forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
Copy pathnode.c
2989 lines (2597 loc) · 74 KB
/
node.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/node.c: TIPC node management routines
*
* Copyright (c) 2000-2006, 2012-2016, Ericsson AB
* Copyright (c) 2005-2006, 2010-2014, 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 "core.h"
#include "link.h"
#include "node.h"
#include "name_distr.h"
#include "socket.h"
#include "bcast.h"
#include "monitor.h"
#include "discover.h"
#include "netlink.h"
#include "trace.h"
#include "crypto.h"
#define INVALID_NODE_SIG 0x10000
#define NODE_CLEANUP_AFTER 300000
/* Flags used to take different actions according to flag type
* TIPC_NOTIFY_NODE_DOWN: notify node is down
* TIPC_NOTIFY_NODE_UP: notify node is up
* TIPC_DISTRIBUTE_NAME: publish or withdraw link state name type
*/
enum {
TIPC_NOTIFY_NODE_DOWN = (1 << 3),
TIPC_NOTIFY_NODE_UP = (1 << 4),
TIPC_NOTIFY_LINK_UP = (1 << 6),
TIPC_NOTIFY_LINK_DOWN = (1 << 7)
};
struct tipc_link_entry {
struct tipc_link *link;
spinlock_t lock; /* per link */
u32 mtu;
struct sk_buff_head inputq;
struct tipc_media_addr maddr;
};
struct tipc_bclink_entry {
struct tipc_link *link;
struct sk_buff_head inputq1;
struct sk_buff_head arrvq;
struct sk_buff_head inputq2;
struct sk_buff_head namedq;
};
/**
* struct tipc_node - TIPC node structure
* @addr: network address of node
* @ref: reference counter to node object
* @lock: rwlock governing access to structure
* @net: the applicable net namespace
* @hash: links to adjacent nodes in unsorted hash chain
* @inputq: pointer to input queue containing messages for msg event
* @namedq: pointer to name table input queue with name table messages
* @active_links: bearer ids of active links, used as index into links[] array
* @links: array containing references to all links to node
* @action_flags: bit mask of different types of node actions
* @state: connectivity state vs peer node
* @preliminary: a preliminary node or not
* @sync_point: sequence number where synch/failover is finished
* @list: links to adjacent nodes in sorted list of cluster's nodes
* @working_links: number of working links to node (both active and standby)
* @link_cnt: number of links to node
* @capabilities: bitmap, indicating peer node's functional capabilities
* @signature: node instance identifier
* @link_id: local and remote bearer ids of changing link, if any
* @publ_list: list of publications
* @rcu: rcu struct for tipc_node
* @delete_at: indicates the time for deleting a down node
* @crypto_rx: RX crypto handler
*/
struct tipc_node {
u32 addr;
struct kref kref;
rwlock_t lock;
struct net *net;
struct hlist_node hash;
int active_links[2];
struct tipc_link_entry links[MAX_BEARERS];
struct tipc_bclink_entry bc_entry;
int action_flags;
struct list_head list;
int state;
bool preliminary;
bool failover_sent;
u16 sync_point;
int link_cnt;
u16 working_links;
u16 capabilities;
u32 signature;
u32 link_id;
u8 peer_id[16];
char peer_id_string[NODE_ID_STR_LEN];
struct list_head publ_list;
struct list_head conn_sks;
unsigned long keepalive_intv;
