summaryrefslogtreecommitdiff
path: root/drivers/net/ppp/pppoe.c
blob: ce61231e96ea5fe27f512fbd0d80d4609997e508 (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
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
/** -*- linux-c -*- ***********************************************************
 * Linux PPP over Ethernet (PPPoX/PPPoE) Sockets
 *
 * PPPoX --- Generic PPP encapsulation socket family
 * PPPoE --- PPP over Ethernet (RFC 2516)
 *
 *
 * Version:	0.7.0
 *
 * 070228 :	Fix to allow multiple sessions with same remote MAC and same
 *		session id by including the local device ifindex in the
 *		tuple identifying a session. This also ensures packets can't
 *		be injected into a session from interfaces other than the one
 *		specified by userspace. Florian Zumbiehl <florz@florz.de>
 *		(Oh, BTW, this one is YYMMDD, in case you were wondering ...)
 * 220102 :	Fix module use count on failure in pppoe_create, pppox_sk -acme
 * 030700 :	Fixed connect logic to allow for disconnect.
 * 270700 :	Fixed potential SMP problems; we must protect against
 *		simultaneous invocation of ppp_input
 *		and ppp_unregister_channel.
 * 040800 :	Respect reference count mechanisms on net-devices.
 * 200800 :	fix kfree(skb) in pppoe_rcv (acme)
 *		Module reference count is decremented in the right spot now,
 *		guards against sock_put not actually freeing the sk
 *		in pppoe_release.
 * 051000 :	Initialization cleanup.
 * 111100 :	Fix recvmsg.
 * 050101 :	Fix PADT procesing.
 * 140501 :	Use pppoe_rcv_core to handle all backlog. (Alexey)
 * 170701 :	Do not lock_sock with rwlock held. (DaveM)
 *		Ignore discovery frames if user has socket
 *		locked. (DaveM)
 *		Ignore return value of dev_queue_xmit in __pppoe_xmit
 *		or else we may kfree an SKB twice. (DaveM)
 * 190701 :	When doing copies of skb's in __pppoe_xmit, always delete
 *		the original skb that was passed in on success, never on
 *		failure.  Delete the copy of the skb on failure to avoid
 *		a memory leak.
 * 081001 :	Misc. cleanup (licence string, non-blocking, prevent
 *		reference of device on close).
 * 121301 :	New ppp channels interface; cannot unregister a channel
 *		from interrupts.  Thus, we mark the socket as a ZOMBIE
 *		and do the unregistration later.
 * 081002 :	seq_file support for proc stuff -acme
 * 111602 :	Merge all 2.4 fixes into 2.5/2.6 tree.  Label 2.5/2.6
 *		as version 0.7.  Spacing cleanup.
 * Author:	Michal Ostrowski <mostrows@speakeasy.net>
 * Contributors:
 * 		Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *		David S. Miller (davem@redhat.com)
 *
 * License:
 *		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 (at your option) any later version.
 *
 */

#include <linux/string.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/errno.h>
#include <linux/netdevice.h>
#include <linux/net.h>
#include <linux/inetdevice.h>
#include <linux/etherdevice.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/if_ether.h>
#include <linux/if_pppox.h>
#include <linux/ppp_channel.h>
#include <linux/ppp_defs.h>
#include <linux/ppp-ioctl.h>
#include <linux/notifier.h>
#include <linux/file.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

#include <linux/nsproxy.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/sock.h>

#include <linux/uaccess.h>

#define PPPOE_HASH_BITS 4
#define PPPOE_HASH_SIZE (1 << PPPOE_HASH_BITS)
#define PPPOE_HASH_MASK	(PPPOE_HASH_SIZE - 1)

static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb);

static const struct proto_ops pppoe_ops;
static const struct ppp_channel_ops pppoe_chan_ops;

/* per-net private data for this module */
static unsigned int pppoe_net_id __read_mostly;
struct pppoe_net {
	/*
	 * we could use _single_ hash table for all
	 * nets by injecting net id into the hash but
	 * it would increase hash chains and add
	 * a few additional math comparations messy
	 * as well, moreover in case of SMP less locking
	 * controversy here
	 */
	struct pppox_sock *hash_table[PPPOE_HASH_SIZE];
	rwlock_t hash_lock;
};

