# 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.
# ====================================================================
# SHA256 block procedure for ARMv4. May 2007.
#
# 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";
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
}
$code=<<___;
-#include "arm_arch.h"
+#ifndef __KERNEL__
+# include "arm_arch.h"
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+#endif
.text
-.code 32
+#if defined(__thumb2__)
+.syntax unified
+.thumb
+#else
+.code 32
+#endif
.type K256,%object
.align 5
.word 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
.size K256,.-K256
.word 0 @ terminator
-#if __ARM_MAX_ARCH__>=7
+#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:
+.Lsha256_block_data_order:
+#if __ARM_ARCH__<7 && !defined(__thumb2__)
sub r3,pc,#8 @ sha256_block_data_order
- add $len,$inp,$len,lsl#6 @ len to point at the end of inp
-#if __ARM_MAX_ARCH__>=7
+#else
+ 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
bne .LNEON
#endif
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
stmdb sp!,{$ctx,$inp,$len,r4-r11,lr}
ldmia $ctx,{$A,$B,$C,$D,$E,$F,$G,$H}
sub $Ktbl,r3,#256+32 @ K256
$code.=".Lrounds_16_xx:\n";
for (;$i<32;$i++) { &BODY_16_XX($i,@V); unshift(@V,pop(@V)); }
$code.=<<___;
+#if __ARM_ARCH__>=7
+ ite eq @ Thumb2 thing, sanity check in ARM
+#endif
ldreq $t3,[sp,#16*4] @ pull ctx
bne .Lrounds_16_xx
.arch armv7-a
.fpu neon
+.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}
+ sub $H,sp,#16*4+16
+ adr $Ktbl,K256
+ bic $H,$H,#15 @ align for 128-bit stores
mov $t2,sp
- sub sp,sp,#16*4+16 @ alloca
- sub $Ktbl,r3,#256+32 @ K256
- bic sp,sp,#15 @ align for 128-bit stores
+ mov sp,$H @ alloca
+ add $len,$inp,$len,lsl#6 @ len to point at the end of inp
vld1.8 {@X[0]},[$inp]!
vld1.8 {@X[1]},[$inp]!
ldr $t0,[sp,#72]
sub $Ktbl,$Ktbl,#256 @ rewind $Ktbl
teq $inp,$t0
+ it eq
subeq $inp,$inp,#64 @ avoid SEGV
vld1.8 {@X[0]},[$inp]! @ load next input block
vld1.8 {@X[1]},[$inp]!
vld1.8 {@X[2]},[$inp]!
vld1.8 {@X[3]},[$inp]!
+ it ne
strne $inp,[sp,#68]
mov $Xfer,sp
___
str $D,[$t1],#4
stmia $t1,{$E-$H}
+ ittte ne
movne $Xfer,sp
ldrne $t1,[sp,#0]
eorne $t2,$t2,$t2
ldreq sp,[sp,#76] @ restore original sp
+ itt ne
eorne $t3,$B,$C
bne .L_00_48
my $Ktbl="r3";
$code.=<<___;
-#if __ARM_MAX_ARCH__>=7
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+
+# if defined(__thumb2__)
+# define INST(a,b,c,d) .byte c,d|0xc,a,b
+# else
+# define INST(a,b,c,d) .byte a,b,c,d
+# endif
+
.type sha256_block_data_order_armv8,%function
.align 5
sha256_block_data_order_armv8:
.LARMv8:
vld1.32 {$ABCD,$EFGH},[$ctx]
- sub $Ktbl,r3,#sha256_block_data_order-K256
+ 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]!
vadd.i32 $ABCD,$ABCD,$ABCD_SAVE
vadd.i32 $EFGH,$EFGH,$EFGH_SAVE
+ it ne
bne .Loop_v8
vst1.32 {$ABCD,$EFGH},[$ctx]
$code.=<<___;
.asciz "SHA256 block transform for ARMv4/NEON/ARMv8, 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
___
+open SELF,$0;
+while(<SELF>) {
+ next if (/^#!/);
+ last if (!s/^#/@/ and !/^$/);
+ print;
+}
+close SELF;
+
{ my %opcode = (
"sha256h" => 0xf3000c40, "sha256h2" => 0xf3100c40,
"sha256su0" => 0xf3ba03c0, "sha256su1" => 0xf3200c40 );
# 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",
+ 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;
projects / openssl.git / blobdiff