diff options
| author | Andy Polyakov <appro@openssl.org> | 2015-04-02 10:17:42 +0200 |
|---|---|---|
| committer | Andy Polyakov <appro@openssl.org> | 2015-04-20 15:06:22 +0200 |
| commit | 313e6ec11fb8a7bda1676ce5804bee8755664141 (patch) | |
| tree | 48646a0e7df9d05ab25b537a201c26f1bfee0b0b /crypto/modes/asm/ghash-armv4.pl | |
| parent | Configure: Engage ecp_nistz256-armv8 module. (diff) | |
| download | openssl-313e6ec11fb8a7bda1676ce5804bee8755664141.tar.xz openssl-313e6ec11fb8a7bda1676ce5804bee8755664141.zip | |
Add assembly support for 32-bit iOS.
Reviewed-by: Matt Caswell <matt@openssl.org>
Reviewed-by: Richard Levitte <levitte@openssl.org>
Diffstat (limited to 'crypto/modes/asm/ghash-armv4.pl')
| -rw-r--r-- | crypto/modes/asm/ghash-armv4.pl | 37 |
1 files changed, 27 insertions, 10 deletions
diff --git a/crypto/modes/asm/ghash-armv4.pl b/crypto/modes/asm/ghash-armv4.pl index 44521f8984..7311ad2966 100644 --- a/crypto/modes/asm/ghash-armv4.pl +++ b/crypto/modes/asm/ghash-armv4.pl @@ -71,8 +71,20 @@ # *native* byte order on current platform. See gcm128.c for working # example... -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"; +} $Xi="r0"; # argument block $Htbl="r1"; @@ -126,6 +138,11 @@ $code=<<___; .text .code 32 +#ifdef __APPLE__ +#define ldrplb ldrbpl +#define ldrneb ldrbne +#endif + .type rem_4bit,%object .align 5 rem_4bit: @@ -373,9 +390,9 @@ $code.=<<___; .type gcm_init_neon,%function .align 4 gcm_init_neon: - vld1.64 $IN#hi,[r1,:64]! @ load H + vld1.64 $IN#hi,[r1]! @ load H vmov.i8 $t0,#0xe1 - vld1.64 $IN#lo,[r1,:64] + vld1.64 $IN#lo,[r1] vshl.i64 $t0#hi,#57 vshr.u64 $t0#lo,#63 @ t0=0xc2....01 vdup.8 $t1,$IN#hi[7] @@ -394,8 +411,8 @@ gcm_init_neon: .type gcm_gmult_neon,%function .align 4 gcm_gmult_neon: - vld1.64 $IN#hi,[$Xi,:64]! @ load Xi - vld1.64 $IN#lo,[$Xi,:64]! + vld1.64 $IN#hi,[$Xi]! @ load Xi + vld1.64 $IN#lo,[$Xi]! vmov.i64 $k48,#0x0000ffffffffffff vldmia $Htbl,{$Hlo-$Hhi} @ load twisted H vmov.i64 $k32,#0x00000000ffffffff @@ -412,8 +429,8 @@ gcm_gmult_neon: .type gcm_ghash_neon,%function .align 4 gcm_ghash_neon: - vld1.64 $Xl#hi,[$Xi,:64]! @ load Xi - vld1.64 $Xl#lo,[$Xi,:64]! + vld1.64 $Xl#hi,[$Xi]! @ load Xi + vld1.64 $Xl#lo,[$Xi]! vmov.i64 $k48,#0x0000ffffffffffff vldmia $Htbl,{$Hlo-$Hhi} @ load twisted H vmov.i64 $k32,#0x00000000ffffffff @@ -468,8 +485,8 @@ $code.=<<___; vrev64.8 $Xl,$Xl #endif sub $Xi,#16 - vst1.64 $Xl#hi,[$Xi,:64]! @ write out Xi - vst1.64 $Xl#lo,[$Xi,:64] + vst1.64 $Xl#hi,[$Xi]! @ write out Xi + vst1.64 $Xl#lo,[$Xi] ret @ bx lr .size gcm_ghash_neon,.-gcm_ghash_neon |