/*
 * PPPoE could be in the following stages:
 * 1) Discovery stage (to obtain remote MAC and Session ID)
 * 2) Session stage (MAC and SID are known)
 *
 * Ethernet frames have a special tag for this but
 * we use simpler approach based on session id
 */
static inline bool stage_session(__be16 sid)
{
	return sid != 0;
}

static inline struct pppoe_net *pppoe_pernet(struct net *net)
{
	BUG_ON(!net);

	return net_generic(net, pppoe_net_id);
}

static inline int cmp_2_addr(struct pppoe_addr *a, struct pppoe_addr *b)
{
	return a->sid == b->sid && ether_addr_equal(a->remote, b->remote);
}

static inline int cmp_addr(struct pppoe_addr *a, __be16 sid, char *addr)
{
	return a->sid == sid && ether_addr_equal(a->remote, addr);
}

#if 8 % PPPOE_HASH_BITS
#error 8 must be a multiple of PPPOE_HASH_BITS
#endif

static int hash_item(__be16 sid, unsigned char *addr)
{
	unsigned char hash = 0;
	unsigned int i;

	for (i = 0; i < ETH_ALEN; i++)
		hash ^= addr[i];
	for (i = 0; i < sizeof(sid_t) * 8; i += 8)
		hash ^= (__force __u32)sid >> i;
	for (i = 8; (i >>= 1) >= PPPOE_HASH_BITS;)
		hash ^= hash >> i;

	return hash & PPPOE_HASH_MASK;
}

/**********************************************************************
 *
 *  Set/get/delete/rehash items  (internal versions)
 *
 **********************************************************************/
static struct pppox_sock *__get_item(struct pppoe_net *pn, __be16 sid,
				unsigned char *addr, int ifindex)
{
	int hash = hash_item(sid, addr);
	struct pppox_sock *ret;

	ret = pn->hash_table[hash];
	while (ret) {
		if (cmp_addr(&ret->pppoe_pa, sid, addr) &&
		    ret->pppoe_ifindex == ifindex)
			return ret;

		ret = ret->next;
	}

	return NULL;
}

static int __set_item(struct pppoe_net *pn, struct pppox_sock *po)
{
	int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
	struct pppox_sock *ret;

	ret = pn->hash_table[hash];
	while (ret) {
		if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa) &&
		    ret->pppoe_ifindex == po->pppoe_ifindex)
			return -EALREADY;

		ret = ret->next;
	}

	po->next = pn->hash_table[hash];
	pn->hash_table[hash] = po;

	return 0;
}

static void __delete_item(struct pppoe_net *pn, __be16 sid,
					char *addr, int ifindex)
{
	int hash = hash_item(sid, addr);
	struct pppox_sock *ret, **src;

	ret = pn->hash_table[hash];
	src = &pn->hash_table[hash];

	while (ret) {
		if (cmp_addr(&ret->pppoe_pa, sid, addr) &&
		    ret->pppoe_ifindex == ifindex) {
			*src = ret->next;
			break;
		}

		src = &ret->next;
		ret = ret->next;
	}
}

/**********************************************************************
 *
 *  Set/get/delete/rehash items
 *
 **********************************************************************/
static inline struct pppox_sock *get_item(struct pppoe_net *pn, __be16 sid,
					unsigned char *addr, int ifindex)
{
	struct pppox_sock *po;

	read_lock_bh(&pn->hash_lock);
	po = __get_item(pn, sid, addr, ifindex);
	if (po)
		sock_hold(sk_pppox(po));
	read_unlock_bh(&pn->hash_lock);

	return po;
}

static inline struct pppox_sock *get_item_by_addr(struct net *net,
						struct sockaddr_pppox *sp)
{
	struct net_device *dev;
	struct pppoe_net *pn;
	struct pppox_sock *pppox_sock = NULL;

	int ifindex;

	rcu_read_lock();
	dev = dev_get_by_name_rcu(net, sp->sa_addr.pppoe.dev);
	if (dev) {
		ifindex = dev->ifindex;
		pn = pppoe_pernet(net);
		pppox_sock = get_item(pn, sp->sa_addr.pppoe.sid,
				sp->sa_addr.pppoe.remote, ifindex);
	}
	rcu_read_unlock();
	return pppox_sock;
}

static inline void delete_item(struct pppoe_net *pn, __be16 sid,
					char *addr, int ifindex)
{
	write_lock_bh(&pn->hash_lock);
	__delete_item(pn, sid, addr, ifindex);
	write_unlock_bh(&pn->hash_lock);
}

