Skip to content
GitLab
Find file Normal viewHistoryPermalink
des_enc.m4 47.8 KB
Newer Older
powelld's avatar
OpenSSL implementing mctls version 0.1
powelld committed
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 

	srl	$2, 8, $4
	and	$4, 255, $4
	stub	$4, [$1+1]

	srl	$2, 16, $4
	and	$4, 255, $4
	stub	$4, [$1+2]

	srl	$2, 24, $4
	stub	$4, [$1+3]


	and	$3, 255, $4
	stub	$4, [$1+0+4]

	srl	$3, 8, $4
	and	$4, 255, $4
	stub	$4, [$1+1+4]

	srl	$3, 16, $4
	and	$4, 255, $4
	stub	$4, [$1+2+4]

	srl	$3, 24, $4
	stub	$4, [$1+3+4]

$5a:

})


! {store_n_bytes}
!
! Stores 1 to 7 bytes little endian
!
! parameter 1  address
! parameter 2  length
! parameter 3  source register left
! parameter 4  source register right
! parameter 5  temp
! parameter 6  temp2
! parameter 7  label
! parameter 8  return label

define(store_n_bytes, {

! {store_n_bytes}
! $1 $2 $5 $6 $7 $8 $7 $8 $9

$7.0:	call	.+8
	sll	$2, 2, $6

	add	%o7,$7.jmp.table-$7.0,$5

	add	$5, $6, $5

	ld	[$5], $5

	jmp	%o7+$5
	nop

$7.7:
	srl	$3, 16, $5
	and	$5, 0xff, $5
	stub	$5, [$1+6]
$7.6:
	srl	$3, 8, $5
	and	$5, 0xff, $5
	stub	$5, [$1+5]
$7.5:
	and	$3, 0xff, $5
	stub	$5, [$1+4]
$7.4:
	srl	$4, 24, $5
	stub	$5, [$1+3]
$7.3:
	srl	$4, 16, $5
	and	$5, 0xff, $5
	stub	$5, [$1+2]
$7.2:
	srl	$4, 8, $5
	and	$5, 0xff, $5
	stub	$5, [$1+1]
$7.1:
	and	$4, 0xff, $5


	ba	$8
	stub	$5, [$1]

	.align 4

$7.jmp.table:

	.word	0
	.word	$7.1-$7.0
	.word	$7.2-$7.0
	.word	$7.3-$7.0
	.word	$7.4-$7.0
	.word	$7.5-$7.0
	.word	$7.6-$7.0
	.word	$7.7-$7.0
})


define(testvalue,{1})

define(register_init, {

! For test purposes:

	sethi	%hi(testvalue), local0
	or	local0, %lo(testvalue), local0

	ifelse($1,{},{}, {mov	local0, $1})
	ifelse($2,{},{}, {mov	local0, $2})
	ifelse($3,{},{}, {mov	local0, $3})
	ifelse($4,{},{}, {mov	local0, $4})
	ifelse($5,{},{}, {mov	local0, $5})
	ifelse($6,{},{}, {mov	local0, $6})
	ifelse($7,{},{}, {mov	local0, $7})
	ifelse($8,{},{}, {mov	local0, $8})

	mov	local0, local1
	mov	local0, local2
	mov	local0, local3
	mov	local0, local4
	mov	local0, local5
	mov	local0, local7
	mov	local0, local6
	mov	local0, out0
	mov	local0, out1
	mov	local0, out2
	mov	local0, out3
	mov	local0, out4
	mov	local0, out5
	mov	local0, global1
	mov	local0, global2
	mov	local0, global3
	mov	local0, global4
	mov	local0, global5

})

.section	".text"

	.align 32

.des_enc:

	! key address in3
	! loads key next encryption/decryption first round from [in4]

	rounds_macro(in5, out5, 1, .des_enc.1, in3, in4, retl)


	.align 32

.des_dec:

	! implemented with out5 as first parameter to avoid
	! register exchange in ede modes

