forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
br_multicast.c
5119 lines (4340 loc) · 135 KB
/
br_multicast.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
/*
* Bridge multicast support.
*
* Copyright (c) 2010 Herbert Xu <[email protected]>
*/
#include <linux/err.h>
#include <linux/export.h>
#include <linux/if_ether.h>
#include <linux/igmp.h>
#include <linux/in.h>
#include <linux/jhash.h>
#include <linux/kernel.h>
#include <linux/log2.h>
#include <linux/netdevice.h>
#include <linux/netfilter_bridge.h>
#include <linux/random.h>
#include <linux/rculist.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/inetdevice.h>
#include <linux/mroute.h>
#include <net/ip.h>
#include <net/switchdev.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <linux/icmpv6.h>
#include <net/ipv6.h>
#include <net/mld.h>
#include <net/ip6_checksum.h>
#include <net/addrconf.h>
#endif
#include <trace/events/bridge.h>
#include "br_private.h"
#include "br_private_mcast_eht.h"
static const struct rhashtable_params br_mdb_rht_params = {
.head_offset = offsetof(struct net_bridge_mdb_entry, rhnode),
.key_offset = offsetof(struct net_bridge_mdb_entry, addr),
.key_len = sizeof(struct br_ip),
.automatic_shrinking = true,
};
static const struct rhashtable_params br_sg_port_rht_params = {
.head_offset = offsetof(struct net_bridge_port_group, rhnode),
.key_offset = offsetof(struct net_bridge_port_group, key),
.key_len = sizeof(struct net_bridge_port_group_sg_key),
.automatic_shrinking = true,
};
static void br_multicast_start_querier(struct net_bridge_mcast *brmctx,
struct bridge_mcast_own_query *query);
static void br_ip4_multicast_add_router(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx);
static void br_ip4_multicast_leave_group(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx,
__be32 group,
__u16 vid,
const unsigned char *src);
static void br_multicast_port_group_rexmit(struct timer_list *t);
static void
br_multicast_rport_del_notify(struct net_bridge_mcast_port *pmctx, bool deleted);
static void br_ip6_multicast_add_router(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx);
#if IS_ENABLED(CONFIG_IPV6)
static void br_ip6_multicast_leave_group(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx,
const struct in6_addr *group,
__u16 vid, const unsigned char *src);
#endif
static struct net_bridge_port_group *
__br_multicast_add_group(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx,
struct br_ip *group,
const unsigned char *src,
u8 filter_mode,
bool igmpv2_mldv1,
bool blocked);
static void br_multicast_find_del_pg(struct net_bridge *br,
struct net_bridge_port_group *pg);
static void __br_multicast_stop(struct net_bridge_mcast *brmctx);
static int br_mc_disabled_update(struct net_device *dev, bool value,
struct netlink_ext_ack *extack);
static struct net_bridge_port_group *
br_sg_port_find(struct net_bridge *br,
struct net_bridge_port_group_sg_key *sg_p)
{
lockdep_assert_held_once(&br->multicast_lock);
return rhashtable_lookup_fast(&br->sg_port_tbl, sg_p,
br_sg_port_rht_params);
}
static struct net_bridge_mdb_entry *br_mdb_ip_get_rcu(struct net_bridge *br,
struct br_ip *dst)
{
return rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params);
}
