forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathsocket.c
3359 lines (2950 loc) · 86.1 KB
/
socket.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
/*
* net/tipc/socket.c: TIPC socket API
*
* Copyright (c) 2001-2007, 2012-2017, Ericsson AB
* Copyright (c) 2004-2008, 2010-2013, Wind River Systems
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
*
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the names of the copyright holders nor the names of its
* contributors may be used to endorse or promote products derived from
* this software without specific prior written permission.
*
* Alternatively, this software may be distributed under the terms of the
* GNU General Public License ("GPL") version 2 as published by the Free
* Software Foundation.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
* AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
* LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
* CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
* SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
* INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
* CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
* ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/
#include <linux/rhashtable.h>
#include <linux/sched/signal.h>
#include "core.h"
#include "name_table.h"
#include "node.h"
#include "link.h"
#include "name_distr.h"
#include "socket.h"
#include "bcast.h"
#include "netlink.h"
#include "group.h"
#define CONN_TIMEOUT_DEFAULT 8000 /* default connect timeout = 8s */
#define CONN_PROBING_INTV msecs_to_jiffies(3600000) /* [ms] => 1 h */
#define TIPC_FWD_MSG 1
#define TIPC_MAX_PORT 0xffffffff
#define TIPC_MIN_PORT 1
#define TIPC_ACK_RATE 4 /* ACK at 1/4 of of rcv window size */
enum {
TIPC_LISTEN = TCP_LISTEN,
TIPC_ESTABLISHED = TCP_ESTABLISHED,
TIPC_OPEN = TCP_CLOSE,
TIPC_DISCONNECTING = TCP_CLOSE_WAIT,
TIPC_CONNECTING = TCP_SYN_SENT,
};
struct sockaddr_pair {
struct sockaddr_tipc sock;
struct sockaddr_tipc member;
};
/**
* struct tipc_sock - TIPC socket structure
* @sk: socket - interacts with 'port' and with user via the socket API
* @conn_type: TIPC type used when connection was established
* @conn_instance: TIPC instance used when connection was established
* @published: non-zero if port has one or more associated names
* @max_pkt: maximum packet size "hint" used when building messages sent by port
* @portid: unique port identity in TIPC socket hash table
* @phdr: preformatted message header used when sending messages
* #cong_links: list of congested links
* @publications: list of publications for port
* @blocking_link: address of the congested link we are currently sleeping on
* @pub_count: total # of publications port has made during its lifetime
* @probing_state:
* @conn_timeout: the time we can wait for an unresponded setup request
* @dupl_rcvcnt: number of bytes counted twice, in both backlog and rcv queue
* @cong_link_cnt: number of congested links
* @snt_unacked: # messages sent by socket, and not yet acked by peer
* @rcv_unacked: # messages read by user, but not yet acked back to peer
* @peer: 'connected' peer for dgram/rdm
* @node: hash table node
* @mc_method: cookie for use between socket and broadcast layer
* @rcu: rcu struct for tipc_sock
*/
struct tipc_sock {
struct sock sk;
u32 conn_type;
u32 conn_instance;
int published;
u32 max_pkt;
u32 portid;
struct tipc_msg phdr;
struct list_head cong_links;
struct list_head publications;
u32 pub_count;
uint conn_timeout;
atomic_t dupl_rcvcnt;
bool probe_unacked;
u16 cong_link_cnt;
u16 snt_unacked;
u16 snd_win;
u16 peer_caps;
u16 rcv_unacked;
u16 rcv_win;
struct sockaddr_tipc peer;
struct rhash_head node;
struct tipc_mc_method mc_method;
struct rcu_head rcu;
struct tipc_group *group;
};
static int tipc_sk_backlog_rcv(struct sock *sk, struct sk_buff *skb);
static void tipc_data_ready(struct sock *sk);
static void tipc_write_space(struct sock *sk);
static void tipc_sock_destruct(struct sock *sk);
static int tipc_release(struct socket *sock);
static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags,
bool kern);