	! key address in4
	! loads key next encryption/decryption first round from [in3]

	rounds_macro(out5, in5, -1, .des_dec.1, in4, in3, retl)



! void DES_encrypt1(data, ks, enc)
! *******************************

	.align 32
	.global DES_encrypt1
	.type	 DES_encrypt1,#function

DES_encrypt1:

	save	%sp, FRAME, %sp

	sethi	%hi(.PIC.DES_SPtrans-1f),global1
	or	global1,%lo(.PIC.DES_SPtrans-1f),global1
1:	call	.+8
	add	%o7,global1,global1
	sub	global1,.PIC.DES_SPtrans-.des_and,out2

	ld	[in0], in5                ! left
	cmp	in2, 0                    ! enc

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	be,pn	%icc, .encrypt.dec        ! enc/dec
#else
	be	.encrypt.dec
#endif
	ld	[in0+4], out5             ! right

	! parameter 6  1/2 for include encryption/decryption
	! parameter 7  1 for move in1 to in3
	! parameter 8  1 for move in3 to in4, 2 for move in4 to in3

	ip_macro(in5, out5, in5, out5, in3, 0, 1, 1)

	rounds_macro(in5, out5, 1, .des_encrypt1.1, in3, in4) ! in4 not used

	fp_macro(in5, out5, 1)            ! 1 for store to [in0]

	ret
	restore

.encrypt.dec:

	add	in1, 120, in3             ! use last subkey for first round

	! parameter 6  1/2 for include encryption/decryption
	! parameter 7  1 for move in1 to in3
	! parameter 8  1 for move in3 to in4, 2 for move in4 to in3

	ip_macro(in5, out5, out5, in5, in4, 2, 0, 1) ! include dec,  ks in4

	fp_macro(out5, in5, 1)            ! 1 for store to [in0]

	ret
	restore

.DES_encrypt1.end:
	.size	 DES_encrypt1,.DES_encrypt1.end-DES_encrypt1


! void DES_encrypt2(data, ks, enc)
!*********************************

	! encrypts/decrypts without initial/final permutation

	.align 32
	.global DES_encrypt2
	.type	 DES_encrypt2,#function

DES_encrypt2:

	save	%sp, FRAME, %sp

	sethi	%hi(.PIC.DES_SPtrans-1f),global1
	or	global1,%lo(.PIC.DES_SPtrans-1f),global1
1:	call	.+8
	add	%o7,global1,global1
	sub	global1,.PIC.DES_SPtrans-.des_and,out2

	! Set sbox address 1 to 6 and rotate halfs 3 left
	! Errors caught by destest? Yes. Still? *NO*

	!sethi	%hi(DES_SPtrans), global1 ! address sbox 1

	!or	global1, %lo(DES_SPtrans), global1  ! sbox 1

	add	global1, 256, global2     ! sbox 2
	add	global1, 512, global3     ! sbox 3

	ld	[in0], out5               ! right
	add	global1, 768, global4     ! sbox 4
	add	global1, 1024, global5    ! sbox 5

	ld	[in0+4], in5              ! left
	add	global1, 1280, local6     ! sbox 6
	add	global1, 1792, out3       ! sbox 8

	! rotate

	sll	in5, 3, local5
	mov	in1, in3                  ! key address to in3

	sll	out5, 3, local7
	srl	in5, 29, in5

	srl	out5, 29, out5
	add	in5, local5, in5

	add	out5, local7, out5
	cmp	in2, 0

	! we use our own stackframe

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	be,pn	%icc, .encrypt2.dec       ! decryption
#else
	be	.encrypt2.dec
#endif
	STPTR	in0, [%sp+BIAS+ARG0+0*ARGSZ]

	ld	[in3], out0               ! key 7531 first round
	mov	LOOPS, out4               ! loop counter

	ld	[in3+4], out1             ! key 8642 first round
	sethi	%hi(0x0000FC00), local5

