forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 17
/
nexthop.c
1828 lines (1499 loc) · 40.1 KB
/
nexthop.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
/* Generic nexthop implementation
*
* Copyright (c) 2017-19 Cumulus Networks
* Copyright (c) 2017-19 David Ahern <[email protected]>
*/
#include <linux/nexthop.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <net/arp.h>
#include <net/ipv6_stubs.h>
#include <net/lwtunnel.h>
#include <net/ndisc.h>
#include <net/nexthop.h>
#include <net/route.h>
#include <net/sock.h>
static void remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo);
#define NH_DEV_HASHBITS 8
#define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS)
static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = {
[NHA_UNSPEC] = { .strict_start_type = NHA_UNSPEC + 1 },
[NHA_ID] = { .type = NLA_U32 },
[NHA_GROUP] = { .type = NLA_BINARY },
[NHA_GROUP_TYPE] = { .type = NLA_U16 },
[NHA_BLACKHOLE] = { .type = NLA_FLAG },
[NHA_OIF] = { .type = NLA_U32 },
[NHA_GATEWAY] = { .type = NLA_BINARY },
[NHA_ENCAP_TYPE] = { .type = NLA_U16 },
[NHA_ENCAP] = { .type = NLA_NESTED },
[NHA_GROUPS] = { .type = NLA_FLAG },
[NHA_MASTER] = { .type = NLA_U32 },
};
static unsigned int nh_dev_hashfn(unsigned int val)
{
unsigned int mask = NH_DEV_HASHSIZE - 1;
return (val ^
(val >> NH_DEV_HASHBITS) ^
(val >> (NH_DEV_HASHBITS * 2))) & mask;
}
static void nexthop_devhash_add(struct net *net, struct nh_info *nhi)
{
struct net_device *dev = nhi->fib_nhc.nhc_dev;
struct hlist_head *head;
unsigned int hash;
WARN_ON(!dev);
hash = nh_dev_hashfn(dev->ifindex);
head = &net->nexthop.devhash[hash];
hlist_add_head(&nhi->dev_hash, head);
}
static void nexthop_free_mpath(struct nexthop *nh)
{
struct nh_group *nhg;
int i;
nhg = rcu_dereference_raw(nh->nh_grp);
for (i = 0; i < nhg->num_nh; ++i)
WARN_ON(nhg->nh_entries[i].nh);
kfree(nhg);
}
static void nexthop_free_single(struct nexthop *nh)
{
struct nh_info *nhi;
nhi = rcu_dereference_raw(nh->nh_info);
switch (nhi->family) {
case AF_INET:
fib_nh_release(nh->net, &nhi->fib_nh);
break;
case AF_INET6:
ipv6_stub->fib6_nh_release(&nhi->fib6_nh);
break;
}
kfree(nhi);
}
void nexthop_free_rcu(struct rcu_head *head)
{
struct nexthop *nh = container_of(head, struct nexthop, rcu);
if (nh->is_group)
nexthop_free_mpath(nh);
else
nexthop_free_single(nh);
kfree(nh);
}
EXPORT_SYMBOL_GPL(nexthop_free_rcu);
static struct nexthop *nexthop_alloc(void)
{
struct nexthop *nh;
nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL);
if (nh) {
INIT_LIST_HEAD(&nh->fi_list);
INIT_LIST_HEAD(&nh->f6i_list);
INIT_LIST_HEAD(&nh->grp_list);
}
return nh;
}
static struct nh_group *nexthop_grp_alloc(u16 num_nh)
{
size_t sz = offsetof(struct nexthop, nh_grp)
+ sizeof(struct nh_group)
+ sizeof(struct nh_grp_entry) * num_nh;
struct nh_group *nhg;
nhg = kzalloc(sz, GFP_KERNEL);
if (nhg)
nhg->num_nh = num_nh;
return nhg;
}
static void nh_base_seq_inc(struct net *net)
{
while (++net->nexthop.seq == 0)
;
}
/* no reference taken; rcu lock or rtnl must be held */
struct nexthop *nexthop_find_by_id(struct net *net, u32 id)
{
struct rb_node **pp, *parent = NULL, *next;
pp = &net->nexthop.rb_root.rb_node;
while (1) {
struct nexthop *nh;
next = rcu_dereference_raw(*pp);
if (!next)
break;
parent = next;
nh = rb_entry(parent, struct nexthop, rb_node);
if (id < nh->id)
