summaryrefslogtreecommitdiff
path: root/arch/x86/crypto/aesni-intel_asm.S
blob: d528fde219d2d2bc189eacdd8ff2a38beb4438d4 (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
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
/*
 * Implement AES algorithm in Intel AES-NI instructions.
 *
 * The white paper of AES-NI instructions can be downloaded from:
 *   http://softwarecommunity.intel.com/isn/downloads/intelavx/AES-Instructions-Set_WP.pdf
 *
 * Copyright (C) 2008, Intel Corp.
 *    Author: Huang Ying <ying.huang@intel.com>
 *            Vinodh Gopal <vinodh.gopal@intel.com>
 *            Kahraman Akdemir
 *
 * Added RFC4106 AES-GCM support for 128-bit keys under the AEAD
 * interface for 64-bit kernels.
 *    Authors: Erdinc Ozturk (erdinc.ozturk@intel.com)
 *             Aidan O'Mahony (aidan.o.mahony@intel.com)
 *             Adrian Hoban <adrian.hoban@intel.com>
 *             James Guilford (james.guilford@intel.com)
 *             Gabriele Paoloni <gabriele.paoloni@intel.com>
 *             Tadeusz Struk (tadeusz.struk@intel.com)
 *             Wajdi Feghali (wajdi.k.feghali@intel.com)
 *    Copyright (c) 2010, Intel Corporation.
 *
 * Ported x86_64 version to x86:
 *    Author: Mathias Krause <minipli@googlemail.com>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 */

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

#ifdef __x86_64__
.data
POLY:   .octa 0xC2000000000000000000000000000001
TWOONE: .octa 0x00000001000000000000000000000001

# order of these constants should not change.
# more specifically, ALL_F should follow SHIFT_MASK,
# and ZERO should follow ALL_F

SHUF_MASK:  .octa 0x000102030405060708090A0B0C0D0E0F
MASK1:      .octa 0x0000000000000000ffffffffffffffff
MASK2:      .octa 0xffffffffffffffff0000000000000000
SHIFT_MASK: .octa 0x0f0e0d0c0b0a09080706050403020100
ALL_F:      .octa 0xffffffffffffffffffffffffffffffff
ZERO:       .octa 0x00000000000000000000000000000000
ONE:        .octa 0x00000000000000000000000000000001
F_MIN_MASK: .octa 0xf1f2f3f4f5f6f7f8f9fafbfcfdfeff0
dec:        .octa 0x1
enc:        .octa 0x2


.text


#define	STACK_OFFSET    8*3
#define	HashKey		16*0	// store HashKey <<1 mod poly here
#define	HashKey_2	16*1	// store HashKey^2 <<1 mod poly here
#define	HashKey_3	16*2	// store HashKey^3 <<1 mod poly here
#define	HashKey_4	16*3	// store HashKey^4 <<1 mod poly here
#define	HashKey_k	16*4	// store XOR of High 64 bits and Low 64
				// bits of  HashKey <<1 mod poly here
				//(for Karatsuba purposes)
#define	HashKey_2_k	16*5	// store XOR of High 64 bits and Low 64
				// bits of  HashKey^2 <<1 mod poly here
				// (for Karatsuba purposes)
#define	HashKey_3_k	16*6	// store XOR of High 64 bits and Low 64
				// bits of  HashKey^3 <<1 mod poly here
				// (for Karatsuba purposes)
#define	HashKey_4_k	16*7	// store XOR of High 64 bits and Low 64
				// bits of  HashKey^4 <<1 mod poly here
				// (for Karatsuba purposes)
#define	VARIABLE_OFFSET	16*8

#define arg1 rdi
#define arg2 rsi
#define arg3 rdx
#define arg4 rcx
#define arg5 r8
#define arg6 r9
#define arg7 STACK_OFFSET+8(%r14)
#define arg8 STACK_OFFSET+16(%r14)
#define arg9 STACK_OFFSET+24(%r14)
#define arg10 STACK_OFFSET+32(%r14)
#endif


#define STATE1	%xmm0
#define STATE2	%xmm4
#define STATE3	%xmm5
#define STATE4	%xmm6
#define STATE	STATE1
#define IN1	%xmm1
#define IN2	%xmm7
#define IN3	%xmm8
#define IN4	%xmm9
#define IN	IN1
#define KEY	%xmm2
#define IV	%xmm3

#define BSWAP_MASK %xmm10
#define CTR	%xmm11
#define INC	%xmm12

#ifdef __x86_64__
#define AREG	%rax
#define KEYP	%rdi
#define OUTP	%rsi
#define UKEYP	OUTP
#define INP	%rdx
#define LEN	%rcx
#define IVP	%r8
#define KLEN	%r9d
#define T1	%r10
#define TKEYP	T1
#define T2	%r11
#define TCTR_LOW T2
#else
#define AREG	%eax
#define KEYP	%edi
#define OUTP	AREG
#define UKEYP	OUTP
#define INP	%edx
#define LEN	%esi
#define IVP	%ebp
#define KLEN	%ebx
#define T1	%ecx
#define TKEYP	T1
#endif


#ifdef __x86_64__
/* GHASH_MUL MACRO to implement: Data*HashKey mod (128,127,126,121,0)
*
*
* Input: A and B (128-bits each, bit-reflected)
* Output: C = A*B*x mod poly, (i.e. >>1 )
* To compute GH = GH*HashKey mod poly, give HK = HashKey<<1 mod poly as input
* GH = GH * HK * x mod poly which is equivalent to GH*HashKey mod poly.
*
*/
.macro GHASH_MUL GH HK TMP1 TMP2 TMP3 TMP4 TMP5
	movdqa	  \GH, \TMP1
	pshufd	  $78, \GH, \TMP2
	pshufd	  $78, \HK, \TMP3
	pxor	  \GH, \TMP2            # TMP2 = a1+a0
	pxor	  \HK, \TMP3            # TMP3 = b1+b0
	PCLMULQDQ 0x11, \HK, \TMP1     # TMP1 = a1*b1
	PCLMULQDQ 0x00, \HK, \GH       # GH = a0*b0
	PCLMULQDQ 0x00, \TMP3, \TMP2   # TMP2 = (a0+a1)*(b1+b0)
	pxor	  \GH, \TMP2
	pxor	  \TMP1, \TMP2          # TMP2 = (a0*b0)+(a1*b0)
	movdqa	  \TMP2, \TMP3
	pslldq	  $8, \TMP3             # left shift TMP3 2 DWs
	psrldq	  $8, \TMP2             # right shift TMP2 2 DWs
	pxor	  \TMP3, \GH
	pxor	  \TMP2, \TMP1          # TMP2:GH holds the result of GH*HK

        # first phase of the reduction

	movdqa    \GH, \TMP2
	movdqa    \GH, \TMP3
	movdqa    \GH, \TMP4            # copy GH into TMP2,TMP3 and TMP4
					# in in order to perform
					# independent shifts
	pslld     $31, \TMP2            # packed right shift <<31
	pslld     $30, \TMP3            # packed right shift <<30
	pslld     $25, \TMP4            # packed right shift <<25
	pxor      \TMP3, \TMP2          # xor the shifted versions
	pxor      \TMP4, \TMP2
	movdqa    \TMP2, \TMP5
	psrldq    $4, \TMP5             # right shift TMP5 1 DW
	pslldq    $12, \TMP2            # left shift TMP2 3 DWs
	pxor      \TMP2, \GH

        # second phase of the reduction

	movdqa    \GH,\TMP2             # copy GH into TMP2,TMP3 and TMP4
					# in in order to perform
					# independent shifts
	movdqa    \GH,\TMP3
	movdqa    \GH,\TMP4
	psrld     $1,\TMP2              # packed left shift >>1
	psrld     $2,\TMP3              # packed left shift >>2
	psrld     $7,\TMP4              # packed left shift >>7
	pxor      \TMP3,\TMP2		# xor the shifted versions
	pxor      \TMP4,\TMP2
	pxor      \TMP5, \TMP2
	pxor      \TMP2, \GH
	pxor      \TMP1, \GH            # result is in TMP1
.endm

/*
* if a = number of total plaintext bytes
* b = floor(a/16)
* num_initial_blocks = b mod 4
* encrypt the initial num_initial_blocks blocks and apply ghash on
* the ciphertext
* %r10, %r11, %r12, %rax, %xmm5, %xmm6, %xmm7, %xmm8, %xmm9 registers
* are clobbered
* arg1, %arg2, %arg3, %r14 are used as a pointer only, not modified
*/

.macro INITIAL_BLOCKS num_initial_blocks TMP1 TMP2 TMP3 TMP4 TMP5 XMM0 XMM1 \
XMM2 XMM3 XMM4 XMMDst TMP6 TMP7 i i_seq operation

	mov	   arg7, %r10           # %r10 = AAD
	mov	   arg8, %r12           # %r12 = aadLen
	mov	   %r12, %r11
	pxor	   %xmm\i, %xmm\i
_get_AAD_loop\num_initial_blocks\operation:
	movd	   (%r10), \TMP1
	pslldq	   $12, \TMP1
	psrldq	   $4, %xmm\i
	pxor	   \TMP1, %xmm\i
	add	   $4, %r10
	sub	   $4, %r12
	jne	   _get_AAD_loop\num_initial_blocks\operation
	cmp	   $16, %r11
	je	   _get_AAD_loop2_done\num_initial_blocks\operation
	mov	   $16, %r12
_get_AAD_loop2\num_initial_blocks\operation:
	psrldq	   $4, %xmm\i
	sub	   $4, %r12
	cmp	   %r11, %r12
	jne	   _get_AAD_loop2\num_initial_blocks\operation
_get_AAD_loop2_done\num_initial_blocks\operation:
	pshufb	   SHUF_MASK(%rip), %xmm\i # byte-reflect the AAD data
	xor	   %r11, %r11 # initialise the data pointer offset as zero

