summaryrefslogtreecommitdiff
path: root/drivers/crypto/atmel-sha.c
blob: e4757f8957ae436cd3cc4f7b54c5492d14663fce (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
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
/*
 * Cryptographic API.
 *
 * Support for ATMEL SHA1/SHA256 HW acceleration.
 *
 * Copyright (c) 2012 Eukréa Electromatique - ATMEL
 * Author: Nicolas Royer <nicolas@eukrea.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as published
 * by the Free Software Foundation.
 *
 * Some ideas are from omap-sham.c drivers.
 */


#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/err.h>
#include <linux/clk.h>
#include <linux/io.h>
#include <linux/hw_random.h>
#include <linux/platform_device.h>

#include <linux/device.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/interrupt.h>
#include <linux/irq.h>
#include <linux/scatterlist.h>
#include <linux/dma-mapping.h>
#include <linux/of_device.h>
#include <linux/delay.h>
#include <linux/crypto.h>
#include <linux/cryptohash.h>
#include <crypto/scatterwalk.h>
#include <crypto/algapi.h>
#include <crypto/sha.h>
#include <crypto/hash.h>
#include <crypto/internal/hash.h>
#include <linux/platform_data/crypto-atmel.h>
#include "atmel-sha-regs.h"

/* SHA flags */
#define SHA_FLAGS_BUSY			BIT(0)
#define	SHA_FLAGS_FINAL			BIT(1)
#define SHA_FLAGS_DMA_ACTIVE	BIT(2)
#define SHA_FLAGS_OUTPUT_READY	BIT(3)
#define SHA_FLAGS_INIT			BIT(4)
#define SHA_FLAGS_CPU			BIT(5)
#define SHA_FLAGS_DMA_READY		BIT(6)

#define SHA_FLAGS_FINUP		BIT(16)
#define SHA_FLAGS_SG		BIT(17)
#define SHA_FLAGS_ALGO_MASK	GENMASK(22, 18)
#define SHA_FLAGS_SHA1		BIT(18)
#define SHA_FLAGS_SHA224	BIT(19)
#define SHA_FLAGS_SHA256	BIT(20)
#define SHA_FLAGS_SHA384	BIT(21)
#define SHA_FLAGS_SHA512	BIT(22)
#define SHA_FLAGS_ERROR		BIT(23)
#define SHA_FLAGS_PAD		BIT(24)
#define SHA_FLAGS_RESTORE	BIT(25)

#define SHA_OP_UPDATE	1
#define SHA_OP_FINAL	2

#define SHA_BUFFER_LEN		(PAGE_SIZE / 16)

#define ATMEL_SHA_DMA_THRESHOLD		56

struct atmel_sha_caps {
	bool	has_dma;
	bool	has_dualbuff;
	bool	has_sha224;
	bool	has_sha_384_512;
	bool	has_uihv;
};

struct atmel_sha_dev;

/*
 * .statesize = sizeof(struct atmel_sha_reqctx) must be <= PAGE_SIZE / 8 as
 * tested by the ahash_prepare_alg() function.
 */
struct atmel_sha_reqctx {
	struct atmel_sha_dev	*dd;
	unsigned long	flags;
	unsigned long	op;

	u8	digest[SHA512_DIGEST_SIZE] __aligned(sizeof(u32));
	u64	digcnt[2];
	size_t	bufcnt;
	size_t	buflen;
	dma_addr_t	dma_addr;

	/* walk state */
	struct scatterlist	*sg;
	unsigned int	offset;	/* offset in current sg */
	unsigned int	total;	/* total request */

	size_t block_size;

	u8 buffer[SHA_BUFFER_LEN + SHA512_BLOCK_SIZE] __aligned(sizeof(u32));
};

struct atmel_sha_ctx {
	struct atmel_sha_dev	*dd;

	unsigned long		flags;
};

#define ATMEL_SHA_QUEUE_LENGTH	50

struct atmel_sha_dma {
	struct dma_chan			*chan;
	struct dma_slave_config dma_conf;
};

struct atmel_sha_dev {
	struct list_head	list;
	unsigned long		phys_base;
	struct device		*dev;
	struct clk			*iclk;
	int					irq;
	void __iomem		*io_base;

	spinlock_t		lock;
	int			err;
	struct tasklet_struct	done_task;
	struct tasklet_struct	queue_task;

	unsigned long		flags;
	struct crypto_queue	queue;
	struct ahash_request	*req;

	struct atmel_sha_dma	dma_lch_in;

	struct atmel_sha_caps	caps;

	u32	hw_version;
};

struct atmel_sha_drv {
	struct list_head	dev_list;
	spinlock_t		lock;
};

static struct atmel_sha_drv atmel_sha = {
	.dev_list = LIST_HEAD_INIT(atmel_sha.dev_list),
	.lock = __SPIN_LOCK_UNLOCKED(atmel_sha.lock),
};

static inline u32 atmel_sha_read(struct atmel_sha_dev *dd, u32 offset)
{
	return readl_relaxed(dd->io_base + offset);
}

static inline void atmel_sha_write(struct atmel_sha_dev *dd,
					u32 offset, u32 value)
{
	writel_relaxed(value, dd->io_base + offset);
}

static size_t atmel_sha_append_sg(struct atmel_sha_reqctx *ctx)
{
	size_t count;

	while ((ctx->bufcnt < ctx->buflen) && ctx->total) {
		count = min(ctx->sg->length - ctx->offset, ctx->total);
		count = min(count, ctx->buflen - ctx->bufcnt);

		if (count <= 0) {
			/*
			* Check if count <= 0 because the buffer is full or
			* because the sg length is 0. In the latest case,
			* check if there is another sg in the list, a 0 length
			* sg doesn't necessarily mean the end of the sg list.
			*/
			if ((ctx->sg->length == 0) && !sg_is_last(ctx->sg)) {
				ctx->sg = sg_next(ctx->sg);
				continue;
			} else {
				break;
			}
		}

		scatterwalk_map_and_copy(ctx->buffer + ctx->bufcnt, ctx->sg,
			ctx->offset, count, 0);

		ctx->bufcnt += count;
		ctx->offset += count;
		ctx->total -= count;

		if (ctx->offset == ctx->sg->length) {
			ctx->sg = sg_next(ctx->sg);
			if (ctx->sg)
				ctx->offset = 0;
			else
				ctx->total = 0;
		}
	}