struct timer_list timer;
struct rcu_head rcu;
unsigned long delete_at;
struct net *peer_net;
u32 peer_hash_mix;
#ifdef CONFIG_TIPC_CRYPTO
struct tipc_crypto *crypto_rx;
#endif
};
/* Node FSM states and events:
*/
enum {
SELF_DOWN_PEER_DOWN = 0xdd,
SELF_UP_PEER_UP = 0xaa,
SELF_DOWN_PEER_LEAVING = 0xd1,
SELF_UP_PEER_COMING = 0xac,
SELF_COMING_PEER_UP = 0xca,
SELF_LEAVING_PEER_DOWN = 0x1d,
NODE_FAILINGOVER = 0xf0,
NODE_SYNCHING = 0xcc
};
enum {
SELF_ESTABL_CONTACT_EVT = 0xece,
SELF_LOST_CONTACT_EVT = 0x1ce,
PEER_ESTABL_CONTACT_EVT = 0x9ece,
PEER_LOST_CONTACT_EVT = 0x91ce,
NODE_FAILOVER_BEGIN_EVT = 0xfbe,
NODE_FAILOVER_END_EVT = 0xfee,
NODE_SYNCH_BEGIN_EVT = 0xcbe,
NODE_SYNCH_END_EVT = 0xcee
};
static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
struct sk_buff_head *xmitq,
struct tipc_media_addr **maddr);
static void tipc_node_link_down(struct tipc_node *n, int bearer_id,
bool delete);
static void node_lost_contact(struct tipc_node *n, struct sk_buff_head *inputq);
static void tipc_node_delete(struct tipc_node *node);
static void tipc_node_timeout(struct timer_list *t);
static void tipc_node_fsm_evt(struct tipc_node *n, int evt);
static struct tipc_node *tipc_node_find(struct net *net, u32 addr);
static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id);
static bool node_is_up(struct tipc_node *n);
static void tipc_node_delete_from_list(struct tipc_node *node);
struct tipc_sock_conn {
u32 port;
u32 peer_port;
u32 peer_node;
struct list_head list;
};
static struct tipc_link *node_active_link(struct tipc_node *n, int sel)
{
int bearer_id = n->active_links[sel & 1];
if (unlikely(bearer_id == INVALID_BEARER_ID))
return NULL;
return n->links[bearer_id].link;
}
int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel, bool connected)
{
struct tipc_node *n;
int bearer_id;
unsigned int mtu = MAX_MSG_SIZE;
n = tipc_node_find(net, addr);
if (unlikely(!n))
return mtu;
/* Allow MAX_MSG_SIZE when building connection oriented message
* if they are in the same core network
*/
if (n->peer_net && connected) {
tipc_node_put(n);
return mtu;
}
bearer_id = n->active_links[sel & 1];
if (likely(bearer_id != INVALID_BEARER_ID))
mtu = n->links[bearer_id].mtu;
tipc_node_put(n);
return mtu;
}
bool tipc_node_get_id(struct net *net, u32 addr, u8 *id)
{
u8 *own_id = tipc_own_id(net);
struct tipc_node *n;
if (!own_id)
return true;
if (addr == tipc_own_addr(net)) {
memcpy(id, own_id, TIPC_NODEID_LEN);
return true;
}
n = tipc_node_find(net, addr);
if (!n)
return false;
memcpy(id, &n->peer_id, TIPC_NODEID_LEN);
tipc_node_put(n);
return true;
}
u16 tipc_node_get_capabilities(struct net *net, u32 addr)
{
struct tipc_node *n;
u16 caps;
n = tipc_node_find(net, addr);
if (unlikely(!n))
return TIPC_NODE_CAPABILITIES;
caps = n->capabilities;
tipc_node_put(n);
return caps;
}
u32 tipc_node_get_addr(struct tipc_node *node)
{
return (node) ? node->addr : 0;
}
char *tipc_node_get_id_str(struct tipc_node *node)
{
return node->peer_id_string;
}
#ifdef CONFIG_TIPC_CRYPTO
/**
* tipc_node_crypto_rx - Retrieve crypto RX handle from node
* Note: node ref counter must be held first!