/***************************************************************************
 *
 *  Handler for device events.
 *  Certain device events require that sockets be unconnected.
 *
 **************************************************************************/

static void pppoe_flush_dev(struct net_device *dev)
{
	struct pppoe_net *pn;
	int i;

	pn = pppoe_pernet(dev_net(dev));
	write_lock_bh(&pn->hash_lock);
	for (i = 0; i < PPPOE_HASH_SIZE; i++) {
		struct pppox_sock *po = pn->hash_table[i];
		struct sock *sk;

		while (po) {
			while (po && po->pppoe_dev != dev) {
				po = po->next;
			}

			if (!po)
				break;

			sk = sk_pppox(po);

			/* We always grab the socket lock, followed by the
			 * hash_lock, in that order.  Since we should hold the
			 * sock lock while doing any unbinding, we need to
			 * release the lock we're holding.  Hold a reference to
			 * the sock so it doesn't disappear as we're jumping
			 * between locks.
			 */

			sock_hold(sk);
			write_unlock_bh(&pn->hash_lock);
			lock_sock(sk);

			if (po->pppoe_dev == dev &&
			    sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
				pppox_unbind_sock(sk);
				sk->sk_state_change(sk);
				po->pppoe_dev = NULL;
				dev_put(dev);
			}

			release_sock(sk);
			sock_put(sk);

			/* Restart the process from the start of the current
			 * hash chain. We dropped locks so the world may have
			 * change from underneath us.
			 */

			BUG_ON(pppoe_pernet(dev_net(dev)) == NULL);
			write_lock_bh(&pn->hash_lock);
			po = pn->hash_table[i];
		}
	}
	write_unlock_bh(&pn->hash_lock);
}

static int pppoe_device_event(struct notifier_block *this,
			      unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);

	/* Only look at sockets that are using this specific device. */
	switch (event) {
	case NETDEV_CHANGEADDR:
	case NETDEV_CHANGEMTU:
		/* A change in mtu or address is a bad thing, requiring
		 * LCP re-negotiation.
		 */

	case NETDEV_GOING_DOWN:
	case NETDEV_DOWN:
		/* Find every socket on this device and kill it. */
		pppoe_flush_dev(dev);
		break;

	default:
		break;
	}

	return NOTIFY_DONE;
}

static struct notifier_block pppoe_notifier = {
	.notifier_call = pppoe_device_event,
};

/************************************************************************
 *
 * Do the real work of receiving a PPPoE Session frame.
 *
 ***********************************************************************/
static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
{
	struct pppox_sock *po = pppox_sk(sk);
	struct pppox_sock *relay_po;

	/* Backlog receive. Semantics of backlog rcv preclude any code from
	 * executing in lock_sock()/release_sock() bounds; meaning sk->sk_state
	 * can't change.
	 */

	if (skb->pkt_type == PACKET_OTHERHOST)
		goto abort_kfree;

	if (sk->sk_state & PPPOX_BOUND) {
		ppp_input(&po->chan, skb);
	} else if (sk->sk_state & PPPOX_RELAY) {
		relay_po = get_item_by_addr(sock_net(sk),
					    &po->pppoe_relay);
		if (relay_po == NULL)
			goto abort_kfree;

		if ((sk_pppox(relay_po)->sk_state & PPPOX_CONNECTED) == 0)
			goto abort_put;

		if (!__pppoe_xmit(sk_pppox(relay_po), skb))
			goto abort_put;

		sock_put(sk_pppox(relay_po));
	} else {
		if (sock_queue_rcv_skb(sk, skb))
			goto abort_kfree;
	}

	return NET_RX_SUCCESS;

abort_put:
	sock_put(sk_pppox(relay_po));

abort_kfree:
	kfree_skb(skb);
	return NET_RX_DROP;
}

/************************************************************************
 *
 * Receive wrapper called in BH context.
 *
 ***********************************************************************/
static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
		     struct packet_type *pt, struct net_device *orig_dev)
{
	struct pppoe_hdr *ph;
	struct pppox_sock *po;
	struct pppoe_net *pn;
	int len;

