forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
af_mpls.c
2546 lines (2130 loc) · 57.8 KB
/
af_mpls.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
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/socket.h>
#include <linux/sysctl.h>
#include <linux/net.h>
#include <linux/module.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/mpls.h>
#include <linux/netconf.h>
#include <linux/vmalloc.h>
#include <linux/percpu.h>
#include <net/ip.h>
#include <net/dst.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/netevent.h>
#include <net/ip_tunnels.h>
#include <net/netns/generic.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#endif
#include <net/addrconf.h>
#include <net/nexthop.h>
#include "internal.h"
/* max memory we will use for mpls_route */
#define MAX_MPLS_ROUTE_MEM 4096
/* Maximum number of labels to look ahead at when selecting a path of
* a multipath route
*/
#define MAX_MP_SELECT_LABELS 4
#define MPLS_NEIGH_TABLE_UNSPEC (NEIGH_LINK_TABLE + 1)
static int zero = 0;
static int one = 1;
static int label_limit = (1 << 20) - 1;
static int ttl_max = 255;
#if IS_ENABLED(CONFIG_NET_IP_TUNNEL)
static size_t ipgre_mpls_encap_hlen(struct ip_tunnel_encap *e)
{
return sizeof(struct mpls_shim_hdr);
}
static const struct ip_tunnel_encap_ops mpls_iptun_ops = {
.encap_hlen = ipgre_mpls_encap_hlen,
};
static int ipgre_tunnel_encap_add_mpls_ops(void)
{
return ip_tunnel_encap_add_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
}
static void ipgre_tunnel_encap_del_mpls_ops(void)
{
ip_tunnel_encap_del_ops(&mpls_iptun_ops, TUNNEL_ENCAP_MPLS);
}
#else
static int ipgre_tunnel_encap_add_mpls_ops(void)
{
return 0;
}
static void ipgre_tunnel_encap_del_mpls_ops(void)
{
}
#endif
static void rtmsg_lfib(int event, u32 label, struct mpls_route *rt,
struct nlmsghdr *nlh, struct net *net, u32 portid,
unsigned int nlm_flags);
static struct mpls_route *mpls_route_input_rcu(struct net *net, unsigned index)
{
struct mpls_route *rt = NULL;
if (index < net->mpls.platform_labels) {
struct mpls_route __rcu **platform_label =
rcu_dereference(net->mpls.platform_label);
rt = rcu_dereference(platform_label[index]);
}
return rt;
}
bool mpls_output_possible(const struct net_device *dev)
{
return dev && (dev->flags & IFF_UP) && netif_carrier_ok(dev);
}
EXPORT_SYMBOL_GPL(mpls_output_possible);
static u8 *__mpls_nh_via(struct mpls_route *rt, struct mpls_nh *nh)
{
return (u8 *)nh + rt->rt_via_offset;
}
static const u8 *mpls_nh_via(const struct mpls_route *rt,
const struct mpls_nh *nh)
{
return __mpls_nh_via((struct mpls_route *)rt, (struct mpls_nh *)nh);
}
static unsigned int mpls_nh_header_size(const struct mpls_nh *nh)
{
/* The size of the layer 2.5 labels to be added for this route */
return nh->nh_labels * sizeof(struct mpls_shim_hdr);
}
unsigned int mpls_dev_mtu(const struct net_device *dev)
{
/* The amount of data the layer 2 frame can hold */
return dev->mtu;
}
EXPORT_SYMBOL_GPL(mpls_dev_mtu);
bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned int mtu)
{
if (skb->len <= mtu)
return false;
if (skb_is_gso(skb) && skb_gso_validate_mtu(skb, mtu))
return false;
return true;
}
EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
void mpls_stats_inc_outucastpkts(struct net_device *dev,
const struct sk_buff *skb)
{
struct mpls_dev *mdev;
if (skb->protocol == htons(ETH_P_MPLS_UC)) {
