X-Git-Url: https://git.librecmc.org/?a=blobdiff_plain;f=crypto%2Fsha%2Fasm%2Fsha1-armv8.pl;h=cb0e38339649a6d947095b9ec2130f8f5af24fa0;hb=32be631ca1f2b73c92e4f7f5d23f1c3aee80ec69;hp=8453297da22e839ae219f23a20edf7ca669aea22;hpb=ddb6b965da0087dadea5488fe11646e3777c66e1;p=oweals%2Fopenssl.git

diff --git a/crypto/sha/asm/sha1-armv8.pl b/crypto/sha/asm/sha1-armv8.pl
index 8453297da2..cb0e383396 100644
--- a/crypto/sha/asm/sha1-armv8.pl
+++ b/crypto/sha/asm/sha1-armv8.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2014-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the Apache License 2.0 (the "License").  You may not use
+# 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
+
 #
 # ====================================================================
 # Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@@ -14,12 +21,31 @@
 #
 #		hardware-assisted	software(*)
 # Apple A7	2.31			4.13 (+14%)
-# Cortex-A5x	n/a			n/a
+# Cortex-A53	2.24			8.03 (+97%)
+# Cortex-A57	2.35			7.88 (+74%)
+# Denver	2.13			3.97 (+0%)(**)
+# X-Gene				8.80 (+200%)
+# Mongoose	2.05			6.50 (+160%)
+# Kryo		1.88			8.00 (+90%)
+# ThunderX2	2.64			6.36 (+150%)
 #
 # (*)	Software results are presented mostly for reference purposes.
+# (**)	Keep in mind that Denver relies on binary translation, which
+#	optimizes compiler output at run-time.
+
+# $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;
 
-$flavour = shift;
-open STDOUT,">".shift;
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $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\""
+    or die "can't call $xlate: $1";
+*STDOUT=*OUT;
 
 ($ctx,$inp,$num)=("x0","x1","x2");
 @Xw=map("w$_",(3..17,19));
@@ -36,10 +62,10 @@ $code.=<<___ if ($i<15 && !($i&1));
 	lsr	@Xx[$i+1],@Xx[$i],#32
 ___
 $code.=<<___ if ($i<14 && !($i&1));
-	ldr	@Xx[$i+2],[$inp,#`($i+2)*4-64`]
+	ldur	@Xx[$i+2],[$inp,#`($i+2)*4-64`]
 ___
 $code.=<<___ if ($i<14 && ($i&1));
-#ifdef	__ARMEB__
+#ifdef	__AARCH64EB__
 	ror	@Xx[$i+1],@Xx[$i+1],#32
 #else
 	rev32	@Xx[$i+1],@Xx[$i+1]
@@ -149,7 +175,10 @@ ___
 }
 
 $code.=<<___;
-#include "arm_arch.h"
+#ifndef	__KERNEL__
+# include "arm_arch.h"
+.extern OPENSSL_armcap_P
+#endif
 
 .text
 
@@ -157,10 +186,8 @@ $code.=<<___;
 .type	sha1_block_data_order,%function
 .align	6
 sha1_block_data_order:
-	ldr	x16,.LOPENSSL_armcap_P
-	adr	x17,.LOPENSSL_armcap_P
-	add	x16,x16,x17
-	ldr	w16,[x16]
+	adrp	x16,OPENSSL_armcap_P
+	ldr	w16,[x16,#:lo12:OPENSSL_armcap_P]
 	tst	w16,#ARMV8_SHA1
 	b.ne	.Lv8_entry
 
@@ -181,7 +208,7 @@ sha1_block_data_order:
 	movz	$K,#0x7999
 	sub	$num,$num,#1
 	movk	$K,#0x5a82,lsl#16
-#ifdef	__ARMEB__
+#ifdef	__AARCH64EB__
 	ror	$Xx[0],@Xx[0],#32
 #else
 	rev32	@Xx[0],@Xx[0]
@@ -294,11 +321,11 @@ $code.=<<___;
 .long	0x6ed9eba1,0x6ed9eba1,0x6ed9eba1,0x6ed9eba1	//K_20_39
 .long	0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc	//K_40_59
 .long	0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6	//K_60_79
-.LOPENSSL_armcap_P:
-.quad	OPENSSL_armcap_P-.
 .asciz	"SHA1 block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align	2
+#if !defined(__KERNELL__) && !defined(_WIN64)
 .comm	OPENSSL_armcap_P,4,4
+#endif
 ___
 }}}
 
@@ -312,7 +339,7 @@ ___
 
 	$arg =~ m/[qv]([0-9]+)[^,]*,\s*[qv]([0-9]+)[^,]*(?:,\s*[qv]([0-9]+))?/o
 	&&
-	sprintf ".long\t0x%08x\t//%s %s",
+	sprintf ".inst\t0x%08x\t//%s %s",
 			$opcode{$mnemonic}|$1|($2<<5)|($3<<16),
 			$mnemonic,$arg;
     }
@@ -330,4 +357,4 @@ foreach(split("\n",$code)) {
 	print $_,"\n";
 }
 
-close STDOUT;
+close STDOUT or die "error closing STDOUT";