#!/usr/bin/env perl
######################################################################
## Constant-time SSSE3 AES core implementation.
## version 0.1
##
## By Mike Hamburg (Stanford University), 2009
## Public domain.
##
## For details see http://shiftleft.org/papers/vector_aes/ and
## http://crypto.stanford.edu/vpaes/.
##
######################################################################
# ARMv8 NEON adaptation by <appro@openssl.org>
#
# Reason for undertaken effort is that there is at least one popular
# SoC based on Cortex-A53 that doesn't have crypto extensions.
#
# CBC enc ECB enc/dec(*) [bit-sliced enc/dec]
# Cortex-A53 21.5 18.1/20.6 [17.5/19.8 ]
# Cortex-A57 36.0(**) 20.4/24.9(**) [14.4/16.6 ]
# X-Gene 45.9(**) 45.8/57.7(**) [33.1/37.6(**) ]
# Denver(***) 16.6(**) 15.1/17.8(**) [8.80/9.93 ]
# Apple A7(***) 22.7(**) 10.9/14.3 [8.45/10.0 ]
#
# (*) ECB denotes approximate result for parallelizeable modes
# such as CBC decrypt, CTR, etc.;
# (**) these results are worse than scalar compiler-generated
# code, but it's constant-time and therefore preferred;
# (***) presented for reference/comparison purposes;
$flavour = shift;
while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
die "can't locate arm-xlate.pl";
open OUT,"| \"$^X\" $xlate $flavour $output";
*STDOUT=*OUT;
$code.=<<___;
.text
.type _vpaes_consts,%object
.align 7 // totally strategic alignment
_vpaes_consts:
.Lk_mc_forward: // mc_forward
.quad 0x0407060500030201, 0x0C0F0E0D080B0A09
.quad 0x080B0A0904070605, 0x000302010C0F0E0D
.quad 0x0C0F0E0D080B0A09, 0x0407060500030201
.quad 0x000302010C0F0E0D, 0x080B0A0904070605
.Lk_mc_backward:// mc_backward
.quad 0x0605040702010003, 0x0E0D0C0F0A09080B
.quad 0x020100030E0D0C0F, 0x0A09080B06050407
.quad 0x0E0D0C0F0A09080B, 0x0605040702010003
.quad 0x0A09080B06050407, 0x020100030E0D0C0F
.Lk_sr: // sr
.quad 0x0706050403020100, 0x0F0E0D0C0B0A0908
.quad 0x030E09040F0A0500, 0x0B06010C07020D08
.quad 0x0F060D040B020900, 0x070E050C030A0108
.quad 0x0B0E0104070A0D00, 0x0306090C0F020508
//
// "Hot" constants
//
.Lk_inv: // inv, inva
.quad 0x0E05060F0D080180, 0x040703090A0B0C02
.quad 0x01040A060F0B0780, 0x030D0E0C02050809
.Lk_ipt: // input transform (lo, hi)
.quad 0xC2B2E8985A2A7000, 0xCABAE09052227808
.quad 0x4C01307D317C4D00, 0xCD80B1FCB0FDCC81
.Lk_sbo: // sbou, sbot
.quad 0xD0D26D176FBDC700, 0x15AABF7AC502A878
.quad 0xCFE474A55FBB6A00, 0x8E1E90D1412B35FA
.Lk_sb1: // sb1u, sb1t
.quad 0x3618D415FAE22300, 0x3BF7CCC10D2ED9EF
.quad 0xB19BE18FCB503E00, 0xA5DF7A6E142AF544
.Lk_sb2: // sb2u, sb2t
.quad 0x69EB88400AE12900, 0xC2A163C8AB82234A
.quad 0xE27A93C60B712400, 0x5EB7E955BC982FCD
//
// Decryption stuff
//
.Lk_dipt: // decryption input transform
.quad 0x0F505B040B545F00, 0x154A411E114E451A
.quad 0x86E383E660056500, 0x12771772F491F194
.Lk_dsbo: // decryption sbox final output
.quad 0x1387EA537EF94000, 0xC7AA6DB9D4943E2D
.quad 0x12D7560F93441D00, 0xCA4B8159D8C58E9C
.Lk_dsb9: // decryption sbox output *9*u, *9*t
.quad 0x851C03539A86D600, 0xCAD51F504F994CC9
.quad 0xC03B1789ECD74900, 0x725E2C9EB2FBA565
.Lk_dsbd: // decryption sbox output *D*u, *D*t
.quad 0x7D57CCDFE6B1A200, 0xF56E9B13882A4439
.quad 0x3CE2FAF724C6CB00, 0x2931180D15DEEFD3
.Lk_dsbb: // decryption sbox output *B*u, *B*t
.quad 0xD022649296B44200, 0x602646F6B0F2D404
.quad 0xC19498A6CD596700, 0xF3FF0C3E3255AA6B
.Lk_dsbe: // decryption sbox output *E*u, *E*t
.quad 0x46F2929626D4D000, 0x2242600464B4F6B0
.quad 0x0C55A6CDFFAAC100, 0x9467F36B98593E32
//
// Key schedule constants
//
.Lk_dksd: // decryption key schedule: invskew x*D
.quad 0xFEB91A5DA3E44700, 0x0740E3A45A1DBEF9
.quad 0x41C277F4B5368300, 0x5FDC69EAAB289D1E
.Lk_dksb: // decryption key schedule: invskew x*B
.quad 0x9A4FCA1F8550D500, 0x03D653861CC94C99
.quad 0x115BEDA7B6FC4A00, 0xD993256F7E3482C8
.Lk_dkse: // decryption key schedule: invskew x*E + 0x63
.quad 0xD5031CCA1FC9D600, 0x53859A4C994F5086
.quad 0xA23196054FDC7BE8, 0xCD5EF96A20B31487
.Lk_dks9: // decryption key schedule: invskew x*9
.quad 0xB6116FC87ED9A700, 0x4AED933482255BFC
.quad 0x4576516227143300, 0x8BB89FACE9DAFDCE
.Lk_rcon: // rcon
.quad 0x1F8391B9AF9DEEB6, 0x702A98084D7C7D81
.Lk_opt: // output transform
.quad 0xFF9F4929D6B66000, 0xF7974121DEBE6808
.quad 0x01EDBD5150BCEC00, 0xE10D5DB1B05C0CE0
.Lk_deskew: // deskew tables: inverts the sbox's "skew"
.quad 0x07E4A34047A4E300, 0x1DFEB95A5DBEF91A
.quad 0x5F36B5DC83EA6900, 0x2841C2ABF49D1E77
.asciz "Vector Permutaion AES for ARMv8, Mike Hamburg (Stanford University)"
.size _vpaes_consts,.-_vpaes_consts
.align 6
___
{
my ($inp,$out,$key) = map("x$_",(0..2));
my ($invlo,$invhi,$iptlo,$ipthi,$sbou,$sbot) = map("v$_.16b",(18..23));
my ($sb1u,$sb1t,$sb2u,$sb2t) = map("v$_.16b",(24..27));
my ($sb9u,<