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (!skb)
		goto out;

	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
		goto drop;

	ph = pppoe_hdr(skb);
	len = ntohs(ph->length);

	skb_pull_rcsum(skb, sizeof(*ph));
	if (skb->len < len)
		goto drop;

	if (pskb_trim_rcsum(skb, len))
		goto drop;

	pn = pppoe_pernet(dev_net(dev));

	/* Note that get_item does a sock_hold(), so sk_pppox(po)
	 * is known to be safe.
	 */
	po = get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
	if (!po)
		goto drop;

	return sk_receive_skb(sk_pppox(po), skb, 0);

drop:
	kfree_skb(skb);
out:
	return NET_RX_DROP;
}

static void pppoe_unbind_sock_work(struct work_struct *work)
{
	struct pppox_sock *po = container_of(work, struct pppox_sock,
					     proto.pppoe.padt_work);
	struct sock *sk = sk_pppox(po);

	lock_sock(sk);
	if (po->pppoe_dev) {
		dev_put(po->pppoe_dev);
		po->pppoe_dev = NULL;
	}
	pppox_unbind_sock(sk);
	release_sock(sk);
	sock_put(sk);
}

/************************************************************************
 *
 * Receive a PPPoE Discovery frame.
 * This is solely for detection of PADT frames
 *
 ***********************************************************************/
static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
			  struct packet_type *pt, struct net_device *orig_dev)

{
	struct pppoe_hdr *ph;
	struct pppox_sock *po;
	struct pppoe_net *pn;

	skb = skb_share_check(skb, GFP_ATOMIC);
	if (!skb)
		goto out;

	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
		goto abort;

	ph = pppoe_hdr(skb);
	if (ph->code != PADT_CODE)
		goto abort;

	pn = pppoe_pernet(dev_net(dev));
	po = get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
	if (po)
		if (!schedule_work(&po->proto.pppoe.padt_work))
			sock_put(sk_pppox(po));

abort:
	kfree_skb(skb);
out:
	return NET_RX_SUCCESS; /* Lies... :-) */
}

static struct packet_type pppoes_ptype __read_mostly = {
	.type	= cpu_to_be16(ETH_P_PPP_SES),
	.func	= pppoe_rcv,
};

static struct packet_type pppoed_ptype __read_mostly = {
	.type	= cpu_to_be16(ETH_P_PPP_DISC),
	.func	= pppoe_disc_rcv,
};

static struct proto pppoe_sk_proto __read_mostly = {
	.name	  = "PPPOE",
	.owner	  = THIS_MODULE,
	.obj_size = sizeof(struct pppox_sock),
};

/***********************************************************************
 *
 * Initialize a new struct sock.
 *
 **********************************************************************/
static int pppoe_create(struct net *net, struct socket *sock, int kern)
{
	struct sock *sk;

	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto, kern);
	if (!sk)
		return -ENOMEM;

	sock_init_data(sock, sk);

	sock->state	= SS_UNCONNECTED;
	sock->ops	= &pppoe_ops;

	sk->sk_backlog_rcv	= pppoe_rcv_core;
	sk->sk_state		= PPPOX_NONE;
	sk->sk_type		= SOCK_STREAM;
	sk->sk_family		= PF_PPPOX;
	sk->sk_protocol		= PX_PROTO_OE;

	INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work,
		  pppoe_unbind_sock_work);

	return 0;
}

static int pppoe_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct pppox_sock *po;
	struct pppoe_net *pn;
	struct net *net = NULL;

	if (!sk)
		return 0;

	lock_sock(sk);
	if (sock_flag(sk, SOCK_DEAD)) {
		release_sock(sk);
		return -EBADF;
	}

	po = pppox_sk(sk);

	if (po->pppoe_dev) {
		dev_put(po->pppoe_dev);
		po->pppoe_dev = NULL;
	}

	pppox_unbind_sock(sk);