static void tipc_sk_timeout(struct timer_list *t);
static int tipc_sk_publish(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq);
static int tipc_sk_withdraw(struct tipc_sock *tsk, uint scope,
struct tipc_name_seq const *seq);
static int tipc_sk_leave(struct tipc_sock *tsk);
static struct tipc_sock *tipc_sk_lookup(struct net *net, u32 portid);
static int tipc_sk_insert(struct tipc_sock *tsk);
static void tipc_sk_remove(struct tipc_sock *tsk);
static int __tipc_sendstream(struct socket *sock, struct msghdr *m, size_t dsz);
static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dsz);
static const struct proto_ops packet_ops;
static const struct proto_ops stream_ops;
static const struct proto_ops msg_ops;
static struct proto tipc_proto;
static const struct rhashtable_params tsk_rht_params;
static u32 tsk_own_node(struct tipc_sock *tsk)
{
return msg_prevnode(&tsk->phdr);
}
static u32 tsk_peer_node(struct tipc_sock *tsk)
{
return msg_destnode(&tsk->phdr);
}
static u32 tsk_peer_port(struct tipc_sock *tsk)
{
return msg_destport(&tsk->phdr);
}
static bool tsk_unreliable(struct tipc_sock *tsk)
{
return msg_src_droppable(&tsk->phdr) != 0;
}
static void tsk_set_unreliable(struct tipc_sock *tsk, bool unreliable)
{
msg_set_src_droppable(&tsk->phdr, unreliable ? 1 : 0);
}
static bool tsk_unreturnable(struct tipc_sock *tsk)
{
return msg_dest_droppable(&tsk->phdr) != 0;
}
static void tsk_set_unreturnable(struct tipc_sock *tsk, bool unreturnable)
{
msg_set_dest_droppable(&tsk->phdr, unreturnable ? 1 : 0);
}
static int tsk_importance(struct tipc_sock *tsk)
{
return msg_importance(&tsk->phdr);
}
static int tsk_set_importance(struct tipc_sock *tsk, int imp)
{
if (imp > TIPC_CRITICAL_IMPORTANCE)
return -EINVAL;
msg_set_importance(&tsk->phdr, (u32)imp);
return 0;
}
static struct tipc_sock *tipc_sk(const struct sock *sk)
{
return container_of(sk, struct tipc_sock, sk);
}
static bool tsk_conn_cong(struct tipc_sock *tsk)
{
return tsk->snt_unacked > tsk->snd_win;
}
static u16 tsk_blocks(int len)
{
return ((len / FLOWCTL_BLK_SZ) + 1);
}
/* tsk_blocks(): translate a buffer size in bytes to number of
* advertisable blocks, taking into account the ratio truesize(len)/len
* We can trust that this ratio is always < 4 for len >= FLOWCTL_BLK_SZ
*/
static u16 tsk_adv_blocks(int len)
{
return len / FLOWCTL_BLK_SZ / 4;
}
/* tsk_inc(): increment counter for sent or received data
* - If block based flow control is not supported by peer we
* fall back to message based ditto, incrementing the counter
*/
static u16 tsk_inc(struct tipc_sock *tsk, int msglen)
{
if (likely(tsk->peer_caps & TIPC_BLOCK_FLOWCTL))
return ((msglen / FLOWCTL_BLK_SZ) + 1);
return 1;
}
/**
* tsk_advance_rx_queue - discard first buffer in socket receive queue
*
* Caller must hold socket lock
*/
static void tsk_advance_rx_queue(struct sock *sk)
{
kfree_skb(__skb_dequeue(&sk->sk_receive_queue));
}
/* tipc_sk_respond() : send response message back to sender
*/
static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err)
{
u32 selector;
u32 dnode;
u32 onode = tipc_own_addr(sock_net(sk));
if (!tipc_msg_reverse(onode, &skb, err))
return;
dnode = msg_destnode(buf_msg(skb));
selector = msg_origport(buf_msg(skb));
tipc_node_xmit_skb(sock_net(sk), skb, dnode, selector);
}
/**
* tsk_rej_rx_queue - reject all buffers in socket receive queue
*
* Caller must hold socket lock
*/
static void tsk_rej_rx_queue(struct sock *sk)
{
struct sk_buff *skb;
while ((skb = __skb_dequeue(&sk->sk_receive_queue)))
tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT);
}
static bool tipc_sk_connected(struct sock *sk)
{
return sk->sk_state == TIPC_ESTABLISHED;
}
/* tipc_sk_type_connectionless - check if the socket is datagram socket
* @sk: socket
*
* Returns true if connection less, false otherwise
*/
static bool tipc_sk_type_connectionless(struct sock *sk)
{
return sk->sk_type == SOCK_RDM || sk->sk_type == SOCK_DGRAM;
}
/* tsk_peer_msg - verify if message was sent by connected port's peer
*
* Handles cases where the node's network address has changed from
* the default of <0.0.0> to its configured setting.