        # start AES for num_initial_blocks blocks

	mov	   %arg5, %rax                      # %rax = *Y0
	movdqu	   (%rax), \XMM0                    # XMM0 = Y0
	pshufb	   SHUF_MASK(%rip), \XMM0
.if \i_seq != 0
.irpc index, \i_seq
	paddd	   ONE(%rip), \XMM0                 # INCR Y0
	movdqa	   \XMM0, %xmm\index
	pshufb	   SHUF_MASK(%rip), %xmm\index      # perform a 16 byte swap
.endr
.irpc index, \i_seq
	pxor	   16*0(%arg1), %xmm\index
.endr
.irpc index, \i_seq
	movaps 0x10(%rdi), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 1
.endr
.irpc index, \i_seq
	movaps 0x20(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x30(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x40(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x50(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x60(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x70(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x80(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0x90(%arg1), \TMP1
	AESENC     \TMP1, %xmm\index          # Round 2
.endr
.irpc index, \i_seq
	movaps 0xa0(%arg1), \TMP1
	AESENCLAST \TMP1, %xmm\index         # Round 10
.endr
.irpc index, \i_seq
	movdqu	   (%arg3 , %r11, 1), \TMP1
	pxor	   \TMP1, %xmm\index
	movdqu	   %xmm\index, (%arg2 , %r11, 1)
	# write back plaintext/ciphertext for num_initial_blocks
	add	   $16, %r11
.if \operation == dec
	movdqa     \TMP1, %xmm\index
.endif
	pshufb	   SHUF_MASK(%rip), %xmm\index
		# prepare plaintext/ciphertext for GHASH computation
.endr
.endif
	GHASH_MUL  %xmm\i, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
        # apply GHASH on num_initial_blocks blocks

.if \i == 5
        pxor       %xmm5, %xmm6
	GHASH_MUL  %xmm6, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
        pxor       %xmm6, %xmm7
	GHASH_MUL  %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
        pxor       %xmm7, %xmm8
	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.elseif \i == 6
        pxor       %xmm6, %xmm7
	GHASH_MUL  %xmm7, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
        pxor       %xmm7, %xmm8
	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.elseif \i == 7
        pxor       %xmm7, %xmm8
	GHASH_MUL  %xmm8, \TMP3, \TMP1, \TMP2, \TMP4, \TMP5, \XMM1
.endif
	cmp	   $64, %r13
	jl	_initial_blocks_done\num_initial_blocks\operation
	# no need for precomputed values
/*
*
* Precomputations for HashKey parallel with encryption of first 4 blocks.
* Haskey_i_k holds XORed values of the low and high parts of the Haskey_i
*/
	paddd	   ONE(%rip), \XMM0              # INCR Y0
	movdqa	   \XMM0, \XMM1
	pshufb	   SHUF_MASK(%rip), \XMM1        # perform a 16 byte swap
	paddd	   ONE(%rip), \XMM0              # INCR Y0
	movdqa	   \XMM0, \XMM2
	pshufb	   SHUF_MASK(%rip), \XMM2        # perform a 16 byte swap
	paddd	   ONE(%rip), \XMM0              # INCR Y0
	movdqa	   \XMM0, \XMM3
	pshufb	   SHUF_MASK(%rip), \XMM3        # perform a 16 byte swap
	paddd	   ONE(%rip), \XMM0              # INCR Y0
	movdqa	   \XMM0, \XMM4
	pshufb	   SHUF_MASK(%rip), \XMM4        # perform a 16 byte swap
	pxor	   16*0(%arg1), \XMM1
	pxor	   16*0(%arg1), \XMM2
	pxor	   16*0(%arg1), \XMM3
	pxor	   16*0(%arg1), \XMM4
	movdqa	   \TMP3, \TMP5
	pshufd	   $78, \TMP3, \TMP1
	pxor	   \TMP3, \TMP1
	movdqa	   \TMP1, HashKey_k(%rsp)
	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^2<<1 (mod poly)
	movdqa	   \TMP5, HashKey_2(%rsp)
# HashKey_2 = HashKey^2<<1 (mod poly)
	pshufd	   $78, \TMP5, \TMP1
	pxor	   \TMP5, \TMP1
	movdqa	   \TMP1, HashKey_2_k(%rsp)
.irpc index, 1234 # do 4 rounds
	movaps 0x10*\index(%arg1), \TMP1
	AESENC	   \TMP1, \XMM1
	AESENC	   \TMP1, \XMM2
	AESENC	   \TMP1, \XMM3
	AESENC	   \TMP1, \XMM4
.endr
	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
	movdqa	   \TMP5, HashKey_3(%rsp)
	pshufd	   $78, \TMP5, \TMP1
	pxor	   \TMP5, \TMP1
	movdqa	   \TMP1, HashKey_3_k(%rsp)
.irpc index, 56789 # do next 5 rounds
	movaps 0x10*\index(%arg1), \TMP1
	AESENC	   \TMP1, \XMM1
	AESENC	   \TMP1, \XMM2
	AESENC	   \TMP1, \XMM3
	AESENC	   \TMP1, \XMM4
.endr
	GHASH_MUL  \TMP5, \TMP3, \TMP1, \TMP2, \TMP4, \TMP6, \TMP7
# TMP5 = HashKey^3<<1 (mod poly)
	movdqa	   \TMP5, HashKey_4(%rsp)
	pshufd	   $78, \TMP5, \TMP1
	pxor	   \TMP5, \TMP1
	movdqa	   \TMP1, HashKey_4_k(%rsp)
	movaps 0xa0(%arg1), \TMP2
	AESENCLAST \TMP2, \XMM1
	AESENCLAST \TMP2, \XMM2
	AESENCLAST \TMP2, \XMM3
	AESENCLAST \TMP2, \XMM4
	movdqu	   16*0(%arg3 , %r11 , 1), \TMP1
	pxor	   \TMP1, \XMM1
.if \operation == dec
	movdqu	   \XMM1, 16*0(%arg2 , %r11 , 1)
	movdqa     \TMP1, \XMM1
.endif
	movdqu	   16*1(%arg3 , %r11 , 1), \TMP1
	pxor	   \TMP1, \XMM2
.if \operation == dec
	movdqu	   \XMM2, 16*1(%arg2 , %r11 , 1)
	movdqa     \TMP1, \XMM2
.endif
	movdqu	   16*2(%arg3 , %r11 , 1), \TMP1
	pxor	   \TMP1, \XMM3
.if \operation == dec
	movdqu	   \XMM3, 16*2(%arg2 , %r11 , 1)
	movdqa     \TMP1, \XMM3
.endif
	movdqu	   16*3(%arg3 , %r11 , 1), \TMP1
	pxor	   \TMP1, \XMM4
.if \operation == dec
	movdqu	   \XMM4, 16*3(%arg2 , %r11 , 1)
	movdqa     \TMP1, \XMM4
.else
	movdqu     \XMM1, 16*0(%arg2 , %r11 , 1)
	movdqu     \XMM2, 16*1(%arg2 , %r11 , 1)
	movdqu     \XMM3, 16*2(%arg2 , %r11 , 1)
	movdqu     \XMM4, 16*3(%arg2 , %r11 , 1)
.endif
	add	   $64, %r11
	pshufb	   SHUF_MASK(%rip), \XMM1 # perform a 16 byte swap
	pxor	   \XMMDst, \XMM1
# combine GHASHed value with the corresponding ciphertext
	pshufb	   SHUF_MASK(%rip), \XMM2 # perform a 16 byte swap
	pshufb	   SHUF_MASK(%rip), \XMM3 # perform a 16 byte swap
	pshufb	   SHUF_MASK(%rip), \XMM4 # perform a 16 byte swap
_initial_blocks_done\num_initial_blocks\operation:
.endm

/*
* encrypt 4 blocks at a time
* ghash the 4 previously encrypted ciphertext blocks
* arg1, %arg2, %arg3 are used as pointers only, not modified
* %r11 is the data offset value
*/
.macro GHASH_4_ENCRYPT_4_PARALLEL TMP1 TMP2 TMP3 TMP4 TMP5 \
TMP6 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 operation

	movdqa	  \XMM1, \XMM5
	movdqa	  \XMM2, \XMM6
	movdqa	  \XMM3, \XMM7
	movdqa	  \XMM4, \XMM8

