Vendor import of OpenSSL 0.9.8i.vendor/openssl/0.9.8i

3 files changed, 832 insertions, 20 deletions

diff --git a/crypto/bn/asm/ia64.S b/crypto/bn/asm/ia64.S
index 7b82b820e62a..951abc53ea5b 100644
--- a/crypto/bn/asm/ia64.S
+++ b/crypto/bn/asm/ia64.S
@@ -171,21 +171,21 @@
 .skip	32	// makes the loop body aligned at 64-byte boundary
 bn_add_words:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 { .mii;	alloc		r2=ar.pfs,4,12,0,16
 	cmp4.le		p6,p0=r35,r0	};;
 { .mfb;	mov		r8=r0			// return value
 (p6)	br.ret.spnt.many	b0	};;
 
-	.save	ar.lc,r3
 { .mib;	sub		r10=r35,r0,1
+	.save	ar.lc,r3
 	mov		r3=ar.lc
 	brp.loop.imp	.L_bn_add_words_ctop,.L_bn_add_words_cend-16
 					}
-	.body
 { .mib;	ADDP		r14=0,r32		// rp
+	.save	pr,r9
 	mov		r9=pr		};;
+	.body
 { .mii;	ADDP		r15=0,r33		// ap
 	mov		ar.lc=r10
 	mov		ar.ec=6		}
@@ -224,21 +224,21 @@ bn_add_words:
 .skip	32	// makes the loop body aligned at 64-byte boundary
 bn_sub_words:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 { .mii;	alloc		r2=ar.pfs,4,12,0,16
 	cmp4.le		p6,p0=r35,r0	};;
 { .mfb;	mov		r8=r0			// return value
 (p6)	br.ret.spnt.many	b0	};;
 
-	.save	ar.lc,r3
 { .mib;	sub		r10=r35,r0,1
+	.save	ar.lc,r3
 	mov		r3=ar.lc
 	brp.loop.imp	.L_bn_sub_words_ctop,.L_bn_sub_words_cend-16
 					}
-	.body
 { .mib;	ADDP		r14=0,r32		// rp
+	.save	pr,r9
 	mov		r9=pr		};;
+	.body
 { .mii;	ADDP		r15=0,r33		// ap
 	mov		ar.lc=r10
 	mov		ar.ec=6		}
@@ -283,7 +283,6 @@ bn_sub_words:
 .skip	32	// makes the loop body aligned at 64-byte boundary
 bn_mul_words:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 #ifdef XMA_TEMPTATION
 { .mfi;	alloc		r2=ar.pfs,4,0,0,0	};;
@@ -294,9 +293,10 @@ bn_mul_words:
 	cmp4.le		p6,p0=r34,r0
 (p6)	br.ret.spnt.many	b0		};;
 
-	.save	ar.lc,r3
 { .mii;	sub	r10=r34,r0,1
+	.save	ar.lc,r3
 	mov	r3=ar.lc
+	.save	pr,r9
 	mov	r9=pr			};;
 
 	.body
@@ -397,22 +397,21 @@ bn_mul_words:
 .skip	48	// makes the loop body aligned at 64-byte boundary
 bn_mul_add_words:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
-	.save	ar.lc,r3
-	.save	pr,r9
 { .mmi;	alloc		r2=ar.pfs,4,4,0,8
 	cmp4.le		p6,p0=r34,r0
+	.save	ar.lc,r3
 	mov		r3=ar.lc	};;
 { .mib;	mov		r8=r0		// return value
 	sub		r10=r34,r0,1
 (p6)	br.ret.spnt.many	b0	};;
 
-	.body
 { .mib;	setf.sig	f8=r35		// w
+	.save	pr,r9
 	mov		r9=pr
 	brp.loop.imp	.L_bn_mul_add_words_ctop,.L_bn_mul_add_words_cend-16
 					}
+	.body
 { .mmi;	ADDP		r14=0,r32	// rp
 	ADDP		r15=0,r33	// ap
 	mov		ar.lc=r10	}
@@ -466,7 +465,6 @@ bn_mul_add_words:
 .skip	32	// makes the loop body aligned at 64-byte boundary 
 bn_sqr_words:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 { .mii;	alloc		r2=ar.pfs,3,0,0,0
 	sxt4		r34=r34		};;