	return 0;
}

/*
 * The purpose of this padding is to ensure that the padded message is a
 * multiple of 512 bits (SHA1/SHA224/SHA256) or 1024 bits (SHA384/SHA512).
 * The bit "1" is appended at the end of the message followed by
 * "padlen-1" zero bits. Then a 64 bits block (SHA1/SHA224/SHA256) or
 * 128 bits block (SHA384/SHA512) equals to the message length in bits
 * is appended.
 *
 * For SHA1/SHA224/SHA256, padlen is calculated as followed:
 *  - if message length < 56 bytes then padlen = 56 - message length
 *  - else padlen = 64 + 56 - message length
 *
 * For SHA384/SHA512, padlen is calculated as followed:
 *  - if message length < 112 bytes then padlen = 112 - message length
 *  - else padlen = 128 + 112 - message length
 */
static void atmel_sha_fill_padding(struct atmel_sha_reqctx *ctx, int length)
{
	unsigned int index, padlen;
	u64 bits[2];
	u64 size[2];

	size[0] = ctx->digcnt[0];
	size[1] = ctx->digcnt[1];

	size[0] += ctx->bufcnt;
	if (size[0] < ctx->bufcnt)
		size[1]++;

	size[0] += length;
	if (size[0]  < length)
		size[1]++;

	bits[1] = cpu_to_be64(size[0] << 3);
	bits[0] = cpu_to_be64(size[1] << 3 | size[0] >> 61);

	if (ctx->flags & (SHA_FLAGS_SHA384 | SHA_FLAGS_SHA512)) {
		index = ctx->bufcnt & 0x7f;
		padlen = (index < 112) ? (112 - index) : ((128+112) - index);
		*(ctx->buffer + ctx->bufcnt) = 0x80;
		memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen-1);
		memcpy(ctx->buffer + ctx->bufcnt + padlen, bits, 16);
		ctx->bufcnt += padlen + 16;
		ctx->flags |= SHA_FLAGS_PAD;
	} else {
		index = ctx->bufcnt & 0x3f;
		padlen = (index < 56) ? (56 - index) : ((64+56) - index);
		*(ctx->buffer + ctx->bufcnt) = 0x80;
		memset(ctx->buffer + ctx->bufcnt + 1, 0, padlen-1);
		memcpy(ctx->buffer + ctx->bufcnt + padlen, &bits[1], 8);
		ctx->bufcnt += padlen + 8;
		ctx->flags |= SHA_FLAGS_PAD;
	}
}

static int atmel_sha_init(struct ahash_request *req)
{
	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
	struct atmel_sha_ctx *tctx = crypto_ahash_ctx(tfm);
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	struct atmel_sha_dev *dd = NULL;
	struct atmel_sha_dev *tmp;

	spin_lock_bh(&atmel_sha.lock);
	if (!tctx->dd) {
		list_for_each_entry(tmp, &atmel_sha.dev_list, list) {
			dd = tmp;
			break;
		}
		tctx->dd = dd;
	} else {
		dd = tctx->dd;
	}

	spin_unlock_bh(&atmel_sha.lock);

	ctx->dd = dd;

	ctx->flags = 0;

	dev_dbg(dd->dev, "init: digest size: %d\n",
		crypto_ahash_digestsize(tfm));

	switch (crypto_ahash_digestsize(tfm)) {
	case SHA1_DIGEST_SIZE:
		ctx->flags |= SHA_FLAGS_SHA1;
		ctx->block_size = SHA1_BLOCK_SIZE;
		break;
	case SHA224_DIGEST_SIZE:
		ctx->flags |= SHA_FLAGS_SHA224;
		ctx->block_size = SHA224_BLOCK_SIZE;
		break;
	case SHA256_DIGEST_SIZE:
		ctx->flags |= SHA_FLAGS_SHA256;
		ctx->block_size = SHA256_BLOCK_SIZE;
		break;
	case SHA384_DIGEST_SIZE:
		ctx->flags |= SHA_FLAGS_SHA384;
		ctx->block_size = SHA384_BLOCK_SIZE;
		break;
	case SHA512_DIGEST_SIZE:
		ctx->flags |= SHA_FLAGS_SHA512;
		ctx->block_size = SHA512_BLOCK_SIZE;
		break;
	default:
		return -EINVAL;
		break;
	}

	ctx->bufcnt = 0;
	ctx->digcnt[0] = 0;
	ctx->digcnt[1] = 0;
	ctx->buflen = SHA_BUFFER_LEN;

	return 0;
}

static void atmel_sha_write_ctrl(struct atmel_sha_dev *dd, int dma)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	u32 valmr = SHA_MR_MODE_AUTO;
	unsigned int i, hashsize = 0;

	if (likely(dma)) {
		if (!dd->caps.has_dma)
			atmel_sha_write(dd, SHA_IER, SHA_INT_TXBUFE);
		valmr = SHA_MR_MODE_PDC;
		if (dd->caps.has_dualbuff)
			valmr |= SHA_MR_DUALBUFF;
	} else {
		atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY);
	}

	switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
	case SHA_FLAGS_SHA1:
		valmr |= SHA_MR_ALGO_SHA1;
		hashsize = SHA1_DIGEST_SIZE;
		break;

	case SHA_FLAGS_SHA224:
		valmr |= SHA_MR_ALGO_SHA224;
		hashsize = SHA256_DIGEST_SIZE;
		break;

	case SHA_FLAGS_SHA256:
		valmr |= SHA_MR_ALGO_SHA256;
		hashsize = SHA256_DIGEST_SIZE;
		break;

	case SHA_FLAGS_SHA384:
		valmr |= SHA_MR_ALGO_SHA384;
		hashsize = SHA512_DIGEST_SIZE;
		break;

	case SHA_FLAGS_SHA512:
		valmr |= SHA_MR_ALGO_SHA512;
		hashsize = SHA512_DIGEST_SIZE;
		break;

	default:
		break;
	}

	/* Setting CR_FIRST only for the first iteration */
	if (!(ctx->digcnt[0] || ctx->digcnt[1])) {
		atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
	} else if (dd->caps.has_uihv && (ctx->flags & SHA_FLAGS_RESTORE)) {
		const u32 *hash = (const u32 *)ctx->digest;

		/*
		 * Restore the hardware context: update the User Initialize
		 * Hash Value (UIHV) with the value saved when the latest
		 * 'update' operation completed on this very same crypto
		 * request.
		 */
		ctx->flags &= ~SHA_FLAGS_RESTORE;
		atmel_sha_write(dd, SHA_CR, SHA_CR_WUIHV);
		for (i = 0; i < hashsize / sizeof(u32); ++i)
			atmel_sha_write(dd, SHA_REG_DIN(i), hash[i]);
		atmel_sha_write(dd, SHA_CR, SHA_CR_FIRST);
		valmr |= SHA_MR_UIHV;
	}
	/*
	 * WARNING: If the UIHV feature is not available, the hardware CANNOT
	 * process concurrent requests: the internal registers used to store
	 * the hash/digest are still set to the partial digest output values
	 * computed during the latest round.
	 */

	atmel_sha_write(dd, SHA_MR, valmr);
}

static int atmel_sha_xmit_cpu(struct atmel_sha_dev *dd, const u8 *buf,
			      size_t length, int final)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	int count, len32;
	const u32 *buffer = (const u32 *)buf;

	dev_dbg(dd->dev, "xmit_cpu: digcnt: 0x%llx 0x%llx, length: %d, final: %d\n",
		ctx->digcnt[1], ctx->digcnt[0], length, final);

	atmel_sha_write_ctrl(dd, 0);

