mo-586.pl

Openssl 0.9.8h 最新版OpenSSL

	&mov	($_bpend,"eax");
	&mov	("eax",&DWP(0,$inp));
	&xor	("edx","edx");

&set_label("mull",16);
	&mov	($carry,"edx");
	&mul	($word);				# ap[j]*bp[0]
	&add	($carry,"eax");
	&lea	($j,&DWP(1,$j));
	&adc	("edx",0);
	&mov	("eax",&DWP(0,$inp,$j,4));		# ap[j+1]
	&cmp	($j,$num);
	&mov	(&DWP($frame-4,"esp",$j,4),$carry);	# tp[j]=
	&jl	(&label("mull"));

	&mov	($carry,"edx");
	&mul	($word);				# ap[num-1]*bp[0]
	 &mov	($word,$_n0);
	&add	("eax",$carry);
	 &mov	($inp,$_np);
	&adc	("edx",0);
	 &imul	($word,&DWP($frame,"esp"));		# n0*tp[0]

	&mov	(&DWP($frame,"esp",$num,4),"eax");	# tp[num-1]=
	&xor	($j,$j);
	&mov	(&DWP($frame+4,"esp",$num,4),"edx");	# tp[num]=
	&mov	(&DWP($frame+8,"esp",$num,4),$j);	# tp[num+1]=

	&mov	("eax",&DWP(0,$inp));			# np[0]
	&mul	($word);				# np[0]*m
	&add	("eax",&DWP($frame,"esp"));		# +=tp[0]
	&mov	("eax",&DWP(4,$inp));			# np[1]
	&adc	("edx",0);
	&inc	($j);

	&jmp	(&label("2ndmadd"));

&set_label("1stmadd",16);
	&mov	($carry,"edx");
	&mul	($word);				# ap[j]*bp[i]
	&add	($carry,&DWP($frame,"esp",$j,4));	# +=tp[j]
	&lea	($j,&DWP(1,$j));
	&adc	("edx",0);
	&add	($carry,"eax");
	&mov	("eax",&DWP(0,$inp,$j,4));		# ap[j+1]
	&adc	("edx",0);
	&cmp	($j,$num);
	&mov	(&DWP($frame-4,"esp",$j,4),$carry);	# tp[j]=
	&jl	(&label("1stmadd"));

	&mov	($carry,"edx");
	&mul	($word);				# ap[num-1]*bp[i]
	&add	("eax",&DWP($frame,"esp",$num,4));	# +=tp[num-1]
	 &mov	($word,$_n0);
	&adc	("edx",0);
	 &mov	($inp,$_np);
	&add	($carry,"eax");
	&adc	("edx",0);
	 &imul	($word,&DWP($frame,"esp"));		# n0*tp[0]

	&xor	($j,$j);
	&add	("edx",&DWP($frame+4,"esp",$num,4));	# carry+=tp[num]
	&mov	(&DWP($frame,"esp",$num,4),$carry);	# tp[num-1]=
	&adc	($j,0);
	 &mov	("eax",&DWP(0,$inp));			# np[0]
	&mov	(&DWP($frame+4,"esp",$num,4),"edx");	# tp[num]=
	&mov	(&DWP($frame+8,"esp",$num,4),$j);	# tp[num+1]=

	&mul	($word);				# np[0]*m
	&add	("eax",&DWP($frame,"esp"));		# +=tp[0]
	&mov	("eax",&DWP(4,$inp));			# np[1]
	&adc	("edx",0);
	&mov	($j,1);

&set_label("2ndmadd",16);
	&mov	($carry,"edx");
	&mul	($word);				# np[j]*m
	&add	($carry,&DWP($frame,"esp",$j,4));	# +=tp[j]
	&lea	($j,&DWP(1,$j));
	&adc	("edx",0);
	&add	($carry,"eax");
	&mov	("eax",&DWP(0,$inp,$j,4));		# np[j+1]
	&adc	("edx",0);
	&cmp	($j,$num);
	&mov	(&DWP($frame-8,"esp",$j,4),$carry);	# tp[j-1]=
	&jl	(&label("2ndmadd"));

	&mov	($carry,"edx");
	&mul	($word);				# np[j]*m
	&add	($carry,&DWP($frame,"esp",$num,4));	# +=tp[num-1]
	&adc	("edx",0);
	&add	($carry,"eax");
	&adc	("edx",0);
	&mov	(&DWP($frame-4,"esp",$num,4),$carry);	# tp[num-2]=