@@ -476,9 +474,10 @@ bn_sqr_words:
 	nop.f		0x0
 (p6)	br.ret.spnt.many	b0	};;
 
-	.save	ar.lc,r3
 { .mii;	sub	r10=r34,r0,1
+	.save	ar.lc,r3
 	mov	r3=ar.lc
+	.save	pr,r9
 	mov	r9=pr			};;
 
 	.body
@@ -545,7 +544,6 @@ bn_sqr_words:
 .align	64
 bn_sqr_comba8:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii;	alloc	r2=ar.pfs,2,1,0,0
@@ -617,7 +615,6 @@ bn_sqr_comba8:
 .align	64
 bn_mul_comba8:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii;	alloc	r2=ar.pfs,3,0,0,0
@@ -1175,7 +1172,6 @@ bn_mul_comba8:
 .align	64
 bn_sqr_comba4:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii;	alloc   r2=ar.pfs,2,1,0,0
@@ -1208,7 +1204,6 @@ bn_sqr_comba4:
 .align	64
 bn_mul_comba4:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
 #if defined(_HPUX_SOURCE) && !defined(_LP64)
 { .mii;	alloc   r2=ar.pfs,3,0,0,0
@@ -1411,11 +1406,11 @@ equ=p24
 .align	64
 bn_div_words:
 	.prologue
-	.fframe	0
 	.save	ar.pfs,r2
-	.save	b0,r3
 { .mii;	alloc		r2=ar.pfs,3,5,0,8
+	.save	b0,r3
 	mov		r3=b0
+	.save	pr,r10
 	mov		r10=pr		};;
 { .mmb;	cmp.eq		p6,p0=r34,r0
 	mov		r8=-1
diff --git a/crypto/bn/asm/mo-586.pl b/crypto/bn/asm/mo-586.pl
new file mode 100755
index 000000000000..0982293094d9
--- /dev/null
+++ b/crypto/bn/asm/mo-586.pl
@@ -0,0 +1,603 @@
+#!/usr/bin/env perl
+
+# This is crypto/bn/asm/x86-mont.pl (with asciz from crypto/perlasm/x86asm.pl)
+# from OpenSSL 0.9.9-dev 
+
+sub ::asciz
+{ my @str=unpack("C*",shift);
+    push @str,0;
+    while ($#str>15) {
+	&data_byte(@str[0..15]);
+	foreach (0..15) { shift @str; }
+    }
+    &data_byte(@str) if (@str);
+}
+
+# ====================================================================
+# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+# ====================================================================
+
+# October 2005
+#
+# This is a "teaser" code, as it can be improved in several ways...
+# First of all non-SSE2 path should be implemented (yes, for now it
+# performs Montgomery multiplication/convolution only on SSE2-capable
+# CPUs such as P4, others fall down to original code). Then inner loop
+# can be unrolled and modulo-scheduled to improve ILP and possibly
+# moved to 128-bit XMM register bank (though it would require input
+# rearrangement and/or increase bus bandwidth utilization). Dedicated
+# squaring procedure should give further performance improvement...
+# Yet, for being draft, the code improves rsa512 *sign* benchmark by
+# 110%(!), rsa1024 one - by 70% and rsa4096 - by 20%:-)
+
+# December 2006
+#
+# Modulo-scheduling SSE2 loops results in further 15-20% improvement.
+# Integer-only code [being equipped with dedicated squaring procedure]
+# gives ~40% on rsa512 sign benchmark...
