summaryrefslogtreecommitdiffstats
path: root/drivers/net/tap.c
blob: 35b55a2fa1a1540d742bf8b18981a630fddf9bb2 (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
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
#include <linux/etherdevice.h>
#include <linux/if_tap.h>
#include <linux/if_vlan.h>
#include <linux/interrupt.h>
#include <linux/nsproxy.h>
#include <linux/compat.h>
#include <linux/if_tun.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/sched.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/wait.h>
#include <linux/cdev.h>
#include <linux/idr.h>
#include <linux/fs.h>
#include <linux/uio.h>

#include <net/net_namespace.h>
#include <net/rtnetlink.h>
#include <net/sock.h>
#include <linux/virtio_net.h>
#include <linux/skb_array.h>

#define TAP_IFFEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)

#define TAP_VNET_LE 0x80000000
#define TAP_VNET_BE 0x40000000

#ifdef CONFIG_TUN_VNET_CROSS_LE
static inline bool tap_legacy_is_little_endian(struct tap_queue *q)
{
	return q->flags & TAP_VNET_BE ? false :
		virtio_legacy_is_little_endian();
}

static long tap_get_vnet_be(struct tap_queue *q, int __user *sp)
{
	int s = !!(q->flags & TAP_VNET_BE);

	if (put_user(s, sp))
		return -EFAULT;

	return 0;
}

static long tap_set_vnet_be(struct tap_queue *q, int __user *sp)
{
	int s;

	if (get_user(s, sp))
		return -EFAULT;

	if (s)
		q->flags |= TAP_VNET_BE;
	else
		q->flags &= ~TAP_VNET_BE;

	return 0;
}
#else
static inline bool tap_legacy_is_little_endian(struct tap_queue *q)
{
	return virtio_legacy_is_little_endian();
}

static long tap_get_vnet_be(struct tap_queue *q, int __user *argp)
{
	return -EINVAL;
}

static long tap_set_vnet_be(struct tap_queue *q, int __user *argp)
{
	return -EINVAL;
}
#endif /* CONFIG_TUN_VNET_CROSS_LE */

static inline bool tap_is_little_endian(struct tap_queue *q)
{
	return q->flags & TAP_VNET_LE ||
		tap_legacy_is_little_endian(q);
}

static inline u16 tap16_to_cpu(struct tap_queue *q, __virtio16 val)
{
	return __virtio16_to_cpu(tap_is_little_endian(q), val);
}

static inline __virtio16 cpu_to_tap16(struct tap_queue *q, u16 val)
{
	return __cpu_to_virtio16(tap_is_little_endian(q), val);
}

static struct proto tap_proto = {
	.name = "tap",
	.owner = THIS_MODULE,
	.obj_size = sizeof(struct tap_queue),
};

#define TAP_NUM_DEVS (1U << MINORBITS)

static LIST_HEAD(major_list);

struct major_info {
	struct rcu_head rcu;
	dev_t major;
	struct idr minor_idr;
	struct mutex minor_lock;
	const char *device_name;
	struct list_head next;
};

#define GOODCOPY_LEN 128

static const struct proto_ops tap_socket_ops;

#define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
#define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG | NETIF_F_FRAGLIST)

static struct tap_dev *tap_dev_get_rcu(const struct net_device *dev)
{
	return rcu_dereference(dev->rx_handler_data);
}

/*
 * RCU usage:
 * The tap_queue and the macvlan_dev are loosely coupled, the
 * pointers from one to the other can only be read while rcu_read_lock
 * or rtnl is held.
 *
 * Both the file and the macvlan_dev hold a reference on the tap_queue
 * through sock_hold(&q->sk). When the macvlan_dev goes away first,
 * q->vlan becomes inaccessible. When the files gets closed,
 * tap_get_queue() fails.
 *
 * There may still be references to the struct sock inside of the
 * queue from outbound SKBs, but these never reference back to the
 * file or the dev. The data structure is freed through __sk_free
 * when both our references and any pending SKBs are gone.
 */

static int tap_enable_queue(struct tap_dev *tap, struct file *file,
			    struct tap_queue *q)
{
	int err = -EINVAL;

