summaryrefslogtreecommitdiffstats
path: root/net/caif/caif_socket.c
blob: 1d337e02bc6319066ab764991316f43388037d1e (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
/*
 * Copyright (C) ST-Ericsson AB 2010
 * Author:	Sjur Brendeland sjur.brandeland@stericsson.com
 * License terms: GNU General Public License (GPL) version 2
 */

#define pr_fmt(fmt) KBUILD_MODNAME ":%s(): " fmt, __func__

#include <linux/fs.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
#include <linux/list.h>
#include <linux/wait.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/uaccess.h>
#include <linux/debugfs.h>
#include <linux/caif/caif_socket.h>
#include <linux/pkt_sched.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/caif/caif_layer.h>
#include <net/caif/caif_dev.h>
#include <net/caif/cfpkt.h>

MODULE_LICENSE("GPL");
MODULE_ALIAS_NETPROTO(AF_CAIF);

/*
 * CAIF state is re-using the TCP socket states.
 * caif_states stored in sk_state reflect the state as reported by
 * the CAIF stack, while sk_socket->state is the state of the socket.
 */
enum caif_states {
	CAIF_CONNECTED		= TCP_ESTABLISHED,
	CAIF_CONNECTING	= TCP_SYN_SENT,
	CAIF_DISCONNECTED	= TCP_CLOSE
};

#define TX_FLOW_ON_BIT	1
#define RX_FLOW_ON_BIT	2

struct caifsock {
	struct sock sk; /* must be first member */
	struct cflayer layer;
	u32 flow_state;
	struct caif_connect_request conn_req;
	struct mutex readlock;
	struct dentry *debugfs_socket_dir;
	int headroom, tailroom, maxframe;
};

static int rx_flow_is_on(struct caifsock *cf_sk)
{
	return test_bit(RX_FLOW_ON_BIT,
			(void *) &cf_sk->flow_state);
}

static int tx_flow_is_on(struct caifsock *cf_sk)
{
	return test_bit(TX_FLOW_ON_BIT,
			(void *) &cf_sk->flow_state);
}

static void set_rx_flow_off(struct caifsock *cf_sk)
{
	 clear_bit(RX_FLOW_ON_BIT,
		 (void *) &cf_sk->flow_state);
}

static void set_rx_flow_on(struct caifsock *cf_sk)
{
	 set_bit(RX_FLOW_ON_BIT,
			(void *) &cf_sk->flow_state);
}

static void set_tx_flow_off(struct caifsock *cf_sk)
{
	 clear_bit(TX_FLOW_ON_BIT,
		(void *) &cf_sk->flow_state);
}

static void set_tx_flow_on(struct caifsock *cf_sk)
{
	 set_bit(TX_FLOW_ON_BIT,
		(void *) &cf_sk->flow_state);
}

static void caif_read_lock(struct sock *sk)
{
	struct caifsock *cf_sk;
	cf_sk = container_of(sk, struct caifsock, sk);
	mutex_lock(&cf_sk->readlock);
}

static void caif_read_unlock(struct sock *sk)
{
	struct caifsock *cf_sk;
	cf_sk = container_of(sk, struct caifsock, sk);
	mutex_unlock(&cf_sk->readlock);
}

static int sk_rcvbuf_lowwater(struct caifsock *cf_sk)
{
	/* A quarter of full buffer is used a low water mark */
	return cf_sk->sk.sk_rcvbuf / 4;
}

static void caif_flow_ctrl(struct sock *sk, int mode)
{
	struct caifsock *cf_sk;
	cf_sk = container_of(sk, struct caifsock, sk);
	if (cf_sk->layer.dn && cf_sk->layer.dn->modemcmd)
		cf_sk->layer.dn->modemcmd(cf_sk->layer.dn, mode);
}

/*
 * Copied from sock.c:sock_queue_rcv_skb(), but changed so packets are
 * not dropped, but CAIF is sending flow off instead.
 */
static int caif_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int err;
	int skb_len;
	unsigned long flags;
	struct sk_buff_head *list = &sk->sk_receive_queue;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);