mdev = mpls_dev_get(dev);
if (mdev)
MPLS_INC_STATS_LEN(mdev, skb->len,
tx_packets,
tx_bytes);
} else if (skb->protocol == htons(ETH_P_IP)) {
IP_UPD_PO_STATS(dev_net(dev), IPSTATS_MIB_OUT, skb->len);
#if IS_ENABLED(CONFIG_IPV6)
} else if (skb->protocol == htons(ETH_P_IPV6)) {
struct inet6_dev *in6dev = __in6_dev_get(dev);
if (in6dev)
IP6_UPD_PO_STATS(dev_net(dev), in6dev,
IPSTATS_MIB_OUT, skb->len);
#endif
}
}
EXPORT_SYMBOL_GPL(mpls_stats_inc_outucastpkts);
static u32 mpls_multipath_hash(struct mpls_route *rt, struct sk_buff *skb)
{
struct mpls_entry_decoded dec;
unsigned int mpls_hdr_len = 0;
struct mpls_shim_hdr *hdr;
bool eli_seen = false;
int label_index;
u32 hash = 0;
for (label_index = 0; label_index < MAX_MP_SELECT_LABELS;
label_index++) {
mpls_hdr_len += sizeof(*hdr);
if (!pskb_may_pull(skb, mpls_hdr_len))
break;
/* Read and decode the current label */
hdr = mpls_hdr(skb) + label_index;
dec = mpls_entry_decode(hdr);
/* RFC6790 - reserved labels MUST NOT be used as keys
* for the load-balancing function
*/
if (likely(dec.label >= MPLS_LABEL_FIRST_UNRESERVED)) {
hash = jhash_1word(dec.label, hash);
/* The entropy label follows the entropy label
* indicator, so this means that the entropy
* label was just added to the hash - no need to
* go any deeper either in the label stack or in the
* payload
*/
if (eli_seen)
break;
} else if (dec.label == MPLS_LABEL_ENTROPY) {
eli_seen = true;
}
if (!dec.bos)
continue;
/* found bottom label; does skb have room for a header? */
if (pskb_may_pull(skb, mpls_hdr_len + sizeof(struct iphdr))) {
const struct iphdr *v4hdr;
v4hdr = (const struct iphdr *)(hdr + 1);
if (v4hdr->version == 4) {
hash = jhash_3words(ntohl(v4hdr->saddr),
ntohl(v4hdr->daddr),
v4hdr->protocol, hash);
} else if (v4hdr->version == 6 &&
pskb_may_pull(skb, mpls_hdr_len +
sizeof(struct ipv6hdr))) {
const struct ipv6hdr *v6hdr;
v6hdr = (const struct ipv6hdr *)(hdr + 1);
hash = __ipv6_addr_jhash(&v6hdr->saddr, hash);
hash = __ipv6_addr_jhash(&v6hdr->daddr, hash);
hash = jhash_1word(v6hdr->nexthdr, hash);
}
}
break;
}
return hash;
}
static struct mpls_nh *mpls_get_nexthop(struct mpls_route *rt, u8 index)
{
return (struct mpls_nh *)((u8 *)rt->rt_nh + index * rt->rt_nh_size);
}
/* number of alive nexthops (rt->rt_nhn_alive) and the flags for
* a next hop (nh->nh_flags) are modified by netdev event handlers.
* Since those fields can change at any moment, use READ_ONCE to
* access both.
*/
static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
struct sk_buff *skb)
{
u32 hash = 0;
int nh_index = 0;
int n = 0;
u8 alive;
/* No need to look further into packet if there's only
* one path
*/
if (rt->rt_nhn == 1)
return rt->rt_nh;
alive = READ_ONCE(rt->rt_nhn_alive);
if (alive == 0)
return NULL;
hash = mpls_multipath_hash(rt, skb);
nh_index = hash % alive;
if (alive == rt->rt_nhn)
goto out;
for_nexthops(rt) {
unsigned int nh_flags = READ_ONCE(nh->nh_flags);
if (nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
continue;
if (n == nh_index)
return nh;
n++;
} endfor_nexthops(rt);
out:
return mpls_get_nexthop(rt, nh_index);
}
static bool mpls_egress(struct net *net, struct mpls_route *rt,
struct sk_buff *skb, struct mpls_entry_decoded dec)
{
enum mpls_payload_type payload_type;
bool success = false;
/* The IPv4 code below accesses through the IPv4 header
* checksum, which is 12 bytes into the packet.