	ASSERT_RTNL();

	if (q->enabled)
		goto out;

	err = 0;
	rcu_assign_pointer(tap->taps[tap->numvtaps], q);
	q->queue_index = tap->numvtaps;
	q->enabled = true;

	tap->numvtaps++;
out:
	return err;
}

/* Requires RTNL */
static int tap_set_queue(struct tap_dev *tap, struct file *file,
			 struct tap_queue *q)
{
	if (tap->numqueues == MAX_TAP_QUEUES)
		return -EBUSY;

	rcu_assign_pointer(q->tap, tap);
	rcu_assign_pointer(tap->taps[tap->numvtaps], q);
	sock_hold(&q->sk);

	q->file = file;
	q->queue_index = tap->numvtaps;
	q->enabled = true;
	file->private_data = q;
	list_add_tail(&q->next, &tap->queue_list);

	tap->numvtaps++;
	tap->numqueues++;

	return 0;
}

static int tap_disable_queue(struct tap_queue *q)
{
	struct tap_dev *tap;
	struct tap_queue *nq;

	ASSERT_RTNL();
	if (!q->enabled)
		return -EINVAL;

	tap = rtnl_dereference(q->tap);

	if (tap) {
		int index = q->queue_index;
		BUG_ON(index >= tap->numvtaps);
		nq = rtnl_dereference(tap->taps[tap->numvtaps - 1]);
		nq->queue_index = index;

		rcu_assign_pointer(tap->taps[index], nq);
		RCU_INIT_POINTER(tap->taps[tap->numvtaps - 1], NULL);
		q->enabled = false;

		tap->numvtaps--;
	}

	return 0;
}

/*
 * The file owning the queue got closed, give up both
 * the reference that the files holds as well as the
 * one from the macvlan_dev if that still exists.
 *
 * Using the spinlock makes sure that we don't get
 * to the queue again after destroying it.
 */
static void tap_put_queue(struct tap_queue *q)
{
	struct tap_dev *tap;

	rtnl_lock();
	tap = rtnl_dereference(q->tap);

	if (tap) {
		if (q->enabled)
			BUG_ON(tap_disable_queue(q));

		tap->numqueues--;
		RCU_INIT_POINTER(q->tap, NULL);
		sock_put(&q->sk);
		list_del_init(&q->next);
	}

	rtnl_unlock();

	synchronize_rcu();
	sock_put(&q->sk);
}

/*
 * Select a queue based on the rxq of the device on which this packet
 * arrived. If the incoming device is not mq, calculate a flow hash
 * to select a queue. If all fails, find the first available queue.
 * Cache vlan->numvtaps since it can become zero during the execution
 * of this function.
 */
static struct tap_queue *tap_get_queue(struct tap_dev *tap,
				       struct sk_buff *skb)
{
	struct tap_queue *queue = NULL;
	/* Access to taps array is protected by rcu, but access to numvtaps
	 * isn't. Below we use it to lookup a queue, but treat it as a hint
	 * and validate that the result isn't NULL - in case we are
	 * racing against queue removal.
	 */
	int numvtaps = ACCESS_ONCE(tap->numvtaps);
	__u32 rxq;

	if (!numvtaps)
		goto out;

	if (numvtaps == 1)
		goto single;

	/* Check if we can use flow to select a queue */
	rxq = skb_get_hash(skb);
	if (rxq) {
		queue = rcu_dereference(tap->taps[rxq % numvtaps]);
		goto out;
	}

	if (likely(skb_rx_queue_recorded(skb))) {
		rxq = skb_get_rx_queue(skb);

		while (unlikely(rxq >= numvtaps))
			rxq -= numvtaps;

		queue = rcu_dereference(tap->taps[rxq]);
		goto out;
	}

single:
	queue = rcu_dereference(tap->taps[0]);
out:
	return queue;
}

/*
 * The net_device is going away, give up the reference
 * that it holds on all queues and safely set the pointer
 * from the queues to NULL.
 */
void tap_del_queues(struct tap_dev *tap)
{
	struct tap_queue *q, *tmp;

	ASSERT_RTNL();
	list_for_each_entry_safe(q, tmp, &tap->queue_list, next) {
		list_del_init(&q->next);
		RCU_INIT_POINTER(q->tap, NULL);
		if (q->enabled)
			tap->numvtaps--;
		tap->numqueues--;
		sock_put(&q->sk);
	}
	BUG_ON(tap->numvtaps);
	BUG_ON(tap->numqueues);
	/* guarantee that any future tap_set_queue will fail */
	tap->numvtaps = MAX_TAP_QUEUES;
}
EXPORT_SYMBOL_GPL(tap_del_queues);

rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
{
	struct sk_buff *skb = *pskb;
	struct net_device *dev = skb->dev;
	struct tap_dev *tap;
	struct tap_queue *q;
	netdev_features_t features = TAP_FEATURES;

	tap = tap_dev_get_rcu(dev);
	if (!tap)
		return RX_HANDLER_PASS;

	q = tap_get_queue(tap, skb);
	if (!q)
		return RX_HANDLER_PASS;

	if (__skb_array_full(&q->skb_array))
		goto drop;

	skb_push(skb, ETH_HLEN);