	/* should be non-zero before next lines to disable clocks later */
	ctx->digcnt[0] += length;
	if (ctx->digcnt[0] < length)
		ctx->digcnt[1]++;

	if (final)
		dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */

	len32 = DIV_ROUND_UP(length, sizeof(u32));

	dd->flags |= SHA_FLAGS_CPU;

	for (count = 0; count < len32; count++)
		atmel_sha_write(dd, SHA_REG_DIN(count), buffer[count]);

	return -EINPROGRESS;
}

static int atmel_sha_xmit_pdc(struct atmel_sha_dev *dd, dma_addr_t dma_addr1,
		size_t length1, dma_addr_t dma_addr2, size_t length2, int final)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	int len32;

	dev_dbg(dd->dev, "xmit_pdc: digcnt: 0x%llx 0x%llx, length: %d, final: %d\n",
		ctx->digcnt[1], ctx->digcnt[0], length1, final);

	len32 = DIV_ROUND_UP(length1, sizeof(u32));
	atmel_sha_write(dd, SHA_PTCR, SHA_PTCR_TXTDIS);
	atmel_sha_write(dd, SHA_TPR, dma_addr1);
	atmel_sha_write(dd, SHA_TCR, len32);

	len32 = DIV_ROUND_UP(length2, sizeof(u32));
	atmel_sha_write(dd, SHA_TNPR, dma_addr2);
	atmel_sha_write(dd, SHA_TNCR, len32);

	atmel_sha_write_ctrl(dd, 1);

	/* should be non-zero before next lines to disable clocks later */
	ctx->digcnt[0] += length1;
	if (ctx->digcnt[0] < length1)
		ctx->digcnt[1]++;

	if (final)
		dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */

	dd->flags |=  SHA_FLAGS_DMA_ACTIVE;

	/* Start DMA transfer */
	atmel_sha_write(dd, SHA_PTCR, SHA_PTCR_TXTEN);

	return -EINPROGRESS;
}

static void atmel_sha_dma_callback(void *data)
{
	struct atmel_sha_dev *dd = data;

	/* dma_lch_in - completed - wait DATRDY */
	atmel_sha_write(dd, SHA_IER, SHA_INT_DATARDY);
}

static int atmel_sha_xmit_dma(struct atmel_sha_dev *dd, dma_addr_t dma_addr1,
		size_t length1, dma_addr_t dma_addr2, size_t length2, int final)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	struct dma_async_tx_descriptor	*in_desc;
	struct scatterlist sg[2];

	dev_dbg(dd->dev, "xmit_dma: digcnt: 0x%llx 0x%llx, length: %d, final: %d\n",
		ctx->digcnt[1], ctx->digcnt[0], length1, final);

	dd->dma_lch_in.dma_conf.src_maxburst = 16;
	dd->dma_lch_in.dma_conf.dst_maxburst = 16;

	dmaengine_slave_config(dd->dma_lch_in.chan, &dd->dma_lch_in.dma_conf);

	if (length2) {
		sg_init_table(sg, 2);
		sg_dma_address(&sg[0]) = dma_addr1;
		sg_dma_len(&sg[0]) = length1;
		sg_dma_address(&sg[1]) = dma_addr2;
		sg_dma_len(&sg[1]) = length2;
		in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, sg, 2,
			DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
	} else {
		sg_init_table(sg, 1);
		sg_dma_address(&sg[0]) = dma_addr1;
		sg_dma_len(&sg[0]) = length1;
		in_desc = dmaengine_prep_slave_sg(dd->dma_lch_in.chan, sg, 1,
			DMA_MEM_TO_DEV, DMA_PREP_INTERRUPT | DMA_CTRL_ACK);
	}
	if (!in_desc)
		return -EINVAL;

	in_desc->callback = atmel_sha_dma_callback;
	in_desc->callback_param = dd;

	atmel_sha_write_ctrl(dd, 1);

	/* should be non-zero before next lines to disable clocks later */
	ctx->digcnt[0] += length1;
	if (ctx->digcnt[0] < length1)
		ctx->digcnt[1]++;

	if (final)
		dd->flags |= SHA_FLAGS_FINAL; /* catch last interrupt */

	dd->flags |=  SHA_FLAGS_DMA_ACTIVE;

	/* Start DMA transfer */
	dmaengine_submit(in_desc);
	dma_async_issue_pending(dd->dma_lch_in.chan);

	return -EINPROGRESS;
}

static int atmel_sha_xmit_start(struct atmel_sha_dev *dd, dma_addr_t dma_addr1,
		size_t length1, dma_addr_t dma_addr2, size_t length2, int final)
{
	if (dd->caps.has_dma)
		return atmel_sha_xmit_dma(dd, dma_addr1, length1,
				dma_addr2, length2, final);
	else
		return atmel_sha_xmit_pdc(dd, dma_addr1, length1,
				dma_addr2, length2, final);
}

static int atmel_sha_update_cpu(struct atmel_sha_dev *dd)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	int bufcnt;

	atmel_sha_append_sg(ctx);
	atmel_sha_fill_padding(ctx, 0);
	bufcnt = ctx->bufcnt;
	ctx->bufcnt = 0;

	return atmel_sha_xmit_cpu(dd, ctx->buffer, bufcnt, 1);
}

static int atmel_sha_xmit_dma_map(struct atmel_sha_dev *dd,
					struct atmel_sha_reqctx *ctx,
					size_t length, int final)
{
	ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer,
				ctx->buflen + ctx->block_size, DMA_TO_DEVICE);
	if (dma_mapping_error(dd->dev, ctx->dma_addr)) {
		dev_err(dd->dev, "dma %u bytes error\n", ctx->buflen +
				ctx->block_size);
		return -EINVAL;
	}

	ctx->flags &= ~SHA_FLAGS_SG;