	call .des_enc
	mov	in3, in4

	! rotate
	sll	in5, 29, in0
	srl	in5, 3, in5
	sll	out5, 29, in1
	add	in5, in0, in5
	srl	out5, 3, out5
	LDPTR	[%sp+BIAS+ARG0+0*ARGSZ], in0
	add	out5, in1, out5
	st	in5, [in0]
	st	out5, [in0+4]

	ret
	restore


.encrypt2.dec:

	add in3, 120, in4

	ld	[in4], out0               ! key 7531 first round
	mov	LOOPS, out4               ! loop counter

	ld	[in4+4], out1             ! key 8642 first round
	sethi	%hi(0x0000FC00), local5

	mov	in5, local1               ! left expected in out5
	mov	out5, in5

	call .des_dec
	mov	local1, out5

.encrypt2.finish:

	! rotate
	sll	in5, 29, in0
	srl	in5, 3, in5
	sll	out5, 29, in1
	add	in5, in0, in5
	srl	out5, 3, out5
	LDPTR	[%sp+BIAS+ARG0+0*ARGSZ], in0
	add	out5, in1, out5
	st	out5, [in0]
	st	in5, [in0+4]

	ret
	restore

.DES_encrypt2.end:
	.size	 DES_encrypt2, .DES_encrypt2.end-DES_encrypt2


! void DES_encrypt3(data, ks1, ks2, ks3)
! **************************************

	.align 32
	.global DES_encrypt3
	.type	 DES_encrypt3,#function

DES_encrypt3:

	save	%sp, FRAME, %sp
	
	sethi	%hi(.PIC.DES_SPtrans-1f),global1
	or	global1,%lo(.PIC.DES_SPtrans-1f),global1
1:	call	.+8
	add	%o7,global1,global1
	sub	global1,.PIC.DES_SPtrans-.des_and,out2

	ld	[in0], in5                ! left
	add	in2, 120, in4             ! ks2

	ld	[in0+4], out5             ! right
	mov	in3, in2                  ! save ks3

	! parameter 6  1/2 for include encryption/decryption
	! parameter 7  1 for mov in1 to in3
	! parameter 8  1 for mov in3 to in4
	! parameter 9  1 for load ks3 and ks2 to in4 and in3

	ip_macro(in5, out5, in5, out5, in3, 1, 1, 0, 0)

	call	.des_dec
	mov	in2, in3                  ! preload ks3

	call	.des_enc
	nop

	fp_macro(in5, out5, 1)

	ret
	restore

.DES_encrypt3.end:
	.size	 DES_encrypt3,.DES_encrypt3.end-DES_encrypt3


! void DES_decrypt3(data, ks1, ks2, ks3)
! **************************************

	.align 32
	.global DES_decrypt3
	.type	 DES_decrypt3,#function

DES_decrypt3:

	save	%sp, FRAME, %sp
	
	sethi	%hi(.PIC.DES_SPtrans-1f),global1
	or	global1,%lo(.PIC.DES_SPtrans-1f),global1
1:	call	.+8
	add	%o7,global1,global1
	sub	global1,.PIC.DES_SPtrans-.des_and,out2

	ld	[in0], in5                ! left
	add	in3, 120, in4             ! ks3

	ld	[in0+4], out5             ! right
	mov	in2, in3                  ! ks2

	! parameter 6  1/2 for include encryption/decryption
	! parameter 7  1 for mov in1 to in3
	! parameter 8  1 for mov in3 to in4
	! parameter 9  1 for load ks3 and ks2 to in4 and in3

	ip_macro(in5, out5, out5, in5, in4, 2, 0, 0, 0)

	call	.des_enc
	add	in1, 120, in4             ! preload ks1

	call	.des_dec
	nop

	fp_macro(out5, in5, 1)

	ret
	restore

.DES_decrypt3.end:
	.size	 DES_decrypt3,.DES_decrypt3.end-DES_decrypt3

! void DES_ncbc_encrypt(input, output, length, schedule, ivec, enc)
! *****************************************************************