+
+push(@INC,"perlasm","../../perlasm");
+require "x86asm.pl";
+
+&asm_init($ARGV[0],$0);
+
+$sse2=0;
+for (@ARGV) { $sse2=1 if (/-DOPENSSL_IA32_SSE2/); }
+
+&external_label("OPENSSL_ia32cap_P") if ($sse2);
+
+&function_begin("bn_mul_mont");
+
+$i="edx";
+$j="ecx";
+$ap="esi";	$tp="esi";		# overlapping variables!!!
+$rp="edi";	$bp="edi";		# overlapping variables!!!
+$np="ebp";
+$num="ebx";
+
+$_num=&DWP(4*0,"esp");			# stack top layout
+$_rp=&DWP(4*1,"esp");
+$_ap=&DWP(4*2,"esp");
+$_bp=&DWP(4*3,"esp");
+$_np=&DWP(4*4,"esp");
+$_n0=&DWP(4*5,"esp");	$_n0q=&QWP(4*5,"esp");
+$_sp=&DWP(4*6,"esp");
+$_bpend=&DWP(4*7,"esp");
+$frame=32;				# size of above frame rounded up to 16n
+
+	&xor	("eax","eax");
+	&mov	("edi",&wparam(5));	# int num
+	&cmp	("edi",4);
+	&jl	(&label("just_leave"));
+
+	&lea	("esi",&wparam(0));	# put aside pointer to argument block
+	&lea	("edx",&wparam(1));	# load ap
+	&mov	("ebp","esp");		# saved stack pointer!
+	&add	("edi",2);		# extra two words on top of tp
+	&neg	("edi");
+	&lea	("esp",&DWP(-$frame,"esp","edi",4));	# alloca($frame+4*(num+2))
+	&neg	("edi");
+
+	# minimize cache contention by arraning 2K window between stack
+	# pointer and ap argument [np is also position sensitive vector,
+	# but it's assumed to be near ap, as it's allocated at ~same
+	# time].
+	&mov	("eax","esp");
+	&sub	("eax","edx");
+	&and	("eax",2047);
+	&sub	("esp","eax");		# this aligns sp and ap modulo 2048
+
+	&xor	("edx","esp");
+	&and	("edx",2048);
+	&xor	("edx",2048);
+	&sub	("esp","edx");		# this splits them apart modulo 4096
+
+	&and	("esp",-64);		# align to cache line
+
+	################################# load argument block...
+	&mov	("eax",&DWP(0*4,"esi"));# BN_ULONG *rp
+	&mov	("ebx",&DWP(1*4,"esi"));# const BN_ULONG *ap
+	&mov	("ecx",&DWP(2*4,"esi"));# const BN_ULONG *bp
+	&mov	("edx",&DWP(3*4,"esi"));# const BN_ULONG *np
+	&mov	("esi",&DWP(4*4,"esi"));# const BN_ULONG *n0
+	#&mov	("edi",&DWP(5*4,"esi"));# int num
+
+	&mov	("esi",&DWP(0,"esi"));	# pull n0[0]
+	&mov	($_rp,"eax");		# ... save a copy of argument block
+	&mov	($_ap,"ebx");
+	&mov	($_bp,"ecx");
+	&mov	($_np,"edx");
+	&mov	($_n0,"esi");
+	&lea	($num,&DWP(-3,"edi"));	# num=num-1 to assist modulo-scheduling
+	#&mov	($_num,$num);		# redundant as $num is not reused
+	&mov	($_sp,"ebp");		# saved stack pointer!