	&xor	("eax","eax");
	 &mov	($j,$_bp);				# &bp[i]
	&add	("edx",&DWP($frame+4,"esp",$num,4));	# carry+=tp[num]
	&adc	("eax",&DWP($frame+8,"esp",$num,4));	# +=tp[num+1]
	 &lea	($j,&DWP(4,$j));
	&mov	(&DWP($frame,"esp",$num,4),"edx");	# tp[num-1]=
	 &cmp	($j,$_bpend);
	&mov	(&DWP($frame+4,"esp",$num,4),"eax");	# tp[num]=
	&je	(&label("common_tail"));

	&mov	($word,&DWP(0,$j));			# bp[i+1]
	&mov	($inp,$_ap);
	&mov	($_bp,$j);				# &bp[++i]
	&xor	($j,$j);
	&xor	("edx","edx");
	&mov	("eax",&DWP(0,$inp));
	&jmp	(&label("1stmadd"));

&set_label("bn_sqr_mont",16);
$sbit=$num;
	&mov	($_num,$num);
	&mov	($_bp,$j);				# i=0

	&mov	("eax",$word);				# ap[0]
	&mul	($word);				# ap[0]*ap[0]
	&mov	(&DWP($frame,"esp"),"eax");		# tp[0]=
	&mov	($sbit,"edx");
	&shr	("edx",1);
	&and	($sbit,1);
	&inc	($j);
&set_label("sqr",16);
	&mov	("eax",&DWP(0,$inp,$j,4));		# ap[j]
	&mov	($carry,"edx");
	&mul	($word);				# ap[j]*ap[0]
	&add	("eax",$carry);
	&lea	($j,&DWP(1,$j));
	&adc	("edx",0);
	&lea	($carry,&DWP(0,$sbit,"eax",2));
	&shr	("eax",31);
	&cmp	($j,$_num);
	&mov	($sbit,"eax");
	&mov	(&DWP($frame-4,"esp",$j,4),$carry);	# tp[j]=
	&jl	(&label("sqr"));

	&mov	("eax",&DWP(0,$inp,$j,4));		# ap[num-1]
	&mov	($carry,"edx");
	&mul	($word);				# ap[num-1]*ap[0]
	&add	("eax",$carry);
	 &mov	($word,$_n0);
	&adc	("edx",0);
	 &mov	($inp,$_np);
	&lea	($carry,&DWP(0,$sbit,"eax",2));
	 &imul	($word,&DWP($frame,"esp"));		# n0*tp[0]
	&shr	("eax",31);
	&mov	(&DWP($frame,"esp",$j,4),$carry);	# tp[num-1]=

	&lea	($carry,&DWP(0,"eax","edx",2));
	 &mov	("eax",&DWP(0,$inp));			# np[0]
	&shr	("edx",31);
	&mov	(&DWP($frame+4,"esp",$j,4),$carry);	# tp[num]=
	&mov	(&DWP($frame+8,"esp",$j,4),"edx");	# tp[num+1]=

	&mul	($word);				# np[0]*m
	&add	("eax",&DWP($frame,"esp"));		# +=tp[0]
	&mov	($num,$j);
	&adc	("edx",0);
	&mov	("eax",&DWP(4,$inp));			# np[1]
	&mov	($j,1);

&set_label("3rdmadd",16);
	&mov	($carry,"edx");
	&mul	($word);				# np[j]*m
	&add	($carry,&DWP($frame,"esp",$j,4));	# +=tp[j]
	&adc	("edx",0);
	&add	($carry,"eax");
	&mov	("eax",&DWP(4,$inp,$j,4));		# np[j+1]
	&adc	("edx",0);
	&mov	(&DWP($frame-4,"esp",$j,4),$carry);	# tp[j-1]=

	&mov	($carry,"edx");
	&mul	($word);				# np[j+1]*m
	&add	($carry,&DWP($frame+4,"esp",$j,4));	# +=tp[j+1]
	&lea	($j,&DWP(2,$j));
	&adc	("edx",0);
	&add	($carry,"eax");
	&mov	("eax",&DWP(0,$inp,$j,4));		# np[j+2]
	&adc	("edx",0);
	&cmp	($j,$num);
	&mov	(&DWP($frame-8,"esp",$j,4),$carry);	# tp[j]=
	&jl	(&label("3rdmadd"));

	&mov	($carry,"edx");
	&mul	($word);				# np[j]*m
	&add	($carry,&DWP($frame,"esp",$num,4));	# +=tp[num-1]
	&adc	("edx",0);
	&add	($carry,"eax");
	&adc	("edx",0);
	&mov	(&DWP($frame-4,"esp",$num,4),$carry);	# tp[num-2]=

