summaryrefslogtreecommitdiff
path: root/net/mctp/route.c
blob: a953f83ed02bb7ee1618d04187ab7f526d2dd41b (plain)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
// SPDX-License-Identifier: GPL-2.0
/*
 * Management Component Transport Protocol (MCTP) - routing
 * implementation.
 *
 * This is currently based on a simple routing table, with no dst cache. The
 * number of routes should stay fairly small, so the lookup cost is small.
 *
 * Copyright (c) 2021 Code Construct
 * Copyright (c) 2021 Google
 */

#include <linux/idr.h>
#include <linux/mctp.h>
#include <linux/netdevice.h>
#include <linux/rtnetlink.h>
#include <linux/skbuff.h>

#include <uapi/linux/if_arp.h>

#include <net/mctp.h>
#include <net/mctpdevice.h>
#include <net/netlink.h>
#include <net/sock.h>

static const unsigned int mctp_message_maxlen = 64 * 1024;

/* route output callbacks */
static int mctp_route_discard(struct mctp_route *route, struct sk_buff *skb)
{
	kfree_skb(skb);
	return 0;
}

static struct mctp_sock *mctp_lookup_bind(struct net *net, struct sk_buff *skb)
{
	struct mctp_skb_cb *cb = mctp_cb(skb);
	struct mctp_hdr *mh;
	struct sock *sk;
	u8 type;

	WARN_ON(!rcu_read_lock_held());

	/* TODO: look up in skb->cb? */
	mh = mctp_hdr(skb);

	if (!skb_headlen(skb))
		return NULL;

	type = (*(u8 *)skb->data) & 0x7f;

	sk_for_each_rcu(sk, &net->mctp.binds) {
		struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);

		if (msk->bind_net != MCTP_NET_ANY && msk->bind_net != cb->net)
			continue;

		if (msk->bind_type != type)
			continue;

		if (msk->bind_addr != MCTP_ADDR_ANY &&
		    msk->bind_addr != mh->dest)
			continue;

		return msk;
	}

	return NULL;
}

static bool mctp_key_match(struct mctp_sk_key *key, mctp_eid_t local,
			   mctp_eid_t peer, u8 tag)
{
	if (key->local_addr != local)
		return false;

	if (key->peer_addr != peer)
		return false;

	if (key->tag != tag)
		return false;

	return true;
}

static struct mctp_sk_key *mctp_lookup_key(struct net *net, struct sk_buff *skb,
					   mctp_eid_t peer)
{
	struct mctp_sk_key *key, *ret;
	struct mctp_hdr *mh;
	u8 tag;

	WARN_ON(!rcu_read_lock_held());

	mh = mctp_hdr(skb);
	tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);

	ret = NULL;

	hlist_for_each_entry_rcu(key, &net->mctp.keys, hlist) {
		if (mctp_key_match(key, mh->dest, peer, tag)) {
			ret = key;
			break;
		}
	}

	return ret;
}

static struct mctp_sk_key *mctp_key_alloc(struct mctp_sock *msk,
					  mctp_eid_t local, mctp_eid_t peer,
					  u8 tag, gfp_t gfp)
{
	struct mctp_sk_key *key;

	key = kzalloc(sizeof(*key), gfp);
	if (!key)
		return NULL;

	key->peer_addr = peer;
	key->local_addr = local;
	key->tag = tag;
	key->sk = &msk->sk;
	spin_lock_init(&key->reasm_lock);

	return key;
}

static int mctp_key_add(struct mctp_sk_key *key, struct mctp_sock *msk)
{
	struct net *net = sock_net(&msk->sk);
	struct mctp_sk_key *tmp;
	unsigned long flags;
	int rc = 0;

	spin_lock_irqsave(&net->mctp.keys_lock, flags);

	hlist_for_each_entry(tmp, &net->mctp.keys, hlist) {
		if (mctp_key_match(tmp, key->local_addr, key->peer_addr,
				   key->tag)) {
			rc = -EEXIST;
			break;
		}
	}

	if (!rc) {
		hlist_add_head(&key->hlist, &net->mctp.keys);
		hlist_add_head(&key->sklist, &msk->keys);
	}