	/* Apply the forward feature mask so that we perform segmentation
	 * according to users wishes.  This only works if VNET_HDR is
	 * enabled.
	 */
	if (q->flags & IFF_VNET_HDR)
		features |= tap->tap_features;
	if (netif_needs_gso(skb, features)) {
		struct sk_buff *segs = __skb_gso_segment(skb, features, false);

		if (IS_ERR(segs))
			goto drop;

		if (!segs) {
			if (skb_array_produce(&q->skb_array, skb))
				goto drop;
			goto wake_up;
		}

		consume_skb(skb);
		while (segs) {
			struct sk_buff *nskb = segs->next;

			segs->next = NULL;
			if (skb_array_produce(&q->skb_array, segs)) {
				kfree_skb(segs);
				kfree_skb_list(nskb);
				break;
			}
			segs = nskb;
		}
	} else {
		/* If we receive a partial checksum and the tap side
		 * doesn't support checksum offload, compute the checksum.
		 * Note: it doesn't matter which checksum feature to
		 *	  check, we either support them all or none.
		 */
		if (skb->ip_summed == CHECKSUM_PARTIAL &&
		    !(features & NETIF_F_CSUM_MASK) &&
		    skb_checksum_help(skb))
			goto drop;
		if (skb_array_produce(&q->skb_array, skb))
			goto drop;
	}

wake_up:
	wake_up_interruptible_poll(sk_sleep(&q->sk), POLLIN | POLLRDNORM | POLLRDBAND);
	return RX_HANDLER_CONSUMED;

drop:
	/* Count errors/drops only here, thus don't care about args. */
	if (tap->count_rx_dropped)
		tap->count_rx_dropped(tap);
	kfree_skb(skb);
	return RX_HANDLER_CONSUMED;
}
EXPORT_SYMBOL_GPL(tap_handle_frame);

static struct major_info *tap_get_major(int major)
{
	struct major_info *tap_major;

	list_for_each_entry_rcu(tap_major, &major_list, next) {
		if (tap_major->major == major)
			return tap_major;
	}

	return NULL;
}

int tap_get_minor(dev_t major, struct tap_dev *tap)
{
	int retval = -ENOMEM;
	struct major_info *tap_major;

	rcu_read_lock();
	tap_major = tap_get_major(MAJOR(major));
	if (!tap_major) {
		retval = -EINVAL;
		goto unlock;
	}

	mutex_lock(&tap_major->minor_lock);
	retval = idr_alloc(&tap_major->minor_idr, tap, 1, TAP_NUM_DEVS, GFP_KERNEL);
	if (retval >= 0) {
		tap->minor = retval;
	} else if (retval == -ENOSPC) {
		netdev_err(tap->dev, "Too many tap devices\n");
		retval = -EINVAL;
	}
	mutex_unlock(&tap_major->minor_lock);

unlock:
	rcu_read_unlock();
	return retval < 0 ? retval : 0;
}
EXPORT_SYMBOL_GPL(tap_get_minor);

void tap_free_minor(dev_t major, struct tap_dev *tap)
{
	struct major_info *tap_major;

	rcu_read_lock();
	tap_major = tap_get_major(MAJOR(major));
	if (!tap_major) {
		goto unlock;
	}

	mutex_lock(&tap_major->minor_lock);
	if (tap->minor) {
		idr_remove(&tap_major->minor_idr, tap->minor);
		tap->minor = 0;
	}
	mutex_unlock(&tap_major->minor_lock);

unlock:
	rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(tap_free_minor);

static struct tap_dev *dev_get_by_tap_file(int major, int minor)
{
	struct net_device *dev = NULL;
	struct tap_dev *tap;
	struct major_info *tap_major;

	rcu_read_lock();
	tap_major = tap_get_major(major);
	if (!tap_major) {
		tap = NULL;
		goto unlock;
	}

	mutex_lock(&tap_major->minor_lock);
	tap = idr_find(&tap_major->minor_idr, minor);
	if (tap) {
		dev = tap->dev;
		dev_hold(dev);
	}
	mutex_unlock(&tap_major->minor_lock);

unlock:
	rcu_read_unlock();
	return tap;
}

static void tap_sock_write_space(struct sock *sk)
{
	wait_queue_head_t *wqueue;

	if (!sock_writeable(sk) ||
	    !test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &sk->sk_socket->flags))
		return;

	wqueue = sk_sleep(sk);
	if (wqueue && waitqueue_active(wqueue))
		wake_up_interruptible_poll(wqueue, POLLOUT | POLLWRNORM | POLLWRBAND);
}