+
+if($sse2) {
+$acc0="mm0";	# mmx register bank layout
+$acc1="mm1";
+$car0="mm2";
+$car1="mm3";
+$mul0="mm4";
+$mul1="mm5";
+$temp="mm6";
+$mask="mm7";
+
+	&picmeup("eax","OPENSSL_ia32cap_P");
+	&bt	(&DWP(0,"eax"),26);
+	&jnc	(&label("non_sse2"));
+
+	&mov	("eax",-1);
+	&movd	($mask,"eax");		# mask 32 lower bits
+
+	&mov	($ap,$_ap);		# load input pointers
+	&mov	($bp,$_bp);
+	&mov	($np,$_np);
+
+	&xor	($i,$i);		# i=0
+	&xor	($j,$j);		# j=0
+
+	&movd	($mul0,&DWP(0,$bp));		# bp[0]
+	&movd	($mul1,&DWP(0,$ap));		# ap[0]
+	&movd	($car1,&DWP(0,$np));		# np[0]
+
+	&pmuludq($mul1,$mul0);			# ap[0]*bp[0]
+	&movq	($car0,$mul1);
+	&movq	($acc0,$mul1);			# I wish movd worked for
+	&pand	($acc0,$mask);			# inter-register transfers
+
+	&pmuludq($mul1,$_n0q);			# *=n0
+
+	&pmuludq($car1,$mul1);			# "t[0]"*np[0]*n0
+	&paddq	($car1,$acc0);
+
+	&movd	($acc1,&DWP(4,$np));		# np[1]
+	&movd	($acc0,&DWP(4,$ap));		# ap[1]
+
+	&psrlq	($car0,32);
+	&psrlq	($car1,32);
+
+	&inc	($j);				# j++
+&set_label("1st",16);
+	&pmuludq($acc0,$mul0);			# ap[j]*bp[0]
+	&pmuludq($acc1,$mul1);			# np[j]*m1
+	&paddq	($car0,$acc0);			# +=c0
+	&paddq	($car1,$acc1);			# +=c1
+
+	&movq	($acc0,$car0);
+	&pand	($acc0,$mask);
+	&movd	($acc1,&DWP(4,$np,$j,4));	# np[j+1]
+	&paddq	($car1,$acc0);			# +=ap[j]*bp[0];
+	&movd	($acc0,&DWP(4,$ap,$j,4));	# ap[j+1]
+	&psrlq	($car0,32);
+	&movd	(&DWP($frame-4,"esp",$j,4),$car1);	# tp[j-1]=
+	&psrlq	($car1,32);
+
+	&lea	($j,&DWP(1,$j));
+	&cmp	($j,$num);
+	&jl	(&label("1st"));
+
+	&pmuludq($acc0,$mul0);			# ap[num-1]*bp[0]
+	&pmuludq($acc1,$mul1);			# np[num-1]*m1
+	&paddq	($car0,$acc0);			# +=c0
+	&paddq	($car1,$acc1);			# +=c1
+
+	&movq	($acc0,$car0);
+	&pand	($acc0,$mask);
+	&paddq	($car1,$acc0);			# +=ap[num-1]*bp[0];
+	&movd	(&DWP($frame-4,"esp",$j,4),$car1);	# tp[num-2]=
+
+	&psrlq	($car0,32);
+	&psrlq	($car1,32);
+
+	&paddq	($car1,$car0);
+	&movq	(&QWP($frame,"esp",$num,4),$car1);	# tp[num].tp[num-1]
+
+	&inc	($i);				# i++
+&set_label("outer");
+	&xor	($j,$j);			# j=0
+
+	&movd	($mul0,&DWP(0,$bp,$i,4));	# bp[i]
+	&movd	($mul1,&DWP(0,$ap));		# ap[0]
+	&movd	($temp,&DWP($frame,"esp"));	# tp[0]
+	&movd	($car1,&DWP(0,$np));		# np[0]
+	&pmuludq($mul1,$mul0);			# ap[0]*bp[i]
+
+	&paddq	($mul1,$temp);			# +=tp[0]
+	&movq	($acc0,$mul1);
+	&movq	($car0,$mul1);
+	&pand	($acc0,$mask);
+
+	&pmuludq($mul1,$_n0q);			# *=n0
+
+	&pmuludq($car1,$mul1);
+	&paddq	($car1,$acc0);
+
+	&movd	($temp,&DWP($frame+4,"esp"));	# tp[1]
+	&movd	($acc1,&DWP(4,$np));		# np[1]
+	&movd	($acc0,&DWP(4,$ap));		# ap[1]
+
+	&psrlq	($car0,32);
+	&psrlq	($car1,32);
+	&paddq	($car0,$temp);			# +=tp[1]
+
+	&inc	($j);				# j++