	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);

	return rc;
}

/* Must be called with key->reasm_lock, which it will release. Will schedule
 * the key for an RCU free.
 */
static void __mctp_key_unlock_drop(struct mctp_sk_key *key, struct net *net,
				   unsigned long flags)
	__releases(&key->reasm_lock)
{
	struct sk_buff *skb;

	skb = key->reasm_head;
	key->reasm_head = NULL;
	key->reasm_dead = true;
	spin_unlock_irqrestore(&key->reasm_lock, flags);

	spin_lock_irqsave(&net->mctp.keys_lock, flags);
	hlist_del_rcu(&key->hlist);
	hlist_del_rcu(&key->sklist);
	spin_unlock_irqrestore(&net->mctp.keys_lock, flags);
	kfree_rcu(key, rcu);

	if (skb)
		kfree_skb(skb);
}

static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
{
	struct mctp_hdr *hdr = mctp_hdr(skb);
	u8 exp_seq, this_seq;

	this_seq = (hdr->flags_seq_tag >> MCTP_HDR_SEQ_SHIFT)
		& MCTP_HDR_SEQ_MASK;

	if (!key->reasm_head) {
		key->reasm_head = skb;
		key->reasm_tailp = &(skb_shinfo(skb)->frag_list);
		key->last_seq = this_seq;
		return 0;
	}

	exp_seq = (key->last_seq + 1) & MCTP_HDR_SEQ_MASK;

	if (this_seq != exp_seq)
		return -EINVAL;

	if (key->reasm_head->len + skb->len > mctp_message_maxlen)
		return -EINVAL;

	skb->next = NULL;
	skb->sk = NULL;
	*key->reasm_tailp = skb;
	key->reasm_tailp = &skb->next;

	key->last_seq = this_seq;

	key->reasm_head->data_len += skb->len;
	key->reasm_head->len += skb->len;
	key->reasm_head->truesize += skb->truesize;

	return 0;
}

static int mctp_route_input(struct mctp_route *route, struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	struct mctp_sk_key *key;
	struct mctp_sock *msk;
	struct mctp_hdr *mh;
	unsigned long f;
	u8 tag, flags;
	int rc;

	msk = NULL;
	rc = -EINVAL;

	/* we may be receiving a locally-routed packet; drop source sk
	 * accounting
	 */
	skb_orphan(skb);

	/* ensure we have enough data for a header and a type */
	if (skb->len < sizeof(struct mctp_hdr) + 1)
		goto out;

	/* grab header, advance data ptr */
	mh = mctp_hdr(skb);
	skb_pull(skb, sizeof(struct mctp_hdr));

	if (mh->ver != 1)
		goto out;

	flags = mh->flags_seq_tag & (MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM);
	tag = mh->flags_seq_tag & (MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);

	rcu_read_lock();

	/* lookup socket / reasm context, exactly matching (src,dest,tag) */
	key = mctp_lookup_key(net, skb, mh->src);

	if (flags & MCTP_HDR_FLAG_SOM) {
		if (key) {
			msk = container_of(key->sk, struct mctp_sock, sk);
		} else {
			/* first response to a broadcast? do a more general
			 * key lookup to find the socket, but don't use this
			 * key for reassembly - we'll create a more specific
			 * one for future packets if required (ie, !EOM).
			 */
			key = mctp_lookup_key(net, skb, MCTP_ADDR_ANY);
			if (key) {
				msk = container_of(key->sk,
						   struct mctp_sock, sk);
				key = NULL;
			}
		}

		if (!key && !msk && (tag & MCTP_HDR_FLAG_TO))
			msk = mctp_lookup_bind(net, skb);

		if (!msk) {
			rc = -ENOENT;
			goto out_unlock;
		}

		/* single-packet message? deliver to socket, clean up any
		 * pending key.
		 */
		if (flags & MCTP_HDR_FLAG_EOM) {
			sock_queue_rcv_skb(&msk->sk, skb);
			if (key) {
				spin_lock_irqsave(&key->reasm_lock, f);
				/* we've hit a pending reassembly; not much we
				 * can do but drop it
				 */
				__mctp_key_unlock_drop(key, net, f);
			}
			rc = 0;
			goto out_unlock;
		}

