summaryrefslogtreecommitdiff
path: root/net/ipv4/esp4.c
blob: e1b1d080e908d4b13561e641cb21437686db6cee (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
// SPDX-License-Identifier: GPL-2.0-only
#define pr_fmt(fmt) "IPsec: " fmt

#include <crypto/aead.h>
#include <crypto/authenc.h>
#include <linux/err.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/xfrm.h>
#include <net/esp.h>
#include <linux/scatterlist.h>
#include <linux/kernel.h>
#include <linux/pfkeyv2.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/in6.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/udp.h>
#include <net/tcp.h>
#include <net/espintcp.h>

#include <linux/highmem.h>

struct esp_skb_cb {
	struct xfrm_skb_cb xfrm;
	void *tmp;
};

struct esp_output_extra {
	__be32 seqhi;
	u32 esphoff;
};

#define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))

/*
 * Allocate an AEAD request structure with extra space for SG and IV.
 *
 * For alignment considerations the IV is placed at the front, followed
 * by the request and finally the SG list.
 *
 * TODO: Use spare space in skb for this where possible.
 */
static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
{
	unsigned int len;

	len = extralen;

	len += crypto_aead_ivsize(aead);

	if (len) {
		len += crypto_aead_alignmask(aead) &
		       ~(crypto_tfm_ctx_alignment() - 1);
		len = ALIGN(len, crypto_tfm_ctx_alignment());
	}

	len += sizeof(struct aead_request) + crypto_aead_reqsize(aead);
	len = ALIGN(len, __alignof__(struct scatterlist));

	len += sizeof(struct scatterlist) * nfrags;

	return kmalloc(len, GFP_ATOMIC);
}

static inline void *esp_tmp_extra(void *tmp)
{
	return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
}

static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
{
	return crypto_aead_ivsize(aead) ?
	       PTR_ALIGN((u8 *)tmp + extralen,
			 crypto_aead_alignmask(aead) + 1) : tmp + extralen;
}

static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
{
	struct aead_request *req;

	req = (void *)PTR_ALIGN(iv + crypto_aead_ivsize(aead),
				crypto_tfm_ctx_alignment());
	aead_request_set_tfm(req, aead);
	return req;
}

static inline struct scatterlist *esp_req_sg(struct crypto_aead *aead,
					     struct aead_request *req)
{
	return (void *)ALIGN((unsigned long)(req + 1) +
			     crypto_aead_reqsize(aead),
			     __alignof__(struct scatterlist));
}

static void esp_ssg_unref(struct xfrm_state *x, void *tmp)
{
	struct crypto_aead *aead = x->data;
	int extralen = 0;
	u8 *iv;
	struct aead_request *req;
	struct scatterlist *sg;

	if (x->props.flags & XFRM_STATE_ESN)
		extralen += sizeof(struct esp_output_extra);

	iv = esp_tmp_iv(aead, tmp, extralen);
	req = esp_tmp_req(aead, iv);

	/* Unref skb_frag_pages in the src scatterlist if necessary.
	 * Skip the first sg which comes from skb->data.
	 */
	if (req->src != req->dst)
		for (sg = sg_next(req->src); sg; sg = sg_next(sg))
			put_page(sg_page(sg));
}

#ifdef CONFIG_INET_ESPINTCP
struct esp_tcp_sk {
	struct sock *sk;
	struct rcu_head rcu;
};

static void esp_free_tcp_sk(struct rcu_head *head)
{
	struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu);

	sock_put(esk->sk);
	kfree(esk);
}

static struct sock *esp_find_tcp_sk(struct xfrm_state *x)
{
	struct xfrm_encap_tmpl *encap = x->encap;
	struct esp_tcp_sk *esk;
	__be16 sport, dport;
	struct sock *nsk;
	struct sock *sk;

	sk = rcu_dereference(x->encap_sk);
	if (sk && sk->sk_state == TCP_ESTABLISHED)
		return sk;

	spin_lock_bh(&x->lock);
	sport = encap->encap_sport;
	dport = encap->encap_dport;
	nsk = rcu_dereference_protected(x->encap_sk,
					lockdep_is_held(&x->lock));
	if (sk && sk == nsk) {
		esk = kmalloc(sizeof(*esk), GFP_ATOMIC);
		if (!esk) {
			spin_unlock_bh(&x->lock);
			return ERR_PTR(-ENOMEM);
		}
		RCU_INIT_POINTER(x->encap_sk, NULL);
		esk->sk = sk;
		call_rcu(&esk->rcu, esp_free_tcp_sk);
	}
	spin_unlock_bh(&x->lock);

	sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4,
				     dport, x->props.saddr.a4, sport, 0);
	if (!sk)
		return ERR_PTR(-ENOENT);

	if (!tcp_is_ulp_esp(sk)) {
		sock_put(sk);
		return ERR_PTR(-EINVAL);
	}

	spin_lock_bh(&x->lock);
	nsk = rcu_dereference_protected(x->encap_sk,
					lockdep_is_held(&x->lock));
	if (encap->encap_sport != sport ||
	    encap->encap_dport != dport) {
		sock_put(sk);
		sk = nsk ?: ERR_PTR(-EREMCHG);
	} else if (sk == nsk) {
		sock_put(sk);
	} else {
		rcu_assign_pointer(x->encap_sk, sk);
	}
	spin_unlock_bh(&x->lock);

	return sk;
}

static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb)
{
	struct sock *sk;
	int err;

	rcu_read_lock();

	sk = esp_find_tcp_sk(x);
	err = PTR_ERR_OR_ZERO(sk);
	if (err)
		goto out;

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk))
		err = espintcp_queue_out(sk, skb);
	else
		err = espintcp_push_skb(sk, skb);
	bh_unlock_sock(sk);

out:
	rcu_read_unlock();
	return err;
}

static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk,
				   struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct xfrm_state *x = dst->xfrm;

	return esp_output_tcp_finish(x, skb);
}

static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
{
	int err;

	local_bh_disable();
	err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb);
	local_bh_enable();

	/* EINPROGRESS just happens to do the right thing.  It
	 * actually means that the skb has been consumed and
	 * isn't coming back.
	 */
	return err ?: -EINPROGRESS;
}
#else
static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
{
	kfree_skb(skb);

	return -EOPNOTSUPP;
}
#endif

static void esp_output_done(struct crypto_async_request *base, int err)
{
	struct sk_buff *skb = base->data;
	struct xfrm_offload *xo = xfrm_offload(skb);
	void *tmp;
	struct xfrm_state *x;

	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
		struct sec_path *sp = skb_sec_path(skb);

		x = sp->xvec[sp->len - 1];
	} else {
		x = skb_dst(skb)->xfrm;
	}

	tmp = ESP_SKB_CB(skb)->tmp;
	esp_ssg_unref(x, tmp);
	kfree(tmp);

	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
		if (err) {
			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
			kfree_skb(skb);
			return;
		}

		skb_push(skb, skb->data - skb_mac_header(skb));
		secpath_reset(skb);
		xfrm_dev_resume(skb);
	} else {
		if (!err &&
		    x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
			esp_output_tail_tcp(x, skb);
		else
			xfrm_output_resume(skb->sk, skb, err);
	}
}

/* Move ESP header back into place. */
static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
{
	struct ip_esp_hdr *esph = (void *)(skb->data + offset);
	void *tmp = ESP_SKB_CB(skb)->tmp;
	__be32 *seqhi = esp_tmp_extra(tmp);

	esph->seq_no = esph->spi;
	esph->spi = *seqhi;
}

static void esp_output_restore_header(struct sk_buff *skb)
{
	void *tmp = ESP_SKB_CB(skb)->tmp;
	struct esp_output_extra *extra = esp_tmp_extra(tmp);

	esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
				sizeof(__be32));
}

static struct ip_esp_hdr *esp_output_set_extra(struct sk_buff *skb,
					       struct xfrm_state *x,
					       struct ip_esp_hdr *esph,
					       struct esp_output_extra *extra)
{
	/* For ESN we move the header forward by 4 bytes to
	 * accommodate the high bits.  We will move it back after
	 * encryption.
	 */
	if ((x->props.flags & XFRM_STATE_ESN)) {
		__u32 seqhi;
		struct xfrm_offload *xo = xfrm_offload(skb);

		if (xo)
			seqhi = xo->seq.hi;
		else
			seqhi = XFRM_SKB_CB(skb)->seq.output.hi;

		extra->esphoff = (unsigned char *)esph -
				 skb_transport_header(skb);
		esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
		extra->seqhi = esph->spi;
		esph->seq_no = htonl(seqhi);
	}

	esph->spi = x->id.spi;

	return esph;
}

static void esp_output_done_esn(struct crypto_async_request *base, int err)
{
	struct sk_buff *skb = base->data;

