Add assembly support to ios64-cross.

Fix typos in ios64-cross config line.
Reviewed-by: NTim Hudson <tjh@openssl.org>

Configure

@@ -599,7 +599,7 @@ my %table=(
 # CROSS_SDK=iPhoneOS7.0.sdk
 #
 "iphoneos-cross","cc:-O3 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fomit-frame-pointer -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:BN_LLONG RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:${no_asm}:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
-"ios64-cross","cc:-O3 -arch arm64 -mios-version-min=7.0.0 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:SIXTY_FOUR_BIT_LONG RC4_CHAR -RC4_CHUNK DES_INT DES_UNROLL -BF_PTR:${no_asm}:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
+"ios64-cross","cc:-O3 -arch arm64 -mios-version-min=7.0.0 -isysroot \$(CROSS_TOP)/SDKs/\$(CROSS_SDK) -fno-common::-D_REENTRANT:iOS:-Wl,-search_paths_first%:SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR:${aarch64_asm}:ios64:dlfcn:darwin-shared:-fPIC -fno-common:-dynamiclib:.\$(SHLIB_MAJOR).\$(SHLIB_MINOR).dylib",
 
 ##### A/UX
 "aux3-gcc","gcc:-O2 -DTERMIO::(unknown):AUX:-lbsd:RC4_CHAR RC4_CHUNK DES_UNROLL BF_PTR:::",

TABLE

@@ -3509,24 +3509,24 @@ $unistd       =
 $thread_cflag = -D_REENTRANT
 $sys_id       = iOS
 $lflags       = -Wl,-search_paths_first%
-$bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHAR -RC4_CHUNK DES_INT DES_UNROLL -BF_PTR
-$cpuid_obj    = 
+$bn_ops       = SIXTY_FOUR_BIT_LONG RC4_CHAR RC4_CHUNK DES_INT DES_UNROLL BF_PTR
+$cpuid_obj    = armcap.o arm64cpuid.o mem_clr.o
 $bn_obj       = 
 $ec_obj       = 
 $des_obj      = 
-$aes_obj      = 
+$aes_obj      = aes_core.o aes_cbc.o aesv8-armx.o
 $bf_obj       = 
 $md5_obj      = 
-$sha1_obj     = 
+$sha1_obj     = sha1-armv8.o sha256-armv8.o sha512-armv8.o
 $cast_obj     = 
 $rc4_obj      = 
 $rmd160_obj   = 
 $rc5_obj      = 
 $wp_obj       = 
 $cmll_obj     = 
-$modes_obj    = 
+$modes_obj    = ghashv8-armx.o
 $engines_obj  = 
-$perlasm_scheme = void
+$perlasm_scheme = ios64
 $dso_scheme   = dlfcn
 $shared_target= darwin-shared
 $shared_cflag = -fPIC -fno-common

crypto/Makefile

@@ -86,6 +86,7 @@ alphacpuid.s:	alphacpuid.pl
 	(preproc=$$$$.$@.S; trap "rm $$preproc" INT; \
 	$(PERL) alphacpuid.pl > $$preproc && \
 	$(CC) -E -P $$preproc > $@ && rm $$preproc)
+arm64cpuid.S:	arm64cpuid.pl;	$(PERL) arm64cpuid.pl $(PERLASM_SCHEME) > $@
 
 subdirs:
 	@target=all; $(RECURSIVE_MAKE)

crypto/aes/asm/aesv8-armx.pl

@@ -28,7 +28,15 @@
 # Cortex-A57	3.64		1.34		1.32
 
 $flavour = shift;
-open STDOUT,">".shift;
+$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;
 
 $prefix="aes_v8";
 
@@ -56,7 +64,7 @@ my ($zero,$rcon,$mask,$in0,$in1,$tmp,$key)=
 
 $code.=<<___;
 .align	5
-rcon:
+.Lrcon:
 .long	0x01,0x01,0x01,0x01
 .long	0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d,0x0c0f0e0d	// rotate-n-splat
 .long	0x1b,0x1b,0x1b,0x1b
@@ -85,7 +93,7 @@ $code.=<<___;
 	tst	$bits,#0x3f
 	b.ne	.Lenc_key_abort
 
-	adr	$ptr,rcon
+	adr	$ptr,.Lrcon
 	cmp	$bits,#192
 
 	veor	$zero,$zero,$zero

crypto/arm64cpuid.S → crypto/arm64cpuid.pl

+#!/usr/bin/env perl
+
+$flavour = shift;
+$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 $output";
+*STDOUT=*OUT;
+
+$code.=<<___;
 #include "arm_arch.h"
 