		/* broadcast response or a bind() - create a key for further
		 * packets for this message
		 */
		if (!key) {
			key = mctp_key_alloc(msk, mh->dest, mh->src,
					     tag, GFP_ATOMIC);
			if (!key) {
				rc = -ENOMEM;
				goto out_unlock;
			}

			/* we can queue without the reasm lock here, as the
			 * key isn't observable yet
			 */
			mctp_frag_queue(key, skb);

			/* if the key_add fails, we've raced with another
			 * SOM packet with the same src, dest and tag. There's
			 * no way to distinguish future packets, so all we
			 * can do is drop; we'll free the skb on exit from
			 * this function.
			 */
			rc = mctp_key_add(key, msk);
			if (rc)
				kfree(key);

		} else {
			/* existing key: start reassembly */
			spin_lock_irqsave(&key->reasm_lock, f);

			if (key->reasm_head || key->reasm_dead) {
				/* duplicate start? drop everything */
				__mctp_key_unlock_drop(key, net, f);
				rc = -EEXIST;
			} else {
				rc = mctp_frag_queue(key, skb);
				spin_unlock_irqrestore(&key->reasm_lock, f);
			}
		}

	} else if (key) {
		/* this packet continues a previous message; reassemble
		 * using the message-specific key
		 */

		spin_lock_irqsave(&key->reasm_lock, f);

		/* we need to be continuing an existing reassembly... */
		if (!key->reasm_head)
			rc = -EINVAL;
		else
			rc = mctp_frag_queue(key, skb);

		/* end of message? deliver to socket, and we're done with
		 * the reassembly/response key
		 */
		if (!rc && flags & MCTP_HDR_FLAG_EOM) {
			sock_queue_rcv_skb(key->sk, key->reasm_head);
			key->reasm_head = NULL;
			__mctp_key_unlock_drop(key, net, f);
		} else {
			spin_unlock_irqrestore(&key->reasm_lock, f);
		}

	} else {
		/* not a start, no matching key */
		rc = -ENOENT;
	}

out_unlock:
	rcu_read_unlock();
out:
	if (rc)
		kfree_skb(skb);
	return rc;
}

static unsigned int mctp_route_mtu(struct mctp_route *rt)
{
	return rt->mtu ?: READ_ONCE(rt->dev->dev->mtu);
}

static int mctp_route_output(struct mctp_route *route, struct sk_buff *skb)
{
	struct mctp_hdr *hdr = mctp_hdr(skb);
	char daddr_buf[MAX_ADDR_LEN];
	char *daddr = NULL;
	unsigned int mtu;
	int rc;

	skb->protocol = htons(ETH_P_MCTP);

	mtu = READ_ONCE(skb->dev->mtu);
	if (skb->len > mtu) {
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	/* If lookup fails let the device handle daddr==NULL */
	if (mctp_neigh_lookup(route->dev, hdr->dest, daddr_buf) == 0)
		daddr = daddr_buf;

	rc = dev_hard_header(skb, skb->dev, ntohs(skb->protocol),
			     daddr, skb->dev->dev_addr, skb->len);
	if (rc) {
		kfree_skb(skb);
		return -EHOSTUNREACH;
	}

	rc = dev_queue_xmit(skb);
	if (rc)
		rc = net_xmit_errno(rc);

	return rc;
}

/* route alloc/release */
static void mctp_route_release(struct mctp_route *rt)
{
	if (refcount_dec_and_test(&rt->refs)) {
		dev_put(rt->dev->dev);
		kfree_rcu(rt, rcu);
	}
}

/* returns a route with the refcount at 1 */
static struct mctp_route *mctp_route_alloc(void)
{
	struct mctp_route *rt;

	rt = kzalloc(sizeof(*rt), GFP_KERNEL);
	if (!rt)
		return NULL;

	INIT_LIST_HEAD(&rt->list);
	refcount_set(&rt->refs, 1);
	rt->output = mctp_route_discard;

	return rt;
}

unsigned int mctp_default_net(struct net *net)
{
	return READ_ONCE(net->mctp.default_net);
}

int mctp_default_net_set(struct net *net, unsigned int index)
{
	if (index == 0)
		return -EINVAL;
	WRITE_ONCE(net->mctp.default_net, index);
	return 0;
}