struct net_bridge_mdb_entry *br_mdb_ip_get(struct net_bridge *br,
struct br_ip *dst)
{
struct net_bridge_mdb_entry *ent;
lockdep_assert_held_once(&br->multicast_lock);
rcu_read_lock();
ent = rhashtable_lookup(&br->mdb_hash_tbl, dst, br_mdb_rht_params);
rcu_read_unlock();
return ent;
}
static struct net_bridge_mdb_entry *br_mdb_ip4_get(struct net_bridge *br,
__be32 dst, __u16 vid)
{
struct br_ip br_dst;
memset(&br_dst, 0, sizeof(br_dst));
br_dst.dst.ip4 = dst;
br_dst.proto = htons(ETH_P_IP);
br_dst.vid = vid;
return br_mdb_ip_get(br, &br_dst);
}
#if IS_ENABLED(CONFIG_IPV6)
static struct net_bridge_mdb_entry *br_mdb_ip6_get(struct net_bridge *br,
const struct in6_addr *dst,
__u16 vid)
{
struct br_ip br_dst;
memset(&br_dst, 0, sizeof(br_dst));
br_dst.dst.ip6 = *dst;
br_dst.proto = htons(ETH_P_IPV6);
br_dst.vid = vid;
return br_mdb_ip_get(br, &br_dst);
}
#endif
struct net_bridge_mdb_entry *br_mdb_get(struct net_bridge_mcast *brmctx,
struct sk_buff *skb, u16 vid)
{
struct net_bridge *br = brmctx->br;
struct br_ip ip;
if (!br_opt_get(br, BROPT_MULTICAST_ENABLED) ||
br_multicast_ctx_vlan_global_disabled(brmctx))
return NULL;
if (BR_INPUT_SKB_CB(skb)->igmp)
return NULL;
memset(&ip, 0, sizeof(ip));
ip.proto = skb->protocol;
ip.vid = vid;
switch (skb->protocol) {
case htons(ETH_P_IP):
ip.dst.ip4 = ip_hdr(skb)->daddr;
if (brmctx->multicast_igmp_version == 3) {
struct net_bridge_mdb_entry *mdb;
ip.src.ip4 = ip_hdr(skb)->saddr;
mdb = br_mdb_ip_get_rcu(br, &ip);
if (mdb)
return mdb;
ip.src.ip4 = 0;
}
break;
#if IS_ENABLED(CONFIG_IPV6)
case htons(ETH_P_IPV6):
ip.dst.ip6 = ipv6_hdr(skb)->daddr;
if (brmctx->multicast_mld_version == 2) {
struct net_bridge_mdb_entry *mdb;
ip.src.ip6 = ipv6_hdr(skb)->saddr;
mdb = br_mdb_ip_get_rcu(br, &ip);
if (mdb)
return mdb;
memset(&ip.src.ip6, 0, sizeof(ip.src.ip6));
}
break;
#endif
default:
ip.proto = 0;
ether_addr_copy(ip.dst.mac_addr, eth_hdr(skb)->h_dest);
}
return br_mdb_ip_get_rcu(br, &ip);
}
/* IMPORTANT: this function must be used only when the contexts cannot be
* passed down (e.g. timer) and must be used for read-only purposes because
* the vlan snooping option can change, so it can return any context
* (non-vlan or vlan). Its initial intended purpose is to read timer values
* from the *current* context based on the option. At worst that could lead
* to inconsistent timers when the contexts are changed, i.e. src timer
* which needs to re-arm with a specific delay taken from the old context
*/
static struct net_bridge_mcast_port *
br_multicast_pg_to_port_ctx(const struct net_bridge_port_group *pg)
{
struct net_bridge_mcast_port *pmctx = &pg->key.port->multicast_ctx;
struct net_bridge_vlan *vlan;
lockdep_assert_held_once(&pg->key.port->br->multicast_lock);
/* if vlan snooping is disabled use the port's multicast context */
if (!pg->key.addr.vid ||
!br_opt_get(pg->key.port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED))
goto out;
/* locking is tricky here, due to different rules for multicast and
* vlans we need to take rcu to find the vlan and make sure it has
* the BR_VLFLAG_MCAST_ENABLED flag set, it can only change under
* multicast_lock which must be already held here, so the vlan's pmctx
* can safely be used on return