*/
static bool tsk_peer_msg(struct tipc_sock *tsk, struct tipc_msg *msg)
{
struct sock *sk = &tsk->sk;
struct tipc_net *tn = net_generic(sock_net(sk), tipc_net_id);
u32 peer_port = tsk_peer_port(tsk);
u32 orig_node;
u32 peer_node;
if (unlikely(!tipc_sk_connected(sk)))
return false;
if (unlikely(msg_origport(msg) != peer_port))
return false;
orig_node = msg_orignode(msg);
peer_node = tsk_peer_node(tsk);
if (likely(orig_node == peer_node))
return true;
if (!orig_node && (peer_node == tn->own_addr))
return true;
if (!peer_node && (orig_node == tn->own_addr))
return true;
return false;
}
/* tipc_set_sk_state - set the sk_state of the socket
* @sk: socket
*
* Caller must hold socket lock
*
* Returns 0 on success, errno otherwise
*/
static int tipc_set_sk_state(struct sock *sk, int state)
{
int oldsk_state = sk->sk_state;
int res = -EINVAL;
switch (state) {
case TIPC_OPEN:
res = 0;
break;
case TIPC_LISTEN:
case TIPC_CONNECTING:
if (oldsk_state == TIPC_OPEN)
res = 0;
break;
case TIPC_ESTABLISHED:
if (oldsk_state == TIPC_CONNECTING ||
oldsk_state == TIPC_OPEN)
res = 0;
break;
case TIPC_DISCONNECTING:
if (oldsk_state == TIPC_CONNECTING ||
oldsk_state == TIPC_ESTABLISHED)
res = 0;
break;
}
if (!res)
sk->sk_state = state;
return res;
}
static int tipc_sk_sock_err(struct socket *sock, long *timeout)
{
struct sock *sk = sock->sk;
int err = sock_error(sk);
int typ = sock->type;
if (err)
return err;
if (typ == SOCK_STREAM || typ == SOCK_SEQPACKET) {
if (sk->sk_state == TIPC_DISCONNECTING)
return -EPIPE;
else if (!tipc_sk_connected(sk))
return -ENOTCONN;
}
if (!*timeout)
return -EAGAIN;
if (signal_pending(current))
return sock_intr_errno(*timeout);
return 0;
}
#define tipc_wait_for_cond(sock_, timeo_, condition_) \
({ \
struct sock *sk_; \
int rc_; \
\
while ((rc_ = !(condition_))) { \
DEFINE_WAIT_FUNC(wait_, woken_wake_function); \
sk_ = (sock_)->sk; \
rc_ = tipc_sk_sock_err((sock_), timeo_); \
if (rc_) \
break; \
prepare_to_wait(sk_sleep(sk_), &wait_, TASK_INTERRUPTIBLE); \
release_sock(sk_); \
*(timeo_) = wait_woken(&wait_, TASK_INTERRUPTIBLE, *(timeo_)); \
sched_annotate_sleep(); \
lock_sock(sk_); \
remove_wait_queue(sk_sleep(sk_), &wait_); \
} \
rc_; \
})
/**
* tipc_sk_create - create a TIPC socket
* @net: network namespace (must be default network)
* @sock: pre-allocated socket structure
* @protocol: protocol indicator (must be 0)
* @kern: caused by kernel or by userspace?