	&mov	($j,$_bp);				# i
	&xor	("eax","eax");
	&mov	($inp,$_ap);
	&add	("edx",&DWP($frame+4,"esp",$num,4));	# carry+=tp[num]
	&adc	("eax",&DWP($frame+8,"esp",$num,4));	# +=tp[num+1]
	&mov	(&DWP($frame,"esp",$num,4),"edx");	# tp[num-1]=
	&cmp	($j,$num);
	&mov	(&DWP($frame+4,"esp",$num,4),"eax");	# tp[num]=
	&je	(&label("common_tail"));

	&mov	($word,&DWP(4,$inp,$j,4));		# ap[i]
	&lea	($j,&DWP(1,$j));
	&mov	("eax",$word);
	&mov	($_bp,$j);				# ++i
	&mul	($word);				# ap[i]*ap[i]
	&add	("eax",&DWP($frame,"esp",$j,4));	# +=tp[i]
	&adc	("edx",0);
	&mov	(&DWP($frame,"esp",$j,4),"eax");	# tp[i]=
	&xor	($carry,$carry);
	&cmp	($j,$num);
	&lea	($j,&DWP(1,$j));
	&je	(&label("sqrlast"));

	&mov	($sbit,"edx");				# zaps $num
	&shr	("edx",1);
	&and	($sbit,1);
&set_label("sqradd",16);
	&mov	("eax",&DWP(0,$inp,$j,4));		# ap[j]
	&mov	($carry,"edx");
	&mul	($word);				# ap[j]*ap[i]
	&add	("eax",$carry);
	&lea	($carry,&DWP(0,"eax","eax"));
	&adc	("edx",0);
	&shr	("eax",31);
	&add	($carry,&DWP($frame,"esp",$j,4));	# +=tp[j]
	&lea	($j,&DWP(1,$j));
	&adc	("eax",0);
	&add	($carry,$sbit);
	&adc	("eax",0);
	&cmp	($j,$_num);
	&mov	(&DWP($frame-4,"esp",$j,4),$carry);	# tp[j]=
	&mov	($sbit,"eax");
	&jle	(&label("sqradd"));

	&mov	($carry,"edx");
	&lea	("edx",&DWP(0,$sbit,"edx",2));
	&shr	($carry,31);
&set_label("sqrlast");
	&mov	($word,$_n0);
	&mov	($inp,$_np);
	&imul	($word,&DWP($frame,"esp"));		# n0*tp[0]

	&add	("edx",&DWP($frame,"esp",$j,4));	# +=tp[num]
	&mov	("eax",&DWP(0,$inp));			# np[0]
	&adc	($carry,0);
	&mov	(&DWP($frame,"esp",$j,4),"edx");	# tp[num]=
	&mov	(&DWP($frame+4,"esp",$j,4),$carry);	# tp[num+1]=

	&mul	($word);				# np[0]*m
	&add	("eax",&DWP($frame,"esp"));		# +=tp[0]
	&lea	($num,&DWP(-1,$j));
	&adc	("edx",0);
	&mov	($j,1);
	&mov	("eax",&DWP(4,$inp));			# np[1]

	&jmp	(&label("3rdmadd"));
}

&set_label("common_tail",16);
	&mov	($np,$_np);			# load modulus pointer
	&mov	($rp,$_rp);			# load result pointer
	&lea	($tp,&DWP($frame,"esp"));	# [$ap and $bp are zapped]

	&mov	("eax",&DWP(0,$tp));		# tp[0]
	&mov	($j,$num);			# j=num-1
	&xor	($i,$i);			# i=0 and clear CF!

&set_label("sub",16);
	&sbb	("eax",&DWP(0,$np,$i,4));
	&mov	(&DWP(0,$rp,$i,4),"eax");	# rp[i]=tp[i]-np[i]
	&dec	($j);				# doesn't affect CF!
	&mov	("eax",&DWP(4,$tp,$i,4));	# tp[i+1]
	&lea	($i,&DWP(1,$i));		# i++
	&jge	(&label("sub"));

	&sbb	("eax",0);			# handle upmost overflow bit
	&and	($tp,"eax");
	&not	("eax");
	&mov	($np,$rp);
	&and	($np,"eax");
	&or	($tp,$np);			# tp=carry?tp:rp

&set_label("copy",16);				# copy or in-place refresh
	&mov	("eax",&DWP(0,$tp,$num,4));
	&mov	(&DWP(0,$rp,$num,4),"eax");	# rp[i]=tp[i]
	&mov	(&DWP($frame,"esp",$num,4),$j);	# zap temporary vector
	&dec	($num);
	&jge	(&label("copy"));

	&mov	("esp",$_sp);		# pull saved stack pointer
	&mov	("eax",1);
&set_label("just_leave");
&function_end("bn_mul_mont");

&asciz("Montgomery Multiplication for x86, CRYPTOGAMS by <appro\@openssl.org>");

&asm_finish();