        # multiply TMP5 * HashKey using karatsuba

	movdqa	  \XMM5, \TMP4
	pshufd	  $78, \XMM5, \TMP6
	pxor	  \XMM5, \TMP6
	paddd     ONE(%rip), \XMM0		# INCR CNT
	movdqa	  HashKey_4(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP4           # TMP4 = a1*b1
	movdqa    \XMM0, \XMM1
	paddd     ONE(%rip), \XMM0		# INCR CNT
	movdqa    \XMM0, \XMM2
	paddd     ONE(%rip), \XMM0		# INCR CNT
	movdqa    \XMM0, \XMM3
	paddd     ONE(%rip), \XMM0		# INCR CNT
	movdqa    \XMM0, \XMM4
	pshufb	  SHUF_MASK(%rip), \XMM1	# perform a 16 byte swap
	PCLMULQDQ 0x00, \TMP5, \XMM5           # XMM5 = a0*b0
	pshufb	  SHUF_MASK(%rip), \XMM2	# perform a 16 byte swap
	pshufb	  SHUF_MASK(%rip), \XMM3	# perform a 16 byte swap
	pshufb	  SHUF_MASK(%rip), \XMM4	# perform a 16 byte swap
	pxor	  (%arg1), \XMM1
	pxor	  (%arg1), \XMM2
	pxor	  (%arg1), \XMM3
	pxor	  (%arg1), \XMM4
	movdqa	  HashKey_4_k(%rsp), \TMP5
	PCLMULQDQ 0x00, \TMP5, \TMP6           # TMP6 = (a1+a0)*(b1+b0)
	movaps 0x10(%arg1), \TMP1
	AESENC	  \TMP1, \XMM1              # Round 1
	AESENC	  \TMP1, \XMM2
	AESENC	  \TMP1, \XMM3
	AESENC	  \TMP1, \XMM4
	movaps 0x20(%arg1), \TMP1
	AESENC	  \TMP1, \XMM1              # Round 2
	AESENC	  \TMP1, \XMM2
	AESENC	  \TMP1, \XMM3
	AESENC	  \TMP1, \XMM4
	movdqa	  \XMM6, \TMP1
	pshufd	  $78, \XMM6, \TMP2
	pxor	  \XMM6, \TMP2
	movdqa	  HashKey_3(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1 * b1
	movaps 0x30(%arg1), \TMP3
	AESENC    \TMP3, \XMM1              # Round 3
	AESENC    \TMP3, \XMM2
	AESENC    \TMP3, \XMM3
	AESENC    \TMP3, \XMM4
	PCLMULQDQ 0x00, \TMP5, \XMM6           # XMM6 = a0*b0
	movaps 0x40(%arg1), \TMP3
	AESENC	  \TMP3, \XMM1              # Round 4
	AESENC	  \TMP3, \XMM2
	AESENC	  \TMP3, \XMM3
	AESENC	  \TMP3, \XMM4
	movdqa	  HashKey_3_k(%rsp), \TMP5
	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
	movaps 0x50(%arg1), \TMP3
	AESENC	  \TMP3, \XMM1              # Round 5
	AESENC	  \TMP3, \XMM2
	AESENC	  \TMP3, \XMM3
	AESENC	  \TMP3, \XMM4
	pxor	  \TMP1, \TMP4
# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
	pxor	  \XMM6, \XMM5
	pxor	  \TMP2, \TMP6
	movdqa	  \XMM7, \TMP1
	pshufd	  $78, \XMM7, \TMP2
	pxor	  \XMM7, \TMP2
	movdqa	  HashKey_2(%rsp ), \TMP5

        # Multiply TMP5 * HashKey using karatsuba

	PCLMULQDQ 0x11, \TMP5, \TMP1           # TMP1 = a1*b1
	movaps 0x60(%arg1), \TMP3
	AESENC	  \TMP3, \XMM1              # Round 6
	AESENC	  \TMP3, \XMM2
	AESENC	  \TMP3, \XMM3
	AESENC	  \TMP3, \XMM4
	PCLMULQDQ 0x00, \TMP5, \XMM7           # XMM7 = a0*b0
	movaps 0x70(%arg1), \TMP3
	AESENC	  \TMP3, \XMM1             # Round 7
	AESENC	  \TMP3, \XMM2
	AESENC	  \TMP3, \XMM3
	AESENC	  \TMP3, \XMM4
	movdqa	  HashKey_2_k(%rsp), \TMP5
	PCLMULQDQ 0x00, \TMP5, \TMP2           # TMP2 = (a1+a0)*(b1+b0)
	movaps 0x80(%arg1), \TMP3
	AESENC	  \TMP3, \XMM1             # Round 8
	AESENC	  \TMP3, \XMM2
	AESENC	  \TMP3, \XMM3
	AESENC	  \TMP3, \XMM4
	pxor	  \TMP1, \TMP4
# accumulate the results in TMP4:XMM5, TMP6 holds the middle part
	pxor	  \XMM7, \XMM5
	pxor	  \TMP2, \TMP6

        # Multiply XMM8 * HashKey
        # XMM8 and TMP5 hold the values for the two operands

	movdqa	  \XMM8, \TMP1
	pshufd	  $78, \XMM8, \TMP2
	pxor	  \XMM8, \TMP2
	movdqa	  HashKey(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP1          # TMP1 = a1*b1
	movaps 0x90(%arg1), \TMP3
	AESENC	  \TMP3, \XMM1            # Round 9
	AESENC	  \TMP3, \XMM2
	AESENC	  \TMP3, \XMM3
	AESENC	  \TMP3, \XMM4
	PCLMULQDQ 0x00, \TMP5, \XMM8          # XMM8 = a0*b0
	movaps 0xa0(%arg1), \TMP3
	AESENCLAST \TMP3, \XMM1           # Round 10
	AESENCLAST \TMP3, \XMM2
	AESENCLAST \TMP3, \XMM3
	AESENCLAST \TMP3, \XMM4
	movdqa    HashKey_k(%rsp), \TMP5
	PCLMULQDQ 0x00, \TMP5, \TMP2          # TMP2 = (a1+a0)*(b1+b0)
	movdqu	  (%arg3,%r11,1), \TMP3
	pxor	  \TMP3, \XMM1                 # Ciphertext/Plaintext XOR EK
.if \operation == dec
	movdqu	  \XMM1, (%arg2,%r11,1)        # Write to plaintext buffer
	movdqa    \TMP3, \XMM1
.endif
	movdqu	  16(%arg3,%r11,1), \TMP3
	pxor	  \TMP3, \XMM2                 # Ciphertext/Plaintext XOR EK
.if \operation == dec
	movdqu	  \XMM2, 16(%arg2,%r11,1)      # Write to plaintext buffer
	movdqa    \TMP3, \XMM2
.endif
	movdqu	  32(%arg3,%r11,1), \TMP3
	pxor	  \TMP3, \XMM3                 # Ciphertext/Plaintext XOR EK
.if \operation == dec
	movdqu	  \XMM3, 32(%arg2,%r11,1)      # Write to plaintext buffer
	movdqa    \TMP3, \XMM3
.endif
	movdqu	  48(%arg3,%r11,1), \TMP3
	pxor	  \TMP3, \XMM4                 # Ciphertext/Plaintext XOR EK
.if \operation == dec
	movdqu	  \XMM4, 48(%arg2,%r11,1)      # Write to plaintext buffer
	movdqa    \TMP3, \XMM4
.else
    movdqu    \XMM1, (%arg2,%r11,1)        # Write to the ciphertext buffer
    movdqu    \XMM2, 16(%arg2,%r11,1)      # Write to the ciphertext buffer
    movdqu    \XMM3, 32(%arg2,%r11,1)      # Write to the ciphertext buffer
    movdqu    \XMM4, 48(%arg2,%r11,1)      # Write to the ciphertext buffer
.endif
	pshufb	  SHUF_MASK(%rip), \XMM1       # perform a 16 byte swap
	pshufb	  SHUF_MASK(%rip), \XMM2       # perform a 16 byte swap
	pshufb	  SHUF_MASK(%rip), \XMM3       # perform a 16 byte swap
	pshufb	  SHUF_MASK(%rip), \XMM4       # perform a 16 byte sway

	pxor	  \TMP4, \TMP1
	pxor	  \XMM8, \XMM5
	pxor	  \TMP6, \TMP2
	pxor	  \TMP1, \TMP2
	pxor	  \XMM5, \TMP2
	movdqa	  \TMP2, \TMP3
	pslldq	  $8, \TMP3                    # left shift TMP3 2 DWs
	psrldq	  $8, \TMP2                    # right shift TMP2 2 DWs
	pxor	  \TMP3, \XMM5
	pxor	  \TMP2, \TMP1	  # accumulate the results in TMP1:XMM5

        # first phase of reduction

	movdqa    \XMM5, \TMP2
	movdqa    \XMM5, \TMP3
	movdqa    \XMM5, \TMP4
# move XMM5 into TMP2, TMP3, TMP4 in order to perform shifts independently
	pslld     $31, \TMP2                   # packed right shift << 31
	pslld     $30, \TMP3                   # packed right shift << 30
	pslld     $25, \TMP4                   # packed right shift << 25
	pxor      \TMP3, \TMP2	               # xor the shifted versions
	pxor      \TMP4, \TMP2
	movdqa    \TMP2, \TMP5
	psrldq    $4, \TMP5                    # right shift T5 1 DW
	pslldq    $12, \TMP2                   # left shift T2 3 DWs
	pxor      \TMP2, \XMM5

        # second phase of reduction

	movdqa    \XMM5,\TMP2 # make 3 copies of XMM5 into TMP2, TMP3, TMP4
	movdqa    \XMM5,\TMP3
	movdqa    \XMM5,\TMP4
	psrld     $1, \TMP2                    # packed left shift >>1
	psrld     $2, \TMP3                    # packed left shift >>2
	psrld     $7, \TMP4                    # packed left shift >>7
	pxor      \TMP3,\TMP2		       # xor the shifted versions
	pxor      \TMP4,\TMP2
	pxor      \TMP5, \TMP2
	pxor      \TMP2, \XMM5
	pxor      \TMP1, \XMM5                 # result is in TMP1

	pxor	  \XMM5, \XMM1
.endm

/* GHASH the last 4 ciphertext blocks. */
.macro	GHASH_LAST_4 TMP1 TMP2 TMP3 TMP4 TMP5 TMP6 \
TMP7 XMM1 XMM2 XMM3 XMM4 XMMDst

        # Multiply TMP6 * HashKey (using Karatsuba)

	movdqa	  \XMM1, \TMP6
	pshufd	  $78, \XMM1, \TMP2
	pxor	  \XMM1, \TMP2
	movdqa	  HashKey_4(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP6       # TMP6 = a1*b1
	PCLMULQDQ 0x00, \TMP5, \XMM1       # XMM1 = a0*b0
	movdqa	  HashKey_4_k(%rsp), \TMP4
	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
	movdqa	  \XMM1, \XMMDst
	movdqa	  \TMP2, \XMM1              # result in TMP6, XMMDst, XMM1