pp = &next->rb_left;
else if (id > nh->id)
pp = &next->rb_right;
else
return nh;
}
return NULL;
}
EXPORT_SYMBOL_GPL(nexthop_find_by_id);
/* used for auto id allocation; called with rtnl held */
static u32 nh_find_unused_id(struct net *net)
{
u32 id_start = net->nexthop.last_id_allocated;
while (1) {
net->nexthop.last_id_allocated++;
if (net->nexthop.last_id_allocated == id_start)
break;
if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated))
return net->nexthop.last_id_allocated;
}
return 0;
}
static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg)
{
struct nexthop_grp *p;
size_t len = nhg->num_nh * sizeof(*p);
struct nlattr *nla;
u16 group_type = 0;
int i;
if (nhg->mpath)
group_type = NEXTHOP_GRP_TYPE_MPATH;
if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type))
goto nla_put_failure;
nla = nla_reserve(skb, NHA_GROUP, len);
if (!nla)
goto nla_put_failure;
p = nla_data(nla);
for (i = 0; i < nhg->num_nh; ++i) {
p->id = nhg->nh_entries[i].nh->id;
p->weight = nhg->nh_entries[i].weight - 1;
p += 1;
}
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh,
int event, u32 portid, u32 seq, unsigned int nlflags)
{
struct fib6_nh *fib6_nh;
struct fib_nh *fib_nh;
struct nlmsghdr *nlh;
struct nh_info *nhi;
struct nhmsg *nhm;
nlh = nlmsg_put(skb, portid, seq, event, sizeof(*nhm), nlflags);
if (!nlh)
return -EMSGSIZE;
nhm = nlmsg_data(nlh);
nhm->nh_family = AF_UNSPEC;
nhm->nh_flags = nh->nh_flags;
nhm->nh_protocol = nh->protocol;
nhm->nh_scope = 0;
nhm->resvd = 0;
if (nla_put_u32(skb, NHA_ID, nh->id))
goto nla_put_failure;
if (nh->is_group) {
struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
if (nla_put_nh_group(skb, nhg))
goto nla_put_failure;
goto out;
}
nhi = rtnl_dereference(nh->nh_info);
nhm->nh_family = nhi->family;
if (nhi->reject_nh) {
if (nla_put_flag(skb, NHA_BLACKHOLE))
goto nla_put_failure;
goto out;
} else {
const struct net_device *dev;
dev = nhi->fib_nhc.nhc_dev;
if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex))
goto nla_put_failure;
}
nhm->nh_scope = nhi->fib_nhc.nhc_scope;
switch (nhi->family) {
case AF_INET:
fib_nh = &nhi->fib_nh;
if (fib_nh->fib_nh_gw_family &&
nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4))
goto nla_put_failure;
break;
case AF_INET6:
fib6_nh = &nhi->fib6_nh;
if (fib6_nh->fib_nh_gw_family &&
nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6))
goto nla_put_failure;
break;
}
if (nhi->fib_nhc.nhc_lwtstate &&
lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate,
NHA_ENCAP, NHA_ENCAP_TYPE) < 0)
goto nla_put_failure;
out:
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
return -EMSGSIZE;
}
static size_t nh_nlmsg_size_grp(struct nexthop *nh)
{
struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh;
return nla_total_size(sz) +
nla_total_size(2); /* NHA_GROUP_TYPE */
}
static size_t nh_nlmsg_size_single(struct nexthop *nh)
{
struct nh_info *nhi = rtnl_dereference(nh->nh_info);
size_t sz;
/* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE
* are mutually exclusive
*/
sz = nla_total_size(4); /* NHA_OIF */
switch (nhi->family) {
case AF_INET:
if (nhi->fib_nh.fib_nh_gw_family)
sz += nla_total_size(4); /* NHA_GATEWAY */
break;
case AF_INET6:
/* NHA_GATEWAY */
if (nhi->fib6_nh.fib_nh_gw_family)
sz += nla_total_size(sizeof(const struct in6_addr));
break;
}
if (nhi->fib_nhc.nhc_lwtstate) {
sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate);
sz += nla_total_size(2); /* NHA_ENCAP_TYPE */
}
return sz;
}
static size_t nh_nlmsg_size(struct nexthop *nh)
{
size_t sz = nla_total_size(4); /* NHA_ID */
if (nh->is_group)
sz += nh_nlmsg_size_grp(nh);
else
sz += nh_nlmsg_size_single(nh);
return sz;
}
static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info)
{
unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0;
u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
struct sk_buff *skb;
int err = -ENOBUFS;
skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any());
if (!skb)
goto errout;
err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags);
if (err < 0) {
/* -EMSGSIZE implies BUG in nh_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP,
info->nlh, gfp_any());
return;
errout:
if (err < 0)
rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err);
}
static bool valid_group_nh(struct nexthop *nh, unsigned int npaths,
struct netlink_ext_ack *extack)
{
if (nh->is_group) {
struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
/* nested multipath (group within a group) is not
* supported
*/
if (nhg->mpath) {
NL_SET_ERR_MSG(extack,
"Multipath group can not be a nexthop within a group");
return false;
}
} else {
struct nh_info *nhi = rtnl_dereference(nh->nh_info);
if (nhi->reject_nh && npaths > 1) {
NL_SET_ERR_MSG(extack,
"Blackhole nexthop can not be used in a group with more than 1 path");
return false;
}
}
return true;
}
static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
struct netlink_ext_ack *extack)
{
unsigned int len = nla_len(tb[NHA_GROUP]);
struct nexthop_grp *nhg;
unsigned int i, j;
if (len & (sizeof(struct nexthop_grp) - 1)) {
NL_SET_ERR_MSG(extack,
"Invalid length for nexthop group attribute");
return -EINVAL;
}
/* convert len to number of nexthop ids */
len /= sizeof(*nhg);
nhg = nla_data(tb[NHA_GROUP]);
for (i = 0; i < len; ++i) {
if (nhg[i].resvd1 || nhg[i].resvd2) {
NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0");
return -EINVAL;
}
if (nhg[i].weight > 254) {
NL_SET_ERR_MSG(extack, "Invalid value for weight");
return -EINVAL;
}
for (j = i + 1; j < len; ++j) {
if (nhg[i].id == nhg[j].id) {
NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group");
return -EINVAL;
}
}
}
nhg = nla_data(tb[NHA_GROUP]);
for (i = 0; i < len; ++i) {
struct nexthop *nh;
nh = nexthop_find_by_id(net, nhg[i].id);
if (!nh) {
NL_SET_ERR_MSG(extack, "Invalid nexthop id");
return -EINVAL;
}
if (!valid_group_nh(nh, len, extack))
return -EINVAL;
}
for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
if (!tb[i])
continue;
NL_SET_ERR_MSG(extack,
"No other attributes can be set in nexthop groups");
return -EINVAL;
}
return 0;
}
static bool ipv6_good_nh(const struct fib6_nh *nh)
{
int state = NUD_REACHABLE;
struct neighbour *n;
rcu_read_lock_bh();
n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6);
if (n)
state = n->nud_state;
rcu_read_unlock_bh();
return !!(state & NUD_VALID);
}
static bool ipv4_good_nh(const struct fib_nh *nh)
{
int state = NUD_REACHABLE;
struct neighbour *n;
rcu_read_lock_bh();
n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
(__force u32)nh->fib_nh_gw4);
if (n)
state = n->nud_state;
rcu_read_unlock_bh();
return !!(state & NUD_VALID);
}
struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