* The IPv6 code below accesses through the IPv6 hop limit
* which is 8 bytes into the packet.
*
* For all supported cases there should always be at least 12
* bytes of packet data present. The IPv4 header is 20 bytes
* without options and the IPv6 header is always 40 bytes
* long.
*/
if (!pskb_may_pull(skb, 12))
return false;
payload_type = rt->rt_payload_type;
if (payload_type == MPT_UNSPEC)
payload_type = ip_hdr(skb)->version;
switch (payload_type) {
case MPT_IPV4: {
struct iphdr *hdr4 = ip_hdr(skb);
u8 new_ttl;
skb->protocol = htons(ETH_P_IP);
/* If propagating TTL, take the decremented TTL from
* the incoming MPLS header, otherwise decrement the
* TTL, but only if not 0 to avoid underflow.
*/
if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
(rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
net->mpls.ip_ttl_propagate))
new_ttl = dec.ttl;
else
new_ttl = hdr4->ttl ? hdr4->ttl - 1 : 0;
csum_replace2(&hdr4->check,
htons(hdr4->ttl << 8),
htons(new_ttl << 8));
hdr4->ttl = new_ttl;
success = true;
break;
}
case MPT_IPV6: {
struct ipv6hdr *hdr6 = ipv6_hdr(skb);
skb->protocol = htons(ETH_P_IPV6);
/* If propagating TTL, take the decremented TTL from
* the incoming MPLS header, otherwise decrement the
* hop limit, but only if not 0 to avoid underflow.
*/
if (rt->rt_ttl_propagate == MPLS_TTL_PROP_ENABLED ||
(rt->rt_ttl_propagate == MPLS_TTL_PROP_DEFAULT &&
net->mpls.ip_ttl_propagate))
hdr6->hop_limit = dec.ttl;
else if (hdr6->hop_limit)
hdr6->hop_limit = hdr6->hop_limit - 1;
success = true;
break;
}
case MPT_UNSPEC:
/* Should have decided which protocol it is by now */
break;
}
return success;
}
static int mpls_forward(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
struct net *net = dev_net(dev);
struct mpls_shim_hdr *hdr;
struct mpls_route *rt;
struct mpls_nh *nh;
struct mpls_entry_decoded dec;
struct net_device *out_dev;
struct mpls_dev *out_mdev;
struct mpls_dev *mdev;
unsigned int hh_len;
unsigned int new_header_size;
unsigned int mtu;
int err;
/* Careful this entire function runs inside of an rcu critical section */
mdev = mpls_dev_get(dev);
if (!mdev)
goto drop;
MPLS_INC_STATS_LEN(mdev, skb->len, rx_packets,
rx_bytes);
if (!mdev->input_enabled) {
MPLS_INC_STATS(mdev, rx_dropped);
goto drop;
}
if (skb->pkt_type != PACKET_HOST)
goto err;
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
goto err;
if (!pskb_may_pull(skb, sizeof(*hdr)))
goto err;
/* Read and decode the label */
hdr = mpls_hdr(skb);
dec = mpls_entry_decode(hdr);
rt = mpls_route_input_rcu(net, dec.label);
if (!rt) {
MPLS_INC_STATS(mdev, rx_noroute);
goto drop;
}
nh = mpls_select_multipath(rt, skb);
if (!nh)
goto err;
/* Pop the label */
skb_pull(skb, sizeof(*hdr));
skb_reset_network_header(skb);
skb_orphan(skb);
if (skb_warn_if_lro(skb))
goto err;
skb_forward_csum(skb);
/* Verify ttl is valid */
if (dec.ttl <= 1)
goto err;
dec.ttl -= 1;
/* Find the output device */
out_dev = rcu_dereference(nh->nh_dev);
if (!mpls_output_possible(out_dev))
goto tx_err;
/* Verify the destination can hold the packet */
new_header_size = mpls_nh_header_size(nh);
mtu = mpls_dev_mtu(out_dev);
