2016-05-21 20:23:39 +08:00
|
|
|
#! /usr/bin/env perl
|
2023-09-07 16:59:15 +08:00
|
|
|
# Copyright 2011-2023 The OpenSSL Project Authors. All Rights Reserved.
|
2016-05-21 20:23:39 +08:00
|
|
|
#
|
2018-12-06 20:22:12 +08:00
|
|
|
# Licensed under the Apache License 2.0 (the "License"). You may not use
|
2016-05-21 20:23:39 +08:00
|
|
|
# this file except in compliance with the License. You can obtain a copy
|
|
|
|
|
# in the file LICENSE in the source distribution or at
|
|
|
|
|
# https://www.openssl.org/source/license.html
|
|
|
|
|
|
2011-05-05 15:21:17 +08:00
|
|
|
#
|
|
|
|
|
# ====================================================================
|
|
|
|
|
# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
|
|
|
|
|
# project. The module is, however, dual licensed under OpenSSL and
|
|
|
|
|
# CRYPTOGAMS licenses depending on where you obtain it. For further
|
|
|
|
|
# details see http://www.openssl.org/~appro/cryptogams/.
|
|
|
|
|
# ====================================================================
|
|
|
|
|
#
|
|
|
|
|
# May 2011
|
|
|
|
|
#
|
|
|
|
|
# The module implements bn_GF2m_mul_2x2 polynomial multiplication
|
|
|
|
|
# used in bn_gf2m.c. It's kind of low-hanging mechanical port from
|
|
|
|
|
# C for the time being... Except that it has two code paths: pure
|
|
|
|
|
# integer code suitable for any ARMv4 and later CPU and NEON code
|
|
|
|
|
# suitable for ARMv7. Pure integer 1x1 multiplication subroutine runs
|
|
|
|
|
# in ~45 cycles on dual-issue core such as Cortex A8, which is ~50%
|
|
|
|
|
# faster than compiler-generated code. For ECDH and ECDSA verify (but
|
|
|
|
|
# not for ECDSA sign) it means 25%-45% improvement depending on key
|
|
|
|
|
# length, more for longer keys. Even though NEON 1x1 multiplication
|
|
|
|
|
# runs in even less cycles, ~30, improvement is measurable only on
|
|
|
|
|
# longer keys. One has to optimize code elsewhere to get NEON glow...
|
2014-04-24 16:16:58 +08:00
|
|
|
#
|
|
|
|
|
# April 2014
|
|
|
|
|
#
|
|
|
|
|
# Double bn_GF2m_mul_2x2 performance by using algorithm from paper
|
|
|
|
|
# referred below, which improves ECDH and ECDSA verify benchmarks
|
|
|
|
|
# by 18-40%.
|
|
|
|
|
#
|
2015-07-13 22:53:37 +08:00
|
|
|
# Câmara, D.; Gouvêa, C. P. L.; López, J. & Dahab, R.: Fast Software
|
2014-04-24 16:16:58 +08:00
|
|
|
# Polynomial Multiplication on ARM Processors using the NEON Engine.
|
2016-10-11 00:01:24 +08:00
|
|
|
#
|
2014-04-24 16:16:58 +08:00
|
|
|
# http://conradoplg.cryptoland.net/files/2010/12/mocrysen13.pdf
|
2011-05-05 15:21:17 +08:00
|
|
|
|
Unify all assembler file generators
They now generally conform to the following argument sequence:
script.pl "$(PERLASM_SCHEME)" [ C preprocessor arguments ... ] \
$(PROCESSOR) <output file>
However, in the spirit of being able to use these scripts manually,
they also allow for no argument, or for only the flavour, or for only
the output file. This is done by only using the last argument as
output file if it's a file (it has an extension), and only using the
first argument as flavour if it isn't a file (it doesn't have an
extension).
While we're at it, we make all $xlate calls the same, i.e. the $output
argument is always quoted, and we always die on error when trying to
start $xlate.
There's a perl lesson in this, regarding operator priority...
