Split bignum code out of the sparcv9cap.c

[openssl.git] / crypto / modes / asm / ghash-sparcv9.pl

diff --git a/crypto/modes/asm/ghash-sparcv9.pl b/crypto/modes/asm/ghash-sparcv9.pl
index 0365e0f1ff429e8e5250e86a627616fb58cbbf3f..d3fa2a68fe143de1e1bac40e0d266adfd1d0b3bf 100644 (file)
--- a/crypto/modes/asm/ghash-sparcv9.pl
+++ b/crypto/modes/asm/ghash-sparcv9.pl
@@ -1,4 +1,11 @@
-#!/usr/bin/env perl
+#! /usr/bin/env perl
+# Copyright 2010-2020 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
@@ -46,13 +53,10 @@
 # saturates at ~15.5x single-process result on 8-core processor,
 # or ~20.5GBps per 2.85GHz socket.
 
-$bits=32;
-for (@ARGV)     { $bits=64 if (/\-m64/ || /\-xarch\=v9/); }
-if ($bits==64)  { $bias=2047; $frame=192; }
-else            { $bias=0;    $frame=112; }
+$output=pop and open STDOUT,">$output";
 
-$output=shift;
-open STDOUT,">$output";
+$frame="STACK_FRAME";
+$bias="STACK_BIAS";
 
 $Zhi="%o0";    # 64-bit values
 $Zlo="%o1";
@@ -75,11 +79,17 @@ $Htbl="%i1";
 $inp="%i2";
 $len="%i3";
 
-$code.=<<___ if ($bits==64);
+$code.=<<___;
+#ifndef __ASSEMBLER__
+# define __ASSEMBLER__ 1
+#endif
+#include "crypto/sparc_arch.h"
+
+#ifdef  __arch64__
 .register      %g2,#scratch
 .register      %g3,#scratch
-___
-$code.=<<___;
+#endif
+
 .section       ".text",#alloc,#execinstr
 
 .align 64
@@ -183,7 +193,7 @@ gcm_ghash_4bit:
 
        add     $inp,16,$inp
        cmp     $inp,$len
-       be,pn   `$bits==64?"%xcc":"%icc"`,.Ldone
+       be,pn   SIZE_T_CC,.Ldone
        and     $Zlo,0xf,$remi
 
        ldx     [$Htblo+$nhi],$Tlo
@@ -379,7 +389,7 @@ gcm_init_vis3:
        or      $V,%lo(0xA0406080),$V
        or      %l0,%lo(0x20C0E000),%l0
        sllx    $V,32,$V
-       or      %l0,$V,$V               ! (0xE0·i)&0xff=0xA040608020C0E000
+       or      %l0,$V,$V               ! (0xE0·i)&0xff=0xA040608020C0E000
        stx     $V,[%i0+16]
 
        ret
@@ -399,7 +409,7 @@ gcm_gmult_vis3:
 
        mov     0xE1,%l7
        sllx    %l7,57,$xE1             ! 57 is not a typo
-       ldx     [$Htable+16],$V         ! (0xE0·i)&0xff=0xA040608020C0E000
+       ldx     [$Htable+16],$V         ! (0xE0·i)&0xff=0xA040608020C0E000
 
        xor     $Hhi,$Hlo,$Hhl          ! Karatsuba pre-processing
        xmulx   $Xlo,$Hlo,$C0
@@ -411,9 +421,9 @@ gcm_gmult_vis3:
        xmulx   $Xhi,$Hhi,$Xhi
 
        sll     $C0,3,$sqr
-       srlx    $V,$sqr,$sqr            ! ·0xE0 [implicit &(7<<3)]
+       srlx    $V,$sqr,$sqr            ! ·0xE0 [implicit &(7<<3)]
        xor     $C0,$sqr,$sqr
-       sllx    $sqr,57,$sqr            ! ($C0·0xE1)<<1<<56 [implicit &0x7f]
+       sllx    $sqr,57,$sqr            ! ($C0·0xE1)<<1<<56 [implicit &0x7f]
 
        xor     $C0,$C1,$C1             ! Karatsuba post-processing
        xor     $Xlo,$C2,$C2
@@ -423,7 +433,7 @@ gcm_gmult_vis3:
        xor     $Xhi,$C2,$C2
        xor     $Xhi,$C1,$C1
 
-       xmulxhi $C0,$xE1,$Xlo           ! ·0xE1<<1<<56
+       xmulxhi $C0,$xE1,$Xlo           ! ·0xE1<<1<<56
         xor    $C0,$C2,$C2
        xmulx   $C1,$xE1,$C0
         xor    $C1,$C3,$C3
@@ -445,6 +455,8 @@ gcm_gmult_vis3:
 .align 32
 gcm_ghash_vis3:
        save    %sp,-$frame,%sp
+       nop
+       srln    $len,0,$len             ! needed on v8+, "nop" on v9
 
        ldx     [$Xip+8],$C2            ! load Xi
        ldx     [$Xip+0],$C3
@@ -453,7 +465,7 @@ gcm_ghash_vis3:
 
        mov     0xE1,%l7
        sllx    %l7,57,$xE1             ! 57 is not a typo
-       ldx     [$Htable+16],$V         ! (0xE0·i)&0xff=0xA040608020C0E000
+       ldx     [$Htable+16],$V         ! (0xE0·i)&0xff=0xA040608020C0E000
 
        and     $inp,7,$shl
        andn    $inp,7,$inp
@@ -490,9 +502,9 @@ gcm_ghash_vis3:
        xmulx   $Xhi,$Hhi,$Xhi
 
        sll     $C0,3,$sqr
-       srlx    $V,$sqr,$sqr            ! ·0xE0 [implicit &(7<<3)]
+       srlx    $V,$sqr,$sqr            ! ·0xE0 [implicit &(7<<3)]
        xor     $C0,$sqr,$sqr
-       sllx    $sqr,57,$sqr            ! ($C0·0xE1)<<1<<56 [implicit &0x7f]
+       sllx    $sqr,57,$sqr            ! ($C0·0xE1)<<1<<56 [implicit &0x7f]
 
        xor     $C0,$C1,$C1             ! Karatsuba post-processing
        xor     $Xlo,$C2,$C2
@@ -502,7 +514,7 @@ gcm_ghash_vis3:
        xor     $Xhi,$C2,$C2
        xor     $Xhi,$C1,$C1
 
-       xmulxhi $C0,$xE1,$Xlo           ! ·0xE1<<1<<56
+       xmulxhi $C0,$xE1,$Xlo           ! ·0xE1<<1<<56
         xor    $C0,$C2,$C2
        xmulx   $C1,$xE1,$C0
         xor    $C1,$C3,$C3
@@ -530,7 +542,7 @@ ___
 \f
 # Purpose of these subroutines is to explicitly encode VIS instructions,
 # so that one can compile the module without having to specify VIS
-# extentions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
+# extensions on compiler command line, e.g. -xarch=v9 vs. -xarch=v9a.
 # Idea is to reserve for option to produce "universal" binary and let
 # programmer detect if current CPU is VIS capable at run-time.
 sub unvis3 {
@@ -568,4 +580,4 @@ foreach (split("\n",$code)) {
        print $_,"\n";
 }
 
-close STDOUT;
+close STDOUT or die "error closing STDOUT: $!";