        # Multiply TMP1 * HashKey (using Karatsuba)

	movdqa	  \XMM2, \TMP1
	pshufd	  $78, \XMM2, \TMP2
	pxor	  \XMM2, \TMP2
	movdqa	  HashKey_3(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
	PCLMULQDQ 0x00, \TMP5, \XMM2       # XMM2 = a0*b0
	movdqa	  HashKey_3_k(%rsp), \TMP4
	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
	pxor	  \TMP1, \TMP6
	pxor	  \XMM2, \XMMDst
	pxor	  \TMP2, \XMM1
# results accumulated in TMP6, XMMDst, XMM1

        # Multiply TMP1 * HashKey (using Karatsuba)

	movdqa	  \XMM3, \TMP1
	pshufd	  $78, \XMM3, \TMP2
	pxor	  \XMM3, \TMP2
	movdqa	  HashKey_2(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP1       # TMP1 = a1*b1
	PCLMULQDQ 0x00, \TMP5, \XMM3       # XMM3 = a0*b0
	movdqa	  HashKey_2_k(%rsp), \TMP4
	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
	pxor	  \TMP1, \TMP6
	pxor	  \XMM3, \XMMDst
	pxor	  \TMP2, \XMM1   # results accumulated in TMP6, XMMDst, XMM1

        # Multiply TMP1 * HashKey (using Karatsuba)
	movdqa	  \XMM4, \TMP1
	pshufd	  $78, \XMM4, \TMP2
	pxor	  \XMM4, \TMP2
	movdqa	  HashKey(%rsp), \TMP5
	PCLMULQDQ 0x11, \TMP5, \TMP1	    # TMP1 = a1*b1
	PCLMULQDQ 0x00, \TMP5, \XMM4       # XMM4 = a0*b0
	movdqa	  HashKey_k(%rsp), \TMP4
	PCLMULQDQ 0x00, \TMP4, \TMP2       # TMP2 = (a1+a0)*(b1+b0)
	pxor	  \TMP1, \TMP6
	pxor	  \XMM4, \XMMDst
	pxor	  \XMM1, \TMP2
	pxor	  \TMP6, \TMP2
	pxor	  \XMMDst, \TMP2
	# middle section of the temp results combined as in karatsuba algorithm
	movdqa	  \TMP2, \TMP4
	pslldq	  $8, \TMP4                 # left shift TMP4 2 DWs
	psrldq	  $8, \TMP2                 # right shift TMP2 2 DWs
	pxor	  \TMP4, \XMMDst
	pxor	  \TMP2, \TMP6
# TMP6:XMMDst holds the result of the accumulated carry-less multiplications
	# first phase of the reduction
	movdqa    \XMMDst, \TMP2
	movdqa    \XMMDst, \TMP3
	movdqa    \XMMDst, \TMP4
# move XMMDst into TMP2, TMP3, TMP4 in order to perform 3 shifts independently
	pslld     $31, \TMP2                # packed right shifting << 31
	pslld     $30, \TMP3                # packed right shifting << 30
	pslld     $25, \TMP4                # packed right shifting << 25
	pxor      \TMP3, \TMP2              # xor the shifted versions
	pxor      \TMP4, \TMP2
	movdqa    \TMP2, \TMP7
	psrldq    $4, \TMP7                 # right shift TMP7 1 DW
	pslldq    $12, \TMP2                # left shift TMP2 3 DWs
	pxor      \TMP2, \XMMDst

        # second phase of the reduction
	movdqa    \XMMDst, \TMP2
	# make 3 copies of XMMDst for doing 3 shift operations
	movdqa    \XMMDst, \TMP3
	movdqa    \XMMDst, \TMP4
	psrld     $1, \TMP2                 # packed left shift >> 1
	psrld     $2, \TMP3                 # packed left shift >> 2
	psrld     $7, \TMP4                 # packed left shift >> 7
	pxor      \TMP3, \TMP2              # xor the shifted versions
	pxor      \TMP4, \TMP2
	pxor      \TMP7, \TMP2
	pxor      \TMP2, \XMMDst
	pxor      \TMP6, \XMMDst            # reduced result is in XMMDst
.endm

/* Encryption of a single block done*/
.macro ENCRYPT_SINGLE_BLOCK XMM0 TMP1

	pxor	(%arg1), \XMM0
        movaps 16(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 32(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 48(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 64(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 80(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 96(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 112(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 128(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 144(%arg1), \TMP1
	AESENC	\TMP1, \XMM0
        movaps 160(%arg1), \TMP1
	AESENCLAST	\TMP1, \XMM0
.endm


/*****************************************************************************
* void aesni_gcm_dec(void *aes_ctx,    // AES Key schedule. Starts on a 16 byte boundary.
*                   u8 *out,           // Plaintext output. Encrypt in-place is allowed.
*                   const u8 *in,      // Ciphertext input
*                   u64 plaintext_len, // Length of data in bytes for decryption.
*                   u8 *iv,            // Pre-counter block j0: 4 byte salt (from Security Association)
*                                      // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload)
*                                      // concatenated with 0x00000001. 16-byte aligned pointer.
*                   u8 *hash_subkey,   // H, the Hash sub key input. Data starts on a 16-byte boundary.
*                   const u8 *aad,     // Additional Authentication Data (AAD)
*                   u64 aad_len,       // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes
*                   u8  *auth_tag,     // Authenticated Tag output. The driver will compare this to the
*                                      // given authentication tag and only return the plaintext if they match.
*                   u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16
*                                      // (most likely), 12 or 8.
*
* Assumptions:
*
* keys:
*       keys are pre-expanded and aligned to 16 bytes. we are using the first
*       set of 11 keys in the data structure void *aes_ctx
*
* iv:
*       0                   1                   2                   3
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                             Salt  (From the SA)               |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                     Initialization Vector                     |
*       |         (This is the sequence number from IPSec header)       |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                              0x1                              |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
*
*
* AAD:
*       AAD padded to 128 bits with 0
*       for example, assume AAD is a u32 vector
*
*       if AAD is 8 bytes:
*       AAD[3] = {A0, A1};
*       padded AAD in xmm register = {A1 A0 0 0}
*
*       0                   1                   2                   3
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                               SPI (A1)                        |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                     32-bit Sequence Number (A0)               |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                              0x0                              |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
*                                       AAD Format with 32-bit Sequence Number
*
*       if AAD is 12 bytes:
*       AAD[3] = {A0, A1, A2};
*       padded AAD in xmm register = {A2 A1 A0 0}
*
*       0                   1                   2                   3
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                               SPI (A2)                        |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                 64-bit Extended Sequence Number {A1,A0}       |
*       |                                                               |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                              0x0                              |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
*                        AAD Format with 64-bit Extended Sequence Number
*
* aadLen:
*       from the definition of the spec, aadLen can only be 8 or 12 bytes.
*       The code supports 16 too but for other sizes, the code will fail.
*
* TLen:
*       from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
*       For other sizes, the code will fail.
*
* poly = x^128 + x^127 + x^126 + x^121 + 1
*
*****************************************************************************/

ENTRY(aesni_gcm_dec)
	push	%r12
	push	%r13
	push	%r14
	mov	%rsp, %r14
/*
* states of %xmm registers %xmm6:%xmm15 not saved
* all %xmm registers are clobbered
*/
	sub	$VARIABLE_OFFSET, %rsp
	and	$~63, %rsp                        # align rsp to 64 bytes
	mov	%arg6, %r12
	movdqu	(%r12), %xmm13			  # %xmm13 = HashKey
	pshufb	SHUF_MASK(%rip), %xmm13

# Precompute HashKey<<1 (mod poly) from the hash key (required for GHASH)

	movdqa	%xmm13, %xmm2
	psllq	$1, %xmm13
	psrlq	$63, %xmm2
	movdqa	%xmm2, %xmm1
	pslldq	$8, %xmm2
	psrldq	$8, %xmm1
	por	%xmm2, %xmm13

        # Reduction

	pshufd	$0x24, %xmm1, %xmm2
	pcmpeqd TWOONE(%rip), %xmm2
	pand	POLY(%rip), %xmm2
	pxor	%xmm2, %xmm13     # %xmm13 holds the HashKey<<1 (mod poly)


        # Decrypt first few blocks

	movdqa %xmm13, HashKey(%rsp)           # store HashKey<<1 (mod poly)
	mov %arg4, %r13    # save the number of bytes of plaintext/ciphertext
	and $-16, %r13                      # %r13 = %r13 - (%r13 mod 16)
	mov %r13, %r12
	and $(3<<4), %r12
	jz _initial_num_blocks_is_0_decrypt
	cmp $(2<<4), %r12
	jb _initial_num_blocks_is_1_decrypt
	je _initial_num_blocks_is_2_decrypt
_initial_num_blocks_is_3_decrypt:
	INITIAL_BLOCKS 3, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, dec
	sub	$48, %r13
	jmp	_initial_blocks_decrypted
_initial_num_blocks_is_2_decrypt:
	INITIAL_BLOCKS	2, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, dec
	sub	$32, %r13
	jmp	_initial_blocks_decrypted
_initial_num_blocks_is_1_decrypt:
	INITIAL_BLOCKS	1, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, dec
	sub	$16, %r13
	jmp	_initial_blocks_decrypted
_initial_num_blocks_is_0_decrypt:
	INITIAL_BLOCKS	0, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, dec
_initial_blocks_decrypted:
	cmp	$0, %r13
	je	_zero_cipher_left_decrypt
	sub	$64, %r13
	je	_four_cipher_left_decrypt
_decrypt_by_4:
	GHASH_4_ENCRYPT_4_PARALLEL	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, \
%xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, dec
	add	$64, %r11
	sub	$64, %r13
	jne	_decrypt_by_4
_four_cipher_left_decrypt:
	GHASH_LAST_4	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
_zero_cipher_left_decrypt:
	mov	%arg4, %r13
	and	$15, %r13				# %r13 = arg4 (mod 16)
	je	_multiple_of_16_bytes_decrypt

