summaryrefslogtreecommitdiff
path: root/net/vmw_vsock/virtio_transport_common.c
blob: 193f959e51efee2fb9ae8d8ed0a7c8d3f894a58d (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * common code for virtio vsock
 *
 * Copyright (C) 2013-2015 Red Hat, Inc.
 * Author: Asias He <asias@redhat.com>
 *         Stefan Hajnoczi <stefanha@redhat.com>
 */
#include <linux/spinlock.h>
#include <linux/module.h>
#include <linux/sched/signal.h>
#include <linux/ctype.h>
#include <linux/list.h>
#include <linux/virtio.h>
#include <linux/virtio_ids.h>
#include <linux/virtio_config.h>
#include <linux/virtio_vsock.h>
#include <uapi/linux/vsockmon.h>

#include <net/sock.h>
#include <net/af_vsock.h>

#define CREATE_TRACE_POINTS
#include <trace/events/vsock_virtio_transport_common.h>

/* How long to wait for graceful shutdown of a connection */
#define VSOCK_CLOSE_TIMEOUT (8 * HZ)

/* Threshold for detecting small packets to copy */
#define GOOD_COPY_LEN  128

static const struct virtio_transport *virtio_transport_get_ops(void)
{
	const struct vsock_transport *t = vsock_core_get_transport();

	return container_of(t, struct virtio_transport, transport);
}

static struct virtio_vsock_pkt *
virtio_transport_alloc_pkt(struct virtio_vsock_pkt_info *info,
			   size_t len,
			   u32 src_cid,
			   u32 src_port,
			   u32 dst_cid,
			   u32 dst_port)
{
	struct virtio_vsock_pkt *pkt;
	int err;

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

	pkt->hdr.type		= cpu_to_le16(info->type);
	pkt->hdr.op		= cpu_to_le16(info->op);
	pkt->hdr.src_cid	= cpu_to_le64(src_cid);
	pkt->hdr.dst_cid	= cpu_to_le64(dst_cid);
	pkt->hdr.src_port	= cpu_to_le32(src_port);
	pkt->hdr.dst_port	= cpu_to_le32(dst_port);
	pkt->hdr.flags		= cpu_to_le32(info->flags);
	pkt->len		= len;
	pkt->hdr.len		= cpu_to_le32(len);
	pkt->reply		= info->reply;
	pkt->vsk		= info->vsk;

	if (info->msg && len > 0) {
		pkt->buf = kmalloc(len, GFP_KERNEL);
		if (!pkt->buf)
			goto out_pkt;

		pkt->buf_len = len;

		err = memcpy_from_msg(pkt->buf, info->msg, len);
		if (err)
			goto out;
	}

	trace_virtio_transport_alloc_pkt(src_cid, src_port,
					 dst_cid, dst_port,
					 len,
					 info->type,
					 info->op,
					 info->flags);

	return pkt;

out:
	kfree(pkt->buf);
out_pkt:
	kfree(pkt);
	return NULL;
}

/* Packet capture */
static struct sk_buff *virtio_transport_build_skb(void *opaque)
{
	struct virtio_vsock_pkt *pkt = opaque;
	struct af_vsockmon_hdr *hdr;
	struct sk_buff *skb;
	size_t payload_len;
	void *payload_buf;

	/* A packet could be split to fit the RX buffer, so we can retrieve
	 * the payload length from the header and the buffer pointer taking
	 * care of the offset in the original packet.
	 */
	payload_len = le32_to_cpu(pkt->hdr.len);
	payload_buf = pkt->buf + pkt->off;

	skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len,
			GFP_ATOMIC);
	if (!skb)
		return NULL;

	hdr = skb_put(skb, sizeof(*hdr));

	/* pkt->hdr is little-endian so no need to byteswap here */
	hdr->src_cid = pkt->hdr.src_cid;
	hdr->src_port = pkt->hdr.src_port;
	hdr->dst_cid = pkt->hdr.dst_cid;
	hdr->dst_port = pkt->hdr.dst_port;

	hdr->transport = cpu_to_le16(AF_VSOCK_TRANSPORT_VIRTIO);
	hdr->len = cpu_to_le16(sizeof(pkt->hdr));
	memset(hdr->reserved, 0, sizeof(hdr->reserved));