*/
struct tipc_crypto *tipc_node_crypto_rx(struct tipc_node *__n)
{
return (__n) ? __n->crypto_rx : NULL;
}
struct tipc_crypto *tipc_node_crypto_rx_by_list(struct list_head *pos)
{
return container_of(pos, struct tipc_node, list)->crypto_rx;
}
#endif
void tipc_node_free(struct rcu_head *rp)
{
struct tipc_node *n = container_of(rp, struct tipc_node, rcu);
#ifdef CONFIG_TIPC_CRYPTO
tipc_crypto_stop(&n->crypto_rx);
#endif
kfree(n);
}
static void tipc_node_kref_release(struct kref *kref)
{
struct tipc_node *n = container_of(kref, struct tipc_node, kref);
kfree(n->bc_entry.link);
call_rcu(&n->rcu, tipc_node_free);
}
void tipc_node_put(struct tipc_node *node)
{
kref_put(&node->kref, tipc_node_kref_release);
}
static void tipc_node_get(struct tipc_node *node)
{
kref_get(&node->kref);
}
/*
* tipc_node_find - locate specified node object, if it exists
*/
static struct tipc_node *tipc_node_find(struct net *net, u32 addr)
{
struct tipc_net *tn = tipc_net(net);
struct tipc_node *node;
unsigned int thash = tipc_hashfn(addr);
rcu_read_lock();
hlist_for_each_entry_rcu(node, &tn->node_htable[thash], hash) {
if (node->addr != addr || node->preliminary)
continue;
if (!kref_get_unless_zero(&node->kref))
node = NULL;
break;
}
rcu_read_unlock();
return node;
}
/* tipc_node_find_by_id - locate specified node object by its 128-bit id
* Note: this function is called only when a discovery request failed
* to find the node by its 32-bit id, and is not time critical
*/
static struct tipc_node *tipc_node_find_by_id(struct net *net, u8 *id)
{
struct tipc_net *tn = tipc_net(net);
struct tipc_node *n;
bool found = false;
rcu_read_lock();
list_for_each_entry_rcu(n, &tn->node_list, list) {
read_lock_bh(&n->lock);
if (!memcmp(id, n->peer_id, 16) &&
kref_get_unless_zero(&n->kref))
found = true;
read_unlock_bh(&n->lock);
if (found)
break;
}
rcu_read_unlock();
return found ? n : NULL;
}
static void tipc_node_read_lock(struct tipc_node *n)
{
read_lock_bh(&n->lock);
}
static void tipc_node_read_unlock(struct tipc_node *n)
{
read_unlock_bh(&n->lock);
}
static void tipc_node_write_lock(struct tipc_node *n)
{
write_lock_bh(&n->lock);
}
static void tipc_node_write_unlock_fast(struct tipc_node *n)
{
write_unlock_bh(&n->lock);
}
static void tipc_node_write_unlock(struct tipc_node *n)
{
struct net *net = n->net;
u32 addr = 0;
u32 flags = n->action_flags;
u32 link_id = 0;
u32 bearer_id;
struct list_head *publ_list;
if (likely(!flags)) {
write_unlock_bh(&n->lock);
return;
}
addr = n->addr;
link_id = n->link_id;
bearer_id = link_id & 0xffff;
publ_list = &n->publ_list;
n->action_flags &= ~(TIPC_NOTIFY_NODE_DOWN | TIPC_NOTIFY_NODE_UP |
TIPC_NOTIFY_LINK_DOWN | TIPC_NOTIFY_LINK_UP);
write_unlock_bh(&n->lock);
if (flags & TIPC_NOTIFY_NODE_DOWN)
tipc_publ_notify(net, publ_list, addr);
if (flags & TIPC_NOTIFY_NODE_UP)
tipc_named_node_up(net, addr);
if (flags & TIPC_NOTIFY_LINK_UP) {
tipc_mon_peer_up(net, addr, bearer_id);
tipc_nametbl_publish(net, TIPC_LINK_STATE, addr, addr,
TIPC_NODE_SCOPE, link_id, link_id);
}
if (flags & TIPC_NOTIFY_LINK_DOWN) {
tipc_mon_peer_down(net, addr, bearer_id);
tipc_nametbl_withdraw(net, TIPC_LINK_STATE, addr,
addr, link_id);
}
}