	esp_output_restore_header(skb);
	esp_output_done(base, err);
}

static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb,
					       int encap_type,
					       struct esp_info *esp,
					       __be16 sport,
					       __be16 dport)
{
	struct udphdr *uh;
	__be32 *udpdata32;
	unsigned int len;

	len = skb->len + esp->tailen - skb_transport_offset(skb);
	if (len + sizeof(struct iphdr) > IP_MAX_MTU)
		return ERR_PTR(-EMSGSIZE);

	uh = (struct udphdr *)esp->esph;
	uh->source = sport;
	uh->dest = dport;
	uh->len = htons(len);
	uh->check = 0;

	*skb_mac_header(skb) = IPPROTO_UDP;

	if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) {
		udpdata32 = (__be32 *)(uh + 1);
		udpdata32[0] = udpdata32[1] = 0;
		return (struct ip_esp_hdr *)(udpdata32 + 2);
	}

	return (struct ip_esp_hdr *)(uh + 1);
}

#ifdef CONFIG_INET_ESPINTCP
static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
						    struct sk_buff *skb,
						    struct esp_info *esp)
{
	__be16 *lenp = (void *)esp->esph;
	struct ip_esp_hdr *esph;
	unsigned int len;
	struct sock *sk;

	len = skb->len + esp->tailen - skb_transport_offset(skb);
	if (len > IP_MAX_MTU)
		return ERR_PTR(-EMSGSIZE);

	rcu_read_lock();
	sk = esp_find_tcp_sk(x);
	rcu_read_unlock();

	if (IS_ERR(sk))
		return ERR_CAST(sk);

	*lenp = htons(len);
	esph = (struct ip_esp_hdr *)(lenp + 1);

	return esph;
}
#else
static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x,
						    struct sk_buff *skb,
						    struct esp_info *esp)
{
	return ERR_PTR(-EOPNOTSUPP);
}
#endif

static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb,
			    struct esp_info *esp)
{
	struct xfrm_encap_tmpl *encap = x->encap;
	struct ip_esp_hdr *esph;
	__be16 sport, dport;
	int encap_type;

	spin_lock_bh(&x->lock);
	sport = encap->encap_sport;
	dport = encap->encap_dport;
	encap_type = encap->encap_type;
	spin_unlock_bh(&x->lock);

	switch (encap_type) {
	default:
	case UDP_ENCAP_ESPINUDP:
	case UDP_ENCAP_ESPINUDP_NON_IKE:
		esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport);
		break;
	case TCP_ENCAP_ESPINTCP:
		esph = esp_output_tcp_encap(x, skb, esp);
		break;
	}

	if (IS_ERR(esph))
		return PTR_ERR(esph);

	esp->esph = esph;

	return 0;
}

int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
{
	u8 *tail;
	int nfrags;
	int esph_offset;
	struct page *page;
	struct sk_buff *trailer;
	int tailen = esp->tailen;

	/* this is non-NULL only with TCP/UDP Encapsulation */
	if (x->encap) {
		int err = esp_output_encap(x, skb, esp);

		if (err < 0)
			return err;
	}

	if (!skb_cloned(skb)) {
		if (tailen <= skb_tailroom(skb)) {
			nfrags = 1;
			trailer = skb;
			tail = skb_tail_pointer(trailer);

			goto skip_cow;
		} else if ((skb_shinfo(skb)->nr_frags < MAX_SKB_FRAGS)
			   && !skb_has_frag_list(skb)) {
			int allocsize;
			struct sock *sk = skb->sk;
			struct page_frag *pfrag = &x->xfrag;

			esp->inplace = false;

			allocsize = ALIGN(tailen, L1_CACHE_BYTES);

			spin_lock_bh(&x->lock);

			if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
				spin_unlock_bh(&x->lock);
				goto cow;
			}

			page = pfrag->page;
			get_page(page);

			tail = page_address(page) + pfrag->offset;

			esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);

			nfrags = skb_shinfo(skb)->nr_frags;