	switch (le16_to_cpu(pkt->hdr.op)) {
	case VIRTIO_VSOCK_OP_REQUEST:
	case VIRTIO_VSOCK_OP_RESPONSE:
		hdr->op = cpu_to_le16(AF_VSOCK_OP_CONNECT);
		break;
	case VIRTIO_VSOCK_OP_RST:
	case VIRTIO_VSOCK_OP_SHUTDOWN:
		hdr->op = cpu_to_le16(AF_VSOCK_OP_DISCONNECT);
		break;
	case VIRTIO_VSOCK_OP_RW:
		hdr->op = cpu_to_le16(AF_VSOCK_OP_PAYLOAD);
		break;
	case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
	case VIRTIO_VSOCK_OP_CREDIT_REQUEST:
		hdr->op = cpu_to_le16(AF_VSOCK_OP_CONTROL);
		break;
	default:
		hdr->op = cpu_to_le16(AF_VSOCK_OP_UNKNOWN);
		break;
	}

	skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr));

	if (payload_len) {
		skb_put_data(skb, payload_buf, payload_len);
	}

	return skb;
}

void virtio_transport_deliver_tap_pkt(struct virtio_vsock_pkt *pkt)
{
	vsock_deliver_tap(virtio_transport_build_skb, pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_deliver_tap_pkt);

static int virtio_transport_send_pkt_info(struct vsock_sock *vsk,
					  struct virtio_vsock_pkt_info *info)
{
	u32 src_cid, src_port, dst_cid, dst_port;
	struct virtio_vsock_sock *vvs;
	struct virtio_vsock_pkt *pkt;
	u32 pkt_len = info->pkt_len;

	src_cid = vm_sockets_get_local_cid();
	src_port = vsk->local_addr.svm_port;
	if (!info->remote_cid) {
		dst_cid	= vsk->remote_addr.svm_cid;
		dst_port = vsk->remote_addr.svm_port;
	} else {
		dst_cid = info->remote_cid;
		dst_port = info->remote_port;
	}

	vvs = vsk->trans;

	/* we can send less than pkt_len bytes */
	if (pkt_len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE)
		pkt_len = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;

	/* virtio_transport_get_credit might return less than pkt_len credit */
	pkt_len = virtio_transport_get_credit(vvs, pkt_len);

	/* Do not send zero length OP_RW pkt */
	if (pkt_len == 0 && info->op == VIRTIO_VSOCK_OP_RW)
		return pkt_len;

	pkt = virtio_transport_alloc_pkt(info, pkt_len,
					 src_cid, src_port,
					 dst_cid, dst_port);
	if (!pkt) {
		virtio_transport_put_credit(vvs, pkt_len);
		return -ENOMEM;
	}

	virtio_transport_inc_tx_pkt(vvs, pkt);

	return virtio_transport_get_ops()->send_pkt(pkt);
}

static bool virtio_transport_inc_rx_pkt(struct virtio_vsock_sock *vvs,
					struct virtio_vsock_pkt *pkt)
{
	if (vvs->rx_bytes + pkt->len > vvs->buf_alloc)
		return false;

	vvs->rx_bytes += pkt->len;
	return true;
}

static void virtio_transport_dec_rx_pkt(struct virtio_vsock_sock *vvs,
					struct virtio_vsock_pkt *pkt)
{
	vvs->rx_bytes -= pkt->len;
	vvs->fwd_cnt += pkt->len;
}

void virtio_transport_inc_tx_pkt(struct virtio_vsock_sock *vvs, struct virtio_vsock_pkt *pkt)
{
	spin_lock_bh(&vvs->rx_lock);
	vvs->last_fwd_cnt = vvs->fwd_cnt;
	pkt->hdr.fwd_cnt = cpu_to_le32(vvs->fwd_cnt);
	pkt->hdr.buf_alloc = cpu_to_le32(vvs->buf_alloc);
	spin_unlock_bh(&vvs->rx_lock);
}
EXPORT_SYMBOL_GPL(virtio_transport_inc_tx_pkt);

u32 virtio_transport_get_credit(struct virtio_vsock_sock *vvs, u32 credit)
{
	u32 ret;

	spin_lock_bh(&vvs->tx_lock);
	ret = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
	if (ret > credit)
		ret = credit;
	vvs->tx_cnt += ret;
	spin_unlock_bh(&vvs->tx_lock);

	return ret;
}
EXPORT_SYMBOL_GPL(virtio_transport_get_credit);

void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit)
{
	spin_lock_bh(&vvs->tx_lock);
	vvs->tx_cnt -= credit;
	spin_unlock_bh(&vvs->tx_lock);
}
EXPORT_SYMBOL_GPL(virtio_transport_put_credit);

static int virtio_transport_send_credit_update(struct vsock_sock *vsk,
					       int type,
					       struct virtio_vsock_hdr *hdr)
{
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_CREDIT_UPDATE,
		.type = type,
		.vsk = vsk,
	};

	return virtio_transport_send_pkt_info(vsk, &info);
}

static ssize_t
virtio_transport_stream_do_peek(struct vsock_sock *vsk,
				struct msghdr *msg,
				size_t len)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	struct virtio_vsock_pkt *pkt;
	size_t bytes, total = 0, off;
	int err = -EFAULT;

	spin_lock_bh(&vvs->rx_lock);

	list_for_each_entry(pkt, &vvs->rx_queue, list) {
		off = pkt->off;

		if (total == len)
			break;

		while (total < len && off < pkt->len) {
			bytes = len - total;
			if (bytes > pkt->len - off)
				bytes = pkt->len - off;