	/* next call does not fail... so no unmap in the case of error */
	return atmel_sha_xmit_start(dd, ctx->dma_addr, length, 0, 0, final);
}

static int atmel_sha_update_dma_slow(struct atmel_sha_dev *dd)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	unsigned int final;
	size_t count;

	atmel_sha_append_sg(ctx);

	final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;

	dev_dbg(dd->dev, "slow: bufcnt: %u, digcnt: 0x%llx 0x%llx, final: %d\n",
		 ctx->bufcnt, ctx->digcnt[1], ctx->digcnt[0], final);

	if (final)
		atmel_sha_fill_padding(ctx, 0);

	if (final || (ctx->bufcnt == ctx->buflen)) {
		count = ctx->bufcnt;
		ctx->bufcnt = 0;
		return atmel_sha_xmit_dma_map(dd, ctx, count, final);
	}

	return 0;
}

static int atmel_sha_update_dma_start(struct atmel_sha_dev *dd)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);
	unsigned int length, final, tail;
	struct scatterlist *sg;
	unsigned int count;

	if (!ctx->total)
		return 0;

	if (ctx->bufcnt || ctx->offset)
		return atmel_sha_update_dma_slow(dd);

	dev_dbg(dd->dev, "fast: digcnt: 0x%llx 0x%llx, bufcnt: %u, total: %u\n",
		ctx->digcnt[1], ctx->digcnt[0], ctx->bufcnt, ctx->total);

	sg = ctx->sg;

	if (!IS_ALIGNED(sg->offset, sizeof(u32)))
		return atmel_sha_update_dma_slow(dd);

	if (!sg_is_last(sg) && !IS_ALIGNED(sg->length, ctx->block_size))
		/* size is not ctx->block_size aligned */
		return atmel_sha_update_dma_slow(dd);

	length = min(ctx->total, sg->length);

	if (sg_is_last(sg)) {
		if (!(ctx->flags & SHA_FLAGS_FINUP)) {
			/* not last sg must be ctx->block_size aligned */
			tail = length & (ctx->block_size - 1);
			length -= tail;
		}
	}

	ctx->total -= length;
	ctx->offset = length; /* offset where to start slow */

	final = (ctx->flags & SHA_FLAGS_FINUP) && !ctx->total;

	/* Add padding */
	if (final) {
		tail = length & (ctx->block_size - 1);
		length -= tail;
		ctx->total += tail;
		ctx->offset = length; /* offset where to start slow */

		sg = ctx->sg;
		atmel_sha_append_sg(ctx);

		atmel_sha_fill_padding(ctx, length);

		ctx->dma_addr = dma_map_single(dd->dev, ctx->buffer,
			ctx->buflen + ctx->block_size, DMA_TO_DEVICE);
		if (dma_mapping_error(dd->dev, ctx->dma_addr)) {
			dev_err(dd->dev, "dma %u bytes error\n",
				ctx->buflen + ctx->block_size);
			return -EINVAL;
		}

		if (length == 0) {
			ctx->flags &= ~SHA_FLAGS_SG;
			count = ctx->bufcnt;
			ctx->bufcnt = 0;
			return atmel_sha_xmit_start(dd, ctx->dma_addr, count, 0,
					0, final);
		} else {
			ctx->sg = sg;
			if (!dma_map_sg(dd->dev, ctx->sg, 1,
				DMA_TO_DEVICE)) {
					dev_err(dd->dev, "dma_map_sg  error\n");
					return -EINVAL;
			}

			ctx->flags |= SHA_FLAGS_SG;

			count = ctx->bufcnt;
			ctx->bufcnt = 0;
			return atmel_sha_xmit_start(dd, sg_dma_address(ctx->sg),
					length, ctx->dma_addr, count, final);
		}
	}

	if (!dma_map_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE)) {
		dev_err(dd->dev, "dma_map_sg  error\n");
		return -EINVAL;
	}

	ctx->flags |= SHA_FLAGS_SG;

	/* next call does not fail... so no unmap in the case of error */
	return atmel_sha_xmit_start(dd, sg_dma_address(ctx->sg), length, 0,
								0, final);
}

static int atmel_sha_update_dma_stop(struct atmel_sha_dev *dd)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(dd->req);

	if (ctx->flags & SHA_FLAGS_SG) {
		dma_unmap_sg(dd->dev, ctx->sg, 1, DMA_TO_DEVICE);
		if (ctx->sg->length == ctx->offset) {
			ctx->sg = sg_next(ctx->sg);
			if (ctx->sg)
				ctx->offset = 0;
		}
		if (ctx->flags & SHA_FLAGS_PAD) {
			dma_unmap_single(dd->dev, ctx->dma_addr,
				ctx->buflen + ctx->block_size, DMA_TO_DEVICE);
		}
	} else {
		dma_unmap_single(dd->dev, ctx->dma_addr, ctx->buflen +
						ctx->block_size, DMA_TO_DEVICE);
	}

	return 0;
}

static int atmel_sha_update_req(struct atmel_sha_dev *dd)
{
	struct ahash_request *req = dd->req;
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	int err;

	dev_dbg(dd->dev, "update_req: total: %u, digcnt: 0x%llx 0x%llx\n",
		ctx->total, ctx->digcnt[1], ctx->digcnt[0]);

	if (ctx->flags & SHA_FLAGS_CPU)
		err = atmel_sha_update_cpu(dd);
	else
		err = atmel_sha_update_dma_start(dd);

	/* wait for dma completion before can take more data */
	dev_dbg(dd->dev, "update: err: %d, digcnt: 0x%llx 0%llx\n",
			err, ctx->digcnt[1], ctx->digcnt[0]);

	return err;
}

static int atmel_sha_final_req(struct atmel_sha_dev *dd)
{
	struct ahash_request *req = dd->req;
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	int err = 0;
	int count;

	if (ctx->bufcnt >= ATMEL_SHA_DMA_THRESHOLD) {
		atmel_sha_fill_padding(ctx, 0);
		count = ctx->bufcnt;
		ctx->bufcnt = 0;
		err = atmel_sha_xmit_dma_map(dd, ctx, count, 1);
	}
	/* faster to handle last block with cpu */
	else {
		atmel_sha_fill_padding(ctx, 0);
		count = ctx->bufcnt;
		ctx->bufcnt = 0;
		err = atmel_sha_xmit_cpu(dd, ctx->buffer, count, 1);
	}

	dev_dbg(dd->dev, "final_req: err: %d\n", err);

	return err;
}

static void atmel_sha_copy_hash(struct ahash_request *req)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	u32 *hash = (u32 *)ctx->digest;
	unsigned int i, hashsize;

	switch (ctx->flags & SHA_FLAGS_ALGO_MASK) {
	case SHA_FLAGS_SHA1:
		hashsize = SHA1_DIGEST_SIZE;
		break;

	case SHA_FLAGS_SHA224:
	case SHA_FLAGS_SHA256:
		hashsize = SHA256_DIGEST_SIZE;
		break;

	case SHA_FLAGS_SHA384:
	case SHA_FLAGS_SHA512:
		hashsize = SHA512_DIGEST_SIZE;
		break;

	default:
		/* Should not happen... */
		return;
	}

	for (i = 0; i < hashsize / sizeof(u32); ++i)
		hash[i] = atmel_sha_read(ctx->dd, SHA_REG_DIGEST(i));
	ctx->flags |= SHA_FLAGS_RESTORE;
}

