forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
dn_route.c
1808 lines (1536 loc) · 43.7 KB
/
dn_route.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
/*
* DECnet An implementation of the DECnet protocol suite for the LINUX
* operating system. DECnet is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* DECnet Routing Functions (Endnode and Router)
*
* Authors: Steve Whitehouse <[email protected]>
* Eduardo Marcelo Serrat <[email protected]>
*
* Changes:
* Steve Whitehouse : Fixes to allow "intra-ethernet" and
* "return-to-sender" bits on outgoing
* packets.
* Steve Whitehouse : Timeouts for cached routes.
* Steve Whitehouse : Use dst cache for input routes too.
* Steve Whitehouse : Fixed error values in dn_send_skb.
* Steve Whitehouse : Rework routing functions to better fit
* DECnet routing design
* Alexey Kuznetsov : New SMP locking
* Steve Whitehouse : More SMP locking changes & dn_cache_dump()
* Steve Whitehouse : Prerouting NF hook, now really is prerouting.
* Fixed possible skb leak in rtnetlink funcs.
* Steve Whitehouse : Dave Miller's dynamic hash table sizing and
* Alexey Kuznetsov's finer grained locking
* from ipv4/route.c.
* Steve Whitehouse : Routing is now starting to look like a
* sensible set of code now, mainly due to
* my copying the IPv4 routing code. The
* hooks here are modified and will continue
* to evolve for a while.
* Steve Whitehouse : Real SMP at last :-) Also new netfilter
* stuff. Look out raw sockets your days
* are numbered!
* Steve Whitehouse : Added return-to-sender functions. Added
* backlog congestion level return codes.
* Steve Whitehouse : Fixed bug where routes were set up with
* no ref count on net devices.
* Steve Whitehouse : RCU for the route cache
* Steve Whitehouse : Preparations for the flow cache
* Steve Whitehouse : Prepare for nonlinear skbs
*/
/******************************************************************************
(c) 1995-1998 E.M. Serrat [email protected]
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2 of the License, or
any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU General Public License for more details.
*******************************************************************************/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/inet.h>
#include <linux/route.h>
#include <linux/in_route.h>
#include <net/sock.h>
#include <linux/mm.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/rtnetlink.h>
#include <linux/string.h>
#include <linux/netfilter_decnet.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <asm/errno.h>
#include <net/net_namespace.h>
#include <net/netlink.h>
#include <net/neighbour.h>
#include <net/dst.h>
#include <net/flow.h>
#include <net/fib_rules.h>
#include <net/dn.h>
#include <net/dn_dev.h>
#include <net/dn_nsp.h>
#include <net/dn_route.h>
#include <net/dn_neigh.h>
#include <net/dn_fib.h>
struct dn_rt_hash_bucket
{
struct dn_route *chain;
spinlock_t lock;
};
extern struct neigh_table dn_neigh_table;
static unsigned char dn_hiord_addr[6] = {0xAA,0x00,0x04,0x00,0x00,0x00};
static const int dn_rt_min_delay = 2 * HZ;
static const int dn_rt_max_delay = 10 * HZ;