*
* This routine creates additional data structures used by the TIPC socket,
* initializes them, and links them together.
*
* Returns 0 on success, errno otherwise
*/
static int tipc_sk_create(struct net *net, struct socket *sock,
int protocol, int kern)
{
struct tipc_net *tn;
const struct proto_ops *ops;
struct sock *sk;
struct tipc_sock *tsk;
struct tipc_msg *msg;
/* Validate arguments */
if (unlikely(protocol != 0))
return -EPROTONOSUPPORT;
switch (sock->type) {
case SOCK_STREAM:
ops = &stream_ops;
break;
case SOCK_SEQPACKET:
ops = &packet_ops;
break;
case SOCK_DGRAM:
case SOCK_RDM:
ops = &msg_ops;
break;
default:
return -EPROTOTYPE;
}
/* Allocate socket's protocol area */
sk = sk_alloc(net, AF_TIPC, GFP_KERNEL, &tipc_proto, kern);
if (sk == NULL)
return -ENOMEM;
tsk = tipc_sk(sk);
tsk->max_pkt = MAX_PKT_DEFAULT;
INIT_LIST_HEAD(&tsk->publications);
INIT_LIST_HEAD(&tsk->cong_links);
msg = &tsk->phdr;
tn = net_generic(sock_net(sk), tipc_net_id);
/* Finish initializing socket data structures */
sock->ops = ops;
sock_init_data(sock, sk);
tipc_set_sk_state(sk, TIPC_OPEN);
if (tipc_sk_insert(tsk)) {
pr_warn("Socket create failed; port number exhausted\n");
return -EINVAL;
}
/* Ensure tsk is visible before we read own_addr. */
smp_mb();
tipc_msg_init(tn->own_addr, msg, TIPC_LOW_IMPORTANCE, TIPC_NAMED_MSG,
NAMED_H_SIZE, 0);
msg_set_origport(msg, tsk->portid);
timer_setup(&sk->sk_timer, tipc_sk_timeout, 0);
sk->sk_shutdown = 0;
sk->sk_backlog_rcv = tipc_sk_backlog_rcv;
sk->sk_rcvbuf = sysctl_tipc_rmem[1];
sk->sk_data_ready = tipc_data_ready;
sk->sk_write_space = tipc_write_space;
sk->sk_destruct = tipc_sock_destruct;
tsk->conn_timeout = CONN_TIMEOUT_DEFAULT;
atomic_set(&tsk->dupl_rcvcnt, 0);
/* Start out with safe limits until we receive an advertised window */
tsk->snd_win = tsk_adv_blocks(RCVBUF_MIN);
tsk->rcv_win = tsk->snd_win;
if (tipc_sk_type_connectionless(sk)) {
tsk_set_unreturnable(tsk, true);
if (sock->type == SOCK_DGRAM)
tsk_set_unreliable(tsk, true);
}
return 0;
}
static void tipc_sk_callback(struct rcu_head *head)
{
struct tipc_sock *tsk = container_of(head, struct tipc_sock, rcu);
sock_put(&tsk->sk);
}
/* Caller should hold socket lock for the socket. */
static void __tipc_shutdown(struct socket *sock, int error)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct net *net = sock_net(sk);
long timeout = CONN_TIMEOUT_DEFAULT;
u32 dnode = tsk_peer_node(tsk);
struct sk_buff *skb;
/* Avoid that hi-prio shutdown msgs bypass msgs in link wakeup queue */
tipc_wait_for_cond(sock, &timeout, (!tsk->cong_link_cnt &&
!tsk_conn_cong(tsk)));
/* Reject all unreceived messages, except on an active connection
* (which disconnects locally & sends a 'FIN+' to peer).