This will always succeed, even when it fails:
open FOO, "something" || die "ERR: $!";
The reason is that '||' has higher priority than list operators (a
function is essentially a list operator and gobbles up everything
following it that isn't lower priority), and since a non-empty string
is always true, so that ends up being exactly the same as:
open FOO, "something";
This, however, will fail if "something" can't be opened:
open FOO, "something" or die "ERR: $!";
The reason is that 'or' has lower priority that list operators,
i.e. it's performed after the 'open' call.
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/9884)
2019-09-13 06:06:46 +08:00
|
|
|
# $output is the last argument if it looks like a file (it has an extension)
|
|
|
|
|
# $flavour is the first argument if it doesn't look like a file
|
|
|
|
|
$output = $#ARGV >= 0 && $ARGV[$#ARGV] =~ m|\.\w+$| ? pop : undef;
|
|
|
|
|
$flavour = $#ARGV >= 0 && $ARGV[0] !~ m|\.| ? shift : undef;
|
2015-04-02 16:17:42 +08:00
|
|
|
|
|
|
|
|
if ($flavour && $flavour ne "void") {
|
|
|
|
|
$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
|
|
|
|
|
( $xlate="${dir}arm-xlate.pl" and -f $xlate ) or
|
|
|
|
|
( $xlate="${dir}../../perlasm/arm-xlate.pl" and -f $xlate) or
|
|
|
|
|
die "can't locate arm-xlate.pl";
|
|
|
|
|
|
Unify all assembler file generators
They now generally conform to the following argument sequence:
script.pl "$(PERLASM_SCHEME)" [ C preprocessor arguments ... ] \
$(PROCESSOR) <output file>
However, in the spirit of being able to use these scripts manually,
they also allow for no argument, or for only the flavour, or for only
the output file. This is done by only using the last argument as
output file if it's a file (it has an extension), and only using the
first argument as flavour if it isn't a file (it doesn't have an
extension).
While we're at it, we make all $xlate calls the same, i.e. the $output
argument is always quoted, and we always die on error when trying to
start $xlate.
There's a perl lesson in this, regarding operator priority...
This will always succeed, even when it fails:
open FOO, "something" || die "ERR: $!";
The reason is that '||' has higher priority than list operators (a
function is essentially a list operator and gobbles up everything
following it that isn't lower priority), and since a non-empty string
is always true, so that ends up being exactly the same as:
open FOO, "something";
This, however, will fail if "something" can't be opened:
open FOO, "something" or die "ERR: $!";
The reason is that 'or' has lower priority that list operators,
i.e. it's performed after the 'open' call.
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/9884)
2019-09-13 06:06:46 +08:00
|
|
|
open STDOUT,"| \"$^X\" $xlate $flavour \"$output\""
|
|
|
|
|
or die "can't call $xlate: $1";
|
2015-04-02 16:17:42 +08:00
|
|
|
} else {
|
Unify all assembler file generators
They now generally conform to the following argument sequence:
script.pl "$(PERLASM_SCHEME)" [ C preprocessor arguments ... ] \
$(PROCESSOR) <output file>
However, in the spirit of being able to use these scripts manually,
they also allow for no argument, or for only the flavour, or for only
the output file. This is done by only using the last argument as
output file if it's a file (it has an extension), and only using the
first argument as flavour if it isn't a file (it doesn't have an
extension).
While we're at it, we make all $xlate calls the same, i.e. the $output
argument is always quoted, and we always die on error when trying to
start $xlate.
There's a perl lesson in this, regarding operator priority...
This will always succeed, even when it fails:
open FOO, "something" || die "ERR: $!";
The reason is that '||' has higher priority than list operators (a
function is essentially a list operator and gobbles up everything
following it that isn't lower priority), and since a non-empty string
is always true, so that ends up being exactly the same as:
open FOO, "something";
This, however, will fail if "something" can't be opened:
open FOO, "something" or die "ERR: $!";
The reason is that 'or' has lower priority that list operators,
i.e. it's performed after the 'open' call.
