deps: upgrade openssl to 1.0.1s

PR-URL: https://github.com/nodejs/node/pull/5509
Reviewed-By: Fedor Indutny <fedor@indutny.com>

deps/openssl/asm/x64-elf-gas/bn/x86_64-mont5.s

@@ -14,47 +14,153 @@ bn_mul_mont_gather5:
 .align	16
 .Lmul_enter:
 	movl	%r9d,%r9d
-	movl	8(%rsp),%r10d
+	movd	8(%rsp),%xmm5
+	leaq	.Linc(%rip),%r10
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
+.Lmul_alloca:
 	movq	%rsp,%rax
 	leaq	2(%r9),%r11
 	negq	%r11
-	leaq	(%rsp,%r11,8),%rsp
+	leaq	-264(%rsp,%r11,8),%rsp
 	andq	$-1024,%rsp
 
 	movq	%rax,8(%rsp,%r9,8)
 .Lmul_body:
-	movq	%rdx,%r12
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	.Lmagic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%r12,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	leaq	128(%rdx),%r12
+	movdqa	0(%r10),%xmm0
+	movdqa	16(%r10),%xmm1
+	leaq	24-112(%rsp,%r9,8),%r10
+	andq	$-16,%r10
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+.byte	0x67
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
+.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$78,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 .byte	102,72,15,126,195
 
 	movq	(%r8),%r8
@@ -63,29 +169,14 @@ bn_mul_mont_gather5:
 	xorq	%r14,%r14
 	xorq	%r15,%r15
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	movq	%r8,%rbp
 	mulq	%rbx
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -118,8 +209,6 @@ bn_mul_mont_gather5:
 	cmpq	%r9,%r15
 	jne	.L1st
 
-.byte	102,72,15,126,195
-
 	addq	%rax,%r13
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -139,33 +228,76 @@ bn_mul_mont_gather5:
 	jmp	.Louter
 .align	16
 .Louter:
+	leaq	24+128(%rsp,%r9,8),%rdx
+	andq	$-16,%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$78,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+.byte	102,72,15,126,195
+
 	xorq	%r15,%r15
 	movq	%r8,%rbp
 	movq	(%rsp),%r10
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	mulq	%rbx
 	addq	%rax,%r10
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -201,8 +333,6 @@ bn_mul_mont_gather5:
 	cmpq	%r9,%r15
 	jne	.Linner
 
-.byte	102,72,15,126,195
-
 	addq	%rax,%r13
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -256,6 +386,7 @@ bn_mul_mont_gather5:
 
 	movq	8(%rsp,%r9,8),%rsi
 	movq	$1,%rax
+
 	movq	(%rsi),%r15
 	movq	8(%rsi),%r14
 	movq	16(%rsi),%r13
@@ -271,78 +402,170 @@ bn_mul_mont_gather5:
 bn_mul4x_mont_gather5:
 .Lmul4x_enter:
 	movl	%r9d,%r9d
-	movl	8(%rsp),%r10d
+	movd	8(%rsp),%xmm5
+	leaq	.Linc(%rip),%r10
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
+.Lmul4x_alloca:
 	movq	%rsp,%rax
 	leaq	4(%r9),%r11
 	negq	%r11
-	leaq	(%rsp,%r11,8),%rsp
+	leaq	-256(%rsp,%r11,8),%rsp
 	andq	$-1024,%rsp
 
 	movq	%rax,8(%rsp,%r9,8)
 .Lmul4x_body:
 	movq	%rdi,16(%rsp,%r9,8)
-	movq	%rdx,%r12
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	.Lmagic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%r12,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	leaq	128(%rdx),%r12
+	movdqa	0(%r10),%xmm0
+	movdqa	16(%r10),%xmm1
+	leaq	32-112(%rsp,%r9,8),%r10
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+.byte	0x67,0x67
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+.byte	0x67
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
+.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$78,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 .byte	102,72,15,126,195
+
 	movq	(%r8),%r8
 	movq	(%rsi),%rax
 
 	xorq	%r14,%r14
 	xorq	%r15,%r15
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	movq	%r8,%rbp
 	mulq	%rbx
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -460,8 +683,6 @@ bn_mul4x_mont_gather5:
 	movq	%rdi,-16(%rsp,%r15,8)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
-
 	xorq	%rdi,%rdi
 	addq	%r10,%r13
 	adcq	$0,%rdi
@@ -471,12 +692,64 @@ bn_mul4x_mont_gather5:
 	leaq	1(%r14),%r14
 .align	4
 .Louter4x:
+	leaq	32+128(%rsp,%r9,8),%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$78,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+.byte	102,72,15,126,195
+
 	xorq	%r15,%r15
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
 
 	movq	(%rsp),%r10
 	movq	%r8,%rbp
@@ -485,18 +758,9 @@ bn_mul4x_mont_gather5:
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -628,7 +892,6 @@ bn_mul4x_mont_gather5:
 	movq	%r13,-24(%rsp,%r15,8)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
 	movq	%rdi,-16(%rsp,%r15,8)
 
 	xorq	%rdi,%rdi
@@ -712,6 +975,7 @@ bn_mul4x_mont_gather5:
 	movdqu	%xmm2,16(%rdi,%r14,1)
 	movq	8(%rsp,%r9,8),%rsi
 	movq	$1,%rax
+
 	movq	(%rsi),%r15
 	movq	8(%rsi),%r14
 	movq	16(%rsi),%r13
@@ -744,42 +1008,169 @@ bn_scatter5:
 .type	bn_gather5,@function
 .align	16
 bn_gather5:
-	movq	%rcx,%r11
-	shrq	$3,%rcx
-	andq	$7,%r11
-	notq	%rcx
-	leaq	.Lmagic_masks(%rip),%rax
-	andq	$3,%rcx
-	leaq	96(%rdx,%r11,8),%rdx
-	movq	0(%rax,%rcx,8),%xmm4
-	movq	8(%rax,%rcx,8),%xmm5
-	movq	16(%rax,%rcx,8),%xmm6
-	movq	24(%rax,%rcx,8),%xmm7
+.LSEH_begin_bn_gather5:
+
+.byte	0x4c,0x8d,0x14,0x24
+
+.byte	0x48,0x81,0xec,0x08,0x01,0x00,0x00
+
+	leaq	.Linc(%rip),%rax
+	andq	$-16,%rsp
+
+	movd	%ecx,%xmm5
+	movdqa	0(%rax),%xmm0
+	movdqa	16(%rax),%xmm1
+	leaq	128(%rdx),%r11
+	leaq	128(%rsp),%rax
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-128(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-112(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-96(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-80(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-48(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-16(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,0(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,16(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,48(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,80(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,96(%rax)
+	movdqa	%xmm4,%xmm2
+	movdqa	%xmm3,112(%rax)
 	jmp	.Lgather
-.align	16
-.Lgather:
-	movq	-96(%rdx),%xmm0
-	movq	-32(%rdx),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%rdx),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%rdx),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-	por	%xmm2,%xmm0
-	leaq	256(%rdx),%rdx
-	por	%xmm3,%xmm0
 
+.align	32
+.Lgather:
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r11),%xmm0
+	movdqa	-112(%r11),%xmm1
+	movdqa	-96(%r11),%xmm2
+	pand	-128(%rax),%xmm0
+	movdqa	-80(%r11),%xmm3
+	pand	-112(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r11),%xmm0
+	movdqa	-48(%r11),%xmm1
+	movdqa	-32(%r11),%xmm2
+	pand	-64(%rax),%xmm0
+	movdqa	-16(%r11),%xmm3
+	pand	-48(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r11),%xmm0
+	movdqa	16(%r11),%xmm1
+	movdqa	32(%r11),%xmm2
+	pand	0(%rax),%xmm0
+	movdqa	48(%r11),%xmm3
+	pand	16(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r11),%xmm0
+	movdqa	80(%r11),%xmm1
+	movdqa	96(%r11),%xmm2
+	pand	64(%rax),%xmm0
+	movdqa	112(%r11),%xmm3
+	pand	80(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	leaq	256(%r11),%r11
+	pshufd	$78,%xmm4,%xmm0
+	por	%xmm4,%xmm0
 	movq	%xmm0,(%rdi)
 	leaq	8(%rdi),%rdi
 	subq	$1,%rsi
 	jnz	.Lgather
+
+	leaq	(%r10),%rsp
 	.byte	0xf3,0xc3
 .LSEH_end_bn_gather5:
 .size	bn_gather5,.-bn_gather5
 .align	64
-.Lmagic_masks:
-.long	0,0, 0,0, 0,0, -1,-1
-.long	0,0, 0,0, 0,0,  0,0
+.Linc:
+.long	0,0, 1,1
+.long	2,2, 2,2
 .byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,119,105,116,104,32,115,99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0

deps/openssl/asm/x64-macosx-gas/bn/x86_64-mont5.s

@@ -14,47 +14,153 @@ _bn_mul_mont_gather5:
 .p2align	4
 L$mul_enter:
 	movl	%r9d,%r9d
-	movl	8(%rsp),%r10d
+	movd	8(%rsp),%xmm5
+	leaq	L$inc(%rip),%r10
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
+L$mul_alloca:
 	movq	%rsp,%rax
 	leaq	2(%r9),%r11
 	negq	%r11
-	leaq	(%rsp,%r11,8),%rsp
+	leaq	-264(%rsp,%r11,8),%rsp
 	andq	$-1024,%rsp
 
 	movq	%rax,8(%rsp,%r9,8)
 L$mul_body:
-	movq	%rdx,%r12
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	L$magic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%r12,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	leaq	128(%rdx),%r12
+	movdqa	0(%r10),%xmm0
+	movdqa	16(%r10),%xmm1
+	leaq	24-112(%rsp,%r9,8),%r10
+	andq	$-16,%r10
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+.byte	0x67
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
+.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$78,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 .byte	102,72,15,126,195
 
 	movq	(%r8),%r8
@@ -63,29 +169,14 @@ L$mul_body:
 	xorq	%r14,%r14
 	xorq	%r15,%r15
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	movq	%r8,%rbp
 	mulq	%rbx
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -118,8 +209,6 @@ L$1st_enter:
 	cmpq	%r9,%r15
 	jne	L$1st
 
-.byte	102,72,15,126,195
-
 	addq	%rax,%r13
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -139,33 +228,76 @@ L$1st_enter:
 	jmp	L$outer
 .p2align	4
 L$outer:
+	leaq	24+128(%rsp,%r9,8),%rdx
+	andq	$-16,%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$78,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+.byte	102,72,15,126,195
+
 	xorq	%r15,%r15
 	movq	%r8,%rbp
 	movq	(%rsp),%r10
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	mulq	%rbx
 	addq	%rax,%r10
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -201,8 +333,6 @@ L$inner_enter:
 	cmpq	%r9,%r15
 	jne	L$inner
 
-.byte	102,72,15,126,195
-
 	addq	%rax,%r13
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -256,6 +386,7 @@ L$copy:
 
 	movq	8(%rsp,%r9,8),%rsi
 	movq	$1,%rax
+
 	movq	(%rsi),%r15
 	movq	8(%rsi),%r14
 	movq	16(%rsi),%r13
@@ -271,78 +402,170 @@ L$mul_epilogue:
 bn_mul4x_mont_gather5:
 L$mul4x_enter:
 	movl	%r9d,%r9d
-	movl	8(%rsp),%r10d
+	movd	8(%rsp),%xmm5
+	leaq	L$inc(%rip),%r10
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
 	pushq	%r13
 	pushq	%r14
 	pushq	%r15
+
+L$mul4x_alloca:
 	movq	%rsp,%rax
 	leaq	4(%r9),%r11
 	negq	%r11
-	leaq	(%rsp,%r11,8),%rsp
+	leaq	-256(%rsp,%r11,8),%rsp
 	andq	$-1024,%rsp
 
 	movq	%rax,8(%rsp,%r9,8)
 L$mul4x_body:
 	movq	%rdi,16(%rsp,%r9,8)
-	movq	%rdx,%r12
-	movq	%r10,%r11
-	shrq	$3,%r10
-	andq	$7,%r11
-	notq	%r10
-	leaq	L$magic_masks(%rip),%rax
-	andq	$3,%r10
-	leaq	96(%r12,%r11,8),%r12
-	movq	0(%rax,%r10,8),%xmm4
-	movq	8(%rax,%r10,8),%xmm5
-	movq	16(%rax,%r10,8),%xmm6
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	leaq	128(%rdx),%r12
+	movdqa	0(%r10),%xmm0
+	movdqa	16(%r10),%xmm1
+	leaq	32-112(%rsp,%r9,8),%r10
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+.byte	0x67,0x67
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+.byte	0x67
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,112(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,128(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,144(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,160(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,176(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,192(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,208(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,224(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,240(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,256(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,272(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,288(%r10)
+	movdqa	%xmm4,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,304(%r10)
+
+	paddd	%xmm2,%xmm3
+.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,320(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,336(%r10)
+	pand	64(%r12),%xmm0
+
+	pand	80(%r12),%xmm1
+	pand	96(%r12),%xmm2
+	movdqa	%xmm3,352(%r10)
+	pand	112(%r12),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-128(%r12),%xmm4
+	movdqa	-112(%r12),%xmm5
+	movdqa	-96(%r12),%xmm2
+	pand	112(%r10),%xmm4
+	movdqa	-80(%r12),%xmm3
+	pand	128(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	144(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	160(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	-64(%r12),%xmm4
+	movdqa	-48(%r12),%xmm5
+	movdqa	-32(%r12),%xmm2
+	pand	176(%r10),%xmm4
+	movdqa	-16(%r12),%xmm3
+	pand	192(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	208(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	224(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	movdqa	0(%r12),%xmm4
+	movdqa	16(%r12),%xmm5
+	movdqa	32(%r12),%xmm2
+	pand	240(%r10),%xmm4
+	movdqa	48(%r12),%xmm3
+	pand	256(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	272(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	288(%r10),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+	por	%xmm1,%xmm0
+	pshufd	$78,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 .byte	102,72,15,126,195
+
 	movq	(%r8),%r8
 	movq	(%rsi),%rax
 
 	xorq	%r14,%r14
 	xorq	%r15,%r15
 
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
-
 	movq	%r8,%rbp
 	mulq	%rbx
 	movq	%rax,%r10
 	movq	(%rcx),%rax
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -460,8 +683,6 @@ L$1st4x:
 	movq	%rdi,-16(%rsp,%r15,8)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
-
 	xorq	%rdi,%rdi
 	addq	%r10,%r13
 	adcq	$0,%rdi
@@ -471,12 +692,64 @@ L$1st4x:
 	leaq	1(%r14),%r14
 .p2align	2
 L$outer4x:
+	leaq	32+128(%rsp,%r9,8),%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r12),%xmm0
+	movdqa	-112(%r12),%xmm1
+	movdqa	-96(%r12),%xmm2
+	movdqa	-80(%r12),%xmm3
+	pand	-128(%rdx),%xmm0
+	pand	-112(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r12),%xmm0
+	movdqa	-48(%r12),%xmm1
+	movdqa	-32(%r12),%xmm2
+	movdqa	-16(%r12),%xmm3
+	pand	-64(%rdx),%xmm0
+	pand	-48(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r12),%xmm0
+	movdqa	16(%r12),%xmm1
+	movdqa	32(%r12),%xmm2
+	movdqa	48(%r12),%xmm3
+	pand	0(%rdx),%xmm0
+	pand	16(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r12),%xmm0
+	movdqa	80(%r12),%xmm1
+	movdqa	96(%r12),%xmm2
+	movdqa	112(%r12),%xmm3
+	pand	64(%rdx),%xmm0
+	pand	80(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	pshufd	$78,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	leaq	256(%r12),%r12
+.byte	102,72,15,126,195
+
 	xorq	%r15,%r15
-	movq	-96(%r12),%xmm0
-	movq	-32(%r12),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%r12),%xmm2
-	pand	%xmm5,%xmm1
 
 	movq	(%rsp),%r10
 	movq	%r8,%rbp
@@ -485,18 +758,9 @@ L$outer4x:
 	movq	(%rcx),%rax
 	adcq	$0,%rdx
 
