summaryrefslogtreecommitdiff
path: root/arch/powerpc/crypto/aes-gcm-p10.S
blob: a51f4b2653082e01ca0a2384a5edf556b99e5b6e (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
/* SPDX-License-Identifier: GPL-2.0-or-later */
 #
 # Accelerated AES-GCM stitched implementation for ppc64le.
 #
 # Copyright 2022- IBM Inc. All rights reserved
 #
 #===================================================================================
 # Written by Danny Tsen <dtsen@linux.ibm.com>
 #
 # GHASH is based on the Karatsuba multiplication method.
 #
 #    Xi xor X1
 #
 #    X1 * H^4 + X2 * H^3 + x3 * H^2 + X4 * H =
 #      (X1.h * H4.h + xX.l * H4.l + X1 * H4) +
 #      (X2.h * H3.h + X2.l * H3.l + X2 * H3) +
 #      (X3.h * H2.h + X3.l * H2.l + X3 * H2) +
 #      (X4.h * H.h + X4.l * H.l + X4 * H)
 #
 # Xi = v0
 # H Poly = v2
 # Hash keys = v3 - v14
 #     ( H.l, H, H.h)
 #     ( H^2.l, H^2, H^2.h)
 #     ( H^3.l, H^3, H^3.h)
 #     ( H^4.l, H^4, H^4.h)
 #
 # v30 is IV
 # v31 - counter 1
 #
 # AES used,
 #     vs0 - vs14 for round keys
 #     v15, v16, v17, v18, v19, v20, v21, v22 for 8 blocks (encrypted)
 #
 # This implementation uses stitched AES-GCM approach to improve overall performance.
 # AES is implemented with 8x blocks and GHASH is using 2 4x blocks.
 #
 # ===================================================================================
 #

#include <asm/ppc_asm.h>
#include <linux/linkage.h>

.machine        "any"
.text

 # 4x loops
 # v15 - v18 - input states
 # vs1 - vs9 - round keys
 #
.macro Loop_aes_middle4x
	xxlor	19+32, 1, 1
	xxlor	20+32, 2, 2
	xxlor	21+32, 3, 3
	xxlor	22+32, 4, 4

	vcipher	15, 15, 19
	vcipher	16, 16, 19
	vcipher	17, 17, 19
	vcipher	18, 18, 19

	vcipher	15, 15, 20
	vcipher	16, 16, 20
	vcipher	17, 17, 20
	vcipher	18, 18, 20

	vcipher	15, 15, 21
	vcipher	16, 16, 21
	vcipher	17, 17, 21
	vcipher	18, 18, 21

	vcipher	15, 15, 22
	vcipher	16, 16, 22
	vcipher	17, 17, 22
	vcipher	18, 18, 22

	xxlor	19+32, 5, 5
	xxlor	20+32, 6, 6
	xxlor	21+32, 7, 7
	xxlor	22+32, 8, 8

	vcipher	15, 15, 19
	vcipher	16, 16, 19
	vcipher	17, 17, 19
	vcipher	18, 18, 19

	vcipher	15, 15, 20
	vcipher	16, 16, 20
	vcipher	17, 17, 20
	vcipher	18, 18, 20

	vcipher	15, 15, 21
	vcipher	16, 16, 21
	vcipher	17, 17, 21
	vcipher	18, 18, 21

	vcipher	15, 15, 22
	vcipher	16, 16, 22
	vcipher	17, 17, 22
	vcipher	18, 18, 22

	xxlor	23+32, 9, 9
	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
.endm

 # 8x loops
 # v15 - v22 - input states
 # vs1 - vs9 - round keys
 #
.macro Loop_aes_middle8x
	xxlor	23+32, 1, 1
	xxlor	24+32, 2, 2
	xxlor	25+32, 3, 3
	xxlor	26+32, 4, 4

	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23

	vcipher	15, 15, 24
	vcipher	16, 16, 24
	vcipher	17, 17, 24
	vcipher	18, 18, 24
	vcipher	19, 19, 24
	vcipher	20, 20, 24
	vcipher	21, 21, 24
	vcipher	22, 22, 24

	vcipher	15, 15, 25
	vcipher	16, 16, 25
	vcipher	17, 17, 25
	vcipher	18, 18, 25
	vcipher	19, 19, 25
	vcipher	20, 20, 25
	vcipher	21, 21, 25
	vcipher	22, 22, 25

	vcipher	15, 15, 26
	vcipher	16, 16, 26
	vcipher	17, 17, 26
	vcipher	18, 18, 26
	vcipher	19, 19, 26
	vcipher	20, 20, 26
	vcipher	21, 21, 26
	vcipher	22, 22, 26

	xxlor	23+32, 5, 5
	xxlor	24+32, 6, 6
	xxlor	25+32, 7, 7
	xxlor	26+32, 8, 8

	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23

	vcipher	15, 15, 24
	vcipher	16, 16, 24
	vcipher	17, 17, 24
	vcipher	18, 18, 24
	vcipher	19, 19, 24
	vcipher	20, 20, 24
	vcipher	21, 21, 24
	vcipher	22, 22, 24