*/
rcu_read_lock();
vlan = br_vlan_find(nbp_vlan_group_rcu(pg->key.port), pg->key.addr.vid);
if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx))
pmctx = &vlan->port_mcast_ctx;
else
pmctx = NULL;
rcu_read_unlock();
out:
return pmctx;
}
static struct net_bridge_mcast_port *
br_multicast_port_vid_to_port_ctx(struct net_bridge_port *port, u16 vid)
{
struct net_bridge_mcast_port *pmctx = NULL;
struct net_bridge_vlan *vlan;
lockdep_assert_held_once(&port->br->multicast_lock);
if (!br_opt_get(port->br, BROPT_MCAST_VLAN_SNOOPING_ENABLED))
return NULL;
/* Take RCU to access the vlan. */
rcu_read_lock();
vlan = br_vlan_find(nbp_vlan_group_rcu(port), vid);
if (vlan && !br_multicast_port_ctx_vlan_disabled(&vlan->port_mcast_ctx))
pmctx = &vlan->port_mcast_ctx;
rcu_read_unlock();
return pmctx;
}
/* when snooping we need to check if the contexts should be used
* in the following order:
* - if pmctx is non-NULL (port), check if it should be used
* - if pmctx is NULL (bridge), check if brmctx should be used
*/
static bool
br_multicast_ctx_should_use(const struct net_bridge_mcast *brmctx,
const struct net_bridge_mcast_port *pmctx)
{
if (!netif_running(brmctx->br->dev))
return false;
if (pmctx)
return !br_multicast_port_ctx_state_disabled(pmctx);
else
return !br_multicast_ctx_vlan_disabled(brmctx);
}
static bool br_port_group_equal(struct net_bridge_port_group *p,
struct net_bridge_port *port,
const unsigned char *src)
{
if (p->key.port != port)
return false;
if (!(port->flags & BR_MULTICAST_TO_UNICAST))
return true;
return ether_addr_equal(src, p->eth_addr);
}
static void __fwd_add_star_excl(struct net_bridge_mcast_port *pmctx,
struct net_bridge_port_group *pg,
struct br_ip *sg_ip)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge_port_group *src_pg;
struct net_bridge_mcast *brmctx;
memset(&sg_key, 0, sizeof(sg_key));
brmctx = br_multicast_port_ctx_get_global(pmctx);
sg_key.port = pg->key.port;
sg_key.addr = *sg_ip;
if (br_sg_port_find(brmctx->br, &sg_key))
return;
src_pg = __br_multicast_add_group(brmctx, pmctx,
sg_ip, pg->eth_addr,
MCAST_INCLUDE, false, false);
if (IS_ERR_OR_NULL(src_pg) ||
src_pg->rt_protocol != RTPROT_KERNEL)
return;
src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
}
static void __fwd_del_star_excl(struct net_bridge_port_group *pg,
struct br_ip *sg_ip)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge *br = pg->key.port->br;
struct net_bridge_port_group *src_pg;
memset(&sg_key, 0, sizeof(sg_key));
sg_key.port = pg->key.port;
sg_key.addr = *sg_ip;
src_pg = br_sg_port_find(br, &sg_key);
if (!src_pg || !(src_pg->flags & MDB_PG_FLAGS_STAR_EXCL) ||
src_pg->rt_protocol != RTPROT_KERNEL)
return;
br_multicast_find_del_pg(br, src_pg);
}
/* When a port group transitions to (or is added as) EXCLUDE we need to add it
* to all other ports' S,G entries which are not blocked by the current group
* for proper replication, the assumption is that any S,G blocked entries
* are already added so the S,G,port lookup should skip them.
* When a port group transitions from EXCLUDE -> INCLUDE mode or is being
* deleted we need to remove it from all ports' S,G entries where it was
* automatically installed before (i.e. where it's MDB_PG_FLAGS_STAR_EXCL).