        # Handle the last <16 byte block seperately

	paddd ONE(%rip), %xmm0         # increment CNT to get Yn
	pshufb SHUF_MASK(%rip), %xmm0
	ENCRYPT_SINGLE_BLOCK  %xmm0, %xmm1    # E(K, Yn)
	sub $16, %r11
	add %r13, %r11
	movdqu (%arg3,%r11,1), %xmm1   # recieve the last <16 byte block
	lea SHIFT_MASK+16(%rip), %r12
	sub %r13, %r12
# adjust the shuffle mask pointer to be able to shift 16-%r13 bytes
# (%r13 is the number of bytes in plaintext mod 16)
	movdqu (%r12), %xmm2           # get the appropriate shuffle mask
	pshufb %xmm2, %xmm1            # right shift 16-%r13 butes
	movdqa  %xmm1, %xmm2
	pxor %xmm1, %xmm0            # Ciphertext XOR E(K, Yn)
	movdqu ALL_F-SHIFT_MASK(%r12), %xmm1
	# get the appropriate mask to mask out top 16-%r13 bytes of %xmm0
	pand %xmm1, %xmm0            # mask out top 16-%r13 bytes of %xmm0
	pand    %xmm1, %xmm2
	pshufb SHUF_MASK(%rip),%xmm2
	pxor %xmm2, %xmm8
	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
	          # GHASH computation for the last <16 byte block
	sub %r13, %r11
	add $16, %r11

        # output %r13 bytes
	movq	%xmm0, %rax
	cmp	$8, %r13
	jle	_less_than_8_bytes_left_decrypt
	mov	%rax, (%arg2 , %r11, 1)
	add	$8, %r11
	psrldq	$8, %xmm0
	movq	%xmm0, %rax
	sub	$8, %r13
_less_than_8_bytes_left_decrypt:
	mov	%al,  (%arg2, %r11, 1)
	add	$1, %r11
	shr	$8, %rax
	sub	$1, %r13
	jne	_less_than_8_bytes_left_decrypt
_multiple_of_16_bytes_decrypt:
	mov	arg8, %r12		  # %r13 = aadLen (number of bytes)
	shl	$3, %r12		  # convert into number of bits
	movd	%r12d, %xmm15		  # len(A) in %xmm15
	shl	$3, %arg4		  # len(C) in bits (*128)
	movq	%arg4, %xmm1
	pslldq	$8, %xmm15		  # %xmm15 = len(A)||0x0000000000000000
	pxor	%xmm1, %xmm15		  # %xmm15 = len(A)||len(C)
	pxor	%xmm15, %xmm8
	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
	         # final GHASH computation
	pshufb	SHUF_MASK(%rip), %xmm8
	mov	%arg5, %rax		  # %rax = *Y0
	movdqu	(%rax), %xmm0		  # %xmm0 = Y0
	ENCRYPT_SINGLE_BLOCK	%xmm0,  %xmm1	  # E(K, Y0)
	pxor	%xmm8, %xmm0
_return_T_decrypt:
	mov	arg9, %r10                # %r10 = authTag
	mov	arg10, %r11               # %r11 = auth_tag_len
	cmp	$16, %r11
	je	_T_16_decrypt
	cmp	$12, %r11
	je	_T_12_decrypt
_T_8_decrypt:
	movq	%xmm0, %rax
	mov	%rax, (%r10)
	jmp	_return_T_done_decrypt
_T_12_decrypt:
	movq	%xmm0, %rax
	mov	%rax, (%r10)
	psrldq	$8, %xmm0
	movd	%xmm0, %eax
	mov	%eax, 8(%r10)
	jmp	_return_T_done_decrypt
_T_16_decrypt:
	movdqu	%xmm0, (%r10)
_return_T_done_decrypt:
	mov	%r14, %rsp
	pop	%r14
	pop	%r13
	pop	%r12
	ret


/*****************************************************************************
* void aesni_gcm_enc(void *aes_ctx,      // AES Key schedule. Starts on a 16 byte boundary.
*                    u8 *out,            // Ciphertext output. Encrypt in-place is allowed.
*                    const u8 *in,       // Plaintext input
*                    u64 plaintext_len,  // Length of data in bytes for encryption.
*                    u8 *iv,             // Pre-counter block j0: 4 byte salt (from Security Association)
*                                        // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload)
*                                        // concatenated with 0x00000001. 16-byte aligned pointer.
*                    u8 *hash_subkey,    // H, the Hash sub key input. Data starts on a 16-byte boundary.
*                    const u8 *aad,      // Additional Authentication Data (AAD)
*                    u64 aad_len,        // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes
*                    u8 *auth_tag,       // Authenticated Tag output.
*                    u64 auth_tag_len);  // Authenticated Tag Length in bytes. Valid values are 16 (most likely),
*                                        // 12 or 8.
*
* Assumptions:
*
* keys:
*       keys are pre-expanded and aligned to 16 bytes. we are using the
*       first set of 11 keys in the data structure void *aes_ctx
*
*
* iv:
*       0                   1                   2                   3
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                             Salt  (From the SA)               |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                     Initialization Vector                     |
*       |         (This is the sequence number from IPSec header)       |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                              0x1                              |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
*
*
* AAD:
*       AAD padded to 128 bits with 0
*       for example, assume AAD is a u32 vector
*
*       if AAD is 8 bytes:
*       AAD[3] = {A0, A1};
*       padded AAD in xmm register = {A1 A0 0 0}
*
*       0                   1                   2                   3
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                               SPI (A1)                        |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                     32-bit Sequence Number (A0)               |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                              0x0                              |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
*                                 AAD Format with 32-bit Sequence Number
*
*       if AAD is 12 bytes:
*       AAD[3] = {A0, A1, A2};
*       padded AAD in xmm register = {A2 A1 A0 0}
*
*       0                   1                   2                   3
*       0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                               SPI (A2)                        |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                 64-bit Extended Sequence Number {A1,A0}       |
*       |                                                               |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*       |                              0x0                              |
*       +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
*
*                         AAD Format with 64-bit Extended Sequence Number
*
* aadLen:
*       from the definition of the spec, aadLen can only be 8 or 12 bytes.
*       The code supports 16 too but for other sizes, the code will fail.
*
* TLen:
*       from the definition of the spec, TLen can only be 8, 12 or 16 bytes.
*       For other sizes, the code will fail.
*
* poly = x^128 + x^127 + x^126 + x^121 + 1
***************************************************************************/
ENTRY(aesni_gcm_enc)
	push	%r12
	push	%r13
	push	%r14
	mov	%rsp, %r14
#
# states of %xmm registers %xmm6:%xmm15 not saved
# all %xmm registers are clobbered
#
	sub	$VARIABLE_OFFSET, %rsp
	and	$~63, %rsp
	mov	%arg6, %r12
	movdqu	(%r12), %xmm13
	pshufb	SHUF_MASK(%rip), %xmm13

# precompute HashKey<<1 mod poly from the HashKey (required for GHASH)

	movdqa	%xmm13, %xmm2
	psllq	$1, %xmm13
	psrlq	$63, %xmm2
	movdqa	%xmm2, %xmm1
	pslldq	$8, %xmm2
	psrldq	$8, %xmm1
	por	%xmm2, %xmm13

        # reduce HashKey<<1

	pshufd	$0x24, %xmm1, %xmm2
	pcmpeqd TWOONE(%rip), %xmm2
	pand	POLY(%rip), %xmm2
	pxor	%xmm2, %xmm13
	movdqa	%xmm13, HashKey(%rsp)
	mov	%arg4, %r13            # %xmm13 holds HashKey<<1 (mod poly)
	and	$-16, %r13
	mov	%r13, %r12

        # Encrypt first few blocks

	and	$(3<<4), %r12
	jz	_initial_num_blocks_is_0_encrypt
	cmp	$(2<<4), %r12
	jb	_initial_num_blocks_is_1_encrypt
	je	_initial_num_blocks_is_2_encrypt
_initial_num_blocks_is_3_encrypt:
	INITIAL_BLOCKS	3, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 5, 678, enc
	sub	$48, %r13
	jmp	_initial_blocks_encrypted
_initial_num_blocks_is_2_encrypt:
	INITIAL_BLOCKS	2, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 6, 78, enc
	sub	$32, %r13
	jmp	_initial_blocks_encrypted
_initial_num_blocks_is_1_encrypt:
	INITIAL_BLOCKS	1, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 7, 8, enc
	sub	$16, %r13
	jmp	_initial_blocks_encrypted
_initial_num_blocks_is_0_encrypt:
	INITIAL_BLOCKS	0, %xmm9, %xmm10, %xmm13, %xmm11, %xmm12, %xmm0, \
%xmm1, %xmm2, %xmm3, %xmm4, %xmm8, %xmm5, %xmm6, 8, 0, enc
_initial_blocks_encrypted:

        # Main loop - Encrypt remaining blocks

	cmp	$0, %r13
	je	_zero_cipher_left_encrypt
	sub	$64, %r13
	je	_four_cipher_left_encrypt
_encrypt_by_4_encrypt:
	GHASH_4_ENCRYPT_4_PARALLEL	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, \
%xmm14, %xmm0, %xmm1, %xmm2, %xmm3, %xmm4, %xmm5, %xmm6, %xmm7, %xmm8, enc
	add	$64, %r11
	sub	$64, %r13
	jne	_encrypt_by_4_encrypt
_four_cipher_left_encrypt:
	GHASH_LAST_4	%xmm9, %xmm10, %xmm11, %xmm12, %xmm13, %xmm14, \
%xmm15, %xmm1, %xmm2, %xmm3, %xmm4, %xmm8
_zero_cipher_left_encrypt:
	mov	%arg4, %r13
	and	$15, %r13			# %r13 = arg4 (mod 16)
	je	_multiple_of_16_bytes_encrypt