	/* Signal the death of the socket. */
	sk->sk_state = PPPOX_DEAD;

	net = sock_net(sk);
	pn = pppoe_pernet(net);

	/*
	 * protect "po" from concurrent updates
	 * on pppoe_flush_dev
	 */
	delete_item(pn, po->pppoe_pa.sid, po->pppoe_pa.remote,
		    po->pppoe_ifindex);

	sock_orphan(sk);
	sock->sk = NULL;

	skb_queue_purge(&sk->sk_receive_queue);
	release_sock(sk);
	sock_put(sk);

	return 0;
}

static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
		  int sockaddr_len, int flags)
{
	struct sock *sk = sock->sk;
	struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr;
	struct pppox_sock *po = pppox_sk(sk);
	struct net_device *dev = NULL;
	struct pppoe_net *pn;
	struct net *net = NULL;
	int error;

	lock_sock(sk);

	error = -EINVAL;

	if (sockaddr_len != sizeof(struct sockaddr_pppox))
		goto end;

	if (sp->sa_protocol != PX_PROTO_OE)
		goto end;

	/* Check for already bound sockets */
	error = -EBUSY;
	if ((sk->sk_state & PPPOX_CONNECTED) &&
	     stage_session(sp->sa_addr.pppoe.sid))
		goto end;

	/* Check for already disconnected sockets, on attempts to disconnect */
	error = -EALREADY;
	if ((sk->sk_state & PPPOX_DEAD) &&
	     !stage_session(sp->sa_addr.pppoe.sid))
		goto end;

	error = 0;

	/* Delete the old binding */
	if (stage_session(po->pppoe_pa.sid)) {
		pppox_unbind_sock(sk);
		pn = pppoe_pernet(sock_net(sk));
		delete_item(pn, po->pppoe_pa.sid,
			    po->pppoe_pa.remote, po->pppoe_ifindex);
		if (po->pppoe_dev) {
			dev_put(po->pppoe_dev);
			po->pppoe_dev = NULL;
		}

		po->pppoe_ifindex = 0;
		memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa));
		memset(&po->pppoe_relay, 0, sizeof(po->pppoe_relay));
		memset(&po->chan, 0, sizeof(po->chan));
		po->next = NULL;
		po->num = 0;

		sk->sk_state = PPPOX_NONE;
	}

	/* Re-bind in session stage only */
	if (stage_session(sp->sa_addr.pppoe.sid)) {
		error = -ENODEV;
		net = sock_net(sk);
		dev = dev_get_by_name(net, sp->sa_addr.pppoe.dev);
		if (!dev)
			goto err_put;

		po->pppoe_dev = dev;
		po->pppoe_ifindex = dev->ifindex;
		pn = pppoe_pernet(net);
		if (!(dev->flags & IFF_UP)) {
			goto err_put;
		}

		memcpy(&po->pppoe_pa,
		       &sp->sa_addr.pppoe,
		       sizeof(struct pppoe_addr));

		write_lock_bh(&pn->hash_lock);
		error = __set_item(pn, po);
		write_unlock_bh(&pn->hash_lock);
		if (error < 0)
			goto err_put;

		po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
				   dev->hard_header_len);

		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
		po->chan.private = sk;
		po->chan.ops = &pppoe_chan_ops;

		error = ppp_register_net_channel(dev_net(dev), &po->chan);
		if (error) {
			delete_item(pn, po->pppoe_pa.sid,
				    po->pppoe_pa.remote, po->pppoe_ifindex);
			goto err_put;
		}

		sk->sk_state = PPPOX_CONNECTED;
	}

	po->num = sp->sa_addr.pppoe.sid;

end:
	release_sock(sk);
	return error;
err_put:
	if (po->pppoe_dev) {
		dev_put(po->pppoe_dev);
		po->pppoe_dev = NULL;
	}
	goto end;
}

static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr,
		  int peer)
{
	int len = sizeof(struct sockaddr_pppox);
	struct sockaddr_pppox sp;

	sp.sa_family	= AF_PPPOX;
	sp.sa_protocol	= PX_PROTO_OE;
	memcpy(&sp.sa_addr.pppoe, &pppox_sk(sock->sk)->pppoe_pa,
	       sizeof(struct pppoe_addr));