if (mpls_pkt_too_big(skb, mtu - new_header_size))
goto tx_err;
hh_len = LL_RESERVED_SPACE(out_dev);
if (!out_dev->header_ops)
hh_len = 0;
/* Ensure there is enough space for the headers in the skb */
if (skb_cow(skb, hh_len + new_header_size))
goto tx_err;
skb->dev = out_dev;
skb->protocol = htons(ETH_P_MPLS_UC);
if (unlikely(!new_header_size && dec.bos)) {
/* Penultimate hop popping */
if (!mpls_egress(dev_net(out_dev), rt, skb, dec))
goto err;
} else {
bool bos;
int i;
skb_push(skb, new_header_size);
skb_reset_network_header(skb);
/* Push the new labels */
hdr = mpls_hdr(skb);
bos = dec.bos;
for (i = nh->nh_labels - 1; i >= 0; i--) {
hdr[i] = mpls_entry_encode(nh->nh_label[i],
dec.ttl, 0, bos);
bos = false;
}
}
mpls_stats_inc_outucastpkts(out_dev, skb);
/* If via wasn't specified then send out using device address */
if (nh->nh_via_table == MPLS_NEIGH_TABLE_UNSPEC)
err = neigh_xmit(NEIGH_LINK_TABLE, out_dev,
out_dev->dev_addr, skb);
else
err = neigh_xmit(nh->nh_via_table, out_dev,
mpls_nh_via(rt, nh), skb);
if (err)
net_dbg_ratelimited("%s: packet transmission failed: %d\n",
__func__, err);
return 0;
tx_err:
out_mdev = out_dev ? mpls_dev_get(out_dev) : NULL;
if (out_mdev)
MPLS_INC_STATS(out_mdev, tx_errors);
goto drop;
err:
MPLS_INC_STATS(mdev, rx_errors);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
static struct packet_type mpls_packet_type __read_mostly = {
.type = cpu_to_be16(ETH_P_MPLS_UC),
.func = mpls_forward,
};
static const struct nla_policy rtm_mpls_policy[RTA_MAX+1] = {
[RTA_DST] = { .type = NLA_U32 },
[RTA_OIF] = { .type = NLA_U32 },
[RTA_TTL_PROPAGATE] = { .type = NLA_U8 },
};
struct mpls_route_config {
u32 rc_protocol;
u32 rc_ifindex;
u8 rc_via_table;
u8 rc_via_alen;
u8 rc_via[MAX_VIA_ALEN];
u32 rc_label;
u8 rc_ttl_propagate;
u8 rc_output_labels;
u32 rc_output_label[MAX_NEW_LABELS];
u32 rc_nlflags;
enum mpls_payload_type rc_payload_type;
struct nl_info rc_nlinfo;
struct rtnexthop *rc_mp;
int rc_mp_len;
};
/* all nexthops within a route have the same size based on max
* number of labels and max via length for a hop
*/
static struct mpls_route *mpls_rt_alloc(u8 num_nh, u8 max_alen, u8 max_labels)
{
u8 nh_size = MPLS_NH_SIZE(max_labels, max_alen);
struct mpls_route *rt;
size_t size;
size = sizeof(*rt) + num_nh * nh_size;
if (size > MAX_MPLS_ROUTE_MEM)
return ERR_PTR(-EINVAL);
rt = kzalloc(size, GFP_KERNEL);
if (!rt)
return ERR_PTR(-ENOMEM);
rt->rt_nhn = num_nh;
rt->rt_nhn_alive = num_nh;
rt->rt_nh_size = nh_size;
rt->rt_via_offset = MPLS_NH_VIA_OFF(max_labels);
return rt;
}
static void mpls_rt_free(struct mpls_route *rt)
{
if (rt)
kfree_rcu(rt, rt_rcu);
}
static void mpls_notify_route(struct net *net, unsigned index,
struct mpls_route *old, struct mpls_route *new,
const struct nl_info *info)
{
struct nlmsghdr *nlh = info ? info->nlh : NULL;
unsigned portid = info ? info->portid : 0;
int event = new ? RTM_NEWROUTE : RTM_DELROUTE;
struct mpls_route *rt = new ? new : old;
unsigned nlm_flags = (old && new) ? NLM_F_REPLACE : 0;
/* Ignore reserved labels for now */
if (rt && (index >= MPLS_LABEL_FIRST_UNRESERVED))
rtmsg_lfib(event, index, rt, nlh, net, portid, nlm_flags);