static void tap_sock_destruct(struct sock *sk)
{
	struct tap_queue *q = container_of(sk, struct tap_queue, sk);

	skb_array_cleanup(&q->skb_array);
}

static int tap_open(struct inode *inode, struct file *file)
{
	struct net *net = current->nsproxy->net_ns;
	struct tap_dev *tap;
	struct tap_queue *q;
	int err = -ENODEV;

	rtnl_lock();
	tap = dev_get_by_tap_file(imajor(inode), iminor(inode));
	if (!tap)
		goto err;

	err = -ENOMEM;
	q = (struct tap_queue *)sk_alloc(net, AF_UNSPEC, GFP_KERNEL,
					     &tap_proto, 0);
	if (!q)
		goto err;

	RCU_INIT_POINTER(q->sock.wq, &q->wq);
	init_waitqueue_head(&q->wq.wait);
	q->sock.type = SOCK_RAW;
	q->sock.state = SS_CONNECTED;
	q->sock.file = file;
	q->sock.ops = &tap_socket_ops;
	sock_init_data(&q->sock, &q->sk);
	q->sk.sk_write_space = tap_sock_write_space;
	q->sk.sk_destruct = tap_sock_destruct;
	q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP;
	q->vnet_hdr_sz = sizeof(struct virtio_net_hdr);

	/*
	 * so far only KVM virtio_net uses tap, enable zero copy between
	 * guest kernel and host kernel when lower device supports zerocopy
	 *
	 * The macvlan supports zerocopy iff the lower device supports zero
	 * copy so we don't have to look at the lower device directly.
	 */
	if ((tap->dev->features & NETIF_F_HIGHDMA) && (tap->dev->features & NETIF_F_SG))
		sock_set_flag(&q->sk, SOCK_ZEROCOPY);

	err = -ENOMEM;
	if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL))
		goto err_array;

	err = tap_set_queue(tap, file, q);
	if (err)
		goto err_queue;

	dev_put(tap->dev);

	rtnl_unlock();
	return err;

err_queue:
	skb_array_cleanup(&q->skb_array);
err_array:
	sock_put(&q->sk);
err:
	if (tap)
		dev_put(tap->dev);

	rtnl_unlock();
	return err;
}

static int tap_release(struct inode *inode, struct file *file)
{
	struct tap_queue *q = file->private_data;
	tap_put_queue(q);
	return 0;
}

static unsigned int tap_poll(struct file *file, poll_table *wait)
{
	struct tap_queue *q = file->private_data;
	unsigned int mask = POLLERR;

	if (!q)
		goto out;

	mask = 0;
	poll_wait(file, &q->wq.wait, wait);

	if (!skb_array_empty(&q->skb_array))
		mask |= POLLIN | POLLRDNORM;

	if (sock_writeable(&q->sk) ||
	    (!test_and_set_bit(SOCKWQ_ASYNC_NOSPACE, &q->sock.flags) &&
	     sock_writeable(&q->sk)))
		mask |= POLLOUT | POLLWRNORM;

out:
	return mask;
}

static inline struct sk_buff *tap_alloc_skb(struct sock *sk, size_t prepad,
					    size_t len, size_t linear,
						int noblock, int *err)
{
	struct sk_buff *skb;

	/* Under a page?  Don't bother with paged skb. */
	if (prepad + len < PAGE_SIZE || !linear)
		linear = len;

	skb = sock_alloc_send_pskb(sk, prepad + linear, len - linear, noblock,
				   err, 0);
	if (!skb)
		return NULL;

	skb_reserve(skb, prepad);
	skb_put(skb, linear);
	skb->data_len = len - linear;
	skb->len += len - linear;

	return skb;
}

/* Neighbour code has some assumptions on HH_DATA_MOD alignment */
#define TAP_RESERVE HH_DATA_OFF(ETH_HLEN)

/* Get packet from user space buffer */
static ssize_t tap_get_user(struct tap_queue *q, struct msghdr *m,
			    struct iov_iter *from, int noblock)
{
	int good_linear = SKB_MAX_HEAD(TAP_RESERVE);
	struct sk_buff *skb;
	struct tap_dev *tap;
	unsigned long total_len = iov_iter_count(from);
	unsigned long len = total_len;
	int err;
	struct virtio_net_hdr vnet_hdr = { 0 };
	int vnet_hdr_len = 0;
	int copylen = 0;
	int depth;
	bool zerocopy = false;
	size_t linear;

	if (q->flags & IFF_VNET_HDR) {
		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);

		err = -EINVAL;
		if (len < vnet_hdr_len)
			goto err;
		len -= vnet_hdr_len;