			/* sk_lock is held by caller so no one else can dequeue.
			 * Unlock rx_lock since memcpy_to_msg() may sleep.
			 */
			spin_unlock_bh(&vvs->rx_lock);

			err = memcpy_to_msg(msg, pkt->buf + off, bytes);
			if (err)
				goto out;

			spin_lock_bh(&vvs->rx_lock);

			total += bytes;
			off += bytes;
		}
	}

	spin_unlock_bh(&vvs->rx_lock);

	return total;

out:
	if (total)
		err = total;
	return err;
}

static ssize_t
virtio_transport_stream_do_dequeue(struct vsock_sock *vsk,
				   struct msghdr *msg,
				   size_t len)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	struct virtio_vsock_pkt *pkt;
	size_t bytes, total = 0;
	u32 free_space;
	int err = -EFAULT;

	spin_lock_bh(&vvs->rx_lock);
	while (total < len && !list_empty(&vvs->rx_queue)) {
		pkt = list_first_entry(&vvs->rx_queue,
				       struct virtio_vsock_pkt, list);

		bytes = len - total;
		if (bytes > pkt->len - pkt->off)
			bytes = pkt->len - pkt->off;

		/* sk_lock is held by caller so no one else can dequeue.
		 * Unlock rx_lock since memcpy_to_msg() may sleep.
		 */
		spin_unlock_bh(&vvs->rx_lock);

		err = memcpy_to_msg(msg, pkt->buf + pkt->off, bytes);
		if (err)
			goto out;

		spin_lock_bh(&vvs->rx_lock);

		total += bytes;
		pkt->off += bytes;
		if (pkt->off == pkt->len) {
			virtio_transport_dec_rx_pkt(vvs, pkt);
			list_del(&pkt->list);
			virtio_transport_free_pkt(pkt);
		}
	}

	free_space = vvs->buf_alloc - (vvs->fwd_cnt - vvs->last_fwd_cnt);

	spin_unlock_bh(&vvs->rx_lock);

	/* To reduce the number of credit update messages,
	 * don't update credits as long as lots of space is available.
	 * Note: the limit chosen here is arbitrary. Setting the limit
	 * too high causes extra messages. Too low causes transmitter
	 * stalls. As stalls are in theory more expensive than extra
	 * messages, we set the limit to a high value. TODO: experiment
	 * with different values.
	 */
	if (free_space < VIRTIO_VSOCK_MAX_PKT_BUF_SIZE) {
		virtio_transport_send_credit_update(vsk,
						    VIRTIO_VSOCK_TYPE_STREAM,
						    NULL);
	}

	return total;

out:
	if (total)
		err = total;
	return err;
}

ssize_t
virtio_transport_stream_dequeue(struct vsock_sock *vsk,
				struct msghdr *msg,
				size_t len, int flags)
{
	if (flags & MSG_PEEK)
		return virtio_transport_stream_do_peek(vsk, msg, len);
	else
		return virtio_transport_stream_do_dequeue(vsk, msg, len);
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_dequeue);

int
virtio_transport_dgram_dequeue(struct vsock_sock *vsk,
			       struct msghdr *msg,
			       size_t len, int flags)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_dequeue);

s64 virtio_transport_stream_has_data(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	s64 bytes;

	spin_lock_bh(&vvs->rx_lock);
	bytes = vvs->rx_bytes;
	spin_unlock_bh(&vvs->rx_lock);

	return bytes;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_has_data);

static s64 virtio_transport_has_space(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	s64 bytes;

	bytes = vvs->peer_buf_alloc - (vvs->tx_cnt - vvs->peer_fwd_cnt);
	if (bytes < 0)
		bytes = 0;

	return bytes;
}

s64 virtio_transport_stream_has_space(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	s64 bytes;

	spin_lock_bh(&vvs->tx_lock);
	bytes = virtio_transport_has_space(vsk);
	spin_unlock_bh(&vvs->tx_lock);