static void tipc_node_assign_peer_net(struct tipc_node *n, u32 hash_mixes)
{
int net_id = tipc_netid(n->net);
struct tipc_net *tn_peer;
struct net *tmp;
u32 hash_chk;
if (n->peer_net)
return;
for_each_net_rcu(tmp) {
tn_peer = tipc_net(tmp);
if (!tn_peer)
continue;
/* Integrity checking whether node exists in namespace or not */
if (tn_peer->net_id != net_id)
continue;
if (memcmp(n->peer_id, tn_peer->node_id, NODE_ID_LEN))
continue;
hash_chk = tipc_net_hash_mixes(tmp, tn_peer->random);
if (hash_mixes ^ hash_chk)
continue;
n->peer_net = tmp;
n->peer_hash_mix = hash_mixes;
break;
}
}
struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id,
u16 capabilities, u32 hash_mixes,
bool preliminary)
{
struct tipc_net *tn = net_generic(net, tipc_net_id);
struct tipc_node *n, *temp_node;
struct tipc_link *l;
unsigned long intv;
int bearer_id;
int i;
spin_lock_bh(&tn->node_list_lock);
n = tipc_node_find(net, addr) ?:
tipc_node_find_by_id(net, peer_id);
if (n) {
if (!n->preliminary)
goto update;
if (preliminary)
goto exit;
/* A preliminary node becomes "real" now, refresh its data */
tipc_node_write_lock(n);
n->preliminary = false;
n->addr = addr;
hlist_del_rcu(&n->hash);
hlist_add_head_rcu(&n->hash,
&tn->node_htable[tipc_hashfn(addr)]);
list_del_rcu(&n->list);
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
if (n->addr < temp_node->addr)
break;
}
list_add_tail_rcu(&n->list, &temp_node->list);
tipc_node_write_unlock_fast(n);
update:
if (n->peer_hash_mix ^ hash_mixes)
tipc_node_assign_peer_net(n, hash_mixes);
if (n->capabilities == capabilities)
goto exit;
/* Same node may come back with new capabilities */
tipc_node_write_lock(n);
n->capabilities = capabilities;
for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) {
l = n->links[bearer_id].link;
if (l)
tipc_link_update_caps(l, capabilities);
}
tipc_node_write_unlock_fast(n);
/* Calculate cluster capabilities */
tn->capabilities = TIPC_NODE_CAPABILITIES;
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
tn->capabilities &= temp_node->capabilities;
}
tipc_bcast_toggle_rcast(net,
(tn->capabilities & TIPC_BCAST_RCAST));
goto exit;
}
n = kzalloc(sizeof(*n), GFP_ATOMIC);
if (!n) {
pr_warn("Node creation failed, no memory\n");
goto exit;
}
tipc_nodeid2string(n->peer_id_string, peer_id);
#ifdef CONFIG_TIPC_CRYPTO
if (unlikely(tipc_crypto_start(&n->crypto_rx, net, n))) {
pr_warn("Failed to start crypto RX(%s)!\n", n->peer_id_string);
kfree(n);
n = NULL;
goto exit;
}
#endif
n->addr = addr;
n->preliminary = preliminary;
memcpy(&n->peer_id, peer_id, 16);
n->net = net;
n->peer_net = NULL;
n->peer_hash_mix = 0;
/* Assign kernel local namespace if exists */
tipc_node_assign_peer_net(n, hash_mixes);
n->capabilities = capabilities;
kref_init(&n->kref);
rwlock_init(&n->lock);
INIT_HLIST_NODE(&n->hash);
INIT_LIST_HEAD(&n->list);
INIT_LIST_HEAD(&n->publ_list);
INIT_LIST_HEAD(&n->conn_sks);
skb_queue_head_init(&n->bc_entry.namedq);
skb_queue_head_init(&n->bc_entry.inputq1);
__skb_queue_head_init(&n->bc_entry.arrvq);
skb_queue_head_init(&n->bc_entry.inputq2);
for (i = 0; i < MAX_BEARERS; i++)
spin_lock_init(&n->links[i].lock);
n->state = SELF_DOWN_PEER_LEAVING;
n->delete_at = jiffies + msecs_to_jiffies(NODE_CLEANUP_AFTER);