	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
		(unsigned int)sk->sk_rcvbuf && rx_flow_is_on(cf_sk)) {
		net_dbg_ratelimited("sending flow OFF (queue len = %d %d)\n",
				    atomic_read(&cf_sk->sk.sk_rmem_alloc),
				    sk_rcvbuf_lowwater(cf_sk));
		set_rx_flow_off(cf_sk);
		caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ);
	}

	err = sk_filter(sk, skb);
	if (err)
		return err;
	if (!sk_rmem_schedule(sk, skb, skb->truesize) && rx_flow_is_on(cf_sk)) {
		set_rx_flow_off(cf_sk);
		net_dbg_ratelimited("sending flow OFF due to rmem_schedule\n");
		caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_OFF_REQ);
	}
	skb->dev = NULL;
	skb_set_owner_r(skb, sk);
	/* Cache the SKB length before we tack it onto the receive
	 * queue. Once it is added it no longer belongs to us and
	 * may be freed by other threads of control pulling packets
	 * from the queue.
	 */
	skb_len = skb->len;
	spin_lock_irqsave(&list->lock, flags);
	if (!sock_flag(sk, SOCK_DEAD))
		__skb_queue_tail(list, skb);
	spin_unlock_irqrestore(&list->lock, flags);

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk, skb_len);
	else
		kfree_skb(skb);
	return 0;
}

/* Packet Receive Callback function called from CAIF Stack */
static int caif_sktrecv_cb(struct cflayer *layr, struct cfpkt *pkt)
{
	struct caifsock *cf_sk;
	struct sk_buff *skb;

	cf_sk = container_of(layr, struct caifsock, layer);
	skb = cfpkt_tonative(pkt);

	if (unlikely(cf_sk->sk.sk_state != CAIF_CONNECTED)) {
		kfree_skb(skb);
		return 0;
	}
	caif_queue_rcv_skb(&cf_sk->sk, skb);
	return 0;
}

static void cfsk_hold(struct cflayer *layr)
{
	struct caifsock *cf_sk = container_of(layr, struct caifsock, layer);
	sock_hold(&cf_sk->sk);
}

static void cfsk_put(struct cflayer *layr)
{
	struct caifsock *cf_sk = container_of(layr, struct caifsock, layer);
	sock_put(&cf_sk->sk);
}

/* Packet Control Callback function called from CAIF */
static void caif_ctrl_cb(struct cflayer *layr,
			 enum caif_ctrlcmd flow,
			 int phyid)
{
	struct caifsock *cf_sk = container_of(layr, struct caifsock, layer);
	switch (flow) {
	case CAIF_CTRLCMD_FLOW_ON_IND:
		/* OK from modem to start sending again */
		set_tx_flow_on(cf_sk);
		cf_sk->sk.sk_state_change(&cf_sk->sk);
		break;

	case CAIF_CTRLCMD_FLOW_OFF_IND:
		/* Modem asks us to shut up */
		set_tx_flow_off(cf_sk);
		cf_sk->sk.sk_state_change(&cf_sk->sk);
		break;

	case CAIF_CTRLCMD_INIT_RSP:
		/* We're now connected */
		caif_client_register_refcnt(&cf_sk->layer,
						cfsk_hold, cfsk_put);
		cf_sk->sk.sk_state = CAIF_CONNECTED;
		set_tx_flow_on(cf_sk);
		cf_sk->sk.sk_shutdown = 0;
		cf_sk->sk.sk_state_change(&cf_sk->sk);
		break;

	case CAIF_CTRLCMD_DEINIT_RSP:
		/* We're now disconnected */
		cf_sk->sk.sk_state = CAIF_DISCONNECTED;
		cf_sk->sk.sk_state_change(&cf_sk->sk);
		break;

	case CAIF_CTRLCMD_INIT_FAIL_RSP:
		/* Connect request failed */
		cf_sk->sk.sk_err = ECONNREFUSED;
		cf_sk->sk.sk_state = CAIF_DISCONNECTED;
		cf_sk->sk.sk_shutdown = SHUTDOWN_MASK;
		/*
		 * Socket "standards" seems to require POLLOUT to
		 * be set at connect failure.
		 */
		set_tx_flow_on(cf_sk);
		cf_sk->sk.sk_state_change(&cf_sk->sk);
		break;

	case CAIF_CTRLCMD_REMOTE_SHUTDOWN_IND:
		/* Modem has closed this connection, or device is down. */
		cf_sk->sk.sk_shutdown = SHUTDOWN_MASK;
		cf_sk->sk.sk_err = ECONNRESET;
		set_rx_flow_on(cf_sk);
		cf_sk->sk.sk_error_report(&cf_sk->sk);
		break;

	default:
		pr_debug("Unexpected flow command %d\n", flow);
	}
}

static void caif_check_flow_release(struct sock *sk)
{
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);

	if (rx_flow_is_on(cf_sk))
		return;

	if (atomic_read(&sk->sk_rmem_alloc) <= sk_rcvbuf_lowwater(cf_sk)) {
			set_rx_flow_on(cf_sk);
			caif_flow_ctrl(sk, CAIF_MODEMCMD_FLOW_ON_REQ);
	}
}