	return bytes;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_has_space);

int virtio_transport_do_socket_init(struct vsock_sock *vsk,
				    struct vsock_sock *psk)
{
	struct virtio_vsock_sock *vvs;

	vvs = kzalloc(sizeof(*vvs), GFP_KERNEL);
	if (!vvs)
		return -ENOMEM;

	vsk->trans = vvs;
	vvs->vsk = vsk;
	if (psk) {
		struct virtio_vsock_sock *ptrans = psk->trans;

		vvs->buf_size	= ptrans->buf_size;
		vvs->buf_size_min = ptrans->buf_size_min;
		vvs->buf_size_max = ptrans->buf_size_max;
		vvs->peer_buf_alloc = ptrans->peer_buf_alloc;
	} else {
		vvs->buf_size = VIRTIO_VSOCK_DEFAULT_BUF_SIZE;
		vvs->buf_size_min = VIRTIO_VSOCK_DEFAULT_MIN_BUF_SIZE;
		vvs->buf_size_max = VIRTIO_VSOCK_DEFAULT_MAX_BUF_SIZE;
	}

	vvs->buf_alloc = vvs->buf_size;

	spin_lock_init(&vvs->rx_lock);
	spin_lock_init(&vvs->tx_lock);
	INIT_LIST_HEAD(&vvs->rx_queue);

	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_do_socket_init);

u64 virtio_transport_get_buffer_size(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	return vvs->buf_size;
}
EXPORT_SYMBOL_GPL(virtio_transport_get_buffer_size);

u64 virtio_transport_get_min_buffer_size(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	return vvs->buf_size_min;
}
EXPORT_SYMBOL_GPL(virtio_transport_get_min_buffer_size);

u64 virtio_transport_get_max_buffer_size(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	return vvs->buf_size_max;
}
EXPORT_SYMBOL_GPL(virtio_transport_get_max_buffer_size);

void virtio_transport_set_buffer_size(struct vsock_sock *vsk, u64 val)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
		val = VIRTIO_VSOCK_MAX_BUF_SIZE;
	if (val < vvs->buf_size_min)
		vvs->buf_size_min = val;
	if (val > vvs->buf_size_max)
		vvs->buf_size_max = val;
	vvs->buf_size = val;
	vvs->buf_alloc = val;

	virtio_transport_send_credit_update(vsk, VIRTIO_VSOCK_TYPE_STREAM,
					    NULL);
}
EXPORT_SYMBOL_GPL(virtio_transport_set_buffer_size);

void virtio_transport_set_min_buffer_size(struct vsock_sock *vsk, u64 val)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
		val = VIRTIO_VSOCK_MAX_BUF_SIZE;
	if (val > vvs->buf_size)
		vvs->buf_size = val;
	vvs->buf_size_min = val;
}
EXPORT_SYMBOL_GPL(virtio_transport_set_min_buffer_size);

void virtio_transport_set_max_buffer_size(struct vsock_sock *vsk, u64 val)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	if (val > VIRTIO_VSOCK_MAX_BUF_SIZE)
		val = VIRTIO_VSOCK_MAX_BUF_SIZE;
	if (val < vvs->buf_size)
		vvs->buf_size = val;
	vvs->buf_size_max = val;
}
EXPORT_SYMBOL_GPL(virtio_transport_set_max_buffer_size);

int
virtio_transport_notify_poll_in(struct vsock_sock *vsk,
				size_t target,
				bool *data_ready_now)
{
	if (vsock_stream_has_data(vsk))
		*data_ready_now = true;
	else
		*data_ready_now = false;

	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_in);

int
virtio_transport_notify_poll_out(struct vsock_sock *vsk,
				 size_t target,
				 bool *space_avail_now)
{
	s64 free_space;

	free_space = vsock_stream_has_space(vsk);
	if (free_space > 0)
		*space_avail_now = true;
	else if (free_space == 0)
		*space_avail_now = false;

	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_poll_out);

int virtio_transport_notify_recv_init(struct vsock_sock *vsk,
	size_t target, struct vsock_transport_recv_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_init);

int virtio_transport_notify_recv_pre_block(struct vsock_sock *vsk,
	size_t target, struct vsock_transport_recv_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_block);

int virtio_transport_notify_recv_pre_dequeue(struct vsock_sock *vsk,
	size_t target, struct vsock_transport_recv_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_pre_dequeue);

int virtio_transport_notify_recv_post_dequeue(struct vsock_sock *vsk,
	size_t target, ssize_t copied, bool data_read,
	struct vsock_transport_recv_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_recv_post_dequeue);