{
struct nexthop *rc = NULL;
struct nh_group *nhg;
int i;
if (!nh->is_group)
return nh;
nhg = rcu_dereference(nh->nh_grp);
for (i = 0; i < nhg->num_nh; ++i) {
struct nh_grp_entry *nhge = &nhg->nh_entries[i];
struct nh_info *nhi;
if (hash > atomic_read(&nhge->upper_bound))
continue;
/* nexthops always check if it is good and does
* not rely on a sysctl for this behavior
*/
nhi = rcu_dereference(nhge->nh->nh_info);
switch (nhi->family) {
case AF_INET:
if (ipv4_good_nh(&nhi->fib_nh))
return nhge->nh;
break;
case AF_INET6:
if (ipv6_good_nh(&nhi->fib6_nh))
return nhge->nh;
break;
}
if (!rc)
rc = nhge->nh;
}
return rc;
}
EXPORT_SYMBOL_GPL(nexthop_select_path);
int nexthop_for_each_fib6_nh(struct nexthop *nh,
int (*cb)(struct fib6_nh *nh, void *arg),
void *arg)
{
struct nh_info *nhi;
int err;
if (nh->is_group) {
struct nh_group *nhg;
int i;
nhg = rcu_dereference_rtnl(nh->nh_grp);
for (i = 0; i < nhg->num_nh; i++) {
struct nh_grp_entry *nhge = &nhg->nh_entries[i];
nhi = rcu_dereference_rtnl(nhge->nh->nh_info);
err = cb(&nhi->fib6_nh, arg);
if (err)
return err;
}
} else {
nhi = rcu_dereference_rtnl(nh->nh_info);
err = cb(&nhi->fib6_nh, arg);
if (err)
return err;
}
return 0;
}
EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh);
static int check_src_addr(const struct in6_addr *saddr,
struct netlink_ext_ack *extack)
{
if (!ipv6_addr_any(saddr)) {
NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects");
return -EINVAL;
}
return 0;
}
int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
struct netlink_ext_ack *extack)
{
struct nh_info *nhi;
/* fib6_src is unique to a fib6_info and limits the ability to cache
* routes in fib6_nh within a nexthop that is potentially shared
* across multiple fib entries. If the config wants to use source
* routing it can not use nexthop objects. mlxsw also does not allow
* fib6_src on routes.
*/
if (cfg && check_src_addr(&cfg->fc_src, extack) < 0)
return -EINVAL;
if (nh->is_group) {
struct nh_group *nhg;
nhg = rtnl_dereference(nh->nh_grp);
if (nhg->has_v4)
goto no_v4_nh;
} else {
nhi = rtnl_dereference(nh->nh_info);
if (nhi->family == AF_INET)
goto no_v4_nh;
}
return 0;
no_v4_nh:
NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop");
return -EINVAL;
}
EXPORT_SYMBOL_GPL(fib6_check_nexthop);
/* if existing nexthop has ipv6 routes linked to it, need
* to verify this new spec works with ipv6
*/
static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new,
struct netlink_ext_ack *extack)
{
struct fib6_info *f6i;
if (list_empty(&old->f6i_list))
return 0;
list_for_each_entry(f6i, &old->f6i_list, nh_list) {
if (check_src_addr(&f6i->fib6_src.addr, extack) < 0)
return -EINVAL;
}
return fib6_check_nexthop(new, NULL, extack);
}
static int nexthop_check_scope(struct nexthop *nh, u8 scope,
struct netlink_ext_ack *extack)
{
struct nh_info *nhi;
nhi = rtnl_dereference(nh->nh_info);
if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) {
NL_SET_ERR_MSG(extack,
"Route with host scope can not have a gateway");
return -EINVAL;
}
if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) {
NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop");
return -EINVAL;
}
return 0;
}
/* Invoked by fib add code to verify nexthop by id is ok with
* config for prefix; parts of fib_check_nh not done when nexthop
* object is used.