/* tag management */
static void mctp_reserve_tag(struct net *net, struct mctp_sk_key *key,
			     struct mctp_sock *msk)
{
	struct netns_mctp *mns = &net->mctp;

	lockdep_assert_held(&mns->keys_lock);

	/* we hold the net->key_lock here, allowing updates to both
	 * then net and sk
	 */
	hlist_add_head_rcu(&key->hlist, &mns->keys);
	hlist_add_head_rcu(&key->sklist, &msk->keys);
}

/* Allocate a locally-owned tag value for (saddr, daddr), and reserve
 * it for the socket msk
 */
static int mctp_alloc_local_tag(struct mctp_sock *msk,
				mctp_eid_t saddr, mctp_eid_t daddr, u8 *tagp)
{
	struct net *net = sock_net(&msk->sk);
	struct netns_mctp *mns = &net->mctp;
	struct mctp_sk_key *key, *tmp;
	unsigned long flags;
	int rc = -EAGAIN;
	u8 tagbits;

	/* be optimistic, alloc now */
	key = mctp_key_alloc(msk, saddr, daddr, 0, GFP_KERNEL);
	if (!key)
		return -ENOMEM;

	/* 8 possible tag values */
	tagbits = 0xff;

	spin_lock_irqsave(&mns->keys_lock, flags);

	/* Walk through the existing keys, looking for potential conflicting
	 * tags. If we find a conflict, clear that bit from tagbits
	 */
	hlist_for_each_entry(tmp, &mns->keys, hlist) {
		/* if we don't own the tag, it can't conflict */
		if (tmp->tag & MCTP_HDR_FLAG_TO)
			continue;

		if ((tmp->peer_addr == daddr ||
		     tmp->peer_addr == MCTP_ADDR_ANY) &&
		    tmp->local_addr == saddr)
			tagbits &= ~(1 << tmp->tag);

		if (!tagbits)
			break;
	}

	if (tagbits) {
		key->tag = __ffs(tagbits);
		mctp_reserve_tag(net, key, msk);
		*tagp = key->tag;
		rc = 0;
	}

	spin_unlock_irqrestore(&mns->keys_lock, flags);

	if (!tagbits)
		kfree(key);

	return rc;
}

/* routing lookups */
static bool mctp_rt_match_eid(struct mctp_route *rt,
			      unsigned int net, mctp_eid_t eid)
{
	return READ_ONCE(rt->dev->net) == net &&
		rt->min <= eid && rt->max >= eid;
}

/* compares match, used for duplicate prevention */
static bool mctp_rt_compare_exact(struct mctp_route *rt1,
				  struct mctp_route *rt2)
{
	ASSERT_RTNL();
	return rt1->dev->net == rt2->dev->net &&
		rt1->min == rt2->min &&
		rt1->max == rt2->max;
}

struct mctp_route *mctp_route_lookup(struct net *net, unsigned int dnet,
				     mctp_eid_t daddr)
{
	struct mctp_route *tmp, *rt = NULL;

	list_for_each_entry_rcu(tmp, &net->mctp.routes, list) {
		/* TODO: add metrics */
		if (mctp_rt_match_eid(tmp, dnet, daddr)) {
			if (refcount_inc_not_zero(&tmp->refs)) {
				rt = tmp;
				break;
			}
		}
	}

	return rt;
}

/* sends a skb to rt and releases the route. */
int mctp_do_route(struct mctp_route *rt, struct sk_buff *skb)
{
	int rc;

	rc = rt->output(rt, skb);
	mctp_route_release(rt);
	return rc;
}

static int mctp_do_fragment_route(struct mctp_route *rt, struct sk_buff *skb,
				  unsigned int mtu, u8 tag)
{
	const unsigned int hlen = sizeof(struct mctp_hdr);
	struct mctp_hdr *hdr, *hdr2;
	unsigned int pos, size;
	struct sk_buff *skb2;
	int rc;
	u8 seq;

	hdr = mctp_hdr(skb);
	seq = 0;
	rc = 0;

	if (mtu < hlen + 1) {
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	/* we've got the header */
	skb_pull(skb, hlen);

	for (pos = 0; pos < skb->len;) {
		/* size of message payload */
		size = min(mtu - hlen, skb->len - pos);

		skb2 = alloc_skb(MCTP_HEADER_MAXLEN + hlen + size, GFP_KERNEL);
		if (!skb2) {
			rc = -ENOMEM;
			break;
		}

