Revert "quantum init"

This reverts commit 53af3b51ae.

crypto/sha/asm/README

@@ -1 +0,0 @@
-C2.pl works

crypto/sha/asm/sha1-586.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 1998-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
+
 
 # ====================================================================
 # [Re]written by Andy Polyakov <appro@openssl.org> for the OpenSSL
@@ -113,6 +120,9 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
 push(@INC,"${dir}","${dir}../../perlasm");
 require "x86asm.pl";
 
+$output=pop;
+open STDOUT,">$output";
+
 &asm_init($ARGV[0],"sha1-586.pl",$ARGV[$#ARGV] eq "386");
 
 $xmm=$ymm=0;
@@ -1474,3 +1484,5 @@ sub Xtail_avx()
 &asciz("SHA1 block transform for x86, CRYPTOGAMS by <appro\@openssl.org>");
 
 &asm_finish();
+
+close STDOUT;

crypto/sha/asm/sha1-alpha.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2009-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -317,6 +324,6 @@ $code.=<<___;
 .ascii	"SHA1 block transform for Alpha, CRYPTOGAMS by <appro\@openssl.org>"
 .align	2
 ___
-$output=shift and open STDOUT,">$output";
+$output=pop and open STDOUT,">$output";
 print $code;
 close STDOUT;

crypto/sha/asm/sha1-armv4-large.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -60,14 +67,28 @@
 # is ~2.5x larger and there are some redundant instructions executed
 # when processing last block, improvement is not as big for smallest
 # blocks, only ~30%. Snapdragon S4 is a tad faster, 6.4 cycles per
-# byte, which is also >80% faster than integer-only code.
+# byte, which is also >80% faster than integer-only code. Cortex-A15
+# is even faster spending 5.6 cycles per byte outperforming integer-
+# only code by factor of 2.
 
 # May 2014.
 #
 # Add ARMv8 code path performing at 2.35 cpb on Apple A7.
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+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 $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $ctx="r0";
 $inp="r1";
@@ -167,7 +188,12 @@ $code=<<___;
 #include "arm_arch.h"
 
 .text
+#if defined(__thumb2__)
+.syntax	unified
+.thumb
+#else
 .code	32
+#endif
 
 .global	sha1_block_data_order
 .type	sha1_block_data_order,%function
@@ -175,9 +201,13 @@ $code=<<___;
 .align	5
 sha1_block_data_order:
 #if __ARM_MAX_ARCH__>=7
-	sub	r3,pc,#8		@ sha1_block_data_order
+.Lsha1_block:
+	adr	r3,.Lsha1_block
 	ldr	r12,.LOPENSSL_armcap
 	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+#ifdef	__APPLE__
+	ldr	r12,[r12]
+#endif
 	tst	r12,#ARMV8_SHA1
 	bne	.LARMv8
 	tst	r12,#ARMV7_NEON
@@ -199,7 +229,12 @@ for($i=0;$i<5;$i++) {
 	&BODY_00_15(@V);	unshift(@V,pop(@V));
 }
 $code.=<<___;
+#if defined(__thumb2__)
+	mov	$t3,sp
+	teq	$Xi,$t3
+#else
 	teq	$Xi,sp
+#endif
 	bne	.L_00_15		@ [((11+4)*5+2)*3]
 	sub	sp,sp,#25*4
 ___
@@ -218,7 +253,12 @@ for($i=0;$i<5;$i++) {
 	&BODY_20_39(@V);	unshift(@V,pop(@V));
 }
 $code.=<<___;
+#if defined(__thumb2__)
+	mov	$t3,sp
+	teq	$Xi,$t3
+#else
 	teq	$Xi,sp			@ preserve carry
+#endif
 	bne	.L_20_39_or_60_79	@ [+((12+3)*5+2)*4]
 	bcs	.L_done			@ [+((12+3)*5+2)*4], spare 300 bytes
 
@@ -230,7 +270,12 @@ for($i=0;$i<5;$i++) {
 	&BODY_40_59(@V);	unshift(@V,pop(@V));
 }
 $code.=<<___;
+#if defined(__thumb2__)
+	mov	$t3,sp
+	teq	$Xi,$t3
+#else
 	teq	$Xi,sp
+#endif
 	bne	.L_40_59		@ [+((12+5)*5+2)*4]
 
 	ldr	$K,.LK_60_79
@@ -266,7 +311,7 @@ $code.=<<___;
 .LK_60_79:	.word	0xca62c1d6
 #if __ARM_MAX_ARCH__>=7
 .LOPENSSL_armcap:
-.word	OPENSSL_armcap_P-sha1_block_data_order
+.word	OPENSSL_armcap_P-.Lsha1_block
 #endif
 .asciz	"SHA1 block transform for ARMv4/NEON/ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align	5
@@ -441,6 +486,7 @@ sub Xuplast_80 ()
 