-	movq	96(%r12),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	%r10,%rbp
 	movq	%rdx,%r11
 
-	por	%xmm2,%xmm0
-	leaq	256(%r12),%r12
-	por	%xmm3,%xmm0
-
 	mulq	%rbp
 	addq	%rax,%r10
 	movq	8(%rsi),%rax
@@ -628,7 +892,6 @@ L$inner4x:
 	movq	%r13,-24(%rsp,%r15,8)
 	movq	%rdx,%r13
 
-.byte	102,72,15,126,195
 	movq	%rdi,-16(%rsp,%r15,8)
 
 	xorq	%rdi,%rdi
@@ -712,6 +975,7 @@ L$copy4x:
 	movdqu	%xmm2,16(%rdi,%r14,1)
 	movq	8(%rsp,%r9,8),%rsi
 	movq	$1,%rax
+
 	movq	(%rsi),%r15
 	movq	8(%rsi),%r14
 	movq	16(%rsi),%r13
@@ -744,42 +1008,169 @@ L$scatter_epilogue:
 
 .p2align	4
 _bn_gather5:
-	movq	%rcx,%r11
-	shrq	$3,%rcx
-	andq	$7,%r11
-	notq	%rcx
-	leaq	L$magic_masks(%rip),%rax
-	andq	$3,%rcx
-	leaq	96(%rdx,%r11,8),%rdx
-	movq	0(%rax,%rcx,8),%xmm4
-	movq	8(%rax,%rcx,8),%xmm5
-	movq	16(%rax,%rcx,8),%xmm6
-	movq	24(%rax,%rcx,8),%xmm7
+L$SEH_begin_bn_gather5:
+
+.byte	0x4c,0x8d,0x14,0x24
+
+.byte	0x48,0x81,0xec,0x08,0x01,0x00,0x00
+
+	leaq	L$inc(%rip),%rax
+	andq	$-16,%rsp
+
+	movd	%ecx,%xmm5
+	movdqa	0(%rax),%xmm0
+	movdqa	16(%rax),%xmm1
+	leaq	128(%rdx),%r11
+	leaq	128(%rsp),%rax
+
+	pshufd	$0,%xmm5,%xmm5
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-128(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-112(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-96(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-80(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,-64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,-48(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,-32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,-16(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,0(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,16(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,32(%rax)
+	movdqa	%xmm4,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,48(%rax)
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,64(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,80(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,96(%rax)
+	movdqa	%xmm4,%xmm2
+	movdqa	%xmm3,112(%rax)
 	jmp	L$gather
-.p2align	4
-L$gather:
-	movq	-96(%rdx),%xmm0
-	movq	-32(%rdx),%xmm1
-	pand	%xmm4,%xmm0
-	movq	32(%rdx),%xmm2
-	pand	%xmm5,%xmm1
-	movq	96(%rdx),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-	por	%xmm2,%xmm0
-	leaq	256(%rdx),%rdx
-	por	%xmm3,%xmm0
 
+.p2align	5
+L$gather:
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+	movdqa	-128(%r11),%xmm0
+	movdqa	-112(%r11),%xmm1
+	movdqa	-96(%r11),%xmm2
+	pand	-128(%rax),%xmm0
+	movdqa	-80(%r11),%xmm3
+	pand	-112(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-80(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	-64(%r11),%xmm0
+	movdqa	-48(%r11),%xmm1
+	movdqa	-32(%r11),%xmm2
+	pand	-64(%rax),%xmm0
+	movdqa	-16(%r11),%xmm3
+	pand	-48(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	-32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	-16(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	0(%r11),%xmm0
+	movdqa	16(%r11),%xmm1
+	movdqa	32(%r11),%xmm2
+	pand	0(%rax),%xmm0
+	movdqa	48(%r11),%xmm3
+	pand	16(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	32(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	48(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqa	64(%r11),%xmm0
+	movdqa	80(%r11),%xmm1
+	movdqa	96(%r11),%xmm2
+	pand	64(%rax),%xmm0
+	movdqa	112(%r11),%xmm3
+	pand	80(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	96(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	112(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	por	%xmm5,%xmm4
+	leaq	256(%r11),%r11
+	pshufd	$78,%xmm4,%xmm0
+	por	%xmm4,%xmm0
 	movq	%xmm0,(%rdi)
 	leaq	8(%rdi),%rdi
 	subq	$1,%rsi
 	jnz	L$gather
+
+	leaq	(%r10),%rsp
 	.byte	0xf3,0xc3
 L$SEH_end_bn_gather5:
 
 .p2align	6
-L$magic_masks:
-.long	0,0, 0,0, 0,0, -1,-1
-.long	0,0, 0,0, 0,0,  0,0
+L$inc:
+.long	0,0, 1,1
+.long	2,2, 2,2
 .byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,119,105,116,104,32,115,99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0

deps/openssl/asm/x64-win32-masm/bn/x86_64-mont5.asm

@@ -26,51 +26,153 @@ $L$SEH_begin_bn_mul_mont_gather5::
 ALIGN	16
 $L$mul_enter::
 	mov	r9d,r9d
-	mov	r10d,DWORD PTR[56+rsp]
+	movd	xmm5,DWORD PTR[56+rsp]
+	lea	r10,QWORD PTR[$L$inc]
 	push	rbx
 	push	rbp
 	push	r12
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,QWORD PTR[((-40))+rsp]
-	movaps	XMMWORD PTR[rsp],xmm6
-	movaps	XMMWORD PTR[16+rsp],xmm7
+
 $L$mul_alloca::
 	mov	rax,rsp
 	lea	r11,QWORD PTR[2+r9]
 	neg	r11
-	lea	rsp,QWORD PTR[r11*8+rsp]
+	lea	rsp,QWORD PTR[((-264))+r11*8+rsp]
 	and	rsp,-1024
 
 	mov	QWORD PTR[8+r9*8+rsp],rax
 $L$mul_body::
-	mov	r12,rdx
-	mov	r11,r10
-	shr	r10,3
-	and	r11,7
-	not	r10
-	lea	rax,QWORD PTR[$L$magic_masks]
-	and	r10,3
-	lea	r12,QWORD PTR[96+r11*8+r12]
-	movq	xmm4,QWORD PTR[r10*8+rax]
-	movq	xmm5,QWORD PTR[8+r10*8+rax]
-	movq	xmm6,QWORD PTR[16+r10*8+rax]
-	movq	xmm7,QWORD PTR[24+r10*8+rax]
-
-	movq	xmm0,QWORD PTR[((-96))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
+	lea	r12,QWORD PTR[128+rdx]
+	movdqa	xmm0,XMMWORD PTR[r10]
+	movdqa	xmm1,XMMWORD PTR[16+r10]
+	lea	r10,QWORD PTR[((24-112))+r9*8+rsp]
+	and	r10,-16
+
+	pshufd	xmm5,xmm5,0
+	movdqa	xmm4,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+DB	067h
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[112+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[128+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[144+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[160+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[176+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[192+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[208+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[224+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[240+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[256+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[272+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[288+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[304+r10],xmm0
+
+	paddd	xmm3,xmm2
+DB	067h
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[320+r10],xmm1
+
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[336+r10],xmm2
+	pand	xmm0,XMMWORD PTR[64+r12]
+
+	pand	xmm1,XMMWORD PTR[80+r12]
+	pand	xmm2,XMMWORD PTR[96+r12]
+	movdqa	XMMWORD PTR[352+r10],xmm3
+	pand	xmm3,XMMWORD PTR[112+r12]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD PTR[((-128))+r12]
+	movdqa	xmm5,XMMWORD PTR[((-112))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-96))+r12]
+	pand	xmm4,XMMWORD PTR[112+r10]
+	movdqa	xmm3,XMMWORD PTR[((-80))+r12]
+	pand	xmm5,XMMWORD PTR[128+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD PTR[144+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD PTR[160+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD PTR[((-64))+r12]
+	movdqa	xmm5,XMMWORD PTR[((-48))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-32))+r12]
+	pand	xmm4,XMMWORD PTR[176+r10]
+	movdqa	xmm3,XMMWORD PTR[((-16))+r12]
+	pand	xmm5,XMMWORD PTR[192+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD PTR[208+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD PTR[224+r10]
 	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD PTR[r12]
+	movdqa	xmm5,XMMWORD PTR[16+r12]
+	movdqa	xmm2,XMMWORD PTR[32+r12]
+	pand	xmm4,XMMWORD PTR[240+r10]
+	movdqa	xmm3,XMMWORD PTR[48+r12]
+	pand	xmm5,XMMWORD PTR[256+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD PTR[272+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD PTR[288+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	por	xmm0,xmm1
+	pshufd	xmm1,xmm0,04eh
+	por	xmm0,xmm1
 	lea	r12,QWORD PTR[256+r12]
-	por	xmm0,xmm3
-
 DB	102,72,15,126,195
 
 	mov	r8,QWORD PTR[r8]
@@ -79,29 +181,14 @@ DB	102,72,15,126,195
 	xor	r14,r14
 	xor	r15,r15
 
-	movq	xmm0,QWORD PTR[((-96))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
-	pand	xmm1,xmm5
-
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
 	mov	rax,QWORD PTR[rcx]
 
-	movq	xmm3,QWORD PTR[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-
 	imul	rbp,r10
 	mov	r11,rdx
 
-	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
-	por	xmm0,xmm3
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD PTR[8+rsi]
@@ -134,8 +221,6 @@ $L$1st_enter::
 	cmp	r15,r9
 	jne	$L$1st
 
-DB	102,72,15,126,195
-
 	add	r13,rax
 	mov	rax,QWORD PTR[rsi]
 	adc	rdx,0
@@ -155,33 +240,76 @@ DB	102,72,15,126,195
 	jmp	$L$outer
 ALIGN	16
 $L$outer::
+	lea	rdx,QWORD PTR[((24+128))+r9*8+rsp]
+	and	rdx,-16
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	movdqa	xmm0,XMMWORD PTR[((-128))+r12]
+	movdqa	xmm1,XMMWORD PTR[((-112))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-96))+r12]
+	movdqa	xmm3,XMMWORD PTR[((-80))+r12]
+	pand	xmm0,XMMWORD PTR[((-128))+rdx]
+	pand	xmm1,XMMWORD PTR[((-112))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[((-96))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[((-80))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[((-64))+r12]
+	movdqa	xmm1,XMMWORD PTR[((-48))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-32))+r12]
+	movdqa	xmm3,XMMWORD PTR[((-16))+r12]
+	pand	xmm0,XMMWORD PTR[((-64))+rdx]
+	pand	xmm1,XMMWORD PTR[((-48))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[((-32))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[((-16))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[r12]
+	movdqa	xmm1,XMMWORD PTR[16+r12]
+	movdqa	xmm2,XMMWORD PTR[32+r12]
+	movdqa	xmm3,XMMWORD PTR[48+r12]
+	pand	xmm0,XMMWORD PTR[rdx]
+	pand	xmm1,XMMWORD PTR[16+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[32+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[48+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[64+r12]
+	movdqa	xmm1,XMMWORD PTR[80+r12]
+	movdqa	xmm2,XMMWORD PTR[96+r12]
+	movdqa	xmm3,XMMWORD PTR[112+r12]
+	pand	xmm0,XMMWORD PTR[64+rdx]
+	pand	xmm1,XMMWORD PTR[80+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[96+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[112+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	por	xmm4,xmm5
+	pshufd	xmm0,xmm4,04eh
+	por	xmm0,xmm4
+	lea	r12,QWORD PTR[256+r12]
+DB	102,72,15,126,195
+
 	xor	r15,r15
 	mov	rbp,r8
 	mov	r10,QWORD PTR[rsp]
 
-	movq	xmm0,QWORD PTR[((-96))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
-	pand	xmm1,xmm5
-
 	mul	rbx
 	add	r10,rax
 	mov	rax,QWORD PTR[rcx]
 	adc	rdx,0
 
-	movq	xmm3,QWORD PTR[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-
 	imul	rbp,r10
 	mov	r11,rdx
 
-	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
-	por	xmm0,xmm3
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD PTR[8+rsi]
@@ -217,8 +345,6 @@ $L$inner_enter::
 	cmp	r15,r9
 	jne	$L$inner
 
-DB	102,72,15,126,195
-
 	add	r13,rax
 	mov	rax,QWORD PTR[rsi]
 	adc	rdx,0
@@ -272,9 +398,7 @@ $L$copy::
 
 	mov	rsi,QWORD PTR[8+r9*8+rsp]
 	mov	rax,1
-	movaps	xmm6,XMMWORD PTR[rsi]
-	movaps	xmm7,XMMWORD PTR[16+rsi]
-	lea	rsi,QWORD PTR[40+rsi]
+
 	mov	r15,QWORD PTR[rsi]
 	mov	r14,QWORD PTR[8+rsi]
 	mov	r13,QWORD PTR[16+rsi]
@@ -305,82 +429,170 @@ $L$SEH_begin_bn_mul4x_mont_gather5::
 