		/* generic skb copy */
		skb2->protocol = skb->protocol;
		skb2->priority = skb->priority;
		skb2->dev = skb->dev;
		memcpy(skb2->cb, skb->cb, sizeof(skb2->cb));

		if (skb->sk)
			skb_set_owner_w(skb2, skb->sk);

		/* establish packet */
		skb_reserve(skb2, MCTP_HEADER_MAXLEN);
		skb_reset_network_header(skb2);
		skb_put(skb2, hlen + size);
		skb2->transport_header = skb2->network_header + hlen;

		/* copy header fields, calculate SOM/EOM flags & seq */
		hdr2 = mctp_hdr(skb2);
		hdr2->ver = hdr->ver;
		hdr2->dest = hdr->dest;
		hdr2->src = hdr->src;
		hdr2->flags_seq_tag = tag &
			(MCTP_HDR_TAG_MASK | MCTP_HDR_FLAG_TO);

		if (pos == 0)
			hdr2->flags_seq_tag |= MCTP_HDR_FLAG_SOM;

		if (pos + size == skb->len)
			hdr2->flags_seq_tag |= MCTP_HDR_FLAG_EOM;

		hdr2->flags_seq_tag |= seq << MCTP_HDR_SEQ_SHIFT;

		/* copy message payload */
		skb_copy_bits(skb, pos, skb_transport_header(skb2), size);

		/* do route, but don't drop the rt reference */
		rc = rt->output(rt, skb2);
		if (rc)
			break;

		seq = (seq + 1) & MCTP_HDR_SEQ_MASK;
		pos += size;
	}

	mctp_route_release(rt);
	consume_skb(skb);
	return rc;
}

int mctp_local_output(struct sock *sk, struct mctp_route *rt,
		      struct sk_buff *skb, mctp_eid_t daddr, u8 req_tag)
{
	struct mctp_sock *msk = container_of(sk, struct mctp_sock, sk);
	struct mctp_skb_cb *cb = mctp_cb(skb);
	struct mctp_hdr *hdr;
	unsigned long flags;
	unsigned int mtu;
	mctp_eid_t saddr;
	int rc;
	u8 tag;

	if (WARN_ON(!rt->dev))
		return -EINVAL;

	spin_lock_irqsave(&rt->dev->addrs_lock, flags);
	if (rt->dev->num_addrs == 0) {
		rc = -EHOSTUNREACH;
	} else {
		/* use the outbound interface's first address as our source */
		saddr = rt->dev->addrs[0];
		rc = 0;
	}
	spin_unlock_irqrestore(&rt->dev->addrs_lock, flags);

	if (rc)
		return rc;

	if (req_tag & MCTP_HDR_FLAG_TO) {
		rc = mctp_alloc_local_tag(msk, saddr, daddr, &tag);
		if (rc)
			return rc;
		tag |= MCTP_HDR_FLAG_TO;
	} else {
		tag = req_tag;
	}


	skb->protocol = htons(ETH_P_MCTP);
	skb->priority = 0;
	skb_reset_transport_header(skb);
	skb_push(skb, sizeof(struct mctp_hdr));
	skb_reset_network_header(skb);
	skb->dev = rt->dev->dev;

	/* cb->net will have been set on initial ingress */
	cb->src = saddr;

	/* set up common header fields */
	hdr = mctp_hdr(skb);
	hdr->ver = 1;
	hdr->dest = daddr;
	hdr->src = saddr;

	mtu = mctp_route_mtu(rt);

	if (skb->len + sizeof(struct mctp_hdr) <= mtu) {
		hdr->flags_seq_tag = MCTP_HDR_FLAG_SOM | MCTP_HDR_FLAG_EOM |
			tag;
		return mctp_do_route(rt, skb);
	} else {
		return mctp_do_fragment_route(rt, skb, mtu, tag);
	}
}