*/
int fib_check_nexthop(struct nexthop *nh, u8 scope,
struct netlink_ext_ack *extack)
{
int err = 0;
if (nh->is_group) {
struct nh_group *nhg;
if (scope == RT_SCOPE_HOST) {
NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops");
err = -EINVAL;
goto out;
}
nhg = rtnl_dereference(nh->nh_grp);
/* all nexthops in a group have the same scope */
err = nexthop_check_scope(nhg->nh_entries[0].nh, scope, extack);
} else {
err = nexthop_check_scope(nh, scope, extack);
}
out:
return err;
}
static int fib_check_nh_list(struct nexthop *old, struct nexthop *new,
struct netlink_ext_ack *extack)
{
struct fib_info *fi;
list_for_each_entry(fi, &old->fi_list, nh_list) {
int err;
err = fib_check_nexthop(new, fi->fib_scope, extack);
if (err)
return err;
}
return 0;
}
static void nh_group_rebalance(struct nh_group *nhg)
{
int total = 0;
int w = 0;
int i;
for (i = 0; i < nhg->num_nh; ++i)
total += nhg->nh_entries[i].weight;
for (i = 0; i < nhg->num_nh; ++i) {
struct nh_grp_entry *nhge = &nhg->nh_entries[i];
int upper_bound;
w += nhge->weight;
upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1;
atomic_set(&nhge->upper_bound, upper_bound);
}
}
static void remove_nh_grp_entry(struct nh_grp_entry *nhge,
struct nh_group *nhg,
struct nl_info *nlinfo)
{
struct nexthop *nh = nhge->nh;
struct nh_grp_entry *nhges;
bool found = false;
int i;
WARN_ON(!nh);
nhges = nhg->nh_entries;
for (i = 0; i < nhg->num_nh; ++i) {
if (found) {
nhges[i-1].nh = nhges[i].nh;
nhges[i-1].weight = nhges[i].weight;
list_del(&nhges[i].nh_list);
list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list);
} else if (nhg->nh_entries[i].nh == nh) {
found = true;
}
}
if (WARN_ON(!found))
return;
nhg->num_nh--;
nhg->nh_entries[nhg->num_nh].nh = NULL;
nh_group_rebalance(nhg);
nexthop_put(nh);
if (nlinfo)
nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo);
}
static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
struct nh_grp_entry *nhge, *tmp;
list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) {
struct nh_group *nhg;
list_del(&nhge->nh_list);
nhg = rtnl_dereference(nhge->nh_parent->nh_grp);
remove_nh_grp_entry(nhge, nhg, nlinfo);
/* if this group has no more entries then remove it */
if (!nhg->num_nh)
remove_nexthop(net, nhge->nh_parent, nlinfo);
}
}
static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
{
struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp);
int i, num_nh = nhg->num_nh;
for (i = 0; i < num_nh; ++i) {
struct nh_grp_entry *nhge = &nhg->nh_entries[i];
if (WARN_ON(!nhge->nh))
continue;
list_del(&nhge->nh_list);
nexthop_put(nhge->nh);
nhge->nh = NULL;
nhg->num_nh--;
}
}
/* not called for nexthop replace */
static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
{
struct fib6_info *f6i, *tmp;
bool do_flush = false;
struct fib_info *fi;
list_for_each_entry(fi, &nh->fi_list, nh_list) {
fi->fib_flags |= RTNH_F_DEAD;
do_flush = true;
}
if (do_flush)
fib_flush(net);
/* ip6_del_rt removes the entry from this list hence the _safe */
list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) {
/* __ip6_del_rt does a release, so do a hold here */
fib6_info_hold(f6i);
ipv6_stub->ip6_del_rt(net, f6i);
}
}
static void __remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
__remove_nexthop_fib(net, nh);
if (nh->is_group) {
remove_nexthop_group(nh, nlinfo);
} else {
struct nh_info *nhi;
nhi = rtnl_dereference(nh->nh_info);
if (nhi->fib_nhc.nhc_dev)
hlist_del(&nhi->dev_hash);
remove_nexthop_from_groups(net, nh, nlinfo);
}
}
static void remove_nexthop(struct net *net, struct nexthop *nh,
struct nl_info *nlinfo)
{
/* remove from the tree */
rb_erase(&nh->rb_node, &net->nexthop.rb_root);
if (nlinfo)
nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo);
__remove_nexthop(net, nh, nlinfo);
nh_base_seq_inc(net);
nexthop_put(nh);
}
/* if any FIB entries reference this nexthop, any dst entries
* need to be regenerated
*/
static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