 	&teq		($inp,$len);
 	&sub		($K_XX_XX,$K_XX_XX,16);	# rewind $K_XX_XX
+	&it		("eq");
 	&subeq		($inp,$inp,64);		# reload last block to avoid SEGV
 	&vld1_8		("{@X[-4&7]-@X[-3&7]}","[$inp]!");
 	 eval(shift(@insns));
@@ -491,12 +537,12 @@ sha1_block_data_order_neon:
 	@ dmb				@ errata #451034 on early Cortex A8
 	@ vstmdb	sp!,{d8-d15}	@ ABI specification says so
 	mov	$saved_sp,sp
-	sub	sp,sp,#64		@ alloca
+	sub	$Xfer,sp,#64
 	adr	$K_XX_XX,.LK_00_19
-	bic	sp,sp,#15		@ align for 128-bit stores
+	bic	$Xfer,$Xfer,#15		@ align for 128-bit stores
 
 	ldmia	$ctx,{$a,$b,$c,$d,$e}	@ load context
-	mov	$Xfer,sp
+	mov	sp,$Xfer		@ alloca
 
 	vld1.8		{@X[-4&7]-@X[-3&7]},[$inp]!	@ handles unaligned
 	veor		$zero,$zero,$zero
@@ -543,10 +589,13 @@ $code.=<<___;
 	add	$b,$b,$t0
 	add	$c,$c,$t1
 	add	$d,$d,$Xfer
+	it	eq
 	moveq	sp,$saved_sp
 	add	$e,$e,$Ki
+	it	ne
 	ldrne	$Ki,[sp]
 	stmia	$ctx,{$a,$b,$c,$d,$e}
+	itt	ne
 	addne	$Xfer,sp,#3*16
 	bne	.Loop_neon
 
@@ -567,6 +616,13 @@ my ($W0,$W1,$ABCD_SAVE)=map("q$_",(12..14));
 
 $code.=<<___;
 #if __ARM_MAX_ARCH__>=7
+
+# if defined(__thumb2__)
+#  define INST(a,b,c,d)	.byte	c,d|0xf,a,b
+# else
+#  define INST(a,b,c,d)	.byte	a,b,c,d|0x10
+# endif
+
 .type	sha1_block_data_order_armv8,%function
 .align	5
 sha1_block_data_order_armv8:
@@ -660,7 +716,10 @@ ___
 	    # since ARMv7 instructions are always encoded little-endian.
 	    # correct solution is to use .inst directive, but older
 	    # assemblers don't implement it:-(
-	    sprintf ".byte\t0x%02x,0x%02x,0x%02x,0x%02x\t@ %s %s",
+
+	    # this fix-up provides Thumb encoding in conjunction with INST
+	    $word &= ~0x10000000 if (($word & 0x0f000000) == 0x02000000);
+	    sprintf "INST(0x%02x,0x%02x,0x%02x,0x%02x)\t@ %s %s",
 			$word&0xff,($word>>8)&0xff,
 			($word>>16)&0xff,($word>>24)&0xff,
 			$mnemonic,$arg;

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 OpenSSL license (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
@@ -18,13 +25,22 @@
 # Cortex-A57	2.35			7.88 (+74%)
 # Denver	2.13			3.97 (+0%)(**)
 # X-Gene				8.80 (+200%)
+# Mongoose	2.05			6.50 (+160%)
 #
 # (*)	Software results are presented mostly for reference purposes.
 # (**)	Keep in mind that Denver relies on binary translation, which
 #	optimizes compiler output at run-time.
 
 $flavour = shift;
-open STDOUT,">".shift;
+$output  = 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";
+*STDOUT=*OUT;
 
 ($ctx,$inp,$num)=("x0","x1","x2");
 @Xw=map("w$_",(3..17,19));
@@ -158,11 +174,16 @@ $code.=<<___;
 
 .text
 
+.extern	OPENSSL_armcap_P
 .globl	sha1_block_data_order
 .type	sha1_block_data_order,%function
 .align	6
 sha1_block_data_order:
+#ifdef	__ILP32__
+	ldrsw	x16,.LOPENSSL_armcap_P
+#else
 	ldr	x16,.LOPENSSL_armcap_P
+#endif
 	adr	x17,.LOPENSSL_armcap_P
 	add	x16,x16,x17
 	ldr	w16,[x16]
@@ -300,7 +321,11 @@ $code.=<<___;
 .long	0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc,0x8f1bbcdc	//K_40_59
 .long	0xca62c1d6,0xca62c1d6,0xca62c1d6,0xca62c1d6	//K_60_79
 .LOPENSSL_armcap_P:
+#ifdef	__ILP32__
+.long	OPENSSL_armcap_P-.
+#else
 .quad	OPENSSL_armcap_P-.
+#endif
 .asciz	"SHA1 block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align	2
 .comm	OPENSSL_armcap_P,4,4

crypto/sha/asm/sha1-ia64.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2004-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -14,6 +21,8 @@
 # Performance under big-endian OS such as HP-UX is 179MBps*1GHz, which
 # is >50% better than HP C and >2x better than gcc.
 