/* route management */
static int mctp_route_add(struct mctp_dev *mdev, mctp_eid_t daddr_start,
			  unsigned int daddr_extent, unsigned int mtu,
			  unsigned char type)
{
	int (*rtfn)(struct mctp_route *rt, struct sk_buff *skb);
	struct net *net = dev_net(mdev->dev);
	struct mctp_route *rt, *ert;

	if (!mctp_address_ok(daddr_start))
		return -EINVAL;

	if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255)
		return -EINVAL;

	switch (type) {
	case RTN_LOCAL:
		rtfn = mctp_route_input;
		break;
	case RTN_UNICAST:
		rtfn = mctp_route_output;
		break;
	default:
		return -EINVAL;
	}

	rt = mctp_route_alloc();
	if (!rt)
		return -ENOMEM;

	rt->min = daddr_start;
	rt->max = daddr_start + daddr_extent;
	rt->mtu = mtu;
	rt->dev = mdev;
	dev_hold(rt->dev->dev);
	rt->type = type;
	rt->output = rtfn;

	ASSERT_RTNL();
	/* Prevent duplicate identical routes. */
	list_for_each_entry(ert, &net->mctp.routes, list) {
		if (mctp_rt_compare_exact(rt, ert)) {
			mctp_route_release(rt);
			return -EEXIST;
		}
	}

	list_add_rcu(&rt->list, &net->mctp.routes);

	return 0;
}

static int mctp_route_remove(struct mctp_dev *mdev, mctp_eid_t daddr_start,
			     unsigned int daddr_extent)
{
	struct net *net = dev_net(mdev->dev);
	struct mctp_route *rt, *tmp;
	mctp_eid_t daddr_end;
	bool dropped;

	if (daddr_extent > 0xff || daddr_start + daddr_extent >= 255)
		return -EINVAL;

	daddr_end = daddr_start + daddr_extent;
	dropped = false;

	ASSERT_RTNL();

	list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) {
		if (rt->dev == mdev &&
		    rt->min == daddr_start && rt->max == daddr_end) {
			list_del_rcu(&rt->list);
			/* TODO: immediate RTM_DELROUTE */
			mctp_route_release(rt);
			dropped = true;
		}
	}

	return dropped ? 0 : -ENOENT;
}

int mctp_route_add_local(struct mctp_dev *mdev, mctp_eid_t addr)
{
	return mctp_route_add(mdev, addr, 0, 0, RTN_LOCAL);
}

int mctp_route_remove_local(struct mctp_dev *mdev, mctp_eid_t addr)
{
	return mctp_route_remove(mdev, addr, 0);
}

/* removes all entries for a given device */
void mctp_route_remove_dev(struct mctp_dev *mdev)
{
	struct net *net = dev_net(mdev->dev);
	struct mctp_route *rt, *tmp;

	ASSERT_RTNL();
	list_for_each_entry_safe(rt, tmp, &net->mctp.routes, list) {
		if (rt->dev == mdev) {
			list_del_rcu(&rt->list);
			/* TODO: immediate RTM_DELROUTE */
			mctp_route_release(rt);
		}
	}
}

/* Incoming packet-handling */

static int mctp_pkttype_receive(struct sk_buff *skb, struct net_device *dev,
				struct packet_type *pt,
				struct net_device *orig_dev)
{
	struct net *net = dev_net(dev);
	struct mctp_dev *mdev;
	struct mctp_skb_cb *cb;
	struct mctp_route *rt;
	struct mctp_hdr *mh;

	rcu_read_lock();
	mdev = __mctp_dev_get(dev);
	rcu_read_unlock();
	if (!mdev) {
		/* basic non-data sanity checks */
		goto err_drop;
	}

	if (!pskb_may_pull(skb, sizeof(struct mctp_hdr)))
		goto err_drop;

	skb_reset_transport_header(skb);
	skb_reset_network_header(skb);

	/* We have enough for a header; decode and route */
	mh = mctp_hdr(skb);
	if (mh->ver < MCTP_VER_MIN || mh->ver > MCTP_VER_MAX)
		goto err_drop;

	cb = __mctp_cb(skb);
	cb->net = READ_ONCE(mdev->net);

	rt = mctp_route_lookup(net, cb->net, mh->dest);
	if (!rt)
		goto err_drop;

	mctp_do_route(rt, skb);

	return NET_RX_SUCCESS;

err_drop:
	kfree_skb(skb);
	return NET_RX_DROP;
}

static struct packet_type mctp_packet_type = {
	.type = cpu_to_be16(ETH_P_MCTP),
	.func = mctp_pkttype_receive,
};