 .text
 .arch	armv8-a+crypto
 
 .align	5
-.global	_armv7_neon_probe
+.globl	_armv7_neon_probe
 .type	_armv7_neon_probe,%function
 _armv7_neon_probe:
 	orr	v15.16b, v15.16b, v15.16b
 	ret
 .size	_armv7_neon_probe,.-_armv7_neon_probe
 
-.global	_armv7_tick
+.globl	_armv7_tick
 .type	_armv7_tick,%function
 _armv7_tick:
+#ifdef	__APPLE__
+	mrs	x0, CNTPCT_EL0
+#else
 	mrs	x0, CNTVCT_EL0
+#endif
 	ret
 .size	_armv7_tick,.-_armv7_tick
 
-.global	_armv8_aes_probe
+.globl	_armv8_aes_probe
 .type	_armv8_aes_probe,%function
 _armv8_aes_probe:
 	aese	v0.16b, v0.16b
 	ret
 .size	_armv8_aes_probe,.-_armv8_aes_probe
 
-.global	_armv8_sha1_probe
+.globl	_armv8_sha1_probe
 .type	_armv8_sha1_probe,%function
 _armv8_sha1_probe:
 	sha1h	s0, s0
 	ret
 .size	_armv8_sha1_probe,.-_armv8_sha1_probe
 
-.global	_armv8_sha256_probe
+.globl	_armv8_sha256_probe
 .type	_armv8_sha256_probe,%function
 _armv8_sha256_probe:
 	sha256su0	v0.4s, v0.4s
 	ret
 .size	_armv8_sha256_probe,.-_armv8_sha256_probe
-.global	_armv8_pmull_probe
+.globl	_armv8_pmull_probe
 .type	_armv8_pmull_probe,%function
 _armv8_pmull_probe:
 	pmull	v0.1q, v0.1d, v0.1d
 	ret
 .size	_armv8_pmull_probe,.-_armv8_pmull_probe
+___
+
+print $code;
+close STDOUT;

crypto/armcap.c

@@ -46,12 +46,14 @@ unsigned long OPENSSL_rdtsc(void)
         return 0;
 }
 
+# if defined(__GNUC__) && __GNUC__>=2
+void OPENSSL_cpuid_setup(void) __attribute__ ((constructor));
+# endif
 /*
  * Use a weak reference to getauxval() so we can use it if it is available but
  * don't break the build if it is not.
  */
-# if defined(__GNUC__) && __GNUC__>=2
-void OPENSSL_cpuid_setup(void) __attribute__ ((constructor));
+# if defined(__GNUC__) && __GNUC__>=2 && defined(__ELF__)
 extern unsigned long getauxval(unsigned long type) __attribute__ ((weak));
 # else
 static unsigned long (*getauxval) (unsigned long) = NULL;

crypto/modes/asm/ghashv8-armx.pl

@@ -26,7 +26,15 @@
 # (*)	presented for reference/comparison purposes;
 
 $flavour = shift;
-open STDOUT,">".shift;
+$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;
 
 $Xi="x0";	# argument block
 $Htbl="x1";