*/
while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
if (TIPC_SKB_CB(skb)->bytes_read) {
kfree_skb(skb);
continue;
}
if (!tipc_sk_type_connectionless(sk) &&
sk->sk_state != TIPC_DISCONNECTING) {
tipc_set_sk_state(sk, TIPC_DISCONNECTING);
tipc_node_remove_conn(net, dnode, tsk->portid);
}
tipc_sk_respond(sk, skb, error);
}
if (tipc_sk_type_connectionless(sk))
return;
if (sk->sk_state != TIPC_DISCONNECTING) {
skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE,
TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode,
tsk_own_node(tsk), tsk_peer_port(tsk),
tsk->portid, error);
if (skb)
tipc_node_xmit_skb(net, skb, dnode, tsk->portid);
tipc_node_remove_conn(net, dnode, tsk->portid);
tipc_set_sk_state(sk, TIPC_DISCONNECTING);
}
}
/**
* tipc_release - destroy a TIPC socket
* @sock: socket to destroy
*
* This routine cleans up any messages that are still queued on the socket.
* For DGRAM and RDM socket types, all queued messages are rejected.
* For SEQPACKET and STREAM socket types, the first message is rejected
* and any others are discarded. (If the first message on a STREAM socket
* is partially-read, it is discarded and the next one is rejected instead.)
*
* NOTE: Rejected messages are not necessarily returned to the sender! They
* are returned or discarded according to the "destination droppable" setting
* specified for the message by the sender.
*
* Returns 0 on success, errno otherwise
*/
static int tipc_release(struct socket *sock)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk;
/*
* Exit if socket isn't fully initialized (occurs when a failed accept()
* releases a pre-allocated child socket that was never used)
*/
if (sk == NULL)
return 0;
tsk = tipc_sk(sk);
lock_sock(sk);
__tipc_shutdown(sock, TIPC_ERR_NO_PORT);
sk->sk_shutdown = SHUTDOWN_MASK;
tipc_sk_leave(tsk);
tipc_sk_withdraw(tsk, 0, NULL);
sk_stop_timer(sk, &sk->sk_timer);
tipc_sk_remove(tsk);
/* Reject any messages that accumulated in backlog queue */
release_sock(sk);
tipc_dest_list_purge(&tsk->cong_links);
tsk->cong_link_cnt = 0;
call_rcu(&tsk->rcu, tipc_sk_callback);
sock->sk = NULL;
return 0;
}
/**
* tipc_bind - associate or disassocate TIPC name(s) with a socket
* @sock: socket structure
* @uaddr: socket address describing name(s) and desired operation
* @uaddr_len: size of socket address data structure
*
* Name and name sequence binding is indicated using a positive scope value;
* a negative scope value unbinds the specified name. Specifying no name
* (i.e. a socket address length of 0) unbinds all names from the socket.
*
* Returns 0 on success, errno otherwise
*
* NOTE: This routine doesn't need to take the socket lock since it doesn't
* access any non-constant socket information.
*/
static int tipc_bind(struct socket *sock, struct sockaddr *uaddr,
int uaddr_len)
{
struct sock *sk = sock->sk;
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
struct tipc_sock *tsk = tipc_sk(sk);
int res = -EINVAL;
lock_sock(sk);
if (unlikely(!uaddr_len)) {
res = tipc_sk_withdraw(tsk, 0, NULL);
goto exit;
}
if (tsk->group) {
res = -EACCES;
goto exit;
}
if (uaddr_len < sizeof(struct sockaddr_tipc)) {
res = -EINVAL;
goto exit;
}
if (addr->family != AF_TIPC) {
res = -EAFNOSUPPORT;
goto exit;
}
if (addr->addrtype == TIPC_ADDR_NAME)
addr->addr.nameseq.upper = addr->addr.nameseq.lower;
else if (addr->addrtype != TIPC_ADDR_NAMESEQ) {
res = -EAFNOSUPPORT;
goto exit;
}
if ((addr->addr.nameseq.type < TIPC_RESERVED_TYPES) &&
(addr->addr.nameseq.type != TIPC_TOP_SRV) &&
(addr->addr.nameseq.type != TIPC_CFG_SRV)) {
res = -EACCES;
goto exit;
}
res = (addr->scope > 0) ?