 $L$mul4x_enter::
 	mov	r9d,r9d
-	mov	r10d,DWORD PTR[56+rsp]
+	movd	xmm5,DWORD PTR[56+rsp]
+	lea	r10,QWORD PTR[$L$inc]
 	push	rbx
 	push	rbp
 	push	r12
 	push	r13
 	push	r14
 	push	r15
-	lea	rsp,QWORD PTR[((-40))+rsp]
-	movaps	XMMWORD PTR[rsp],xmm6
-	movaps	XMMWORD PTR[16+rsp],xmm7
+
 $L$mul4x_alloca::
 	mov	rax,rsp
 	lea	r11,QWORD PTR[4+r9]
 	neg	r11
-	lea	rsp,QWORD PTR[r11*8+rsp]
+	lea	rsp,QWORD PTR[((-256))+r11*8+rsp]
 	and	rsp,-1024
 
 	mov	QWORD PTR[8+r9*8+rsp],rax
 $L$mul4x_body::
 	mov	QWORD PTR[16+r9*8+rsp],rdi
-	mov	r12,rdx
-	mov	r11,r10
-	shr	r10,3
-	and	r11,7
-	not	r10
-	lea	rax,QWORD PTR[$L$magic_masks]
-	and	r10,3
-	lea	r12,QWORD PTR[96+r11*8+r12]
-	movq	xmm4,QWORD PTR[r10*8+rax]
-	movq	xmm5,QWORD PTR[8+r10*8+rax]
-	movq	xmm6,QWORD PTR[16+r10*8+rax]
-	movq	xmm7,QWORD PTR[24+r10*8+rax]
-
-	movq	xmm0,QWORD PTR[((-96))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
+	lea	r12,QWORD PTR[128+rdx]
+	movdqa	xmm0,XMMWORD PTR[r10]
+	movdqa	xmm1,XMMWORD PTR[16+r10]
+	lea	r10,QWORD PTR[((32-112))+r9*8+rsp]
+
+	pshufd	xmm5,xmm5,0
+	movdqa	xmm4,xmm1
+DB	067h,067h
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+DB	067h
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[112+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[128+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[144+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[160+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[176+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[192+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[208+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[224+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[240+r10],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[256+r10],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[272+r10],xmm2
+	movdqa	xmm2,xmm4
+
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[288+r10],xmm3
+	movdqa	xmm3,xmm4
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[304+r10],xmm0
+
+	paddd	xmm3,xmm2
+DB	067h
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[320+r10],xmm1
+
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[336+r10],xmm2
+	pand	xmm0,XMMWORD PTR[64+r12]
+
+	pand	xmm1,XMMWORD PTR[80+r12]
+	pand	xmm2,XMMWORD PTR[96+r12]
+	movdqa	XMMWORD PTR[352+r10],xmm3
+	pand	xmm3,XMMWORD PTR[112+r12]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD PTR[((-128))+r12]
+	movdqa	xmm5,XMMWORD PTR[((-112))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-96))+r12]
+	pand	xmm4,XMMWORD PTR[112+r10]
+	movdqa	xmm3,XMMWORD PTR[((-80))+r12]
+	pand	xmm5,XMMWORD PTR[128+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD PTR[144+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD PTR[160+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD PTR[((-64))+r12]
+	movdqa	xmm5,XMMWORD PTR[((-48))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-32))+r12]
+	pand	xmm4,XMMWORD PTR[176+r10]
+	movdqa	xmm3,XMMWORD PTR[((-16))+r12]
+	pand	xmm5,XMMWORD PTR[192+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD PTR[208+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD PTR[224+r10]
 	por	xmm0,xmm2
+	por	xmm1,xmm3
+	movdqa	xmm4,XMMWORD PTR[r12]
+	movdqa	xmm5,XMMWORD PTR[16+r12]
+	movdqa	xmm2,XMMWORD PTR[32+r12]
+	pand	xmm4,XMMWORD PTR[240+r10]
+	movdqa	xmm3,XMMWORD PTR[48+r12]
+	pand	xmm5,XMMWORD PTR[256+r10]
+	por	xmm0,xmm4
+	pand	xmm2,XMMWORD PTR[272+r10]
+	por	xmm1,xmm5
+	pand	xmm3,XMMWORD PTR[288+r10]
+	por	xmm0,xmm2
+	por	xmm1,xmm3
+	por	xmm0,xmm1
+	pshufd	xmm1,xmm0,04eh
+	por	xmm0,xmm1
 	lea	r12,QWORD PTR[256+r12]
-	por	xmm0,xmm3
-
 DB	102,72,15,126,195
+
 	mov	r8,QWORD PTR[r8]
 	mov	rax,QWORD PTR[rsi]
 
 	xor	r14,r14
 	xor	r15,r15
 
-	movq	xmm0,QWORD PTR[((-96))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
-	pand	xmm1,xmm5
-
 	mov	rbp,r8
 	mul	rbx
 	mov	r10,rax
 	mov	rax,QWORD PTR[rcx]
 
-	movq	xmm3,QWORD PTR[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-
 	imul	rbp,r10
 	mov	r11,rdx
 
-	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
-	por	xmm0,xmm3
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD PTR[8+rsi]
@@ -498,8 +710,6 @@ $L$1st4x::
 	mov	QWORD PTR[((-16))+r15*8+rsp],rdi
 	mov	r13,rdx
 
-DB	102,72,15,126,195
-
 	xor	rdi,rdi
 	add	r13,r10
 	adc	rdi,0
@@ -509,12 +719,64 @@ DB	102,72,15,126,195
 	lea	r14,QWORD PTR[1+r14]
 ALIGN	4
 $L$outer4x::
+	lea	rdx,QWORD PTR[((32+128))+r9*8+rsp]
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	movdqa	xmm0,XMMWORD PTR[((-128))+r12]
+	movdqa	xmm1,XMMWORD PTR[((-112))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-96))+r12]
+	movdqa	xmm3,XMMWORD PTR[((-80))+r12]
+	pand	xmm0,XMMWORD PTR[((-128))+rdx]
+	pand	xmm1,XMMWORD PTR[((-112))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[((-96))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[((-80))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[((-64))+r12]
+	movdqa	xmm1,XMMWORD PTR[((-48))+r12]
+	movdqa	xmm2,XMMWORD PTR[((-32))+r12]
+	movdqa	xmm3,XMMWORD PTR[((-16))+r12]
+	pand	xmm0,XMMWORD PTR[((-64))+rdx]
+	pand	xmm1,XMMWORD PTR[((-48))+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[((-32))+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[((-16))+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[r12]
+	movdqa	xmm1,XMMWORD PTR[16+r12]
+	movdqa	xmm2,XMMWORD PTR[32+r12]
+	movdqa	xmm3,XMMWORD PTR[48+r12]
+	pand	xmm0,XMMWORD PTR[rdx]
+	pand	xmm1,XMMWORD PTR[16+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[32+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[48+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[64+r12]
+	movdqa	xmm1,XMMWORD PTR[80+r12]
+	movdqa	xmm2,XMMWORD PTR[96+r12]
+	movdqa	xmm3,XMMWORD PTR[112+r12]
+	pand	xmm0,XMMWORD PTR[64+rdx]
+	pand	xmm1,XMMWORD PTR[80+rdx]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[96+rdx]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[112+rdx]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	por	xmm4,xmm5
+	pshufd	xmm0,xmm4,04eh
+	por	xmm0,xmm4
+	lea	r12,QWORD PTR[256+r12]
+DB	102,72,15,126,195
+
 	xor	r15,r15
-	movq	xmm0,QWORD PTR[((-96))+r12]
-	movq	xmm1,QWORD PTR[((-32))+r12]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r12]
-	pand	xmm1,xmm5
 
 	mov	r10,QWORD PTR[rsp]
 	mov	rbp,r8
@@ -523,18 +785,9 @@ $L$outer4x::
 	mov	rax,QWORD PTR[rcx]
 	adc	rdx,0
 
-	movq	xmm3,QWORD PTR[96+r12]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-
 	imul	rbp,r10
 	mov	r11,rdx
 
-	por	xmm0,xmm2
-	lea	r12,QWORD PTR[256+r12]
-	por	xmm0,xmm3
-
 	mul	rbp
 	add	r10,rax
 	mov	rax,QWORD PTR[8+rsi]
@@ -666,7 +919,6 @@ $L$inner4x::
 	mov	QWORD PTR[((-24))+r15*8+rsp],r13
 	mov	r13,rdx
 
-DB	102,72,15,126,195
 	mov	QWORD PTR[((-16))+r15*8+rsp],rdi
 
 	xor	rdi,rdi
@@ -750,9 +1002,7 @@ $L$copy4x::
 	movdqu	XMMWORD PTR[16+r14*1+rdi],xmm2
 	mov	rsi,QWORD PTR[8+r9*8+rsp]
 	mov	rax,1
-	movaps	xmm6,XMMWORD PTR[rsi]
-	movaps	xmm7,XMMWORD PTR[16+rsi]
-	lea	rsi,QWORD PTR[40+rsi]
+
 	mov	r15,QWORD PTR[rsi]
 	mov	r14,QWORD PTR[8+rsi]
 	mov	r13,QWORD PTR[16+rsi]
@@ -790,53 +1040,169 @@ ALIGN	16
 bn_gather5	PROC PUBLIC
 $L$SEH_begin_bn_gather5::
 
-DB	048h,083h,0ech,028h
-
-DB	00fh,029h,034h,024h
-
-DB	00fh,029h,07ch,024h,010h
-
-	mov	r11,r9
-	shr	r9,3
-	and	r11,7
-	not	r9
-	lea	rax,QWORD PTR[$L$magic_masks]
-	and	r9,3
-	lea	r8,QWORD PTR[96+r11*8+r8]
-	movq	xmm4,QWORD PTR[r9*8+rax]
-	movq	xmm5,QWORD PTR[8+r9*8+rax]
-	movq	xmm6,QWORD PTR[16+r9*8+rax]
-	movq	xmm7,QWORD PTR[24+r9*8+rax]
+DB	04ch,08dh,014h,024h
+
+DB	048h,081h,0ech,008h,001h,000h,000h
+
+	lea	rax,QWORD PTR[$L$inc]
+	and	rsp,-16
+
+	movd	xmm5,r9d
+	movdqa	xmm0,XMMWORD PTR[rax]
+	movdqa	xmm1,XMMWORD PTR[16+rax]
+	lea	r11,QWORD PTR[128+r8]
+	lea	rax,QWORD PTR[128+rsp]
+
+	pshufd	xmm5,xmm5,0
+	movdqa	xmm4,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[(-128)+rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[(-112)+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[(-96)+rax],xmm2
+	movdqa	xmm2,xmm4
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[(-80)+rax],xmm3
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[(-64)+rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[(-48)+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[(-32)+rax],xmm2
+	movdqa	xmm2,xmm4
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[(-16)+rax],xmm3
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[16+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[32+rax],xmm2
+	movdqa	xmm2,xmm4
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm5
+	movdqa	XMMWORD PTR[48+rax],xmm3
+	movdqa	xmm3,xmm4
+
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm5
+	movdqa	XMMWORD PTR[64+rax],xmm0
+	movdqa	xmm0,xmm4
+
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm5
+	movdqa	XMMWORD PTR[80+rax],xmm1
+	movdqa	xmm1,xmm4
+
+	paddd	xmm0,xmm3
+	pcmpeqd	xmm3,xmm5
+	movdqa	XMMWORD PTR[96+rax],xmm2
+	movdqa	xmm2,xmm4
+	movdqa	XMMWORD PTR[112+rax],xmm3
 	jmp	$L$gather
-ALIGN	16
-$L$gather::
-	movq	xmm0,QWORD PTR[((-96))+r8]
-	movq	xmm1,QWORD PTR[((-32))+r8]
-	pand	xmm0,xmm4
-	movq	xmm2,QWORD PTR[32+r8]
-	pand	xmm1,xmm5
-	movq	xmm3,QWORD PTR[96+r8]
-	pand	xmm2,xmm6
-	por	xmm0,xmm1
-	pand	xmm3,xmm7
-	por	xmm0,xmm2
-	lea	r8,QWORD PTR[256+r8]
-	por	xmm0,xmm3
 
+ALIGN	32
+$L$gather::
+	pxor	xmm4,xmm4
+	pxor	xmm5,xmm5
+	movdqa	xmm0,XMMWORD PTR[((-128))+r11]
+	movdqa	xmm1,XMMWORD PTR[((-112))+r11]
+	movdqa	xmm2,XMMWORD PTR[((-96))+r11]
+	pand	xmm0,XMMWORD PTR[((-128))+rax]
+	movdqa	xmm3,XMMWORD PTR[((-80))+r11]
+	pand	xmm1,XMMWORD PTR[((-112))+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[((-96))+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[((-80))+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[((-64))+r11]
+	movdqa	xmm1,XMMWORD PTR[((-48))+r11]
+	movdqa	xmm2,XMMWORD PTR[((-32))+r11]
+	pand	xmm0,XMMWORD PTR[((-64))+rax]
+	movdqa	xmm3,XMMWORD PTR[((-16))+r11]
+	pand	xmm1,XMMWORD PTR[((-48))+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[((-32))+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[((-16))+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[r11]
+	movdqa	xmm1,XMMWORD PTR[16+r11]
+	movdqa	xmm2,XMMWORD PTR[32+r11]
+	pand	xmm0,XMMWORD PTR[rax]
+	movdqa	xmm3,XMMWORD PTR[48+r11]
+	pand	xmm1,XMMWORD PTR[16+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[32+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[48+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqa	xmm0,XMMWORD PTR[64+r11]
+	movdqa	xmm1,XMMWORD PTR[80+r11]
+	movdqa	xmm2,XMMWORD PTR[96+r11]
+	pand	xmm0,XMMWORD PTR[64+rax]
+	movdqa	xmm3,XMMWORD PTR[112+r11]
+	pand	xmm1,XMMWORD PTR[80+rax]
+	por	xmm4,xmm0
+	pand	xmm2,XMMWORD PTR[96+rax]
+	por	xmm5,xmm1
+	pand	xmm3,XMMWORD PTR[112+rax]
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	por	xmm4,xmm5
+	lea	r11,QWORD PTR[256+r11]
+	pshufd	xmm0,xmm4,04eh
+	por	xmm0,xmm4
 	movq	QWORD PTR[rcx],xmm0
 	lea	rcx,QWORD PTR[8+rcx]
 	sub	rdx,1
 	jnz	$L$gather
-	movaps	xmm6,XMMWORD PTR[rsp]
-	movaps	xmm7,XMMWORD PTR[16+rsp]
-	lea	rsp,QWORD PTR[40+rsp]
+
+	lea	rsp,QWORD PTR[r10]
 	DB	0F3h,0C3h		;repret
 $L$SEH_end_bn_gather5::
 bn_gather5	ENDP
 ALIGN	64
-$L$magic_masks::
-	DD	0,0,0,0,0,0,-1,-1
-	DD	0,0,0,0,0,0,0,0
+$L$inc::
+	DD	0,0,1,1
+	DD	2,2,2,2
 DB	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105
 DB	112,108,105,99,97,116,105,111,110,32,119,105,116,104,32,115
 DB	99,97,116,116,101,114,47,103,97,116,104,101,114,32,102,111
@@ -869,7 +1235,7 @@ mul_handler	PROC PRIVATE
 	cmp	rbx,r10
 	jb	$L$common_seh_tail
 
-	lea	rax,QWORD PTR[88+rax]
+	lea	rax,QWORD PTR[48+rax]
 
 	mov	r10d,DWORD PTR[4+r11]
 	lea	r10,QWORD PTR[r10*1+rsi]
@@ -886,9 +1252,7 @@ mul_handler	PROC PRIVATE
 	mov	r10,QWORD PTR[192+r8]
 	mov	rax,QWORD PTR[8+r10*8+rax]
 
-	movaps	xmm0,XMMWORD PTR[rax]
-	movaps	xmm1,XMMWORD PTR[16+rax]
-	lea	rax,QWORD PTR[88+rax]
+	lea	rax,QWORD PTR[48+rax]
 
 	mov	rbx,QWORD PTR[((-8))+rax]
 	mov	rbp,QWORD PTR[((-16))+rax]
@@ -902,8 +1266,6 @@ mul_handler	PROC PRIVATE
 	mov	QWORD PTR[224+r8],r13
 	mov	QWORD PTR[232+r8],r14
 	mov	QWORD PTR[240+r8],r15
-	movups	XMMWORD PTR[512+r8],xmm0
-	movups	XMMWORD PTR[528+r8],xmm1
 
 $L$common_seh_tail::
 	mov	rdi,QWORD PTR[8+rax]
@@ -977,12 +1339,10 @@ DB	9,0,0,0
 
 ALIGN	8
 $L$SEH_info_bn_gather5::
-DB	001h,00dh,005h,000h
-DB	00dh,078h,001h,000h
-
-DB	008h,068h,000h,000h
+DB	001h,00bh,003h,00ah
+DB	00bh,001h,021h,000h
 