		err = -EFAULT;
		if (!copy_from_iter_full(&vnet_hdr, sizeof(vnet_hdr), from))
			goto err;
		iov_iter_advance(from, vnet_hdr_len - sizeof(vnet_hdr));
		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
		     tap16_to_cpu(q, vnet_hdr.csum_start) +
		     tap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
			     tap16_to_cpu(q, vnet_hdr.hdr_len))
			vnet_hdr.hdr_len = cpu_to_tap16(q,
				 tap16_to_cpu(q, vnet_hdr.csum_start) +
				 tap16_to_cpu(q, vnet_hdr.csum_offset) + 2);
		err = -EINVAL;
		if (tap16_to_cpu(q, vnet_hdr.hdr_len) > len)
			goto err;
	}

	err = -EINVAL;
	if (unlikely(len < ETH_HLEN))
		goto err;

	if (m && m->msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
		struct iov_iter i;

		copylen = vnet_hdr.hdr_len ?
			tap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
		if (copylen > good_linear)
			copylen = good_linear;
		else if (copylen < ETH_HLEN)
			copylen = ETH_HLEN;
		linear = copylen;
		i = *from;
		iov_iter_advance(&i, copylen);
		if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
			zerocopy = true;
	}

	if (!zerocopy) {
		copylen = len;
		linear = tap16_to_cpu(q, vnet_hdr.hdr_len);
		if (linear > good_linear)
			linear = good_linear;
		else if (linear < ETH_HLEN)
			linear = ETH_HLEN;
	}

	skb = tap_alloc_skb(&q->sk, TAP_RESERVE, copylen,
			    linear, noblock, &err);
	if (!skb)
		goto err;

	if (zerocopy)
		err = zerocopy_sg_from_iter(skb, from);
	else
		err = skb_copy_datagram_from_iter(skb, 0, from, len);

	if (err)
		goto err_kfree;

	skb_set_network_header(skb, ETH_HLEN);
	skb_reset_mac_header(skb);
	skb->protocol = eth_hdr(skb)->h_proto;

	if (vnet_hdr_len) {
		err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
					    tap_is_little_endian(q));
		if (err)
			goto err_kfree;
	}

	skb_probe_transport_header(skb, ETH_HLEN);

	/* Move network header to the right position for VLAN tagged packets */
	if ((skb->protocol == htons(ETH_P_8021Q) ||
	     skb->protocol == htons(ETH_P_8021AD)) &&
	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
		skb_set_network_header(skb, depth);

	rcu_read_lock();
	tap = rcu_dereference(q->tap);
	/* copy skb_ubuf_info for callback when skb has no error */
	if (zerocopy) {
		skb_shinfo(skb)->destructor_arg = m->msg_control;
		skb_shinfo(skb)->tx_flags |= SKBTX_DEV_ZEROCOPY;
		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
	} else if (m && m->msg_control) {
		struct ubuf_info *uarg = m->msg_control;
		uarg->callback(uarg, false);
	}

	if (tap) {
		skb->dev = tap->dev;
		dev_queue_xmit(skb);
	} else {
		kfree_skb(skb);
	}
	rcu_read_unlock();

	return total_len;

err_kfree:
	kfree_skb(skb);

err:
	rcu_read_lock();
	tap = rcu_dereference(q->tap);
	if (tap && tap->count_tx_dropped)
		tap->count_tx_dropped(tap);
	rcu_read_unlock();

	return err;
}

static ssize_t tap_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct tap_queue *q = file->private_data;

	return tap_get_user(q, NULL, from, file->f_flags & O_NONBLOCK);
}

/* Put packet to the user space buffer */
static ssize_t tap_put_user(struct tap_queue *q,
			    const struct sk_buff *skb,
			    struct iov_iter *iter)
{
	int ret;
	int vnet_hdr_len = 0;
	int vlan_offset = 0;
	int total;

	if (q->flags & IFF_VNET_HDR) {
		struct virtio_net_hdr vnet_hdr;
		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
		if (iov_iter_count(iter) < vnet_hdr_len)
			return -EINVAL;

		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
					    tap_is_little_endian(q), true))
			BUG();

		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
		    sizeof(vnet_hdr))
			return -EFAULT;

		iov_iter_advance(iter, vnet_hdr_len - sizeof(vnet_hdr));
	}
	total = vnet_hdr_len;
	total += skb->len;

	if (skb_vlan_tag_present(skb)) {
		struct {
			__be16 h_vlan_proto;
			__be16 h_vlan_TCI;
		} veth;
		veth.h_vlan_proto = skb->vlan_proto;
		veth.h_vlan_TCI = htons(skb_vlan_tag_get(skb));