*/
void br_multicast_star_g_handle_mode(struct net_bridge_port_group *pg,
u8 filter_mode)
{
struct net_bridge *br = pg->key.port->br;
struct net_bridge_port_group *pg_lst;
struct net_bridge_mcast_port *pmctx;
struct net_bridge_mdb_entry *mp;
struct br_ip sg_ip;
if (WARN_ON(!br_multicast_is_star_g(&pg->key.addr)))
return;
mp = br_mdb_ip_get(br, &pg->key.addr);
if (!mp)
return;
pmctx = br_multicast_pg_to_port_ctx(pg);
if (!pmctx)
return;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = pg->key.addr;
for (pg_lst = mlock_dereference(mp->ports, br);
pg_lst;
pg_lst = mlock_dereference(pg_lst->next, br)) {
struct net_bridge_group_src *src_ent;
if (pg_lst == pg)
continue;
hlist_for_each_entry(src_ent, &pg_lst->src_list, node) {
if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
continue;
sg_ip.src = src_ent->addr.src;
switch (filter_mode) {
case MCAST_INCLUDE:
__fwd_del_star_excl(pg, &sg_ip);
break;
case MCAST_EXCLUDE:
__fwd_add_star_excl(pmctx, pg, &sg_ip);
break;
}
}
}
}
/* called when adding a new S,G with host_joined == false by default */
static void br_multicast_sg_host_state(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg)
{
struct net_bridge_mdb_entry *sg_mp;
if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
return;
if (!star_mp->host_joined)
return;
sg_mp = br_mdb_ip_get(star_mp->br, &sg->key.addr);
if (!sg_mp)
return;
sg_mp->host_joined = true;
}
/* set the host_joined state of all of *,G's S,G entries */
static void br_multicast_star_g_host_state(struct net_bridge_mdb_entry *star_mp)
{
struct net_bridge *br = star_mp->br;
struct net_bridge_mdb_entry *sg_mp;
struct net_bridge_port_group *pg;
struct br_ip sg_ip;
if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
return;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = star_mp->addr;
for (pg = mlock_dereference(star_mp->ports, br);
pg;
pg = mlock_dereference(pg->next, br)) {
struct net_bridge_group_src *src_ent;
hlist_for_each_entry(src_ent, &pg->src_list, node) {
if (!(src_ent->flags & BR_SGRP_F_INSTALLED))
continue;
sg_ip.src = src_ent->addr.src;
sg_mp = br_mdb_ip_get(br, &sg_ip);
if (!sg_mp)
continue;
sg_mp->host_joined = star_mp->host_joined;
}
}
}
static void br_multicast_sg_del_exclude_ports(struct net_bridge_mdb_entry *sgmp)
{
struct net_bridge_port_group __rcu **pp;
struct net_bridge_port_group *p;
/* *,G exclude ports are only added to S,G entries */
if (WARN_ON(br_multicast_is_star_g(&sgmp->addr)))
return;
/* we need the STAR_EXCLUDE ports if there are non-STAR_EXCLUDE ports
* we should ignore perm entries since they're managed by user-space
*/
for (pp = &sgmp->ports;
(p = mlock_dereference(*pp, sgmp->br)) != NULL;
pp = &p->next)
if (!(p->flags & (MDB_PG_FLAGS_STAR_EXCL |
MDB_PG_FLAGS_PERMANENT)))
return;
/* currently the host can only have joined the *,G which means
* we treat it as EXCLUDE {}, so for an S,G it's considered a
* STAR_EXCLUDE entry and we can safely leave it
*/
sgmp->host_joined = false;
for (pp = &sgmp->ports;
(p = mlock_dereference(*pp, sgmp->br)) != NULL;) {
if (!(p->flags & MDB_PG_FLAGS_PERMANENT))
br_multicast_del_pg(sgmp, p, pp);
else
pp = &p->next;
}
}
void br_multicast_sg_add_exclude_ports(struct net_bridge_mdb_entry *star_mp,
struct net_bridge_port_group *sg)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge *br = star_mp->br;