static const int dn_rt_mtu_expires = 10 * 60 * HZ;
static unsigned long dn_rt_deadline;
static int dn_dst_gc(struct dst_ops *ops);
static struct dst_entry *dn_dst_check(struct dst_entry *, __u32);
static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
static void dn_dst_link_failure(struct sk_buff *);
static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu);
static int dn_route_input(struct sk_buff *);
static void dn_run_flush(unsigned long dummy);
static struct dn_rt_hash_bucket *dn_rt_hash_table;
static unsigned dn_rt_hash_mask;
static struct timer_list dn_route_timer;
static DEFINE_TIMER(dn_rt_flush_timer, dn_run_flush, 0, 0);
int decnet_dst_gc_interval = 2;
static struct dst_ops dn_dst_ops = {
.family = PF_DECnet,
.protocol = cpu_to_be16(ETH_P_DNA_RT),
.gc_thresh = 128,
.gc = dn_dst_gc,
.check = dn_dst_check,
.negative_advice = dn_dst_negative_advice,
.link_failure = dn_dst_link_failure,
.update_pmtu = dn_dst_update_pmtu,
.entries = ATOMIC_INIT(0),
};
static __inline__ unsigned dn_hash(__le16 src, __le16 dst)
{
__u16 tmp = (__u16 __force)(src ^ dst);
tmp ^= (tmp >> 3);
tmp ^= (tmp >> 5);
tmp ^= (tmp >> 10);
return dn_rt_hash_mask & (unsigned)tmp;
}
static inline void dnrt_free(struct dn_route *rt)
{
call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}
static inline void dnrt_drop(struct dn_route *rt)
{
dst_release(&rt->u.dst);
call_rcu_bh(&rt->u.dst.rcu_head, dst_rcu_free);
}
static void dn_dst_check_expire(unsigned long dummy)
{
int i;
struct dn_route *rt, **rtp;
unsigned long now = jiffies;
unsigned long expire = 120 * HZ;
for(i = 0; i <= dn_rt_hash_mask; i++) {
rtp = &dn_rt_hash_table[i].chain;
spin_lock(&dn_rt_hash_table[i].lock);
while((rt=*rtp) != NULL) {
if (atomic_read(&rt->u.dst.__refcnt) ||
(now - rt->u.dst.lastuse) < expire) {
rtp = &rt->u.dst.dn_next;
continue;
}
*rtp = rt->u.dst.dn_next;
rt->u.dst.dn_next = NULL;
dnrt_free(rt);
}
spin_unlock(&dn_rt_hash_table[i].lock);
if ((jiffies - now) > 0)
break;
}
mod_timer(&dn_route_timer, now + decnet_dst_gc_interval * HZ);
}
static int dn_dst_gc(struct dst_ops *ops)
{
struct dn_route *rt, **rtp;
int i;
unsigned long now = jiffies;
unsigned long expire = 10 * HZ;
for(i = 0; i <= dn_rt_hash_mask; i++) {
spin_lock_bh(&dn_rt_hash_table[i].lock);
rtp = &dn_rt_hash_table[i].chain;
while((rt=*rtp) != NULL) {
if (atomic_read(&rt->u.dst.__refcnt) ||
(now - rt->u.dst.lastuse) < expire) {
rtp = &rt->u.dst.dn_next;
continue;
}
*rtp = rt->u.dst.dn_next;
rt->u.dst.dn_next = NULL;
dnrt_drop(rt);
break;
}
spin_unlock_bh(&dn_rt_hash_table[i].lock);
}
return 0;
}
/*
* The decnet standards don't impose a particular minimum mtu, what they
* do insist on is that the routing layer accepts a datagram of at least
* 230 bytes long. Here we have to subtract the routing header length from
* 230 to get the minimum acceptable mtu. If there is no neighbour, then we
* assume the worst and use a long header size.
*
* We update both the mtu and the advertised mss (i.e. the segment size we
* advertise to the other end).
*/
static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu)
{
u32 min_mtu = 230;
struct dn_dev *dn = dst->neighbour ?