+$output = pop;
+
 $code=<<___;
 .ident  \"sha1-ia64.s, version 1.3\"
 .ident  \"IA-64 ISA artwork by Andy Polyakov <appro\@fy.chalmers.se>\"
@@ -301,5 +310,5 @@ $code.=<<___;
 stringz	"SHA1 block transform for IA64, CRYPTOGAMS by <appro\@openssl.org>"
 ___
 
-$output=shift and open STDOUT,">$output";
+open STDOUT,">$output" if $output;
 print $code;

crypto/sha/asm/sha1-mb-x86_64.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2013-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -19,6 +26,7 @@
 # Sandy Bridge	(8.16	+5.15=13.3)/n	4.99	5.98		+80%
 # Ivy Bridge	(8.08	+5.14=13.2)/n	4.60	5.54		+68%
 # Haswell(iii)	(8.96	+5.00=14.0)/n	3.57	4.55		+160%
+# Skylake	(8.70	+5.00=13.7)/n	3.64	4.20		+145%
 # Bulldozer	(9.76	+5.76=15.5)/n	5.95	6.37		+64%
 #
 # (i)	multi-block CBC encrypt with 128-bit key;
@@ -62,7 +70,7 @@ if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([
 	$avx = ($2>=3.0) + ($2>3.0);
 }
 
-open OUT,"| \"$^X\" $xlate $flavour $output";
+open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
 *STDOUT=*OUT;
 
 # void sha1_multi_block (
@@ -478,7 +486,7 @@ $code.=<<___;
 	jnz	.Loop_grande
 
 .Ldone:
-	mov	`$REG_SZ*17`(%rsp),%rax		# orignal %rsp
+	mov	`$REG_SZ*17`(%rsp),%rax		# original %rsp
 ___
 $code.=<<___ if ($win64);
 	movaps	-0xb8(%rax),%xmm6
@@ -538,7 +546,7 @@ $code.=<<___;
 	movdqa	K_XX_XX+0x80(%rip),$BSWAP	# byte-n-word swap
 
 .Loop_grande_shaext:
-	mov	$num,`$REG_SZ*17+8`(%rsp)	# orignal $num
+	mov	$num,`$REG_SZ*17+8`(%rsp)	# original $num
 	xor	$num,$num
 ___
 for($i=0;$i<2;$i++) {
@@ -1116,7 +1124,7 @@ $code.=<<___;
 	jnz	.Loop_grande_avx
 
 .Ldone_avx:
-	mov	`$REG_SZ*17`(%rsp),%rax		# orignal %rsp
+	mov	`$REG_SZ*17`(%rsp),%rax		# original %rsp
 	vzeroupper
 ___
 $code.=<<___ if ($win64);
@@ -1271,7 +1279,7 @@ $code.=<<___;
 	#jnz	.Loop_grande_avx2
 
 .Ldone_avx2:
-	mov	`$REG_SZ*17`(%rsp),%rax		# orignal %rsp
+	mov	`$REG_SZ*17`(%rsp),%rax		# original %rsp
 	vzeroupper
 ___
 $code.=<<___ if ($win64);

crypto/sha/asm/sha1-mips.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2009-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -70,7 +77,7 @@ if ($flavour =~ /64|n32/i) {
 
 $big_endian=(`echo MIPSEL | $ENV{CC} -E -`=~/MIPSEL/)?1:0 if ($ENV{CC});
 
-for (@ARGV) {	$output=$_ if (/^\w[\w\-]*\.\w+$/);   }
+for (@ARGV) {	$output=$_ if (/\w[\w\-]*\.\w+$/);   }
 open STDOUT,">$output";
 
 if (!defined($big_endian))
@@ -325,8 +332,8 @@ $code.=<<___ if ($i<79);
 ___
 }
 
-$FRAMESIZE=16;	# large enough to accomodate NUBI saved registers
-$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? 0xc0fff008 : 0xc0ff0000;
+$FRAMESIZE=16;	# large enough to accommodate NUBI saved registers
+$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0xc0fff008" : "0xc0ff0000";
 
 $code=<<___;
 #ifdef OPENSSL_FIPSCANISTER

crypto/sha/asm/sha1-parisc.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2009-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL

crypto/sha/asm/sha1-ppc.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2006-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -37,7 +44,7 @@ if ($flavour =~ /64/) {
 	$PUSH	="stw";
 } else { die "nonsense $flavour"; }
 
-# Define endianess based on flavour
+# Define endianness based on flavour
 # i.e.: linux64le
 $LITTLE_ENDIAN = ($flavour=~/le$/) ? $SIZE_T : 0;
 

crypto/sha/asm/sha1-s390x.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -28,7 +35,8 @@
 # instructions and achieve "64-bit" performance even in 31-bit legacy
 # application context. The feature is not specific to any particular
 # processor, as long as it's "z-CPU". Latter implies that the code
-# remains z/Architecture specific.
+# remains z/Architecture specific. On z990 it was measured to perform
+# 23% better than code generated by gcc 4.3.
 
 $kimdfunc=1;	# magic function code for kimd instruction
 
@@ -42,7 +50,7 @@ if ($flavour =~ /3[12]/) {
 	$g="g";
 }
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
 open STDOUT,">$output";
 
 $K_00_39="%r0"; $K=$K_00_39;

crypto/sha/asm/sha1-sparcv9.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -25,7 +32,7 @@
 # single-process result on 8-core processor, or ~9GBps per 2.85GHz
 # socket.
 
