOPT_RECV_CSCOV:
val = dp->dccps_pcrlen;
break;
case DCCP_SOCKOPT_QPOLICY_ID:
val = dp->dccps_qpolicy;
break;
case DCCP_SOCKOPT_QPOLICY_TXQLEN:
val = dp->dccps_tx_qlen;
break;
case 128 ... 191:
return ccid_hc_rx_getsockopt(dp->dccps_hc_rx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
case 192 ... 255:
return ccid_hc_tx_getsockopt(dp->dccps_hc_tx_ccid, sk, optname,
len, (u32 __user *)optval, optlen);
default:
return -ENOPROTOOPT;
}
len = sizeof(val);
if (put_user(len, optlen) || copy_to_user(optval, &val, len))
return -EFAULT;
return 0;
}
int dccp_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen)
{
if (level != SOL_DCCP)
return inet_csk(sk)->icsk_af_ops->getsockopt(sk, level,
optname, optval,
optlen);
return do_dccp_getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL_GPL(dccp_getsockopt);
static int dccp_msghdr_parse(struct msghdr *msg, struct sk_buff *skb)
{
struct cmsghdr *cmsg;
/*
* Assign an (opaque) qpolicy priority value to skb->priority.
*
* We are overloading this skb field for use with the qpolicy subystem.
* The skb->priority is normally used for the SO_PRIORITY option, which
* is initialised from sk_priority. Since the assignment of sk_priority
* to skb->priority happens later (on layer 3), we overload this field
* for use with queueing priorities as long as the skb is on layer 4.
* The default priority value (if nothing is set) is 0.
*/
skb->priority = 0;
for_each_cmsghdr(cmsg, msg) {
if (!CMSG_OK(msg, cmsg))
return -EINVAL;
if (cmsg->cmsg_level != SOL_DCCP)
continue;
if (cmsg->cmsg_type <= DCCP_SCM_QPOLICY_MAX &&
!dccp_qpolicy_param_ok(skb->sk, cmsg->cmsg_type))
return -EINVAL;
switch (cmsg->cmsg_type) {
case DCCP_SCM_PRIORITY:
if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u32)))
return -EINVAL;
skb->priority = *(__u32 *)CMSG_DATA(cmsg);
break;
default:
return -EINVAL;
}
}
return 0;
}
int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
const struct dccp_sock *dp = dccp_sk(sk);
const int flags = msg->msg_flags;
const int noblock = flags & MSG_DONTWAIT;
struct sk_buff *skb;
int rc, size;
long timeo;
trace_dccp_probe(sk, len);
if (len > READ_ONCE(dp->dccps_mss_cache))
return -EMSGSIZE;
lock_sock(sk);
timeo = sock_sndtimeo(sk, noblock);
/*
* We have to use sk_stream_wait_connect here to set sk_write_pending,
* so that the trick in dccp_rcv_request_sent_state_process.
*/
/* Wait for a connection to finish. */
if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
if ((rc = sk_stream_wait_connect(sk, &timeo)) != 0)
goto out_release;
size = sk->sk_prot->max_header + len;
release_sock(sk);
skb = sock_alloc_send_skb(sk, size, noblock, &rc);
lock_sock(sk);
if (skb == NULL)
goto out_release;
if (dccp_qpolicy_full(sk)) {
rc = -EAGAIN;
goto out_discard;
}
if (sk->sk_state == DCCP_CLOSED) {
rc = -ENOTCONN;
goto out_discard;
}
/* We need to check dccps_mss_cache after socket is locked. */
if (len > dp->dccps_mss_cache) {
rc = -EMSGSIZE;
goto out_discard;
}
skb_reserve(skb, sk->sk_prot->max_header);
rc = memcpy_from_msg(skb_put(skb, len), msg, len);
if (rc != 0)
goto out_discard;
rc = dccp_msghdr_parse(msg, skb);
if (rc != 0)
goto out_discard;
dccp_qpolicy_push(sk, skb);
/*
* The xmit_timer is set if the TX CCID is rate-based and will expire
* when congestion control permits to release further packets into the
* network. Window-based CCIDs do not use this timer.