-DB	004h,042h,000h,000h
+DB	004h,0a3h,000h,000h
 
 ALIGN	8
 

deps/openssl/openssl/CHANGES

@@ -2,6 +2,138 @@
  OpenSSL CHANGES
  _______________
 
+ Changes between 1.0.1r and 1.0.1s [1 Mar 2016]
+
+  * Disable weak ciphers in SSLv3 and up in default builds of OpenSSL.
+    Builds that are not configured with "enable-weak-ssl-ciphers" will not
+    provide any "EXPORT" or "LOW" strength ciphers.
+    [Viktor Dukhovni]
+
+  * Disable SSLv2 default build, default negotiation and weak ciphers.  SSLv2
+    is by default disabled at build-time.  Builds that are not configured with
+    "enable-ssl2" will not support SSLv2.  Even if "enable-ssl2" is used,
+    users who want to negotiate SSLv2 via the version-flexible SSLv23_method()
+    will need to explicitly call either of:
+
+        SSL_CTX_clear_options(ctx, SSL_OP_NO_SSLv2);
+    or
+        SSL_clear_options(ssl, SSL_OP_NO_SSLv2);
+
+    as appropriate.  Even if either of those is used, or the application
+    explicitly uses the version-specific SSLv2_method() or its client and
+    server variants, SSLv2 ciphers vulnerable to exhaustive search key
+    recovery have been removed.  Specifically, the SSLv2 40-bit EXPORT
+    ciphers, and SSLv2 56-bit DES are no longer available.
+    (CVE-2016-0800)
+    [Viktor Dukhovni]
+
+  *) Fix a double-free in DSA code
+
+     A double free bug was discovered when OpenSSL parses malformed DSA private
+     keys and could lead to a DoS attack or memory corruption for applications
+     that receive DSA private keys from untrusted sources.  This scenario is
+     considered rare.
+
+     This issue was reported to OpenSSL by Adam Langley(Google/BoringSSL) using
+     libFuzzer.
+     (CVE-2016-0705)
+     [Stephen Henson]
+
+  *) Disable SRP fake user seed to address a server memory leak.
+
+     Add a new method SRP_VBASE_get1_by_user that handles the seed properly.
+
+     SRP_VBASE_get_by_user had inconsistent memory management behaviour.
+     In order to fix an unavoidable memory leak, SRP_VBASE_get_by_user
+     was changed to ignore the "fake user" SRP seed, even if the seed
+     is configured.
+
+     Users should use SRP_VBASE_get1_by_user instead. Note that in
+     SRP_VBASE_get1_by_user, caller must free the returned value. Note
+     also that even though configuring the SRP seed attempts to hide
+     invalid usernames by continuing the handshake with fake
+     credentials, this behaviour is not constant time and no strong
+     guarantees are made that the handshake is indistinguishable from
+     that of a valid user.
+     (CVE-2016-0798)
+     [Emilia Käsper]
+
+  *) Fix BN_hex2bn/BN_dec2bn NULL pointer deref/heap corruption
+
+     In the BN_hex2bn function the number of hex digits is calculated using an
+     int value |i|. Later |bn_expand| is called with a value of |i * 4|. For
+     large values of |i| this can result in |bn_expand| not allocating any
+     memory because |i * 4| is negative. This can leave the internal BIGNUM data
+     field as NULL leading to a subsequent NULL ptr deref. For very large values
+     of |i|, the calculation |i * 4| could be a positive value smaller than |i|.
+     In this case memory is allocated to the internal BIGNUM data field, but it
+     is insufficiently sized leading to heap corruption. A similar issue exists
+     in BN_dec2bn. This could have security consequences if BN_hex2bn/BN_dec2bn
+     is ever called by user applications with very large untrusted hex/dec data.
+     This is anticipated to be a rare occurrence.
+
+     All OpenSSL internal usage of these functions use data that is not expected
+     to be untrusted, e.g. config file data or application command line
+     arguments. If user developed applications generate config file data based
+     on untrusted data then it is possible that this could also lead to security
+     consequences. This is also anticipated to be rare.
+
+     This issue was reported to OpenSSL by Guido Vranken.
+     (CVE-2016-0797)
+     [Matt Caswell]
+
+  *) Fix memory issues in BIO_*printf functions
+
+     The internal |fmtstr| function used in processing a "%s" format string in
+     the BIO_*printf functions could overflow while calculating the length of a
+     string and cause an OOB read when printing very long strings.
+
+     Additionally the internal |doapr_outch| function can attempt to write to an
+     OOB memory location (at an offset from the NULL pointer) in the event of a
+     memory allocation failure. In 1.0.2 and below this could be caused where
+     the size of a buffer to be allocated is greater than INT_MAX. E.g. this
+     could be in processing a very long "%s" format string. Memory leaks can
+     also occur.
+
+     The first issue may mask the second issue dependent on compiler behaviour.
+     These problems could enable attacks where large amounts of untrusted data
+     is passed to the BIO_*printf functions. If applications use these functions
+     in this way then they could be vulnerable. OpenSSL itself uses these
+     functions when printing out human-readable dumps of ASN.1 data. Therefore
+     applications that print this data could be vulnerable if the data is from
+     untrusted sources. OpenSSL command line applications could also be
+     vulnerable where they print out ASN.1 data, or if untrusted data is passed
+     as command line arguments.
+
+     Libssl is not considered directly vulnerable. Additionally certificates etc
+     received via remote connections via libssl are also unlikely to be able to
+     trigger these issues because of message size limits enforced within libssl.
+
+     This issue was reported to OpenSSL Guido Vranken.
+     (CVE-2016-0799)
+     [Matt Caswell]
+
+  *) Side channel attack on modular exponentiation
+
+     A side-channel attack was found which makes use of cache-bank conflicts on
+     the Intel Sandy-Bridge microarchitecture which could lead to the recovery
+     of RSA keys.  The ability to exploit this issue is limited as it relies on
+     an attacker who has control of code in a thread running on the same
+     hyper-threaded core as the victim thread which is performing decryptions.
+
+     This issue was reported to OpenSSL by Yuval Yarom, The University of
+     Adelaide and NICTA, Daniel Genkin, Technion and Tel Aviv University, and
+     Nadia Heninger, University of Pennsylvania with more information at
+     http://cachebleed.info.
+     (CVE-2016-0702)
+     [Andy Polyakov]
+
+  *) Change the req app to generate a 2048-bit RSA/DSA key by default,
+     if no keysize is specified with default_bits. This fixes an
+     omission in an earlier change that changed all RSA/DSA key generation
+     apps to use 2048 bits by default.
+     [Emilia Käsper]
+
  Changes between 1.0.1q and 1.0.1r [28 Jan 2016]
 
   *) Protection for DH small subgroup attacks
@@ -62,7 +194,7 @@
      [Emilia Käsper]
 
   *) In DSA_generate_parameters_ex, if the provided seed is too short,
-     return an error
+     use a random seed, as already documented.
      [Rich Salz and Ismo Puustinen <ismo.puustinen@intel.com>]
 
  Changes between 1.0.1o and 1.0.1p [9 Jul 2015]

deps/openssl/openssl/Configure

@@ -58,6 +58,10 @@ my $usage="Usage: Configure [no-<cipher> ...] [enable-<cipher> ...] [experimenta
 #		library and will be loaded in run-time by the OpenSSL library.
 # sctp          include SCTP support
 # 386           generate 80386 code
+# enable-weak-ssl-ciphers
+#		Enable EXPORT and LOW SSLv3 ciphers that are disabled by
+#		default.  Note, weak SSLv2 ciphers are unconditionally
+#		disabled.
 # no-sse2	disables IA-32 SSE2 code, above option implies no-sse2
 # no-<cipher>   build without specified algorithm (rsa, idea, rc5, ...)
 # -<xxx> +<xxx> compiler options are passed through 
@@ -724,10 +728,12 @@ my %disabled = ( # "what"         => "comment" [or special keyword "experimental
 		 "md2"            => "default",
 		 "rc5"            => "default",
 		 "rfc3779"	  => "default",
-		 "sctp"       => "default",
+		 "sctp"           => "default",
 		 "shared"         => "default",
+		 "ssl2"           => "default",
 		 "store"	  => "experimental",
 		 "unit-test"	  => "default",
+		 "weak-ssl-ciphers" => "default",
 		 "zlib"           => "default",
 		 "zlib-dynamic"   => "default"
 	       );

deps/openssl/openssl/NEWS

@@ -5,6 +5,19 @@
   This file gives a brief overview of the major changes between each OpenSSL
   release. For more details please read the CHANGES file.
 
+  Major changes between OpenSSL 1.0.1r and OpenSSL 1.0.1s [1 Mar 2016]
+
+      o Disable weak ciphers in SSLv3 and up in default builds of OpenSSL.
+      o Disable SSLv2 default build, default negotiation and weak ciphers
+        (CVE-2016-0800)
+      o Fix a double-free in DSA code (CVE-2016-0705)
+      o Disable SRP fake user seed to address a server memory leak
+        (CVE-2016-0798)
+      o Fix BN_hex2bn/BN_dec2bn NULL pointer deref/heap corruption
+        (CVE-2016-0797)
+      o Fix memory issues in BIO_*printf functions (CVE-2016-0799)
+      o Fix side channel attack on modular exponentiation (CVE-2016-0702)
+
   Major changes between OpenSSL 1.0.1q and OpenSSL 1.0.1r [28 Jan 2016]
 
       o Protection for DH small subgroup attacks

deps/openssl/openssl/README

@@ -1,5 +1,5 @@
 
- OpenSSL 1.0.1r 28 Jan 2016
+ OpenSSL 1.0.1s 1 Mar 2016
 
  Copyright (c) 1998-2015 The OpenSSL Project
  Copyright (c) 1995-1998 Eric A. Young, Tim J. Hudson

deps/openssl/openssl/apps/s_server.c

@@ -416,6 +416,8 @@ typedef struct srpsrvparm_st {
 static int MS_CALLBACK ssl_srp_server_param_cb(SSL *s, int *ad, void *arg)
 {
     srpsrvparm *p = (srpsrvparm *) arg;
+    int ret = SSL3_AL_FATAL;
+
     if (p->login == NULL && p->user == NULL) {
         p->login = SSL_get_srp_username(s);
         BIO_printf(bio_err, "SRP username = \"%s\"\n", p->login);
@@ -424,21 +426,25 @@ static int MS_CALLBACK ssl_srp_server_param_cb(SSL *s, int *ad, void *arg)
 
     if (p->user == NULL) {
         BIO_printf(bio_err, "User %s doesn't exist\n", p->login);
-        return SSL3_AL_FATAL;
+        goto err;
     }
+
     if (SSL_set_srp_server_param
         (s, p->user->N, p->user->g, p->user->s, p->user->v,
          p->user->info) < 0) {
         *ad = SSL_AD_INTERNAL_ERROR;
-        return SSL3_AL_FATAL;
+        goto err;
     }
     BIO_printf(bio_err,
                "SRP parameters set: username = \"%s\" info=\"%s\" \n",
                p->login, p->user->info);
-    /* need to check whether there are memory leaks */
+    ret = SSL_ERROR_NONE;
+
+err:
+    SRP_user_pwd_free(p->user);
     p->user = NULL;
     p->login = NULL;
-    return SSL_ERROR_NONE;
+    return ret;
 }
 
 #endif
@@ -2244,9 +2250,10 @@ static int sv_body(char *hostname, int s, unsigned char *context)
 #ifndef OPENSSL_NO_SRP
                 while (SSL_get_error(con, k) == SSL_ERROR_WANT_X509_LOOKUP) {
                     BIO_printf(bio_s_out, "LOOKUP renego during write\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
                     srp_callback_parm.user =
-                        SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                              srp_callback_parm.login);
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
                     if (srp_callback_parm.user)
                         BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                    srp_callback_parm.user->info);
@@ -2300,9 +2307,10 @@ static int sv_body(char *hostname, int s, unsigned char *context)
 #ifndef OPENSSL_NO_SRP
                 while (SSL_get_error(con, i) == SSL_ERROR_WANT_X509_LOOKUP) {
                     BIO_printf(bio_s_out, "LOOKUP renego during read\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
                     srp_callback_parm.user =
-                        SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                              srp_callback_parm.login);
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
                     if (srp_callback_parm.user)
                         BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                    srp_callback_parm.user->info);
@@ -2387,9 +2395,10 @@ static int init_ssl_connection(SSL *con)
     while (i <= 0 && SSL_get_error(con, i) == SSL_ERROR_WANT_X509_LOOKUP) {
         BIO_printf(bio_s_out, "LOOKUP during accept %s\n",
                    srp_callback_parm.login);
+        SRP_user_pwd_free(srp_callback_parm.user);
         srp_callback_parm.user =
-            SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                  srp_callback_parm.login);
+            SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                   srp_callback_parm.login);
         if (srp_callback_parm.user)
             BIO_printf(bio_s_out, "LOOKUP done %s\n",
                        srp_callback_parm.user->info);
@@ -2616,9 +2625,10 @@ static int www_body(char *hostname, int s, unsigned char *context)
                    && SSL_get_error(con, i) == SSL_ERROR_WANT_X509_LOOKUP) {
                 BIO_printf(bio_s_out, "LOOKUP during accept %s\n",
                            srp_callback_parm.login);
+                SRP_user_pwd_free(srp_callback_parm.user);
                 srp_callback_parm.user =
-                    SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                          srp_callback_parm.login);
+                    SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                           srp_callback_parm.login);
                 if (srp_callback_parm.user)
                     BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                srp_callback_parm.user->info);
@@ -2658,9 +2668,10 @@ static int www_body(char *hostname, int s, unsigned char *context)
                 if (BIO_should_io_special(io)
                     && BIO_get_retry_reason(io) == BIO_RR_SSL_X509_LOOKUP) {
                     BIO_printf(bio_s_out, "LOOKUP renego during read\n");
+                    SRP_user_pwd_free(srp_callback_parm.user);
                     srp_callback_parm.user =
-                        SRP_VBASE_get_by_user(srp_callback_parm.vb,
-                                              srp_callback_parm.login);
+                        SRP_VBASE_get1_by_user(srp_callback_parm.vb,
+                                               srp_callback_parm.login);
                     if (srp_callback_parm.user)
                         BIO_printf(bio_s_out, "LOOKUP done %s\n",
                                    srp_callback_parm.user->info);

deps/openssl/openssl/crypto/bio/b_print.c

@@ -125,16 +125,16 @@
 # define LLONG long
 #endif
 
-static void fmtstr(char **, char **, size_t *, size_t *,
-                   const char *, int, int, int);
-static void fmtint(char **, char **, size_t *, size_t *,
-                   LLONG, int, int, int, int);
-static void fmtfp(char **, char **, size_t *, size_t *,
-                  LDOUBLE, int, int, int);
-static void doapr_outch(char **, char **, size_t *, size_t *, int);
-static void _dopr(char **sbuffer, char **buffer,
-                  size_t *maxlen, size_t *retlen, int *truncated,
-                  const char *format, va_list args);
+static int fmtstr(char **, char **, size_t *, size_t *,
+                  const char *, int, int, int);
+static int fmtint(char **, char **, size_t *, size_t *,
+                  LLONG, int, int, int, int);
+static int fmtfp(char **, char **, size_t *, size_t *,
+                 LDOUBLE, int, int, int);
+static int doapr_outch(char **, char **, size_t *, size_t *, int);
+static int _dopr(char **sbuffer, char **buffer,
+                 size_t *maxlen, size_t *retlen, int *truncated,
+                 const char *format, va_list args);
 