-$output=shift;
+$output=pop;
 open STDOUT,">$output";
 
 @X=("%o0","%o1","%o2","%o3","%o4","%o5","%g1","%o7");
@@ -368,7 +375,7 @@ ___
 
 # Purpose of these subroutines is to explicitly encode VIS instructions,
 # so that one can compile the module without having to specify VIS
-# extentions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
+# extensions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
 # Idea is to reserve for option to produce "universal" binary and let
 # programmer detect if current CPU is VIS capable at run-time.
 sub unvis {

crypto/sha/asm/sha1-sparcv9a.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2009-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -544,7 +551,7 @@ ___
 
 # Purpose of these subroutines is to explicitly encode VIS instructions,
 # so that one can compile the module without having to specify VIS
-# extentions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
+# extensions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
 # Idea is to reserve for option to produce "universal" binary and let
 # programmer detect if current CPU is VIS capable at run-time.
 sub unvis {

crypto/sha/asm/sha1-thumb.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL

crypto/sha/asm/sha1-x86_64.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2006-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -73,13 +80,16 @@
 # Sandy Bridge	7.70		6.10/+26%	4.99/+54%
 # Ivy Bridge	6.06		4.67/+30%	4.60/+32%
 # Haswell	5.45		4.15/+31%	3.57/+53%
+# Skylake	5.18		4.06/+28%	3.54/+46%
 # Bulldozer	9.11		5.95/+53%
 # VIA Nano	9.32		7.15/+30%
 # Atom		10.3		9.17/+12%
 # Silvermont	13.1(*)		9.37/+40%
+# Goldmont	8.13		6.42/+27%	1.70/+380%(**)
 #
 # (*)	obviously suboptimal result, nothing was done about it,
 #	because SSSE3 code is compiled unconditionally;
+# (**)	SHAEXT result
 
 $flavour = shift;
 $output  = shift;
@@ -114,7 +124,7 @@ if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([
 $shaext=1;	### set to zero if compiling for 1.0.1
 $avx=1		if (!$shaext && $avx);
 
-open OUT,"| \"$^X\" $xlate $flavour $output";
+open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
 *STDOUT=*OUT;
 
 $ctx="%rdi";	# 1st arg

crypto/sha/asm/sha256-586.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -63,6 +70,9 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
 push(@INC,"${dir}","${dir}../../perlasm");
 require "x86asm.pl";
 
+$output=pop;
+open STDOUT,">$output";
+
 &asm_init($ARGV[0],"sha512-586.pl",$ARGV[$#ARGV] eq "386");
 
 $xmm=$avx=0;
@@ -1279,3 +1289,5 @@ sub bodyx_00_15 () {			# +10%
 &function_end_B("sha256_block_data_order");
 
 &asm_finish();
+
+close STDOUT;

crypto/sha/asm/sha256-armv4.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -37,8 +44,20 @@
 #
 # Add ARMv8 code path performing at 2.0 cpb on Apple A7.
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+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 $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $ctx="r0";	$t0="r0";
 $inp="r1";	$t4="r1";
@@ -73,7 +92,9 @@ $code.=<<___ if ($i<16);
 	eor	$t0,$e,$e,ror#`$Sigma1[1]-$Sigma1[0]`
 	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
 	eor	$t0,$t0,$e,ror#`$Sigma1[2]-$Sigma1[0]`	@ Sigma1(e)
+# ifndef __ARMEB__
 	rev	$t1,$t1
+# endif
 #else
 	@ ldrb	$t1,[$inp,#3]			@ $i
 	add	$a,$a,$t2			@ h+=Maj(a,b,c) from the past
@@ -161,15 +182,11 @@ $code=<<___;
 #endif
 
 .text
-#if __ARM_ARCH__<7
-.code	32
-#else
+#if defined(__thumb2__)
 .syntax unified
-# ifdef __thumb2__
 .thumb
-# else
+#else
 .code   32
-# endif
 #endif
 
 .type	K256,%object
@@ -195,21 +212,25 @@ K256:
 .word	0				@ terminator
 #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 .LOPENSSL_armcap:
-.word	OPENSSL_armcap_P-sha256_block_data_order
+.word	OPENSSL_armcap_P-.Lsha256_block_data_order
 #endif
 .align	5
 
 .global	sha256_block_data_order
 .type	sha256_block_data_order,%function
 sha256_block_data_order:
-#if __ARM_ARCH__<7
+.Lsha256_block_data_order:
+#if __ARM_ARCH__<7 && !defined(__thumb2__)
 	sub	r3,pc,#8		@ sha256_block_data_order
 #else
-	adr	r3,sha256_block_data_order
+	adr	r3,.Lsha256_block_data_order
 #endif
 #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 	ldr	r12,.LOPENSSL_armcap
 	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+#ifdef	__APPLE__
+	ldr	r12,[r12]
+#endif
 	tst	r12,#ARMV8_SHA256
 	bne	.LARMv8
 	tst	r12,#ARMV7_NEON
@@ -454,7 +475,8 @@ $code.=<<___;
 