	.align 32
	.global DES_ncbc_encrypt
	.type	 DES_ncbc_encrypt,#function

DES_ncbc_encrypt:

	save	%sp, FRAME, %sp
	
	define({INPUT},  { [%sp+BIAS+ARG0+0*ARGSZ] })
	define({OUTPUT}, { [%sp+BIAS+ARG0+1*ARGSZ] })
	define({IVEC},   { [%sp+BIAS+ARG0+4*ARGSZ] })

	sethi	%hi(.PIC.DES_SPtrans-1f),global1
	or	global1,%lo(.PIC.DES_SPtrans-1f),global1
1:	call	.+8
	add	%o7,global1,global1
	sub	global1,.PIC.DES_SPtrans-.des_and,out2

	cmp	in5, 0                    ! enc   

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	be,pn	%icc, .ncbc.dec
#else
	be	.ncbc.dec
#endif
	STPTR	in4, IVEC

	! addr  left  right  temp  label
	load_little_endian(in4, in5, out5, local3, .LLE1)  ! iv

	addcc	in2, -8, in2              ! bytes missing when first block done

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bl,pn	%icc, .ncbc.enc.seven.or.less
#else
	bl	.ncbc.enc.seven.or.less
#endif
	mov	in3, in4                  ! schedule

.ncbc.enc.next.block:

	load_little_endian(in0, out4, global4, local3, .LLE2)  ! block

.ncbc.enc.next.block_1:

	xor	in5, out4, in5            ! iv xor
	xor	out5, global4, out5       ! iv xor

	! parameter 8  1 for move in3 to in4, 2 for move in4 to in3
	ip_macro(in5, out5, in5, out5, in3, 0, 0, 2)

.ncbc.enc.next.block_2:

!//	call .des_enc                     ! compares in2 to 8
!	rounds inlined for alignment purposes

	add	global1, 768, global4     ! address sbox 4 since register used below

	rounds_macro(in5, out5, 1, .ncbc.enc.1, in3, in4) ! include encryption  ks in3

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bl,pn	%icc, .ncbc.enc.next.block_fp
#else
	bl	.ncbc.enc.next.block_fp
#endif
	add	in0, 8, in0               ! input address

	! If 8 or more bytes are to be encrypted after this block,
	! we combine final permutation for this block with initial
	! permutation for next block. Load next block:

	load_little_endian(in0, global3, global4, local5, .LLE12)

	!  parameter 1   original left
	!  parameter 2   original right
	!  parameter 3   left ip
	!  parameter 4   right ip
	!  parameter 5   1: load ks1/ks2 to in3/in4, add 120 to in4
	!                2: mov in4 to in3
	!
	! also adds -8 to length in2 and loads loop counter to out4

	fp_ip_macro(out0, out1, global3, global4, 2)

	store_little_endian(in1, out0, out1, local3, .SLE10)  ! block

	ld	[in3], out0               ! key 7531 first round next block
	mov 	in5, local1
	xor	global3, out5, in5        ! iv xor next block

	ld	[in3+4], out1             ! key 8642
	add	global1, 512, global3     ! address sbox 3 since register used
	xor	global4, local1, out5     ! iv xor next block

	ba	.ncbc.enc.next.block_2
	add	in1, 8, in1               ! output adress

.ncbc.enc.next.block_fp:

	fp_macro(in5, out5)

	store_little_endian(in1, in5, out5, local3, .SLE1)  ! block

	addcc   in2, -8, in2              ! bytes missing when next block done

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bpos,pt	%icc, .ncbc.enc.next.block  ! also jumps if 0
#else
	bpos	.ncbc.enc.next.block
#endif
	add	in1, 8, in1

.ncbc.enc.seven.or.less:

	cmp	in2, -8

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	ble,pt	%icc, .ncbc.enc.finish
#else
	ble	.ncbc.enc.finish
#endif
	nop

	add	in2, 8, local1            ! bytes to load

	! addr, length, dest left, dest right, temp, temp2, label, ret label
	load_n_bytes(in0, local1, global4, out4, local2, local3, .LNB1, .ncbc.enc.next.block_1)