n->signature = INVALID_NODE_SIG;
n->active_links[0] = INVALID_BEARER_ID;
n->active_links[1] = INVALID_BEARER_ID;
n->bc_entry.link = NULL;
tipc_node_get(n);
timer_setup(&n->timer, tipc_node_timeout, 0);
/* Start a slow timer anyway, crypto needs it */
n->keepalive_intv = 10000;
intv = jiffies + msecs_to_jiffies(n->keepalive_intv);
if (!mod_timer(&n->timer, intv))
tipc_node_get(n);
hlist_add_head_rcu(&n->hash, &tn->node_htable[tipc_hashfn(addr)]);
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
if (n->addr < temp_node->addr)
break;
}
list_add_tail_rcu(&n->list, &temp_node->list);
/* Calculate cluster capabilities */
tn->capabilities = TIPC_NODE_CAPABILITIES;
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
tn->capabilities &= temp_node->capabilities;
}
tipc_bcast_toggle_rcast(net, (tn->capabilities & TIPC_BCAST_RCAST));
trace_tipc_node_create(n, true, " ");
exit:
spin_unlock_bh(&tn->node_list_lock);
return n;
}
static void tipc_node_calculate_timer(struct tipc_node *n, struct tipc_link *l)
{
unsigned long tol = tipc_link_tolerance(l);
unsigned long intv = ((tol / 4) > 500) ? 500 : tol / 4;
/* Link with lowest tolerance determines timer interval */
if (intv < n->keepalive_intv)
n->keepalive_intv = intv;
/* Ensure link's abort limit corresponds to current tolerance */
tipc_link_set_abort_limit(l, tol / n->keepalive_intv);
}
static void tipc_node_delete_from_list(struct tipc_node *node)
{
list_del_rcu(&node->list);
hlist_del_rcu(&node->hash);
tipc_node_put(node);
}
static void tipc_node_delete(struct tipc_node *node)
{
trace_tipc_node_delete(node, true, " ");
tipc_node_delete_from_list(node);
del_timer_sync(&node->timer);
tipc_node_put(node);
}
void tipc_node_stop(struct net *net)
{
struct tipc_net *tn = tipc_net(net);
struct tipc_node *node, *t_node;
spin_lock_bh(&tn->node_list_lock);
list_for_each_entry_safe(node, t_node, &tn->node_list, list)
tipc_node_delete(node);
spin_unlock_bh(&tn->node_list_lock);
}
void tipc_node_subscribe(struct net *net, struct list_head *subscr, u32 addr)
{
struct tipc_node *n;
if (in_own_node(net, addr))
return;
n = tipc_node_find(net, addr);
if (!n) {
pr_warn("Node subscribe rejected, unknown node 0x%x\n", addr);
return;
}
tipc_node_write_lock(n);
list_add_tail(subscr, &n->publ_list);
tipc_node_write_unlock_fast(n);
tipc_node_put(n);
}
void tipc_node_unsubscribe(struct net *net, struct list_head *subscr, u32 addr)
{
struct tipc_node *n;
if (in_own_node(net, addr))
return;
n = tipc_node_find(net, addr);
if (!n) {
pr_warn("Node unsubscribe rejected, unknown node 0x%x\n", addr);
return;
}
tipc_node_write_lock(n);
list_del_init(subscr);
tipc_node_write_unlock_fast(n);
tipc_node_put(n);
}
int tipc_node_add_conn(struct net *net, u32 dnode, u32 port, u32 peer_port)
{
struct tipc_node *node;
struct tipc_sock_conn *conn;
int err = 0;
if (in_own_node(net, dnode))
return 0;
node = tipc_node_find(net, dnode);
if (!node) {
pr_warn("Connecting sock to node 0x%x failed\n", dnode);
return -EHOSTUNREACH;
}
conn = kmalloc(sizeof(*conn), GFP_ATOMIC);
if (!conn) {
err = -EHOSTUNREACH;
goto exit;
}
conn->peer_node = dnode;
conn->port = port;
conn->peer_port = peer_port;
tipc_node_write_lock(node);
list_add_tail(&conn->list, &node->conn_sks);