static void atmel_sha_copy_ready_hash(struct ahash_request *req)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);

	if (!req->result)
		return;

	if (ctx->flags & SHA_FLAGS_SHA1)
		memcpy(req->result, ctx->digest, SHA1_DIGEST_SIZE);
	else if (ctx->flags & SHA_FLAGS_SHA224)
		memcpy(req->result, ctx->digest, SHA224_DIGEST_SIZE);
	else if (ctx->flags & SHA_FLAGS_SHA256)
		memcpy(req->result, ctx->digest, SHA256_DIGEST_SIZE);
	else if (ctx->flags & SHA_FLAGS_SHA384)
		memcpy(req->result, ctx->digest, SHA384_DIGEST_SIZE);
	else
		memcpy(req->result, ctx->digest, SHA512_DIGEST_SIZE);
}

static int atmel_sha_finish(struct ahash_request *req)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	struct atmel_sha_dev *dd = ctx->dd;

	if (ctx->digcnt[0] || ctx->digcnt[1])
		atmel_sha_copy_ready_hash(req);

	dev_dbg(dd->dev, "digcnt: 0x%llx 0x%llx, bufcnt: %d\n", ctx->digcnt[1],
		ctx->digcnt[0], ctx->bufcnt);

	return 0;
}

static void atmel_sha_finish_req(struct ahash_request *req, int err)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	struct atmel_sha_dev *dd = ctx->dd;

	if (!err) {
		atmel_sha_copy_hash(req);
		if (SHA_FLAGS_FINAL & dd->flags)
			err = atmel_sha_finish(req);
	} else {
		ctx->flags |= SHA_FLAGS_ERROR;
	}

	/* atomic operation is not needed here */
	dd->flags &= ~(SHA_FLAGS_BUSY | SHA_FLAGS_FINAL | SHA_FLAGS_CPU |
			SHA_FLAGS_DMA_READY | SHA_FLAGS_OUTPUT_READY);

	clk_disable_unprepare(dd->iclk);

	if (req->base.complete)
		req->base.complete(&req->base, err);

	/* handle new request */
	tasklet_schedule(&dd->queue_task);
}

static int atmel_sha_hw_init(struct atmel_sha_dev *dd)
{
	int err;

	err = clk_prepare_enable(dd->iclk);
	if (err)
		return err;

	if (!(SHA_FLAGS_INIT & dd->flags)) {
		atmel_sha_write(dd, SHA_CR, SHA_CR_SWRST);
		dd->flags |= SHA_FLAGS_INIT;
		dd->err = 0;
	}

	return 0;
}

static inline unsigned int atmel_sha_get_version(struct atmel_sha_dev *dd)
{
	return atmel_sha_read(dd, SHA_HW_VERSION) & 0x00000fff;
}

static void atmel_sha_hw_version_init(struct atmel_sha_dev *dd)
{
	atmel_sha_hw_init(dd);

	dd->hw_version = atmel_sha_get_version(dd);

	dev_info(dd->dev,
			"version: 0x%x\n", dd->hw_version);

	clk_disable_unprepare(dd->iclk);
}

static int atmel_sha_handle_queue(struct atmel_sha_dev *dd,
				  struct ahash_request *req)
{
	struct crypto_async_request *async_req, *backlog;
	struct atmel_sha_reqctx *ctx;
	unsigned long flags;
	int err = 0, ret = 0;

	spin_lock_irqsave(&dd->lock, flags);
	if (req)
		ret = ahash_enqueue_request(&dd->queue, req);

	if (SHA_FLAGS_BUSY & dd->flags) {
		spin_unlock_irqrestore(&dd->lock, flags);
		return ret;
	}

	backlog = crypto_get_backlog(&dd->queue);
	async_req = crypto_dequeue_request(&dd->queue);
	if (async_req)
		dd->flags |= SHA_FLAGS_BUSY;

	spin_unlock_irqrestore(&dd->lock, flags);

	if (!async_req)
		return ret;

	if (backlog)
		backlog->complete(backlog, -EINPROGRESS);

	req = ahash_request_cast(async_req);
	dd->req = req;
	ctx = ahash_request_ctx(req);

	dev_dbg(dd->dev, "handling new req, op: %lu, nbytes: %d\n",
						ctx->op, req->nbytes);

	err = atmel_sha_hw_init(dd);

	if (err)
		goto err1;

	if (ctx->op == SHA_OP_UPDATE) {
		err = atmel_sha_update_req(dd);
		if (err != -EINPROGRESS && (ctx->flags & SHA_FLAGS_FINUP))
			/* no final() after finup() */
			err = atmel_sha_final_req(dd);
	} else if (ctx->op == SHA_OP_FINAL) {
		err = atmel_sha_final_req(dd);
	}

err1:
	if (err != -EINPROGRESS)
		/* done_task will not finish it, so do it here */
		atmel_sha_finish_req(req, err);

	dev_dbg(dd->dev, "exit, err: %d\n", err);

	return ret;
}

static int atmel_sha_enqueue(struct ahash_request *req, unsigned int op)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
	struct atmel_sha_dev *dd = tctx->dd;

	ctx->op = op;

	return atmel_sha_handle_queue(dd, req);
}

static int atmel_sha_update(struct ahash_request *req)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);

	if (!req->nbytes)
		return 0;

	ctx->total = req->nbytes;
	ctx->sg = req->src;
	ctx->offset = 0;

	if (ctx->flags & SHA_FLAGS_FINUP) {
		if (ctx->bufcnt + ctx->total < ATMEL_SHA_DMA_THRESHOLD)
			/* faster to use CPU for short transfers */
			ctx->flags |= SHA_FLAGS_CPU;
	} else if (ctx->bufcnt + ctx->total < ctx->buflen) {
		atmel_sha_append_sg(ctx);
		return 0;
	}
	return atmel_sha_enqueue(req, SHA_OP_UPDATE);
}

static int atmel_sha_final(struct ahash_request *req)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	struct atmel_sha_ctx *tctx = crypto_tfm_ctx(req->base.tfm);
	struct atmel_sha_dev *dd = tctx->dd;

	int err = 0;

	ctx->flags |= SHA_FLAGS_FINUP;

	if (ctx->flags & SHA_FLAGS_ERROR)
		return 0; /* uncompleted hash is not needed */

	if (ctx->bufcnt) {
		return atmel_sha_enqueue(req, SHA_OP_FINAL);
	} else if (!(ctx->flags & SHA_FLAGS_PAD)) { /* add padding */
		err = atmel_sha_hw_init(dd);
		if (err)
			goto err1;

		dd->req = req;
		dd->flags |= SHA_FLAGS_BUSY;
		err = atmel_sha_final_req(dd);
	} else {
		/* copy ready hash (+ finalize hmac) */
		return atmel_sha_finish(req);
	}

err1:
	if (err != -EINPROGRESS)
		/* done_task will not finish it, so do it here */
		atmel_sha_finish_req(req, err);

	return err;
}

static int atmel_sha_finup(struct ahash_request *req)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);
	int err1, err2;

	ctx->flags |= SHA_FLAGS_FINUP;

	err1 = atmel_sha_update(req);
	if (err1 == -EINPROGRESS || err1 == -EBUSY)
		return err1;

