summaryrefslogtreecommitdiffstats
path: root/net/tls/tls_device.c
blob: 0683788bbef07adec1e60b0e5545e904edfa9dcf (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
/* Copyright (c) 2018, Mellanox Technologies All rights reserved.
 *
 * This software is available to you under a choice of one of two
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#include <crypto/aead.h>
#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/netdevice.h>
#include <net/dst.h>
#include <net/inet_connection_sock.h>
#include <net/tcp.h>
#include <net/tls.h>

#include "trace.h"

/* device_offload_lock is used to synchronize tls_dev_add
 * against NETDEV_DOWN notifications.
 */
static DECLARE_RWSEM(device_offload_lock);

static void tls_device_gc_task(struct work_struct *work);

static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task);
static LIST_HEAD(tls_device_gc_list);
static LIST_HEAD(tls_device_list);
static DEFINE_SPINLOCK(tls_device_lock);

static void tls_device_free_ctx(struct tls_context *ctx)
{
	if (ctx->tx_conf == TLS_HW) {
		kfree(tls_offload_ctx_tx(ctx));
		kfree(ctx->tx.rec_seq);
		kfree(ctx->tx.iv);
	}

	if (ctx->rx_conf == TLS_HW)
		kfree(tls_offload_ctx_rx(ctx));

	tls_ctx_free(NULL, ctx);
}

static void tls_device_gc_task(struct work_struct *work)
{
	struct tls_context *ctx, *tmp;
	unsigned long flags;
	LIST_HEAD(gc_list);

	spin_lock_irqsave(&tls_device_lock, flags);
	list_splice_init(&tls_device_gc_list, &gc_list);
	spin_unlock_irqrestore(&tls_device_lock, flags);

	list_for_each_entry_safe(ctx, tmp, &gc_list, list) {
		struct net_device *netdev = ctx->netdev;

		if (netdev && ctx->tx_conf == TLS_HW) {
			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
							TLS_OFFLOAD_CTX_DIR_TX);
			dev_put(netdev);
			ctx->netdev = NULL;
		}

		list_del(&ctx->list);
		tls_device_free_ctx(ctx);
	}
}

static void tls_device_queue_ctx_destruction(struct tls_context *ctx)
{
	unsigned long flags;

	spin_lock_irqsave(&tls_device_lock, flags);
	list_move_tail(&ctx->list, &tls_device_gc_list);

	/* schedule_work inside the spinlock
	 * to make sure tls_device_down waits for that work.
	 */
	schedule_work(&tls_device_gc_work);

	spin_unlock_irqrestore(&tls_device_lock, flags);
}

/* We assume that the socket is already connected */
static struct net_device *get_netdev_for_sock(struct sock *sk)
{
	struct dst_entry *dst = sk_dst_get(sk);
	struct net_device *netdev = NULL;

	if (likely(dst)) {
		netdev = dst->dev;
		dev_hold(netdev);
	}

	dst_release(dst);

	return netdev;
}

static void destroy_record(struct tls_record_info *record)
{
	int i;

	for (i = 0; i < record->num_frags; i++)
		__skb_frag_unref(&record->frags[i]);
	kfree(record);
}

static void delete_all_records(struct tls_offload_context_tx *offload_ctx)
{
	struct tls_record_info *info, *temp;

	list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) {
		list_del(&info->list);
		destroy_record(info);
	}

	offload_ctx->retransmit_hint = NULL;
}

static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct tls_record_info *info, *temp;
	struct tls_offload_context_tx *ctx;
	u64 deleted_records = 0;
	unsigned long flags;

	if (!tls_ctx)
		return;

	ctx = tls_offload_ctx_tx(tls_ctx);

	spin_lock_irqsave(&ctx->lock, flags);
	info = ctx->retransmit_hint;
	if (info && !before(acked_seq, info->end_seq))
		ctx->retransmit_hint = NULL;

	list_for_each_entry_safe(info, temp, &ctx->records_list, list) {
		if (before(acked_seq, info->end_seq))
			break;
		list_del(&info->list);

		destroy_record(info);
		deleted_records++;
	}

	ctx->unacked_record_sn += deleted_records;
	spin_unlock_irqrestore(&ctx->lock, flags);
}