	memcpy(uaddr, &sp, len);

	return len;
}

static int pppoe_ioctl(struct socket *sock, unsigned int cmd,
		unsigned long arg)
{
	struct sock *sk = sock->sk;
	struct pppox_sock *po = pppox_sk(sk);
	int val;
	int err;

	switch (cmd) {
	case PPPIOCGMRU:
		err = -ENXIO;
		if (!(sk->sk_state & PPPOX_CONNECTED))
			break;

		err = -EFAULT;
		if (put_user(po->pppoe_dev->mtu -
			     sizeof(struct pppoe_hdr) -
			     PPP_HDRLEN,
			     (int __user *)arg))
			break;
		err = 0;
		break;

	case PPPIOCSMRU:
		err = -ENXIO;
		if (!(sk->sk_state & PPPOX_CONNECTED))
			break;

		err = -EFAULT;
		if (get_user(val, (int __user *)arg))
			break;

		if (val < (po->pppoe_dev->mtu
			   - sizeof(struct pppoe_hdr)
			   - PPP_HDRLEN))
			err = 0;
		else
			err = -EINVAL;
		break;

	case PPPIOCSFLAGS:
		err = -EFAULT;
		if (get_user(val, (int __user *)arg))
			break;
		err = 0;
		break;

	case PPPOEIOCSFWD:
	{
		struct pppox_sock *relay_po;

		err = -EBUSY;
		if (sk->sk_state & (PPPOX_BOUND | PPPOX_DEAD))
			break;

		err = -ENOTCONN;
		if (!(sk->sk_state & PPPOX_CONNECTED))
			break;

		/* PPPoE address from the user specifies an outbound
		   PPPoE address which frames are forwarded to */
		err = -EFAULT;
		if (copy_from_user(&po->pppoe_relay,
				   (void __user *)arg,
				   sizeof(struct sockaddr_pppox)))
			break;

		err = -EINVAL;
		if (po->pppoe_relay.sa_family != AF_PPPOX ||
		    po->pppoe_relay.sa_protocol != PX_PROTO_OE)
			break;

		/* Check that the socket referenced by the address
		   actually exists. */
		relay_po = get_item_by_addr(sock_net(sk), &po->pppoe_relay);
		if (!relay_po)
			break;

		sock_put(sk_pppox(relay_po));
		sk->sk_state |= PPPOX_RELAY;
		err = 0;
		break;
	}

	case PPPOEIOCDFWD:
		err = -EALREADY;
		if (!(sk->sk_state & PPPOX_RELAY))
			break;

		sk->sk_state &= ~PPPOX_RELAY;
		err = 0;
		break;

	default:
		err = -ENOTTY;
	}

	return err;
}

static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
			 size_t total_len)
{
	struct sk_buff *skb;
	struct sock *sk = sock->sk;
	struct pppox_sock *po = pppox_sk(sk);
	int error;
	struct pppoe_hdr hdr;
	struct pppoe_hdr *ph;
	struct net_device *dev;
	char *start;
	int hlen;

	lock_sock(sk);
	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
		error = -ENOTCONN;
		goto end;
	}

	hdr.ver = 1;
	hdr.type = 1;
	hdr.code = 0;
	hdr.sid = po->num;

	dev = po->pppoe_dev;

	error = -EMSGSIZE;
	if (total_len > (dev->mtu + dev->hard_header_len))
		goto end;

	hlen = LL_RESERVED_SPACE(dev);
	skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
			   dev->needed_tailroom, 0, GFP_KERNEL);
	if (!skb) {
		error = -ENOMEM;
		goto end;
	}