(struct dn_dev *)dst->neighbour->dev->dn_ptr : NULL;
if (dn && dn->use_long == 0)
min_mtu -= 6;
else
min_mtu -= 21;
if (dst_metric(dst, RTAX_MTU) > mtu && mtu >= min_mtu) {
if (!(dst_metric_locked(dst, RTAX_MTU))) {
dst->metrics[RTAX_MTU-1] = mtu;
dst_set_expires(dst, dn_rt_mtu_expires);
}
if (!(dst_metric_locked(dst, RTAX_ADVMSS))) {
u32 mss = mtu - DN_MAX_NSP_DATA_HEADER;
if (dst_metric(dst, RTAX_ADVMSS) > mss)
dst->metrics[RTAX_ADVMSS-1] = mss;
}
}
}
/*
* When a route has been marked obsolete. (e.g. routing cache flush)
*/
static struct dst_entry *dn_dst_check(struct dst_entry *dst, __u32 cookie)
{
return NULL;
}
static struct dst_entry *dn_dst_negative_advice(struct dst_entry *dst)
{
dst_release(dst);
return NULL;
}
static void dn_dst_link_failure(struct sk_buff *skb)
{
return;
}
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
return ((fl1->nl_u.dn_u.daddr ^ fl2->nl_u.dn_u.daddr) |
(fl1->nl_u.dn_u.saddr ^ fl2->nl_u.dn_u.saddr) |
(fl1->mark ^ fl2->mark) |
(fl1->nl_u.dn_u.scope ^ fl2->nl_u.dn_u.scope) |
(fl1->oif ^ fl2->oif) |
(fl1->iif ^ fl2->iif)) == 0;
}
static int dn_insert_route(struct dn_route *rt, unsigned hash, struct dn_route **rp)
{
struct dn_route *rth, **rthp;
unsigned long now = jiffies;
rthp = &dn_rt_hash_table[hash].chain;
spin_lock_bh(&dn_rt_hash_table[hash].lock);
while((rth = *rthp) != NULL) {
if (compare_keys(&rth->fl, &rt->fl)) {
/* Put it first */
*rthp = rth->u.dst.dn_next;
rcu_assign_pointer(rth->u.dst.dn_next,
dn_rt_hash_table[hash].chain);
rcu_assign_pointer(dn_rt_hash_table[hash].chain, rth);
dst_use(&rth->u.dst, now);
spin_unlock_bh(&dn_rt_hash_table[hash].lock);
dnrt_drop(rt);
*rp = rth;
return 0;
}
rthp = &rth->u.dst.dn_next;
}
rcu_assign_pointer(rt->u.dst.dn_next, dn_rt_hash_table[hash].chain);
rcu_assign_pointer(dn_rt_hash_table[hash].chain, rt);
dst_use(&rt->u.dst, now);
spin_unlock_bh(&dn_rt_hash_table[hash].lock);
*rp = rt;
return 0;
}
static void dn_run_flush(unsigned long dummy)
{
int i;
struct dn_route *rt, *next;
for(i = 0; i < dn_rt_hash_mask; i++) {
spin_lock_bh(&dn_rt_hash_table[i].lock);
if ((rt = xchg(&dn_rt_hash_table[i].chain, NULL)) == NULL)
goto nothing_to_declare;
for(; rt; rt=next) {
next = rt->u.dst.dn_next;
rt->u.dst.dn_next = NULL;
dst_free((struct dst_entry *)rt);
}
nothing_to_declare:
spin_unlock_bh(&dn_rt_hash_table[i].lock);
}
}
static DEFINE_SPINLOCK(dn_rt_flush_lock);
void dn_rt_cache_flush(int delay)
{
unsigned long now = jiffies;
int user_mode = !in_interrupt();
if (delay < 0)
delay = dn_rt_min_delay;
spin_lock_bh(&dn_rt_flush_lock);
if (del_timer(&dn_rt_flush_timer) && delay > 0 && dn_rt_deadline) {