 /* format read states */
 #define DP_S_DEFAULT    0
@@ -165,7 +165,7 @@ static void _dopr(char **sbuffer, char **buffer,
 #define char_to_int(p) (p - '0')
 #define OSSL_MAX(p,q) ((p >= q) ? p : q)
 
-static void
+static int
 _dopr(char **sbuffer,
       char **buffer,
       size_t *maxlen,
@@ -196,7 +196,8 @@ _dopr(char **sbuffer,
             if (ch == '%')
                 state = DP_S_FLAGS;
             else
-                doapr_outch(sbuffer, buffer, &currlen, maxlen, ch);
+                if(!doapr_outch(sbuffer, buffer, &currlen, maxlen, ch))
+                    return 0;
             ch = *format++;
             break;
         case DP_S_FLAGS:
@@ -302,8 +303,9 @@ _dopr(char **sbuffer,
                     value = va_arg(args, int);
                     break;
                 }
-                fmtint(sbuffer, buffer, &currlen, maxlen,
-                       value, 10, min, max, flags);
+                if (!fmtint(sbuffer, buffer, &currlen, maxlen, value, 10, min,
+                            max, flags))
+                    return 0;
                 break;
             case 'X':
                 flags |= DP_F_UP;
@@ -326,17 +328,19 @@ _dopr(char **sbuffer,
                     value = (LLONG) va_arg(args, unsigned int);
                     break;
                 }
-                fmtint(sbuffer, buffer, &currlen, maxlen, value,
-                       ch == 'o' ? 8 : (ch == 'u' ? 10 : 16),
-                       min, max, flags);
+                if (!fmtint(sbuffer, buffer, &currlen, maxlen, value,
+                            ch == 'o' ? 8 : (ch == 'u' ? 10 : 16),
+                            min, max, flags))
+                    return 0;
                 break;
             case 'f':
                 if (cflags == DP_C_LDOUBLE)
                     fvalue = va_arg(args, LDOUBLE);
                 else
                     fvalue = va_arg(args, double);
-                fmtfp(sbuffer, buffer, &currlen, maxlen,
-                      fvalue, min, max, flags);
+                if (!fmtfp(sbuffer, buffer, &currlen, maxlen, fvalue, min, max,
+                           flags))
+                    return 0;
                 break;
             case 'E':
                 flags |= DP_F_UP;
@@ -355,8 +359,9 @@ _dopr(char **sbuffer,
                     fvalue = va_arg(args, double);
                 break;
             case 'c':
-                doapr_outch(sbuffer, buffer, &currlen, maxlen,
-                            va_arg(args, int));
+                if(!doapr_outch(sbuffer, buffer, &currlen, maxlen,
+                            va_arg(args, int)))
+                    return 0;
                 break;
             case 's':
                 strvalue = va_arg(args, char *);
@@ -366,13 +371,15 @@ _dopr(char **sbuffer,
                     else
                         max = *maxlen;
                 }
-                fmtstr(sbuffer, buffer, &currlen, maxlen, strvalue,
-                       flags, min, max);
+                if (!fmtstr(sbuffer, buffer, &currlen, maxlen, strvalue,
+                            flags, min, max))
+                    return 0;
                 break;
             case 'p':
                 value = (long)va_arg(args, void *);
-                fmtint(sbuffer, buffer, &currlen, maxlen,
-                       value, 16, min, max, flags | DP_F_NUM);
+                if (!fmtint(sbuffer, buffer, &currlen, maxlen,
+                            value, 16, min, max, flags | DP_F_NUM))
+                    return 0;
                 break;
             case 'n':          /* XXX */
                 if (cflags == DP_C_SHORT) {
@@ -394,7 +401,8 @@ _dopr(char **sbuffer,
                 }
                 break;
             case '%':
-                doapr_outch(sbuffer, buffer, &currlen, maxlen, ch);
+                if(!doapr_outch(sbuffer, buffer, &currlen, maxlen, ch))
+                    return 0;
                 break;
             case 'w':
                 /* not supported yet, treat as next char */
@@ -418,46 +426,56 @@ _dopr(char **sbuffer,
     *truncated = (currlen > *maxlen - 1);
     if (*truncated)
         currlen = *maxlen - 1;
-    doapr_outch(sbuffer, buffer, &currlen, maxlen, '\0');
+    if(!doapr_outch(sbuffer, buffer, &currlen, maxlen, '\0'))
+        return 0;
     *retlen = currlen - 1;
-    return;
+    return 1;
 }
 
-static void
+static int
 fmtstr(char **sbuffer,
        char **buffer,
        size_t *currlen,
        size_t *maxlen, const char *value, int flags, int min, int max)
 {
-    int padlen, strln;
+    int padlen;
+    size_t strln;
     int cnt = 0;
 
     if (value == 0)
         value = "<NULL>";
-    for (strln = 0; value[strln]; ++strln) ;
+
+    strln = strlen(value);
+    if (strln > INT_MAX)
+        strln = INT_MAX;
+
     padlen = min - strln;
-    if (padlen < 0)
+    if (min < 0 || padlen < 0)
         padlen = 0;
     if (flags & DP_F_MINUS)
         padlen = -padlen;
 
     while ((padlen > 0) && (cnt < max)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         --padlen;
         ++cnt;
     }
     while (*value && (cnt < max)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, *value++);
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, *value++))
+            return 0;
         ++cnt;
     }
     while ((padlen < 0) && (cnt < max)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         ++padlen;
         ++cnt;
     }
+    return 1;
 }
 
-static void
+static int
 fmtint(char **sbuffer,
        char **buffer,
        size_t *currlen,
@@ -517,37 +535,44 @@ fmtint(char **sbuffer,
 
     /* spaces */
     while (spadlen > 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         --spadlen;
     }
 
     /* sign */
     if (signvalue)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue);
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue))
+            return 0;
 
     /* prefix */
     while (*prefix) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, *prefix);
+        if(!doapr_outch(sbuffer, buffer, currlen, maxlen, *prefix))
+            return 0;
         prefix++;
     }
 
     /* zeros */
     if (zpadlen > 0) {
         while (zpadlen > 0) {
-            doapr_outch(sbuffer, buffer, currlen, maxlen, '0');
+            if(!doapr_outch(sbuffer, buffer, currlen, maxlen, '0'))
+                return 0;
             --zpadlen;
         }
     }
     /* digits */
-    while (place > 0)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, convert[--place]);
+    while (place > 0) {
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, convert[--place]))
+            return 0;
+    }
 
     /* left justified spaces */
     while (spadlen < 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         ++spadlen;
     }
-    return;
+    return 1;
 }
 
 static LDOUBLE abs_val(LDOUBLE value)
@@ -578,7 +603,7 @@ static long roundv(LDOUBLE value)
     return intpart;
 }
 
-static void
+static int
 fmtfp(char **sbuffer,
       char **buffer,
       size_t *currlen,
@@ -657,47 +682,61 @@ fmtfp(char **sbuffer,
 
     if ((flags & DP_F_ZERO) && (padlen > 0)) {
         if (signvalue) {
-            doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue);
+            if (!doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue))
+                return 0;
             --padlen;
             signvalue = 0;
         }
         while (padlen > 0) {
-            doapr_outch(sbuffer, buffer, currlen, maxlen, '0');
+            if (!doapr_outch(sbuffer, buffer, currlen, maxlen, '0'))
+                return 0;
             --padlen;
         }
     }
     while (padlen > 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         --padlen;
     }
-    if (signvalue)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue);
+    if (signvalue && !doapr_outch(sbuffer, buffer, currlen, maxlen, signvalue))
+        return 0;
 
-    while (iplace > 0)
-        doapr_outch(sbuffer, buffer, currlen, maxlen, iconvert[--iplace]);
+    while (iplace > 0) {
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, iconvert[--iplace]))
+            return 0;
+    }
 
     /*
      * Decimal point. This should probably use locale to find the correct
      * char to print out.
      */
     if (max > 0 || (flags & DP_F_NUM)) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, '.');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, '.'))
+            return 0;
 
-        while (fplace > 0)
-            doapr_outch(sbuffer, buffer, currlen, maxlen, fconvert[--fplace]);
+        while (fplace > 0) {
+            if(!doapr_outch(sbuffer, buffer, currlen, maxlen,
+                            fconvert[--fplace]))
+                return 0;
+        }
     }
     while (zpadlen > 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, '0');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, '0'))
+            return 0;
         --zpadlen;
     }
 
     while (padlen < 0) {
-        doapr_outch(sbuffer, buffer, currlen, maxlen, ' ');
+        if (!doapr_outch(sbuffer, buffer, currlen, maxlen, ' '))
+            return 0;
         ++padlen;
     }
+    return 1;
 }
 
-static void
+#define BUFFER_INC  1024
+
+static int
 doapr_outch(char **sbuffer,
             char **buffer, size_t *currlen, size_t *maxlen, int c)
 {
@@ -708,24 +747,25 @@ doapr_outch(char **sbuffer,
     assert(*currlen <= *maxlen);
 
     if (buffer && *currlen == *maxlen) {
-        *maxlen += 1024;
+        if (*maxlen > INT_MAX - BUFFER_INC)
+            return 0;
+
+        *maxlen += BUFFER_INC;
         if (*buffer == NULL) {
             *buffer = OPENSSL_malloc(*maxlen);
-            if (!*buffer) {
-                /* Panic! Can't really do anything sensible. Just return */
-                return;
-            }
+            if (*buffer == NULL)
+                return 0;
             if (*currlen > 0) {
                 assert(*sbuffer != NULL);
                 memcpy(*buffer, *sbuffer, *currlen);
             }
             *sbuffer = NULL;
         } else {
-            *buffer = OPENSSL_realloc(*buffer, *maxlen);
-            if (!*buffer) {
-                /* Panic! Can't really do anything sensible. Just return */
-                return;
-            }
+            char *tmpbuf;
+            tmpbuf = OPENSSL_realloc(*buffer, *maxlen);
+            if (tmpbuf == NULL)
+                return 0;
+            *buffer = tmpbuf;
         }
     }
 
@@ -736,7 +776,7 @@ doapr_outch(char **sbuffer,
             (*buffer)[(*currlen)++] = (char)c;
     }
 
-    return;
+    return 1;
 }
 
 /***************************************************************************/
@@ -768,7 +808,11 @@ int BIO_vprintf(BIO *bio, const char *format, va_list args)
 
     dynbuf = NULL;
     CRYPTO_push_info("doapr()");
-    _dopr(&hugebufp, &dynbuf, &hugebufsize, &retlen, &ignored, format, args);
+    if (!_dopr(&hugebufp, &dynbuf, &hugebufsize, &retlen, &ignored, format,
+                args)) {
+        OPENSSL_free(dynbuf);
+        return -1;
+    }
     if (dynbuf) {
         ret = BIO_write(bio, dynbuf, (int)retlen);
         OPENSSL_free(dynbuf);
@@ -803,7 +847,8 @@ int BIO_vsnprintf(char *buf, size_t n, const char *format, va_list args)
     size_t retlen;
     int truncated;
 
-    _dopr(&buf, NULL, &n, &retlen, &truncated, format, args);
+    if(!_dopr(&buf, NULL, &n, &retlen, &truncated, format, args))
+        return -1;
 
     if (truncated)
         /*

deps/openssl/openssl/crypto/bio/bio.h

@@ -478,7 +478,7 @@ struct bio_dgram_sctp_prinfo {
 # define BIO_get_conn_hostname(b)  BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,0)
 # define BIO_get_conn_port(b)      BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,1)
 # define BIO_get_conn_ip(b)               BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,2)
-# define BIO_get_conn_int_port(b) BIO_ctrl(b,BIO_C_GET_CONNECT,3,0,NULL)
+# define BIO_get_conn_int_port(b) BIO_ctrl(b,BIO_C_GET_CONNECT,3,NULL)
 
 # define BIO_set_nbio(b,n)       BIO_ctrl(b,BIO_C_SET_NBIO,(n),NULL)
 

deps/openssl/openssl/crypto/bn/Makefile

@@ -243,7 +243,8 @@ bn_exp.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h
 bn_exp.o: ../../include/openssl/lhash.h ../../include/openssl/opensslconf.h
 bn_exp.o: ../../include/openssl/opensslv.h ../../include/openssl/ossl_typ.h
 bn_exp.o: ../../include/openssl/safestack.h ../../include/openssl/stack.h
-bn_exp.o: ../../include/openssl/symhacks.h ../cryptlib.h bn_exp.c bn_lcl.h
+bn_exp.o: ../../include/openssl/symhacks.h ../constant_time_locl.h
+bn_exp.o: ../cryptlib.h bn_exp.c bn_lcl.h
 bn_exp2.o: ../../e_os.h ../../include/openssl/bio.h ../../include/openssl/bn.h
 bn_exp2.o: ../../include/openssl/buffer.h ../../include/openssl/crypto.h
 bn_exp2.o: ../../include/openssl/e_os2.h ../../include/openssl/err.h

deps/openssl/openssl/crypto/bn/asm/x86_64-mont5.pl

@@ -66,60 +66,113 @@ bn_mul_mont_gather5:
 .align	16
 .Lmul_enter:
 	mov	${num}d,${num}d
-	mov	`($win64?56:8)`(%rsp),%r10d	# load 7th argument
+	movd	`($win64?56:8)`(%rsp),%xmm5	# load 7th argument
+	lea	.Linc(%rip),%r10
 	push	%rbx
 	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
 	push	%r15
-___
-$code.=<<___ if ($win64);
-	lea	-0x28(%rsp),%rsp
-	movaps	%xmm6,(%rsp)
-	movaps	%xmm7,0x10(%rsp)
+
 .Lmul_alloca:
-___
-$code.=<<___;
 	mov	%rsp,%rax
 	lea	2($num),%r11
 	neg	%r11
-	lea	(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+2))
+	lea	-264(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+2)+256+8)
 	and	\$-1024,%rsp		# minimize TLB usage
 
 	mov	%rax,8(%rsp,$num,8)	# tp[num+1]=%rsp
 .Lmul_body:
-	mov	$bp,%r12		# reassign $bp
+	lea	128($bp),%r12		# reassign $bp (+size optimization)
 ___
 		$bp="%r12";
 		$STRIDE=2**5*8;		# 5 is "window size"
 		$N=$STRIDE/4;		# should match cache line size
 $code.=<<___;
-	mov	%r10,%r11
-	shr	\$`log($N/8)/log(2)`,%r10
-	and	\$`$N/8-1`,%r11
-	not	%r10
-	lea	.Lmagic_masks(%rip),%rax
-	and	\$`2**5/($N/8)-1`,%r10	# 5 is "window size"
-	lea	96($bp,%r11,8),$bp	# pointer within 1st cache line
-	movq	0(%rax,%r10,8),%xmm4	# set of masks denoting which
-	movq	8(%rax,%r10,8),%xmm5	# cache line contains element
-	movq	16(%rax,%r10,8),%xmm6	# denoted by 7th argument
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	movdqa	0(%r10),%xmm0		# 00000001000000010000000000000000
+	movdqa	16(%r10),%xmm1		# 00000002000000020000000200000002
+	lea	24-112(%rsp,$num,8),%r10# place the mask after tp[num+3] (+ICache optimization)
+	and	\$-16,%r10
+
+	pshufd	\$0,%xmm5,%xmm5		# broadcast index
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..31 to index and save result to stack
+#
+$code.=<<___;
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0		# compare to 1,0
+	.byte	0x67
+	movdqa	%xmm4,%xmm3
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1		# compare to 3,2
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2		# compare to 5,4
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3		# compare to 7,6
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	movdqa	%xmm4,%xmm3
+___
+}
+$code.=<<___;				# last iteration can be optimized
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+
+	paddd	%xmm2,%xmm3
+	.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	pand	`16*($k+0)-128`($bp),%xmm0	# while it's still in register
+
+	pand	`16*($k+1)-128`($bp),%xmm1
+	pand	`16*($k+2)-128`($bp),%xmm2
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	pand	`16*($k+3)-128`($bp),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm4
+	movdqa	`16*($k+1)-128`($bp),%xmm5
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	pand	`16*($k+0)+112`(%r10),%xmm4
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+1)+112`(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	`16*($k+2)+112`(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	`16*($k+3)+112`(%r10),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+}
+$code.=<<___;
+	por	%xmm1,%xmm0
+	pshufd	\$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	movq	%xmm0,$m0		# m0=bp[0]
 
 	mov	($n0),$n0		# pull n0[0] value
@@ -128,29 +181,14 @@ $code.=<<___;
 	xor	$i,$i			# i=0
 	xor	$j,$j			# j=0
 