int virtio_transport_notify_send_init(struct vsock_sock *vsk,
	struct vsock_transport_send_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_init);

int virtio_transport_notify_send_pre_block(struct vsock_sock *vsk,
	struct vsock_transport_send_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_block);

int virtio_transport_notify_send_pre_enqueue(struct vsock_sock *vsk,
	struct vsock_transport_send_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_pre_enqueue);

int virtio_transport_notify_send_post_enqueue(struct vsock_sock *vsk,
	ssize_t written, struct vsock_transport_send_notify_data *data)
{
	return 0;
}
EXPORT_SYMBOL_GPL(virtio_transport_notify_send_post_enqueue);

u64 virtio_transport_stream_rcvhiwat(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	return vvs->buf_size;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_rcvhiwat);

bool virtio_transport_stream_is_active(struct vsock_sock *vsk)
{
	return true;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_is_active);

bool virtio_transport_stream_allow(u32 cid, u32 port)
{
	return true;
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_allow);

int virtio_transport_dgram_bind(struct vsock_sock *vsk,
				struct sockaddr_vm *addr)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_bind);

bool virtio_transport_dgram_allow(u32 cid, u32 port)
{
	return false;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_allow);

int virtio_transport_connect(struct vsock_sock *vsk)
{
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_REQUEST,
		.type = VIRTIO_VSOCK_TYPE_STREAM,
		.vsk = vsk,
	};

	return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_connect);

int virtio_transport_shutdown(struct vsock_sock *vsk, int mode)
{
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_SHUTDOWN,
		.type = VIRTIO_VSOCK_TYPE_STREAM,
		.flags = (mode & RCV_SHUTDOWN ?
			  VIRTIO_VSOCK_SHUTDOWN_RCV : 0) |
			 (mode & SEND_SHUTDOWN ?
			  VIRTIO_VSOCK_SHUTDOWN_SEND : 0),
		.vsk = vsk,
	};

	return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_shutdown);

int
virtio_transport_dgram_enqueue(struct vsock_sock *vsk,
			       struct sockaddr_vm *remote_addr,
			       struct msghdr *msg,
			       size_t dgram_len)
{
	return -EOPNOTSUPP;
}
EXPORT_SYMBOL_GPL(virtio_transport_dgram_enqueue);

ssize_t
virtio_transport_stream_enqueue(struct vsock_sock *vsk,
				struct msghdr *msg,
				size_t len)
{
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_RW,
		.type = VIRTIO_VSOCK_TYPE_STREAM,
		.msg = msg,
		.pkt_len = len,
		.vsk = vsk,
	};

	return virtio_transport_send_pkt_info(vsk, &info);
}
EXPORT_SYMBOL_GPL(virtio_transport_stream_enqueue);

void virtio_transport_destruct(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;

	kfree(vvs);
}
EXPORT_SYMBOL_GPL(virtio_transport_destruct);

static int virtio_transport_reset(struct vsock_sock *vsk,
				  struct virtio_vsock_pkt *pkt)
{
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_RST,
		.type = VIRTIO_VSOCK_TYPE_STREAM,
		.reply = !!pkt,
		.vsk = vsk,
	};

	/* Send RST only if the original pkt is not a RST pkt */
	if (pkt && le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
		return 0;

	return virtio_transport_send_pkt_info(vsk, &info);
}

/* Normally packets are associated with a socket.  There may be no socket if an
 * attempt was made to connect to a socket that does not exist.
 */
static int virtio_transport_reset_no_sock(struct virtio_vsock_pkt *pkt)
{
	const struct virtio_transport *t;
	struct virtio_vsock_pkt *reply;
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_RST,
		.type = le16_to_cpu(pkt->hdr.type),
		.reply = true,
	};

	/* Send RST only if the original pkt is not a RST pkt */
	if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
		return 0;

	reply = virtio_transport_alloc_pkt(&info, 0,
					   le64_to_cpu(pkt->hdr.dst_cid),
					   le32_to_cpu(pkt->hdr.dst_port),
					   le64_to_cpu(pkt->hdr.src_cid),
					   le32_to_cpu(pkt->hdr.src_port));
	if (!reply)
		return -ENOMEM;

	t = virtio_transport_get_ops();
	if (!t) {
		virtio_transport_free_pkt(reply);
		return -ENOTCONN;
	}

	return t->send_pkt(reply);
}

static void virtio_transport_wait_close(struct sock *sk, long timeout)
{
	if (timeout) {
		DEFINE_WAIT_FUNC(wait, woken_wake_function);

		add_wait_queue(sk_sleep(sk), &wait);