long tmo = (long)(dn_rt_deadline - now);
if (user_mode && tmo < dn_rt_max_delay - dn_rt_min_delay)
tmo = 0;
if (delay > tmo)
delay = tmo;
}
if (delay <= 0) {
spin_unlock_bh(&dn_rt_flush_lock);
dn_run_flush(0);
return;
}
if (dn_rt_deadline == 0)
dn_rt_deadline = now + dn_rt_max_delay;
dn_rt_flush_timer.expires = now + delay;
add_timer(&dn_rt_flush_timer);
spin_unlock_bh(&dn_rt_flush_lock);
}
/**
* dn_return_short - Return a short packet to its sender
* @skb: The packet to return
*
*/
static int dn_return_short(struct sk_buff *skb)
{
struct dn_skb_cb *cb;
unsigned char *ptr;
__le16 *src;
__le16 *dst;
/* Add back headers */
skb_push(skb, skb->data - skb_network_header(skb));
if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL)
return NET_RX_DROP;
cb = DN_SKB_CB(skb);
/* Skip packet length and point to flags */
ptr = skb->data + 2;
*ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS;
dst = (__le16 *)ptr;
ptr += 2;
src = (__le16 *)ptr;
ptr += 2;
*ptr = 0; /* Zero hop count */
swap(*src, *dst);
skb->pkt_type = PACKET_OUTGOING;
dn_rt_finish_output(skb, NULL, NULL);
return NET_RX_SUCCESS;
}
/**
* dn_return_long - Return a long packet to its sender
* @skb: The long format packet to return
*
*/
static int dn_return_long(struct sk_buff *skb)
{
struct dn_skb_cb *cb;
unsigned char *ptr;
unsigned char *src_addr, *dst_addr;
unsigned char tmp[ETH_ALEN];
/* Add back all headers */
skb_push(skb, skb->data - skb_network_header(skb));
if ((skb = skb_unshare(skb, GFP_ATOMIC)) == NULL)
return NET_RX_DROP;
cb = DN_SKB_CB(skb);
/* Ignore packet length and point to flags */
ptr = skb->data + 2;
/* Skip padding */
if (*ptr & DN_RT_F_PF) {
char padlen = (*ptr & ~DN_RT_F_PF);
ptr += padlen;
}
*ptr++ = (cb->rt_flags & ~DN_RT_F_RQR) | DN_RT_F_RTS;
ptr += 2;
dst_addr = ptr;
ptr += 8;
src_addr = ptr;
ptr += 6;
*ptr = 0; /* Zero hop count */
/* Swap source and destination */
memcpy(tmp, src_addr, ETH_ALEN);
memcpy(src_addr, dst_addr, ETH_ALEN);
memcpy(dst_addr, tmp, ETH_ALEN);
skb->pkt_type = PACKET_OUTGOING;
dn_rt_finish_output(skb, dst_addr, src_addr);
return NET_RX_SUCCESS;
}
/**
* dn_route_rx_packet - Try and find a route for an incoming packet
* @skb: The packet to find a route for
*
* Returns: result of input function if route is found, error code otherwise
*/
static int dn_route_rx_packet(struct sk_buff *skb)
{
struct dn_skb_cb *cb = DN_SKB_CB(skb);
int err;
if ((err = dn_route_input(skb)) == 0)
return dst_input(skb);
if (decnet_debug_level & 4) {
char *devname = skb->dev ? skb->dev->name : "???";
struct dn_skb_cb *cb = DN_SKB_CB(skb);