tipc_sk_publish(tsk, addr->scope, &addr->addr.nameseq) :
tipc_sk_withdraw(tsk, -addr->scope, &addr->addr.nameseq);
exit:
release_sock(sk);
return res;
}
/**
* tipc_getname - get port ID of socket or peer socket
* @sock: socket structure
* @uaddr: area for returned socket address
* @uaddr_len: area for returned length of socket address
* @peer: 0 = own ID, 1 = current peer ID, 2 = current/former peer ID
*
* Returns 0 on success, errno otherwise
*
* NOTE: This routine doesn't need to take the socket lock since it only
* accesses socket information that is unchanging (or which changes in
* a completely predictable manner).
*/
static int tipc_getname(struct socket *sock, struct sockaddr *uaddr,
int *uaddr_len, int peer)
{
struct sockaddr_tipc *addr = (struct sockaddr_tipc *)uaddr;
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_net *tn = net_generic(sock_net(sock->sk), tipc_net_id);
memset(addr, 0, sizeof(*addr));
if (peer) {
if ((!tipc_sk_connected(sk)) &&
((peer != 2) || (sk->sk_state != TIPC_DISCONNECTING)))
return -ENOTCONN;
addr->addr.id.ref = tsk_peer_port(tsk);
addr->addr.id.node = tsk_peer_node(tsk);
} else {
addr->addr.id.ref = tsk->portid;
addr->addr.id.node = tn->own_addr;
}
*uaddr_len = sizeof(*addr);
addr->addrtype = TIPC_ADDR_ID;
addr->family = AF_TIPC;
addr->scope = 0;
addr->addr.name.domain = 0;
return 0;
}
/**
* tipc_poll - read and possibly block on pollmask
* @file: file structure associated with the socket
* @sock: socket for which to calculate the poll bits
* @wait: ???
*
* Returns pollmask value
*
* COMMENTARY:
* It appears that the usual socket locking mechanisms are not useful here
* since the pollmask info is potentially out-of-date the moment this routine
* exits. TCP and other protocols seem to rely on higher level poll routines
* to handle any preventable race conditions, so TIPC will do the same ...
*
* IMPORTANT: The fact that a read or write operation is indicated does NOT
* imply that the operation will succeed, merely that it should be performed
* and will not block.