	vcipher	15, 15, 25
	vcipher	16, 16, 25
	vcipher	17, 17, 25
	vcipher	18, 18, 25
	vcipher	19, 19, 25
	vcipher	20, 20, 25
	vcipher	21, 21, 25
	vcipher	22, 22, 25

	vcipher	15, 15, 26
	vcipher	16, 16, 26
	vcipher	17, 17, 26
	vcipher	18, 18, 26
	vcipher	19, 19, 26
	vcipher	20, 20, 26
	vcipher	21, 21, 26
	vcipher	22, 22, 26

	xxlor	23+32, 9, 9
	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23
.endm

.macro Loop_aes_middle_1x
	xxlor	19+32, 1, 1
	xxlor	20+32, 2, 2
	xxlor	21+32, 3, 3
	xxlor	22+32, 4, 4

	vcipher 15, 15, 19
	vcipher 15, 15, 20
	vcipher 15, 15, 21
	vcipher 15, 15, 22

	xxlor	19+32, 5, 5
	xxlor	20+32, 6, 6
	xxlor	21+32, 7, 7
	xxlor	22+32, 8, 8

	vcipher 15, 15, 19
	vcipher 15, 15, 20
	vcipher 15, 15, 21
	vcipher 15, 15, 22

	xxlor	19+32, 9, 9
	vcipher 15, 15, 19
.endm

 #
 # Compute 4x hash values based on Karatsuba method.
 #
.macro ppc_aes_gcm_ghash
	vxor		15, 15, 0

	vpmsumd		23, 12, 15		# H4.L * X.L
	vpmsumd		24, 9, 16
	vpmsumd		25, 6, 17
	vpmsumd		26, 3, 18

	vxor		23, 23, 24
	vxor		23, 23, 25
	vxor		23, 23, 26		# L

	vpmsumd		24, 13, 15		# H4.L * X.H + H4.H * X.L
	vpmsumd		25, 10, 16		# H3.L * X1.H + H3.H * X1.L
	vpmsumd		26, 7, 17
	vpmsumd		27, 4, 18

	vxor		24, 24, 25
	vxor		24, 24, 26
	vxor		24, 24, 27		# M

	# sum hash and reduction with H Poly
	vpmsumd		28, 23, 2		# reduction

	vxor		29, 29, 29
	vsldoi		26, 24, 29, 8		# mL
	vsldoi		29, 29, 24, 8		# mH
	vxor		23, 23, 26		# mL + L

	vsldoi		23, 23, 23, 8		# swap
	vxor		23, 23, 28

	vpmsumd		24, 14, 15		# H4.H * X.H
	vpmsumd		25, 11, 16
	vpmsumd		26, 8, 17
	vpmsumd		27, 5, 18

	vxor		24, 24, 25
	vxor		24, 24, 26
	vxor		24, 24, 27

	vxor		24, 24, 29

	# sum hash and reduction with H Poly
	vsldoi		27, 23, 23, 8		# swap
	vpmsumd		23, 23, 2
	vxor		27, 27, 24
	vxor		23, 23, 27

	xxlor		32, 23+32, 23+32		# update hash

.endm

 #
 # Combine two 4x ghash
 # v15 - v22 - input blocks
 #
.macro ppc_aes_gcm_ghash2_4x
	# first 4x hash
	vxor		15, 15, 0		# Xi + X

	vpmsumd		23, 12, 15		# H4.L * X.L
	vpmsumd		24, 9, 16
	vpmsumd		25, 6, 17
	vpmsumd		26, 3, 18

	vxor		23, 23, 24
	vxor		23, 23, 25
	vxor		23, 23, 26		# L

	vpmsumd		24, 13, 15		# H4.L * X.H + H4.H * X.L
	vpmsumd		25, 10, 16		# H3.L * X1.H + H3.H * X1.L
	vpmsumd		26, 7, 17
	vpmsumd		27, 4, 18

	vxor		24, 24, 25
	vxor		24, 24, 26

	# sum hash and reduction with H Poly
	vpmsumd		28, 23, 2		# reduction

	vxor		29, 29, 29

	vxor		24, 24, 27		# M
	vsldoi		26, 24, 29, 8		# mL
	vsldoi		29, 29, 24, 8		# mH
	vxor		23, 23, 26		# mL + L

	vsldoi		23, 23, 23, 8		# swap
	vxor		23, 23, 28

	vpmsumd		24, 14, 15		# H4.H * X.H
	vpmsumd		25, 11, 16
	vpmsumd		26, 8, 17
	vpmsumd		27, 5, 18

	vxor		24, 24, 25
	vxor		24, 24, 26
	vxor		24, 24, 27		# H

	vxor		24, 24, 29		# H + mH

	# sum hash and reduction with H Poly
	vsldoi		27, 23, 23, 8		# swap
	vpmsumd		23, 23, 2
	vxor		27, 27, 24
	vxor		27, 23, 27		# 1st Xi