Reviewed-by: Matt Caswell <matt@openssl.org>
(Merged from https://github.com/openssl/openssl/pull/9884)
2019-09-13 06:06:46 +08:00
|
|
|
$output and open STDOUT,">$output";
|
2015-04-02 16:17:42 +08:00
|
|
|
}
|
2011-05-05 15:21:17 +08:00
|
|
|
|
|
|
|
|
$code=<<___;
|
|
|
|
|
#include "arm_arch.h"
|
|
|
|
|
|
2015-12-07 05:02:39 +08:00
|
|
|
#if defined(__thumb2__)
|
2015-09-24 00:41:27 +08:00
|
|
|
.syntax unified
|
|
|
|
|
.thumb
|
|
|
|
|
#else
|
2011-05-05 15:21:17 +08:00
|
|
|
.code 32
|
2015-09-24 00:41:27 +08:00
|
|
|
#endif
|
2019-02-15 16:44:39 +08:00
|
|
|
|
|
|
|
|
.text
|
2011-05-06 05:57:11 +08:00
|
|
|
___
|
|
|
|
|
################
|
|
|
|
|
# private interface to mul_1x1_ialu
|
|
|
|
|
#
|
|
|
|
|
$a="r1";
|
|
|
|
|
$b="r0";
|
2011-05-05 15:21:17 +08:00
|
|
|
|
2011-05-06 05:57:11 +08:00
|
|
|
($a0,$a1,$a2,$a12,$a4,$a14)=
|
|
|
|
|
($hi,$lo,$t0,$t1, $i0,$i1 )=map("r$_",(4..9),12);
|
|
|
|
|
|
|
|
|
|
$mask="r12";
|
|
|
|
|
|
|
|
|
|
$code.=<<___;
|
2011-05-05 15:21:17 +08:00
|
|
|
.type mul_1x1_ialu,%function
|
2011-05-06 05:57:11 +08:00
|
|
|
.align 5
|
2011-05-05 15:21:17 +08:00
|
|
|
mul_1x1_ialu:
|
|
|
|
|
mov $a0,#0
|
|
|
|
|
bic $a1,$a,#3<<30 @ a1=a&0x3fffffff
|
|
|
|
|
str $a0,[sp,#0] @ tab[0]=0
|
|
|
|
|
add $a2,$a1,$a1 @ a2=a1<<1
|
|
|
|
|
str $a1,[sp,#4] @ tab[1]=a1
|
|
|
|
|
eor $a12,$a1,$a2 @ a1^a2
|
|
|
|
|
str $a2,[sp,#8] @ tab[2]=a2
|
|
|
|
|
mov $a4,$a1,lsl#2 @ a4=a1<<2
|
|
|
|
|
str $a12,[sp,#12] @ tab[3]=a1^a2
|
|
|
|
|
eor $a14,$a1,$a4 @ a1^a4
|
|
|
|
|
str $a4,[sp,#16] @ tab[4]=a4
|
|
|
|
|
eor $a0,$a2,$a4 @ a2^a4
|
|
|
|
|
str $a14,[sp,#20] @ tab[5]=a1^a4
|
|
|
|
|
eor $a12,$a12,$a4 @ a1^a2^a4
|
|
|
|
|
str $a0,[sp,#24] @ tab[6]=a2^a4
|
|
|
|
|
and $i0,$mask,$b,lsl#2
|
|
|
|
|
str $a12,[sp,#28] @ tab[7]=a1^a2^a4
|
|
|
|
|
|
|
|
|
|
and $i1,$mask,$b,lsr#1
|
|
|
|
|
ldr $lo,[sp,$i0] @ tab[b & 0x7]
|
|
|
|
|
and $i0,$mask,$b,lsr#4
|
|
|
|
|
ldr $t1,[sp,$i1] @ tab[b >> 3 & 0x7]
|
|
|
|
|
and $i1,$mask,$b,lsr#7
|
|
|
|
|
ldr $t0,[sp,$i0] @ tab[b >> 6 & 0x7]
|
|
|
|
|
eor $lo,$lo,$t1,lsl#3 @ stall
|
|
|
|
|
mov $hi,$t1,lsr#29
|
|
|
|
|
ldr $t1,[sp,$i1] @ tab[b >> 9 & 0x7]
|