struct net_bridge_mcast_port *pmctx;
struct net_bridge_port_group *pg;
struct net_bridge_mcast *brmctx;
if (WARN_ON(br_multicast_is_star_g(&sg->key.addr)))
return;
if (WARN_ON(!br_multicast_is_star_g(&star_mp->addr)))
return;
br_multicast_sg_host_state(star_mp, sg);
memset(&sg_key, 0, sizeof(sg_key));
sg_key.addr = sg->key.addr;
/* we need to add all exclude ports to the S,G */
for (pg = mlock_dereference(star_mp->ports, br);
pg;
pg = mlock_dereference(pg->next, br)) {
struct net_bridge_port_group *src_pg;
if (pg == sg || pg->filter_mode == MCAST_INCLUDE)
continue;
sg_key.port = pg->key.port;
if (br_sg_port_find(br, &sg_key))
continue;
pmctx = br_multicast_pg_to_port_ctx(pg);
if (!pmctx)
continue;
brmctx = br_multicast_port_ctx_get_global(pmctx);
src_pg = __br_multicast_add_group(brmctx, pmctx,
&sg->key.addr,
sg->eth_addr,
MCAST_INCLUDE, false, false);
if (IS_ERR_OR_NULL(src_pg) ||
src_pg->rt_protocol != RTPROT_KERNEL)
continue;
src_pg->flags |= MDB_PG_FLAGS_STAR_EXCL;
}
}
static void br_multicast_fwd_src_add(struct net_bridge_group_src *src)
{
struct net_bridge_mdb_entry *star_mp;
struct net_bridge_mcast_port *pmctx;
struct net_bridge_port_group *sg;
struct net_bridge_mcast *brmctx;
struct br_ip sg_ip;
if (src->flags & BR_SGRP_F_INSTALLED)
return;
memset(&sg_ip, 0, sizeof(sg_ip));
pmctx = br_multicast_pg_to_port_ctx(src->pg);
if (!pmctx)
return;
brmctx = br_multicast_port_ctx_get_global(pmctx);
sg_ip = src->pg->key.addr;
sg_ip.src = src->addr.src;
sg = __br_multicast_add_group(brmctx, pmctx, &sg_ip,
src->pg->eth_addr, MCAST_INCLUDE, false,
!timer_pending(&src->timer));
if (IS_ERR_OR_NULL(sg))
return;
src->flags |= BR_SGRP_F_INSTALLED;
sg->flags &= ~MDB_PG_FLAGS_STAR_EXCL;
/* if it was added by user-space as perm we can skip next steps */
if (sg->rt_protocol != RTPROT_KERNEL &&
(sg->flags & MDB_PG_FLAGS_PERMANENT))
return;
/* the kernel is now responsible for removing this S,G */
del_timer(&sg->timer);
star_mp = br_mdb_ip_get(src->br, &src->pg->key.addr);
if (!star_mp)
return;
br_multicast_sg_add_exclude_ports(star_mp, sg);
}
static void br_multicast_fwd_src_remove(struct net_bridge_group_src *src,
bool fastleave)
{
struct net_bridge_port_group *p, *pg = src->pg;
struct net_bridge_port_group __rcu **pp;
struct net_bridge_mdb_entry *mp;
struct br_ip sg_ip;
memset(&sg_ip, 0, sizeof(sg_ip));
sg_ip = pg->key.addr;
sg_ip.src = src->addr.src;
mp = br_mdb_ip_get(src->br, &sg_ip);
if (!mp)
return;
for (pp = &mp->ports;
(p = mlock_dereference(*pp, src->br)) != NULL;
pp = &p->next) {
if (!br_port_group_equal(p, pg->key.port, pg->eth_addr))
continue;
if (p->rt_protocol != RTPROT_KERNEL &&
(p->flags & MDB_PG_FLAGS_PERMANENT) &&
!(src->flags & BR_SGRP_F_USER_ADDED))
break;
if (fastleave)
p->flags |= MDB_PG_FLAGS_FAST_LEAVE;
br_multicast_del_pg(mp, p, pp);
break;
}
src->flags &= ~BR_SGRP_F_INSTALLED;
}
/* install S,G and based on src's timer enable or disable forwarding */
static void br_multicast_fwd_src_handle(struct net_bridge_group_src *src)
{
struct net_bridge_port_group_sg_key sg_key;
struct net_bridge_port_group *sg;
u8 old_flags;
br_multicast_fwd_src_add(src);
memset(&sg_key, 0, sizeof(sg_key));
sg_key.addr = src->pg->key.addr;
sg_key.addr.src = src->addr.src;
sg_key.port = src->pg->key.port;