	/*
	 * final() has to be always called to cleanup resources
	 * even if udpate() failed, except EINPROGRESS
	 */
	err2 = atmel_sha_final(req);

	return err1 ?: err2;
}

static int atmel_sha_digest(struct ahash_request *req)
{
	return atmel_sha_init(req) ?: atmel_sha_finup(req);
}


static int atmel_sha_export(struct ahash_request *req, void *out)
{
	const struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);

	memcpy(out, ctx, sizeof(*ctx));
	return 0;
}

static int atmel_sha_import(struct ahash_request *req, const void *in)
{
	struct atmel_sha_reqctx *ctx = ahash_request_ctx(req);

	memcpy(ctx, in, sizeof(*ctx));
	return 0;
}

static int atmel_sha_cra_init(struct crypto_tfm *tfm)
{
	crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
				 sizeof(struct atmel_sha_reqctx));

	return 0;
}

static struct ahash_alg sha_1_256_algs[] = {
{
	.init		= atmel_sha_init,
	.update		= atmel_sha_update,
	.final		= atmel_sha_final,
	.finup		= atmel_sha_finup,
	.digest		= atmel_sha_digest,
	.export		= atmel_sha_export,
	.import		= atmel_sha_import,
	.halg = {
		.digestsize	= SHA1_DIGEST_SIZE,
		.statesize	= sizeof(struct atmel_sha_reqctx),
		.base	= {
			.cra_name		= "sha1",
			.cra_driver_name	= "atmel-sha1",
			.cra_priority		= 100,
			.cra_flags		= CRYPTO_ALG_ASYNC,
			.cra_blocksize		= SHA1_BLOCK_SIZE,
			.cra_ctxsize		= sizeof(struct atmel_sha_ctx),
			.cra_alignmask		= 0,
			.cra_module		= THIS_MODULE,
			.cra_init		= atmel_sha_cra_init,
		}
	}
},
{
	.init		= atmel_sha_init,
	.update		= atmel_sha_update,
	.final		= atmel_sha_final,
	.finup		= atmel_sha_finup,
	.digest		= atmel_sha_digest,
	.export		= atmel_sha_export,
	.import		= atmel_sha_import,
	.halg = {
		.digestsize	= SHA256_DIGEST_SIZE,
		.statesize	= sizeof(struct atmel_sha_reqctx),
		.base	= {
			.cra_name		= "sha256",
			.cra_driver_name	= "atmel-sha256",
			.cra_priority		= 100,
			.cra_flags		= CRYPTO_ALG_ASYNC,
			.cra_blocksize		= SHA256_BLOCK_SIZE,
			.cra_ctxsize		= sizeof(struct atmel_sha_ctx),
			.cra_alignmask		= 0,
			.cra_module		= THIS_MODULE,
			.cra_init		= atmel_sha_cra_init,
		}
	}
},
};

static struct ahash_alg sha_224_alg = {
	.init		= atmel_sha_init,
	.update		= atmel_sha_update,
	.final		= atmel_sha_final,
	.finup		= atmel_sha_finup,
	.digest		= atmel_sha_digest,
	.export		= atmel_sha_export,
	.import		= atmel_sha_import,
	.halg = {
		.digestsize	= SHA224_DIGEST_SIZE,
		.statesize	= sizeof(struct atmel_sha_reqctx),
		.base	= {
			.cra_name		= "sha224",
			.cra_driver_name	= "atmel-sha224",
			.cra_priority		= 100,
			.cra_flags		= CRYPTO_ALG_ASYNC,
			.cra_blocksize		= SHA224_BLOCK_SIZE,
			.cra_ctxsize		= sizeof(struct atmel_sha_ctx),
			.cra_alignmask		= 0,
			.cra_module		= THIS_MODULE,
			.cra_init		= atmel_sha_cra_init,
		}
	}
};

static struct ahash_alg sha_384_512_algs[] = {
{
	.init		= atmel_sha_init,
	.update		= atmel_sha_update,
	.final		= atmel_sha_final,
	.finup		= atmel_sha_finup,
	.digest		= atmel_sha_digest,
	.export		= atmel_sha_export,
	.import		= atmel_sha_import,
	.halg = {
		.digestsize	= SHA384_DIGEST_SIZE,
		.statesize	= sizeof(struct atmel_sha_reqctx),
		.base	= {
			.cra_name		= "sha384",
			.cra_driver_name	= "atmel-sha384",
			.cra_priority		= 100,
			.cra_flags		= CRYPTO_ALG_ASYNC,
			.cra_blocksize		= SHA384_BLOCK_SIZE,
			.cra_ctxsize		= sizeof(struct atmel_sha_ctx),
			.cra_alignmask		= 0x3,
			.cra_module		= THIS_MODULE,
			.cra_init		= atmel_sha_cra_init,
		}
	}
},
{
	.init		= atmel_sha_init,
	.update		= atmel_sha_update,
	.final		= atmel_sha_final,
	.finup		= atmel_sha_finup,
	.digest		= atmel_sha_digest,
	.export		= atmel_sha_export,
	.import		= atmel_sha_import,
	.halg = {
		.digestsize	= SHA512_DIGEST_SIZE,
		.statesize	= sizeof(struct atmel_sha_reqctx),
		.base	= {
			.cra_name		= "sha512",
			.cra_driver_name	= "atmel-sha512",
			.cra_priority		= 100,
			.cra_flags		= CRYPTO_ALG_ASYNC,
			.cra_blocksize		= SHA512_BLOCK_SIZE,
			.cra_ctxsize		= sizeof(struct atmel_sha_ctx),
			.cra_alignmask		= 0x3,
			.cra_module		= THIS_MODULE,
			.cra_init		= atmel_sha_cra_init,
		}
	}
},
};

static void atmel_sha_queue_task(unsigned long data)
{
	struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data;

	atmel_sha_handle_queue(dd, NULL);
}

static void atmel_sha_done_task(unsigned long data)
{
	struct atmel_sha_dev *dd = (struct atmel_sha_dev *)data;
	int err = 0;