		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
		total += VLAN_HLEN;

		ret = skb_copy_datagram_iter(skb, 0, iter, vlan_offset);
		if (ret || !iov_iter_count(iter))
			goto done;

		ret = copy_to_iter(&veth, sizeof(veth), iter);
		if (ret != sizeof(veth) || !iov_iter_count(iter))
			goto done;
	}

	ret = skb_copy_datagram_iter(skb, vlan_offset, iter,
				     skb->len - vlan_offset);

done:
	return ret ? ret : total;
}

static ssize_t tap_do_read(struct tap_queue *q,
			   struct iov_iter *to,
			   int noblock)
{
	DEFINE_WAIT(wait);
	struct sk_buff *skb;
	ssize_t ret = 0;

	if (!iov_iter_count(to))
		return 0;

	while (1) {
		if (!noblock)
			prepare_to_wait(sk_sleep(&q->sk), &wait,
					TASK_INTERRUPTIBLE);

		/* Read frames from the queue */
		skb = skb_array_consume(&q->skb_array);
		if (skb)
			break;
		if (noblock) {
			ret = -EAGAIN;
			break;
		}
		if (signal_pending(current)) {
			ret = -ERESTARTSYS;
			break;
		}
		/* Nothing to read, let's sleep */
		schedule();
	}
	if (!noblock)
		finish_wait(sk_sleep(&q->sk), &wait);

	if (skb) {
		ret = tap_put_user(q, skb, to);
		if (unlikely(ret < 0))
			kfree_skb(skb);
		else
			consume_skb(skb);
	}
	return ret;
}

static ssize_t tap_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *file = iocb->ki_filp;
	struct tap_queue *q = file->private_data;
	ssize_t len = iov_iter_count(to), ret;

	ret = tap_do_read(q, to, file->f_flags & O_NONBLOCK);
	ret = min_t(ssize_t, ret, len);
	if (ret > 0)
		iocb->ki_pos = ret;
	return ret;
}

static struct tap_dev *tap_get_tap_dev(struct tap_queue *q)
{
	struct tap_dev *tap;

	ASSERT_RTNL();
	tap = rtnl_dereference(q->tap);
	if (tap)
		dev_hold(tap->dev);

	return tap;
}

static void tap_put_tap_dev(struct tap_dev *tap)
{
	dev_put(tap->dev);
}

static int tap_ioctl_set_queue(struct file *file, unsigned int flags)
{
	struct tap_queue *q = file->private_data;
	struct tap_dev *tap;
	int ret;

	tap = tap_get_tap_dev(q);
	if (!tap)
		return -EINVAL;

	if (flags & IFF_ATTACH_QUEUE)
		ret = tap_enable_queue(tap, file, q);
	else if (flags & IFF_DETACH_QUEUE)
		ret = tap_disable_queue(q);
	else
		ret = -EINVAL;

	tap_put_tap_dev(tap);
	return ret;
}

static int set_offload(struct tap_queue *q, unsigned long arg)
{
	struct tap_dev *tap;
	netdev_features_t features;
	netdev_features_t feature_mask = 0;

	tap = rtnl_dereference(q->tap);
	if (!tap)
		return -ENOLINK;

	features = tap->dev->features;

	if (arg & TUN_F_CSUM) {
		feature_mask = NETIF_F_HW_CSUM;

		if (arg & (TUN_F_TSO4 | TUN_F_TSO6)) {
			if (arg & TUN_F_TSO_ECN)
				feature_mask |= NETIF_F_TSO_ECN;
			if (arg & TUN_F_TSO4)
				feature_mask |= NETIF_F_TSO;
			if (arg & TUN_F_TSO6)
				feature_mask |= NETIF_F_TSO6;
		}

		if (arg & TUN_F_UFO)
			feature_mask |= NETIF_F_UFO;
	}

	/* tun/tap driver inverts the usage for TSO offloads, where
	 * setting the TSO bit means that the userspace wants to
	 * accept TSO frames and turning it off means that user space
	 * does not support TSO.
	 * For tap, we have to invert it to mean the same thing.
	 * When user space turns off TSO, we turn off GSO/LRO so that
	 * user-space will not receive TSO frames.
	 */
	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO))
		features |= RX_OFFLOADS;
	else
		features &= ~RX_OFFLOADS;