|
|
|
|
|
|
|
|
|
and $i0,$mask,$b,lsr#10
|
|
|
|
|
eor $lo,$lo,$t0,lsl#6
|
|
|
|
|
eor $hi,$hi,$t0,lsr#26
|
|
|
|
|
ldr $t0,[sp,$i0] @ tab[b >> 12 & 0x7]
|
|
|
|
|
|
|
|
|
|
and $i1,$mask,$b,lsr#13
|
|
|
|
|
eor $lo,$lo,$t1,lsl#9
|
|
|
|
|
eor $hi,$hi,$t1,lsr#23
|
|
|
|
|
ldr $t1,[sp,$i1] @ tab[b >> 15 & 0x7]
|
|
|
|
|
|
|
|
|
|
and $i0,$mask,$b,lsr#16
|
|
|
|
|
eor $lo,$lo,$t0,lsl#12
|
|
|
|
|
eor $hi,$hi,$t0,lsr#20
|
|
|
|
|
ldr $t0,[sp,$i0] @ tab[b >> 18 & 0x7]
|
|
|
|
|
|
|
|
|
|
and $i1,$mask,$b,lsr#19
|
|
|
|
|
eor $lo,$lo,$t1,lsl#15
|
|
|
|
|
eor $hi,$hi,$t1,lsr#17
|
|
|
|
|
ldr $t1,[sp,$i1] @ tab[b >> 21 & 0x7]
|
|
|
|
|
|
|
|
|
|
and $i0,$mask,$b,lsr#22
|
|
|
|
|
eor $lo,$lo,$t0,lsl#18
|
|
|
|
|
eor $hi,$hi,$t0,lsr#14
|
|
|
|
|
ldr $t0,[sp,$i0] @ tab[b >> 24 & 0x7]
|
|
|
|
|
|
|
|
|
|
and $i1,$mask,$b,lsr#25
|
|
|
|
|
eor $lo,$lo,$t1,lsl#21
|
|
|
|
|
eor $hi,$hi,$t1,lsr#11
|
|
|
|
|
ldr $t1,[sp,$i1] @ tab[b >> 27 & 0x7]
|
|
|
|
|
|
|
|
|
|
tst $a,#1<<30
|
|
|
|
|
and $i0,$mask,$b,lsr#28
|
|
|
|
|
eor $lo,$lo,$t0,lsl#24
|
|
|
|
|
eor $hi,$hi,$t0,lsr#8
|
|
|
|
|
ldr $t0,[sp,$i0] @ tab[b >> 30 ]
|
|
|
|
|
|
2015-09-24 00:41:27 +08:00
|
|
|
#ifdef __thumb2__
|
|
|
|
|
itt ne
|
|
|
|
|
#endif
|
2011-05-05 15:21:17 +08:00
|
|
|
eorne $lo,$lo,$b,lsl#30
|
|
|
|
|
eorne $hi,$hi,$b,lsr#2
|
|
|
|
|
tst $a,#1<<31
|
|
|
|
|
eor $lo,$lo,$t1,lsl#27
|
|
|
|
|
eor $hi,$hi,$t1,lsr#5
|
2015-09-24 00:41:27 +08:00
|
|
|
#ifdef __thumb2__
|
|
|
|
|
itt ne
|
|
|
|
|
#endif
|
2011-05-05 15:21:17 +08:00
|
|
|
eorne $lo,$lo,$b,lsl#31
|
|
|
|
|
eorne $hi,$hi,$b,lsr#1
|
|
|
|
|
eor $lo,$lo,$t0,lsl#30
|
|
|
|
|
eor $hi,$hi,$t0,lsr#2
|
|
|
|
|
|
|
|
|
|
mov pc,lr
|
|
|
|
|
.size mul_1x1_ialu,.-mul_1x1_ialu
|
2011-05-06 05:57:11 +08:00
|
|
|
___
|
|
|
|
|
################
|
|
|
|
|
# void bn_GF2m_mul_2x2(BN_ULONG *r,
|
|
|
|
|
# BN_ULONG a1,BN_ULONG a0,
|
2015-07-13 22:53:37 +08:00
|
|
|
# BN_ULONG b1,BN_ULONG b0); # r[3..0]=a1a0·b1b0
|
2014-04-24 16:16:58 +08:00
|
|
|
{
|
2011-05-06 05:57:11 +08:00
|
|
|
$code.=<<___;
|
2011-05-05 15:21:17 +08:00
|
|
|
.global bn_GF2m_mul_2x2
|
|
|
|
|
.type bn_GF2m_mul_2x2,%function
|
|
|
|
|