}
static void mpls_route_update(struct net *net, unsigned index,
struct mpls_route *new,
const struct nl_info *info)
{
struct mpls_route __rcu **platform_label;
struct mpls_route *rt;
ASSERT_RTNL();
platform_label = rtnl_dereference(net->mpls.platform_label);
rt = rtnl_dereference(platform_label[index]);
rcu_assign_pointer(platform_label[index], new);
mpls_notify_route(net, index, rt, new, info);
/* If we removed a route free it now */
mpls_rt_free(rt);
}
static unsigned find_free_label(struct net *net)
{
struct mpls_route __rcu **platform_label;
size_t platform_labels;
unsigned index;
platform_label = rtnl_dereference(net->mpls.platform_label);
platform_labels = net->mpls.platform_labels;
for (index = MPLS_LABEL_FIRST_UNRESERVED; index < platform_labels;
index++) {
if (!rtnl_dereference(platform_label[index]))
return index;
}
return LABEL_NOT_SPECIFIED;
}
#if IS_ENABLED(CONFIG_INET)
static struct net_device *inet_fib_lookup_dev(struct net *net,
const void *addr)
{
struct net_device *dev;
struct rtable *rt;
struct in_addr daddr;
memcpy(&daddr, addr, sizeof(struct in_addr));
rt = ip_route_output(net, daddr.s_addr, 0, 0, 0);
if (IS_ERR(rt))
return ERR_CAST(rt);
dev = rt->dst.dev;
dev_hold(dev);
ip_rt_put(rt);
return dev;
}
#else
static struct net_device *inet_fib_lookup_dev(struct net *net,
const void *addr)
{
return ERR_PTR(-EAFNOSUPPORT);
}
#endif
#if IS_ENABLED(CONFIG_IPV6)
static struct net_device *inet6_fib_lookup_dev(struct net *net,
const void *addr)
{
struct net_device *dev;
struct dst_entry *dst;
struct flowi6 fl6;
int err;
if (!ipv6_stub)
return ERR_PTR(-EAFNOSUPPORT);
memset(&fl6, 0, sizeof(fl6));
memcpy(&fl6.daddr, addr, sizeof(struct in6_addr));
err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6);
if (err)
return ERR_PTR(err);
dev = dst->dev;
dev_hold(dev);
dst_release(dst);
return dev;
}
#else
static struct net_device *inet6_fib_lookup_dev(struct net *net,
const void *addr)
{
return ERR_PTR(-EAFNOSUPPORT);
}
#endif
static struct net_device *find_outdev(struct net *net,
struct mpls_route *rt,
struct mpls_nh *nh, int oif)
{
struct net_device *dev = NULL;
if (!oif) {
switch (nh->nh_via_table) {
case NEIGH_ARP_TABLE:
dev = inet_fib_lookup_dev(net, mpls_nh_via(rt, nh));
break;
case NEIGH_ND_TABLE:
dev = inet6_fib_lookup_dev(net, mpls_nh_via(rt, nh));
break;
case NEIGH_LINK_TABLE:
break;
}
} else {
dev = dev_get_by_index(net, oif);
}
if (!dev)
return ERR_PTR(-ENODEV);
if (IS_ERR(dev))
return dev;
/* The caller is holding rtnl anyways, so release the dev reference */
dev_put(dev);
return dev;
}
static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
struct mpls_nh *nh, int oif)
{
struct net_device *dev = NULL;
int err = -ENODEV;
dev = find_outdev(net, rt, nh, oif);
if (IS_ERR(dev)) {
err = PTR_ERR(dev);
dev = NULL;
goto errout;
}
/* Ensure this is a supported device */
err = -EINVAL;
if (!mpls_dev_get(dev))
goto errout;
if ((nh->nh_via_table == NEIGH_LINK_TABLE) &&
(dev->addr_len != nh->nh_via_alen))
goto errout;
RCU_INIT_POINTER(nh->nh_dev, dev);
if (!(dev->flags & IFF_UP)) {
nh->nh_flags |= RTNH_F_DEAD;
} else {
unsigned int flags;
flags = dev_get_flags(dev);