		do {
			if (sk_wait_event(sk, &timeout,
					  sock_flag(sk, SOCK_DONE), &wait))
				break;
		} while (!signal_pending(current) && timeout);

		remove_wait_queue(sk_sleep(sk), &wait);
	}
}

static void virtio_transport_do_close(struct vsock_sock *vsk,
				      bool cancel_timeout)
{
	struct sock *sk = sk_vsock(vsk);

	sock_set_flag(sk, SOCK_DONE);
	vsk->peer_shutdown = SHUTDOWN_MASK;
	if (vsock_stream_has_data(vsk) <= 0)
		sk->sk_state = TCP_CLOSING;
	sk->sk_state_change(sk);

	if (vsk->close_work_scheduled &&
	    (!cancel_timeout || cancel_delayed_work(&vsk->close_work))) {
		vsk->close_work_scheduled = false;

		vsock_remove_sock(vsk);

		/* Release refcnt obtained when we scheduled the timeout */
		sock_put(sk);
	}
}

static void virtio_transport_close_timeout(struct work_struct *work)
{
	struct vsock_sock *vsk =
		container_of(work, struct vsock_sock, close_work.work);
	struct sock *sk = sk_vsock(vsk);

	sock_hold(sk);
	lock_sock(sk);

	if (!sock_flag(sk, SOCK_DONE)) {
		(void)virtio_transport_reset(vsk, NULL);

		virtio_transport_do_close(vsk, false);
	}

	vsk->close_work_scheduled = false;

	release_sock(sk);
	sock_put(sk);
}

/* User context, vsk->sk is locked */
static bool virtio_transport_close(struct vsock_sock *vsk)
{
	struct sock *sk = &vsk->sk;

	if (!(sk->sk_state == TCP_ESTABLISHED ||
	      sk->sk_state == TCP_CLOSING))
		return true;

	/* Already received SHUTDOWN from peer, reply with RST */
	if ((vsk->peer_shutdown & SHUTDOWN_MASK) == SHUTDOWN_MASK) {
		(void)virtio_transport_reset(vsk, NULL);
		return true;
	}

	if ((sk->sk_shutdown & SHUTDOWN_MASK) != SHUTDOWN_MASK)
		(void)virtio_transport_shutdown(vsk, SHUTDOWN_MASK);

	if (sock_flag(sk, SOCK_LINGER) && !(current->flags & PF_EXITING))
		virtio_transport_wait_close(sk, sk->sk_lingertime);

	if (sock_flag(sk, SOCK_DONE)) {
		return true;
	}

	sock_hold(sk);
	INIT_DELAYED_WORK(&vsk->close_work,
			  virtio_transport_close_timeout);
	vsk->close_work_scheduled = true;
	schedule_delayed_work(&vsk->close_work, VSOCK_CLOSE_TIMEOUT);
	return false;
}

void virtio_transport_release(struct vsock_sock *vsk)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	struct virtio_vsock_pkt *pkt, *tmp;
	struct sock *sk = &vsk->sk;
	bool remove_sock = true;

	lock_sock_nested(sk, SINGLE_DEPTH_NESTING);
	if (sk->sk_type == SOCK_STREAM)
		remove_sock = virtio_transport_close(vsk);

	list_for_each_entry_safe(pkt, tmp, &vvs->rx_queue, list) {
		list_del(&pkt->list);
		virtio_transport_free_pkt(pkt);
	}
	release_sock(sk);

	if (remove_sock)
		vsock_remove_sock(vsk);
}
EXPORT_SYMBOL_GPL(virtio_transport_release);

static int
virtio_transport_recv_connecting(struct sock *sk,
				 struct virtio_vsock_pkt *pkt)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	int err;
	int skerr;

	switch (le16_to_cpu(pkt->hdr.op)) {
	case VIRTIO_VSOCK_OP_RESPONSE:
		sk->sk_state = TCP_ESTABLISHED;
		sk->sk_socket->state = SS_CONNECTED;
		vsock_insert_connected(vsk);
		sk->sk_state_change(sk);
		break;
	case VIRTIO_VSOCK_OP_INVALID:
		break;
	case VIRTIO_VSOCK_OP_RST:
		skerr = ECONNRESET;
		err = 0;
		goto destroy;
	default:
		skerr = EPROTO;
		err = -EINVAL;
		goto destroy;
	}
	return 0;

destroy:
	virtio_transport_reset(vsk, pkt);
	sk->sk_state = TCP_CLOSE;
	sk->sk_err = skerr;
	sk->sk_error_report(sk);
	return err;
}

static void
virtio_transport_recv_enqueue(struct vsock_sock *vsk,
			      struct virtio_vsock_pkt *pkt)
{
	struct virtio_vsock_sock *vvs = vsk->trans;
	bool can_enqueue, free_pkt = false;

	pkt->len = le32_to_cpu(pkt->hdr.len);
	pkt->off = 0;

	spin_lock_bh(&vvs->rx_lock);

	can_enqueue = virtio_transport_inc_rx_pkt(vvs, pkt);
	if (!can_enqueue) {
		free_pkt = true;
		goto out;
	}