/*
 * Copied from unix_dgram_recvmsg, but removed credit checks,
 * changed locking, address handling and added MSG_TRUNC.
 */
static int caif_seqpkt_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *m, size_t len, int flags)

{
	struct sock *sk = sock->sk;
	struct sk_buff *skb;
	int ret;
	int copylen;

	ret = -EOPNOTSUPP;
	if (m->msg_flags&MSG_OOB)
		goto read_error;

	skb = skb_recv_datagram(sk, flags, 0 , &ret);
	if (!skb)
		goto read_error;
	copylen = skb->len;
	if (len < copylen) {
		m->msg_flags |= MSG_TRUNC;
		copylen = len;
	}

	ret = skb_copy_datagram_iovec(skb, 0, m->msg_iov, copylen);
	if (ret)
		goto out_free;

	ret = (flags & MSG_TRUNC) ? skb->len : copylen;
out_free:
	skb_free_datagram(sk, skb);
	caif_check_flow_release(sk);
	return ret;

read_error:
	return ret;
}


/* Copied from unix_stream_wait_data, identical except for lock call. */
static long caif_stream_data_wait(struct sock *sk, long timeo)
{
	DEFINE_WAIT(wait);
	lock_sock(sk);

	for (;;) {
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);

		if (!skb_queue_empty(&sk->sk_receive_queue) ||
			sk->sk_err ||
			sk->sk_state != CAIF_CONNECTED ||
			sock_flag(sk, SOCK_DEAD) ||
			(sk->sk_shutdown & RCV_SHUTDOWN) ||
			signal_pending(current) ||
			!timeo)
			break;

		set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
		release_sock(sk);
		timeo = schedule_timeout(timeo);
		lock_sock(sk);
		clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	}

	finish_wait(sk_sleep(sk), &wait);
	release_sock(sk);
	return timeo;
}


/*
 * Copied from unix_stream_recvmsg, but removed credit checks,
 * changed locking calls, changed address handling.
 */
static int caif_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size,
			       int flags)
{
	struct sock *sk = sock->sk;
	int copied = 0;
	int target;
	int err = 0;
	long timeo;

	err = -EOPNOTSUPP;
	if (flags&MSG_OOB)
		goto out;

	msg->msg_namelen = 0;

	/*
	 * Lock the socket to prevent queue disordering
	 * while sleeps in memcpy_tomsg
	 */
	err = -EAGAIN;
	if (sk->sk_state == CAIF_CONNECTING)
		goto out;

	caif_read_lock(sk);
	target = sock_rcvlowat(sk, flags&MSG_WAITALL, size);
	timeo = sock_rcvtimeo(sk, flags&MSG_DONTWAIT);

	do {
		int chunk;
		struct sk_buff *skb;

		lock_sock(sk);
		skb = skb_dequeue(&sk->sk_receive_queue);
		caif_check_flow_release(sk);

		if (skb == NULL) {
			if (copied >= target)
				goto unlock;
			/*
			 *	POSIX 1003.1g mandates this order.
			 */
			err = sock_error(sk);
			if (err)
				goto unlock;
			err = -ECONNRESET;
			if (sk->sk_shutdown & RCV_SHUTDOWN)
				goto unlock;

			err = -EPIPE;
			if (sk->sk_state != CAIF_CONNECTED)
				goto unlock;
			if (sock_flag(sk, SOCK_DEAD))
				goto unlock;

			release_sock(sk);

			err = -EAGAIN;
			if (!timeo)
				break;

			caif_read_unlock(sk);

			timeo = caif_stream_data_wait(sk, timeo);

			if (signal_pending(current)) {
				err = sock_intr_errno(timeo);
				goto out;
			}
			caif_read_lock(sk);
			continue;
unlock:
			release_sock(sk);
			break;
		}
		release_sock(sk);
		chunk = min_t(unsigned int, skb->len, size);
		if (memcpy_toiovec(msg->msg_iov, skb->data, chunk)) {
			skb_queue_head(&sk->sk_receive_queue, skb);
			if (copied == 0)
				copied = -EFAULT;
			break;
		}
		copied += chunk;
		size -= chunk;

		/* Mark read part of skb as used */
		if (!(flags & MSG_PEEK)) {
			skb_pull(skb, chunk);