.align 5
|
|
|
|
|
bn_GF2m_mul_2x2:
|
2014-11-08 05:48:22 +08:00
|
|
|
#if __ARM_MAX_ARCH__>=7
|
2015-09-24 00:41:27 +08:00
|
|
|
stmdb sp!,{r10,lr}
|
2011-05-05 15:21:17 +08:00
|
|
|
ldr r12,.LOPENSSL_armcap
|
2019-02-15 16:44:39 +08:00
|
|
|
# if !defined(_WIN32)
|
2015-09-24 00:41:27 +08:00
|
|
|
adr r10,.LOPENSSL_armcap
|
|
|
|
|
ldr r12,[r12,r10]
|
2019-02-15 16:44:39 +08:00
|
|
|
# endif
|
|
|
|
|
# if defined(__APPLE__) || defined(_WIN32)
|
2015-09-24 00:41:27 +08:00
|
|
|
ldr r12,[r12]
|
2019-02-15 16:44:39 +08:00
|
|
|
# endif
|
2015-09-24 00:41:27 +08:00
|
|
|
tst r12,#ARMV7_NEON
|
|
|
|
|
itt ne
|
|
|
|
|
ldrne r10,[sp],#8
|
2014-11-08 05:48:22 +08:00
|
|
|
bne .LNEON
|
2015-09-24 00:41:27 +08:00
|
|
|
stmdb sp!,{r4-r9}
|
|
|
|
|
#else
|
|
|
|
|
stmdb sp!,{r4-r10,lr}
|
2014-11-08 05:48:22 +08:00
|
|
|
#endif
|
|
|
|
|
___
|
|
|
|
|
$ret="r10"; # reassigned 1st argument
|
|
|
|
|
$code.=<<___;
|
|
|
|
|
mov $ret,r0 @ reassign 1st argument
|
|
|
|
|
mov $b,r3 @ $b=b1
|
2015-09-24 00:41:27 +08:00
|
|
|
sub r7,sp,#36
|
|
|
|
|
mov r8,sp
|
|
|
|
|
and r7,r7,#-32
|
2014-11-08 05:48:22 +08:00
|
|
|
ldr r3,[sp,#32] @ load b0
|
|
|
|
|
mov $mask,#7<<2
|
2015-09-24 00:41:27 +08:00
|
|
|
mov sp,r7 @ allocate tab[8]
|
|
|
|
|
str r8,[r7,#32]
|
2014-11-08 05:48:22 +08:00
|
|
|
|
2015-07-13 22:53:37 +08:00
|
|
|
bl mul_1x1_ialu @ a1·b1
|
2014-11-08 05:48:22 +08:00
|
|
|
str $lo,[$ret,#8]
|
|
|
|
|
str $hi,[$ret,#12]
|
|
|
|
|
|
|
|
|
|
eor $b,$b,r3 @ flip b0 and b1
|
|
|
|
|
eor $a,$a,r2 @ flip a0 and a1
|
|
|
|
|
eor r3,r3,$b
|
|
|
|
|
eor r2,r2,$a
|
|
|
|
|
eor $b,$b,r3
|
|
|
|
|
eor $a,$a,r2
|
2015-07-13 22:53:37 +08:00
|
|
|
bl mul_1x1_ialu @ a0·b0
|
2014-11-08 05:48:22 +08:00
|
|
|
str $lo,[$ret]
|
|
|
|
|
str $hi,[$ret,#4]
|
2011-05-06 05:57:11 +08:00
|
|
|
|
2014-11-08 05:48:22 +08:00
|
|
|
eor $a,$a,r2
|
|
|
|
|
eor $b,$b,r3
|
2015-07-13 22:53:37 +08:00
|
|
|
bl mul_1x1_ialu @ (a1+a0)·(b1+b0)
|
2014-11-08 05:48:22 +08:00
|
|
|
___
|
|
|
|
|
@r=map("r$_",(6..9));
|
|
|
|
|
$code.=<<___;
|
|
|
|
|
ldmia $ret,{@r[0]-@r[3]}
|
|
|
|
|
eor $lo,$lo,$hi
|
2015-09-24 00:41:27 +08:00
|
|
|
ldr sp,[sp,#32] @ destroy tab[8]