/* netlink interface */

static const struct nla_policy rta_mctp_policy[RTA_MAX + 1] = {
	[RTA_DST]		= { .type = NLA_U8 },
	[RTA_METRICS]		= { .type = NLA_NESTED },
	[RTA_OIF]		= { .type = NLA_U32 },
};

/* Common part for RTM_NEWROUTE and RTM_DELROUTE parsing.
 * tb must hold RTA_MAX+1 elements.
 */
static int mctp_route_nlparse(struct sk_buff *skb, struct nlmsghdr *nlh,
			      struct netlink_ext_ack *extack,
			      struct nlattr **tb, struct rtmsg **rtm,
			      struct mctp_dev **mdev, mctp_eid_t *daddr_start)
{
	struct net *net = sock_net(skb->sk);
	struct net_device *dev;
	unsigned int ifindex;
	int rc;

	rc = nlmsg_parse(nlh, sizeof(struct rtmsg), tb, RTA_MAX,
			 rta_mctp_policy, extack);
	if (rc < 0) {
		NL_SET_ERR_MSG(extack, "incorrect format");
		return rc;
	}

	if (!tb[RTA_DST]) {
		NL_SET_ERR_MSG(extack, "dst EID missing");
		return -EINVAL;
	}
	*daddr_start = nla_get_u8(tb[RTA_DST]);

	if (!tb[RTA_OIF]) {
		NL_SET_ERR_MSG(extack, "ifindex missing");
		return -EINVAL;
	}
	ifindex = nla_get_u32(tb[RTA_OIF]);

	*rtm = nlmsg_data(nlh);
	if ((*rtm)->rtm_family != AF_MCTP) {
		NL_SET_ERR_MSG(extack, "route family must be AF_MCTP");
		return -EINVAL;
	}

	dev = __dev_get_by_index(net, ifindex);
	if (!dev) {
		NL_SET_ERR_MSG(extack, "bad ifindex");
		return -ENODEV;
	}
	*mdev = mctp_dev_get_rtnl(dev);
	if (!*mdev)
		return -ENODEV;

	if (dev->flags & IFF_LOOPBACK) {
		NL_SET_ERR_MSG(extack, "no routes to loopback");
		return -EINVAL;
	}

	return 0;
}

static int mctp_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
			 struct netlink_ext_ack *extack)
{
	struct nlattr *tb[RTA_MAX + 1];
	mctp_eid_t daddr_start;
	struct mctp_dev *mdev;
	struct rtmsg *rtm;
	unsigned int mtu;
	int rc;

	rc = mctp_route_nlparse(skb, nlh, extack, tb,
				&rtm, &mdev, &daddr_start);
	if (rc < 0)
		return rc;

	if (rtm->rtm_type != RTN_UNICAST) {
		NL_SET_ERR_MSG(extack, "rtm_type must be RTN_UNICAST");
		return -EINVAL;
	}

	/* TODO: parse mtu from nlparse */
	mtu = 0;

	if (rtm->rtm_type != RTN_UNICAST)
		return -EINVAL;

	rc = mctp_route_add(mdev, daddr_start, rtm->rtm_dst_len, mtu,
			    rtm->rtm_type);
	return rc;
}

static int mctp_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
			 struct netlink_ext_ack *extack)
{
	struct nlattr *tb[RTA_MAX + 1];
	mctp_eid_t daddr_start;
	struct mctp_dev *mdev;
	struct rtmsg *rtm;
	int rc;

	rc = mctp_route_nlparse(skb, nlh, extack, tb,
				&rtm, &mdev, &daddr_start);
	if (rc < 0)
		return rc;

	/* we only have unicast routes */
	if (rtm->rtm_type != RTN_UNICAST)
		return -EINVAL;

	rc = mctp_route_remove(mdev, daddr_start, rtm->rtm_dst_len);
	return rc;
}

static int mctp_fill_rtinfo(struct sk_buff *skb, struct mctp_route *rt,
			    u32 portid, u32 seq, int event, unsigned int flags)
{
	struct nlmsghdr *nlh;
	struct rtmsg *hdr;
	void *metrics;