	/* Try to copy small packets into the buffer of last packet queued,
	 * to avoid wasting memory queueing the entire buffer with a small
	 * payload.
	 */
	if (pkt->len <= GOOD_COPY_LEN && !list_empty(&vvs->rx_queue)) {
		struct virtio_vsock_pkt *last_pkt;

		last_pkt = list_last_entry(&vvs->rx_queue,
					   struct virtio_vsock_pkt, list);

		/* If there is space in the last packet queued, we copy the
		 * new packet in its buffer.
		 */
		if (pkt->len <= last_pkt->buf_len - last_pkt->len) {
			memcpy(last_pkt->buf + last_pkt->len, pkt->buf,
			       pkt->len);
			last_pkt->len += pkt->len;
			free_pkt = true;
			goto out;
		}
	}

	list_add_tail(&pkt->list, &vvs->rx_queue);

out:
	spin_unlock_bh(&vvs->rx_lock);
	if (free_pkt)
		virtio_transport_free_pkt(pkt);
}

static int
virtio_transport_recv_connected(struct sock *sk,
				struct virtio_vsock_pkt *pkt)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	int err = 0;

	switch (le16_to_cpu(pkt->hdr.op)) {
	case VIRTIO_VSOCK_OP_RW:
		virtio_transport_recv_enqueue(vsk, pkt);
		sk->sk_data_ready(sk);
		return err;
	case VIRTIO_VSOCK_OP_CREDIT_UPDATE:
		sk->sk_write_space(sk);
		break;
	case VIRTIO_VSOCK_OP_SHUTDOWN:
		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_RCV)
			vsk->peer_shutdown |= RCV_SHUTDOWN;
		if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND)
			vsk->peer_shutdown |= SEND_SHUTDOWN;
		if (vsk->peer_shutdown == SHUTDOWN_MASK &&
		    vsock_stream_has_data(vsk) <= 0) {
			sock_set_flag(sk, SOCK_DONE);
			sk->sk_state = TCP_CLOSING;
		}
		if (le32_to_cpu(pkt->hdr.flags))
			sk->sk_state_change(sk);
		break;
	case VIRTIO_VSOCK_OP_RST:
		virtio_transport_do_close(vsk, true);
		break;
	default:
		err = -EINVAL;
		break;
	}

	virtio_transport_free_pkt(pkt);
	return err;
}

static void
virtio_transport_recv_disconnecting(struct sock *sk,
				    struct virtio_vsock_pkt *pkt)
{
	struct vsock_sock *vsk = vsock_sk(sk);

	if (le16_to_cpu(pkt->hdr.op) == VIRTIO_VSOCK_OP_RST)
		virtio_transport_do_close(vsk, true);
}

static int
virtio_transport_send_response(struct vsock_sock *vsk,
			       struct virtio_vsock_pkt *pkt)
{
	struct virtio_vsock_pkt_info info = {
		.op = VIRTIO_VSOCK_OP_RESPONSE,
		.type = VIRTIO_VSOCK_TYPE_STREAM,
		.remote_cid = le64_to_cpu(pkt->hdr.src_cid),
		.remote_port = le32_to_cpu(pkt->hdr.src_port),
		.reply = true,
		.vsk = vsk,
	};

	return virtio_transport_send_pkt_info(vsk, &info);
}

/* Handle server socket */
static int
virtio_transport_recv_listen(struct sock *sk, struct virtio_vsock_pkt *pkt)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	struct vsock_sock *vchild;
	struct sock *child;

	if (le16_to_cpu(pkt->hdr.op) != VIRTIO_VSOCK_OP_REQUEST) {
		virtio_transport_reset(vsk, pkt);
		return -EINVAL;
	}

	if (sk_acceptq_is_full(sk)) {
		virtio_transport_reset(vsk, pkt);
		return -ENOMEM;
	}

	child = __vsock_create(sock_net(sk), NULL, sk, GFP_KERNEL,
			       sk->sk_type, 0);
	if (!child) {
		virtio_transport_reset(vsk, pkt);
		return -ENOMEM;
	}

	sk_acceptq_added(sk);