|
2014-11-08 05:48:22 +08:00
|
|
|
eor $hi,$hi,@r[1]
|
|
|
|
|
eor $lo,$lo,@r[0]
|
|
|
|
|
eor $hi,$hi,@r[2]
|
|
|
|
|
eor $lo,$lo,@r[3]
|
|
|
|
|
eor $hi,$hi,@r[3]
|
|
|
|
|
str $hi,[$ret,#8]
|
|
|
|
|
eor $lo,$lo,$hi
|
|
|
|
|
str $lo,[$ret,#4]
|
|
|
|
|
|
|
|
|
|
#if __ARM_ARCH__>=5
|
|
|
|
|
ldmia sp!,{r4-r10,pc}
|
|
|
|
|
#else
|
|
|
|
|
ldmia sp!,{r4-r10,lr}
|
|
|
|
|
tst lr,#1
|
|
|
|
|
moveq pc,lr @ be binary compatible with V4, yet
|
|
|
|
|
bx lr @ interoperable with Thumb ISA:-)
|
|
|
|
|
#endif
|
|
|
|
|
___
|
|
|
|
|
}
|
|
|
|
|
{
|
|
|
|
|
my ($r,$t0,$t1,$t2,$t3)=map("q$_",(0..3,8..12));
|
|
|
|
|
my ($a,$b,$k48,$k32,$k16)=map("d$_",(26..31));
|
|
|
|
|
|
|
|
|
|
$code.=<<___;
|
|
|
|
|
#if __ARM_MAX_ARCH__>=7
|
|
|
|
|
.arch armv7-a
|
|
|
|
|
.fpu neon
|
|
|
|
|
|
|
|
|
|
.align 5
|
|
|
|
|
.LNEON:
|
2014-04-24 16:16:58 +08:00
|
|
|
ldr r12, [sp] @ 5th argument
|
2015-04-02 16:17:42 +08:00
|
|
|
vmov $a, r2, r1
|
|
|
|
|
vmov $b, r12, r3
|
2014-04-24 16:16:58 +08:00
|
|
|
vmov.i64 $k48, #0x0000ffffffffffff
|
|
|
|
|
vmov.i64 $k32, #0x00000000ffffffff
|
|
|
|
|
vmov.i64 $k16, #0x000000000000ffff
|
|
|
|
|
|
|
|
|
|
vext.8 $t0#lo, $a, $a, #1 @ A1
|
|
|
|
|
vmull.p8 $t0, $t0#lo, $b @ F = A1*B
|
|
|
|
|
vext.8 $r#lo, $b, $b, #1 @ B1
|
|
|
|
|
vmull.p8 $r, $a, $r#lo @ E = A*B1
|
|
|
|
|
vext.8 $t1#lo, $a, $a, #2 @ A2
|
|
|
|
|
vmull.p8 $t1, $t1#lo, $b @ H = A2*B
|
|
|
|
|
vext.8 $t3#lo, $b, $b, #2 @ B2
|
|
|
|
|
vmull.p8 $t3, $a, $t3#lo @ G = A*B2
|
|
|
|
|
vext.8 $t2#lo, $a, $a, #3 @ A3
|
|
|
|
|
veor $t0, $t0, $r @ L = E + F
|
|
|
|
|
vmull.p8 $t2, $t2#lo, $b @ J = A3*B
|
|
|
|
|
vext.8 $r#lo, $b, $b, #3 @ B3
|
|
|
|
|
veor $t1, $t1, $t3 @ M = G + H
|
|
|
|
|
vmull.p8 $r, $a, $r#lo @ I = A*B3
|
|
|
|
|
veor $t0#lo, $t0#lo, $t0#hi @ t0 = (L) (P0 + P1) << 8
|
|
|
|
|
vand $t0#hi, $t0#hi, $k48
|
|
|
|
|
vext.8 $t3#lo, $b, $b, #4 @ B4
|
|
|
|
|
veor $t1#lo, $t1#lo, $t1#hi @ t1 = (M) (P2 + P3) << 16
|
|
|
|
|
vand $t1#hi, $t1#hi, $k32
|
|
|
|
|
vmull.p8 $t3, $a, $t3#lo @ K = A*B4
|
|
|
|
|
veor $t2, $t2, $r @ N = I + J
|
|
|
|
|
veor $t0#lo, $t0#lo, $t0#hi
|
|
|
|
|
veor $t1#lo, $t1#lo, $t1#hi