			/* put the skb back if we didn't use it up. */
			if (skb->len) {
				skb_queue_head(&sk->sk_receive_queue, skb);
				break;
			}
			kfree_skb(skb);

		} else {
			/*
			 * It is questionable, see note in unix_dgram_recvmsg.
			 */
			/* put message back and return */
			skb_queue_head(&sk->sk_receive_queue, skb);
			break;
		}
	} while (size);
	caif_read_unlock(sk);

out:
	return copied ? : err;
}

/*
 * Copied from sock.c:sock_wait_for_wmem, but change to wait for
 * CAIF flow-on and sock_writable.
 */
static long caif_wait_for_flow_on(struct caifsock *cf_sk,
				  int wait_writeable, long timeo, int *err)
{
	struct sock *sk = &cf_sk->sk;
	DEFINE_WAIT(wait);
	for (;;) {
		*err = 0;
		if (tx_flow_is_on(cf_sk) &&
			(!wait_writeable || sock_writeable(&cf_sk->sk)))
			break;
		*err = -ETIMEDOUT;
		if (!timeo)
			break;
		*err = -ERESTARTSYS;
		if (signal_pending(current))
			break;
		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
		*err = -ECONNRESET;
		if (sk->sk_shutdown & SHUTDOWN_MASK)
			break;
		*err = -sk->sk_err;
		if (sk->sk_err)
			break;
		*err = -EPIPE;
		if (cf_sk->sk.sk_state != CAIF_CONNECTED)
			break;
		timeo = schedule_timeout(timeo);
	}
	finish_wait(sk_sleep(sk), &wait);
	return timeo;
}

/*
 * Transmit a SKB. The device may temporarily request re-transmission
 * by returning EAGAIN.
 */
static int transmit_skb(struct sk_buff *skb, struct caifsock *cf_sk,
			int noblock, long timeo)
{
	struct cfpkt *pkt;

	pkt = cfpkt_fromnative(CAIF_DIR_OUT, skb);
	memset(skb->cb, 0, sizeof(struct caif_payload_info));
	cfpkt_set_prio(pkt, cf_sk->sk.sk_priority);

	if (cf_sk->layer.dn == NULL) {
		kfree_skb(skb);
		return -EINVAL;
	}

	return cf_sk->layer.dn->transmit(cf_sk->layer.dn, pkt);
}

/* Copied from af_unix:unix_dgram_sendmsg, and adapted to CAIF */
static int caif_seqpkt_sendmsg(struct kiocb *kiocb, struct socket *sock,
			       struct msghdr *msg, size_t len)
{
	struct sock *sk = sock->sk;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
	int buffer_size;
	int ret = 0;
	struct sk_buff *skb = NULL;
	int noblock;
	long timeo;
	caif_assert(cf_sk);
	ret = sock_error(sk);
	if (ret)
		goto err;

	ret = -EOPNOTSUPP;
	if (msg->msg_flags&MSG_OOB)
		goto err;

	ret = -EOPNOTSUPP;
	if (msg->msg_namelen)
		goto err;

	ret = -EINVAL;
	if (unlikely(msg->msg_iov->iov_base == NULL))
		goto err;
	noblock = msg->msg_flags & MSG_DONTWAIT;

	timeo = sock_sndtimeo(sk, noblock);
	timeo = caif_wait_for_flow_on(container_of(sk, struct caifsock, sk),
				1, timeo, &ret);

	if (ret)
		goto err;
	ret = -EPIPE;
	if (cf_sk->sk.sk_state != CAIF_CONNECTED ||
		sock_flag(sk, SOCK_DEAD) ||
		(sk->sk_shutdown & RCV_SHUTDOWN))
		goto err;

	/* Error if trying to write more than maximum frame size. */
	ret = -EMSGSIZE;
	if (len > cf_sk->maxframe && cf_sk->sk.sk_protocol != CAIFPROTO_RFM)
		goto err;

	buffer_size = len + cf_sk->headroom + cf_sk->tailroom;

	ret = -ENOMEM;
	skb = sock_alloc_send_skb(sk, buffer_size, noblock, &ret);

	if (!skb || skb_tailroom(skb) < buffer_size)
		goto err;

	skb_reserve(skb, cf_sk->headroom);

	ret = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);

	if (ret)
		goto err;
	ret = transmit_skb(skb, cf_sk, noblock, timeo);
	if (ret < 0)
		/* skb is already freed */
		return ret;