printk(KERN_DEBUG
"DECnet: dn_route_rx_packet: rt_flags=0x%02x dev=%s len=%d src=0x%04hx dst=0x%04hx err=%d type=%d\n",
(int)cb->rt_flags, devname, skb->len,
le16_to_cpu(cb->src), le16_to_cpu(cb->dst),
err, skb->pkt_type);
}
if ((skb->pkt_type == PACKET_HOST) && (cb->rt_flags & DN_RT_F_RQR)) {
switch(cb->rt_flags & DN_RT_PKT_MSK) {
case DN_RT_PKT_SHORT:
return dn_return_short(skb);
case DN_RT_PKT_LONG:
return dn_return_long(skb);
}
}
kfree_skb(skb);
return NET_RX_DROP;
}
static int dn_route_rx_long(struct sk_buff *skb)
{
struct dn_skb_cb *cb = DN_SKB_CB(skb);
unsigned char *ptr = skb->data;
if (!pskb_may_pull(skb, 21)) /* 20 for long header, 1 for shortest nsp */
goto drop_it;
skb_pull(skb, 20);
skb_reset_transport_header(skb);
/* Destination info */
ptr += 2;
cb->dst = dn_eth2dn(ptr);
if (memcmp(ptr, dn_hiord_addr, 4) != 0)
goto drop_it;
ptr += 6;
/* Source info */
ptr += 2;
cb->src = dn_eth2dn(ptr);
if (memcmp(ptr, dn_hiord_addr, 4) != 0)
goto drop_it;
ptr += 6;
/* Other junk */
ptr++;
cb->hops = *ptr++; /* Visit Count */
return NF_HOOK(PF_DECnet, NF_DN_PRE_ROUTING, skb, skb->dev, NULL, dn_route_rx_packet);
drop_it:
kfree_skb(skb);
return NET_RX_DROP;
}
static int dn_route_rx_short(struct sk_buff *skb)
{
struct dn_skb_cb *cb = DN_SKB_CB(skb);
unsigned char *ptr = skb->data;
if (!pskb_may_pull(skb, 6)) /* 5 for short header + 1 for shortest nsp */
goto drop_it;
skb_pull(skb, 5);
skb_reset_transport_header(skb);
cb->dst = *(__le16 *)ptr;
ptr += 2;
cb->src = *(__le16 *)ptr;
ptr += 2;
cb->hops = *ptr & 0x3f;
return NF_HOOK(PF_DECnet, NF_DN_PRE_ROUTING, skb, skb->dev, NULL, dn_route_rx_packet);
drop_it:
kfree_skb(skb);
return NET_RX_DROP;
}
static int dn_route_discard(struct sk_buff *skb)
{
/*
* I know we drop the packet here, but thats considered success in
* this case
*/
kfree_skb(skb);
return NET_RX_SUCCESS;
}
static int dn_route_ptp_hello(struct sk_buff *skb)
{
dn_dev_hello(skb);
dn_neigh_pointopoint_hello(skb);
return NET_RX_SUCCESS;
}
int dn_route_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)
{
struct dn_skb_cb *cb;
unsigned char flags = 0;
__u16 len = le16_to_cpu(*(__le16 *)skb->data);
struct dn_dev *dn = (struct dn_dev *)dev->dn_ptr;
unsigned char padlen = 0;
if (!net_eq(dev_net(dev), &init_net))
goto dump_it;
if (dn == NULL)
goto dump_it;
if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
goto out;
if (!pskb_may_pull(skb, 3))
goto dump_it;
skb_pull(skb, 2);
if (len > skb->len)
goto dump_it;
skb_trim(skb, len);
flags = *skb->data;
cb = DN_SKB_CB(skb);
cb->stamp = jiffies;
cb->iif = dev->ifindex;
/*
* If we have padding, remove it.