	! Loads 1 to 7 bytes little endian to global4, out4


.ncbc.enc.finish:

	LDPTR	IVEC, local4
	store_little_endian(local4, in5, out5, local5, .SLE2)  ! ivec

	ret
	restore


.ncbc.dec:

	STPTR	in0, INPUT
	cmp	in2, 0                    ! length
	add	in3, 120, in3

	LDPTR	IVEC, local7              ! ivec
#ifdef OPENSSL_SYSNAME_ULTRASPARC
	ble,pn	%icc, .ncbc.dec.finish
#else
	ble	.ncbc.dec.finish
#endif
	mov	in3, in4                  ! schedule

	STPTR	in1, OUTPUT
	mov	in0, local5               ! input

	load_little_endian(local7, in0, in1, local3, .LLE3)   ! ivec

.ncbc.dec.next.block:

	load_little_endian(local5, in5, out5, local3, .LLE4)  ! block

	! parameter 6  1/2 for include encryption/decryption
	! parameter 7  1 for mov in1 to in3
	! parameter 8  1 for mov in3 to in4

	ip_macro(in5, out5, out5, in5, in4, 2, 0, 1) ! include decryprion  ks in4

	fp_macro(out5, in5, 0, 1) ! 1 for input and output address to local5/7

	! in2 is bytes left to be stored
	! in2 is compared to 8 in the rounds

	xor	out5, in0, out4           ! iv xor
#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bl,pn	%icc, .ncbc.dec.seven.or.less
#else
	bl	.ncbc.dec.seven.or.less
#endif
	xor	in5, in1, global4         ! iv xor

	! Load ivec next block now, since input and output address might be the same.

	load_little_endian_inc(local5, in0, in1, local3, .LLE5)  ! iv

	store_little_endian(local7, out4, global4, local3, .SLE3)

	STPTR	local5, INPUT
	add	local7, 8, local7
	addcc   in2, -8, in2

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bg,pt	%icc, .ncbc.dec.next.block
#else
	bg	.ncbc.dec.next.block
#endif
	STPTR	local7, OUTPUT


.ncbc.dec.store.iv:

	LDPTR	IVEC, local4              ! ivec
	store_little_endian(local4, in0, in1, local5, .SLE4)

.ncbc.dec.finish:

	ret
	restore

.ncbc.dec.seven.or.less:

	load_little_endian_inc(local5, in0, in1, local3, .LLE13)     ! ivec

	store_n_bytes(local7, in2, global4, out4, local3, local4, .SNB1, .ncbc.dec.store.iv)


.DES_ncbc_encrypt.end:
	.size	 DES_ncbc_encrypt, .DES_ncbc_encrypt.end-DES_ncbc_encrypt


! void DES_ede3_cbc_encrypt(input, output, lenght, ks1, ks2, ks3, ivec, enc)
! **************************************************************************


	.align 32
	.global DES_ede3_cbc_encrypt
	.type	 DES_ede3_cbc_encrypt,#function

DES_ede3_cbc_encrypt:

	save	%sp, FRAME, %sp

	define({KS1}, { [%sp+BIAS+ARG0+3*ARGSZ] })
	define({KS2}, { [%sp+BIAS+ARG0+4*ARGSZ] })
	define({KS3}, { [%sp+BIAS+ARG0+5*ARGSZ] })

	sethi	%hi(.PIC.DES_SPtrans-1f),global1
	or	global1,%lo(.PIC.DES_SPtrans-1f),global1
1:	call	.+8
	add	%o7,global1,global1
	sub	global1,.PIC.DES_SPtrans-.des_and,out2

	LDPTR	[%fp+BIAS+ARG0+7*ARGSZ], local3          ! enc
	LDPTR	[%fp+BIAS+ARG0+6*ARGSZ], local4          ! ivec
	cmp	local3, 0                 ! enc

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	be,pn	%icc, .ede3.dec
#else
	be	.ede3.dec
#endif
	STPTR	in4, KS2