	if (SHA_FLAGS_CPU & dd->flags) {
		if (SHA_FLAGS_OUTPUT_READY & dd->flags) {
			dd->flags &= ~SHA_FLAGS_OUTPUT_READY;
			goto finish;
		}
	} else if (SHA_FLAGS_DMA_READY & dd->flags) {
		if (SHA_FLAGS_DMA_ACTIVE & dd->flags) {
			dd->flags &= ~SHA_FLAGS_DMA_ACTIVE;
			atmel_sha_update_dma_stop(dd);
			if (dd->err) {
				err = dd->err;
				goto finish;
			}
		}
		if (SHA_FLAGS_OUTPUT_READY & dd->flags) {
			/* hash or semi-hash ready */
			dd->flags &= ~(SHA_FLAGS_DMA_READY |
						SHA_FLAGS_OUTPUT_READY);
			err = atmel_sha_update_dma_start(dd);
			if (err != -EINPROGRESS)
				goto finish;
		}
	}
	return;

finish:
	/* finish curent request */
	atmel_sha_finish_req(dd->req, err);
}

static irqreturn_t atmel_sha_irq(int irq, void *dev_id)
{
	struct atmel_sha_dev *sha_dd = dev_id;
	u32 reg;

	reg = atmel_sha_read(sha_dd, SHA_ISR);
	if (reg & atmel_sha_read(sha_dd, SHA_IMR)) {
		atmel_sha_write(sha_dd, SHA_IDR, reg);
		if (SHA_FLAGS_BUSY & sha_dd->flags) {
			sha_dd->flags |= SHA_FLAGS_OUTPUT_READY;
			if (!(SHA_FLAGS_CPU & sha_dd->flags))
				sha_dd->flags |= SHA_FLAGS_DMA_READY;
			tasklet_schedule(&sha_dd->done_task);
		} else {
			dev_warn(sha_dd->dev, "SHA interrupt when no active requests.\n");
		}
		return IRQ_HANDLED;
	}

	return IRQ_NONE;
}

static void atmel_sha_unregister_algs(struct atmel_sha_dev *dd)
{
	int i;

	for (i = 0; i < ARRAY_SIZE(sha_1_256_algs); i++)
		crypto_unregister_ahash(&sha_1_256_algs[i]);

	if (dd->caps.has_sha224)
		crypto_unregister_ahash(&sha_224_alg);

	if (dd->caps.has_sha_384_512) {
		for (i = 0; i < ARRAY_SIZE(sha_384_512_algs); i++)
			crypto_unregister_ahash(&sha_384_512_algs[i]);
	}
}

static int atmel_sha_register_algs(struct atmel_sha_dev *dd)
{
	int err, i, j;

	for (i = 0; i < ARRAY_SIZE(sha_1_256_algs); i++) {
		err = crypto_register_ahash(&sha_1_256_algs[i]);
		if (err)
			goto err_sha_1_256_algs;
	}

	if (dd->caps.has_sha224) {
		err = crypto_register_ahash(&sha_224_alg);
		if (err)
			goto err_sha_224_algs;
	}

	if (dd->caps.has_sha_384_512) {
		for (i = 0; i < ARRAY_SIZE(sha_384_512_algs); i++) {
			err = crypto_register_ahash(&sha_384_512_algs[i]);
			if (err)
				goto err_sha_384_512_algs;
		}
	}

	return 0;

err_sha_384_512_algs:
	for (j = 0; j < i; j++)
		crypto_unregister_ahash(&sha_384_512_algs[j]);
	crypto_unregister_ahash(&sha_224_alg);
err_sha_224_algs:
	i = ARRAY_SIZE(sha_1_256_algs);
err_sha_1_256_algs:
	for (j = 0; j < i; j++)
		crypto_unregister_ahash(&sha_1_256_algs[j]);

	return err;
}

static bool atmel_sha_filter(struct dma_chan *chan, void *slave)
{
	struct at_dma_slave	*sl = slave;

	if (sl && sl->dma_dev == chan->device->dev) {
		chan->private = sl;
		return true;
	} else {
		return false;
	}
}

static int atmel_sha_dma_init(struct atmel_sha_dev *dd,
				struct crypto_platform_data *pdata)
{
	int err = -ENOMEM;
	dma_cap_mask_t mask_in;

	/* Try to grab DMA channel */
	dma_cap_zero(mask_in);
	dma_cap_set(DMA_SLAVE, mask_in);

	dd->dma_lch_in.chan = dma_request_slave_channel_compat(mask_in,
			atmel_sha_filter, &pdata->dma_slave->rxdata, dd->dev, "tx");
	if (!dd->dma_lch_in.chan) {
		dev_warn(dd->dev, "no DMA channel available\n");
		return err;
	}

	dd->dma_lch_in.dma_conf.direction = DMA_MEM_TO_DEV;
	dd->dma_lch_in.dma_conf.dst_addr = dd->phys_base +
		SHA_REG_DIN(0);
	dd->dma_lch_in.dma_conf.src_maxburst = 1;
	dd->dma_lch_in.dma_conf.src_addr_width =
		DMA_SLAVE_BUSWIDTH_4_BYTES;
	dd->dma_lch_in.dma_conf.dst_maxburst = 1;
	dd->dma_lch_in.dma_conf.dst_addr_width =
		DMA_SLAVE_BUSWIDTH_4_BYTES;
	dd->dma_lch_in.dma_conf.device_fc = false;

	return 0;
}

static void atmel_sha_dma_cleanup(struct atmel_sha_dev *dd)
{
	dma_release_channel(dd->dma_lch_in.chan);
}

static void atmel_sha_get_cap(struct atmel_sha_dev *dd)
{

	dd->caps.has_dma = 0;
	dd->caps.has_dualbuff = 0;
	dd->caps.has_sha224 = 0;
	dd->caps.has_sha_384_512 = 0;
	dd->caps.has_uihv = 0;

	/* keep only major version number */
	switch (dd->hw_version & 0xff0) {
	case 0x510:
		dd->caps.has_dma = 1;
		dd->caps.has_dualbuff = 1;
		dd->caps.has_sha224 = 1;
		dd->caps.has_sha_384_512 = 1;
		dd->caps.has_uihv = 1;
		break;
	case 0x420:
		dd->caps.has_dma = 1;
		dd->caps.has_dualbuff = 1;
		dd->caps.has_sha224 = 1;
		dd->caps.has_sha_384_512 = 1;
		dd->caps.has_uihv = 1;
		break;
	case 0x410:
		dd->caps.has_dma = 1;
		dd->caps.has_dualbuff = 1;
		dd->caps.has_sha224 = 1;
		dd->caps.has_sha_384_512 = 1;
		break;
	case 0x400:
		dd->caps.has_dma = 1;
		dd->caps.has_dualbuff = 1;
		dd->caps.has_sha224 = 1;
		break;
	case 0x320:
		break;
	default:
		dev_warn(dd->dev,
				"Unmanaged sha version, set minimum capabilities\n");
		break;
	}
}