 .global	sha256_block_data_order_neon
 .type	sha256_block_data_order_neon,%function
-.align	4
+.align	5
+.skip	16
 sha256_block_data_order_neon:
 .LNEON:
 	stmdb	sp!,{r4-r12,lr}
@@ -580,7 +602,7 @@ my $Ktbl="r3";
 $code.=<<___;
 #if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 
-# ifdef __thumb2__
+# if defined(__thumb2__)
 #  define INST(a,b,c,d)	.byte	c,d|0xc,a,b
 # else
 #  define INST(a,b,c,d)	.byte	a,b,c,d
@@ -591,14 +613,11 @@ $code.=<<___;
 sha256_block_data_order_armv8:
 .LARMv8:
 	vld1.32	{$ABCD,$EFGH},[$ctx]
-# ifdef __thumb2__
-	adr	$Ktbl,.LARMv8
-	sub	$Ktbl,$Ktbl,#.LARMv8-K256
-# else
-	adrl	$Ktbl,K256
-# endif
+	sub	$Ktbl,$Ktbl,#256+32
 	add	$len,$inp,$len,lsl#6	@ len to point at the end of inp
+	b	.Loop_v8
 
+.align	4
 .Loop_v8:
 	vld1.8		{@MSG[0]-@MSG[1]},[$inp]!
 	vld1.8		{@MSG[2]-@MSG[3]},[$inp]!

crypto/sha/asm/sha256-mb-x86_64.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2013-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -19,6 +26,7 @@
 # Sandy Bridge	(20.5	+5.15=25.7)/n	11.6	13.0		+103%
 # Ivy Bridge	(20.4	+5.14=25.5)/n	10.3	11.6		+82%
 # Haswell(iii)	(21.0	+5.00=26.0)/n	7.80	8.79		+170%
+# Skylake	(18.9	+5.00=23.9)/n	7.70	8.17		+170%
 # Bulldozer	(21.6	+5.76=27.4)/n	13.6	13.7		+100%
 #
 # (i)	multi-block CBC encrypt with 128-bit key;
@@ -63,7 +71,7 @@ if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([
 	$avx = ($2>=3.0) + ($2>3.0);
 }
 
-open OUT,"| \"$^X\" $xlate $flavour $output";
+open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
 *STDOUT=*OUT;
 
 # void sha256_multi_block (
@@ -382,7 +390,7 @@ $code.=<<___;
 	jnz	.Loop_grande
 
 .Ldone:
-	mov	`$REG_SZ*17`(%rsp),%rax		# orignal %rsp
+	mov	`$REG_SZ*17`(%rsp),%rax		# original %rsp
 ___
 $code.=<<___ if ($win64);
 	movaps	-0xb8(%rax),%xmm6
@@ -442,7 +450,7 @@ $code.=<<___;
 	lea	K256_shaext+0x80(%rip),$Tbl
 
 .Loop_grande_shaext:
-	mov	$num,`$REG_SZ*17+8`(%rsp)	# orignal $num
+	mov	$num,`$REG_SZ*17+8`(%rsp)	# original $num
 	xor	$num,$num
 ___
 for($i=0;$i<2;$i++) {
@@ -1061,7 +1069,7 @@ $code.=<<___;
 	jnz	.Loop_grande_avx
 
 .Ldone_avx:
-	mov	`$REG_SZ*17`(%rsp),%rax		# orignal %rsp
+	mov	`$REG_SZ*17`(%rsp),%rax		# original %rsp
 	vzeroupper
 ___
 $code.=<<___ if ($win64);
@@ -1237,7 +1245,7 @@ $code.=<<___;
 	#jnz	.Loop_grande_avx2
 
 .Ldone_avx2:
-	mov	`$REG_SZ*17`(%rsp),%rax		# orignal %rsp
+	mov	`$REG_SZ*17`(%rsp),%rax		# original %rsp
 	vzeroupper
 ___
 $code.=<<___ if ($win64);

crypto/sha/asm/sha512-586.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -29,6 +36,7 @@
 # VIA Nano	91	-	52	33	14.7
 # Atom		126	-	68	48(***)	14.7
 # Silvermont	97	-	58	42(***)	17.5
+# Goldmont	80	-	48	19.5	12.0
 #
 # (*)	whichever best applicable.
 # (**)	x86_64 assembler performance is presented for reference
@@ -50,6 +58,9 @@ $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
 push(@INC,"${dir}","${dir}../../perlasm");
 require "x86asm.pl";
 
+$output=pop;
+open STDOUT,">$output";
+
 &asm_init($ARGV[0],"sha512-586.pl",$ARGV[$#ARGV] eq "386");
 
 $sse2=0;
@@ -909,3 +920,5 @@ sub BODY_00_15_ssse3 {		# "phase-less" copy of BODY_00_15_sse2
 &asciz("SHA512 block transform for x86, CRYPTOGAMS by <appro\@openssl.org>");
 
 &asm_finish();
+
+close STDOUT;

crypto/sha/asm/sha512-armv4.pl

@@ -1,10 +1,19 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
 # 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/.
+#
+# Permission to use under GPL terms is granted.
 # ====================================================================
 