	STPTR	in5, KS3

	load_little_endian(local4, in5, out5, local3, .LLE6)  ! ivec

	addcc	in2, -8, in2              ! bytes missing after next block

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bl,pn	%icc,  .ede3.enc.seven.or.less
#else
	bl	.ede3.enc.seven.or.less
#endif
	STPTR	in3, KS1

.ede3.enc.next.block:

	load_little_endian(in0, out4, global4, local3, .LLE7)

.ede3.enc.next.block_1:

	LDPTR	KS2, in4
	xor	in5, out4, in5            ! iv xor
	xor	out5, global4, out5       ! iv xor

	LDPTR	KS1, in3
	add	in4, 120, in4             ! for decryption we use last subkey first
	nop

	ip_macro(in5, out5, in5, out5, in3)

.ede3.enc.next.block_2:

	call .des_enc                     ! ks1 in3
	nop

	call .des_dec                     ! ks2 in4
	LDPTR	KS3, in3

	call .des_enc                     ! ks3 in3  compares in2 to 8
	nop

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bl,pn	%icc, .ede3.enc.next.block_fp
#else
	bl	.ede3.enc.next.block_fp
#endif
	add	in0, 8, in0

	! If 8 or more bytes are to be encrypted after this block,
	! we combine final permutation for this block with initial
	! permutation for next block. Load next block:

	load_little_endian(in0, global3, global4, local5, .LLE11)

	!  parameter 1   original left
	!  parameter 2   original right
	!  parameter 3   left ip
	!  parameter 4   right ip
	!  parameter 5   1: load ks1/ks2 to in3/in4, add 120 to in4
	!                2: mov in4 to in3
	!
	! also adds -8 to length in2 and loads loop counter to out4

	fp_ip_macro(out0, out1, global3, global4, 1)

	store_little_endian(in1, out0, out1, local3, .SLE9)  ! block

	mov 	in5, local1
	xor	global3, out5, in5        ! iv xor next block

	ld	[in3], out0               ! key 7531
	add	global1, 512, global3     ! address sbox 3
	xor	global4, local1, out5     ! iv xor next block

	ld	[in3+4], out1             ! key 8642
	add	global1, 768, global4     ! address sbox 4
	ba	.ede3.enc.next.block_2
	add	in1, 8, in1

.ede3.enc.next.block_fp:

	fp_macro(in5, out5)

	store_little_endian(in1, in5, out5, local3, .SLE5)  ! block

	addcc   in2, -8, in2              ! bytes missing when next block done

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bpos,pt	%icc, .ede3.enc.next.block
#else
	bpos	.ede3.enc.next.block
#endif
	add	in1, 8, in1

.ede3.enc.seven.or.less:

	cmp	in2, -8

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	ble,pt	%icc, .ede3.enc.finish
#else
	ble	.ede3.enc.finish
#endif
	nop

	add	in2, 8, local1            ! bytes to load

	! addr, length, dest left, dest right, temp, temp2, label, ret label
	load_n_bytes(in0, local1, global4, out4, local2, local3, .LNB2, .ede3.enc.next.block_1)

.ede3.enc.finish:

	LDPTR	[%fp+BIAS+ARG0+6*ARGSZ], local4          ! ivec
	store_little_endian(local4, in5, out5, local5, .SLE6)  ! ivec

	ret
	restore

.ede3.dec:

	STPTR	in0, INPUT
	add	in5, 120, in5

	STPTR	in1, OUTPUT
	mov	in0, local5
	add	in3, 120, in3

	STPTR	in3, KS1
	cmp	in2, 0

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	ble	%icc, .ede3.dec.finish
#else
	ble	.ede3.dec.finish
#endif
	STPTR	in5, KS3

	LDPTR	[%fp+BIAS+ARG0+6*ARGSZ], local7          ! iv
	load_little_endian(local7, in0, in1, local3, .LLE8)

.ede3.dec.next.block:

	load_little_endian(local5, in5, out5, local3, .LLE9)