tipc_node_write_unlock(node);
exit:
tipc_node_put(node);
return err;
}
void tipc_node_remove_conn(struct net *net, u32 dnode, u32 port)
{
struct tipc_node *node;
struct tipc_sock_conn *conn, *safe;
if (in_own_node(net, dnode))
return;
node = tipc_node_find(net, dnode);
if (!node)
return;
tipc_node_write_lock(node);
list_for_each_entry_safe(conn, safe, &node->conn_sks, list) {
if (port != conn->port)
continue;
list_del(&conn->list);
kfree(conn);
}
tipc_node_write_unlock(node);
tipc_node_put(node);
}
static void tipc_node_clear_links(struct tipc_node *node)
{
int i;
for (i = 0; i < MAX_BEARERS; i++) {
struct tipc_link_entry *le = &node->links[i];
if (le->link) {
kfree(le->link);
le->link = NULL;
node->link_cnt--;
}
}
}
/* tipc_node_cleanup - delete nodes that does not
* have active links for NODE_CLEANUP_AFTER time
*/
static bool tipc_node_cleanup(struct tipc_node *peer)
{
struct tipc_node *temp_node;
struct tipc_net *tn = tipc_net(peer->net);
bool deleted = false;
/* If lock held by tipc_node_stop() the node will be deleted anyway */
if (!spin_trylock_bh(&tn->node_list_lock))
return false;
tipc_node_write_lock(peer);
if (!node_is_up(peer) && time_after(jiffies, peer->delete_at)) {
tipc_node_clear_links(peer);
tipc_node_delete_from_list(peer);
deleted = true;
}
tipc_node_write_unlock(peer);
if (!deleted) {
spin_unlock_bh(&tn->node_list_lock);
return deleted;
}
/* Calculate cluster capabilities */
tn->capabilities = TIPC_NODE_CAPABILITIES;
list_for_each_entry_rcu(temp_node, &tn->node_list, list) {
tn->capabilities &= temp_node->capabilities;
}
tipc_bcast_toggle_rcast(peer->net,
(tn->capabilities & TIPC_BCAST_RCAST));
spin_unlock_bh(&tn->node_list_lock);
return deleted;
}
/* tipc_node_timeout - handle expiration of node timer
*/
static void tipc_node_timeout(struct timer_list *t)
{
struct tipc_node *n = from_timer(n, t, timer);
struct tipc_link_entry *le;
struct sk_buff_head xmitq;
int remains = n->link_cnt;
int bearer_id;
int rc = 0;
trace_tipc_node_timeout(n, false, " ");
if (!node_is_up(n) && tipc_node_cleanup(n)) {
/*Removing the reference of Timer*/
tipc_node_put(n);
return;
}
#ifdef CONFIG_TIPC_CRYPTO
/* Take any crypto key related actions first */
tipc_crypto_timeout(n->crypto_rx);
#endif
__skb_queue_head_init(&xmitq);
/* Initial node interval to value larger (10 seconds), then it will be
* recalculated with link lowest tolerance
*/
tipc_node_read_lock(n);
n->keepalive_intv = 10000;
tipc_node_read_unlock(n);
for (bearer_id = 0; remains && (bearer_id < MAX_BEARERS); bearer_id++) {
tipc_node_read_lock(n);
le = &n->links[bearer_id];
if (le->link) {
spin_lock_bh(&le->lock);
/* Link tolerance may change asynchronously: */
tipc_node_calculate_timer(n, le->link);
rc = tipc_link_timeout(le->link, &xmitq);
spin_unlock_bh(&le->lock);
remains--;
}
tipc_node_read_unlock(n);
tipc_bearer_xmit(n->net, bearer_id, &xmitq, &le->maddr, n);
if (rc & TIPC_LINK_DOWN_EVT)
tipc_node_link_down(n, bearer_id, false);
}
mod_timer(&n->timer, jiffies + msecs_to_jiffies(n->keepalive_intv));
}
/**
* __tipc_node_link_up - handle addition of link
* Node lock must be held by caller
* Link becomes active (alone or shared) or standby, depending on its priority.