			__skb_fill_page_desc(skb, nfrags, page, pfrag->offset,
					     tailen);
			skb_shinfo(skb)->nr_frags = ++nfrags;

			pfrag->offset = pfrag->offset + allocsize;

			spin_unlock_bh(&x->lock);

			nfrags++;

			skb->len += tailen;
			skb->data_len += tailen;
			skb->truesize += tailen;
			if (sk && sk_fullsock(sk))
				refcount_add(tailen, &sk->sk_wmem_alloc);

			goto out;
		}
	}

cow:
	esph_offset = (unsigned char *)esp->esph - skb_transport_header(skb);

	nfrags = skb_cow_data(skb, tailen, &trailer);
	if (nfrags < 0)
		goto out;
	tail = skb_tail_pointer(trailer);
	esp->esph = (struct ip_esp_hdr *)(skb_transport_header(skb) + esph_offset);

skip_cow:
	esp_output_fill_trailer(tail, esp->tfclen, esp->plen, esp->proto);
	pskb_put(skb, trailer, tailen);

out:
	return nfrags;
}
EXPORT_SYMBOL_GPL(esp_output_head);

int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp)
{
	u8 *iv;
	int alen;
	void *tmp;
	int ivlen;
	int assoclen;
	int extralen;
	struct page *page;
	struct ip_esp_hdr *esph;
	struct crypto_aead *aead;
	struct aead_request *req;
	struct scatterlist *sg, *dsg;
	struct esp_output_extra *extra;
	int err = -ENOMEM;

	assoclen = sizeof(struct ip_esp_hdr);
	extralen = 0;

	if (x->props.flags & XFRM_STATE_ESN) {
		extralen += sizeof(*extra);
		assoclen += sizeof(__be32);
	}

	aead = x->data;
	alen = crypto_aead_authsize(aead);
	ivlen = crypto_aead_ivsize(aead);

	tmp = esp_alloc_tmp(aead, esp->nfrags + 2, extralen);
	if (!tmp)
		goto error;

	extra = esp_tmp_extra(tmp);
	iv = esp_tmp_iv(aead, tmp, extralen);
	req = esp_tmp_req(aead, iv);
	sg = esp_req_sg(aead, req);

	if (esp->inplace)
		dsg = sg;
	else
		dsg = &sg[esp->nfrags];

	esph = esp_output_set_extra(skb, x, esp->esph, extra);
	esp->esph = esph;

	sg_init_table(sg, esp->nfrags);
	err = skb_to_sgvec(skb, sg,
		           (unsigned char *)esph - skb->data,
		           assoclen + ivlen + esp->clen + alen);
	if (unlikely(err < 0))
		goto error_free;

	if (!esp->inplace) {
		int allocsize;
		struct page_frag *pfrag = &x->xfrag;

		allocsize = ALIGN(skb->data_len, L1_CACHE_BYTES);

		spin_lock_bh(&x->lock);
		if (unlikely(!skb_page_frag_refill(allocsize, pfrag, GFP_ATOMIC))) {
			spin_unlock_bh(&x->lock);
			goto error_free;
		}

		skb_shinfo(skb)->nr_frags = 1;

		page = pfrag->page;
		get_page(page);
		/* replace page frags in skb with new page */
		__skb_fill_page_desc(skb, 0, page, pfrag->offset, skb->data_len);
		pfrag->offset = pfrag->offset + allocsize;
		spin_unlock_bh(&x->lock);

		sg_init_table(dsg, skb_shinfo(skb)->nr_frags + 1);
		err = skb_to_sgvec(skb, dsg,
			           (unsigned char *)esph - skb->data,
			           assoclen + ivlen + esp->clen + alen);
		if (unlikely(err < 0))
			goto error_free;
	}

	if ((x->props.flags & XFRM_STATE_ESN))
		aead_request_set_callback(req, 0, esp_output_done_esn, skb);
	else
		aead_request_set_callback(req, 0, esp_output_done, skb);

	aead_request_set_crypt(req, sg, dsg, ivlen + esp->clen, iv);
	aead_request_set_ad(req, assoclen);

	memset(iv, 0, ivlen);
	memcpy(iv + ivlen - min(ivlen, 8), (u8 *)&esp->seqno + 8 - min(ivlen, 8),
	       min(ivlen, 8));

	ESP_SKB_CB(skb)->tmp = tmp;
	err = crypto_aead_encrypt(req);

	switch (err) {
	case -EINPROGRESS:
		goto error;

	case -ENOSPC:
		err = NET_XMIT_DROP;
		break;

	case 0:
		if ((x->props.flags & XFRM_STATE_ESN))
			esp_output_restore_header(skb);
	}

	if (sg != dsg)
		esp_ssg_unref(x, tmp);

	if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP)
		err = esp_output_tail_tcp(x, skb);

error_free:
	kfree(tmp);
error:
	return err;
}
EXPORT_SYMBOL_GPL(esp_output_tail);

static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
{
	int alen;
	int blksize;
	struct ip_esp_hdr *esph;
	struct crypto_aead *aead;
	struct esp_info esp;

	esp.inplace = true;

	esp.proto = *skb_mac_header(skb);
	*skb_mac_header(skb) = IPPROTO_ESP;