/* At this point, there should be no references on this
 * socket and no in-flight SKBs associated with this
 * socket, so it is safe to free all the resources.
 */
static void tls_device_sk_destruct(struct sock *sk)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);

	tls_ctx->sk_destruct(sk);

	if (tls_ctx->tx_conf == TLS_HW) {
		if (ctx->open_record)
			destroy_record(ctx->open_record);
		delete_all_records(ctx);
		crypto_free_aead(ctx->aead_send);
		clean_acked_data_disable(inet_csk(sk));
	}

	if (refcount_dec_and_test(&tls_ctx->refcount))
		tls_device_queue_ctx_destruction(tls_ctx);
}

void tls_device_free_resources_tx(struct sock *sk)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);

	tls_free_partial_record(sk, tls_ctx);
}

void tls_offload_tx_resync_request(struct sock *sk, u32 got_seq, u32 exp_seq)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);

	trace_tls_device_tx_resync_req(sk, got_seq, exp_seq);
	WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags));
}
EXPORT_SYMBOL_GPL(tls_offload_tx_resync_request);

static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx,
				 u32 seq)
{
	struct net_device *netdev;
	struct sk_buff *skb;
	int err = 0;
	u8 *rcd_sn;

	skb = tcp_write_queue_tail(sk);
	if (skb)
		TCP_SKB_CB(skb)->eor = 1;

	rcd_sn = tls_ctx->tx.rec_seq;

	trace_tls_device_tx_resync_send(sk, seq, rcd_sn);
	down_read(&device_offload_lock);
	netdev = tls_ctx->netdev;
	if (netdev)
		err = netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq,
							 rcd_sn,
							 TLS_OFFLOAD_CTX_DIR_TX);
	up_read(&device_offload_lock);
	if (err)
		return;

	clear_bit_unlock(TLS_TX_SYNC_SCHED, &tls_ctx->flags);
}

static void tls_append_frag(struct tls_record_info *record,
			    struct page_frag *pfrag,
			    int size)
{
	skb_frag_t *frag;

	frag = &record->frags[record->num_frags - 1];
	if (skb_frag_page(frag) == pfrag->page &&
	    skb_frag_off(frag) + skb_frag_size(frag) == pfrag->offset) {
		skb_frag_size_add(frag, size);
	} else {
		++frag;
		__skb_frag_set_page(frag, pfrag->page);
		skb_frag_off_set(frag, pfrag->offset);
		skb_frag_size_set(frag, size);
		++record->num_frags;
		get_page(pfrag->page);
	}

	pfrag->offset += size;
	record->len += size;
}

static int tls_push_record(struct sock *sk,
			   struct tls_context *ctx,
			   struct tls_offload_context_tx *offload_ctx,
			   struct tls_record_info *record,
			   int flags)
{
	struct tls_prot_info *prot = &ctx->prot_info;
	struct tcp_sock *tp = tcp_sk(sk);
	skb_frag_t *frag;
	int i;

	record->end_seq = tp->write_seq + record->len;
	list_add_tail_rcu(&record->list, &offload_ctx->records_list);
	offload_ctx->open_record = NULL;

	if (test_bit(TLS_TX_SYNC_SCHED, &ctx->flags))
		tls_device_resync_tx(sk, ctx, tp->write_seq);

	tls_advance_record_sn(sk, prot, &ctx->tx);

	for (i = 0; i < record->num_frags; i++) {
		frag = &record->frags[i];
		sg_unmark_end(&offload_ctx->sg_tx_data[i]);
		sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag),
			    skb_frag_size(frag), skb_frag_off(frag));
		sk_mem_charge(sk, skb_frag_size(frag));
		get_page(skb_frag_page(frag));
	}
	sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]);

	/* all ready, send */
	return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags);
}

static int tls_device_record_close(struct sock *sk,
				   struct tls_context *ctx,
				   struct tls_record_info *record,
				   struct page_frag *pfrag,
				   unsigned char record_type)
{
	struct tls_prot_info *prot = &ctx->prot_info;
	int ret;

	/* append tag
	 * device will fill in the tag, we just need to append a placeholder
	 * use socket memory to improve coalescing (re-using a single buffer
	 * increases frag count)
	 * if we can't allocate memory now, steal some back from data
	 */
	if (likely(skb_page_frag_refill(prot->tag_size, pfrag,
					sk->sk_allocation))) {
		ret = 0;
		tls_append_frag(record, pfrag, prot->tag_size);
	} else {
		ret = prot->tag_size;
		if (record->len <= prot->overhead_size)
			return -ENOMEM;
	}

	/* fill prepend */
	tls_fill_prepend(ctx, skb_frag_address(&record->frags[0]),
			 record->len - prot->overhead_size,
			 record_type, prot->version);
	return ret;
}

static int tls_create_new_record(struct tls_offload_context_tx *offload_ctx,
				 struct page_frag *pfrag,
				 size_t prepend_size)
{
	struct tls_record_info *record;
	skb_frag_t *frag;