sg = br_sg_port_find(src->br, &sg_key);
if (!sg || (sg->flags & MDB_PG_FLAGS_PERMANENT))
return;
old_flags = sg->flags;
if (timer_pending(&src->timer))
sg->flags &= ~MDB_PG_FLAGS_BLOCKED;
else
sg->flags |= MDB_PG_FLAGS_BLOCKED;
if (old_flags != sg->flags) {
struct net_bridge_mdb_entry *sg_mp;
sg_mp = br_mdb_ip_get(src->br, &sg_key.addr);
if (!sg_mp)
return;
br_mdb_notify(src->br->dev, sg_mp, sg, RTM_NEWMDB);
}
}
static void br_multicast_destroy_mdb_entry(struct net_bridge_mcast_gc *gc)
{
struct net_bridge_mdb_entry *mp;
mp = container_of(gc, struct net_bridge_mdb_entry, mcast_gc);
WARN_ON(!hlist_unhashed(&mp->mdb_node));
WARN_ON(mp->ports);
timer_shutdown_sync(&mp->timer);
kfree_rcu(mp, rcu);
}
static void br_multicast_del_mdb_entry(struct net_bridge_mdb_entry *mp)
{
struct net_bridge *br = mp->br;
rhashtable_remove_fast(&br->mdb_hash_tbl, &mp->rhnode,
br_mdb_rht_params);
hlist_del_init_rcu(&mp->mdb_node);
hlist_add_head(&mp->mcast_gc.gc_node, &br->mcast_gc_list);
queue_work(system_long_wq, &br->mcast_gc_work);
}
static void br_multicast_group_expired(struct timer_list *t)
{
struct net_bridge_mdb_entry *mp = from_timer(mp, t, timer);
struct net_bridge *br = mp->br;
spin_lock(&br->multicast_lock);
if (hlist_unhashed(&mp->mdb_node) || !netif_running(br->dev) ||
timer_pending(&mp->timer))
goto out;
br_multicast_host_leave(mp, true);
if (mp->ports)
goto out;
br_multicast_del_mdb_entry(mp);
out:
spin_unlock(&br->multicast_lock);
}
static void br_multicast_destroy_group_src(struct net_bridge_mcast_gc *gc)
{
struct net_bridge_group_src *src;
src = container_of(gc, struct net_bridge_group_src, mcast_gc);
WARN_ON(!hlist_unhashed(&src->node));
timer_shutdown_sync(&src->timer);
kfree_rcu(src, rcu);
}
void __br_multicast_del_group_src(struct net_bridge_group_src *src)
{
struct net_bridge *br = src->pg->key.port->br;
hlist_del_init_rcu(&src->node);
src->pg->src_ents--;
hlist_add_head(&src->mcast_gc.gc_node, &br->mcast_gc_list);
queue_work(system_long_wq, &br->mcast_gc_work);
}
void br_multicast_del_group_src(struct net_bridge_group_src *src,
bool fastleave)
{
br_multicast_fwd_src_remove(src, fastleave);
__br_multicast_del_group_src(src);
}
static int
br_multicast_port_ngroups_inc_one(struct net_bridge_mcast_port *pmctx,
struct netlink_ext_ack *extack,
const char *what)
{
u32 max = READ_ONCE(pmctx->mdb_max_entries);
u32 n = READ_ONCE(pmctx->mdb_n_entries);
if (max && n >= max) {
NL_SET_ERR_MSG_FMT_MOD(extack, "%s is already in %u groups, and mcast_max_groups=%u",
what, n, max);
return -E2BIG;
}
WRITE_ONCE(pmctx->mdb_n_entries, n + 1);
return 0;
}
static void br_multicast_port_ngroups_dec_one(struct net_bridge_mcast_port *pmctx)
{
u32 n = READ_ONCE(pmctx->mdb_n_entries);
WARN_ON_ONCE(n == 0);
WRITE_ONCE(pmctx->mdb_n_entries, n - 1);
}
static int br_multicast_port_ngroups_inc(struct net_bridge_port *port,
const struct br_ip *group,
struct netlink_ext_ack *extack)
{
struct net_bridge_mcast_port *pmctx;
int err;
lockdep_assert_held_once(&port->br->multicast_lock);
/* Always count on the port context. */
err = br_multicast_port_ngroups_inc_one(&port->multicast_ctx, extack,
"Port");
if (err) {
trace_br_mdb_full(port->dev, group);
return err;
}
/* Only count on the VLAN context if VID is given, and if snooping on
* that VLAN is enabled.