*/
static void __tipc_node_link_up(struct tipc_node *n, int bearer_id,
struct sk_buff_head *xmitq)
{
int *slot0 = &n->active_links[0];
int *slot1 = &n->active_links[1];
struct tipc_link *ol = node_active_link(n, 0);
struct tipc_link *nl = n->links[bearer_id].link;
if (!nl || tipc_link_is_up(nl))
return;
tipc_link_fsm_evt(nl, LINK_ESTABLISH_EVT);
if (!tipc_link_is_up(nl))
return;
n->working_links++;
n->action_flags |= TIPC_NOTIFY_LINK_UP;
n->link_id = tipc_link_id(nl);
/* Leave room for tunnel header when returning 'mtu' to users: */
n->links[bearer_id].mtu = tipc_link_mss(nl);
tipc_bearer_add_dest(n->net, bearer_id, n->addr);
tipc_bcast_inc_bearer_dst_cnt(n->net, bearer_id);
pr_debug("Established link <%s> on network plane %c\n",
tipc_link_name(nl), tipc_link_plane(nl));
trace_tipc_node_link_up(n, true, " ");
/* Ensure that a STATE message goes first */
tipc_link_build_state_msg(nl, xmitq);
/* First link? => give it both slots */
if (!ol) {
*slot0 = bearer_id;
*slot1 = bearer_id;
tipc_node_fsm_evt(n, SELF_ESTABL_CONTACT_EVT);
n->action_flags |= TIPC_NOTIFY_NODE_UP;
tipc_link_set_active(nl, true);
tipc_bcast_add_peer(n->net, nl, xmitq);
return;
}
/* Second link => redistribute slots */
if (tipc_link_prio(nl) > tipc_link_prio(ol)) {
pr_debug("Old link <%s> becomes standby\n", tipc_link_name(ol));
*slot0 = bearer_id;
*slot1 = bearer_id;
tipc_link_set_active(nl, true);
tipc_link_set_active(ol, false);
} else if (tipc_link_prio(nl) == tipc_link_prio(ol)) {
tipc_link_set_active(nl, true);
*slot1 = bearer_id;
} else {
pr_debug("New link <%s> is standby\n", tipc_link_name(nl));
}
/* Prepare synchronization with first link */
tipc_link_tnl_prepare(ol, nl, SYNCH_MSG, xmitq);
}
/**
* tipc_node_link_up - handle addition of link
*
* Link becomes active (alone or shared) or standby, depending on its priority.
*/
static void tipc_node_link_up(struct tipc_node *n, int bearer_id,
struct sk_buff_head *xmitq)
{
struct tipc_media_addr *maddr;
tipc_node_write_lock(n);
__tipc_node_link_up(n, bearer_id, xmitq);
maddr = &n->links[bearer_id].maddr;
tipc_bearer_xmit(n->net, bearer_id, xmitq, maddr, n);
tipc_node_write_unlock(n);
}
/**
* tipc_node_link_failover() - start failover in case "half-failover"
*
* This function is only called in a very special situation where link
* failover can be already started on peer node but not on this node.
* This can happen when e.g.
* 1. Both links <1A-2A>, <1B-2B> down
* 2. Link endpoint 2A up, but 1A still down (e.g. due to network
* disturbance, wrong session, etc.)