	/* Reserve space for headers. */
	skb_reserve(skb, hlen);
	skb_reset_network_header(skb);

	skb->dev = dev;

	skb->priority = sk->sk_priority;
	skb->protocol = cpu_to_be16(ETH_P_PPP_SES);

	ph = skb_put(skb, total_len + sizeof(struct pppoe_hdr));
	start = (char *)&ph->tag[0];

	error = memcpy_from_msg(start, m, total_len);
	if (error < 0) {
		kfree_skb(skb);
		goto end;
	}

	error = total_len;
	dev_hard_header(skb, dev, ETH_P_PPP_SES,
			po->pppoe_pa.remote, NULL, total_len);

	memcpy(ph, &hdr, sizeof(struct pppoe_hdr));

	ph->length = htons(total_len);

	dev_queue_xmit(skb);

end:
	release_sock(sk);
	return error;
}

/************************************************************************
 *
 * xmit function for internal use.
 *
 ***********************************************************************/
static int __pppoe_xmit(struct sock *sk, struct sk_buff *skb)
{
	struct pppox_sock *po = pppox_sk(sk);
	struct net_device *dev = po->pppoe_dev;
	struct pppoe_hdr *ph;
	int data_len = skb->len;

	/* The higher-level PPP code (ppp_unregister_channel()) ensures the PPP
	 * xmit operations conclude prior to an unregistration call.  Thus
	 * sk->sk_state cannot change, so we don't need to do lock_sock().
	 * But, we also can't do a lock_sock since that introduces a potential
	 * deadlock as we'd reverse the lock ordering used when calling
	 * ppp_unregister_channel().
	 */

	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
		goto abort;

	if (!dev)
		goto abort;

	/* Copy the data if there is no space for the header or if it's
	 * read-only.
	 */
	if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
		goto abort;

	__skb_push(skb, sizeof(*ph));
	skb_reset_network_header(skb);

	ph = pppoe_hdr(skb);
	ph->ver	= 1;
	ph->type = 1;
	ph->code = 0;
	ph->sid	= po->num;
	ph->length = htons(data_len);

	skb->protocol = cpu_to_be16(ETH_P_PPP_SES);
	skb->dev = dev;

	dev_hard_header(skb, dev, ETH_P_PPP_SES,
			po->pppoe_pa.remote, NULL, data_len);

	dev_queue_xmit(skb);
	return 1;

abort:
	kfree_skb(skb);
	return 1;
}

/************************************************************************
 *
 * xmit function called by generic PPP driver
 * sends PPP frame over PPPoE socket
 *
 ***********************************************************************/
static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb)
{
	struct sock *sk = (struct sock *)chan->private;
	return __pppoe_xmit(sk, skb);
}

static const struct ppp_channel_ops pppoe_chan_ops = {
	.start_xmit = pppoe_xmit,
};

static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
			 size_t total_len, int flags)
{
	struct sock *sk = sock->sk;
	struct sk_buff *skb;
	int error = 0;

	if (sk->sk_state & PPPOX_BOUND) {
		error = -EIO;
		goto end;
	}

	skb = skb_recv_datagram(sk, flags & ~MSG_DONTWAIT,
				flags & MSG_DONTWAIT, &error);
	if (error < 0)
		goto end;

	if (skb) {
		total_len = min_t(size_t, total_len, skb->len);
		error = skb_copy_datagram_msg(skb, 0, m, total_len);
		if (error == 0) {
			consume_skb(skb);
			return total_len;
		}
	}

	kfree_skb(skb);
end:
	return error;
}

#ifdef CONFIG_PROC_FS
static int pppoe_seq_show(struct seq_file *seq, void *v)
{
	struct pppox_sock *po;
	char *dev_name;

	if (v == SEQ_START_TOKEN) {
		seq_puts(seq, "Id       Address              Device\n");
		goto out;
	}

	po = v;
	dev_name = po->pppoe_pa.dev;

	seq_printf(seq, "%08X %pM %8s\n",
		po->pppoe_pa.sid, po->pppoe_pa.remote, dev_name);
out:
	return 0;
}

static inline struct pppox_sock *pppoe_get_idx(struct pppoe_net *pn, loff_t pos)
{
	struct pppox_sock *po;
	int i;

	for (i = 0; i < PPPOE_HASH_SIZE; i++) {
		po = pn->hash_table[i];
		while (po) {
			if (!pos--)
				goto out;
			po = po->next;
		}
	}

out:
	return po;
}

static void *pppoe_seq_start(struct seq_file *seq, loff_t *pos)
	__acquires(pn->hash_lock)
{
	struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
	loff_t l = *pos;

	read_lock_bh(&pn->hash_lock);
	return l ? pppoe_get_idx(pn, --l) : SEQ_START_TOKEN;
}

static void *pppoe_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
	struct pppox_sock *po;