	lock_sock_nested(child, SINGLE_DEPTH_NESTING);

	child->sk_state = TCP_ESTABLISHED;

	vchild = vsock_sk(child);
	vsock_addr_init(&vchild->local_addr, le64_to_cpu(pkt->hdr.dst_cid),
			le32_to_cpu(pkt->hdr.dst_port));
	vsock_addr_init(&vchild->remote_addr, le64_to_cpu(pkt->hdr.src_cid),
			le32_to_cpu(pkt->hdr.src_port));

	vsock_insert_connected(vchild);
	vsock_enqueue_accept(sk, child);
	virtio_transport_send_response(vchild, pkt);

	release_sock(child);

	sk->sk_data_ready(sk);
	return 0;
}

static bool virtio_transport_space_update(struct sock *sk,
					  struct virtio_vsock_pkt *pkt)
{
	struct vsock_sock *vsk = vsock_sk(sk);
	struct virtio_vsock_sock *vvs = vsk->trans;
	bool space_available;

	/* buf_alloc and fwd_cnt is always included in the hdr */
	spin_lock_bh(&vvs->tx_lock);
	vvs->peer_buf_alloc = le32_to_cpu(pkt->hdr.buf_alloc);
	vvs->peer_fwd_cnt = le32_to_cpu(pkt->hdr.fwd_cnt);
	space_available = virtio_transport_has_space(vsk);
	spin_unlock_bh(&vvs->tx_lock);
	return space_available;
}

/* We are under the virtio-vsock's vsock->rx_lock or vhost-vsock's vq->mutex
 * lock.
 */
void virtio_transport_recv_pkt(struct virtio_vsock_pkt *pkt)
{
	struct sockaddr_vm src, dst;
	struct vsock_sock *vsk;
	struct sock *sk;
	bool space_available;

	vsock_addr_init(&src, le64_to_cpu(pkt->hdr.src_cid),
			le32_to_cpu(pkt->hdr.src_port));
	vsock_addr_init(&dst, le64_to_cpu(pkt->hdr.dst_cid),
			le32_to_cpu(pkt->hdr.dst_port));

	trace_virtio_transport_recv_pkt(src.svm_cid, src.svm_port,
					dst.svm_cid, dst.svm_port,
					le32_to_cpu(pkt->hdr.len),
					le16_to_cpu(pkt->hdr.type),
					le16_to_cpu(pkt->hdr.op),
					le32_to_cpu(pkt->hdr.flags),
					le32_to_cpu(pkt->hdr.buf_alloc),
					le32_to_cpu(pkt->hdr.fwd_cnt));

	if (le16_to_cpu(pkt->hdr.type) != VIRTIO_VSOCK_TYPE_STREAM) {
		(void)virtio_transport_reset_no_sock(pkt);
		goto free_pkt;
	}

	/* The socket must be in connected or bound table
	 * otherwise send reset back
	 */
	sk = vsock_find_connected_socket(&src, &dst);
	if (!sk) {
		sk = vsock_find_bound_socket(&dst);
		if (!sk) {
			(void)virtio_transport_reset_no_sock(pkt);
			goto free_pkt;
		}
	}

	vsk = vsock_sk(sk);

	space_available = virtio_transport_space_update(sk, pkt);

	lock_sock(sk);

	/* Update CID in case it has changed after a transport reset event */
	vsk->local_addr.svm_cid = dst.svm_cid;

	if (space_available)
		sk->sk_write_space(sk);

	switch (sk->sk_state) {
	case TCP_LISTEN:
		virtio_transport_recv_listen(sk, pkt);
		virtio_transport_free_pkt(pkt);
		break;
	case TCP_SYN_SENT:
		virtio_transport_recv_connecting(sk, pkt);
		virtio_transport_free_pkt(pkt);
		break;
	case TCP_ESTABLISHED:
		virtio_transport_recv_connected(sk, pkt);
		break;
	case TCP_CLOSING:
		virtio_transport_recv_disconnecting(sk, pkt);
		virtio_transport_free_pkt(pkt);
		break;
	default:
		virtio_transport_free_pkt(pkt);
		break;
	}
	release_sock(sk);

	/* Release refcnt obtained when we fetched this socket out of the
	 * bound or connected list.
	 */
	sock_put(sk);
	return;

free_pkt:
	virtio_transport_free_pkt(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_recv_pkt);

void virtio_transport_free_pkt(struct virtio_vsock_pkt *pkt)
{
	kfree(pkt->buf);
	kfree(pkt);
}
EXPORT_SYMBOL_GPL(virtio_transport_free_pkt);

MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("common code for virtio vsock");