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

	frag = &record->frags[0];
	__skb_frag_set_page(frag, pfrag->page);
	skb_frag_off_set(frag, pfrag->offset);
	skb_frag_size_set(frag, prepend_size);

	get_page(pfrag->page);
	pfrag->offset += prepend_size;

	record->num_frags = 1;
	record->len = prepend_size;
	offload_ctx->open_record = record;
	return 0;
}

static int tls_do_allocation(struct sock *sk,
			     struct tls_offload_context_tx *offload_ctx,
			     struct page_frag *pfrag,
			     size_t prepend_size)
{
	int ret;

	if (!offload_ctx->open_record) {
		if (unlikely(!skb_page_frag_refill(prepend_size, pfrag,
						   sk->sk_allocation))) {
			sk->sk_prot->enter_memory_pressure(sk);
			sk_stream_moderate_sndbuf(sk);
			return -ENOMEM;
		}

		ret = tls_create_new_record(offload_ctx, pfrag, prepend_size);
		if (ret)
			return ret;

		if (pfrag->size > pfrag->offset)
			return 0;
	}

	if (!sk_page_frag_refill(sk, pfrag))
		return -ENOMEM;

	return 0;
}

static int tls_device_copy_data(void *addr, size_t bytes, struct iov_iter *i)
{
	size_t pre_copy, nocache;

	pre_copy = ~((unsigned long)addr - 1) & (SMP_CACHE_BYTES - 1);
	if (pre_copy) {
		pre_copy = min(pre_copy, bytes);
		if (copy_from_iter(addr, pre_copy, i) != pre_copy)
			return -EFAULT;
		bytes -= pre_copy;
		addr += pre_copy;
	}

	nocache = round_down(bytes, SMP_CACHE_BYTES);
	if (copy_from_iter_nocache(addr, nocache, i) != nocache)
		return -EFAULT;
	bytes -= nocache;
	addr += nocache;

	if (bytes && copy_from_iter(addr, bytes, i) != bytes)
		return -EFAULT;

	return 0;
}

static int tls_push_data(struct sock *sk,
			 struct iov_iter *msg_iter,
			 size_t size, int flags,
			 unsigned char record_type)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct tls_prot_info *prot = &tls_ctx->prot_info;
	struct tls_offload_context_tx *ctx = tls_offload_ctx_tx(tls_ctx);
	int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE);
	struct tls_record_info *record = ctx->open_record;
	int tls_push_record_flags;
	struct page_frag *pfrag;
	size_t orig_size = size;
	u32 max_open_record_len;
	int copy, rc = 0;
	bool done = false;
	long timeo;

	if (flags &
	    ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST))
		return -ENOTSUPP;

	if (unlikely(sk->sk_err))
		return -sk->sk_err;

	flags |= MSG_SENDPAGE_DECRYPTED;
	tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST;

	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
	if (tls_is_partially_sent_record(tls_ctx)) {
		rc = tls_push_partial_record(sk, tls_ctx, flags);
		if (rc < 0)
			return rc;
	}

	pfrag = sk_page_frag(sk);

	/* TLS_HEADER_SIZE is not counted as part of the TLS record, and
	 * we need to leave room for an authentication tag.
	 */
	max_open_record_len = TLS_MAX_PAYLOAD_SIZE +
			      prot->prepend_size;
	do {
		rc = tls_do_allocation(sk, ctx, pfrag, prot->prepend_size);
		if (unlikely(rc)) {
			rc = sk_stream_wait_memory(sk, &timeo);
			if (!rc)
				continue;

			record = ctx->open_record;
			if (!record)
				break;
handle_error:
			if (record_type != TLS_RECORD_TYPE_DATA) {
				/* avoid sending partial
				 * record with type !=
				 * application_data
				 */
				size = orig_size;
				destroy_record(record);
				ctx->open_record = NULL;
			} else if (record->len > prot->prepend_size) {
				goto last_record;
			}

			break;
		}

		record = ctx->open_record;
		copy = min_t(size_t, size, (pfrag->size - pfrag->offset));
		copy = min_t(size_t, copy, (max_open_record_len - record->len));

		rc = tls_device_copy_data(page_address(pfrag->page) +
					  pfrag->offset, copy, msg_iter);
		if (rc)
			goto handle_error;
		tls_append_frag(record, pfrag, copy);

		size -= copy;
		if (!size) {
last_record:
			tls_push_record_flags = flags;
			if (more) {
				tls_ctx->pending_open_record_frags =
						!!record->num_frags;
				break;
			}