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-
 	mov	$n0,$m1
 	mulq	$m0			# ap[0]*bp[0]
 	mov	%rax,$lo0
 	mov	($np),%rax
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$lo0,$m1		# "tp[0]"*n0
 	mov	%rdx,$hi0
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$lo0		# discarded
 	mov	8($ap),%rax
@@ -183,8 +221,6 @@ $code.=<<___;
 	cmp	$num,$j
 	jne	.L1st
 
-	movq	%xmm0,$m0		# bp[1]
-
 	add	%rax,$hi1
 	mov	($ap),%rax		# ap[0]
 	adc	\$0,%rdx
@@ -204,33 +240,46 @@ $code.=<<___;
 	jmp	.Louter
 .align	16
 .Louter:
+	lea	24+128(%rsp,$num,8),%rdx	# where 256-byte mask is (+size optimization)
+	and	\$-16,%rdx
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+___
+for($k=0;$k<$STRIDE/16;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm0
+	movdqa	`16*($k+1)-128`($bp),%xmm1
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+0)-128`(%rdx),%xmm0
+	pand	`16*($k+1)-128`(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	`16*($k+2)-128`(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	`16*($k+3)-128`(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+___
+}
+$code.=<<___;
+	por	%xmm5,%xmm4
+	pshufd	\$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	lea	$STRIDE($bp),$bp
+	movq	%xmm0,$m0		# m0=bp[i]
+
 	xor	$j,$j			# j=0
 	mov	$n0,$m1
 	mov	(%rsp),$lo0
 
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-
 	mulq	$m0			# ap[0]*bp[i]
 	add	%rax,$lo0		# ap[0]*bp[i]+tp[0]
 	mov	($np),%rax
 	adc	\$0,%rdx
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$lo0,$m1		# tp[0]*n0
 	mov	%rdx,$hi0
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$lo0		# discarded
 	mov	8($ap),%rax
@@ -266,8 +315,6 @@ $code.=<<___;
 	cmp	$num,$j
 	jne	.Linner
 
-	movq	%xmm0,$m0		# bp[i+1]
-
 	add	%rax,$hi1
 	mov	($ap),%rax		# ap[0]
 	adc	\$0,%rdx
@@ -321,13 +368,7 @@ $code.=<<___;
 
 	mov	8(%rsp,$num,8),%rsi	# restore %rsp
 	mov	\$1,%rax
-___
-$code.=<<___ if ($win64);
-	movaps	(%rsi),%xmm6
-	movaps	0x10(%rsi),%xmm7
-	lea	0x28(%rsi),%rsi
-___
-$code.=<<___;
+
 	mov	(%rsi),%r15
 	mov	8(%rsi),%r14
 	mov	16(%rsi),%r13
@@ -348,91 +389,130 @@ $code.=<<___;
 bn_mul4x_mont_gather5:
 .Lmul4x_enter:
 	mov	${num}d,${num}d
-	mov	`($win64?56:8)`(%rsp),%r10d	# load 7th argument
+	movd	`($win64?56:8)`(%rsp),%xmm5	# load 7th argument
+	lea	.Linc(%rip),%r10
 	push	%rbx
 	push	%rbp
 	push	%r12
 	push	%r13
 	push	%r14
 	push	%r15
-___
-$code.=<<___ if ($win64);
-	lea	-0x28(%rsp),%rsp
-	movaps	%xmm6,(%rsp)
-	movaps	%xmm7,0x10(%rsp)
+
 .Lmul4x_alloca:
-___
-$code.=<<___;
 	mov	%rsp,%rax
 	lea	4($num),%r11
 	neg	%r11
-	lea	(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+4))
+	lea	-256(%rsp,%r11,8),%rsp	# tp=alloca(8*(num+4)+256)
 	and	\$-1024,%rsp		# minimize TLB usage
 
 	mov	%rax,8(%rsp,$num,8)	# tp[num+1]=%rsp
 .Lmul4x_body:
 	mov	$rp,16(%rsp,$num,8)	# tp[num+2]=$rp
-	mov	%rdx,%r12		# reassign $bp
+	lea	128(%rdx),%r12		# reassign $bp (+size optimization)
 ___
 		$bp="%r12";
 		$STRIDE=2**5*8;		# 5 is "window size"
 		$N=$STRIDE/4;		# should match cache line size
 $code.=<<___;
-	mov	%r10,%r11
-	shr	\$`log($N/8)/log(2)`,%r10
-	and	\$`$N/8-1`,%r11
-	not	%r10
-	lea	.Lmagic_masks(%rip),%rax
-	and	\$`2**5/($N/8)-1`,%r10	# 5 is "window size"
-	lea	96($bp,%r11,8),$bp	# pointer within 1st cache line
-	movq	0(%rax,%r10,8),%xmm4	# set of masks denoting which
-	movq	8(%rax,%r10,8),%xmm5	# cache line contains element
-	movq	16(%rax,%r10,8),%xmm6	# denoted by 7th argument
-	movq	24(%rax,%r10,8),%xmm7
-
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
+	movdqa	0(%r10),%xmm0		# 00000001000000010000000000000000
+	movdqa	16(%r10),%xmm1		# 00000002000000020000000200000002
+	lea	32-112(%rsp,$num,8),%r10# place the mask after tp[num+4] (+ICache optimization)
+
+	pshufd	\$0,%xmm5,%xmm5		# broadcast index
+	movdqa	%xmm1,%xmm4
+	.byte	0x67,0x67
+	movdqa	%xmm1,%xmm2
+___
+########################################################################
+# calculate mask by comparing 0..31 to index and save result to stack
+#
+$code.=<<___;
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0		# compare to 1,0
+	.byte	0x67
+	movdqa	%xmm4,%xmm3
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1		# compare to 3,2
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2		# compare to 5,4
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3		# compare to 7,6
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	movdqa	%xmm4,%xmm2
+
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	movdqa	%xmm4,%xmm3
+___
+}
+$code.=<<___;				# last iteration can be optimized
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1
+	movdqa	%xmm0,`16*($k+0)+112`(%r10)
+
+	paddd	%xmm2,%xmm3
+	.byte	0x67
+	pcmpeqd	%xmm5,%xmm2
+	movdqa	%xmm1,`16*($k+1)+112`(%r10)
+
+	pcmpeqd	%xmm5,%xmm3
+	movdqa	%xmm2,`16*($k+2)+112`(%r10)
+	pand	`16*($k+0)-128`($bp),%xmm0	# while it's still in register
+
+	pand	`16*($k+1)-128`($bp),%xmm1
+	pand	`16*($k+2)-128`($bp),%xmm2
+	movdqa	%xmm3,`16*($k+3)+112`(%r10)
+	pand	`16*($k+3)-128`($bp),%xmm3
+	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+for($k=0;$k<$STRIDE/16-4;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm4
+	movdqa	`16*($k+1)-128`($bp),%xmm5
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	pand	`16*($k+0)+112`(%r10),%xmm4
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+1)+112`(%r10),%xmm5
+	por	%xmm4,%xmm0
+	pand	`16*($k+2)+112`(%r10),%xmm2
+	por	%xmm5,%xmm1
+	pand	`16*($k+3)+112`(%r10),%xmm3
 	por	%xmm2,%xmm0
+	por	%xmm3,%xmm1
+___
+}
+$code.=<<___;
+	por	%xmm1,%xmm0
+	pshufd	\$0x4e,%xmm0,%xmm1
+	por	%xmm1,%xmm0
 	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	movq	%xmm0,$m0		# m0=bp[0]
+
 	mov	($n0),$n0		# pull n0[0] value
 	mov	($ap),%rax
 
 	xor	$i,$i			# i=0
 	xor	$j,$j			# j=0
 
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
-
 	mov	$n0,$m1
 	mulq	$m0			# ap[0]*bp[0]
 	mov	%rax,$A[0]
 	mov	($np),%rax
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$A[0],$m1		# "tp[0]"*n0
 	mov	%rdx,$A[1]
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$A[0]		# discarded
 	mov	8($ap),%rax
@@ -550,8 +630,6 @@ $code.=<<___;
 	mov	$N[1],-16(%rsp,$j,8)	# tp[j-1]
 	mov	%rdx,$N[0]
 
-	movq	%xmm0,$m0		# bp[1]
-
 	xor	$N[1],$N[1]
 	add	$A[0],$N[0]
 	adc	\$0,$N[1]
@@ -561,12 +639,34 @@ $code.=<<___;
 	lea	1($i),$i		# i++
 .align	4
 .Louter4x:
+	lea	32+128(%rsp,$num,8),%rdx	# where 256-byte mask is (+size optimization)
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+___
+for($k=0;$k<$STRIDE/16;$k+=4) {
+$code.=<<___;
+	movdqa	`16*($k+0)-128`($bp),%xmm0
+	movdqa	`16*($k+1)-128`($bp),%xmm1
+	movdqa	`16*($k+2)-128`($bp),%xmm2
+	movdqa	`16*($k+3)-128`($bp),%xmm3
+	pand	`16*($k+0)-128`(%rdx),%xmm0
+	pand	`16*($k+1)-128`(%rdx),%xmm1
+	por	%xmm0,%xmm4
+	pand	`16*($k+2)-128`(%rdx),%xmm2
+	por	%xmm1,%xmm5
+	pand	`16*($k+3)-128`(%rdx),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+___
+}
+$code.=<<___;
+	por	%xmm5,%xmm4
+	pshufd	\$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
+	lea	$STRIDE($bp),$bp
+	movq	%xmm0,$m0		# m0=bp[i]
+
 	xor	$j,$j			# j=0
-	movq	`0*$STRIDE/4-96`($bp),%xmm0
-	movq	`1*$STRIDE/4-96`($bp),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($bp),%xmm2
-	pand	%xmm5,%xmm1
 
 	mov	(%rsp),$A[0]
 	mov	$n0,$m1
@@ -575,18 +675,9 @@ $code.=<<___;
 	mov	($np),%rax
 	adc	\$0,%rdx
 
-	movq	`3*$STRIDE/4-96`($bp),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-
 	imulq	$A[0],$m1		# tp[0]*n0
 	mov	%rdx,$A[1]
 
-	por	%xmm2,%xmm0
-	lea	$STRIDE($bp),$bp
-	por	%xmm3,%xmm0
-
 	mulq	$m1			# np[0]*m1
 	add	%rax,$A[0]		# "$N[0]", discarded
 	mov	8($ap),%rax
@@ -718,7 +809,6 @@ $code.=<<___;
 	mov	$N[0],-24(%rsp,$j,8)	# tp[j-1]
 	mov	%rdx,$N[0]
 
-	movq	%xmm0,$m0		# bp[i+1]
 	mov	$N[1],-16(%rsp,$j,8)	# tp[j-1]
 
 	xor	$N[1],$N[1]
@@ -809,13 +899,7 @@ ___
 $code.=<<___;
 	mov	8(%rsp,$num,8),%rsi	# restore %rsp
 	mov	\$1,%rax
-___
-$code.=<<___ if ($win64);
-	movaps	(%rsi),%xmm6
-	movaps	0x10(%rsi),%xmm7
-	lea	0x28(%rsi),%rsi
-___
-$code.=<<___;
+
 	mov	(%rsi),%r15
 	mov	8(%rsi),%r14
 	mov	16(%rsi),%r13
@@ -830,8 +914,8 @@ ___
 }}}
 
 {
-my ($inp,$num,$tbl,$idx)=$win64?("%rcx","%rdx","%r8", "%r9") : # Win64 order
-				("%rdi","%rsi","%rdx","%rcx"); # Unix order
+my ($inp,$num,$tbl,$idx)=$win64?("%rcx","%rdx","%r8", "%r9d") : # Win64 order
+				("%rdi","%rsi","%rdx","%ecx"); # Unix order
 my $out=$inp;
 my $STRIDE=2**5*8;
 my $N=$STRIDE/4;
@@ -859,53 +943,89 @@ bn_scatter5:
 .type	bn_gather5,\@abi-omnipotent
 .align	16
 bn_gather5:
-___
-$code.=<<___ if ($win64);
-.LSEH_begin_bn_gather5:
+.LSEH_begin_bn_gather5:			# Win64 thing, but harmless in other cases
 	# I can't trust assembler to use specific encoding:-(
-	.byte	0x48,0x83,0xec,0x28		#sub	\$0x28,%rsp
-	.byte	0x0f,0x29,0x34,0x24		#movaps	%xmm6,(%rsp)
-	.byte	0x0f,0x29,0x7c,0x24,0x10	#movdqa	%xmm7,0x10(%rsp)
+	.byte	0x4c,0x8d,0x14,0x24			# lea    (%rsp),%r10
+	.byte	0x48,0x81,0xec,0x08,0x01,0x00,0x00	# sub	$0x108,%rsp
+	lea	.Linc(%rip),%rax
+	and	\$-16,%rsp		# shouldn't be formally required
+
+	movd	$idx,%xmm5
+	movdqa	0(%rax),%xmm0		# 00000001000000010000000000000000
+	movdqa	16(%rax),%xmm1		# 00000002000000020000000200000002
+	lea	128($tbl),%r11		# size optimization
+	lea	128(%rsp),%rax		# size optimization
+
+	pshufd	\$0,%xmm5,%xmm5		# broadcast $idx
+	movdqa	%xmm1,%xmm4
+	movdqa	%xmm1,%xmm2
 ___
+########################################################################
+# calculate mask by comparing 0..31 to $idx and save result to stack
+#
+for($i=0;$i<$STRIDE/16;$i+=4) {
+$code.=<<___;
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm5,%xmm0		# compare to 1,0
+___
+$code.=<<___	if ($i);
+	movdqa	%xmm3,`16*($i-1)-128`(%rax)
+___
+$code.=<<___;
+	movdqa	%xmm4,%xmm3
+
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm5,%xmm1		# compare to 3,2
+	movdqa	%xmm0,`16*($i+0)-128`(%rax)
+	movdqa	%xmm4,%xmm0
+
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm5,%xmm2		# compare to 5,4
+	movdqa	%xmm1,`16*($i+1)-128`(%rax)
+	movdqa	%xmm4,%xmm1
+
+	paddd	%xmm3,%xmm0
+	pcmpeqd	%xmm5,%xmm3		# compare to 7,6
+	movdqa	%xmm2,`16*($i+2)-128`(%rax)
+	movdqa	%xmm4,%xmm2
+___
+}
 $code.=<<___;
-	mov	$idx,%r11
-	shr	\$`log($N/8)/log(2)`,$idx
-	and	\$`$N/8-1`,%r11
-	not	$idx
-	lea	.Lmagic_masks(%rip),%rax
-	and	\$`2**5/($N/8)-1`,$idx	# 5 is "window size"
-	lea	96($tbl,%r11,8),$tbl	# pointer within 1st cache line
-	movq	0(%rax,$idx,8),%xmm4	# set of masks denoting which
-	movq	8(%rax,$idx,8),%xmm5	# cache line contains element
-	movq	16(%rax,$idx,8),%xmm6	# denoted by 7th argument
-	movq	24(%rax,$idx,8),%xmm7
+	movdqa	%xmm3,`16*($i-1)-128`(%rax)
 	jmp	.Lgather
-.align	16
-.Lgather:
-	movq	`0*$STRIDE/4-96`($tbl),%xmm0
-	movq	`1*$STRIDE/4-96`($tbl),%xmm1
-	pand	%xmm4,%xmm0
-	movq	`2*$STRIDE/4-96`($tbl),%xmm2
-	pand	%xmm5,%xmm1
-	movq	`3*$STRIDE/4-96`($tbl),%xmm3
-	pand	%xmm6,%xmm2
-	por	%xmm1,%xmm0
-	pand	%xmm7,%xmm3
-	por	%xmm2,%xmm0
-	lea	$STRIDE($tbl),$tbl
-	por	%xmm3,%xmm0
 