	++*pos;
	if (v == SEQ_START_TOKEN) {
		po = pppoe_get_idx(pn, 0);
		goto out;
	}
	po = v;
	if (po->next)
		po = po->next;
	else {
		int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);

		po = NULL;
		while (++hash < PPPOE_HASH_SIZE) {
			po = pn->hash_table[hash];
			if (po)
				break;
		}
	}

out:
	return po;
}

static void pppoe_seq_stop(struct seq_file *seq, void *v)
	__releases(pn->hash_lock)
{
	struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
	read_unlock_bh(&pn->hash_lock);
}

static const struct seq_operations pppoe_seq_ops = {
	.start		= pppoe_seq_start,
	.next		= pppoe_seq_next,
	.stop		= pppoe_seq_stop,
	.show		= pppoe_seq_show,
};
#endif /* CONFIG_PROC_FS */

static const struct proto_ops pppoe_ops = {
	.family		= AF_PPPOX,
	.owner		= THIS_MODULE,
	.release	= pppoe_release,
	.bind		= sock_no_bind,
	.connect	= pppoe_connect,
	.socketpair	= sock_no_socketpair,
	.accept		= sock_no_accept,
	.getname	= pppoe_getname,
	.poll		= datagram_poll,
	.listen		= sock_no_listen,
	.shutdown	= sock_no_shutdown,
	.setsockopt	= sock_no_setsockopt,
	.getsockopt	= sock_no_getsockopt,
	.sendmsg	= pppoe_sendmsg,
	.recvmsg	= pppoe_recvmsg,
	.mmap		= sock_no_mmap,
	.ioctl		= pppox_ioctl,
};

static const struct pppox_proto pppoe_proto = {
	.create	= pppoe_create,
	.ioctl	= pppoe_ioctl,
	.owner	= THIS_MODULE,
};

static __net_init int pppoe_init_net(struct net *net)
{
	struct pppoe_net *pn = pppoe_pernet(net);
	struct proc_dir_entry *pde;

	rwlock_init(&pn->hash_lock);

	pde = proc_create_net("pppoe", 0444, net->proc_net,
			&pppoe_seq_ops, sizeof(struct seq_net_private));
#ifdef CONFIG_PROC_FS
	if (!pde)
		return -ENOMEM;
#endif

	return 0;
}

static __net_exit void pppoe_exit_net(struct net *net)
{
	remove_proc_entry("pppoe", net->proc_net);
}

static struct pernet_operations pppoe_net_ops = {
	.init = pppoe_init_net,
	.exit = pppoe_exit_net,
	.id   = &pppoe_net_id,
	.size = sizeof(struct pppoe_net),
};

static int __init pppoe_init(void)
{
	int err;

	err = register_pernet_device(&pppoe_net_ops);
	if (err)
		goto out;

	err = proto_register(&pppoe_sk_proto, 0);
	if (err)
		goto out_unregister_net_ops;

	err = register_pppox_proto(PX_PROTO_OE, &pppoe_proto);
	if (err)
		goto out_unregister_pppoe_proto;

	dev_add_pack(&pppoes_ptype);
	dev_add_pack(&pppoed_ptype);
	register_netdevice_notifier(&pppoe_notifier);

	return 0;

out_unregister_pppoe_proto:
	proto_unregister(&pppoe_sk_proto);
out_unregister_net_ops:
	unregister_pernet_device(&pppoe_net_ops);
out:
	return err;
}

static void __exit pppoe_exit(void)
{
	unregister_netdevice_notifier(&pppoe_notifier);
	dev_remove_pack(&pppoed_ptype);
	dev_remove_pack(&pppoes_ptype);
	unregister_pppox_proto(PX_PROTO_OE);
	proto_unregister(&pppoe_sk_proto);
	unregister_pernet_device(&pppoe_net_ops);
}

module_init(pppoe_init);
module_exit(pppoe_exit);

MODULE_AUTHOR("Michal Ostrowski <mostrows@speakeasy.net>");
MODULE_DESCRIPTION("PPP over Ethernet driver");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OE);