	/* tap_features are the same as features on tun/tap and
	 * reflect user expectations.
	 */
	tap->tap_features = feature_mask;
	if (tap->update_features)
		tap->update_features(tap, features);

	return 0;
}

/*
 * provide compatibility with generic tun/tap interface
 */
static long tap_ioctl(struct file *file, unsigned int cmd,
		      unsigned long arg)
{
	struct tap_queue *q = file->private_data;
	struct tap_dev *tap;
	void __user *argp = (void __user *)arg;
	struct ifreq __user *ifr = argp;
	unsigned int __user *up = argp;
	unsigned short u;
	int __user *sp = argp;
	struct sockaddr sa;
	int s;
	int ret;

	switch (cmd) {
	case TUNSETIFF:
		/* ignore the name, just look at flags */
		if (get_user(u, &ifr->ifr_flags))
			return -EFAULT;

		ret = 0;
		if ((u & ~TAP_IFFEATURES) != (IFF_NO_PI | IFF_TAP))
			ret = -EINVAL;
		else
			q->flags = (q->flags & ~TAP_IFFEATURES) | u;

		return ret;

	case TUNGETIFF:
		rtnl_lock();
		tap = tap_get_tap_dev(q);
		if (!tap) {
			rtnl_unlock();
			return -ENOLINK;
		}

		ret = 0;
		u = q->flags;
		if (copy_to_user(&ifr->ifr_name, tap->dev->name, IFNAMSIZ) ||
		    put_user(u, &ifr->ifr_flags))
			ret = -EFAULT;
		tap_put_tap_dev(tap);
		rtnl_unlock();
		return ret;

	case TUNSETQUEUE:
		if (get_user(u, &ifr->ifr_flags))
			return -EFAULT;
		rtnl_lock();
		ret = tap_ioctl_set_queue(file, u);
		rtnl_unlock();
		return ret;

	case TUNGETFEATURES:
		if (put_user(IFF_TAP | IFF_NO_PI | TAP_IFFEATURES, up))
			return -EFAULT;
		return 0;

	case TUNSETSNDBUF:
		if (get_user(s, sp))
			return -EFAULT;

		q->sk.sk_sndbuf = s;
		return 0;

	case TUNGETVNETHDRSZ:
		s = q->vnet_hdr_sz;
		if (put_user(s, sp))
			return -EFAULT;
		return 0;

	case TUNSETVNETHDRSZ:
		if (get_user(s, sp))
			return -EFAULT;
		if (s < (int)sizeof(struct virtio_net_hdr))
			return -EINVAL;

		q->vnet_hdr_sz = s;
		return 0;

	case TUNGETVNETLE:
		s = !!(q->flags & TAP_VNET_LE);
		if (put_user(s, sp))
			return -EFAULT;
		return 0;

	case TUNSETVNETLE:
		if (get_user(s, sp))
			return -EFAULT;
		if (s)
			q->flags |= TAP_VNET_LE;
		else
			q->flags &= ~TAP_VNET_LE;
		return 0;

	case TUNGETVNETBE:
		return tap_get_vnet_be(q, sp);

	case TUNSETVNETBE:
		return tap_set_vnet_be(q, sp);

	case TUNSETOFFLOAD:
		/* let the user check for future flags */
		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
			    TUN_F_TSO_ECN | TUN_F_UFO))
			return -EINVAL;

		rtnl_lock();
		ret = set_offload(q, arg);
		rtnl_unlock();
		return ret;

	case SIOCGIFHWADDR:
		rtnl_lock();
		tap = tap_get_tap_dev(q);
		if (!tap) {
			rtnl_unlock();
			return -ENOLINK;
		}
		ret = 0;
		u = tap->dev->type;
		if (copy_to_user(&ifr->ifr_name, tap->dev->name, IFNAMSIZ) ||
		    copy_to_user(&ifr->ifr_hwaddr.sa_data, tap->dev->dev_addr, ETH_ALEN) ||
		    put_user(u, &ifr->ifr_hwaddr.sa_family))
			ret = -EFAULT;
		tap_put_tap_dev(tap);
		rtnl_unlock();
		return ret;

	case SIOCSIFHWADDR:
		if (copy_from_user(&sa, &ifr->ifr_hwaddr, sizeof(sa)))
			return -EFAULT;
		rtnl_lock();
		tap = tap_get_tap_dev(q);
		if (!tap) {
			rtnl_unlock();
			return -ENOLINK;
		}
		ret = dev_set_mac_address(tap->dev, &sa);
		tap_put_tap_dev(tap);
		rtnl_unlock();
		return ret;

	default:
		return -EINVAL;
	}
}

#ifdef CONFIG_COMPAT
static long tap_compat_ioctl(struct file *file, unsigned int cmd,
			     unsigned long arg)
{
	return tap_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
}
#endif