	# 2nd 4x hash
	vpmsumd		24, 9, 20
	vpmsumd		25, 6, 21
	vpmsumd		26, 3, 22
	vxor		19, 19, 27		# Xi + X
	vpmsumd		23, 12, 19		# H4.L * X.L

	vxor		23, 23, 24
	vxor		23, 23, 25
	vxor		23, 23, 26		# L

	vpmsumd		24, 13, 19		# H4.L * X.H + H4.H * X.L
	vpmsumd		25, 10, 20		# H3.L * X1.H + H3.H * X1.L
	vpmsumd		26, 7, 21
	vpmsumd		27, 4, 22

	vxor		24, 24, 25
	vxor		24, 24, 26

	# sum hash and reduction with H Poly
	vpmsumd		28, 23, 2		# reduction

	vxor		29, 29, 29

	vxor		24, 24, 27		# M
	vsldoi		26, 24, 29, 8		# mL
	vsldoi		29, 29, 24, 8		# mH
	vxor		23, 23, 26		# mL + L

	vsldoi		23, 23, 23, 8		# swap
	vxor		23, 23, 28

	vpmsumd		24, 14, 19		# H4.H * X.H
	vpmsumd		25, 11, 20
	vpmsumd		26, 8, 21
	vpmsumd		27, 5, 22

	vxor		24, 24, 25
	vxor		24, 24, 26
	vxor		24, 24, 27		# H

	vxor		24, 24, 29		# H + mH

	# sum hash and reduction with H Poly
	vsldoi		27, 23, 23, 8		# swap
	vpmsumd		23, 23, 2
	vxor		27, 27, 24
	vxor		23, 23, 27

	xxlor		32, 23+32, 23+32		# update hash

.endm

 #
 # Compute update single hash
 #
.macro ppc_update_hash_1x
	vxor		28, 28, 0

	vxor		19, 19, 19

	vpmsumd		22, 3, 28		# L
	vpmsumd		23, 4, 28		# M
	vpmsumd		24, 5, 28		# H

	vpmsumd		27, 22, 2		# reduction

	vsldoi		25, 23, 19, 8		# mL
	vsldoi		26, 19, 23, 8		# mH
	vxor		22, 22, 25		# LL + LL
	vxor		24, 24, 26		# HH + HH

	vsldoi		22, 22, 22, 8		# swap
	vxor		22, 22, 27

	vsldoi		20, 22, 22, 8		# swap
	vpmsumd		22, 22, 2		# reduction
	vxor		20, 20, 24
	vxor		22, 22, 20

	vmr		0, 22			# update hash

.endm

.macro SAVE_REGS
	stdu 1,-640(1)
	mflr 0

	std	14,112(1)
	std	15,120(1)
	std	16,128(1)
	std	17,136(1)
	std	18,144(1)
	std	19,152(1)
	std	20,160(1)
	std	21,168(1)
	li	9, 256
	stvx	20, 9, 1
	addi	9, 9, 16
	stvx	21, 9, 1
	addi	9, 9, 16
	stvx	22, 9, 1
	addi	9, 9, 16
	stvx	23, 9, 1
	addi	9, 9, 16
	stvx	24, 9, 1
	addi	9, 9, 16
	stvx	25, 9, 1
	addi	9, 9, 16
	stvx	26, 9, 1
	addi	9, 9, 16
	stvx	27, 9, 1
	addi	9, 9, 16
	stvx	28, 9, 1
	addi	9, 9, 16
	stvx	29, 9, 1
	addi	9, 9, 16
	stvx	30, 9, 1
	addi	9, 9, 16
	stvx	31, 9, 1
	stxv	14, 464(1)
	stxv	15, 480(1)
	stxv	16, 496(1)
	stxv	17, 512(1)
	stxv	18, 528(1)
	stxv	19, 544(1)
	stxv	20, 560(1)
	stxv	21, 576(1)
	stxv	22, 592(1)
	std	0, 656(1)
.endm

.macro RESTORE_REGS
	lxv	14, 464(1)
	lxv	15, 480(1)
	lxv	16, 496(1)
	lxv	17, 512(1)
	lxv	18, 528(1)
	lxv	19, 544(1)
	lxv	20, 560(1)
	lxv	21, 576(1)
	lxv	22, 592(1)
	li	9, 256
	lvx	20, 9, 1
	addi	9, 9, 16
	lvx	21, 9, 1
	addi	9, 9, 16
	lvx	22, 9, 1
	addi	9, 9, 16
	lvx	23, 9, 1
	addi	9, 9, 16
	lvx	24, 9, 1
	addi	9, 9, 16
	lvx	25, 9, 1
	addi	9, 9, 16
	lvx	26, 9, 1
	addi	9, 9, 16
	lvx	27, 9, 1
	addi	9, 9, 16
	lvx	28, 9, 1
	addi	9, 9, 16
	lvx	29, 9, 1
	addi	9, 9, 16
	lvx	30, 9, 1
	addi	9, 9, 16
	lvx	31, 9, 1

	ld	0, 656(1)
	ld      14,112(1)
	ld      15,120(1)
	ld      16,128(1)
	ld      17,136(1)
	ld      18,144(1)
	ld      19,152(1)
	ld      20,160(1)
	ld	21,168(1)