*/
if (!timer_pending(&dp->dccps_xmit_timer))
dccp_write_xmit(sk);
out_release:
release_sock(sk);
return rc ? : len;
out_discard:
kfree_skb(skb);
goto out_release;
}
EXPORT_SYMBOL_GPL(dccp_sendmsg);
int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
int *addr_len)
{
const struct dccp_hdr *dh;
long timeo;
lock_sock(sk);
if (sk->sk_state == DCCP_LISTEN) {
len = -ENOTCONN;
goto out;
}
timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
do {
struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);
if (skb == NULL)
goto verify_sock_status;
dh = dccp_hdr(skb);
switch (dh->dccph_type) {
case DCCP_PKT_DATA:
case DCCP_PKT_DATAACK:
goto found_ok_skb;
case DCCP_PKT_CLOSE:
case DCCP_PKT_CLOSEREQ:
if (!(flags & MSG_PEEK))
dccp_finish_passive_close(sk);
fallthrough;
case DCCP_PKT_RESET:
dccp_pr_debug("found fin (%s) ok!\n",
dccp_packet_name(dh->dccph_type));
len = 0;
goto found_fin_ok;
default:
dccp_pr_debug("packet_type=%s\n",
dccp_packet_name(dh->dccph_type));
sk_eat_skb(sk, skb);
}
verify_sock_status:
if (sock_flag(sk, SOCK_DONE)) {
len = 0;
break;
}
if (sk->sk_err) {
len = sock_error(sk);
break;
}
if (sk->sk_shutdown & RCV_SHUTDOWN) {
len = 0;
break;
}
if (sk->sk_state == DCCP_CLOSED) {
if (!sock_flag(sk, SOCK_DONE)) {
/* This occurs when user tries to read
* from never connected socket.
*/
len = -ENOTCONN;
break;
}
len = 0;
break;
}
if (!timeo) {
len = -EAGAIN;
break;
}
if (signal_pending(current)) {
len = sock_intr_errno(timeo);
break;
}
sk_wait_data(sk, &timeo, NULL);
continue;
found_ok_skb:
if (len > skb->len)
len = skb->len;
else if (len < skb->len)
msg->msg_flags |= MSG_TRUNC;
if (skb_copy_datagram_msg(skb, 0, msg, len)) {
/* Exception. Bailout! */
len = -EFAULT;
break;
}
if (flags & MSG_TRUNC)
len = skb->len;
found_fin_ok:
if (!(flags & MSG_PEEK))
sk_eat_skb(sk, skb);
break;
} while (1);
out:
release_sock(sk);
return len;
}
EXPORT_SYMBOL_GPL(dccp_recvmsg);
int inet_dccp_listen(struct socket *sock, int backlog)
{
struct sock *sk = sock->sk;
unsigned char old_state;
int err;
lock_sock(sk);
err = -EINVAL;
if (sock->state != SS_UNCONNECTED || sock->type != SOCK_DCCP)
goto out;
old_state = sk->sk_state;
if (!((1 << old_state) & (DCCPF_CLOSED | DCCPF_LISTEN)))
goto out;
WRITE_ONCE(sk->sk_max_ack_backlog, backlog);
/* Really, if the socket is already in listen state
* we can only allow the backlog to be adjusted.
*/
if (old_state != DCCP_LISTEN) {
struct dccp_sock *dp = dccp_sk(sk);
dp->dccps_role = DCCP_ROLE_LISTEN;
/* do not start to listen if feature negotiation setup fails */
if (dccp_feat_finalise_settings(dp)) {
err = -EPROTO;
goto out;
}
err = inet_csk_listen_start(sk);
if (err)
goto out;
}
err = 0;
out:
release_sock(sk);
return err;
}
EXPORT_SYMBOL_GPL(inet_dccp_listen);
static void dccp_terminate_connection(struct sock *sk)
{
u8 next_state = DCCP_CLOSED;
switch (sk->sk_state) {
case DCCP_PASSIVE_CLOSE:
case DCCP_PASSIVE_CLOSEREQ:
dccp_finish_passive_close(sk);
break;
case DCCP_PARTOPEN:
dccp_pr_debug("Stop PARTOPEN timer (%p)\n", sk);
inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
fallthrough;
case DCCP_OPEN:
dccp_send_close(sk, 1);
if (dccp_sk(sk)->dccps_role == DCCP_ROLE_SERVER &&
!dccp_sk(sk)->dccps_server_timewait)
next_state = DCCP_ACTIVE_CLOSEREQ;
else
next_state = DCCP_CLOSING;
fallthrough;
default:
dccp_set_state(sk, next_state);
}
}
void dccp_close(struct sock *sk, long timeout)
{
struct dccp_sock *dp = dccp_sk(sk);
struct sk_buff *skb;
u32 data_was_unread = 0;
int state;
lock_sock(sk);
sk->sk_shutdown = SHUTDOWN_MASK;