			done = true;
		}

		if (done || record->len >= max_open_record_len ||
		    (record->num_frags >= MAX_SKB_FRAGS - 1)) {
			rc = tls_device_record_close(sk, tls_ctx, record,
						     pfrag, record_type);
			if (rc) {
				if (rc > 0) {
					size += rc;
				} else {
					size = orig_size;
					destroy_record(record);
					ctx->open_record = NULL;
					break;
				}
			}

			rc = tls_push_record(sk,
					     tls_ctx,
					     ctx,
					     record,
					     tls_push_record_flags);
			if (rc < 0)
				break;
		}
	} while (!done);

	if (orig_size - size > 0)
		rc = orig_size - size;

	return rc;
}

int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
{
	unsigned char record_type = TLS_RECORD_TYPE_DATA;
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	int rc;

	mutex_lock(&tls_ctx->tx_lock);
	lock_sock(sk);

	if (unlikely(msg->msg_controllen)) {
		rc = tls_proccess_cmsg(sk, msg, &record_type);
		if (rc)
			goto out;
	}

	rc = tls_push_data(sk, &msg->msg_iter, size,
			   msg->msg_flags, record_type);

out:
	release_sock(sk);
	mutex_unlock(&tls_ctx->tx_lock);
	return rc;
}

int tls_device_sendpage(struct sock *sk, struct page *page,
			int offset, size_t size, int flags)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct iov_iter	msg_iter;
	char *kaddr = kmap(page);
	struct kvec iov;
	int rc;

	if (flags & MSG_SENDPAGE_NOTLAST)
		flags |= MSG_MORE;

	mutex_lock(&tls_ctx->tx_lock);
	lock_sock(sk);

	if (flags & MSG_OOB) {
		rc = -ENOTSUPP;
		goto out;
	}

	iov.iov_base = kaddr + offset;
	iov.iov_len = size;
	iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size);
	rc = tls_push_data(sk, &msg_iter, size,
			   flags, TLS_RECORD_TYPE_DATA);
	kunmap(page);

out:
	release_sock(sk);
	mutex_unlock(&tls_ctx->tx_lock);
	return rc;
}

struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context,
				       u32 seq, u64 *p_record_sn)
{
	u64 record_sn = context->hint_record_sn;
	struct tls_record_info *info;

	info = context->retransmit_hint;
	if (!info ||
	    before(seq, info->end_seq - info->len)) {
		/* if retransmit_hint is irrelevant start
		 * from the beggining of the list
		 */
		info = list_first_entry_or_null(&context->records_list,
						struct tls_record_info, list);
		if (!info)
			return NULL;
		record_sn = context->unacked_record_sn;
	}

	/* We just need the _rcu for the READ_ONCE() */
	rcu_read_lock();
	list_for_each_entry_from_rcu(info, &context->records_list, list) {
		if (before(seq, info->end_seq)) {
			if (!context->retransmit_hint ||
			    after(info->end_seq,
				  context->retransmit_hint->end_seq)) {
				context->hint_record_sn = record_sn;
				context->retransmit_hint = info;
			}
			*p_record_sn = record_sn;
			goto exit_rcu_unlock;
		}
		record_sn++;
	}
	info = NULL;

exit_rcu_unlock:
	rcu_read_unlock();
	return info;
}
EXPORT_SYMBOL(tls_get_record);

static int tls_device_push_pending_record(struct sock *sk, int flags)
{
	struct iov_iter	msg_iter;

	iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0);
	return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA);
}

void tls_device_write_space(struct sock *sk, struct tls_context *ctx)
{
	if (tls_is_partially_sent_record(ctx)) {
		gfp_t sk_allocation = sk->sk_allocation;

		WARN_ON_ONCE(sk->sk_write_pending);

		sk->sk_allocation = GFP_ATOMIC;
		tls_push_partial_record(sk, ctx,
					MSG_DONTWAIT | MSG_NOSIGNAL |
					MSG_SENDPAGE_DECRYPTED);
		sk->sk_allocation = sk_allocation;
	}
}

static void tls_device_resync_rx(struct tls_context *tls_ctx,
				 struct sock *sk, u32 seq, u8 *rcd_sn)
{
	struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx);
	struct net_device *netdev;

	if (WARN_ON(test_and_set_bit(TLS_RX_SYNC_RUNNING, &tls_ctx->flags)))
		return;

	trace_tls_device_rx_resync_send(sk, seq, rcd_sn, rx_ctx->resync_type);
	netdev = READ_ONCE(tls_ctx->netdev);
	if (netdev)
		netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn,
						   TLS_OFFLOAD_CTX_DIR_RX);
	clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags);
	TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSRXDEVICERESYNC);
}

void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct tls_offload_context_rx *rx_ctx;
	u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE];
	u32 sock_data, is_req_pending;
	struct tls_prot_info *prot;
	s64 resync_req;
	u32 req_seq;