*/
if (!group->vid)
return 0;
pmctx = br_multicast_port_vid_to_port_ctx(port, group->vid);
if (!pmctx)
return 0;
err = br_multicast_port_ngroups_inc_one(pmctx, extack, "Port-VLAN");
if (err) {
trace_br_mdb_full(port->dev, group);
goto dec_one_out;
}
return 0;
dec_one_out:
br_multicast_port_ngroups_dec_one(&port->multicast_ctx);
return err;
}
static void br_multicast_port_ngroups_dec(struct net_bridge_port *port, u16 vid)
{
struct net_bridge_mcast_port *pmctx;
lockdep_assert_held_once(&port->br->multicast_lock);
if (vid) {
pmctx = br_multicast_port_vid_to_port_ctx(port, vid);
if (pmctx)
br_multicast_port_ngroups_dec_one(pmctx);
}
br_multicast_port_ngroups_dec_one(&port->multicast_ctx);
}
u32 br_multicast_ngroups_get(const struct net_bridge_mcast_port *pmctx)
{
return READ_ONCE(pmctx->mdb_n_entries);
}
void br_multicast_ngroups_set_max(struct net_bridge_mcast_port *pmctx, u32 max)
{
WRITE_ONCE(pmctx->mdb_max_entries, max);
}
u32 br_multicast_ngroups_get_max(const struct net_bridge_mcast_port *pmctx)
{
return READ_ONCE(pmctx->mdb_max_entries);
}
static void br_multicast_destroy_port_group(struct net_bridge_mcast_gc *gc)
{
struct net_bridge_port_group *pg;
pg = container_of(gc, struct net_bridge_port_group, mcast_gc);
WARN_ON(!hlist_unhashed(&pg->mglist));
WARN_ON(!hlist_empty(&pg->src_list));
timer_shutdown_sync(&pg->rexmit_timer);
timer_shutdown_sync(&pg->timer);
kfree_rcu(pg, rcu);
}
void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
struct net_bridge_port_group *pg,
struct net_bridge_port_group __rcu **pp)
{
struct net_bridge *br = pg->key.port->br;
struct net_bridge_group_src *ent;
struct hlist_node *tmp;
rcu_assign_pointer(*pp, pg->next);
hlist_del_init(&pg->mglist);
br_multicast_eht_clean_sets(pg);
hlist_for_each_entry_safe(ent, tmp, &pg->src_list, node)
br_multicast_del_group_src(ent, false);
br_mdb_notify(br->dev, mp, pg, RTM_DELMDB);
if (!br_multicast_is_star_g(&mp->addr)) {
rhashtable_remove_fast(&br->sg_port_tbl, &pg->rhnode,
br_sg_port_rht_params);
br_multicast_sg_del_exclude_ports(mp);
} else {
br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
}
br_multicast_port_ngroups_dec(pg->key.port, pg->key.addr.vid);
hlist_add_head(&pg->mcast_gc.gc_node, &br->mcast_gc_list);
queue_work(system_long_wq, &br->mcast_gc_work);
if (!mp->ports && !mp->host_joined && netif_running(br->dev))
mod_timer(&mp->timer, jiffies);
}
static void br_multicast_find_del_pg(struct net_bridge *br,
struct net_bridge_port_group *pg)
{
struct net_bridge_port_group __rcu **pp;
struct net_bridge_mdb_entry *mp;
struct net_bridge_port_group *p;
mp = br_mdb_ip_get(br, &pg->key.addr);
if (WARN_ON(!mp))
return;
for (pp = &mp->ports;
(p = mlock_dereference(*pp, br)) != NULL;
pp = &p->next) {
if (p != pg)
continue;
br_multicast_del_pg(mp, pg, pp);
return;
}
WARN_ON(1);
}
static void br_multicast_port_group_expired(struct timer_list *t)
{
struct net_bridge_port_group *pg = from_timer(pg, t, timer);
struct net_bridge_group_src *src_ent;
struct net_bridge *br = pg->key.port->br;
struct hlist_node *tmp;
bool changed;
spin_lock(&br->multicast_lock);
if (!netif_running(br->dev) || timer_pending(&pg->timer) ||
hlist_unhashed(&pg->mglist) || pg->flags & MDB_PG_FLAGS_PERMANENT)
goto out;
changed = !!(pg->filter_mode == MCAST_EXCLUDE);
pg->filter_mode = MCAST_INCLUDE;