	mtlr	0
	addi	1, 1, 640
.endm

.macro LOAD_HASH_TABLE
	# Load Xi
	lxvb16x	32, 0, 8	# load Xi

	# load Hash - h^4, h^3, h^2, h
	li	10, 32
	lxvd2x	2+32, 10, 8	# H Poli
	li	10, 48
	lxvd2x	3+32, 10, 8	# Hl
	li	10, 64
	lxvd2x	4+32, 10, 8	# H
	li	10, 80
	lxvd2x	5+32, 10, 8	# Hh

	li	10, 96
	lxvd2x	6+32, 10, 8	# H^2l
	li	10, 112
	lxvd2x	7+32, 10, 8	# H^2
	li	10, 128
	lxvd2x	8+32, 10, 8	# H^2h

	li	10, 144
	lxvd2x	9+32, 10, 8	# H^3l
	li	10, 160
	lxvd2x	10+32, 10, 8	# H^3
	li	10, 176
	lxvd2x	11+32, 10, 8	# H^3h

	li	10, 192
	lxvd2x	12+32, 10, 8	# H^4l
	li	10, 208
	lxvd2x	13+32, 10, 8	# H^4
	li	10, 224
	lxvd2x	14+32, 10, 8	# H^4h
.endm

 #
 # aes_p10_gcm_encrypt (const void *inp, void *out, size_t len,
 #               const char *rk, unsigned char iv[16], void *Xip);
 #
 #    r3 - inp
 #    r4 - out
 #    r5 - len
 #    r6 - AES round keys
 #    r7 - iv and other data
 #    r8 - Xi, HPoli, hash keys
 #
 #    rounds is at offset 240 in rk
 #    Xi is at 0 in gcm_table (Xip).
 #
_GLOBAL(aes_p10_gcm_encrypt)
.align 5

	SAVE_REGS

	LOAD_HASH_TABLE

	# initialize ICB: GHASH( IV ), IV - r7
	lxvb16x	30+32, 0, 7	# load IV  - v30

	mr	12, 5		# length
	li	11, 0		# block index

	# counter 1
	vxor	31, 31, 31
	vspltisb 22, 1
	vsldoi	31, 31, 22,1	# counter 1

	# load round key to VSR
	lxv	0, 0(6)
	lxv	1, 0x10(6)
	lxv	2, 0x20(6)
	lxv	3, 0x30(6)
	lxv	4, 0x40(6)
	lxv	5, 0x50(6)
	lxv	6, 0x60(6)
	lxv	7, 0x70(6)
	lxv	8, 0x80(6)
	lxv	9, 0x90(6)
	lxv	10, 0xa0(6)

	# load rounds - 10 (128), 12 (192), 14 (256)
	lwz	9,240(6)

	#
	# vxor	state, state, w # addroundkey
	xxlor	32+29, 0, 0
	vxor	15, 30, 29	# IV + round key - add round key 0

	cmpdi	9, 10
	beq	Loop_aes_gcm_8x

	# load 2 more round keys (v11, v12)
	lxv	11, 0xb0(6)
	lxv	12, 0xc0(6)

	cmpdi	9, 12
	beq	Loop_aes_gcm_8x

	# load 2 more round keys (v11, v12, v13, v14)
	lxv	13, 0xd0(6)
	lxv	14, 0xe0(6)
	cmpdi	9, 14
	beq	Loop_aes_gcm_8x

	b	aes_gcm_out

.align 5
Loop_aes_gcm_8x:
	mr	14, 3
	mr	9, 4

	#
	# check partial block
	#
Continue_partial_check:
	ld	15, 56(7)
	cmpdi	15, 0
	beq	Continue
	bgt	Final_block
	cmpdi	15, 16
	blt	Final_block

Continue:
	# n blcoks
	li	10, 128
	divdu	10, 12, 10	# n 128 bytes-blocks
	cmpdi	10, 0
	beq	Loop_last_block

	vaddudm	30, 30, 31	# IV + counter
	vxor	16, 30, 29
	vaddudm	30, 30, 31
	vxor	17, 30, 29
	vaddudm	30, 30, 31
	vxor	18, 30, 29
	vaddudm	30, 30, 31
	vxor	19, 30, 29
	vaddudm	30, 30, 31
	vxor	20, 30, 29
	vaddudm	30, 30, 31
	vxor	21, 30, 29
	vaddudm	30, 30, 31
	vxor	22, 30, 29

	mtctr	10

	li	15, 16
	li	16, 32
	li	17, 48
	li	18, 64
	li	19, 80
	li	20, 96
	li	21, 112

	lwz	10, 240(6)

Loop_8x_block:

	lxvb16x		15, 0, 14	# load block
	lxvb16x		16, 15, 14	# load block
	lxvb16x		17, 16, 14	# load block
	lxvb16x		18, 17, 14	# load block
	lxvb16x		19, 18, 14	# load block
	lxvb16x		20, 19, 14	# load block
	lxvb16x		21, 20, 14	# load block
	lxvb16x		22, 21, 14	# load block
	addi		14, 14, 128