	return len;
err:
	kfree_skb(skb);
	return ret;
}

/*
 * Copied from unix_stream_sendmsg and adapted to CAIF:
 * Changed removed permission handling and added waiting for flow on
 * and other minor adaptations.
 */
static int caif_stream_sendmsg(struct kiocb *kiocb, struct socket *sock,
			       struct msghdr *msg, size_t len)
{
	struct sock *sk = sock->sk;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
	int err, size;
	struct sk_buff *skb;
	int sent = 0;
	long timeo;

	err = -EOPNOTSUPP;
	if (unlikely(msg->msg_flags&MSG_OOB))
		goto out_err;

	if (unlikely(msg->msg_namelen))
		goto out_err;

	timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
	timeo = caif_wait_for_flow_on(cf_sk, 1, timeo, &err);

	if (unlikely(sk->sk_shutdown & SEND_SHUTDOWN))
		goto pipe_err;

	while (sent < len) {

		size = len-sent;

		if (size > cf_sk->maxframe)
			size = cf_sk->maxframe;

		/* If size is more than half of sndbuf, chop up message */
		if (size > ((sk->sk_sndbuf >> 1) - 64))
			size = (sk->sk_sndbuf >> 1) - 64;

		if (size > SKB_MAX_ALLOC)
			size = SKB_MAX_ALLOC;

		skb = sock_alloc_send_skb(sk,
					size + cf_sk->headroom +
					cf_sk->tailroom,
					msg->msg_flags&MSG_DONTWAIT,
					&err);
		if (skb == NULL)
			goto out_err;

		skb_reserve(skb, cf_sk->headroom);
		/*
		 *	If you pass two values to the sock_alloc_send_skb
		 *	it tries to grab the large buffer with GFP_NOFS
		 *	(which can fail easily), and if it fails grab the
		 *	fallback size buffer which is under a page and will
		 *	succeed. [Alan]
		 */
		size = min_t(int, size, skb_tailroom(skb));

		err = memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size);
		if (err) {
			kfree_skb(skb);
			goto out_err;
		}
		err = transmit_skb(skb, cf_sk,
				msg->msg_flags&MSG_DONTWAIT, timeo);
		if (err < 0)
			/* skb is already freed */
			goto pipe_err;

		sent += size;
	}

	return sent;

pipe_err:
	if (sent == 0 && !(msg->msg_flags&MSG_NOSIGNAL))
		send_sig(SIGPIPE, current, 0);
	err = -EPIPE;
out_err:
	return sent ? : err;
}

static int setsockopt(struct socket *sock,
		      int lvl, int opt, char __user *ov, unsigned int ol)
{
	struct sock *sk = sock->sk;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
	int linksel;

	if (cf_sk->sk.sk_socket->state != SS_UNCONNECTED)
		return -ENOPROTOOPT;

	switch (opt) {
	case CAIFSO_LINK_SELECT:
		if (ol < sizeof(int))
			return -EINVAL;
		if (lvl != SOL_CAIF)
			goto bad_sol;
		if (copy_from_user(&linksel, ov, sizeof(int)))
			return -EINVAL;
		lock_sock(&(cf_sk->sk));
		cf_sk->conn_req.link_selector = linksel;
		release_sock(&cf_sk->sk);
		return 0;

	case CAIFSO_REQ_PARAM:
		if (lvl != SOL_CAIF)
			goto bad_sol;
		if (cf_sk->sk.sk_protocol != CAIFPROTO_UTIL)
			return -ENOPROTOOPT;
		lock_sock(&(cf_sk->sk));
		if (ol > sizeof(cf_sk->conn_req.param.data) ||
			copy_from_user(&cf_sk->conn_req.param.data, ov, ol)) {
			release_sock(&cf_sk->sk);
			return -EINVAL;
		}
		cf_sk->conn_req.param.size = ol;
		release_sock(&cf_sk->sk);
		return 0;

	default:
		return -ENOPROTOOPT;
	}

	return 0;
bad_sol:
	return -ENOPROTOOPT;