+.align	32
+.Lgather:
+	pxor	%xmm4,%xmm4
+	pxor	%xmm5,%xmm5
+___
+for($i=0;$i<$STRIDE/16;$i+=4) {
+$code.=<<___;
+	movdqa	`16*($i+0)-128`(%r11),%xmm0
+	movdqa	`16*($i+1)-128`(%r11),%xmm1
+	movdqa	`16*($i+2)-128`(%r11),%xmm2
+	pand	`16*($i+0)-128`(%rax),%xmm0
+	movdqa	`16*($i+3)-128`(%r11),%xmm3
+	pand	`16*($i+1)-128`(%rax),%xmm1
+	por	%xmm0,%xmm4
+	pand	`16*($i+2)-128`(%rax),%xmm2
+	por	%xmm1,%xmm5
+	pand	`16*($i+3)-128`(%rax),%xmm3
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+___
+}
+$code.=<<___;
+	por	%xmm5,%xmm4
+	lea	$STRIDE(%r11),%r11
+	pshufd	\$0x4e,%xmm4,%xmm0
+	por	%xmm4,%xmm0
 	movq	%xmm0,($out)		# m0=bp[0]
 	lea	8($out),$out
 	sub	\$1,$num
 	jnz	.Lgather
-___
-$code.=<<___ if ($win64);
-	movaps	(%rsp),%xmm6
-	movaps	0x10(%rsp),%xmm7
-	lea	0x28(%rsp),%rsp
-___
-$code.=<<___;
+
+	lea	(%r10),%rsp
 	ret
 .LSEH_end_bn_gather5:
 .size	bn_gather5,.-bn_gather5
@@ -913,9 +1033,9 @@ ___
 }
 $code.=<<___;
 .align	64
-.Lmagic_masks:
-	.long	0,0, 0,0, 0,0, -1,-1
-	.long	0,0, 0,0, 0,0,  0,0
+.Linc:
+	.long	0,0, 1,1
+	.long	2,2, 2,2
 .asciz	"Montgomery Multiplication with scatter/gather for x86_64, CRYPTOGAMS by <appro\@openssl.org>"
 ___
 
@@ -954,7 +1074,7 @@ mul_handler:
 	cmp	%r10,%rbx		# context->Rip<end of prologue label
 	jb	.Lcommon_seh_tail
 
-	lea	`40+48`(%rax),%rax
+	lea	48(%rax),%rax
 
 	mov	4(%r11),%r10d		# HandlerData[1]
 	lea	(%rsi,%r10),%r10	# end of alloca label
@@ -971,9 +1091,7 @@ mul_handler:
 	mov	192($context),%r10	# pull $num
 	mov	8(%rax,%r10,8),%rax	# pull saved stack pointer
 
-	movaps	(%rax),%xmm0
-	movaps	16(%rax),%xmm1
-	lea	`40+48`(%rax),%rax
+	lea	48(%rax),%rax
 
 	mov	-8(%rax),%rbx
 	mov	-16(%rax),%rbp
@@ -987,8 +1105,6 @@ mul_handler:
 	mov	%r13,224($context)	# restore context->R13
 	mov	%r14,232($context)	# restore context->R14
 	mov	%r15,240($context)	# restore context->R15
-	movups	%xmm0,512($context)	# restore context->Xmm6
-	movups	%xmm1,528($context)	# restore context->Xmm7
 
 .Lcommon_seh_tail:
 	mov	8(%rax),%rdi
@@ -1057,10 +1173,9 @@ mul_handler:
 	.rva	.Lmul4x_alloca,.Lmul4x_body,.Lmul4x_epilogue	# HandlerData[]
 .align	8
 .LSEH_info_bn_gather5:
-        .byte   0x01,0x0d,0x05,0x00
-        .byte   0x0d,0x78,0x01,0x00	#movaps	0x10(rsp),xmm7
-        .byte   0x08,0x68,0x00,0x00	#movaps	(rsp),xmm6
-        .byte   0x04,0x42,0x00,0x00	#sub	rsp,0x28
+	.byte	0x01,0x0b,0x03,0x0a
+	.byte	0x0b,0x01,0x21,0x00	# sub	rsp,0x108
+	.byte	0x04,0xa3,0x00,0x00	# lea	r10,(rsp), set_frame r10
 .align	8
 ___
 }

deps/openssl/openssl/crypto/bn/bn.h

@@ -125,6 +125,7 @@
 #ifndef HEADER_BN_H
 # define HEADER_BN_H
 
+# include <limits.h>
 # include <openssl/e_os2.h>
 # ifndef OPENSSL_NO_FP_API
 #  include <stdio.h>            /* FILE */
@@ -739,8 +740,17 @@ const BIGNUM *BN_get0_nist_prime_521(void);
 
 /* library internal functions */
 
-# define bn_expand(a,bits) ((((((bits+BN_BITS2-1))/BN_BITS2)) <= (a)->dmax)?\
-        (a):bn_expand2((a),(bits+BN_BITS2-1)/BN_BITS2))
+# define bn_expand(a,bits) \
+    ( \
+        bits > (INT_MAX - BN_BITS2 + 1) ? \
+            NULL \
+        : \
+            (((bits+BN_BITS2-1)/BN_BITS2) <= (a)->dmax) ? \
+                (a) \
+            : \
+                bn_expand2((a),(bits+BN_BITS2-1)/BN_BITS2) \
+    )
+
 # define bn_wexpand(a,words) (((words) <= (a)->dmax)?(a):bn_expand2((a),(words)))
 BIGNUM *bn_expand2(BIGNUM *a, int words);
 # ifndef OPENSSL_NO_DEPRECATED

deps/openssl/openssl/crypto/bn/bn_exp.c

@@ -110,6 +110,7 @@
  */
 
 #include "cryptlib.h"
+#include "constant_time_locl.h"
 #include "bn_lcl.h"
 
 #include <stdlib.h>
@@ -546,15 +547,17 @@ int BN_mod_exp_mont(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
 
 static int MOD_EXP_CTIME_COPY_TO_PREBUF(const BIGNUM *b, int top,
                                         unsigned char *buf, int idx,
-                                        int width)
+                                        int window)
 {
-    size_t i, j;
+    int i, j;
+    int width = 1 << window;
+    BN_ULONG *table = (BN_ULONG *)buf;
 
     if (top > b->top)
         top = b->top;           /* this works because 'buf' is explicitly
                                  * zeroed */
-    for (i = 0, j = idx; i < top * sizeof b->d[0]; i++, j += width) {
-        buf[j] = ((unsigned char *)b->d)[i];
+    for (i = 0, j = idx; i < top; i++, j += width) {
+        table[j] = b->d[i];
     }
 
     return 1;
@@ -562,15 +565,51 @@ static int MOD_EXP_CTIME_COPY_TO_PREBUF(const BIGNUM *b, int top,
 
 static int MOD_EXP_CTIME_COPY_FROM_PREBUF(BIGNUM *b, int top,
                                           unsigned char *buf, int idx,
-                                          int width)
+                                          int window)
 {
-    size_t i, j;
+    int i, j;
+    int width = 1 << window;
+    volatile BN_ULONG *table = (volatile BN_ULONG *)buf;
 
     if (bn_wexpand(b, top) == NULL)
         return 0;
 
-    for (i = 0, j = idx; i < top * sizeof b->d[0]; i++, j += width) {
-        ((unsigned char *)b->d)[i] = buf[j];
+    if (window <= 3) {
+        for (i = 0; i < top; i++, table += width) {
+            BN_ULONG acc = 0;
+
+            for (j = 0; j < width; j++) {
+                acc |= table[j] &
+                       ((BN_ULONG)0 - (constant_time_eq_int(j,idx)&1));
+            }
+
+            b->d[i] = acc;
+        }
+    } else {
+        int xstride = 1 << (window - 2);
+        BN_ULONG y0, y1, y2, y3;
+
+        i = idx >> (window - 2);        /* equivalent of idx / xstride */
+        idx &= xstride - 1;             /* equivalent of idx % xstride */
+
+        y0 = (BN_ULONG)0 - (constant_time_eq_int(i,0)&1);
+        y1 = (BN_ULONG)0 - (constant_time_eq_int(i,1)&1);
+        y2 = (BN_ULONG)0 - (constant_time_eq_int(i,2)&1);
+        y3 = (BN_ULONG)0 - (constant_time_eq_int(i,3)&1);
+
+        for (i = 0; i < top; i++, table += width) {
+            BN_ULONG acc = 0;
+
+            for (j = 0; j < xstride; j++) {
+                acc |= ( (table[j + 0 * xstride] & y0) |
+                         (table[j + 1 * xstride] & y1) |
+                         (table[j + 2 * xstride] & y2) |
+                         (table[j + 3 * xstride] & y3) )
+                       & ((BN_ULONG)0 - (constant_time_eq_int(j,idx)&1));
+            }
+
+            b->d[i] = acc;
+        }
     }
 
     b->top = top;
@@ -800,9 +839,9 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
     } else
 #endif
     {
-        if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 0, numPowers))
+        if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 0, window))
             goto err;
-        if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&am, top, powerbuf, 1, numPowers))
+        if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&am, top, powerbuf, 1, window))
             goto err;
 
         /*
@@ -814,15 +853,15 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
         if (window > 1) {
             if (!BN_mod_mul_montgomery(&tmp, &am, &am, mont, ctx))
                 goto err;
-            if (!MOD_EXP_CTIME_COPY_TO_PREBUF
-                (&tmp, top, powerbuf, 2, numPowers))
+            if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 2,
+                                              window))
                 goto err;
             for (i = 3; i < numPowers; i++) {
                 /* Calculate a^i = a^(i-1) * a */
                 if (!BN_mod_mul_montgomery(&tmp, &am, &tmp, mont, ctx))
                     goto err;
-                if (!MOD_EXP_CTIME_COPY_TO_PREBUF
-                    (&tmp, top, powerbuf, i, numPowers))
+                if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, i,
+                                                  window))
                     goto err;
             }
         }
@@ -830,8 +869,8 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
         bits--;
         for (wvalue = 0, i = bits % window; i >= 0; i--, bits--)
             wvalue = (wvalue << 1) + BN_is_bit_set(p, bits);
-        if (!MOD_EXP_CTIME_COPY_FROM_PREBUF
-            (&tmp, top, powerbuf, wvalue, numPowers))
+        if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&tmp, top, powerbuf, wvalue,
+                                            window))
             goto err;
 
         /*
@@ -851,8 +890,8 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
             /*
              * Fetch the appropriate pre-computed value from the pre-buf
              */
-            if (!MOD_EXP_CTIME_COPY_FROM_PREBUF
-                (&am, top, powerbuf, wvalue, numPowers))
+            if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&am, top, powerbuf, wvalue,
+                                                window))
                 goto err;
 
             /* Multiply the result into the intermediate result */

deps/openssl/openssl/crypto/bn/bn_print.c

@@ -58,6 +58,7 @@
 
 #include <stdio.h>
 #include <ctype.h>
+#include <limits.h>
 #include "cryptlib.h"
 #include <openssl/buffer.h>
 #include "bn_lcl.h"
@@ -189,7 +190,11 @@ int BN_hex2bn(BIGNUM **bn, const char *a)
         a++;
     }
 
-    for (i = 0; isxdigit((unsigned char)a[i]); i++) ;
+    for (i = 0; i <= (INT_MAX/4) && isxdigit((unsigned char)a[i]); i++)
+        continue;
+
+    if (i > INT_MAX/4)
+        goto err;
 
     num = i + neg;
     if (bn == NULL)
@@ -204,7 +209,7 @@ int BN_hex2bn(BIGNUM **bn, const char *a)
         BN_zero(ret);
     }
 
-    /* i is the number of hex digests; */
+    /* i is the number of hex digits */
     if (bn_expand(ret, i * 4) == NULL)
         goto err;
 
@@ -260,7 +265,11 @@ int BN_dec2bn(BIGNUM **bn, const char *a)
         a++;
     }
 
-    for (i = 0; isdigit((unsigned char)a[i]); i++) ;
+    for (i = 0; i <= (INT_MAX/4) && isdigit((unsigned char)a[i]); i++)
+        continue;
+
+    if (i > INT_MAX/4)
+        goto err;
 
     num = i + neg;
     if (bn == NULL)
@@ -278,7 +287,7 @@ int BN_dec2bn(BIGNUM **bn, const char *a)
         BN_zero(ret);
     }
 
-    /* i is the number of digests, a bit of an over expand; */
+    /* i is the number of digits, a bit of an over expand */
     if (bn_expand(ret, i * 4) == NULL)
         goto err;
 

deps/openssl/openssl/crypto/bn/bn_recp.c

@@ -65,6 +65,7 @@ void BN_RECP_CTX_init(BN_RECP_CTX *recp)
     BN_init(&(recp->N));
     BN_init(&(recp->Nr));
     recp->num_bits = 0;
+    recp->shift = 0;
     recp->flags = 0;
 }
 

deps/openssl/openssl/crypto/dsa/dsa_ameth.c

@@ -191,6 +191,8 @@ static int dsa_priv_decode(EVP_PKEY *pkey, PKCS8_PRIV_KEY_INFO *p8)
     STACK_OF(ASN1_TYPE) *ndsa = NULL;
     DSA *dsa = NULL;
 
+    int ret = 0;
+
     if (!PKCS8_pkey_get0(NULL, &p, &pklen, &palg, p8))
         return 0;
     X509_ALGOR_get0(NULL, &ptype, &pval, palg);
@@ -262,23 +264,21 @@ static int dsa_priv_decode(EVP_PKEY *pkey, PKCS8_PRIV_KEY_INFO *p8)
     }
 
     EVP_PKEY_assign_DSA(pkey, dsa);
-    BN_CTX_free(ctx);
-    if (ndsa)
-        sk_ASN1_TYPE_pop_free(ndsa, ASN1_TYPE_free);
-    else
-        ASN1_STRING_clear_free(privkey);
 