	/* skb is pure payload to encrypt */

	aead = x->data;
	alen = crypto_aead_authsize(aead);

	esp.tfclen = 0;
	if (x->tfcpad) {
		struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb);
		u32 padto;

		padto = min(x->tfcpad, xfrm_state_mtu(x, dst->child_mtu_cached));
		if (skb->len < padto)
			esp.tfclen = padto - skb->len;
	}
	blksize = ALIGN(crypto_aead_blocksize(aead), 4);
	esp.clen = ALIGN(skb->len + 2 + esp.tfclen, blksize);
	esp.plen = esp.clen - skb->len - esp.tfclen;
	esp.tailen = esp.tfclen + esp.plen + alen;

	esp.esph = ip_esp_hdr(skb);

	esp.nfrags = esp_output_head(x, skb, &esp);
	if (esp.nfrags < 0)
		return esp.nfrags;

	esph = esp.esph;
	esph->spi = x->id.spi;

	esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.low);
	esp.seqno = cpu_to_be64(XFRM_SKB_CB(skb)->seq.output.low +
				 ((u64)XFRM_SKB_CB(skb)->seq.output.hi << 32));

	skb_push(skb, -skb_network_offset(skb));

	return esp_output_tail(x, skb, &esp);
}

static inline int esp_remove_trailer(struct sk_buff *skb)
{
	struct xfrm_state *x = xfrm_input_state(skb);
	struct xfrm_offload *xo = xfrm_offload(skb);
	struct crypto_aead *aead = x->data;
	int alen, hlen, elen;
	int padlen, trimlen;
	__wsum csumdiff;
	u8 nexthdr[2];
	int ret;

	alen = crypto_aead_authsize(aead);
	hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
	elen = skb->len - hlen;

	if (xo && (xo->flags & XFRM_ESP_NO_TRAILER)) {
		ret = xo->proto;
		goto out;
	}

	if (skb_copy_bits(skb, skb->len - alen - 2, nexthdr, 2))
		BUG();

	ret = -EINVAL;
	padlen = nexthdr[0];
	if (padlen + 2 + alen >= elen) {
		net_dbg_ratelimited("ipsec esp packet is garbage padlen=%d, elen=%d\n",
				    padlen + 2, elen - alen);
		goto out;
	}

	trimlen = alen + padlen + 2;
	if (skb->ip_summed == CHECKSUM_COMPLETE) {
		csumdiff = skb_checksum(skb, skb->len - trimlen, trimlen, 0);
		skb->csum = csum_block_sub(skb->csum, csumdiff,
					   skb->len - trimlen);
	}
	pskb_trim(skb, skb->len - trimlen);

	ret = nexthdr[1];

out:
	return ret;
}

int esp_input_done2(struct sk_buff *skb, int err)
{
	const struct iphdr *iph;
	struct xfrm_state *x = xfrm_input_state(skb);
	struct xfrm_offload *xo = xfrm_offload(skb);
	struct crypto_aead *aead = x->data;
	int hlen = sizeof(struct ip_esp_hdr) + crypto_aead_ivsize(aead);
	int ihl;

	if (!xo || !(xo->flags & CRYPTO_DONE))
		kfree(ESP_SKB_CB(skb)->tmp);

	if (unlikely(err))
		goto out;

	err = esp_remove_trailer(skb);
	if (unlikely(err < 0))
		goto out;

	iph = ip_hdr(skb);
	ihl = iph->ihl * 4;

	if (x->encap) {
		struct xfrm_encap_tmpl *encap = x->encap;
		struct tcphdr *th = (void *)(skb_network_header(skb) + ihl);
		struct udphdr *uh = (void *)(skb_network_header(skb) + ihl);
		__be16 source;

		switch (x->encap->encap_type) {
		case TCP_ENCAP_ESPINTCP:
			source = th->source;
			break;
		case UDP_ENCAP_ESPINUDP:
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			source = uh->source;
			break;
		default:
			WARN_ON_ONCE(1);
			err = -EINVAL;
			goto out;
		}