         # Handle the last <16 Byte block seperately
	paddd ONE(%rip), %xmm0                # INCR CNT to get Yn
	pshufb SHUF_MASK(%rip), %xmm0
	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm1        # Encrypt(K, Yn)
	sub $16, %r11
	add %r13, %r11
	movdqu (%arg3,%r11,1), %xmm1     # receive the last <16 byte blocks
	lea SHIFT_MASK+16(%rip), %r12
	sub %r13, %r12
	# adjust the shuffle mask pointer to be able to shift 16-r13 bytes
	# (%r13 is the number of bytes in plaintext mod 16)
	movdqu	(%r12), %xmm2           # get the appropriate shuffle mask
	pshufb	%xmm2, %xmm1            # shift right 16-r13 byte
	pxor	%xmm1, %xmm0            # Plaintext XOR Encrypt(K, Yn)
	movdqu	ALL_F-SHIFT_MASK(%r12), %xmm1
	# get the appropriate mask to mask out top 16-r13 bytes of xmm0
	pand	%xmm1, %xmm0            # mask out top 16-r13 bytes of xmm0

	pshufb	SHUF_MASK(%rip),%xmm0
	pxor	%xmm0, %xmm8
	GHASH_MUL %xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
	# GHASH computation for the last <16 byte block
	sub	%r13, %r11
	add	$16, %r11
	pshufb SHUF_MASK(%rip), %xmm0
	# shuffle xmm0 back to output as ciphertext

        # Output %r13 bytes
	movq %xmm0, %rax
	cmp $8, %r13
	jle _less_than_8_bytes_left_encrypt
	mov %rax, (%arg2 , %r11, 1)
	add $8, %r11
	psrldq $8, %xmm0
	movq %xmm0, %rax
	sub $8, %r13
_less_than_8_bytes_left_encrypt:
	mov %al,  (%arg2, %r11, 1)
	add $1, %r11
	shr $8, %rax
	sub $1, %r13
	jne _less_than_8_bytes_left_encrypt
_multiple_of_16_bytes_encrypt:
	mov	arg8, %r12    # %r12 = addLen (number of bytes)
	shl	$3, %r12
	movd	%r12d, %xmm15       # len(A) in %xmm15
	shl	$3, %arg4               # len(C) in bits (*128)
	movq	%arg4, %xmm1
	pslldq	$8, %xmm15          # %xmm15 = len(A)||0x0000000000000000
	pxor	%xmm1, %xmm15       # %xmm15 = len(A)||len(C)
	pxor	%xmm15, %xmm8
	GHASH_MUL	%xmm8, %xmm13, %xmm9, %xmm10, %xmm11, %xmm5, %xmm6
	# final GHASH computation

	pshufb	SHUF_MASK(%rip), %xmm8         # perform a 16 byte swap
	mov	%arg5, %rax		       # %rax  = *Y0
	movdqu	(%rax), %xmm0		       # %xmm0 = Y0
	ENCRYPT_SINGLE_BLOCK	%xmm0, %xmm15         # Encrypt(K, Y0)
	pxor	%xmm8, %xmm0
_return_T_encrypt:
	mov	arg9, %r10                     # %r10 = authTag
	mov	arg10, %r11                    # %r11 = auth_tag_len
	cmp	$16, %r11
	je	_T_16_encrypt
	cmp	$12, %r11
	je	_T_12_encrypt
_T_8_encrypt:
	movq	%xmm0, %rax
	mov	%rax, (%r10)
	jmp	_return_T_done_encrypt
_T_12_encrypt:
	movq	%xmm0, %rax
	mov	%rax, (%r10)
	psrldq	$8, %xmm0
	movd	%xmm0, %eax
	mov	%eax, 8(%r10)
	jmp	_return_T_done_encrypt
_T_16_encrypt:
	movdqu	%xmm0, (%r10)
_return_T_done_encrypt:
	mov	%r14, %rsp
	pop	%r14
	pop	%r13
	pop	%r12
	ret
#endif


_key_expansion_128:
_key_expansion_256a:
	pshufd $0b11111111, %xmm1, %xmm1
	shufps $0b00010000, %xmm0, %xmm4
	pxor %xmm4, %xmm0
	shufps $0b10001100, %xmm0, %xmm4
	pxor %xmm4, %xmm0
	pxor %xmm1, %xmm0
	movaps %xmm0, (TKEYP)
	add $0x10, TKEYP
	ret

.align 4
_key_expansion_192a:
	pshufd $0b01010101, %xmm1, %xmm1
	shufps $0b00010000, %xmm0, %xmm4
	pxor %xmm4, %xmm0
	shufps $0b10001100, %xmm0, %xmm4
	pxor %xmm4, %xmm0
	pxor %xmm1, %xmm0

	movaps %xmm2, %xmm5
	movaps %xmm2, %xmm6
	pslldq $4, %xmm5
	pshufd $0b11111111, %xmm0, %xmm3
	pxor %xmm3, %xmm2
	pxor %xmm5, %xmm2

	movaps %xmm0, %xmm1
	shufps $0b01000100, %xmm0, %xmm6
	movaps %xmm6, (TKEYP)
	shufps $0b01001110, %xmm2, %xmm1
	movaps %xmm1, 0x10(TKEYP)
	add $0x20, TKEYP
	ret

.align 4
_key_expansion_192b:
	pshufd $0b01010101, %xmm1, %xmm1
	shufps $0b00010000, %xmm0, %xmm4
	pxor %xmm4, %xmm0
	shufps $0b10001100, %xmm0, %xmm4
	pxor %xmm4, %xmm0
	pxor %xmm1, %xmm0

	movaps %xmm2, %xmm5
	pslldq $4, %xmm5
	pshufd $0b11111111, %xmm0, %xmm3
	pxor %xmm3, %xmm2
	pxor %xmm5, %xmm2

	movaps %xmm0, (TKEYP)
	add $0x10, TKEYP
	ret

.align 4
_key_expansion_256b:
	pshufd $0b10101010, %xmm1, %xmm1
	shufps $0b00010000, %xmm2, %xmm4
	pxor %xmm4, %xmm2
	shufps $0b10001100, %xmm2, %xmm4
	pxor %xmm4, %xmm2
	pxor %xmm1, %xmm2
	movaps %xmm2, (TKEYP)
	add $0x10, TKEYP
	ret

/*
 * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key,
 *                   unsigned int key_len)
 */
ENTRY(aesni_set_key)
#ifndef __x86_64__
	pushl KEYP
	movl 8(%esp), KEYP		# ctx
	movl 12(%esp), UKEYP		# in_key
	movl 16(%esp), %edx		# key_len
#endif
	movups (UKEYP), %xmm0		# user key (first 16 bytes)
	movaps %xmm0, (KEYP)
	lea 0x10(KEYP), TKEYP		# key addr
	movl %edx, 480(KEYP)
	pxor %xmm4, %xmm4		# xmm4 is assumed 0 in _key_expansion_x
	cmp $24, %dl
	jb .Lenc_key128
	je .Lenc_key192
	movups 0x10(UKEYP), %xmm2	# other user key
	movaps %xmm2, (TKEYP)
	add $0x10, TKEYP
	AESKEYGENASSIST 0x1 %xmm2 %xmm1		# round 1
	call _key_expansion_256a
	AESKEYGENASSIST 0x1 %xmm0 %xmm1
	call _key_expansion_256b
	AESKEYGENASSIST 0x2 %xmm2 %xmm1		# round 2
	call _key_expansion_256a
	AESKEYGENASSIST 0x2 %xmm0 %xmm1
	call _key_expansion_256b
	AESKEYGENASSIST 0x4 %xmm2 %xmm1		# round 3
	call _key_expansion_256a
	AESKEYGENASSIST 0x4 %xmm0 %xmm1
	call _key_expansion_256b
	AESKEYGENASSIST 0x8 %xmm2 %xmm1		# round 4
	call _key_expansion_256a
	AESKEYGENASSIST 0x8 %xmm0 %xmm1
	call _key_expansion_256b
	AESKEYGENASSIST 0x10 %xmm2 %xmm1	# round 5
	call _key_expansion_256a
	AESKEYGENASSIST 0x10 %xmm0 %xmm1
	call _key_expansion_256b
	AESKEYGENASSIST 0x20 %xmm2 %xmm1	# round 6
	call _key_expansion_256a
	AESKEYGENASSIST 0x20 %xmm0 %xmm1
	call _key_expansion_256b
	AESKEYGENASSIST 0x40 %xmm2 %xmm1	# round 7
	call _key_expansion_256a
	jmp .Ldec_key
.Lenc_key192:
	movq 0x10(UKEYP), %xmm2		# other user key
	AESKEYGENASSIST 0x1 %xmm2 %xmm1		# round 1
	call _key_expansion_192a
	AESKEYGENASSIST 0x2 %xmm2 %xmm1		# round 2
	call _key_expansion_192b
	AESKEYGENASSIST 0x4 %xmm2 %xmm1		# round 3
	call _key_expansion_192a
	AESKEYGENASSIST 0x8 %xmm2 %xmm1		# round 4
	call _key_expansion_192b
	AESKEYGENASSIST 0x10 %xmm2 %xmm1	# round 5
	call _key_expansion_192a
	AESKEYGENASSIST 0x20 %xmm2 %xmm1	# round 6
	call _key_expansion_192b
	AESKEYGENASSIST 0x40 %xmm2 %xmm1	# round 7
	call _key_expansion_192a
	AESKEYGENASSIST 0x80 %xmm2 %xmm1	# round 8
	call _key_expansion_192b
	jmp .Ldec_key
.Lenc_key128:
	AESKEYGENASSIST 0x1 %xmm0 %xmm1		# round 1
	call _key_expansion_128
	AESKEYGENASSIST 0x2 %xmm0 %xmm1		# round 2
	call _key_expansion_128
	AESKEYGENASSIST 0x4 %xmm0 %xmm1		# round 3
	call _key_expansion_128
	AESKEYGENASSIST 0x8 %xmm0 %xmm1		# round 4
	call _key_expansion_128
	AESKEYGENASSIST 0x10 %xmm0 %xmm1	# round 5
	call _key_expansion_128
	AESKEYGENASSIST 0x20 %xmm0 %xmm1	# round 6
	call _key_expansion_128
	AESKEYGENASSIST 0x40 %xmm0 %xmm1	# round 7
	call _key_expansion_128
	AESKEYGENASSIST 0x80 %xmm0 %xmm1	# round 8
	call _key_expansion_128
	AESKEYGENASSIST 0x1b %xmm0 %xmm1	# round 9
	call _key_expansion_128
	AESKEYGENASSIST 0x36 %xmm0 %xmm1	# round 10
	call _key_expansion_128
.Ldec_key:
	sub $0x10, TKEYP
	movaps (KEYP), %xmm0
	movaps (TKEYP), %xmm1
	movaps %xmm0, 240(TKEYP)
	movaps %xmm1, 240(KEYP)
	add $0x10, KEYP
	lea 240-16(TKEYP), UKEYP
.align 4
.Ldec_key_loop:
	movaps (KEYP), %xmm0
	AESIMC %xmm0 %xmm1
	movaps %xmm1, (UKEYP)
	add $0x10, KEYP
	sub $0x10, UKEYP
	cmp TKEYP, KEYP
	jb .Ldec_key_loop
	xor AREG, AREG
#ifndef __x86_64__
	popl KEYP
#endif
	ret