*/
static unsigned int tipc_poll(struct file *file, struct socket *sock,
poll_table *wait)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_group *grp = tsk->group;
u32 revents = 0;
sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_shutdown & RCV_SHUTDOWN)
revents |= POLLRDHUP | POLLIN | POLLRDNORM;
if (sk->sk_shutdown == SHUTDOWN_MASK)
revents |= POLLHUP;
switch (sk->sk_state) {
case TIPC_ESTABLISHED:
case TIPC_CONNECTING:
if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk))
revents |= POLLOUT;
/* fall thru' */
case TIPC_LISTEN:
if (!skb_queue_empty(&sk->sk_receive_queue))
revents |= POLLIN | POLLRDNORM;
break;
case TIPC_OPEN:
if (!grp || tipc_group_size(grp))
if (!tsk->cong_link_cnt)
revents |= POLLOUT;
if (!tipc_sk_type_connectionless(sk))
break;
if (skb_queue_empty(&sk->sk_receive_queue))
break;
revents |= POLLIN | POLLRDNORM;
break;
case TIPC_DISCONNECTING:
revents = POLLIN | POLLRDNORM | POLLHUP;
break;
}
return revents;
}
/**
* tipc_sendmcast - send multicast message
* @sock: socket structure
* @seq: destination address
* @msg: message to send
* @dlen: length of data to send
* @timeout: timeout to wait for wakeup
*
* Called from function tipc_sendmsg(), which has done all sanity checks
* Returns the number of bytes sent on success, or errno
*/
static int tipc_sendmcast(struct socket *sock, struct tipc_name_seq *seq,
struct msghdr *msg, size_t dlen, long timeout)
{
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_msg *hdr = &tsk->phdr;
struct net *net = sock_net(sk);
int mtu = tipc_bcast_get_mtu(net);
struct tipc_mc_method *method = &tsk->mc_method;
u32 domain = addr_domain(net, TIPC_CLUSTER_SCOPE);
struct sk_buff_head pkts;
struct tipc_nlist dsts;
int rc;
if (tsk->group)
return -EACCES;
/* Block or return if any destination link is congested */
rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt);
if (unlikely(rc))
return rc;
/* Lookup destination nodes */
tipc_nlist_init(&dsts, tipc_own_addr(net));
tipc_nametbl_lookup_dst_nodes(net, seq->type, seq->lower,
seq->upper, domain, &dsts);
if (!dsts.local && !dsts.remote)
return -EHOSTUNREACH;
/* Build message header */
msg_set_type(hdr, TIPC_MCAST_MSG);
msg_set_hdr_sz(hdr, MCAST_H_SIZE);
msg_set_lookup_scope(hdr, TIPC_CLUSTER_SCOPE);
msg_set_destport(hdr, 0);
msg_set_destnode(hdr, 0);
msg_set_nametype(hdr, seq->type);
msg_set_namelower(hdr, seq->lower);
msg_set_nameupper(hdr, seq->upper);
/* Build message as chain of buffers */
skb_queue_head_init(&pkts);
rc = tipc_msg_build(hdr, msg, 0, dlen, mtu, &pkts);
/* Send message if build was successful */
if (unlikely(rc == dlen))
rc = tipc_mcast_xmit(net, &pkts, method, &dsts,
&tsk->cong_link_cnt);
tipc_nlist_purge(&dsts);
return rc ? rc : dlen;
}
/**
* tipc_send_group_msg - send a message to a member in the group
* @net: network namespace
* @m: message to send
* @mb: group member
* @dnode: destination node
* @dport: destination port
* @dlen: total length of message data
*/
static int tipc_send_group_msg(struct net *net, struct tipc_sock *tsk,
struct msghdr *m, struct tipc_member *mb,
u32 dnode, u32 dport, int dlen)
{
u16 bc_snd_nxt = tipc_group_bc_snd_nxt(tsk->group);
struct tipc_mc_method *method = &tsk->mc_method;
int blks = tsk_blocks(GROUP_H_SIZE + dlen);
struct tipc_msg *hdr = &tsk->phdr;
struct sk_buff_head pkts;
int mtu, rc;
/* Complete message header */
msg_set_type(hdr, TIPC_GRP_UCAST_MSG);
msg_set_hdr_sz(hdr, GROUP_H_SIZE);
msg_set_destport(hdr, dport);
msg_set_destnode(hdr, dnode);
msg_set_grp_bc_seqno(hdr, bc_snd_nxt);
/* Build message as chain of buffers */
skb_queue_head_init(&pkts);
mtu = tipc_node_get_mtu(net, dnode, tsk->portid);
rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts);
if (unlikely(rc != dlen))
return rc;
/* Send message */
rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid);
if (unlikely(rc == -ELINKCONG)) {
tipc_dest_push(&tsk->cong_links, dnode, 0);
tsk->cong_link_cnt++;
}
/* Update send window */
tipc_group_update_member(mb, blks);
/* A broadcast sent within next EXPIRE period must follow same path */
method->rcast = true;
method->mandatory = true;
return dlen;
}
/**
* tipc_send_group_unicast - send message to a member in the group
* @sock: socket structure
* @m: message to send
* @dlen: total length of message data
* @timeout: timeout to wait for wakeup
*
* Called from function tipc_sendmsg(), which has done all sanity checks
* Returns the number of bytes sent on success, or errno
*/
static int tipc_send_group_unicast(struct socket *sock, struct msghdr *m,
int dlen, long timeout)
{
struct sock *sk = sock->sk;
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
int blks = tsk_blocks(GROUP_H_SIZE + dlen);
struct tipc_sock *tsk = tipc_sk(sk);
struct tipc_group *grp = tsk->group;
struct net *net = sock_net(sk);
struct tipc_member *mb = NULL;
u32 node, port;
int rc;
node = dest->addr.id.node;
port = dest->addr.id.ref;
if (!port && !node)
return -EHOSTUNREACH;
/* Block or return if destination link or member is congested */
rc = tipc_wait_for_cond(sock, &timeout,
!tipc_dest_find(&tsk->cong_links, node, 0) &&
!tipc_group_cong(grp, node, port, blks, &mb));
if (unlikely(rc))
return rc;
if (unlikely(!mb))
return -EHOSTUNREACH;
rc = tipc_send_group_msg(net, tsk, m, mb, node, port, dlen);
return rc ? rc : dlen;
}
/**
* tipc_send_group_anycast - send message to any member with given identity
* @sock: socket structure
* @m: message to send
* @dlen: total length of message data
* @timeout: timeout to wait for wakeup
*
* Called from function tipc_sendmsg(), which has done all sanity checks
* Returns the number of bytes sent on success, or errno
*/
static int tipc_send_group_anycast(struct socket *sock, struct msghdr *m,
int dlen, long timeout)
{
DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
struct sock *sk = sock->sk;
struct tipc_sock *tsk = tipc_sk(sk);
struct list_head *cong_links = &tsk->cong_links;
int blks = tsk_blocks(GROUP_H_SIZE + dlen);
struct tipc_group *grp = tsk->group;
struct tipc_member *first = NULL;
struct tipc_member *mbr = NULL;
struct net *net = sock_net(sk);
u32 node, port, exclude;
u32 type, inst, domain;
struct list_head dsts;
int lookups = 0;
int dstcnt, rc;
bool cong;
INIT_LIST_HEAD(&dsts);
type = dest->addr.name.name.type;
inst = dest->addr.name.name.instance;
domain = addr_domain(net, dest->scope);
exclude = tipc_group_exclude(grp);
while (++lookups < 4) {
first = NULL;
/* Look for a non-congested destination member, if any */
while (1) {
if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts,
&dstcnt, exclude, false))
return -EHOSTUNREACH;
tipc_dest_pop(&dsts, &node, &port);
cong = tipc_group_cong(grp, node, port, blks, &mbr);
if (!cong)
break;
if (mbr == first)
break;
if (!first)
first = mbr;
}
/* Start over if destination was not in member list */
if (unlikely(!mbr))
continue;
if (likely(!cong && !tipc_dest_find(cong_links, node, 0)))
break;
/* Block or return if destination link or member is congested */
rc = tipc_wait_for_cond(sock, &timeout,
!tipc_dest_find(cong_links, node, 0) &&
!tipc_group_cong(grp, node, port,
blks, &mbr));
if (unlikely(rc))
return rc;
/* Send, unless destination disappeared while waiting */
if (likely(mbr))
break;
}
if (unlikely(lookups >= 4))
return -EHOSTUNREACH;
rc = tipc_send_group_msg(net, tsk, m, mbr, node, port, dlen);
return rc ? rc : dlen;
}
/**
* tipc_send_group_bcast - send message to all members in communication group
* @sk: socket structure
* @m: message to send
* @dlen: total length of message data
* @timeout: timeout to wait for wakeup
*