		/*
		 * 1) if the NAT-T peer's IP or port changed then
		 *    advertize the change to the keying daemon.
		 *    This is an inbound SA, so just compare
		 *    SRC ports.
		 */
		if (iph->saddr != x->props.saddr.a4 ||
		    source != encap->encap_sport) {
			xfrm_address_t ipaddr;

			ipaddr.a4 = iph->saddr;
			km_new_mapping(x, &ipaddr, source);

			/* XXX: perhaps add an extra
			 * policy check here, to see
			 * if we should allow or
			 * reject a packet from a
			 * different source
			 * address/port.
			 */
		}

		/*
		 * 2) ignore UDP/TCP checksums in case
		 *    of NAT-T in Transport Mode, or
		 *    perform other post-processing fixes
		 *    as per draft-ietf-ipsec-udp-encaps-06,
		 *    section 3.1.2
		 */
		if (x->props.mode == XFRM_MODE_TRANSPORT)
			skb->ip_summed = CHECKSUM_UNNECESSARY;
	}

	skb_pull_rcsum(skb, hlen);
	if (x->props.mode == XFRM_MODE_TUNNEL)
		skb_reset_transport_header(skb);
	else
		skb_set_transport_header(skb, -ihl);

	/* RFC4303: Drop dummy packets without any error */
	if (err == IPPROTO_NONE)
		err = -EINVAL;

out:
	return err;
}
EXPORT_SYMBOL_GPL(esp_input_done2);

static void esp_input_done(struct crypto_async_request *base, int err)
{
	struct sk_buff *skb = base->data;

	xfrm_input_resume(skb, esp_input_done2(skb, err));
}

static void esp_input_restore_header(struct sk_buff *skb)
{
	esp_restore_header(skb, 0);
	__skb_pull(skb, 4);
}

static void esp_input_set_header(struct sk_buff *skb, __be32 *seqhi)
{
	struct xfrm_state *x = xfrm_input_state(skb);
	struct ip_esp_hdr *esph;

	/* For ESN we move the header forward by 4 bytes to
	 * accommodate the high bits.  We will move it back after
	 * decryption.
	 */
	if ((x->props.flags & XFRM_STATE_ESN)) {
		esph = skb_push(skb, 4);
		*seqhi = esph->spi;
		esph->spi = esph->seq_no;
		esph->seq_no = XFRM_SKB_CB(skb)->seq.input.hi;
	}
}

static void esp_input_done_esn(struct crypto_async_request *base, int err)
{
	struct sk_buff *skb = base->data;

	esp_input_restore_header(skb);
	esp_input_done(base, err);
}

/*
 * Note: detecting truncated vs. non-truncated authentication data is very
 * expensive, so we only support truncated data, which is the recommended
 * and common case.
 */
static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
{
	struct crypto_aead *aead = x->data;
	struct aead_request *req;
	struct sk_buff *trailer;
	int ivlen = crypto_aead_ivsize(aead);
	int elen = skb->len - sizeof(struct ip_esp_hdr) - ivlen;
	int nfrags;
	int assoclen;
	int seqhilen;
	__be32 *seqhi;
	void *tmp;
	u8 *iv;
	struct scatterlist *sg;
	int err = -EINVAL;

	if (!pskb_may_pull(skb, sizeof(struct ip_esp_hdr) + ivlen))
		goto out;

	if (elen <= 0)
		goto out;

	assoclen = sizeof(struct ip_esp_hdr);
	seqhilen = 0;

	if (x->props.flags & XFRM_STATE_ESN) {
		seqhilen += sizeof(__be32);
		assoclen += seqhilen;
	}

	if (!skb_cloned(skb)) {
		if (!skb_is_nonlinear(skb)) {
			nfrags = 1;

			goto skip_cow;
		} else if (!skb_has_frag_list(skb)) {
			nfrags = skb_shinfo(skb)->nr_frags;
			nfrags++;

			goto skip_cow;
		}
	}

	err = skb_cow_data(skb, 0, &trailer);
	if (err < 0)
		goto out;

	nfrags = err;

skip_cow:
	err = -ENOMEM;
	tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
	if (!tmp)
		goto out;