	if (tls_ctx->rx_conf != TLS_HW)
		return;

	prot = &tls_ctx->prot_info;
	rx_ctx = tls_offload_ctx_rx(tls_ctx);
	memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size);

	switch (rx_ctx->resync_type) {
	case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ:
		resync_req = atomic64_read(&rx_ctx->resync_req);
		req_seq = resync_req >> 32;
		seq += TLS_HEADER_SIZE - 1;
		is_req_pending = resync_req;

		if (likely(!is_req_pending) || req_seq != seq ||
		    !atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0))
			return;
		break;
	case TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT:
		if (likely(!rx_ctx->resync_nh_do_now))
			return;

		/* head of next rec is already in, note that the sock_inq will
		 * include the currently parsed message when called from parser
		 */
		sock_data = tcp_inq(sk);
		if (sock_data > rcd_len) {
			trace_tls_device_rx_resync_nh_delay(sk, sock_data,
							    rcd_len);
			return;
		}

		rx_ctx->resync_nh_do_now = 0;
		seq += rcd_len;
		tls_bigint_increment(rcd_sn, prot->rec_seq_size);
		break;
	}

	tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn);
}

static void tls_device_core_ctrl_rx_resync(struct tls_context *tls_ctx,
					   struct tls_offload_context_rx *ctx,
					   struct sock *sk, struct sk_buff *skb)
{
	struct strp_msg *rxm;

	/* device will request resyncs by itself based on stream scan */
	if (ctx->resync_type != TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT)
		return;
	/* already scheduled */
	if (ctx->resync_nh_do_now)
		return;
	/* seen decrypted fragments since last fully-failed record */
	if (ctx->resync_nh_reset) {
		ctx->resync_nh_reset = 0;
		ctx->resync_nh.decrypted_failed = 1;
		ctx->resync_nh.decrypted_tgt = TLS_DEVICE_RESYNC_NH_START_IVAL;
		return;
	}

	if (++ctx->resync_nh.decrypted_failed <= ctx->resync_nh.decrypted_tgt)
		return;

	/* doing resync, bump the next target in case it fails */
	if (ctx->resync_nh.decrypted_tgt < TLS_DEVICE_RESYNC_NH_MAX_IVAL)
		ctx->resync_nh.decrypted_tgt *= 2;
	else
		ctx->resync_nh.decrypted_tgt += TLS_DEVICE_RESYNC_NH_MAX_IVAL;

	rxm = strp_msg(skb);

	/* head of next rec is already in, parser will sync for us */
	if (tcp_inq(sk) > rxm->full_len) {
		trace_tls_device_rx_resync_nh_schedule(sk);
		ctx->resync_nh_do_now = 1;
	} else {
		struct tls_prot_info *prot = &tls_ctx->prot_info;
		u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE];

		memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size);
		tls_bigint_increment(rcd_sn, prot->rec_seq_size);

		tls_device_resync_rx(tls_ctx, sk, tcp_sk(sk)->copied_seq,
				     rcd_sn);
	}
}

static int tls_device_reencrypt(struct sock *sk, struct sk_buff *skb)
{
	struct strp_msg *rxm = strp_msg(skb);
	int err = 0, offset = rxm->offset, copy, nsg, data_len, pos;
	struct sk_buff *skb_iter, *unused;
	struct scatterlist sg[1];
	char *orig_buf, *buf;

	orig_buf = kmalloc(rxm->full_len + TLS_HEADER_SIZE +
			   TLS_CIPHER_AES_GCM_128_IV_SIZE, sk->sk_allocation);
	if (!orig_buf)
		return -ENOMEM;
	buf = orig_buf;

	nsg = skb_cow_data(skb, 0, &unused);
	if (unlikely(nsg < 0)) {
		err = nsg;
		goto free_buf;
	}

	sg_init_table(sg, 1);
	sg_set_buf(&sg[0], buf,
		   rxm->full_len + TLS_HEADER_SIZE +
		   TLS_CIPHER_AES_GCM_128_IV_SIZE);
	err = skb_copy_bits(skb, offset, buf,
			    TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE);
	if (err)
		goto free_buf;

	/* We are interested only in the decrypted data not the auth */
	err = decrypt_skb(sk, skb, sg);
	if (err != -EBADMSG)
		goto free_buf;
	else
		err = 0;

	data_len = rxm->full_len - TLS_CIPHER_AES_GCM_128_TAG_SIZE;

	if (skb_pagelen(skb) > offset) {
		copy = min_t(int, skb_pagelen(skb) - offset, data_len);

		if (skb->decrypted) {
			err = skb_store_bits(skb, offset, buf, copy);
			if (err)
				goto free_buf;
		}

		offset += copy;
		buf += copy;
	}

	pos = skb_pagelen(skb);
	skb_walk_frags(skb, skb_iter) {
		int frag_pos;