	! parameter 6  1/2 for include encryption/decryption
	! parameter 7  1 for mov in1 to in3
	! parameter 8  1 for mov in3 to in4
	! parameter 9  1 for load ks3 and ks2 to in4 and in3

	ip_macro(in5, out5, out5, in5, in4, 2, 0, 0, 1) ! inc .des_dec ks3 in4

	call .des_enc                     ! ks2 in3
	LDPTR	KS1, in4

	call .des_dec                     ! ks1 in4
	nop

	fp_macro(out5, in5, 0, 1)   ! 1 for input and output address local5/7

	! in2 is bytes left to be stored
	! in2 is compared to 8 in the rounds

	xor	out5, in0, out4
#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bl,pn	%icc, .ede3.dec.seven.or.less
#else
	bl	.ede3.dec.seven.or.less
#endif
	xor	in5, in1, global4

	load_little_endian_inc(local5, in0, in1, local3, .LLE10)   ! iv next block

	store_little_endian(local7, out4, global4, local3, .SLE7)  ! block

	STPTR	local5, INPUT
	addcc   in2, -8, in2
	add	local7, 8, local7

#ifdef OPENSSL_SYSNAME_ULTRASPARC
	bg,pt	%icc, .ede3.dec.next.block
#else
	bg	.ede3.dec.next.block
#endif
	STPTR	local7, OUTPUT

.ede3.dec.store.iv:

	LDPTR	[%fp+BIAS+ARG0+6*ARGSZ], local4          ! ivec
	store_little_endian(local4, in0, in1, local5, .SLE8)  ! ivec

.ede3.dec.finish:

	ret
	restore

.ede3.dec.seven.or.less:

	load_little_endian_inc(local5, in0, in1, local3, .LLE14)     ! iv

	store_n_bytes(local7, in2, global4, out4, local3, local4, .SNB2, .ede3.dec.store.iv)


.DES_ede3_cbc_encrypt.end:
	.size	 DES_ede3_cbc_encrypt,.DES_ede3_cbc_encrypt.end-DES_ede3_cbc_encrypt

	.align	256
	.type	 .des_and,#object
	.size	 .des_and,284

.des_and:

! This table is used for AND 0xFC when it is known that register
! bits 8-31 are zero. Makes it possible to do three arithmetic
! operations in one cycle.

	.byte  0, 0, 0, 0, 4, 4, 4, 4
	.byte  8, 8, 8, 8, 12, 12, 12, 12
	.byte  16, 16, 16, 16, 20, 20, 20, 20
	.byte  24, 24, 24, 24, 28, 28, 28, 28
	.byte  32, 32, 32, 32, 36, 36, 36, 36
	.byte  40, 40, 40, 40, 44, 44, 44, 44
	.byte  48, 48, 48, 48, 52, 52, 52, 52
	.byte  56, 56, 56, 56, 60, 60, 60, 60
	.byte  64, 64, 64, 64, 68, 68, 68, 68
	.byte  72, 72, 72, 72, 76, 76, 76, 76
	.byte  80, 80, 80, 80, 84, 84, 84, 84
	.byte  88, 88, 88, 88, 92, 92, 92, 92
	.byte  96, 96, 96, 96, 100, 100, 100, 100
	.byte  104, 104, 104, 104, 108, 108, 108, 108
	.byte  112, 112, 112, 112, 116, 116, 116, 116
	.byte  120, 120, 120, 120, 124, 124, 124, 124
	.byte  128, 128, 128, 128, 132, 132, 132, 132
	.byte  136, 136, 136, 136, 140, 140, 140, 140
	.byte  144, 144, 144, 144, 148, 148, 148, 148
	.byte  152, 152, 152, 152, 156, 156, 156, 156
	.byte  160, 160, 160, 160, 164, 164, 164, 164
	.byte  168, 168, 168, 168, 172, 172, 172, 172
	.byte  176, 176, 176, 176, 180, 180, 180, 180
	.byte  184, 184, 184, 184, 188, 188, 188, 188
	.byte  192, 192, 192, 192, 196, 196, 196, 196
	.byte  200, 200, 200, 200, 204, 204, 204, 204
	.byte  208, 208, 208, 208, 212, 212, 212, 212
	.byte  216, 216, 216, 216, 220, 220, 220, 220
	.byte  224, 224, 224, 224, 228, 228, 228, 228
	.byte  232, 232, 232, 232, 236, 236, 236, 236
	.byte  240, 240, 240, 240, 244, 244, 244, 244
	.byte  248, 248, 248, 248, 252, 252, 252, 252