	ESP_SKB_CB(skb)->tmp = tmp;
	seqhi = esp_tmp_extra(tmp);
	iv = esp_tmp_iv(aead, tmp, seqhilen);
	req = esp_tmp_req(aead, iv);
	sg = esp_req_sg(aead, req);

	esp_input_set_header(skb, seqhi);

	sg_init_table(sg, nfrags);
	err = skb_to_sgvec(skb, sg, 0, skb->len);
	if (unlikely(err < 0)) {
		kfree(tmp);
		goto out;
	}

	skb->ip_summed = CHECKSUM_NONE;

	if ((x->props.flags & XFRM_STATE_ESN))
		aead_request_set_callback(req, 0, esp_input_done_esn, skb);
	else
		aead_request_set_callback(req, 0, esp_input_done, skb);

	aead_request_set_crypt(req, sg, sg, elen + ivlen, iv);
	aead_request_set_ad(req, assoclen);

	err = crypto_aead_decrypt(req);
	if (err == -EINPROGRESS)
		goto out;

	if ((x->props.flags & XFRM_STATE_ESN))
		esp_input_restore_header(skb);

	err = esp_input_done2(skb, err);

out:
	return err;
}

static int esp4_err(struct sk_buff *skb, u32 info)
{
	struct net *net = dev_net(skb->dev);
	const struct iphdr *iph = (const struct iphdr *)skb->data;
	struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2));
	struct xfrm_state *x;

	switch (icmp_hdr(skb)->type) {
	case ICMP_DEST_UNREACH:
		if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED)
			return 0;
		break;
	case ICMP_REDIRECT:
		break;
	default:
		return 0;
	}

	x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr,
			      esph->spi, IPPROTO_ESP, AF_INET);
	if (!x)
		return 0;

	if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
		ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ESP);
	else
		ipv4_redirect(skb, net, 0, IPPROTO_ESP);
	xfrm_state_put(x);

	return 0;
}

static void esp_destroy(struct xfrm_state *x)
{
	struct crypto_aead *aead = x->data;

	if (!aead)
		return;

	crypto_free_aead(aead);
}

static int esp_init_aead(struct xfrm_state *x)
{
	char aead_name[CRYPTO_MAX_ALG_NAME];
	struct crypto_aead *aead;
	int err;

	err = -ENAMETOOLONG;
	if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
		     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
		goto error;

	aead = crypto_alloc_aead(aead_name, 0, 0);
	err = PTR_ERR(aead);
	if (IS_ERR(aead))
		goto error;

	x->data = aead;

	err = crypto_aead_setkey(aead, x->aead->alg_key,
				 (x->aead->alg_key_len + 7) / 8);
	if (err)
		goto error;

	err = crypto_aead_setauthsize(aead, x->aead->alg_icv_len / 8);
	if (err)
		goto error;

error:
	return err;
}

static int esp_init_authenc(struct xfrm_state *x)
{
	struct crypto_aead *aead;
	struct crypto_authenc_key_param *param;
	struct rtattr *rta;
	char *key;
	char *p;
	char authenc_name[CRYPTO_MAX_ALG_NAME];
	unsigned int keylen;
	int err;

	err = -EINVAL;
	if (!x->ealg)
		goto error;

	err = -ENAMETOOLONG;

	if ((x->props.flags & XFRM_STATE_ESN)) {
		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
			     "%s%sauthencesn(%s,%s)%s",
			     x->geniv ?: "", x->geniv ? "(" : "",
			     x->aalg ? x->aalg->alg_name : "digest_null",
			     x->ealg->alg_name,
			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
			goto error;
	} else {
		if (snprintf(authenc_name, CRYPTO_MAX_ALG_NAME,
			     "%s%sauthenc(%s,%s)%s",
			     x->geniv ?: "", x->geniv ? "(" : "",
			     x->aalg ? x->aalg->alg_name : "digest_null",
			     x->ealg->alg_name,
			     x->geniv ? ")" : "") >= CRYPTO_MAX_ALG_NAME)
			goto error;
	}

	aead = crypto_alloc_aead(authenc_name, 0, 0);
	err = PTR_ERR(aead);
	if (IS_ERR(aead))
		goto error;

	x->data = aead;

	keylen = (x->aalg ? (x->aalg->alg_key_len + 7) / 8 : 0) +
		 (x->ealg->alg_key_len + 7) / 8 + RTA_SPACE(sizeof(*param));
	err = -ENOMEM;
	key = kmalloc(keylen, GFP_KERNEL);
	if (!key)
		goto error;

	p = key;
	rta = (void *)p;
	rta->rta_type = CRYPTO_AUTHENC_KEYA_PARAM;
	rta->rta_len = RTA_LENGTH(sizeof(*param));
	param = RTA_DATA(rta);
	p += RTA_SPACE(sizeof(*param));