}

/*
 * caif_connect() - Connect a CAIF Socket
 * Copied and modified af_irda.c:irda_connect().
 *
 * Note : by consulting "errno", the user space caller may learn the cause
 * of the failure. Most of them are visible in the function, others may come
 * from subroutines called and are listed here :
 *  o -EAFNOSUPPORT: bad socket family or type.
 *  o -ESOCKTNOSUPPORT: bad socket type or protocol
 *  o -EINVAL: bad socket address, or CAIF link type
 *  o -ECONNREFUSED: remote end refused the connection.
 *  o -EINPROGRESS: connect request sent but timed out (or non-blocking)
 *  o -EISCONN: already connected.
 *  o -ETIMEDOUT: Connection timed out (send timeout)
 *  o -ENODEV: No link layer to send request
 *  o -ECONNRESET: Received Shutdown indication or lost link layer
 *  o -ENOMEM: Out of memory
 *
 *  State Strategy:
 *  o sk_state: holds the CAIF_* protocol state, it's updated by
 *	caif_ctrl_cb.
 *  o sock->state: holds the SS_* socket state and is updated by connect and
 *	disconnect.
 */
static int caif_connect(struct socket *sock, struct sockaddr *uaddr,
			int addr_len, int flags)
{
	struct sock *sk = sock->sk;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
	long timeo;
	int err;
	int ifindex, headroom, tailroom;
	unsigned int mtu;
	struct net_device *dev;

	lock_sock(sk);

	err = -EAFNOSUPPORT;
	if (uaddr->sa_family != AF_CAIF)
		goto out;

	switch (sock->state) {
	case SS_UNCONNECTED:
		/* Normal case, a fresh connect */
		caif_assert(sk->sk_state == CAIF_DISCONNECTED);
		break;
	case SS_CONNECTING:
		switch (sk->sk_state) {
		case CAIF_CONNECTED:
			sock->state = SS_CONNECTED;
			err = -EISCONN;
			goto out;
		case CAIF_DISCONNECTED:
			/* Reconnect allowed */
			break;
		case CAIF_CONNECTING:
			err = -EALREADY;
			if (flags & O_NONBLOCK)
				goto out;
			goto wait_connect;
		}
		break;
	case SS_CONNECTED:
		caif_assert(sk->sk_state == CAIF_CONNECTED ||
				sk->sk_state == CAIF_DISCONNECTED);
		if (sk->sk_shutdown & SHUTDOWN_MASK) {
			/* Allow re-connect after SHUTDOWN_IND */
			caif_disconnect_client(sock_net(sk), &cf_sk->layer);
			caif_free_client(&cf_sk->layer);
			break;
		}
		/* No reconnect on a seqpacket socket */
		err = -EISCONN;
		goto out;
	case SS_DISCONNECTING:
	case SS_FREE:
		caif_assert(1); /*Should never happen */
		break;
	}
	sk->sk_state = CAIF_DISCONNECTED;
	sock->state = SS_UNCONNECTED;
	sk_stream_kill_queues(&cf_sk->sk);

	err = -EINVAL;
	if (addr_len != sizeof(struct sockaddr_caif))
		goto out;

	memcpy(&cf_sk->conn_req.sockaddr, uaddr,
		sizeof(struct sockaddr_caif));

	/* Move to connecting socket, start sending Connect Requests */
	sock->state = SS_CONNECTING;
	sk->sk_state = CAIF_CONNECTING;

	/* Check priority value comming from socket */
	/* if priority value is out of range it will be ajusted */
	if (cf_sk->sk.sk_priority > CAIF_PRIO_MAX)
		cf_sk->conn_req.priority = CAIF_PRIO_MAX;
	else if (cf_sk->sk.sk_priority < CAIF_PRIO_MIN)
		cf_sk->conn_req.priority = CAIF_PRIO_MIN;
	else
		cf_sk->conn_req.priority = cf_sk->sk.sk_priority;

	/*ifindex = id of the interface.*/
	cf_sk->conn_req.ifindex = cf_sk->sk.sk_bound_dev_if;

	cf_sk->layer.receive = caif_sktrecv_cb;

	err = caif_connect_client(sock_net(sk), &cf_sk->conn_req,
				&cf_sk->layer, &ifindex, &headroom, &tailroom);

	if (err < 0) {
		cf_sk->sk.sk_socket->state = SS_UNCONNECTED;
		cf_sk->sk.sk_state = CAIF_DISCONNECTED;
		goto out;
	}

	err = -ENODEV;
	rcu_read_lock();
	dev = dev_get_by_index_rcu(sock_net(sk), ifindex);
	if (!dev) {
		rcu_read_unlock();
		goto out;
	}
	cf_sk->headroom = LL_RESERVED_SPACE_EXTRA(dev, headroom);
	mtu = dev->mtu;
	rcu_read_unlock();

	cf_sk->tailroom = tailroom;
	cf_sk->maxframe = mtu - (headroom + tailroom);
	if (cf_sk->maxframe < 1) {
		pr_warn("CAIF Interface MTU too small (%d)\n", dev->mtu);
		err = -ENODEV;
		goto out;
	}

	err = -EINPROGRESS;
wait_connect:

	if (sk->sk_state != CAIF_CONNECTED && (flags & O_NONBLOCK))
		goto out;

	timeo = sock_sndtimeo(sk, flags & O_NONBLOCK);

	release_sock(sk);
	err = -ERESTARTSYS;
	timeo = wait_event_interruptible_timeout(*sk_sleep(sk),
			sk->sk_state != CAIF_CONNECTING,
			timeo);
	lock_sock(sk);
	if (timeo < 0)
		goto out; /* -ERESTARTSYS */

	err = -ETIMEDOUT;
	if (timeo == 0 && sk->sk_state != CAIF_CONNECTED)
		goto out;
	if (sk->sk_state != CAIF_CONNECTED) {
		sock->state = SS_UNCONNECTED;
		err = sock_error(sk);
		if (!err)
			err = -ECONNREFUSED;
		goto out;
	}
	sock->state = SS_CONNECTED;
	err = 0;
out:
	release_sock(sk);
	return err;
}

/*
 * caif_release() - Disconnect a CAIF Socket
 * Copied and modified af_irda.c:irda_release().
 */
static int caif_release(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);

	if (!sk)
		return 0;

	set_tx_flow_off(cf_sk);

	/*
	 * Ensure that packets are not queued after this point in time.
	 * caif_queue_rcv_skb checks SOCK_DEAD holding the queue lock,
	 * this ensures no packets when sock is dead.
	 */
	spin_lock_bh(&sk->sk_receive_queue.lock);
	sock_set_flag(sk, SOCK_DEAD);
	spin_unlock_bh(&sk->sk_receive_queue.lock);
	sock->sk = NULL;

	WARN_ON(IS_ERR(cf_sk->debugfs_socket_dir));
	if (cf_sk->debugfs_socket_dir != NULL)
		debugfs_remove_recursive(cf_sk->debugfs_socket_dir);

	lock_sock(&(cf_sk->sk));
	sk->sk_state = CAIF_DISCONNECTED;
	sk->sk_shutdown = SHUTDOWN_MASK;

	caif_disconnect_client(sock_net(sk), &cf_sk->layer);
	cf_sk->sk.sk_socket->state = SS_DISCONNECTING;
	wake_up_interruptible_poll(sk_sleep(sk), POLLERR|POLLHUP);

	sock_orphan(sk);
	sk_stream_kill_queues(&cf_sk->sk);
	release_sock(sk);
	sock_put(sk);
	return 0;
}

/* Copied from af_unix.c:unix_poll(), added CAIF tx_flow handling */
static unsigned int caif_poll(struct file *file,
			      struct socket *sock, poll_table *wait)
{
	struct sock *sk = sock->sk;
	unsigned int mask;
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);

	sock_poll_wait(file, sk_sleep(sk), wait);
	mask = 0;

	/* exceptional events? */
	if (sk->sk_err)
		mask |= POLLERR;
	if (sk->sk_shutdown == SHUTDOWN_MASK)
		mask |= POLLHUP;
	if (sk->sk_shutdown & RCV_SHUTDOWN)
		mask |= POLLRDHUP;

	/* readable? */
	if (!skb_queue_empty(&sk->sk_receive_queue) ||
		(sk->sk_shutdown & RCV_SHUTDOWN))
		mask |= POLLIN | POLLRDNORM;

	/*
	 * we set writable also when the other side has shut down the
	 * connection. This prevents stuck sockets.
	 */
	if (sock_writeable(sk) && tx_flow_is_on(cf_sk))
		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;

	return mask;
}

static const struct proto_ops caif_seqpacket_ops = {
	.family = PF_CAIF,
	.owner = THIS_MODULE,
	.release = caif_release,
	.bind = sock_no_bind,
	.connect = caif_connect,
	.socketpair = sock_no_socketpair,
	.accept = sock_no_accept,
	.getname = sock_no_getname,
	.poll = caif_poll,
	.ioctl = sock_no_ioctl,
	.listen = sock_no_listen,
	.shutdown = sock_no_shutdown,
	.setsockopt = setsockopt,
	.getsockopt = sock_no_getsockopt,
	.sendmsg = caif_seqpkt_sendmsg,
	.recvmsg = caif_seqpkt_recvmsg,
	.mmap = sock_no_mmap,
	.sendpage = sock_no_sendpage,
};

static const struct proto_ops caif_stream_ops = {
	.family = PF_CAIF,
	.owner = THIS_MODULE,
	.release = caif_release,
	.bind = sock_no_bind,
	.connect = caif_connect,
	.socketpair = sock_no_socketpair,
	.accept = sock_no_accept,
	.getname = sock_no_getname,
	.poll = caif_poll,
	.ioctl = sock_no_ioctl,
	.listen = sock_no_listen,
	.shutdown = sock_no_shutdown,
	.setsockopt = setsockopt,
	.getsockopt = sock_no_getsockopt,
	.sendmsg = caif_stream_sendmsg,
	.recvmsg = caif_stream_recvmsg,
	.mmap = sock_no_mmap,
	.sendpage = sock_no_sendpage,
};