	Loop_aes_middle8x

	xxlor	23+32, 10, 10

	cmpdi	10, 10
	beq	Do_next_ghash

	# 192 bits
	xxlor	24+32, 11, 11

	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23

	vcipher	15, 15, 24
	vcipher	16, 16, 24
	vcipher	17, 17, 24
	vcipher	18, 18, 24
	vcipher	19, 19, 24
	vcipher	20, 20, 24
	vcipher	21, 21, 24
	vcipher	22, 22, 24

	xxlor	23+32, 12, 12

	cmpdi	10, 12
	beq	Do_next_ghash

	# 256 bits
	xxlor	24+32, 13, 13

	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23

	vcipher	15, 15, 24
	vcipher	16, 16, 24
	vcipher	17, 17, 24
	vcipher	18, 18, 24
	vcipher	19, 19, 24
	vcipher	20, 20, 24
	vcipher	21, 21, 24
	vcipher	22, 22, 24

	xxlor	23+32, 14, 14

	cmpdi	10, 14
	beq	Do_next_ghash
	b	aes_gcm_out

Do_next_ghash:

	#
	# last round
	vcipherlast     15, 15, 23
	vcipherlast     16, 16, 23

	xxlxor		47, 47, 15
	stxvb16x        47, 0, 9	# store output
	xxlxor		48, 48, 16
	stxvb16x        48, 15, 9	# store output

	vcipherlast     17, 17, 23
	vcipherlast     18, 18, 23

	xxlxor		49, 49, 17
	stxvb16x        49, 16, 9	# store output
	xxlxor		50, 50, 18
	stxvb16x        50, 17, 9	# store output

	vcipherlast     19, 19, 23
	vcipherlast     20, 20, 23

	xxlxor		51, 51, 19
	stxvb16x        51, 18, 9	# store output
	xxlxor		52, 52, 20
	stxvb16x        52, 19, 9	# store output

	vcipherlast     21, 21, 23
	vcipherlast     22, 22, 23

	xxlxor		53, 53, 21
	stxvb16x        53, 20, 9	# store output
	xxlxor		54, 54, 22
	stxvb16x        54, 21, 9	# store output

	addi		9, 9, 128

	# ghash here
	ppc_aes_gcm_ghash2_4x

	xxlor	27+32, 0, 0
	vaddudm 30, 30, 31		# IV + counter
	vmr	29, 30
	vxor    15, 30, 27		# add round key
	vaddudm 30, 30, 31
	vxor    16, 30, 27
	vaddudm 30, 30, 31
	vxor    17, 30, 27
	vaddudm 30, 30, 31
	vxor    18, 30, 27
	vaddudm 30, 30, 31
	vxor    19, 30, 27
	vaddudm 30, 30, 31
	vxor    20, 30, 27
	vaddudm 30, 30, 31
	vxor    21, 30, 27
	vaddudm 30, 30, 31
	vxor    22, 30, 27

	addi    12, 12, -128
	addi    11, 11, 128

	bdnz	Loop_8x_block

	vmr	30, 29
	stxvb16x 30+32, 0, 7		# update IV

Loop_last_block:
	cmpdi   12, 0
	beq     aes_gcm_out

	# loop last few blocks
	li      10, 16
	divdu   10, 12, 10

	mtctr   10

	lwz	10, 240(6)

	cmpdi   12, 16
	blt     Final_block

Next_rem_block:
	lxvb16x 15, 0, 14		# load block

	Loop_aes_middle_1x

	xxlor	23+32, 10, 10

	cmpdi	10, 10
	beq	Do_next_1x

	# 192 bits
	xxlor	24+32, 11, 11

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 12, 12

	cmpdi	10, 12
	beq	Do_next_1x

	# 256 bits
	xxlor	24+32, 13, 13

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 14, 14

	cmpdi	10, 14
	beq	Do_next_1x

Do_next_1x:
	vcipherlast     15, 15, 23

	xxlxor		47, 47, 15
	stxvb16x	47, 0, 9	# store output
	addi		14, 14, 16
	addi		9, 9, 16

	vmr		28, 15
	ppc_update_hash_1x

	addi		12, 12, -16
	addi		11, 11, 16
	xxlor		19+32, 0, 0
	vaddudm		30, 30, 31		# IV + counter
	vxor		15, 30, 19		# add round key

	bdnz	Next_rem_block

	li	15, 0
	std	15, 56(7)		# clear partial?
	stxvb16x 30+32, 0, 7		# update IV
	cmpdi	12, 0
	beq	aes_gcm_out