 # SHA512 block procedure for ARMv4. September 2007.
@@ -34,16 +43,9 @@
 # terms it's 22.6 cycles per byte, which is disappointing result.
 # Technical writers asserted that 3-way S4 pipeline can sustain
 # multiple NEON instructions per cycle, but dual NEON issue could
-# not be observed, and for NEON-only sequences IPC(*) was found to
-# be limited by 1:-( 0.33 and 0.66 were measured for sequences with
-# ILPs(*) of 1 and 2 respectively. This in turn means that you can
-# even find yourself striving, as I did here, for achieving IPC
-# adequate to one delivered by Cortex A8 [for reference, it's
-# 0.5 for ILP of 1, and 1 for higher ILPs].
-#
-# (*) ILP, instruction-level parallelism, how many instructions
-#     *can* execute at the same time. IPC, instructions per cycle,
-#     indicates how many instructions actually execute.
+# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# for further details. On side note Cortex-A15 processes one byte in
+# 16 cycles.
 
 # Byte order [in]dependence. =========================================
 #
@@ -55,8 +57,20 @@ $hi="HI";
 $lo="LO";
 # ====================================================================
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
-open STDOUT,">$output";
+$flavour = shift;
+if ($flavour=~/\w[\w\-]*\.\w+$/) { $output=$flavour; undef $flavour; }
+else { while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {} }
+
+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 $xlate) or
+    die "can't locate arm-xlate.pl";
+
+    open STDOUT,"| \"$^X\" $xlate $flavour $output";
+} else {
+    open STDOUT,">$output";
+}
 
 $ctx="r0";	# parameter block
 $inp="r1";
@@ -143,6 +157,9 @@ $code.=<<___;
 	teq	$t0,#$magic
 
 	ldr	$t3,[sp,#$Coff+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
 	orreq	$Ktbl,$Ktbl,#1
 	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
 	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
@@ -180,7 +197,17 @@ $code.=<<___;
 ___
 }
 $code=<<___;
-#include "arm_arch.h"
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
 #ifdef __ARMEL__
 # define LO 0
 # define HI 4
@@ -192,7 +219,14 @@ $code=<<___;
 #endif
 
 .text
+#if defined(__thumb2__)
+.syntax unified
+.thumb
+# define adrl adr
+#else
 .code	32
+#endif
+
 .type	K512,%object
 .align	5
 K512:
@@ -237,9 +271,9 @@ WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
 WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
 WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
 .size	K512,.-K512
-#if __ARM_MAX_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 .LOPENSSL_armcap:
-.word	OPENSSL_armcap_P-sha512_block_data_order
+.word	OPENSSL_armcap_P-.Lsha512_block_data_order
 .skip	32-4
 #else
 .skip	32
@@ -248,14 +282,22 @@ WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
 .global	sha512_block_data_order
 .type	sha512_block_data_order,%function
 sha512_block_data_order:
+.Lsha512_block_data_order:
+#if __ARM_ARCH__<7 && !defined(__thumb2__)
 	sub	r3,pc,#8		@ sha512_block_data_order
-	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
-#if __ARM_MAX_ARCH__>=7
+#else
+	adr	r3,.Lsha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 	ldr	r12,.LOPENSSL_armcap
 	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
-	tst	r12,#1
+#ifdef	__APPLE__
+	ldr	r12,[r12]
+#endif
+	tst	r12,#ARMV7_NEON
 	bne	.LNEON
 #endif
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
 	stmdb	sp!,{r4-r12,lr}
 	sub	$Ktbl,r3,#672		@ K512
 	sub	sp,sp,#9*8
@@ -369,6 +411,9 @@ $code.=<<___;
 ___
 	&BODY_00_15(0x17);
 $code.=<<___;
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
 	ldreq	$t0,[sp,#`$Xoff+8*(16-1)`+0]
 	ldreq	$t1,[sp,#`$Xoff+8*(16-1)`+4]
 	beq	.L16_79
@@ -453,6 +498,7 @@ $code.=<<___;
 	moveq	pc,lr			@ be binary compatible with V4, yet
 	bx	lr			@ interoperable with Thumb ISA:-)
 #endif
+.size	sha512_block_data_order,.-sha512_block_data_order
 ___
 
 {
@@ -559,11 +605,15 @@ $code.=<<___;
 .arch	armv7-a
 .fpu	neon
 
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
 .align	4
+sha512_block_data_order_neon:
 .LNEON:
 	dmb				@ errata #451034 on early Cortex A8
-	vstmdb	sp!,{d8-d15}		@ ABI specification says so
-	sub	$Ktbl,r3,#672		@ K512
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	adr	$Ktbl,K512
+	VFP_ABI_PUSH
 	vldmia	$ctx,{$A-$H}		@ load context
 .Loop_neon:
 ___
@@ -588,16 +638,16 @@ $code.=<<___;
 	sub		$Ktbl,#640	@ rewind K512
 	bne		.Loop_neon
 