/* This function is called when a socket is finally destroyed. */
static void caif_sock_destructor(struct sock *sk)
{
	struct caifsock *cf_sk = container_of(sk, struct caifsock, sk);
	caif_assert(!atomic_read(&sk->sk_wmem_alloc));
	caif_assert(sk_unhashed(sk));
	caif_assert(!sk->sk_socket);
	if (!sock_flag(sk, SOCK_DEAD)) {
		pr_debug("Attempt to release alive CAIF socket: %p\n", sk);
		return;
	}
	sk_stream_kill_queues(&cf_sk->sk);
	caif_free_client(&cf_sk->layer);
}

static int caif_create(struct net *net, struct socket *sock, int protocol,
		       int kern)
{
	struct sock *sk = NULL;
	struct caifsock *cf_sk = NULL;
	static struct proto prot = {.name = "PF_CAIF",
		.owner = THIS_MODULE,
		.obj_size = sizeof(struct caifsock),
	};

	if (!capable(CAP_SYS_ADMIN) && !capable(CAP_NET_ADMIN))
		return -EPERM;
	/*
	 * The sock->type specifies the socket type to use.
	 * The CAIF socket is a packet stream in the sense
	 * that it is packet based. CAIF trusts the reliability
	 * of the link, no resending is implemented.
	 */
	if (sock->type == SOCK_SEQPACKET)
		sock->ops = &caif_seqpacket_ops;
	else if (sock->type == SOCK_STREAM)
		sock->ops = &caif_stream_ops;
	else
		return -ESOCKTNOSUPPORT;

	if (protocol < 0 || protocol >= CAIFPROTO_MAX)
		return -EPROTONOSUPPORT;
	/*
	 * Set the socket state to unconnected.	 The socket state
	 * is really not used at all in the net/core or socket.c but the
	 * initialization makes sure that sock->state is not uninitialized.
	 */
	sk = sk_alloc(net, PF_CAIF, GFP_KERNEL, &prot);
	if (!sk)
		return -ENOMEM;

	cf_sk = container_of(sk, struct caifsock, sk);

	/* Store the protocol */
	sk->sk_protocol = (unsigned char) protocol;

	/* Initialize default priority for well-known cases */
	switch (protocol) {
	case CAIFPROTO_AT:
		sk->sk_priority = TC_PRIO_CONTROL;
		break;
	case CAIFPROTO_RFM:
		sk->sk_priority = TC_PRIO_INTERACTIVE_BULK;
		break;
	default:
		sk->sk_priority = TC_PRIO_BESTEFFORT;
	}

	/*
	 * Lock in order to try to stop someone from opening the socket
	 * too early.
	 */
	lock_sock(&(cf_sk->sk));

	/* Initialize the nozero default sock structure data. */
	sock_init_data(sock, sk);
	sk->sk_destruct = caif_sock_destructor;

	mutex_init(&cf_sk->readlock); /* single task reading lock */
	cf_sk->layer.ctrlcmd = caif_ctrl_cb;
	cf_sk->sk.sk_socket->state = SS_UNCONNECTED;
	cf_sk->sk.sk_state = CAIF_DISCONNECTED;

	set_tx_flow_off(cf_sk);
	set_rx_flow_on(cf_sk);

	/* Set default options on configuration */
	cf_sk->conn_req.link_selector = CAIF_LINK_LOW_LATENCY;
	cf_sk->conn_req.protocol = protocol;
	release_sock(&cf_sk->sk);
	return 0;
}


static struct net_proto_family caif_family_ops = {
	.family = PF_CAIF,
	.create = caif_create,
	.owner = THIS_MODULE,
};

static int __init caif_sktinit_module(void)
{
	int err = sock_register(&caif_family_ops);
	if (!err)
		return err;
	return 0;
}

static void __exit caif_sktexit_module(void)
{
	sock_unregister(PF_CAIF);
}
module_init(caif_sktinit_module);
module_exit(caif_sktexit_module);