+	&dec	($num);
+&set_label("inner");
+	&pmuludq($acc0,$mul0);			# ap[j]*bp[i]
+	&pmuludq($acc1,$mul1);			# np[j]*m1
+	&paddq	($car0,$acc0);			# +=c0
+	&paddq	($car1,$acc1);			# +=c1
+
+	&movq	($acc0,$car0);
+	&movd	($temp,&DWP($frame+4,"esp",$j,4));# tp[j+1]
+	&pand	($acc0,$mask);
+	&movd	($acc1,&DWP(4,$np,$j,4));	# np[j+1]
+	&paddq	($car1,$acc0);			# +=ap[j]*bp[i]+tp[j]
+	&movd	($acc0,&DWP(4,$ap,$j,4));	# ap[j+1]
+	&psrlq	($car0,32);
+	&movd	(&DWP($frame-4,"esp",$j,4),$car1);# tp[j-1]=
+	&psrlq	($car1,32);
+	&paddq	($car0,$temp);			# +=tp[j+1]
+
+	&dec	($num);
+	&lea	($j,&DWP(1,$j));		# j++
+	&jnz	(&label("inner"));
+
+	&mov	($num,$j);
+	&pmuludq($acc0,$mul0);			# ap[num-1]*bp[i]
+	&pmuludq($acc1,$mul1);			# np[num-1]*m1
+	&paddq	($car0,$acc0);			# +=c0
+	&paddq	($car1,$acc1);			# +=c1
+
+	&movq	($acc0,$car0);
+	&pand	($acc0,$mask);
+	&paddq	($car1,$acc0);			# +=ap[num-1]*bp[i]+tp[num-1]
+	&movd	(&DWP($frame-4,"esp",$j,4),$car1);	# tp[num-2]=
+	&psrlq	($car0,32);
+	&psrlq	($car1,32);
+
+	&movd	($temp,&DWP($frame+4,"esp",$num,4));	# += tp[num]
+	&paddq	($car1,$car0);
+	&paddq	($car1,$temp);
+	&movq	(&QWP($frame,"esp",$num,4),$car1);	# tp[num].tp[num-1]
+
+	&lea	($i,&DWP(1,$i));		# i++
+	&cmp	($i,$num);
+	&jle	(&label("outer"));
+
+	&emms	();				# done with mmx bank
+	&jmp	(&label("common_tail"));
+
+&set_label("non_sse2",16);
+}
+
+if (0) {
+	&mov	("esp",$_sp);
+	&xor	("eax","eax");	# signal "not fast enough [yet]"
+	&jmp	(&label("just_leave"));
+	# While the below code provides competitive performance for
+	# all key lengthes on modern Intel cores, it's still more
+	# than 10% slower for 4096-bit key elsewhere:-( "Competitive"
+	# means compared to the original integer-only assembler.
+	# 512-bit RSA sign is better by ~40%, but that's about all
+	# one can say about all CPUs...
+} else {
+$inp="esi";	# integer path uses these registers differently
+$word="edi";
+$carry="ebp";
+
+	&mov	($inp,$_ap);
+	&lea	($carry,&DWP(1,$num));
+	&mov	($word,$_bp);
+	&xor	($j,$j);				# j=0
+	&mov	("edx",$inp);
+	&and	($carry,1);				# see if num is even
+	&sub	("edx",$word);				# see if ap==bp
+	&lea	("eax",&DWP(4,$word,$num,4));		# &bp[num]
+	&or	($carry,"edx");
+	&mov	($word,&DWP(0,$word));			# bp[0]
+	&jz	(&label("bn_sqr_mont"));
+	&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();
diff --git a/crypto/bn/asm/x86_64-mont.pl b/crypto/bn/asm/x86_64-mont.pl
new file mode 100755
index 000000000000..c43b69592a5c
--- /dev/null
+++ b/crypto/bn/asm/x86_64-mont.pl
@@ -0,0 +1,214 @@
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
+# 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/.