		/* Practically all frags must belong to msg if reencrypt
		 * is needed with current strparser and coalescing logic,
		 * but strparser may "get optimized", so let's be safe.
		 */
		if (pos + skb_iter->len <= offset)
			goto done_with_frag;
		if (pos >= data_len + rxm->offset)
			break;

		frag_pos = offset - pos;
		copy = min_t(int, skb_iter->len - frag_pos,
			     data_len + rxm->offset - offset);

		if (skb_iter->decrypted) {
			err = skb_store_bits(skb_iter, frag_pos, buf, copy);
			if (err)
				goto free_buf;
		}

		offset += copy;
		buf += copy;
done_with_frag:
		pos += skb_iter->len;
	}

free_buf:
	kfree(orig_buf);
	return err;
}

int tls_device_decrypted(struct sock *sk, struct tls_context *tls_ctx,
			 struct sk_buff *skb, struct strp_msg *rxm)
{
	struct tls_offload_context_rx *ctx = tls_offload_ctx_rx(tls_ctx);
	int is_decrypted = skb->decrypted;
	int is_encrypted = !is_decrypted;
	struct sk_buff *skb_iter;

	/* Check if all the data is decrypted already */
	skb_walk_frags(skb, skb_iter) {
		is_decrypted &= skb_iter->decrypted;
		is_encrypted &= !skb_iter->decrypted;
	}

	trace_tls_device_decrypted(sk, tcp_sk(sk)->copied_seq - rxm->full_len,
				   tls_ctx->rx.rec_seq, rxm->full_len,
				   is_encrypted, is_decrypted);

	ctx->sw.decrypted |= is_decrypted;

	/* Return immediately if the record is either entirely plaintext or
	 * entirely ciphertext. Otherwise handle reencrypt partially decrypted
	 * record.
	 */
	if (is_decrypted) {
		ctx->resync_nh_reset = 1;
		return 0;
	}
	if (is_encrypted) {
		tls_device_core_ctrl_rx_resync(tls_ctx, ctx, sk, skb);
		return 0;
	}

	ctx->resync_nh_reset = 1;
	return tls_device_reencrypt(sk, skb);
}

static void tls_device_attach(struct tls_context *ctx, struct sock *sk,
			      struct net_device *netdev)
{
	if (sk->sk_destruct != tls_device_sk_destruct) {
		refcount_set(&ctx->refcount, 1);
		dev_hold(netdev);
		ctx->netdev = netdev;
		spin_lock_irq(&tls_device_lock);
		list_add_tail(&ctx->list, &tls_device_list);
		spin_unlock_irq(&tls_device_lock);

		ctx->sk_destruct = sk->sk_destruct;
		sk->sk_destruct = tls_device_sk_destruct;
	}
}

int tls_set_device_offload(struct sock *sk, struct tls_context *ctx)
{
	u16 nonce_size, tag_size, iv_size, rec_seq_size;
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct tls_prot_info *prot = &tls_ctx->prot_info;
	struct tls_record_info *start_marker_record;
	struct tls_offload_context_tx *offload_ctx;
	struct tls_crypto_info *crypto_info;
	struct net_device *netdev;
	char *iv, *rec_seq;
	struct sk_buff *skb;
	__be64 rcd_sn;
	int rc;

	if (!ctx)
		return -EINVAL;

	if (ctx->priv_ctx_tx)
		return -EEXIST;

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

	offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_TX, GFP_KERNEL);
	if (!offload_ctx) {
		rc = -ENOMEM;
		goto free_marker_record;
	}

	crypto_info = &ctx->crypto_send.info;
	if (crypto_info->version != TLS_1_2_VERSION) {
		rc = -EOPNOTSUPP;
		goto free_offload_ctx;
	}

	switch (crypto_info->cipher_type) {
	case TLS_CIPHER_AES_GCM_128:
		nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
		tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE;
		iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE;
		iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv;
		rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE;
		rec_seq =
		 ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq;
		break;
	default:
		rc = -EINVAL;
		goto free_offload_ctx;
	}