	if (x->aalg) {
		struct xfrm_algo_desc *aalg_desc;

		memcpy(p, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8);
		p += (x->aalg->alg_key_len + 7) / 8;

		aalg_desc = xfrm_aalg_get_byname(x->aalg->alg_name, 0);
		BUG_ON(!aalg_desc);

		err = -EINVAL;
		if (aalg_desc->uinfo.auth.icv_fullbits / 8 !=
		    crypto_aead_authsize(aead)) {
			pr_info("ESP: %s digestsize %u != %hu\n",
				x->aalg->alg_name,
				crypto_aead_authsize(aead),
				aalg_desc->uinfo.auth.icv_fullbits / 8);
			goto free_key;
		}

		err = crypto_aead_setauthsize(
			aead, x->aalg->alg_trunc_len / 8);
		if (err)
			goto free_key;
	}

	param->enckeylen = cpu_to_be32((x->ealg->alg_key_len + 7) / 8);
	memcpy(p, x->ealg->alg_key, (x->ealg->alg_key_len + 7) / 8);

	err = crypto_aead_setkey(aead, key, keylen);

free_key:
	kfree(key);

error:
	return err;
}

static int esp_init_state(struct xfrm_state *x)
{
	struct crypto_aead *aead;
	u32 align;
	int err;

	x->data = NULL;

	if (x->aead)
		err = esp_init_aead(x);
	else
		err = esp_init_authenc(x);

	if (err)
		goto error;

	aead = x->data;

	x->props.header_len = sizeof(struct ip_esp_hdr) +
			      crypto_aead_ivsize(aead);
	if (x->props.mode == XFRM_MODE_TUNNEL)
		x->props.header_len += sizeof(struct iphdr);
	else if (x->props.mode == XFRM_MODE_BEET && x->sel.family != AF_INET6)
		x->props.header_len += IPV4_BEET_PHMAXLEN;
	if (x->encap) {
		struct xfrm_encap_tmpl *encap = x->encap;

		switch (encap->encap_type) {
		default:
			err = -EINVAL;
			goto error;
		case UDP_ENCAP_ESPINUDP:
			x->props.header_len += sizeof(struct udphdr);
			break;
		case UDP_ENCAP_ESPINUDP_NON_IKE:
			x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32);
			break;
#ifdef CONFIG_INET_ESPINTCP
		case TCP_ENCAP_ESPINTCP:
			/* only the length field, TCP encap is done by
			 * the socket
			 */
			x->props.header_len += 2;
			break;
#endif
		}
	}

	align = ALIGN(crypto_aead_blocksize(aead), 4);
	x->props.trailer_len = align + 1 + crypto_aead_authsize(aead);

error:
	return err;
}

static int esp4_rcv_cb(struct sk_buff *skb, int err)
{
	return 0;
}

static const struct xfrm_type esp_type =
{
	.owner		= THIS_MODULE,
	.proto	     	= IPPROTO_ESP,
	.flags		= XFRM_TYPE_REPLAY_PROT,
	.init_state	= esp_init_state,
	.destructor	= esp_destroy,
	.input		= esp_input,
	.output		= esp_output,
};

static struct xfrm4_protocol esp4_protocol = {
	.handler	=	xfrm4_rcv,
	.input_handler	=	xfrm_input,
	.cb_handler	=	esp4_rcv_cb,
	.err_handler	=	esp4_err,
	.priority	=	0,
};

static int __init esp4_init(void)
{
	if (xfrm_register_type(&esp_type, AF_INET) < 0) {
		pr_info("%s: can't add xfrm type\n", __func__);
		return -EAGAIN;
	}
	if (xfrm4_protocol_register(&esp4_protocol, IPPROTO_ESP) < 0) {
		pr_info("%s: can't add protocol\n", __func__);
		xfrm_unregister_type(&esp_type, AF_INET);
		return -EAGAIN;
	}
	return 0;
}

static void __exit esp4_fini(void)
{
	if (xfrm4_protocol_deregister(&esp4_protocol, IPPROTO_ESP) < 0)
		pr_info("%s: can't remove protocol\n", __func__);
	xfrm_unregister_type(&esp_type, AF_INET);
}

module_init(esp4_init);
module_exit(esp4_fini);
MODULE_LICENSE("GPL");
MODULE_ALIAS_XFRM_TYPE(AF_INET, XFRM_PROTO_ESP);