+# ====================================================================
+
+# October 2005.
+#
+# Montgomery multiplication routine for x86_64. While it gives modest
+# 9% improvement of rsa4096 sign on Opteron, rsa512 sign runs more
+# than twice, >2x, as fast. Most common rsa1024 sign is improved by
+# respectful 50%. It remains to be seen if loop unrolling and
+# dedicated squaring routine can provide further improvement...
+
+$output=shift;
+
+$0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
+( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or
+( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or
+die "can't locate x86_64-xlate.pl";
+
+open STDOUT,"| $^X $xlate $output";
+
+# int bn_mul_mont(
+$rp="%rdi";	# BN_ULONG *rp,
+$ap="%rsi";	# const BN_ULONG *ap,
+$bp="%rdx";	# const BN_ULONG *bp,
+$np="%rcx";	# const BN_ULONG *np,
+$n0="%r8";	# const BN_ULONG *n0,
+$num="%r9";	# int num);
+$lo0="%r10";
+$hi0="%r11";
+$bp="%r12";	# reassign $bp
+$hi1="%r13";
+$i="%r14";
+$j="%r15";
+$m0="%rbx";
+$m1="%rbp";
+
+$code=<<___;
+.text
+
+.globl	bn_mul_mont
+.type	bn_mul_mont,\@function,6
+.align	16
+bn_mul_mont:
+	push	%rbx
+	push	%rbp
+	push	%r12
+	push	%r13
+	push	%r14
+	push	%r15
+
+	mov	${num}d,${num}d
+	lea	2($num),%rax
+	mov	%rsp,%rbp
+	neg	%rax
+	lea	(%rsp,%rax,8),%rsp	# tp=alloca(8*(num+2))
+	and	\$-1024,%rsp		# minimize TLB usage
+
+	mov	%rbp,8(%rsp,$num,8)	# tp[num+1]=%rsp
+	mov	%rdx,$bp		# $bp reassigned, remember?
+
+	mov	($n0),$n0		# pull n0[0] value
+
+	xor	$i,$i			# i=0
+	xor	$j,$j			# j=0
+
+	mov	($bp),$m0		# m0=bp[0]
+	mov	($ap),%rax
+	mulq	$m0			# ap[0]*bp[0]
+	mov	%rax,$lo0
+	mov	%rdx,$hi0
+
+	imulq	$n0,%rax		# "tp[0]"*n0
+	mov	%rax,$m1
+
+	mulq	($np)			# np[0]*m1
+	add	$lo0,%rax		# discarded
+	adc	\$0,%rdx
+	mov	%rdx,$hi1
+
+	lea	1($j),$j		# j++
+.L1st:
+	mov	($ap,$j,8),%rax
+	mulq	$m0			# ap[j]*bp[0]
+	add	$hi0,%rax
+	adc	\$0,%rdx
+	mov	%rax,$lo0
+	mov	($np,$j,8),%rax
+	mov	%rdx,$hi0
+
+	mulq	$m1			# np[j]*m1
+	add	$hi1,%rax
+	lea	1($j),$j		# j++
+	adc	\$0,%rdx
+	add	$lo0,%rax		# np[j]*m1+ap[j]*bp[0]
+	adc	\$0,%rdx
+	mov	%rax,-16(%rsp,$j,8)	# tp[j-1]
+	cmp	$num,$j
+	mov	%rdx,$hi1
+	jl	.L1st
+