	/* Sanity-check the rec_seq_size for stack allocations */
	if (rec_seq_size > TLS_MAX_REC_SEQ_SIZE) {
		rc = -EINVAL;
		goto free_offload_ctx;
	}

	prot->version = crypto_info->version;
	prot->cipher_type = crypto_info->cipher_type;
	prot->prepend_size = TLS_HEADER_SIZE + nonce_size;
	prot->tag_size = tag_size;
	prot->overhead_size = prot->prepend_size + prot->tag_size;
	prot->iv_size = iv_size;
	ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE,
			     GFP_KERNEL);
	if (!ctx->tx.iv) {
		rc = -ENOMEM;
		goto free_offload_ctx;
	}

	memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size);

	prot->rec_seq_size = rec_seq_size;
	ctx->tx.rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL);
	if (!ctx->tx.rec_seq) {
		rc = -ENOMEM;
		goto free_iv;
	}

	rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info);
	if (rc)
		goto free_rec_seq;

	/* start at rec_seq - 1 to account for the start marker record */
	memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn));
	offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1;

	start_marker_record->end_seq = tcp_sk(sk)->write_seq;
	start_marker_record->len = 0;
	start_marker_record->num_frags = 0;

	INIT_LIST_HEAD(&offload_ctx->records_list);
	list_add_tail(&start_marker_record->list, &offload_ctx->records_list);
	spin_lock_init(&offload_ctx->lock);
	sg_init_table(offload_ctx->sg_tx_data,
		      ARRAY_SIZE(offload_ctx->sg_tx_data));

	clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked);
	ctx->push_pending_record = tls_device_push_pending_record;

	/* TLS offload is greatly simplified if we don't send
	 * SKBs where only part of the payload needs to be encrypted.
	 * So mark the last skb in the write queue as end of record.
	 */
	skb = tcp_write_queue_tail(sk);
	if (skb)
		TCP_SKB_CB(skb)->eor = 1;

	netdev = get_netdev_for_sock(sk);
	if (!netdev) {
		pr_err_ratelimited("%s: netdev not found\n", __func__);
		rc = -EINVAL;
		goto disable_cad;
	}

	if (!(netdev->features & NETIF_F_HW_TLS_TX)) {
		rc = -ENOTSUPP;
		goto release_netdev;
	}

	/* Avoid offloading if the device is down
	 * We don't want to offload new flows after
	 * the NETDEV_DOWN event
	 *
	 * device_offload_lock is taken in tls_devices's NETDEV_DOWN
	 * handler thus protecting from the device going down before
	 * ctx was added to tls_device_list.
	 */
	down_read(&device_offload_lock);
	if (!(netdev->flags & IFF_UP)) {
		rc = -EINVAL;
		goto release_lock;
	}

	ctx->priv_ctx_tx = offload_ctx;
	rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX,
					     &ctx->crypto_send.info,
					     tcp_sk(sk)->write_seq);
	trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_TX,
				     tcp_sk(sk)->write_seq, rec_seq, rc);
	if (rc)
		goto release_lock;

	tls_device_attach(ctx, sk, netdev);
	up_read(&device_offload_lock);

	/* following this assignment tls_is_sk_tx_device_offloaded
	 * will return true and the context might be accessed
	 * by the netdev's xmit function.
	 */
	smp_store_release(&sk->sk_validate_xmit_skb, tls_validate_xmit_skb);
	dev_put(netdev);

	return 0;

release_lock:
	up_read(&device_offload_lock);
release_netdev:
	dev_put(netdev);
disable_cad:
	clean_acked_data_disable(inet_csk(sk));
	crypto_free_aead(offload_ctx->aead_send);
free_rec_seq:
	kfree(ctx->tx.rec_seq);
free_iv:
	kfree(ctx->tx.iv);
free_offload_ctx:
	kfree(offload_ctx);
	ctx->priv_ctx_tx = NULL;
free_marker_record:
	kfree(start_marker_record);
	return rc;
}

int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx)
{
	struct tls12_crypto_info_aes_gcm_128 *info;
	struct tls_offload_context_rx *context;
	struct net_device *netdev;
	int rc = 0;

	if (ctx->crypto_recv.info.version != TLS_1_2_VERSION)
		return -EOPNOTSUPP;

	netdev = get_netdev_for_sock(sk);
	if (!netdev) {
		pr_err_ratelimited("%s: netdev not found\n", __func__);
		return -EINVAL;
	}

	if (!(netdev->features & NETIF_F_HW_TLS_RX)) {
		rc = -ENOTSUPP;
		goto release_netdev;
	}