#if defined(CONFIG_OF)
static const struct of_device_id atmel_sha_dt_ids[] = {
	{ .compatible = "atmel,at91sam9g46-sha" },
	{ /* sentinel */ }
};

MODULE_DEVICE_TABLE(of, atmel_sha_dt_ids);

static struct crypto_platform_data *atmel_sha_of_init(struct platform_device *pdev)
{
	struct device_node *np = pdev->dev.of_node;
	struct crypto_platform_data *pdata;

	if (!np) {
		dev_err(&pdev->dev, "device node not found\n");
		return ERR_PTR(-EINVAL);
	}

	pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL);
	if (!pdata) {
		dev_err(&pdev->dev, "could not allocate memory for pdata\n");
		return ERR_PTR(-ENOMEM);
	}

	pdata->dma_slave = devm_kzalloc(&pdev->dev,
					sizeof(*(pdata->dma_slave)),
					GFP_KERNEL);
	if (!pdata->dma_slave) {
		dev_err(&pdev->dev, "could not allocate memory for dma_slave\n");
		return ERR_PTR(-ENOMEM);
	}

	return pdata;
}
#else /* CONFIG_OF */
static inline struct crypto_platform_data *atmel_sha_of_init(struct platform_device *dev)
{
	return ERR_PTR(-EINVAL);
}
#endif

static int atmel_sha_probe(struct platform_device *pdev)
{
	struct atmel_sha_dev *sha_dd;
	struct crypto_platform_data	*pdata;
	struct device *dev = &pdev->dev;
	struct resource *sha_res;
	int err;

	sha_dd = devm_kzalloc(&pdev->dev, sizeof(*sha_dd), GFP_KERNEL);
	if (sha_dd == NULL) {
		dev_err(dev, "unable to alloc data struct.\n");
		err = -ENOMEM;
		goto sha_dd_err;
	}

	sha_dd->dev = dev;

	platform_set_drvdata(pdev, sha_dd);

	INIT_LIST_HEAD(&sha_dd->list);
	spin_lock_init(&sha_dd->lock);

	tasklet_init(&sha_dd->done_task, atmel_sha_done_task,
					(unsigned long)sha_dd);
	tasklet_init(&sha_dd->queue_task, atmel_sha_queue_task,
					(unsigned long)sha_dd);

	crypto_init_queue(&sha_dd->queue, ATMEL_SHA_QUEUE_LENGTH);

	sha_dd->irq = -1;

	/* Get the base address */
	sha_res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (!sha_res) {
		dev_err(dev, "no MEM resource info\n");
		err = -ENODEV;
		goto res_err;
	}
	sha_dd->phys_base = sha_res->start;

	/* Get the IRQ */
	sha_dd->irq = platform_get_irq(pdev,  0);
	if (sha_dd->irq < 0) {
		dev_err(dev, "no IRQ resource info\n");
		err = sha_dd->irq;
		goto res_err;
	}

	err = devm_request_irq(&pdev->dev, sha_dd->irq, atmel_sha_irq,
			       IRQF_SHARED, "atmel-sha", sha_dd);
	if (err) {
		dev_err(dev, "unable to request sha irq.\n");
		goto res_err;
	}

	/* Initializing the clock */
	sha_dd->iclk = devm_clk_get(&pdev->dev, "sha_clk");
	if (IS_ERR(sha_dd->iclk)) {
		dev_err(dev, "clock initialization failed.\n");
		err = PTR_ERR(sha_dd->iclk);
		goto res_err;
	}

	sha_dd->io_base = devm_ioremap_resource(&pdev->dev, sha_res);
	if (!sha_dd->io_base) {
		dev_err(dev, "can't ioremap\n");
		err = -ENOMEM;
		goto res_err;
	}

	atmel_sha_hw_version_init(sha_dd);

	atmel_sha_get_cap(sha_dd);

	if (sha_dd->caps.has_dma) {
		pdata = pdev->dev.platform_data;
		if (!pdata) {
			pdata = atmel_sha_of_init(pdev);
			if (IS_ERR(pdata)) {
				dev_err(&pdev->dev, "platform data not available\n");
				err = PTR_ERR(pdata);
				goto res_err;
			}
		}
		if (!pdata->dma_slave) {
			err = -ENXIO;
			goto res_err;
		}
		err = atmel_sha_dma_init(sha_dd, pdata);
		if (err)
			goto err_sha_dma;

		dev_info(dev, "using %s for DMA transfers\n",
				dma_chan_name(sha_dd->dma_lch_in.chan));
	}

	spin_lock(&atmel_sha.lock);
	list_add_tail(&sha_dd->list, &atmel_sha.dev_list);
	spin_unlock(&atmel_sha.lock);

	err = atmel_sha_register_algs(sha_dd);
	if (err)
		goto err_algs;

	dev_info(dev, "Atmel SHA1/SHA256%s%s\n",
			sha_dd->caps.has_sha224 ? "/SHA224" : "",
			sha_dd->caps.has_sha_384_512 ? "/SHA384/SHA512" : "");

	return 0;

err_algs:
	spin_lock(&atmel_sha.lock);
	list_del(&sha_dd->list);
	spin_unlock(&atmel_sha.lock);
	if (sha_dd->caps.has_dma)
		atmel_sha_dma_cleanup(sha_dd);
err_sha_dma:
res_err:
	tasklet_kill(&sha_dd->queue_task);
	tasklet_kill(&sha_dd->done_task);
sha_dd_err:
	dev_err(dev, "initialization failed.\n");

	return err;
}

static int atmel_sha_remove(struct platform_device *pdev)
{
	static struct atmel_sha_dev *sha_dd;

	sha_dd = platform_get_drvdata(pdev);
	if (!sha_dd)
		return -ENODEV;
	spin_lock(&atmel_sha.lock);
	list_del(&sha_dd->list);
	spin_unlock(&atmel_sha.lock);

	atmel_sha_unregister_algs(sha_dd);

	tasklet_kill(&sha_dd->queue_task);
	tasklet_kill(&sha_dd->done_task);

	if (sha_dd->caps.has_dma)
		atmel_sha_dma_cleanup(sha_dd);

	iounmap(sha_dd->io_base);

	clk_put(sha_dd->iclk);

	if (sha_dd->irq >= 0)
		free_irq(sha_dd->irq, sha_dd);

	return 0;
}

static struct platform_driver atmel_sha_driver = {
	.probe		= atmel_sha_probe,
	.remove		= atmel_sha_remove,
	.driver		= {
		.name	= "atmel_sha",
		.of_match_table	= of_match_ptr(atmel_sha_dt_ids),
	},
};

module_platform_driver(atmel_sha_driver);

MODULE_DESCRIPTION("Atmel SHA (1/256/224/384/512) hw acceleration support.");
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Nicolas Royer - Eukréa Electromatique");