crypto/perlasm/arm-xlate.pl

+#!/usr/bin/env perl
+
+# ARM assembler distiller by <appro>.
+
+my $flavour = shift;
+my $output = shift;
+open STDOUT,">$output" || die "can't open $output: $!";
+
+$flavour = "linux32" if (!$flavour or $flavour eq "void");
+
+my %GLOBALS;
+my $dotinlocallabels=($flavour=~/linux/)?1:0;
+
+################################################################
+# directives which need special treatment on different platforms
+################################################################
+my $arch = sub {
+    if ($flavour =~ /linux/)	{ ".arch\t".join(',',@_); }
+    else			{ ""; }
+};
+my $globl = sub {
+    my $name = shift;
+    my $global = \$GLOBALS{$name};
+    my $ret;
+
+    SWITCH: for ($flavour) {
+	/ios/		&& do { $name = "_$name";
+				last;
+			      };
+    }
+
+    $ret = ".globl	$name" if (!$ret);
+    $$global = $name;
+    $ret;
+};
+my $global = $globl;
+my $extern = sub {
+    &$globl(@_);
+    return;	# return nothing
+};
+my $type = sub {
+    if ($flavour =~ /linux/)	{ ".type\t".join(',',@_); }
+    else			{ ""; }
+};
+my $size = sub {
+    if ($flavour =~ /linux/)	{ ".size\t".join(',',@_); }
+    else			{ ""; }
+};
+my $inst = sub {
+    if ($flavour =~ /linux/)    { ".inst\t".join(',',@_); }
+    else                        { ".long\t".join(',',@_); }
+};
+my $asciz = sub {
+    my $line = join(",",@_);
+    if ($line =~ /^"(.*)"$/)
+    {	".byte	" . join(",",unpack("C*",$1),0) . "\n.align	2";	}
+    else
+    {	"";	}
+};
+
+sub range {
+  my ($r,$sfx,$start,$end) = @_;
+
+    join(",",map("$r$_$sfx",($start..$end)));
+}
+
+sub parse_args {
+  my $line = shift;
+  my @ret = ();
+
+    pos($line)=0;
+
+    while (1) {
+	if ($line =~ m/\G\[/gc) {
+	    $line =~ m/\G([^\]]+\][^,]*)\s*/g;
+	    push @ret,"[$1";
+	}
+	elsif ($line =~ m/\G\{/gc) {
+	    $line =~ m/\G([^\}]+\}[^,]*)\s*/g;
+	    my $arg = $1;
+	    $arg =~ s/([rdqv])([0-9]+)([^\-]*)\-\1([0-9]+)\3/range($1,$3,$2,$4)/ge;
+	    push @ret,"{$arg";
+	}
+	elsif ($line =~ m/\G([^,]+)\s*/g) {
+	    push @ret,$1;
+	}
+
+	last if ($line =~ m/\G$/gc);
+
+	$line =~ m/\G,\s*/g;
+    }
+
+    map {my $s=$_;$s=~s/\b(\w+)/$GLOBALS{$1} or $1/ge;$s} @ret;
+}
+
+while($line=<>) {
+
+    $line =~ s|/\*.*\*/||;	# get rid of C-style comments...
+    $line =~ s|^\s+||;		# ... and skip white spaces in beginning...
+    $line =~ s|\s+$||;		# ... and at the end
+
+    {
+	$line =~ s|[\b\.]L(\w+)|L$1|g;	# common denominator for Locallabel
+	$line =~ s|\bL(\w+)|\.L$1|g	if ($dotinlocallabels);
+    }
+
+    {
+	$line =~ s|(^[\.\w]+)\:\s*||;
+	my $label = $1;
+	if ($label) {
+	    printf "%s:",($GLOBALS{$label} or $label);
+	}
+    }
+
+    if ($line !~ m/^#/o) {
+	$line =~ s|^\s*(\.?)(\S+)\s*||o;
+	my $c = $1; $c = "\t" if ($c eq "");
+	my $mnemonic = $2;
+	my $opcode;
+	if ($mnemonic =~ m/([^\.]+)\.([^\.]+)/o) {
+	    $opcode = eval("\$$1_$2");
+	} else {
+	    $opcode = eval("\$$mnemonic");
+	}
+
+	my @args=parse_args($line);
+
+	if (ref($opcode) eq 'CODE') {
+		$line = &$opcode(@args);
+	} elsif ($mnemonic)         {
+		$line = $c.$mnemonic;
+		$line.= "\t".join(',',@args) if ($#args>=0);
+	}
+    }
+
+    print $line if ($line);
+    print "\n";
+}
+
+close STDOUT;

crypto/sha/asm/sha1-armv8.pl

@@ -20,7 +20,15 @@
 # (*)	Software results are presented mostly for reference purposes.
 
 $flavour = shift;
-open STDOUT,">".shift;
+$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));
@@ -154,6 +162,7 @@ $code.=<<___;
 
 .text
 
+.extern	OPENSSL_armcap_P
 .globl	sha1_block_data_order
 .type	sha1_block_data_order,%function
 .align	6

crypto/sha/asm/sha512-armv8.pl

@@ -29,7 +29,14 @@
 
 $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;
@@ -153,6 +160,7 @@ $code.=<<___;
 
 .text
 
+.extern	OPENSSL_armcap_P
 .globl	$func
 .type	$func,%function
 .align	6
@@ -182,7 +190,7 @@ $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:
@@ -232,8 +240,8 @@ $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
@@ -298,7 +306,7 @@ $code.=<<___ if ($SZ==4);
 	.long	0	//terminator
 ___
 $code.=<<___;
-.size	K$BITS,.-K$BITS
+.size	.LK$BITS,.-.LK$BITS
 .align	3
 .LOPENSSL_armcap_P:
 	.quad	OPENSSL_armcap_P-.
@@ -323,7 +331,7 @@ 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