if (!(flags & (IFF_RUNNING | IFF_LOWER_UP)))
nh->nh_flags |= RTNH_F_LINKDOWN;
}
return 0;
errout:
return err;
}
static int nla_get_via(const struct nlattr *nla, u8 *via_alen, u8 *via_table,
u8 via_addr[], struct netlink_ext_ack *extack)
{
struct rtvia *via = nla_data(nla);
int err = -EINVAL;
int alen;
if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) {
NL_SET_ERR_MSG_ATTR(extack, nla,
"Invalid attribute length for RTA_VIA");
goto errout;
}
alen = nla_len(nla) -
offsetof(struct rtvia, rtvia_addr);
if (alen > MAX_VIA_ALEN) {
NL_SET_ERR_MSG_ATTR(extack, nla,
"Invalid address length for RTA_VIA");
goto errout;
}
/* Validate the address family */
switch (via->rtvia_family) {
case AF_PACKET:
*via_table = NEIGH_LINK_TABLE;
break;
case AF_INET:
*via_table = NEIGH_ARP_TABLE;
if (alen != 4)
goto errout;
break;
case AF_INET6:
*via_table = NEIGH_ND_TABLE;
if (alen != 16)
goto errout;
break;
default:
/* Unsupported address family */
goto errout;
}
memcpy(via_addr, via->rtvia_addr, alen);
*via_alen = alen;
err = 0;
errout:
return err;
}
static int mpls_nh_build_from_cfg(struct mpls_route_config *cfg,
struct mpls_route *rt)
{
struct net *net = cfg->rc_nlinfo.nl_net;
struct mpls_nh *nh = rt->rt_nh;
int err;
int i;
if (!nh)
return -ENOMEM;
nh->nh_labels = cfg->rc_output_labels;
for (i = 0; i < nh->nh_labels; i++)
nh->nh_label[i] = cfg->rc_output_label[i];
nh->nh_via_table = cfg->rc_via_table;
memcpy(__mpls_nh_via(rt, nh), cfg->rc_via, cfg->rc_via_alen);
nh->nh_via_alen = cfg->rc_via_alen;
err = mpls_nh_assign_dev(net, rt, nh, cfg->rc_ifindex);
if (err)
goto errout;
if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
rt->rt_nhn_alive--;
return 0;
errout:
return err;
}
static int mpls_nh_build(struct net *net, struct mpls_route *rt,
struct mpls_nh *nh, int oif, struct nlattr *via,
struct nlattr *newdst, u8 max_labels,
struct netlink_ext_ack *extack)
{
int err = -ENOMEM;
if (!nh)
goto errout;
if (newdst) {
err = nla_get_labels(newdst, max_labels, &nh->nh_labels,
nh->nh_label, extack);
if (err)
goto errout;
}
if (via) {
err = nla_get_via(via, &nh->nh_via_alen, &nh->nh_via_table,
__mpls_nh_via(rt, nh), extack);
if (err)
goto errout;
} else {
nh->nh_via_table = MPLS_NEIGH_TABLE_UNSPEC;
}
err = mpls_nh_assign_dev(net, rt, nh, oif);
if (err)
goto errout;
return 0;
errout:
return err;
}
static u8 mpls_count_nexthops(struct rtnexthop *rtnh, int len,
u8 cfg_via_alen, u8 *max_via_alen,
u8 *max_labels)
{
int remaining = len;
u8 nhs = 0;
*max_via_alen = 0;
*max_labels = 0;
while (rtnh_ok(rtnh, remaining)) {
struct nlattr *nla, *attrs = rtnh_attrs(rtnh);
int attrlen;
u8 n_labels = 0;
attrlen = rtnh_attrlen(rtnh);
nla = nla_find(attrs, attrlen, RTA_VIA);
if (nla && nla_len(nla) >=
offsetof(struct rtvia, rtvia_addr)) {
int via_alen = nla_len(nla) -
offsetof(struct rtvia, rtvia_addr);
if (via_alen <= MAX_VIA_ALEN)
*max_via_alen = max_t(u16, *max_via_alen,
via_alen);
}
nla = nla_find(attrs, attrlen, RTA_NEWDST);
if (nla &&
nla_get_labels(nla, MAX_NEW_LABELS, &n_labels,
NULL, NULL) != 0)
return 0;
*max_labels = max_t(u8, *max_labels, n_labels);
/* number of nexthops is tracked by a u8.