Final_block:
	lwz	10, 240(6)
	Loop_aes_middle_1x

	xxlor	23+32, 10, 10

	cmpdi	10, 10
	beq	Do_final_1x

	# 192 bits
	xxlor	24+32, 11, 11

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 12, 12

	cmpdi	10, 12
	beq	Do_final_1x

	# 256 bits
	xxlor	24+32, 13, 13

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 14, 14

	cmpdi	10, 14
	beq	Do_final_1x

Do_final_1x:
	vcipherlast     15, 15, 23

	# check partial block
	li	21, 0			# encrypt
	ld	15, 56(7)		# partial?
	cmpdi	15, 0
	beq	Normal_block
	bl	Do_partial_block

	cmpdi	12, 0
	ble aes_gcm_out

	b Continue_partial_check

Normal_block:
	lxvb16x	15, 0, 14		# load last block
	xxlxor	47, 47, 15

	# create partial block mask
	li	15, 16
	sub	15, 15, 12		# index to the mask

	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
	vspltisb	17, 0		# second 16 bytes - 0x0000...00
	li	10, 192
	stvx	16, 10, 1
	addi	10, 10, 16
	stvx	17, 10, 1

	addi	10, 1, 192
	lxvb16x	16, 15, 10		# load partial block mask
	xxland	47, 47, 16

	vmr	28, 15
	ppc_update_hash_1x

	# * should store only the remaining bytes.
	bl	Write_partial_block

	stxvb16x 30+32, 0, 7		# update IV
	std	12, 56(7)		# update partial?
	li	16, 16

	stxvb16x	32, 0, 8		# write out Xi
	stxvb16x	32, 16, 8		# write out Xi
	b aes_gcm_out

 #
 # Compute data mask
 #
.macro GEN_MASK _mask _start _end
	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
	vspltisb	17, 0		# second 16 bytes - 0x0000...00
	li	10, 192
	stxvb16x	17+32, 10, 1
	add	10, 10, \_start
	stxvb16x	16+32, 10, 1
	add	10, 10, \_end
	stxvb16x	17+32, 10, 1

	addi	10, 1, 192
	lxvb16x	\_mask, 0, 10		# load partial block mask
.endm

 #
 # Handle multiple partial blocks for encrypt and decrypt
 #   operations.
 #
SYM_FUNC_START_LOCAL(Do_partial_block)
	add	17, 15, 5
	cmpdi	17, 16
	bgt	Big_block
	GEN_MASK 18, 15, 5
	b	_Partial
SYM_FUNC_END(Do_partial_block)
Big_block:
	li	16, 16
	GEN_MASK 18, 15, 16

_Partial:
	lxvb16x	17+32, 0, 14		# load last block
	sldi	16, 15, 3
	mtvsrdd	32+16, 0, 16
	vsro	17, 17, 16
	xxlxor	47, 47, 17+32
	xxland	47, 47, 18

	vxor	0, 0, 0			# clear Xi
	vmr	28, 15

	cmpdi	21, 0			# encrypt/decrypt ops?
	beq	Skip_decrypt
	xxland	32+28, 32+17, 18

Skip_decrypt:

	ppc_update_hash_1x

	li	16, 16
	lxvb16x 32+29, 16, 8
	vxor	0, 0, 29
	stxvb16x 32, 0, 8		# save Xi
	stxvb16x 32, 16, 8		# save Xi

	# store partial block
	# loop the rest of the stream if any
	sldi	16, 15, 3
	mtvsrdd	32+16, 0, 16
	vslo	15, 15, 16
	#stxvb16x 15+32, 0, 9		# last block

	li	16, 16
	sub	17, 16, 15		# 16 - partial

	add	16, 15, 5
	cmpdi	16, 16
	bgt	Larger_16
	mr	17, 5
Larger_16:

	# write partial
	li		10, 192
	stxvb16x	15+32, 10, 1	# save current block

	addi		10, 9, -1
	addi		16, 1, 191
	mtctr		17		# move partial byte count

Write_last_partial:
        lbzu		18, 1(16)
	stbu		18, 1(10)
        bdnz		Write_last_partial
	# Complete loop partial

	add	14, 14, 17
	add	9, 9, 17
	sub	12, 12, 17
	add	11, 11, 17

	add	15, 15, 5
	cmpdi	15, 16
	blt	Save_partial

	vaddudm	30, 30, 31
	stxvb16x 30+32, 0, 7		# update IV
	xxlor	32+29, 0, 0
	vxor	15, 30, 29		# IV + round key - add round key 0
	li	15, 0
	std	15, 56(7)		# partial done - clear
	b	Partial_done
Save_partial:
	std	15, 56(7)		# partial

Partial_done:
	blr

 #
 # Write partial block
 # r9 - output
 # r12 - remaining bytes
 # v15 - partial input data
 #
SYM_FUNC_START_LOCAL(Write_partial_block)
	li		10, 192
	stxvb16x	15+32, 10, 1		# last block

	addi		10, 9, -1
	addi		16, 1, 191

        mtctr		12			# remaining bytes
	li		15, 0

Write_last_byte:
        lbzu		14, 1(16)
	stbu		14, 1(10)
        bdnz		Write_last_byte
	blr
SYM_FUNC_END(Write_partial_block)

aes_gcm_out:
	# out = state
	stxvb16x	32, 0, 8		# write out Xi
	add	3, 11, 12		# return count