hlist_for_each_entry_safe(src_ent, tmp, &pg->src_list, node) {
if (!timer_pending(&src_ent->timer)) {
br_multicast_del_group_src(src_ent, false);
changed = true;
}
}
if (hlist_empty(&pg->src_list)) {
br_multicast_find_del_pg(br, pg);
} else if (changed) {
struct net_bridge_mdb_entry *mp = br_mdb_ip_get(br, &pg->key.addr);
if (changed && br_multicast_is_star_g(&pg->key.addr))
br_multicast_star_g_handle_mode(pg, MCAST_INCLUDE);
if (WARN_ON(!mp))
goto out;
br_mdb_notify(br->dev, mp, pg, RTM_NEWMDB);
}
out:
spin_unlock(&br->multicast_lock);
}
static void br_multicast_gc(struct hlist_head *head)
{
struct net_bridge_mcast_gc *gcent;
struct hlist_node *tmp;
hlist_for_each_entry_safe(gcent, tmp, head, gc_node) {
hlist_del_init(&gcent->gc_node);
gcent->destroy(gcent);
}
}
static void __br_multicast_query_handle_vlan(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx,
struct sk_buff *skb)
{
struct net_bridge_vlan *vlan = NULL;
if (pmctx && br_multicast_port_ctx_is_vlan(pmctx))
vlan = pmctx->vlan;
else if (br_multicast_ctx_is_vlan(brmctx))
vlan = brmctx->vlan;
if (vlan && !(vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED)) {
u16 vlan_proto;
if (br_vlan_get_proto(brmctx->br->dev, &vlan_proto) != 0)
return;
__vlan_hwaccel_put_tag(skb, htons(vlan_proto), vlan->vid);
}
}
static struct sk_buff *br_ip4_multicast_alloc_query(struct net_bridge_mcast *brmctx,
struct net_bridge_mcast_port *pmctx,
struct net_bridge_port_group *pg,
__be32 ip_dst, __be32 group,
bool with_srcs, bool over_lmqt,
u8 sflag, u8 *igmp_type,
bool *need_rexmit)
{
struct net_bridge_port *p = pg ? pg->key.port : NULL;
struct net_bridge_group_src *ent;
size_t pkt_size, igmp_hdr_size;
unsigned long now = jiffies;
struct igmpv3_query *ihv3;
void *csum_start = NULL;
__sum16 *csum = NULL;
struct sk_buff *skb;
struct igmphdr *ih;
struct ethhdr *eth;
unsigned long lmqt;
struct iphdr *iph;
u16 lmqt_srcs = 0;
igmp_hdr_size = sizeof(*ih);
if (brmctx->multicast_igmp_version == 3) {
igmp_hdr_size = sizeof(*ihv3);
if (pg && with_srcs) {
lmqt = now + (brmctx->multicast_last_member_interval *
brmctx->multicast_last_member_count);
hlist_for_each_entry(ent, &pg->src_list, node) {
if (over_lmqt == time_after(ent->timer.expires,
lmqt) &&
ent->src_query_rexmit_cnt > 0)
lmqt_srcs++;
}
if (!lmqt_srcs)
return NULL;
igmp_hdr_size += lmqt_srcs * sizeof(__be32);
}
}
pkt_size = sizeof(*eth) + sizeof(*iph) + 4 + igmp_hdr_size;
if ((p && pkt_size > p->dev->mtu) ||
pkt_size > brmctx->br->dev->mtu)
return NULL;
skb = netdev_alloc_skb_ip_align(brmctx->br->dev, pkt_size);
if (!skb)
goto out;
__br_multicast_query_handle_vlan(brmctx, pmctx, skb);
skb->protocol = htons(ETH_P_IP);
skb_reset_mac_header(skb);
eth = eth_hdr(skb);
ether_addr_copy(eth->h_source, brmctx->br->dev->dev_addr);
ip_eth_mc_map(ip_dst, eth->h_dest);
eth->h_proto = htons(ETH_P_IP);
skb_put(skb, sizeof(*eth));
skb_set_network_header(skb, skb->len);
iph = ip_hdr(skb);
iph->tot_len = htons(pkt_size - sizeof(*eth));
iph->version = 4;
iph->ihl = 6;
iph->tos = 0xc0;
iph->id = 0;
iph->frag_off = htons(IP_DF);
iph->ttl = 1;
iph->protocol = IPPROTO_IGMP;
iph->saddr = br_opt_get(brmctx->br, BROPT_MULTICAST_QUERY_USE_IFADDR) ?
inet_select_addr(brmctx->br->dev, 0, RT_SCOPE_LINK) : 0;
iph->daddr = ip_dst;
((u8 *)&iph[1])[0] = IPOPT_RA;