*/
if (flags & DN_RT_F_PF) {
padlen = flags & ~DN_RT_F_PF;
if (!pskb_may_pull(skb, padlen + 1))
goto dump_it;
skb_pull(skb, padlen);
flags = *skb->data;
}
skb_reset_network_header(skb);
/*
* Weed out future version DECnet
*/
if (flags & DN_RT_F_VER)
goto dump_it;
cb->rt_flags = flags;
if (decnet_debug_level & 1)
printk(KERN_DEBUG
"dn_route_rcv: got 0x%02x from %s [%d %d %d]\n",
(int)flags, (dev) ? dev->name : "???", len, skb->len,
padlen);
if (flags & DN_RT_PKT_CNTL) {
if (unlikely(skb_linearize(skb)))
goto dump_it;
switch(flags & DN_RT_CNTL_MSK) {
case DN_RT_PKT_INIT:
dn_dev_init_pkt(skb);
break;
case DN_RT_PKT_VERI:
dn_dev_veri_pkt(skb);
break;
}
if (dn->parms.state != DN_DEV_S_RU)
goto dump_it;
switch(flags & DN_RT_CNTL_MSK) {
case DN_RT_PKT_HELO:
return NF_HOOK(PF_DECnet, NF_DN_HELLO, skb, skb->dev, NULL, dn_route_ptp_hello);
case DN_RT_PKT_L1RT:
case DN_RT_PKT_L2RT:
return NF_HOOK(PF_DECnet, NF_DN_ROUTE, skb, skb->dev, NULL, dn_route_discard);
case DN_RT_PKT_ERTH:
return NF_HOOK(PF_DECnet, NF_DN_HELLO, skb, skb->dev, NULL, dn_neigh_router_hello);
case DN_RT_PKT_EEDH:
return NF_HOOK(PF_DECnet, NF_DN_HELLO, skb, skb->dev, NULL, dn_neigh_endnode_hello);
}
} else {
if (dn->parms.state != DN_DEV_S_RU)
goto dump_it;
skb_pull(skb, 1); /* Pull flags */
switch(flags & DN_RT_PKT_MSK) {
case DN_RT_PKT_LONG:
return dn_route_rx_long(skb);
case DN_RT_PKT_SHORT:
return dn_route_rx_short(skb);
}
}
dump_it:
kfree_skb(skb);
out:
return NET_RX_DROP;
}
static int dn_output(struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
struct dn_route *rt = (struct dn_route *)dst;
struct net_device *dev = dst->dev;
struct dn_skb_cb *cb = DN_SKB_CB(skb);
struct neighbour *neigh;
int err = -EINVAL;
if ((neigh = dst->neighbour) == NULL)
goto error;
skb->dev = dev;
cb->src = rt->rt_saddr;
cb->dst = rt->rt_daddr;
/*
* Always set the Intra-Ethernet bit on all outgoing packets
* originated on this node. Only valid flag from upper layers
* is return-to-sender-requested. Set hop count to 0 too.
*/
cb->rt_flags &= ~DN_RT_F_RQR;
cb->rt_flags |= DN_RT_F_IE;
cb->hops = 0;
return NF_HOOK(PF_DECnet, NF_DN_LOCAL_OUT, skb, NULL, dev, neigh->output);
error:
if (net_ratelimit())
printk(KERN_DEBUG "dn_output: This should not happen\n");
kfree_skb(skb);
return err;
}
static int dn_forward(struct sk_buff *skb)
{
struct dn_skb_cb *cb = DN_SKB_CB(skb);
struct dst_entry *dst = skb_dst(skb);
struct dn_dev *dn_db = dst->dev->dn_ptr;
struct dn_route *rt;
struct neighbour *neigh = dst->neighbour;
int header_len;
#ifdef CONFIG_NETFILTER
struct net_device *dev = skb->dev;
#endif
if (skb->pkt_type != PACKET_HOST)
goto drop;
/* Ensure that we have enough space for headers */
rt = (struct dn_route *)skb_dst(skb);
header_len = dn_db->use_long ? 21 : 6;
if (skb_cow(skb, LL_RESERVED_SPACE(rt->u.dst.dev)+header_len))
goto drop;
/*
* Hop count exceeded.
*/
if (++cb->hops > 30)
goto drop;
skb->dev = rt->u.dst.dev;
/*
* If packet goes out same interface it came in on, then set
* the Intra-Ethernet bit. This has no effect for short
* packets, so we don't need to test for them here.
*/
cb->rt_flags &= ~DN_RT_F_IE;
if (rt->rt_flags & RTCF_DOREDIRECT)
cb->rt_flags |= DN_RT_F_IE;
return NF_HOOK(PF_DECnet, NF_DN_FORWARD, skb, dev, skb->dev, neigh->output);
drop:
kfree_skb(skb);
return NET_RX_DROP;
}
/*
* Used to catch bugs. This should never normally get
* called.