	RESTORE_REGS
	blr

 #
 # 8x Decrypt
 #
_GLOBAL(aes_p10_gcm_decrypt)
.align 5

	SAVE_REGS

	LOAD_HASH_TABLE

	# initialize ICB: GHASH( IV ), IV - r7
	lxvb16x	30+32, 0, 7	# load IV  - v30

	mr	12, 5		# length
	li	11, 0		# block index

	# counter 1
	vxor	31, 31, 31
	vspltisb 22, 1
	vsldoi	31, 31, 22,1	# counter 1

	# load round key to VSR
	lxv	0, 0(6)
	lxv	1, 0x10(6)
	lxv	2, 0x20(6)
	lxv	3, 0x30(6)
	lxv	4, 0x40(6)
	lxv	5, 0x50(6)
	lxv	6, 0x60(6)
	lxv	7, 0x70(6)
	lxv	8, 0x80(6)
	lxv	9, 0x90(6)
	lxv	10, 0xa0(6)

	# load rounds - 10 (128), 12 (192), 14 (256)
	lwz	9,240(6)

	#
	# vxor	state, state, w # addroundkey
	xxlor	32+29, 0, 0
	vxor	15, 30, 29	# IV + round key - add round key 0

	cmpdi	9, 10
	beq	Loop_aes_gcm_8x_dec

	# load 2 more round keys (v11, v12)
	lxv	11, 0xb0(6)
	lxv	12, 0xc0(6)

	cmpdi	9, 12
	beq	Loop_aes_gcm_8x_dec

	# load 2 more round keys (v11, v12, v13, v14)
	lxv	13, 0xd0(6)
	lxv	14, 0xe0(6)
	cmpdi	9, 14
	beq	Loop_aes_gcm_8x_dec

	b	aes_gcm_out

.align 5
Loop_aes_gcm_8x_dec:
	mr	14, 3
	mr	9, 4

	#
	# check partial block
	#
Continue_partial_check_dec:
	ld	15, 56(7)
	cmpdi	15, 0
	beq	Continue_dec
	bgt	Final_block_dec
	cmpdi	15, 16
	blt	Final_block_dec

Continue_dec:
	# n blcoks
	li	10, 128
	divdu	10, 12, 10	# n 128 bytes-blocks
	cmpdi	10, 0
	beq	Loop_last_block_dec

	vaddudm	30, 30, 31	# IV + counter
	vxor	16, 30, 29
	vaddudm	30, 30, 31
	vxor	17, 30, 29
	vaddudm	30, 30, 31
	vxor	18, 30, 29
	vaddudm	30, 30, 31
	vxor	19, 30, 29
	vaddudm	30, 30, 31
	vxor	20, 30, 29
	vaddudm	30, 30, 31
	vxor	21, 30, 29
	vaddudm	30, 30, 31
	vxor	22, 30, 29

	mtctr	10

	li	15, 16
	li	16, 32
	li	17, 48
	li	18, 64
	li	19, 80
	li	20, 96
	li	21, 112

	lwz	10, 240(6)

Loop_8x_block_dec:

	lxvb16x		15, 0, 14	# load block
	lxvb16x		16, 15, 14	# load block
	lxvb16x		17, 16, 14	# load block
	lxvb16x		18, 17, 14	# load block
	lxvb16x		19, 18, 14	# load block
	lxvb16x		20, 19, 14	# load block
	lxvb16x		21, 20, 14	# load block
	lxvb16x		22, 21, 14	# load block
	addi		14, 14, 128

	Loop_aes_middle8x

	xxlor	23+32, 10, 10

	cmpdi	10, 10
	beq	Do_next_ghash_dec

	# 192 bits
	xxlor	24+32, 11, 11

	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23

	vcipher	15, 15, 24
	vcipher	16, 16, 24
	vcipher	17, 17, 24
	vcipher	18, 18, 24
	vcipher	19, 19, 24
	vcipher	20, 20, 24
	vcipher	21, 21, 24
	vcipher	22, 22, 24

	xxlor	23+32, 12, 12

	cmpdi	10, 12
	beq	Do_next_ghash_dec

	# 256 bits
	xxlor	24+32, 13, 13

	vcipher	15, 15, 23
	vcipher	16, 16, 23
	vcipher	17, 17, 23
	vcipher	18, 18, 23
	vcipher	19, 19, 23
	vcipher	20, 20, 23
	vcipher	21, 21, 23
	vcipher	22, 22, 23

	vcipher	15, 15, 24
	vcipher	16, 16, 24
	vcipher	17, 17, 24
	vcipher	18, 18, 24
	vcipher	19, 19, 24
	vcipher	20, 20, 24
	vcipher	21, 21, 24
	vcipher	22, 22, 24

	xxlor	23+32, 14, 14

	cmpdi	10, 14
	beq	Do_next_ghash_dec
	b	aes_gcm_out

Do_next_ghash_dec:

	#
	# last round
	vcipherlast     15, 15, 23
	vcipherlast     16, 16, 23

	xxlxor		47, 47, 15
	stxvb16x        47, 0, 9	# store output
	xxlxor		48, 48, 16
	stxvb16x        48, 15, 9	# store output

	vcipherlast     17, 17, 23
	vcipherlast     18, 18, 23

	xxlxor		49, 49, 17
	stxvb16x        49, 16, 9	# store output
	xxlxor		50, 50, 18
	stxvb16x        50, 17, 9	# store output

	vcipherlast     19, 19, 23
	vcipherlast     20, 20, 23

	xxlxor		51, 51, 19
	stxvb16x        51, 18, 9	# store output
	xxlxor		52, 52, 20
	stxvb16x        52, 19, 9	# store output

	vcipherlast     21, 21, 23
	vcipherlast     22, 22, 23

	xxlxor		53, 53, 21
	stxvb16x        53, 20, 9	# store output
	xxlxor		54, 54, 22
	stxvb16x        54, 21, 9	# store output

	addi		9, 9, 128

	xxlor           15+32, 15, 15
	xxlor           16+32, 16, 16
	xxlor           17+32, 17, 17
	xxlor           18+32, 18, 18
	xxlor           19+32, 19, 19
	xxlor           20+32, 20, 20
	xxlor           21+32, 21, 21
	xxlor           22+32, 22, 22

	# ghash here
	ppc_aes_gcm_ghash2_4x

	xxlor	27+32, 0, 0
	vaddudm 30, 30, 31		# IV + counter
	vmr	29, 30
	vxor    15, 30, 27		# add round key
	vaddudm 30, 30, 31
	vxor    16, 30, 27
	vaddudm 30, 30, 31
	vxor    17, 30, 27
	vaddudm 30, 30, 31
	vxor    18, 30, 27
	vaddudm 30, 30, 31
	vxor    19, 30, 27
	vaddudm 30, 30, 31
	vxor    20, 30, 27
	vaddudm 30, 30, 31
	vxor    21, 30, 27
	vaddudm 30, 30, 31
	vxor    22, 30, 27

	addi    12, 12, -128
	addi    11, 11, 128

	bdnz	Loop_8x_block_dec

	vmr	30, 29
	stxvb16x 30+32, 0, 7		# update IV

Loop_last_block_dec:
	cmpdi   12, 0
	beq     aes_gcm_out

	# loop last few blocks
	li      10, 16
	divdu   10, 12, 10

	mtctr   10

	lwz	10, 240(6)

	cmpdi   12, 16
	blt     Final_block_dec

Next_rem_block_dec:
	lxvb16x 15, 0, 14		# load block

	Loop_aes_middle_1x

	xxlor	23+32, 10, 10

	cmpdi	10, 10
	beq	Do_next_1x_dec

	# 192 bits
	xxlor	24+32, 11, 11

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 12, 12

	cmpdi	10, 12
	beq	Do_next_1x_dec

	# 256 bits
	xxlor	24+32, 13, 13

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 14, 14

	cmpdi	10, 14
	beq	Do_next_1x_dec

Do_next_1x_dec:
	vcipherlast     15, 15, 23

	xxlxor		47, 47, 15
	stxvb16x	47, 0, 9	# store output
	addi		14, 14, 16
	addi		9, 9, 16

	xxlor           28+32, 15, 15
	#vmr		28, 15
	ppc_update_hash_1x

	addi		12, 12, -16
	addi		11, 11, 16
	xxlor		19+32, 0, 0
	vaddudm		30, 30, 31		# IV + counter
	vxor		15, 30, 19		# add round key

	bdnz	Next_rem_block_dec

	li	15, 0
	std	15, 56(7)		# clear partial?
	stxvb16x 30+32, 0, 7		# update IV
	cmpdi	12, 0
	beq	aes_gcm_out

Final_block_dec:
	lwz	10, 240(6)
	Loop_aes_middle_1x

	xxlor	23+32, 10, 10

	cmpdi	10, 10
	beq	Do_final_1x_dec

	# 192 bits
	xxlor	24+32, 11, 11

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 12, 12

	cmpdi	10, 12
	beq	Do_final_1x_dec

	# 256 bits
	xxlor	24+32, 13, 13

	vcipher	15, 15, 23
	vcipher	15, 15, 24

	xxlor	23+32, 14, 14

	cmpdi	10, 14
	beq	Do_final_1x_dec

Do_final_1x_dec:
	vcipherlast     15, 15, 23

	# check partial block
	li	21, 1			# decrypt
	ld	15, 56(7)		# partial?
	cmpdi	15, 0
	beq	Normal_block_dec
	bl	Do_partial_block
	cmpdi	12, 0
	ble aes_gcm_out

	b Continue_partial_check_dec

Normal_block_dec:
	lxvb16x	15, 0, 14		# load last block
	xxlxor	47, 47, 15

	# create partial block mask
	li	15, 16
	sub	15, 15, 12		# index to the mask

	vspltisb	16, -1		# first 16 bytes - 0xffff...ff
	vspltisb	17, 0		# second 16 bytes - 0x0000...00
	li	10, 192
	stvx	16, 10, 1
	addi	10, 10, 16
	stvx	17, 10, 1

	addi	10, 1, 192
	lxvb16x	16, 15, 10		# load partial block mask
	xxland	47, 47, 16

	xxland	32+28, 15, 16
	#vmr	28, 15
	ppc_update_hash_1x

	# * should store only the remaining bytes.
	bl	Write_partial_block

	stxvb16x 30+32, 0, 7		# update IV
	std	12, 56(7)		# update partial?
	li	16, 16

	stxvb16x	32, 0, 8		# write out Xi
	stxvb16x	32, 16, 8		# write out Xi
	b aes_gcm_out