/*
 * void aesni_enc(struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
 */
ENTRY(aesni_enc)
#ifndef __x86_64__
	pushl KEYP
	pushl KLEN
	movl 12(%esp), KEYP
	movl 16(%esp), OUTP
	movl 20(%esp), INP
#endif
	movl 480(KEYP), KLEN		# key length
	movups (INP), STATE		# input
	call _aesni_enc1
	movups STATE, (OUTP)		# output
#ifndef __x86_64__
	popl KLEN
	popl KEYP
#endif
	ret

/*
 * _aesni_enc1:		internal ABI
 * input:
 *	KEYP:		key struct pointer
 *	KLEN:		round count
 *	STATE:		initial state (input)
 * output:
 *	STATE:		finial state (output)
 * changed:
 *	KEY
 *	TKEYP (T1)
 */
.align 4
_aesni_enc1:
	movaps (KEYP), KEY		# key
	mov KEYP, TKEYP
	pxor KEY, STATE		# round 0
	add $0x30, TKEYP
	cmp $24, KLEN
	jb .Lenc128
	lea 0x20(TKEYP), TKEYP
	je .Lenc192
	add $0x20, TKEYP
	movaps -0x60(TKEYP), KEY
	AESENC KEY STATE
	movaps -0x50(TKEYP), KEY
	AESENC KEY STATE
.align 4
.Lenc192:
	movaps -0x40(TKEYP), KEY
	AESENC KEY STATE
	movaps -0x30(TKEYP), KEY
	AESENC KEY STATE
.align 4
.Lenc128:
	movaps -0x20(TKEYP), KEY
	AESENC KEY STATE
	movaps -0x10(TKEYP), KEY
	AESENC KEY STATE
	movaps (TKEYP), KEY
	AESENC KEY STATE
	movaps 0x10(TKEYP), KEY
	AESENC KEY STATE
	movaps 0x20(TKEYP), KEY
	AESENC KEY STATE
	movaps 0x30(TKEYP), KEY
	AESENC KEY STATE
	movaps 0x40(TKEYP), KEY
	AESENC KEY STATE
	movaps 0x50(TKEYP), KEY
	AESENC KEY STATE
	movaps 0x60(TKEYP), KEY
	AESENC KEY STATE
	movaps 0x70(TKEYP), KEY
	AESENCLAST KEY STATE
	ret

/*
 * _aesni_enc4:	internal ABI
 * input:
 *	KEYP:		key struct pointer
 *	KLEN:		round count
 *	STATE1:		initial state (input)
 *	STATE2
 *	STATE3
 *	STATE4
 * output:
 *	STATE1:		finial state (output)
 *	STATE2
 *	STATE3
 *	STATE4
 * changed:
 *	KEY
 *	TKEYP (T1)
 */
.align 4
_aesni_enc4:
	movaps (KEYP), KEY		# key
	mov KEYP, TKEYP
	pxor KEY, STATE1		# round 0
	pxor KEY, STATE2
	pxor KEY, STATE3
	pxor KEY, STATE4
	add $0x30, TKEYP
	cmp $24, KLEN
	jb .L4enc128
	lea 0x20(TKEYP), TKEYP
	je .L4enc192
	add $0x20, TKEYP
	movaps -0x60(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps -0x50(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
#.align 4
.L4enc192:
	movaps -0x40(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps -0x30(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
#.align 4
.L4enc128:
	movaps -0x20(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps -0x10(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps (TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x10(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x20(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x30(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x40(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x50(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x60(TKEYP), KEY
	AESENC KEY STATE1
	AESENC KEY STATE2
	AESENC KEY STATE3
	AESENC KEY STATE4
	movaps 0x70(TKEYP), KEY
	AESENCLAST KEY STATE1		# last round
	AESENCLAST KEY STATE2
	AESENCLAST KEY STATE3
	AESENCLAST KEY STATE4
	ret

/*
 * void aesni_dec (struct crypto_aes_ctx *ctx, u8 *dst, const u8 *src)
 */
ENTRY(aesni_dec)
#ifndef __x86_64__
	pushl KEYP
	pushl KLEN
	movl 12(%esp), KEYP
	movl 16(%esp), OUTP
	movl 20(%esp), INP
#endif
	mov 480(KEYP), KLEN		# key length
	add $240, KEYP
	movups (INP), STATE		# input
	call _aesni_dec1
	movups STATE, (OUTP)		#output
#ifndef __x86_64__
	popl KLEN
	popl KEYP
#endif
	ret

/*
 * _aesni_dec1:		internal ABI
 * input:
 *	KEYP:		key struct pointer
 *	KLEN:		key length
 *	STATE:		initial state (input)
 * output:
 *	STATE:		finial state (output)
 * changed:
 *	KEY
 *	TKEYP (T1)
 */
.align 4
_aesni_dec1:
	movaps (KEYP), KEY		# key
	mov KEYP, TKEYP
	pxor KEY, STATE		# round 0
	add $0x30, TKEYP
	cmp $24, KLEN
	jb .Ldec128
	lea 0x20(TKEYP), TKEYP
	je .Ldec192
	add $0x20, TKEYP
	movaps -0x60(TKEYP), KEY
	AESDEC KEY STATE
	movaps -0x50(TKEYP), KEY
	AESDEC KEY STATE
.align 4
.Ldec192:
	movaps -0x40(TKEYP), KEY
	AESDEC KEY STATE
	movaps -0x30(TKEYP), KEY
	AESDEC KEY STATE
.align 4
.Ldec128:
	movaps -0x20(TKEYP), KEY
	AESDEC KEY STATE
	movaps -0x10(TKEYP), KEY
	AESDEC KEY STATE
	movaps (TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x10(TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x20(TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x30(TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x40(TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x50(TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x60(TKEYP), KEY
	AESDEC KEY STATE
	movaps 0x70(TKEYP), KEY
	AESDECLAST KEY STATE
	ret

/*
 * _aesni_dec4:	internal ABI
 * input:
 *	KEYP:		key struct pointer
 *	KLEN:		key length
 *	STATE1:		initial state (input)
 *	STATE2
 *	STATE3
 *	STATE4
 * output:
 *	STATE1:		finial state (output)
 *	STATE2
 *	STATE3
 *	STATE4
 * changed:
 *	KEY
 *	TKEYP (T1)
 */
.align 4
_aesni_dec4:
	movaps (KEYP), KEY		# key
	mov KEYP, TKEYP
	pxor KEY, STATE1		# round 0
	pxor KEY, STATE2
	pxor KEY, STATE3
	pxor KEY, STATE4
	add $0x30, TKEYP
	cmp $24, KLEN
	jb .L4dec128
	lea 0x20(TKEYP), TKEYP
	je .L4dec192
	add $0x20, TKEYP
	movaps -0x60(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps -0x50(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
.align 4
.L4dec192:
	movaps -0x40(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps -0x30(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
.align 4
.L4dec128:
	movaps -0x20(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps -0x10(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps (TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x10(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x20(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x30(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x40(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x50(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x60(TKEYP), KEY
	AESDEC KEY STATE1
	AESDEC KEY STATE2
	AESDEC KEY STATE3
	AESDEC KEY STATE4
	movaps 0x70(TKEYP), KEY
	AESDECLAST KEY STATE1		# last round
	AESDECLAST KEY STATE2
	AESDECLAST KEY STATE3
	AESDECLAST KEY STATE4
	ret