*/
static int dn_rt_bug(struct sk_buff *skb)
{
if (net_ratelimit()) {
struct dn_skb_cb *cb = DN_SKB_CB(skb);
printk(KERN_DEBUG "dn_rt_bug: skb from:%04x to:%04x\n",
le16_to_cpu(cb->src), le16_to_cpu(cb->dst));
}
kfree_skb(skb);
return NET_RX_DROP;
}
static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res)
{
struct dn_fib_info *fi = res->fi;
struct net_device *dev = rt->u.dst.dev;
struct neighbour *n;
unsigned mss;
if (fi) {
if (DN_FIB_RES_GW(*res) &&
DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = DN_FIB_RES_GW(*res);
memcpy(rt->u.dst.metrics, fi->fib_metrics,
sizeof(rt->u.dst.metrics));
}
rt->rt_type = res->type;
if (dev != NULL && rt->u.dst.neighbour == NULL) {
n = __neigh_lookup_errno(&dn_neigh_table, &rt->rt_gateway, dev);
if (IS_ERR(n))
return PTR_ERR(n);
rt->u.dst.neighbour = n;
}
if (dst_metric(&rt->u.dst, RTAX_MTU) == 0 ||
dst_metric(&rt->u.dst, RTAX_MTU) > rt->u.dst.dev->mtu)
rt->u.dst.metrics[RTAX_MTU-1] = rt->u.dst.dev->mtu;
mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->u.dst));
if (dst_metric(&rt->u.dst, RTAX_ADVMSS) == 0 ||
dst_metric(&rt->u.dst, RTAX_ADVMSS) > mss)
rt->u.dst.metrics[RTAX_ADVMSS-1] = mss;
return 0;
}
static inline int dn_match_addr(__le16 addr1, __le16 addr2)
{
__u16 tmp = le16_to_cpu(addr1) ^ le16_to_cpu(addr2);
int match = 16;
while(tmp) {
tmp >>= 1;
match--;
}
return match;
}
static __le16 dnet_select_source(const struct net_device *dev, __le16 daddr, int scope)
{
__le16 saddr = 0;
struct dn_dev *dn_db = dev->dn_ptr;
struct dn_ifaddr *ifa;
int best_match = 0;
int ret;
read_lock(&dev_base_lock);
for(ifa = dn_db->ifa_list; ifa; ifa = ifa->ifa_next) {
if (ifa->ifa_scope > scope)
continue;
if (!daddr) {
saddr = ifa->ifa_local;
break;
}
ret = dn_match_addr(daddr, ifa->ifa_local);
if (ret > best_match)
saddr = ifa->ifa_local;
if (best_match == 0)
saddr = ifa->ifa_local;
}
read_unlock(&dev_base_lock);
return saddr;
}
static inline __le16 __dn_fib_res_prefsrc(struct dn_fib_res *res)
{
return dnet_select_source(DN_FIB_RES_DEV(*res), DN_FIB_RES_GW(*res), res->scope);
}
static inline __le16 dn_fib_rules_map_destination(__le16 daddr, struct dn_fib_res *res)
{
__le16 mask = dnet_make_mask(res->prefixlen);
return (daddr&~mask)|res->fi->fib_nh->nh_gw;
}
static int dn_route_output_slow(struct dst_entry **pprt, const struct flowi *oldflp, int try_hard)
{
struct flowi fl = { .nl_u = { .dn_u =
{ .daddr = oldflp->fld_dst,
.saddr = oldflp->fld_src,
.scope = RT_SCOPE_UNIVERSE,
} },
.mark = oldflp->mark,
.iif = init_net.loopback_dev->ifindex,
.oif = oldflp->oif };
struct dn_route *rt = NULL;
struct net_device *dev_out = NULL, *dev;
struct neighbour *neigh = NULL;
unsigned hash;
unsigned flags = 0;
struct dn_fib_res res = { .fi = NULL, .type = RTN_UNICAST };
int err;