-	vldmia	sp!,{d8-d15}		@ epilogue
+	VFP_ABI_POP
 	ret				@ bx lr
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
 #endif
 ___
 }
 $code.=<<___;
-.size	sha512_block_data_order,.-sha512_block_data_order
 .asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
 .align	2
-#if __ARM_MAX_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
 .comm	OPENSSL_armcap_P,4,4
 #endif
 ___
@@ -605,5 +655,14 @@ ___
 $code =~ s/\`([^\`]*)\`/eval $1/gem;
 $code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm;	# make it possible to compile with -march=armv4
 $code =~ s/\bret\b/bx	lr/gm;
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
 print $code;
 close STDOUT; # enforce flush

crypto/sha/asm/sha512-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 OpenSSL license (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
@@ -18,6 +25,7 @@
 # Cortex-A57	2.31		11.6 (+86%)	7.51 (+260%(***))
 # Denver	2.01		10.5 (+26%)	6.70 (+8%)
 # X-Gene			20.0 (+100%)	12.8 (+300%(***))
+# Mongoose	2.36		13.0 (+50%)	8.36 (+33%)
 # 
 # (*)	Software SHA256 results are of lesser relevance, presented
 #	mostly for informational purposes.
@@ -31,7 +39,14 @@
 
 $flavour=shift;
 $output=shift;
-open STDOUT,">$output";
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $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;
 
 if ($output =~ /512/) {
 	$BITS=512;
@@ -155,13 +170,18 @@ $code.=<<___;
 
 .text
 
+.extern	OPENSSL_armcap_P
 .globl	$func
 .type	$func,%function
 .align	6
 $func:
 ___
 $code.=<<___	if ($SZ==4);
+#ifdef	__ILP32__
+	ldrsw	x16,.LOPENSSL_armcap_P
+#else
 	ldr	x16,.LOPENSSL_armcap_P
+#endif
 	adr	x17,.LOPENSSL_armcap_P
 	add	x16,x16,x17
 	ldr	w16,[x16]
@@ -184,7 +204,7 @@ $code.=<<___;
 	ldp	$E,$F,[$ctx,#4*$SZ]
 	add	$num,$inp,$num,lsl#`log(16*$SZ)/log(2)`	// end of input
 	ldp	$G,$H,[$ctx,#6*$SZ]
-	adr	$Ktbl,K$BITS
+	adr	$Ktbl,.LK$BITS
 	stp	$ctx,$num,[x29,#96]
 
 .Loop:
@@ -234,8 +254,8 @@ $code.=<<___;
 .size	$func,.-$func
 
 .align	6
-.type	K$BITS,%object
-K$BITS:
+.type	.LK$BITS,%object
+.LK$BITS:
 ___
 $code.=<<___ if ($SZ==8);
 	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
@@ -300,10 +320,14 @@ $code.=<<___ if ($SZ==4);
 	.long	0	//terminator
 ___
 $code.=<<___;
-.size	K$BITS,.-K$BITS
+.size	.LK$BITS,.-.LK$BITS
 .align	3
 .LOPENSSL_armcap_P:
+#ifdef	__ILP32__
+	.long	OPENSSL_armcap_P-.
+#else
 	.quad	OPENSSL_armcap_P-.
+#endif
 .asciz	"SHA$BITS block transform for ARMv8, CRYPTOGAMS by <appro\@openssl.org>"
 .align	2
 ___
@@ -325,7 +349,7 @@ sha256_block_armv8:
 	add		x29,sp,#0
 
 	ld1.32		{$ABCD,$EFGH},[$ctx]
-	adr		$Ktbl,K256
+	adr		$Ktbl,.LK256
 
 .Loop_hw:
 	ld1		{@MSG[0]-@MSG[3]},[$inp],#64

crypto/sha/asm/sha512-ia64.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2004-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -68,7 +75,7 @@
 # To generate code, pass the file name with either 256 or 512 in its
 # name and compiler flags.
 
-$output=shift;
+$output=pop;
 
 if ($output =~ /512.*\.[s|asm]/) {
 	$SZ=8;

crypto/sha/asm/sha512-mips.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2010-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -52,6 +59,7 @@
 $flavour = shift || "o32"; # supported flavours are o32,n32,64,nubi32,nubi64
 
 if ($flavour =~ /64|n32/i) {
+	$PTR_LA="dla";
 	$PTR_ADD="dadd";	# incidentally works even on n32
 	$PTR_SUB="dsub";	# incidentally works even on n32
 	$REG_S="sd";
@@ -59,6 +67,7 @@ if ($flavour =~ /64|n32/i) {
 	$PTR_SLL="dsll";	# incidentally works even on n32
 	$SZREG=8;
 } else {
+	$PTR_LA="la";
 	$PTR_ADD="add";
 	$PTR_SUB="sub";
 	$REG_S="sw";
@@ -74,7 +83,7 @@ $pf = ($flavour =~ /nubi/i) ? $t0 : $t2;
 
 $big_endian=(`echo MIPSEL | $ENV{CC} -E -`=~/MIPSEL/)?1:0 if ($ENV{CC});
 