* 3. Link <1B-2B> up
* 4. Link endpoint 2A down (e.g. due to link tolerance timeout)
* 5. Node 2 starts failover onto link <1B-2B>
*
* ==> Node 1 does never start link/node failover!
*
* @n: tipc node structure
* @l: link peer endpoint failingover (- can be NULL)
* @tnl: tunnel link
* @xmitq: queue for messages to be xmited on tnl link later
*/
static void tipc_node_link_failover(struct tipc_node *n, struct tipc_link *l,
struct tipc_link *tnl,
struct sk_buff_head *xmitq)
{
/* Avoid to be "self-failover" that can never end */
if (!tipc_link_is_up(tnl))
return;
/* Don't rush, failure link may be in the process of resetting */
if (l && !tipc_link_is_reset(l))
return;
tipc_link_fsm_evt(tnl, LINK_SYNCH_END_EVT);
tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT);
n->sync_point = tipc_link_rcv_nxt(tnl) + (U16_MAX / 2 - 1);
tipc_link_failover_prepare(l, tnl, xmitq);
if (l)
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);
tipc_node_fsm_evt(n, NODE_FAILOVER_BEGIN_EVT);
}
/**
* __tipc_node_link_down - handle loss of link
*/
static void __tipc_node_link_down(struct tipc_node *n, int *bearer_id,
struct sk_buff_head *xmitq,
struct tipc_media_addr **maddr)
{
struct tipc_link_entry *le = &n->links[*bearer_id];
int *slot0 = &n->active_links[0];
int *slot1 = &n->active_links[1];
int i, highest = 0, prio;
struct tipc_link *l, *_l, *tnl;
l = n->links[*bearer_id].link;
if (!l || tipc_link_is_reset(l))
return;
n->working_links--;
n->action_flags |= TIPC_NOTIFY_LINK_DOWN;
n->link_id = tipc_link_id(l);
tipc_bearer_remove_dest(n->net, *bearer_id, n->addr);
pr_debug("Lost link <%s> on network plane %c\n",
tipc_link_name(l), tipc_link_plane(l));
/* Select new active link if any available */
*slot0 = INVALID_BEARER_ID;
*slot1 = INVALID_BEARER_ID;
for (i = 0; i < MAX_BEARERS; i++) {
_l = n->links[i].link;
if (!_l || !tipc_link_is_up(_l))
continue;
if (_l == l)
continue;
prio = tipc_link_prio(_l);
if (prio < highest)
continue;
if (prio > highest) {
highest = prio;
*slot0 = i;
*slot1 = i;
continue;
}
*slot1 = i;
}
if (!node_is_up(n)) {
if (tipc_link_peer_is_down(l))
tipc_node_fsm_evt(n, PEER_LOST_CONTACT_EVT);
tipc_node_fsm_evt(n, SELF_LOST_CONTACT_EVT);
trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link down!");
tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_reset(l);
tipc_link_build_reset_msg(l, xmitq);
*maddr = &n->links[*bearer_id].maddr;
node_lost_contact(n, &le->inputq);
tipc_bcast_dec_bearer_dst_cnt(n->net, *bearer_id);
return;
}
tipc_bcast_dec_bearer_dst_cnt(n->net, *bearer_id);
/* There is still a working link => initiate failover */
*bearer_id = n->active_links[0];
tnl = n->links[*bearer_id].link;
tipc_link_fsm_evt(tnl, LINK_SYNCH_END_EVT);
tipc_node_fsm_evt(n, NODE_SYNCH_END_EVT);
n->sync_point = tipc_link_rcv_nxt(tnl) + (U16_MAX / 2 - 1);
tipc_link_tnl_prepare(l, tnl, FAILOVER_MSG, xmitq);
trace_tipc_link_reset(l, TIPC_DUMP_ALL, "link down -> failover!");
tipc_link_reset(l);
tipc_link_fsm_evt(l, LINK_RESET_EVT);
tipc_link_fsm_evt(l, LINK_FAILOVER_BEGIN_EVT);