const struct file_operations tap_fops = {
	.owner		= THIS_MODULE,
	.open		= tap_open,
	.release	= tap_release,
	.read_iter	= tap_read_iter,
	.write_iter	= tap_write_iter,
	.poll		= tap_poll,
	.llseek		= no_llseek,
	.unlocked_ioctl	= tap_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= tap_compat_ioctl,
#endif
};

static int tap_sendmsg(struct socket *sock, struct msghdr *m,
		       size_t total_len)
{
	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
	return tap_get_user(q, m, &m->msg_iter, m->msg_flags & MSG_DONTWAIT);
}

static int tap_recvmsg(struct socket *sock, struct msghdr *m,
		       size_t total_len, int flags)
{
	struct tap_queue *q = container_of(sock, struct tap_queue, sock);
	int ret;
	if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
		return -EINVAL;
	ret = tap_do_read(q, &m->msg_iter, flags & MSG_DONTWAIT);
	if (ret > total_len) {
		m->msg_flags |= MSG_TRUNC;
		ret = flags & MSG_TRUNC ? ret : total_len;
	}
	return ret;
}

static int tap_peek_len(struct socket *sock)
{
	struct tap_queue *q = container_of(sock, struct tap_queue,
					       sock);
	return skb_array_peek_len(&q->skb_array);
}

/* Ops structure to mimic raw sockets with tun */
static const struct proto_ops tap_socket_ops = {
	.sendmsg = tap_sendmsg,
	.recvmsg = tap_recvmsg,
	.peek_len = tap_peek_len,
};

/* Get an underlying socket object from tun file.  Returns error unless file is
 * attached to a device.  The returned object works like a packet socket, it
 * can be used for sock_sendmsg/sock_recvmsg.  The caller is responsible for
 * holding a reference to the file for as long as the socket is in use. */
struct socket *tap_get_socket(struct file *file)
{
	struct tap_queue *q;
	if (file->f_op != &tap_fops)
		return ERR_PTR(-EINVAL);
	q = file->private_data;
	if (!q)
		return ERR_PTR(-EBADFD);
	return &q->sock;
}
EXPORT_SYMBOL_GPL(tap_get_socket);

int tap_queue_resize(struct tap_dev *tap)
{
	struct net_device *dev = tap->dev;
	struct tap_queue *q;
	struct skb_array **arrays;
	int n = tap->numqueues;
	int ret, i = 0;

	arrays = kmalloc(sizeof *arrays * n, GFP_KERNEL);
	if (!arrays)
		return -ENOMEM;

	list_for_each_entry(q, &tap->queue_list, next)
		arrays[i++] = &q->skb_array;

	ret = skb_array_resize_multiple(arrays, n,
					dev->tx_queue_len, GFP_KERNEL);

	kfree(arrays);
	return ret;
}
EXPORT_SYMBOL_GPL(tap_queue_resize);

static int tap_list_add(dev_t major, const char *device_name)
{
	struct major_info *tap_major;

	tap_major = kzalloc(sizeof(*tap_major), GFP_ATOMIC);
	if (!tap_major)
		return -ENOMEM;

	tap_major->major = MAJOR(major);

	idr_init(&tap_major->minor_idr);
	mutex_init(&tap_major->minor_lock);

	tap_major->device_name = device_name;

	list_add_tail_rcu(&tap_major->next, &major_list);
	return 0;
}

int tap_create_cdev(struct cdev *tap_cdev,
		    dev_t *tap_major, const char *device_name)
{
	int err;

	err = alloc_chrdev_region(tap_major, 0, TAP_NUM_DEVS, device_name);
	if (err)
		goto out1;

	cdev_init(tap_cdev, &tap_fops);
	err = cdev_add(tap_cdev, *tap_major, TAP_NUM_DEVS);
	if (err)
		goto out2;

	err =  tap_list_add(*tap_major, device_name);
	if (err)
		goto out3;

	return 0;

out3:
	cdev_del(tap_cdev);
out2:
	unregister_chrdev_region(*tap_major, TAP_NUM_DEVS);
out1:
	return err;
}
EXPORT_SYMBOL_GPL(tap_create_cdev);

void tap_destroy_cdev(dev_t major, struct cdev *tap_cdev)
{
	struct major_info *tap_major, *tmp;

	cdev_del(tap_cdev);
	unregister_chrdev_region(major, TAP_NUM_DEVS);
	list_for_each_entry_safe(tap_major, tmp, &major_list, next) {
		if (tap_major->major == MAJOR(major)) {
			idr_destroy(&tap_major->minor_idr);
			list_del_rcu(&tap_major->next);
			kfree_rcu(tap_major, rcu);
		}
	}
}
EXPORT_SYMBOL_GPL(tap_destroy_cdev);

MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>");
MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
MODULE_LICENSE("GPL");