{
struct fib6_info *f6i;
if (!list_empty(&nh->fi_list))
rt_cache_flush(net);
list_for_each_entry(f6i, &nh->f6i_list, nh_list)
ipv6_stub->fib6_update_sernum(net, f6i);
}
static int replace_nexthop_grp(struct net *net, struct nexthop *old,
struct nexthop *new,
struct netlink_ext_ack *extack)
{
struct nh_group *oldg, *newg;
int i;
if (!new->is_group) {
NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop.");
return -EINVAL;
}
oldg = rtnl_dereference(old->nh_grp);
newg = rtnl_dereference(new->nh_grp);
/* update parents - used by nexthop code for cleanup */
for (i = 0; i < newg->num_nh; i++)
newg->nh_entries[i].nh_parent = old;
rcu_assign_pointer(old->nh_grp, newg);
for (i = 0; i < oldg->num_nh; i++)
oldg->nh_entries[i].nh_parent = new;
rcu_assign_pointer(new->nh_grp, oldg);
return 0;
}
static int replace_nexthop_single(struct net *net, struct nexthop *old,
struct nexthop *new,
struct netlink_ext_ack *extack)
{
struct nh_info *oldi, *newi;
if (new->is_group) {
NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group.");
return -EINVAL;
}
oldi = rtnl_dereference(old->nh_info);
newi = rtnl_dereference(new->nh_info);
newi->nh_parent = old;
oldi->nh_parent = new;
old->protocol = new->protocol;
old->nh_flags = new->nh_flags;
rcu_assign_pointer(old->nh_info, newi);
rcu_assign_pointer(new->nh_info, oldi);
return 0;
}
static void __nexthop_replace_notify(struct net *net, struct nexthop *nh,
struct nl_info *info)
{
struct fib6_info *f6i;
if (!list_empty(&nh->fi_list)) {
struct fib_info *fi;
/* expectation is a few fib_info per nexthop and then
* a lot of routes per fib_info. So mark the fib_info
* and then walk the fib tables once
*/
list_for_each_entry(fi, &nh->fi_list, nh_list)
fi->nh_updated = true;
fib_info_notify_update(net, info);
list_for_each_entry(fi, &nh->fi_list, nh_list)
fi->nh_updated = false;
}
list_for_each_entry(f6i, &nh->f6i_list, nh_list)
ipv6_stub->fib6_rt_update(net, f6i, info);
}
/* send RTM_NEWROUTE with REPLACE flag set for all FIB entries
* linked to this nexthop and for all groups that the nexthop
* is a member of
*/
static void nexthop_replace_notify(struct net *net, struct nexthop *nh,
struct nl_info *info)
{
struct nh_grp_entry *nhge;
__nexthop_replace_notify(net, nh, info);
list_for_each_entry(nhge, &nh->grp_list, nh_list)
__nexthop_replace_notify(net, nhge->nh_parent, info);
}
static int replace_nexthop(struct net *net, struct nexthop *old,
struct nexthop *new, struct netlink_ext_ack *extack)
{
bool new_is_reject = false;
struct nh_grp_entry *nhge;
int err;
/* check that existing FIB entries are ok with the
* new nexthop definition
*/
err = fib_check_nh_list(old, new, extack);
if (err)
return err;
err = fib6_check_nh_list(old, new, extack);
if (err)
return err;
if (!new->is_group) {
struct nh_info *nhi = rtnl_dereference(new->nh_info);
new_is_reject = nhi->reject_nh;
}
list_for_each_entry(nhge, &old->grp_list, nh_list) {
/* if new nexthop is a blackhole, any groups using this
* nexthop cannot have more than 1 path
*/
if (new_is_reject &&
nexthop_num_path(nhge->nh_parent) > 1) {
NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path");
return -EINVAL;
}
err = fib_check_nh_list(nhge->nh_parent, new, extack);
if (err)
return err;
err = fib6_check_nh_list(nhge->nh_parent, new, extack);
if (err)
return err;
}
if (old->is_group)
err = replace_nexthop_grp(net, old, new, extack);
else
err = replace_nexthop_single(net, old, new, extack);
if (!err) {
nh_rt_cache_flush(net, old);
__remove_nexthop(net, new, NULL);
nexthop_put(new);
}
return err;
}
/* called with rtnl_lock held */
static int insert_nexthop(struct net *net, struct nexthop *new_nh,
struct nh_config *cfg, struct netlink_ext_ack *extack)
{
struct rb_node **pp, *parent = NULL, *next;
struct rb_root *root = &net->nexthop.rb_root;
bool replace = !!(cfg->nlflags & NLM_F_REPLACE);
bool create = !!(cfg->nlflags & NLM_F_CREATE);
u32 new_id = new_nh->id;
int replace_notify = 0;
int rc = -EEXIST;