-for (@ARGV) {	$output=$_ if (/^\w[\w\-]*\.\w+$/);	}
+for (@ARGV) {	$output=$_ if (/\w[\w\-]*\.\w+$/);	}
 open STDOUT,">$output";
 
 if (!defined($big_endian)) { $big_endian=(unpack('L',pack('N',1))==1); }
@@ -286,7 +295,7 @@ ___
 }
 
 $FRAMESIZE=16*$SZ+16*$SZREG;
-$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? 0xc0fff008 : 0xc0ff0000;
+$SAVED_REGS_MASK = ($flavour =~ /nubi/i) ? "0xc0fff008" : "0xc0ff0000";
 
 $code.=<<___;
 #ifdef OPENSSL_FIPSCANISTER
@@ -343,7 +352,7 @@ $code.=<<___ if ($flavour !~ /o32/i);	# non-o32 PIC-ification
 ___
 $code.=<<___;
 	.set	reorder
-	la	$Ktbl,K${label}		# PIC-ified 'load address'
+	$PTR_LA	$Ktbl,K${label}		# PIC-ified 'load address'
 
 	$LD	$A,0*$SZ($ctx)		# load context
 	$LD	$B,1*$SZ($ctx)

crypto/sha/asm/sha512-parisc.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2009-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL

crypto/sha/asm/sha512-ppc.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2006-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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

crypto/sha/asm/sha512-s390x.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -33,7 +40,7 @@
 # instructions and achieve "64-bit" performance even in 31-bit legacy
 # application context. The feature is not specific to any particular
 # processor, as long as it's "z-CPU". Latter implies that the code
-# remains z/Architecture specific. On z900 SHA256 was measured to
+# remains z/Architecture specific. On z990 SHA256 was measured to
 # perform 2.4x and SHA512 - 13x better than code generated by gcc 4.3.
 
 $flavour = shift;
@@ -64,7 +71,7 @@ $tbl="%r13";
 $T1="%r14";
 $sp="%r15";
 
-while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+while (($output=shift) && ($output!~/\w[\w\-]*\.\w+$/)) {}
 open STDOUT,">$output";
 
 if ($output =~ /512/) {

crypto/sha/asm/sha512-sparcv9.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2007-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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@fy.chalmers.se> for the OpenSSL
@@ -49,7 +56,7 @@
 # saturates at 11.5x single-process result on 8-core processor, or
 # ~11/16GBps per 2.85GHz socket.
 
-$output=shift;
+$output=pop;
 open STDOUT,">$output";
 
 if ($output =~ /512/) {
@@ -791,7 +798,7 @@ ___
 
 # Purpose of these subroutines is to explicitly encode VIS instructions,
 # so that one can compile the module without having to specify VIS
-# extentions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
+# extensions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
 # Idea is to reserve for option to produce "universal" binary and let
 # programmer detect if current CPU is VIS capable at run-time.
 sub unvis {

crypto/sha/asm/sha512-x86_64.pl

@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2005-2016 The OpenSSL Project Authors. All Rights Reserved.
+#
+# Licensed under the OpenSSL license (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
@@ -34,7 +41,7 @@
 # level parallelism, on a given CPU implementation in this case.
 #
 # Special note on Intel EM64T. While Opteron CPU exhibits perfect
-# perfromance ratio of 1.5 between 64- and 32-bit flavors [see above],
+# performance ratio of 1.5 between 64- and 32-bit flavors [see above],
 # [currently available] EM64T CPUs apparently are far from it. On the
 # contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit
 # sha256_block:-( This is presumably because 64-bit shifts/rotates
@@ -86,12 +93,14 @@
 # Sandy Bridge	17.4	14.2(+23%)  11.6(+50%(**))  11.2    8.10(+38%(**))
 # Ivy Bridge	12.6	10.5(+20%)  10.3(+22%)	    8.17    7.22(+13%)
 # Haswell	12.2	9.28(+31%)  7.80(+56%)	    7.66    5.40(+42%)
+# Skylake	11.4	9.03(+26%)  7.70(+48%)      7.25    5.20(+40%)
 # Bulldozer	21.1	13.6(+54%)  13.6(+54%(***)) 13.5    8.58(+57%)
 # VIA Nano	23.0	16.5(+39%)  -		    14.7    -
 # Atom		23.0	18.9(+22%)  -		    14.7    -
 # Silvermont	27.4	20.6(+33%)  -               17.5    -
+# Goldmont	18.9	14.3(+32%)  4.16(+350%)     12.0    -
 #
-# (*)	whichever best applicable;
+# (*)	whichever best applicable, including SHAEXT;
 # (**)	switch from ror to shrd stands for fair share of improvement;
 # (***)	execution time is fully determined by remaining integer-only
 #	part, body_00_15; reducing the amount of SIMD instructions
@@ -131,7 +140,7 @@ if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([
 $shaext=1;	### set to zero if compiling for 1.0.1
 $avx=1		if (!$shaext && $avx);
 
-open OUT,"| \"$^X\" $xlate $flavour $output";
+open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
 *STDOUT=*OUT;
 
 if ($output =~ /512/) {

crypto/sha/asm/sha512p8-ppc.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 OpenSSL license (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