	/* Avoid offloading if the device is down
	 * We don't want to offload new flows after
	 * the NETDEV_DOWN event
	 *
	 * device_offload_lock is taken in tls_devices's NETDEV_DOWN
	 * handler thus protecting from the device going down before
	 * ctx was added to tls_device_list.
	 */
	down_read(&device_offload_lock);
	if (!(netdev->flags & IFF_UP)) {
		rc = -EINVAL;
		goto release_lock;
	}

	context = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE_RX, GFP_KERNEL);
	if (!context) {
		rc = -ENOMEM;
		goto release_lock;
	}
	context->resync_nh_reset = 1;

	ctx->priv_ctx_rx = context;
	rc = tls_set_sw_offload(sk, ctx, 0);
	if (rc)
		goto release_ctx;

	rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_RX,
					     &ctx->crypto_recv.info,
					     tcp_sk(sk)->copied_seq);
	info = (void *)&ctx->crypto_recv.info;
	trace_tls_device_offload_set(sk, TLS_OFFLOAD_CTX_DIR_RX,
				     tcp_sk(sk)->copied_seq, info->rec_seq, rc);
	if (rc)
		goto free_sw_resources;

	tls_device_attach(ctx, sk, netdev);
	up_read(&device_offload_lock);

	dev_put(netdev);

	return 0;

free_sw_resources:
	up_read(&device_offload_lock);
	tls_sw_free_resources_rx(sk);
	down_read(&device_offload_lock);
release_ctx:
	ctx->priv_ctx_rx = NULL;
release_lock:
	up_read(&device_offload_lock);
release_netdev:
	dev_put(netdev);
	return rc;
}

void tls_device_offload_cleanup_rx(struct sock *sk)
{
	struct tls_context *tls_ctx = tls_get_ctx(sk);
	struct net_device *netdev;

	down_read(&device_offload_lock);
	netdev = tls_ctx->netdev;
	if (!netdev)
		goto out;

	netdev->tlsdev_ops->tls_dev_del(netdev, tls_ctx,
					TLS_OFFLOAD_CTX_DIR_RX);

	if (tls_ctx->tx_conf != TLS_HW) {
		dev_put(netdev);
		tls_ctx->netdev = NULL;
	}
out:
	up_read(&device_offload_lock);
	tls_sw_release_resources_rx(sk);
}

static int tls_device_down(struct net_device *netdev)
{
	struct tls_context *ctx, *tmp;
	unsigned long flags;
	LIST_HEAD(list);

	/* Request a write lock to block new offload attempts */
	down_write(&device_offload_lock);

	spin_lock_irqsave(&tls_device_lock, flags);
	list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) {
		if (ctx->netdev != netdev ||
		    !refcount_inc_not_zero(&ctx->refcount))
			continue;

		list_move(&ctx->list, &list);
	}
	spin_unlock_irqrestore(&tls_device_lock, flags);

	list_for_each_entry_safe(ctx, tmp, &list, list)	{
		if (ctx->tx_conf == TLS_HW)
			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
							TLS_OFFLOAD_CTX_DIR_TX);
		if (ctx->rx_conf == TLS_HW)
			netdev->tlsdev_ops->tls_dev_del(netdev, ctx,
							TLS_OFFLOAD_CTX_DIR_RX);
		WRITE_ONCE(ctx->netdev, NULL);
		smp_mb__before_atomic(); /* pairs with test_and_set_bit() */
		while (test_bit(TLS_RX_SYNC_RUNNING, &ctx->flags))
			usleep_range(10, 200);
		dev_put(netdev);
		list_del_init(&ctx->list);

		if (refcount_dec_and_test(&ctx->refcount))
			tls_device_free_ctx(ctx);
	}

	up_write(&device_offload_lock);

	flush_work(&tls_device_gc_work);

	return NOTIFY_DONE;
}

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

	if (!dev->tlsdev_ops &&
	    !(dev->features & (NETIF_F_HW_TLS_RX | NETIF_F_HW_TLS_TX)))
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_REGISTER:
	case NETDEV_FEAT_CHANGE:
		if ((dev->features & NETIF_F_HW_TLS_RX) &&
		    !dev->tlsdev_ops->tls_dev_resync)
			return NOTIFY_BAD;

		if  (dev->tlsdev_ops &&
		     dev->tlsdev_ops->tls_dev_add &&
		     dev->tlsdev_ops->tls_dev_del)
			return NOTIFY_DONE;
		else
			return NOTIFY_BAD;
	case NETDEV_DOWN:
		return tls_device_down(dev);
	}
	return NOTIFY_DONE;
}

static struct notifier_block tls_dev_notifier = {
	.notifier_call	= tls_dev_event,
};

void __init tls_device_init(void)
{
	register_netdevice_notifier(&tls_dev_notifier);
}

void __exit tls_device_cleanup(void)
{
	unregister_netdevice_notifier(&tls_dev_notifier);
	flush_work(&tls_device_gc_work);
	clean_acked_data_flush();
}