	! 5 numbers for initil/final permutation

	.word   0x0f0f0f0f                ! offset 256
	.word	0x0000ffff                ! 260
	.word	0x33333333                ! 264
	.word	0x00ff00ff                ! 268
	.word	0x55555555                ! 272

	.word	0                         ! 276
	.word	LOOPS                     ! 280
	.word	0x0000FC00                ! 284

	.global	DES_SPtrans
	.type	DES_SPtrans,#object
	.size	DES_SPtrans,2048
.align	64
DES_SPtrans:
.PIC.DES_SPtrans:
	! nibble 0
	.word	0x02080800, 0x00080000, 0x02000002, 0x02080802
	.word	0x02000000, 0x00080802, 0x00080002, 0x02000002
	.word	0x00080802, 0x02080800, 0x02080000, 0x00000802
	.word	0x02000802, 0x02000000, 0x00000000, 0x00080002
	.word	0x00080000, 0x00000002, 0x02000800, 0x00080800
	.word	0x02080802, 0x02080000, 0x00000802, 0x02000800
	.word	0x00000002, 0x00000800, 0x00080800, 0x02080002
	.word	0x00000800, 0x02000802, 0x02080002, 0x00000000
	.word	0x00000000, 0x02080802, 0x02000800, 0x00080002
	.word	0x02080800, 0x00080000, 0x00000802, 0x02000800
	.word	0x02080002, 0x00000800, 0x00080800, 0x02000002
	.word	0x00080802, 0x00000002, 0x02000002, 0x02080000
	.word	0x02080802, 0x00080800, 0x02080000, 0x02000802
	.word	0x02000000, 0x00000802, 0x00080002, 0x00000000
	.word	0x00080000, 0x02000000, 0x02000802, 0x02080800
	.word	0x00000002, 0x02080002, 0x00000800, 0x00080802
	! nibble 1
	.word	0x40108010, 0x00000000, 0x00108000, 0x40100000
	.word	0x40000010, 0x00008010, 0x40008000, 0x00108000
	.word	0x00008000, 0x40100010, 0x00000010, 0x40008000
	.word	0x00100010, 0x40108000, 0x40100000, 0x00000010
	.word	0x00100000, 0x40008010, 0x40100010, 0x00008000
	.word	0x00108010, 0x40000000, 0x00000000, 0x00100010
	.word	0x40008010, 0x00108010, 0x40108000, 0x40000010
	.word	0x40000000, 0x00100000, 0x00008010, 0x40108010
	.word	0x00100010, 0x40108000, 0x40008000, 0x00108010
	.word	0x40108010, 0x00100010, 0x40000010, 0x00000000
	.word	0x40000000, 0x00008010, 0x00100000, 0x40100010
	.word	0x00008000, 0x40000000, 0x00108010, 0x40008010
	.word	0x40108000, 0x00008000, 0x00000000, 0x40000010
	.word	0x00000010, 0x40108010, 0x00108000, 0x40100000
	.word	0x40100010, 0x00100000, 0x00008010, 0x40008000
	.word	0x40008010, 0x00000010, 0x40100000, 0x00108000
	! nibble 2
	.word	0x04000001, 0x04040100, 0x00000100, 0x04000101
	.word	0x00040001, 0x04000000, 0x04000101, 0x00040100
	.word	0x04000100, 0x00040000, 0x04040000, 0x00000001
Show full blame