|
|
|
|
|
veor $t2#lo, $t2#lo, $t2#hi @ t2 = (N) (P4 + P5) << 24
|
|
|
|
|
vand $t2#hi, $t2#hi, $k16
|
|
|
|
|
vext.8 $t0, $t0, $t0, #15
|
|
|
|
|
veor $t3#lo, $t3#lo, $t3#hi @ t3 = (K) (P6 + P7) << 32
|
|
|
|
|
vmov.i64 $t3#hi, #0
|
|
|
|
|
vext.8 $t1, $t1, $t1, #14
|
|
|
|
|
veor $t2#lo, $t2#lo, $t2#hi
|
|
|
|
|
vmull.p8 $r, $a, $b @ D = A*B
|
|
|
|
|
vext.8 $t3, $t3, $t3, #12
|
|
|
|
|
vext.8 $t2, $t2, $t2, #13
|
|
|
|
|
veor $t0, $t0, $t1
|
|
|
|
|
veor $t2, $t2, $t3
|
|
|
|
|
veor $r, $r, $t0
|
|
|
|
|
veor $r, $r, $t2
|
|
|
|
|
|
|
|
|
|
vst1.32 {$r}, [r0]
|
2014-06-07 03:27:18 +08:00
|
|
|
ret @ bx lr
|
2011-05-05 15:21:17 +08:00
|
|
|
#endif
|
|
|
|
|
___
|
2014-04-24 16:16:58 +08:00
|
|
|
}
|
2011-05-05 15:21:17 +08:00
|
|
|
$code.=<<___;
|
|
|
|
|
.size bn_GF2m_mul_2x2,.-bn_GF2m_mul_2x2
|
2014-11-08 05:48:22 +08:00
|
|
|
#if __ARM_MAX_ARCH__>=7
|
2011-05-05 15:21:17 +08:00
|
|
|
.align 5
|
|
|
|
|
.LOPENSSL_armcap:
|
2019-02-15 16:44:39 +08:00
|
|
|
# ifdef _WIN32
|
|
|
|
|
.word OPENSSL_armcap_P
|
|
|
|
|
# else
|
2015-09-24 00:41:27 +08:00
|
|
|
.word OPENSSL_armcap_P-.
|
2019-02-15 16:44:39 +08:00
|
|
|
# endif
|
2011-05-05 15:21:17 +08:00
|
|
|
#endif
|
2011-07-18 01:40:29 +08:00
|
|
|
.asciz "GF(2^m) Multiplication for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
|
2011-05-05 15:21:17 +08:00
|
|
|
.align 5
|
|
|
|
|
|
2014-11-08 05:48:22 +08:00
|
|
|
#if __ARM_MAX_ARCH__>=7
|
2023-03-28 05:05:13 +08:00
|
|
|
.extern OPENSSL_armcap_P
|
2023-09-24 02:22:03 +08:00
|
|
|
.hidden OPENSSL_armcap_P
|
2014-11-08 05:48:22 +08:00
|
|
|
#endif
|
2011-05-05 15:21:17 +08:00
|
|
|
___
|
|
|
|
|
|
2014-04-24 16:16:58 +08:00
|
|
|
foreach (split("\n",$code)) {
|
|
|
|
|
s/\`([^\`]*)\`/eval $1/geo;
|
|
|
|
|
|
|
|
|
|
s/\bq([0-9]+)#(lo|hi)/sprintf "d%d",2*$1+($2 eq "hi")/geo or
|
2014-06-07 03:27:18 +08:00
|
|
|
s/\bret\b/bx lr/go or
|
2014-04-24 16:16:58 +08:00
|
|
|
s/\bbx\s+lr\b/.word\t0xe12fff1e/go; # make it possible to compile with -march=armv4
|
|
|
|
|
|
|
|
|
|
print $_,"\n";
|
|
|
|
|
}
|
2020-02-17 10:17:53 +08:00
|
|
|
close STDOUT or die "error closing STDOUT: $!"; # enforce flush
|