/*
 * void aesni_ecb_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
 *		      size_t len)
 */
ENTRY(aesni_ecb_enc)
#ifndef __x86_64__
	pushl LEN
	pushl KEYP
	pushl KLEN
	movl 16(%esp), KEYP
	movl 20(%esp), OUTP
	movl 24(%esp), INP
	movl 28(%esp), LEN
#endif
	test LEN, LEN		# check length
	jz .Lecb_enc_ret
	mov 480(KEYP), KLEN
	cmp $16, LEN
	jb .Lecb_enc_ret
	cmp $64, LEN
	jb .Lecb_enc_loop1
.align 4
.Lecb_enc_loop4:
	movups (INP), STATE1
	movups 0x10(INP), STATE2
	movups 0x20(INP), STATE3
	movups 0x30(INP), STATE4
	call _aesni_enc4
	movups STATE1, (OUTP)
	movups STATE2, 0x10(OUTP)
	movups STATE3, 0x20(OUTP)
	movups STATE4, 0x30(OUTP)
	sub $64, LEN
	add $64, INP
	add $64, OUTP
	cmp $64, LEN
	jge .Lecb_enc_loop4
	cmp $16, LEN
	jb .Lecb_enc_ret
.align 4
.Lecb_enc_loop1:
	movups (INP), STATE1
	call _aesni_enc1
	movups STATE1, (OUTP)
	sub $16, LEN
	add $16, INP
	add $16, OUTP
	cmp $16, LEN
	jge .Lecb_enc_loop1
.Lecb_enc_ret:
#ifndef __x86_64__
	popl KLEN
	popl KEYP
	popl LEN
#endif
	ret

/*
 * void aesni_ecb_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
 *		      size_t len);
 */
ENTRY(aesni_ecb_dec)
#ifndef __x86_64__
	pushl LEN
	pushl KEYP
	pushl KLEN
	movl 16(%esp), KEYP
	movl 20(%esp), OUTP
	movl 24(%esp), INP
	movl 28(%esp), LEN
#endif
	test LEN, LEN
	jz .Lecb_dec_ret
	mov 480(KEYP), KLEN
	add $240, KEYP
	cmp $16, LEN
	jb .Lecb_dec_ret
	cmp $64, LEN
	jb .Lecb_dec_loop1
.align 4
.Lecb_dec_loop4:
	movups (INP), STATE1
	movups 0x10(INP), STATE2
	movups 0x20(INP), STATE3
	movups 0x30(INP), STATE4
	call _aesni_dec4
	movups STATE1, (OUTP)
	movups STATE2, 0x10(OUTP)
	movups STATE3, 0x20(OUTP)
	movups STATE4, 0x30(OUTP)
	sub $64, LEN
	add $64, INP
	add $64, OUTP
	cmp $64, LEN
	jge .Lecb_dec_loop4
	cmp $16, LEN
	jb .Lecb_dec_ret
.align 4
.Lecb_dec_loop1:
	movups (INP), STATE1
	call _aesni_dec1
	movups STATE1, (OUTP)
	sub $16, LEN
	add $16, INP
	add $16, OUTP
	cmp $16, LEN
	jge .Lecb_dec_loop1
.Lecb_dec_ret:
#ifndef __x86_64__
	popl KLEN
	popl KEYP
	popl LEN
#endif
	ret

/*
 * void aesni_cbc_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
 *		      size_t len, u8 *iv)
 */
ENTRY(aesni_cbc_enc)
#ifndef __x86_64__
	pushl IVP
	pushl LEN
	pushl KEYP
	pushl KLEN
	movl 20(%esp), KEYP
	movl 24(%esp), OUTP
	movl 28(%esp), INP
	movl 32(%esp), LEN
	movl 36(%esp), IVP
#endif
	cmp $16, LEN
	jb .Lcbc_enc_ret
	mov 480(KEYP), KLEN
	movups (IVP), STATE	# load iv as initial state
.align 4
.Lcbc_enc_loop:
	movups (INP), IN	# load input
	pxor IN, STATE
	call _aesni_enc1
	movups STATE, (OUTP)	# store output
	sub $16, LEN
	add $16, INP
	add $16, OUTP
	cmp $16, LEN
	jge .Lcbc_enc_loop
	movups STATE, (IVP)
.Lcbc_enc_ret:
#ifndef __x86_64__
	popl KLEN
	popl KEYP
	popl LEN
	popl IVP
#endif
	ret

/*
 * void aesni_cbc_dec(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
 *		      size_t len, u8 *iv)
 */
ENTRY(aesni_cbc_dec)
#ifndef __x86_64__
	pushl IVP
	pushl LEN
	pushl KEYP
	pushl KLEN
	movl 20(%esp), KEYP
	movl 24(%esp), OUTP
	movl 28(%esp), INP
	movl 32(%esp), LEN
	movl 36(%esp), IVP
#endif
	cmp $16, LEN
	jb .Lcbc_dec_just_ret
	mov 480(KEYP), KLEN
	add $240, KEYP
	movups (IVP), IV
	cmp $64, LEN
	jb .Lcbc_dec_loop1
.align 4
.Lcbc_dec_loop4:
	movups (INP), IN1
	movaps IN1, STATE1
	movups 0x10(INP), IN2
	movaps IN2, STATE2
#ifdef __x86_64__
	movups 0x20(INP), IN3
	movaps IN3, STATE3
	movups 0x30(INP), IN4
	movaps IN4, STATE4
#else
	movups 0x20(INP), IN1
	movaps IN1, STATE3
	movups 0x30(INP), IN2
	movaps IN2, STATE4
#endif
	call _aesni_dec4
	pxor IV, STATE1
#ifdef __x86_64__
	pxor IN1, STATE2
	pxor IN2, STATE3
	pxor IN3, STATE4
	movaps IN4, IV
#else
	pxor (INP), STATE2
	pxor 0x10(INP), STATE3
	pxor IN1, STATE4
	movaps IN2, IV
#endif
	movups STATE1, (OUTP)
	movups STATE2, 0x10(OUTP)
	movups STATE3, 0x20(OUTP)
	movups STATE4, 0x30(OUTP)
	sub $64, LEN
	add $64, INP
	add $64, OUTP
	cmp $64, LEN
	jge .Lcbc_dec_loop4
	cmp $16, LEN
	jb .Lcbc_dec_ret
.align 4
.Lcbc_dec_loop1:
	movups (INP), IN
	movaps IN, STATE
	call _aesni_dec1
	pxor IV, STATE
	movups STATE, (OUTP)
	movaps IN, IV
	sub $16, LEN
	add $16, INP
	add $16, OUTP
	cmp $16, LEN
	jge .Lcbc_dec_loop1
.Lcbc_dec_ret:
	movups IV, (IVP)
.Lcbc_dec_just_ret:
#ifndef __x86_64__
	popl KLEN
	popl KEYP
	popl LEN
	popl IVP
#endif
	ret

#ifdef __x86_64__
.align 16
.Lbswap_mask:
	.byte 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0

/*
 * _aesni_inc_init:	internal ABI
 *	setup registers used by _aesni_inc
 * input:
 *	IV
 * output:
 *	CTR:	== IV, in little endian
 *	TCTR_LOW: == lower qword of CTR
 *	INC:	== 1, in little endian
 *	BSWAP_MASK == endian swapping mask
 */
.align 4
_aesni_inc_init:
	movaps .Lbswap_mask, BSWAP_MASK
	movaps IV, CTR
	PSHUFB_XMM BSWAP_MASK CTR
	mov $1, TCTR_LOW
	MOVQ_R64_XMM TCTR_LOW INC
	MOVQ_R64_XMM CTR TCTR_LOW
	ret

/*
 * _aesni_inc:		internal ABI
 *	Increase IV by 1, IV is in big endian
 * input:
 *	IV
 *	CTR:	== IV, in little endian
 *	TCTR_LOW: == lower qword of CTR
 *	INC:	== 1, in little endian
 *	BSWAP_MASK == endian swapping mask
 * output:
 *	IV:	Increase by 1
 * changed:
 *	CTR:	== output IV, in little endian
 *	TCTR_LOW: == lower qword of CTR
 */
.align 4
_aesni_inc:
	paddq INC, CTR
	add $1, TCTR_LOW
	jnc .Linc_low
	pslldq $8, INC
	paddq INC, CTR
	psrldq $8, INC
.Linc_low:
	movaps CTR, IV
	PSHUFB_XMM BSWAP_MASK IV
	ret

/*
 * void aesni_ctr_enc(struct crypto_aes_ctx *ctx, const u8 *dst, u8 *src,
 *		      size_t len, u8 *iv)
 */
ENTRY(aesni_ctr_enc)
	cmp $16, LEN
	jb .Lctr_enc_just_ret
	mov 480(KEYP), KLEN
	movups (IVP), IV
	call _aesni_inc_init
	cmp $64, LEN
	jb .Lctr_enc_loop1
.align 4
.Lctr_enc_loop4:
	movaps IV, STATE1
	call _aesni_inc
	movups (INP), IN1
	movaps IV, STATE2
	call _aesni_inc
	movups 0x10(INP), IN2
	movaps IV, STATE3
	call _aesni_inc
	movups 0x20(INP), IN3
	movaps IV, STATE4
	call _aesni_inc
	movups 0x30(INP), IN4
	call _aesni_enc4
	pxor IN1, STATE1
	movups STATE1, (OUTP)
	pxor IN2, STATE2
	movups STATE2, 0x10(OUTP)
	pxor IN3, STATE3
	movups STATE3, 0x20(OUTP)
	pxor IN4, STATE4
	movups STATE4, 0x30(OUTP)
	sub $64, LEN
	add $64, INP
	add $64, OUTP
	cmp $64, LEN
	jge .Lctr_enc_loop4
	cmp $16, LEN
	jb .Lctr_enc_ret
.align 4
.Lctr_enc_loop1:
	movaps IV, STATE
	call _aesni_inc
	movups (INP), IN
	call _aesni_enc1
	pxor IN, STATE
	movups STATE, (OUTP)
	sub $16, LEN
	add $16, INP
	add $16, OUTP
	cmp $16, LEN
	jge .Lctr_enc_loop1
.Lctr_enc_ret:
	movups IV, (IVP)
.Lctr_enc_just_ret:
	ret
#endif