int free_res = 0;
__le16 gateway = 0;
if (decnet_debug_level & 16)
printk(KERN_DEBUG
"dn_route_output_slow: dst=%04x src=%04x mark=%d"
" iif=%d oif=%d\n", le16_to_cpu(oldflp->fld_dst),
le16_to_cpu(oldflp->fld_src),
oldflp->mark, init_net.loopback_dev->ifindex, oldflp->oif);
/* If we have an output interface, verify its a DECnet device */
if (oldflp->oif) {
dev_out = dev_get_by_index(&init_net, oldflp->oif);
err = -ENODEV;
if (dev_out && dev_out->dn_ptr == NULL) {
dev_put(dev_out);
dev_out = NULL;
}
if (dev_out == NULL)
goto out;
}
/* If we have a source address, verify that its a local address */
if (oldflp->fld_src) {
err = -EADDRNOTAVAIL;
if (dev_out) {
if (dn_dev_islocal(dev_out, oldflp->fld_src))
goto source_ok;
dev_put(dev_out);
goto out;
}
rcu_read_lock();
for_each_netdev_rcu(&init_net, dev) {
if (!dev->dn_ptr)
continue;
if (!dn_dev_islocal(dev, oldflp->fld_src))
continue;
if ((dev->flags & IFF_LOOPBACK) &&
oldflp->fld_dst &&
!dn_dev_islocal(dev, oldflp->fld_dst))
continue;
dev_out = dev;
break;
}
rcu_read_unlock();
if (dev_out == NULL)
goto out;
dev_hold(dev_out);
source_ok:
;
}
/* No destination? Assume its local */
if (!fl.fld_dst) {
fl.fld_dst = fl.fld_src;
err = -EADDRNOTAVAIL;
if (dev_out)
dev_put(dev_out);
dev_out = init_net.loopback_dev;
dev_hold(dev_out);
if (!fl.fld_dst) {
fl.fld_dst =
fl.fld_src = dnet_select_source(dev_out, 0,
RT_SCOPE_HOST);
if (!fl.fld_dst)
goto out;
}
fl.oif = init_net.loopback_dev->ifindex;
res.type = RTN_LOCAL;
goto make_route;
}
if (decnet_debug_level & 16)
printk(KERN_DEBUG
"dn_route_output_slow: initial checks complete."
" dst=%o4x src=%04x oif=%d try_hard=%d\n",
le16_to_cpu(fl.fld_dst), le16_to_cpu(fl.fld_src),
fl.oif, try_hard);
/*
* N.B. If the kernel is compiled without router support then
* dn_fib_lookup() will evaluate to non-zero so this if () block
* will always be executed.
*/
err = -ESRCH;
if (try_hard || (err = dn_fib_lookup(&fl, &res)) != 0) {
struct dn_dev *dn_db;
if (err != -ESRCH)
goto out;
/*
* Here the fallback is basically the standard algorithm for
* routing in endnodes which is described in the DECnet routing
* docs
*
* If we are not trying hard, look in neighbour cache.
* The result is tested to ensure that if a specific output
* device/source address was requested, then we honour that
* here
*/
if (!try_hard) {
neigh = neigh_lookup_nodev(&dn_neigh_table, &init_net, &fl.fld_dst);
if (neigh) {
if ((oldflp->oif &&
(neigh->dev->ifindex != oldflp->oif)) ||
(oldflp->fld_src &&
(!dn_dev_islocal(neigh->dev,
oldflp->fld_src)))) {
neigh_release(neigh);
neigh = NULL;
} else {
if (dev_out)
dev_put(dev_out);
if (dn_dev_islocal(neigh->dev, fl.fld_dst)) {
dev_out = init_net.loopback_dev;
res.type = RTN_LOCAL;
} else {
dev_out = neigh->dev;
}
dev_hold(dev_out);