* Check for overflow.
*/
if (nhs == 255)
return 0;
nhs++;
rtnh = rtnh_next(rtnh, &remaining);
}
/* leftover implies invalid nexthop configuration, discard it */
return remaining > 0 ? 0 : nhs;
}
static int mpls_nh_build_multi(struct mpls_route_config *cfg,
struct mpls_route *rt, u8 max_labels,
struct netlink_ext_ack *extack)
{
struct rtnexthop *rtnh = cfg->rc_mp;
struct nlattr *nla_via, *nla_newdst;
int remaining = cfg->rc_mp_len;
int err = 0;
u8 nhs = 0;
change_nexthops(rt) {
int attrlen;
nla_via = NULL;
nla_newdst = NULL;
err = -EINVAL;
if (!rtnh_ok(rtnh, remaining))
goto errout;
/* neither weighted multipath nor any flags
* are supported
*/
if (rtnh->rtnh_hops || rtnh->rtnh_flags)
goto errout;
attrlen = rtnh_attrlen(rtnh);
if (attrlen > 0) {
struct nlattr *attrs = rtnh_attrs(rtnh);
nla_via = nla_find(attrs, attrlen, RTA_VIA);
nla_newdst = nla_find(attrs, attrlen, RTA_NEWDST);
}
err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
rtnh->rtnh_ifindex, nla_via, nla_newdst,
max_labels, extack);
if (err)
goto errout;
if (nh->nh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
rt->rt_nhn_alive--;
rtnh = rtnh_next(rtnh, &remaining);
nhs++;
} endfor_nexthops(rt);
rt->rt_nhn = nhs;
return 0;
errout:
return err;
}
static bool mpls_label_ok(struct net *net, unsigned int index,
struct netlink_ext_ack *extack)
{
/* Reserved labels may not be set */
if (index < MPLS_LABEL_FIRST_UNRESERVED) {
NL_SET_ERR_MSG(extack,
"Invalid label - must be MPLS_LABEL_FIRST_UNRESERVED or higher");
return false;
}
/* The full 20 bit range may not be supported. */
if (index >= net->mpls.platform_labels) {
NL_SET_ERR_MSG(extack,
"Label >= configured maximum in platform_labels");
return false;
}
return true;
}
static int mpls_route_add(struct mpls_route_config *cfg,
struct netlink_ext_ack *extack)
{
struct mpls_route __rcu **platform_label;
struct net *net = cfg->rc_nlinfo.nl_net;
struct mpls_route *rt, *old;
int err = -EINVAL;
u8 max_via_alen;
unsigned index;
u8 max_labels;
u8 nhs;
index = cfg->rc_label;
/* If a label was not specified during insert pick one */
if ((index == LABEL_NOT_SPECIFIED) &&
(cfg->rc_nlflags & NLM_F_CREATE)) {
index = find_free_label(net);
}
if (!mpls_label_ok(net, index, extack))
goto errout;
/* Append makes no sense with mpls */
err = -EOPNOTSUPP;
if (cfg->rc_nlflags & NLM_F_APPEND) {
NL_SET_ERR_MSG(extack, "MPLS does not support route append");
goto errout;
}
err = -EEXIST;
platform_label = rtnl_dereference(net->mpls.platform_label);
old = rtnl_dereference(platform_label[index]);
if ((cfg->rc_nlflags & NLM_F_EXCL) && old)
goto errout;
err = -EEXIST;
if (!(cfg->rc_nlflags & NLM_F_REPLACE) && old)
goto errout;
err = -ENOENT;
if (!(cfg->rc_nlflags & NLM_F_CREATE) && !old)
goto errout;