+	xor	%rdx,%rdx
+	add	$hi0,$hi1
+	adc	\$0,%rdx
+	mov	$hi1,-8(%rsp,$num,8)
+	mov	%rdx,(%rsp,$num,8)	# store upmost overflow bit
+
+	lea	1($i),$i		# i++
+.align	4
+.Louter:
+	xor	$j,$j			# j=0
+
+	mov	($bp,$i,8),$m0		# m0=bp[i]
+	mov	($ap),%rax		# ap[0]
+	mulq	$m0			# ap[0]*bp[i]
+	add	(%rsp),%rax		# ap[0]*bp[i]+tp[0]
+	adc	\$0,%rdx
+	mov	%rax,$lo0
+	mov	%rdx,$hi0
+
+	imulq	$n0,%rax		# tp[0]*n0
+	mov	%rax,$m1
+
+	mulq	($np,$j,8)		# np[0]*m1
+	add	$lo0,%rax		# discarded
+	mov	8(%rsp),$lo0		# tp[1]
+	adc	\$0,%rdx
+	mov	%rdx,$hi1
+
+	lea	1($j),$j		# j++
+.align	4
+.Linner:
+	mov	($ap,$j,8),%rax
+	mulq	$m0			# ap[j]*bp[i]
+	add	$hi0,%rax
+	adc	\$0,%rdx
+	add	%rax,$lo0		# ap[j]*bp[i]+tp[j]
+	mov	($np,$j,8),%rax
+	adc	\$0,%rdx
+	mov	%rdx,$hi0
+
+	mulq	$m1			# np[j]*m1
+	add	$hi1,%rax
+	lea	1($j),$j		# j++
+	adc	\$0,%rdx
+	add	$lo0,%rax		# np[j]*m1+ap[j]*bp[i]+tp[j]
+	adc	\$0,%rdx
+	mov	(%rsp,$j,8),$lo0
+	cmp	$num,$j
+	mov	%rax,-16(%rsp,$j,8)	# tp[j-1]
+	mov	%rdx,$hi1
+	jl	.Linner
+
+	xor	%rdx,%rdx
+	add	$hi0,$hi1
+	adc	\$0,%rdx
+	add	$lo0,$hi1		# pull upmost overflow bit
+	adc	\$0,%rdx
+	mov	$hi1,-8(%rsp,$num,8)
+	mov	%rdx,(%rsp,$num,8)	# store upmost overflow bit
+
+	lea	1($i),$i		# i++
+	cmp	$num,$i
+	jl	.Louter
+
+	lea	(%rsp),$ap		# borrow ap for tp
+	lea	-1($num),$j		# j=num-1
+
+	mov	($ap),%rax		# tp[0]
+	xor	$i,$i			# i=0 and clear CF!
+	jmp	.Lsub
+.align	16
+.Lsub:	sbb	($np,$i,8),%rax
+	mov	%rax,($rp,$i,8)		# rp[i]=tp[i]-np[i]
+	dec	$j			# doesn't affect CF!
+	mov	8($ap,$i,8),%rax	# tp[i+1]
+	lea	1($i),$i		# i++
+	jge	.Lsub
+
+	sbb	\$0,%rax		# handle upmost overflow bit
+	and	%rax,$ap
+	not	%rax
+	mov	$rp,$np
+	and	%rax,$np
+	lea	-1($num),$j
+	or	$np,$ap			# ap=borrow?tp:rp
+.align	16
+.Lcopy:					# copy or in-place refresh
+	mov	($ap,$j,8),%rax
+	mov	%rax,($rp,$j,8)		# rp[i]=tp[i]
+	mov	$i,(%rsp,$j,8)		# zap temporary vector
+	dec	$j
+	jge	.Lcopy
+
+	mov	8(%rsp,$num,8),%rsp	# restore %rsp
+	mov	\$1,%rax
+	pop	%r15
+	pop	%r14
+	pop	%r13
+	pop	%r12
+	pop	%rbp
+	pop	%rbx
+	ret
+.size	bn_mul_mont,.-bn_mul_mont
+.asciz	"Montgomery Multiplication for x86_64, CRYPTOGAMS by <appro\@openssl.org>"
+___
+
+print $code;
+close STDOUT;