	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*hdr), flags);
	if (!nlh)
		return -EMSGSIZE;

	hdr = nlmsg_data(nlh);
	hdr->rtm_family = AF_MCTP;

	/* we use the _len fields as a number of EIDs, rather than
	 * a number of bits in the address
	 */
	hdr->rtm_dst_len = rt->max - rt->min;
	hdr->rtm_src_len = 0;
	hdr->rtm_tos = 0;
	hdr->rtm_table = RT_TABLE_DEFAULT;
	hdr->rtm_protocol = RTPROT_STATIC; /* everything is user-defined */
	hdr->rtm_scope = RT_SCOPE_LINK; /* TODO: scope in mctp_route? */
	hdr->rtm_type = rt->type;

	if (nla_put_u8(skb, RTA_DST, rt->min))
		goto cancel;

	metrics = nla_nest_start_noflag(skb, RTA_METRICS);
	if (!metrics)
		goto cancel;

	if (rt->mtu) {
		if (nla_put_u32(skb, RTAX_MTU, rt->mtu))
			goto cancel;
	}

	nla_nest_end(skb, metrics);

	if (rt->dev) {
		if (nla_put_u32(skb, RTA_OIF, rt->dev->dev->ifindex))
			goto cancel;
	}

	/* TODO: conditional neighbour physaddr? */

	nlmsg_end(skb, nlh);

	return 0;

cancel:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

static int mctp_dump_rtinfo(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct net *net = sock_net(skb->sk);
	struct mctp_route *rt;
	int s_idx, idx;

	/* TODO: allow filtering on route data, possibly under
	 * cb->strict_check
	 */

	/* TODO: change to struct overlay */
	s_idx = cb->args[0];
	idx = 0;

	rcu_read_lock();
	list_for_each_entry_rcu(rt, &net->mctp.routes, list) {
		if (idx++ < s_idx)
			continue;
		if (mctp_fill_rtinfo(skb, rt,
				     NETLINK_CB(cb->skb).portid,
				     cb->nlh->nlmsg_seq,
				     RTM_NEWROUTE, NLM_F_MULTI) < 0)
			break;
	}

	rcu_read_unlock();
	cb->args[0] = idx;

	return skb->len;
}

/* net namespace implementation */
static int __net_init mctp_routes_net_init(struct net *net)
{
	struct netns_mctp *ns = &net->mctp;

	INIT_LIST_HEAD(&ns->routes);
	INIT_HLIST_HEAD(&ns->binds);
	mutex_init(&ns->bind_lock);
	INIT_HLIST_HEAD(&ns->keys);
	spin_lock_init(&ns->keys_lock);
	WARN_ON(mctp_default_net_set(net, MCTP_INITIAL_DEFAULT_NET));
	return 0;
}

static void __net_exit mctp_routes_net_exit(struct net *net)
{
	struct mctp_route *rt;

	rcu_read_lock();
	list_for_each_entry_rcu(rt, &net->mctp.routes, list)
		mctp_route_release(rt);
	rcu_read_unlock();
}

static struct pernet_operations mctp_net_ops = {
	.init = mctp_routes_net_init,
	.exit = mctp_routes_net_exit,
};

int __init mctp_routes_init(void)
{
	dev_add_pack(&mctp_packet_type);

	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_GETROUTE,
			     NULL, mctp_dump_rtinfo, 0);
	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_NEWROUTE,
			     mctp_newroute, NULL, 0);
	rtnl_register_module(THIS_MODULE, PF_MCTP, RTM_DELROUTE,
			     mctp_delroute, NULL, 0);

	return register_pernet_subsys(&mctp_net_ops);
}

void __exit mctp_routes_exit(void)
{
	unregister_pernet_subsys(&mctp_net_ops);
	rtnl_unregister(PF_MCTP, RTM_DELROUTE);
	rtnl_unregister(PF_MCTP, RTM_NEWROUTE);
	rtnl_unregister(PF_MCTP, RTM_GETROUTE);
	dev_remove_pack(&mctp_packet_type);
}