-    return 1;
+    ret = 1;
+    goto done;
 
  decerr:
     DSAerr(DSA_F_DSA_PRIV_DECODE, EVP_R_DECODE_ERROR);
  dsaerr:
+    DSA_free(dsa);
+ done:
     BN_CTX_free(ctx);
-    if (privkey)
+    if (ndsa)
+        sk_ASN1_TYPE_pop_free(ndsa, ASN1_TYPE_free);
+    else
         ASN1_STRING_clear_free(privkey);
-    sk_ASN1_TYPE_pop_free(ndsa, ASN1_TYPE_free);
-    DSA_free(dsa);
-    return 0;
+    return ret;
 }
 
 static int dsa_priv_encode(PKCS8_PRIV_KEY_INFO *p8, const EVP_PKEY *pkey)

deps/openssl/openssl/crypto/modes/ctr128.c

@@ -67,23 +67,20 @@
 /* increment counter (128-bit int) by 1 */
 static void ctr128_inc(unsigned char *counter)
 {
-    u32 n = 16;
-    u8 c;
+    u32 n = 16, c = 1;
 
     do {
         --n;
-        c = counter[n];
-        ++c;
-        counter[n] = c;
-        if (c)
-            return;
+        c += counter[n];
+        counter[n] = (u8)c;
+        c >>= 8;
     } while (n);
 }
 
 #if !defined(OPENSSL_SMALL_FOOTPRINT)
 static void ctr128_inc_aligned(unsigned char *counter)
 {
-    size_t *data, c, n;
+    size_t *data, c, d, n;
     const union {
         long one;
         char little;
@@ -91,20 +88,19 @@ static void ctr128_inc_aligned(unsigned char *counter)
         1
     };
 
-    if (is_endian.little) {
+    if (is_endian.little || ((size_t)counter % sizeof(size_t)) != 0) {
         ctr128_inc(counter);
         return;
     }
 
     data = (size_t *)counter;
+    c = 1;
     n = 16 / sizeof(size_t);
     do {
         --n;
-        c = data[n];
-        ++c;
-        data[n] = c;
-        if (c)
-            return;
+        d = data[n] += c;
+        /* did addition carry? */
+        c = ((d - c) ^ d) >> (sizeof(size_t) * 8 - 1);
     } while (n);
 }
 #endif
@@ -144,14 +140,14 @@ void CRYPTO_ctr128_encrypt(const unsigned char *in, unsigned char *out,
             }
 
 # if defined(STRICT_ALIGNMENT)
-            if (((size_t)in | (size_t)out | (size_t)ivec) % sizeof(size_t) !=
-                0)
+            if (((size_t)in | (size_t)out | (size_t)ecount_buf)
+                % sizeof(size_t) != 0)
                 break;
 # endif
             while (len >= 16) {
                 (*block) (ivec, ecount_buf, key);
                 ctr128_inc_aligned(ivec);
-                for (; n < 16; n += sizeof(size_t))
+                for (n = 0; n < 16; n += sizeof(size_t))
                     *(size_t *)(out + n) =
                         *(size_t *)(in + n) ^ *(size_t *)(ecount_buf + n);
                 len -= 16;
@@ -189,16 +185,13 @@ void CRYPTO_ctr128_encrypt(const unsigned char *in, unsigned char *out,
 /* increment upper 96 bits of 128-bit counter by 1 */
 static void ctr96_inc(unsigned char *counter)
 {
-    u32 n = 12;
-    u8 c;
+    u32 n = 12, c = 1;
 
     do {
         --n;
-        c = counter[n];
-        ++c;
-        counter[n] = c;
-        if (c)
-            return;
+        c += counter[n];
+        counter[n] = (u8)c;
+        c >>= 8;
     } while (n);
 }
 

deps/openssl/openssl/crypto/opensslv.h

@@ -30,11 +30,11 @@ extern "C" {
  * (Prior to 0.9.5a beta1, a different scheme was used: MMNNFFRBB for
  *  major minor fix final patch/beta)
  */
-# define OPENSSL_VERSION_NUMBER  0x1000112fL
+# define OPENSSL_VERSION_NUMBER  0x1000113fL
 # ifdef OPENSSL_FIPS
-#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1r-fips  28 Jan 2016"
+#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1s-fips  1 Mar 2016"
 # else
-#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1r  28 Jan 2016"
+#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1s  1 Mar 2016"
 # endif
 # define OPENSSL_VERSION_PTEXT   " part of " OPENSSL_VERSION_TEXT
 

deps/openssl/openssl/crypto/perlasm/x86_64-xlate.pl

@@ -121,7 +121,7 @@ my %globals;
 		$self->{sz} = "";
 	    } elsif ($self->{op} =~ /^v/) { # VEX
 		$self->{sz} = "";
-	    } elsif ($self->{op} =~ /movq/ && $line =~ /%xmm/) {
+	    } elsif ($self->{op} =~ /mov[dq]/ && $line =~ /%xmm/) {
 		$self->{sz} = "";
 	    } elsif ($self->{op} =~ /([a-z]{3,})([qlwb])$/) {
 		$self->{op} = $1;

deps/openssl/openssl/crypto/rsa/rsa_sign.c

@@ -84,7 +84,7 @@ int RSA_sign(int type, const unsigned char *m, unsigned int m_len,
         return 0;
     }
 #endif
-    if (rsa->meth->rsa_sign) {
+    if ((rsa->flags & RSA_FLAG_SIGN_VER) && rsa->meth->rsa_sign) {
         return rsa->meth->rsa_sign(type, m, m_len, sigret, siglen, rsa);
     }
     /* Special case: SSL signature, just check the length */
@@ -304,7 +304,7 @@ int RSA_verify(int dtype, const unsigned char *m, unsigned int m_len,
                const unsigned char *sigbuf, unsigned int siglen, RSA *rsa)
 {
 
-    if (rsa->meth->rsa_verify) {
+    if ((rsa->flags & RSA_FLAG_SIGN_VER) && rsa->meth->rsa_verify) {
         return rsa->meth->rsa_verify(dtype, m, m_len, sigbuf, siglen, rsa);
     }
 

deps/openssl/openssl/crypto/srp/srp.h

@@ -82,16 +82,21 @@ typedef struct SRP_gN_cache_st {
 DECLARE_STACK_OF(SRP_gN_cache)
 
 typedef struct SRP_user_pwd_st {
+    /* Owned by us. */
     char *id;
     BIGNUM *s;
     BIGNUM *v;
+    /* Not owned by us. */
     const BIGNUM *g;
     const BIGNUM *N;
+    /* Owned by us. */
     char *info;
 } SRP_user_pwd;
 
 DECLARE_STACK_OF(SRP_user_pwd)
 
+void SRP_user_pwd_free(SRP_user_pwd *user_pwd);
+
 typedef struct SRP_VBASE_st {
     STACK_OF(SRP_user_pwd) *users_pwd;
     STACK_OF(SRP_gN_cache) *gN_cache;
@@ -115,7 +120,12 @@ DECLARE_STACK_OF(SRP_gN)
 SRP_VBASE *SRP_VBASE_new(char *seed_key);
 int SRP_VBASE_free(SRP_VBASE *vb);
 int SRP_VBASE_init(SRP_VBASE *vb, char *verifier_file);
+
+/* This method ignores the configured seed and fails for an unknown user. */
 SRP_user_pwd *SRP_VBASE_get_by_user(SRP_VBASE *vb, char *username);
+/* NOTE: unlike in SRP_VBASE_get_by_user, caller owns the returned pointer.*/
+SRP_user_pwd *SRP_VBASE_get1_by_user(SRP_VBASE *vb, char *username);
+
 char *SRP_create_verifier(const char *user, const char *pass, char **salt,
                           char **verifier, const char *N, const char *g);
 int SRP_create_verifier_BN(const char *user, const char *pass, BIGNUM **salt,

deps/openssl/openssl/crypto/srp/srp_vfy.c

@@ -185,7 +185,7 @@ static char *t_tob64(char *dst, const unsigned char *src, int size)
     return olddst;
 }
 
-static void SRP_user_pwd_free(SRP_user_pwd *user_pwd)
+void SRP_user_pwd_free(SRP_user_pwd *user_pwd)
 {
     if (user_pwd == NULL)
         return;
@@ -247,6 +247,24 @@ static int SRP_user_pwd_set_sv_BN(SRP_user_pwd *vinfo, BIGNUM *s, BIGNUM *v)
     return (vinfo->s != NULL && vinfo->v != NULL);
 }
 
+static SRP_user_pwd *srp_user_pwd_dup(SRP_user_pwd *src)
+{
+    SRP_user_pwd *ret;
+
+    if (src == NULL)
+        return NULL;
+    if ((ret = SRP_user_pwd_new()) == NULL)
+        return NULL;
+
+    SRP_user_pwd_set_gN(ret, src->g, src->N);
+    if (!SRP_user_pwd_set_ids(ret, src->id, src->info)
+        || !SRP_user_pwd_set_sv_BN(ret, BN_dup(src->s), BN_dup(src->v))) {
+            SRP_user_pwd_free(ret);
+            return NULL;
+    }
+    return ret;
+}
+
 SRP_VBASE *SRP_VBASE_new(char *seed_key)
 {
     SRP_VBASE *vb = (SRP_VBASE *)OPENSSL_malloc(sizeof(SRP_VBASE));
@@ -468,21 +486,50 @@ int SRP_VBASE_init(SRP_VBASE *vb, char *verifier_file)
 
 }
 
-SRP_user_pwd *SRP_VBASE_get_by_user(SRP_VBASE *vb, char *username)
+static SRP_user_pwd *find_user(SRP_VBASE *vb, char *username)
 {
     int i;
     SRP_user_pwd *user;
-    unsigned char digv[SHA_DIGEST_LENGTH];
-    unsigned char digs[SHA_DIGEST_LENGTH];
-    EVP_MD_CTX ctxt;
 
     if (vb == NULL)
         return NULL;
+
     for (i = 0; i < sk_SRP_user_pwd_num(vb->users_pwd); i++) {
         user = sk_SRP_user_pwd_value(vb->users_pwd, i);
         if (strcmp(user->id, username) == 0)
             return user;
     }
+
+    return NULL;
+}
+
+/*
+ * This method ignores the configured seed and fails for an unknown user.
+ * Ownership of the returned pointer is not released to the caller.
+ * In other words, caller must not free the result.
+ */
+SRP_user_pwd *SRP_VBASE_get_by_user(SRP_VBASE *vb, char *username)
+{
+    return find_user(vb, username);
+}
+
+/*
+ * Ownership of the returned pointer is released to the caller.
+ * In other words, caller must free the result once done.
+ */
+SRP_user_pwd *SRP_VBASE_get1_by_user(SRP_VBASE *vb, char *username)
+{
+    SRP_user_pwd *user;
+    unsigned char digv[SHA_DIGEST_LENGTH];
+    unsigned char digs[SHA_DIGEST_LENGTH];
+    EVP_MD_CTX ctxt;
+
+    if (vb == NULL)
+        return NULL;
+
+    if ((user = find_user(vb, username)) != NULL)
+        return srp_user_pwd_dup(user);
+
     if ((vb->seed_key == NULL) ||
         (vb->default_g == NULL) || (vb->default_N == NULL))
         return NULL;

deps/openssl/openssl/doc/apps/ciphers.pod

@@ -38,25 +38,21 @@ SSL v2 and for SSL v3/TLS v1.
 
 Like B<-v>, but include cipher suite codes in output (hex format).
 
-=item B<-ssl3>
+=item B<-ssl3>, B<-tls1>
 
-only include SSL v3 ciphers.
+This lists ciphers compatible with any of SSLv3, TLSv1, TLSv1.1 or TLSv1.2.
 
 =item B<-ssl2>
 
-only include SSL v2 ciphers.
-
-=item B<-tls1>
-
-only include TLS v1 ciphers.
+Only include SSLv2 ciphers.
 
 =item B<-h>, B<-?>
 
-print a brief usage message.
+Print a brief usage message.
 
 =item B<cipherlist>
 
-a cipher list to convert to a cipher preference list. If it is not included
+A cipher list to convert to a cipher preference list. If it is not included
 then the default cipher list will be used. The format is described below.
 
 =back
@@ -109,9 +105,10 @@ The following is a list of all permitted cipher strings and their meanings.
 
 =item B<DEFAULT>
 
-the default cipher list. This is determined at compile time and
-is normally B<ALL:!EXPORT:!aNULL:!eNULL:!SSLv2>. This must be the firstcipher string
-specified.
+The default cipher list.
+This is determined at compile time and is normally
+B<ALL:!EXPORT:!aNULL:!eNULL:!SSLv2>.
+When used, this must be the first cipherstring specified.
 
 =item B<COMPLEMENTOFDEFAULT>
 
@@ -139,34 +136,46 @@ than 128 bits, and some cipher suites with 128-bit keys.
 
 =item B<LOW>
 
-"low" encryption cipher suites, currently those using 64 or 56 bit encryption algorithms
-but excluding export cipher suites.
+Low strength encryption cipher suites, currently those using 64 or 56 bit
+encryption algorithms but excluding export cipher suites.
+As of OpenSSL 1.0.1s, these are disabled in default builds.
 
 =item B<EXP>, B<EXPORT>
 
-export encryption algorithms. Including 40 and 56 bits algorithms.
+Export strength encryption algorithms. Including 40 and 56 bits algorithms.
+As of OpenSSL 1.0.1s, these are disabled in default builds.
 
 =item B<EXPORT40>
 
-40 bit export encryption algorithms
+40-bit export encryption algorithms
+As of OpenSSL 1.0.1s, these are disabled in default builds.
 
 =item B<EXPORT56>
 
-56 bit export encryption algorithms. In OpenSSL 0.9.8c and later the set of
+56-bit export encryption algorithms. In OpenSSL 0.9.8c and later the set of
 56 bit export ciphers is empty unless OpenSSL has been explicitly configured
 with support for experimental ciphers.
+As of OpenSSL 1.0.1s, these are disabled in default builds.
 
 =item B<eNULL>, B<NULL>
 
-the "NULL" ciphers that is those offering no encryption. Because these offer no
-encryption at all and are a security risk they are disabled unless explicitly
-included.
+The "NULL" ciphers that is those offering no encryption. Because these offer no
+encryption at all and are a security risk they are not enabled via either the
+B<DEFAULT> or B<ALL> cipher strings.
+Be careful when building cipherlists out of lower-level primitives such as
+B<kRSA> or B<aECDSA> as these do overlap with the B<eNULL> ciphers.
+When in doubt, include B<!eNULL> in your cipherlist.
 
 =item B<aNULL>
 
-the cipher suites offering no authentication. This is currently the anonymous
+The cipher suites offering no authentication. This is currently the anonymous
 DH algorithms and anonymous ECDH algorithms. These cipher suites are vulnerable
 to a "man in the middle" attack and so their use is normally discouraged.
+These are excluded from the B<DEFAULT> ciphers, but included in the B<ALL>
+ciphers.
+Be careful when building cipherlists out of lower-level primitives such as
+B<kDHE> or B<AES> as these do overlap with the B<aNULL> ciphers.
+When in doubt, include B<!aNULL> in your cipherlist.
 
 =item B<kRSA>, B<RSA>
 
@@ -572,11 +581,11 @@ Note: these ciphers can also be used in SSL v3.
 =head2 Deprecated SSL v2.0 cipher suites.
 
  SSL_CK_RC4_128_WITH_MD5                 RC4-MD5
- SSL_CK_RC4_128_EXPORT40_WITH_MD5        EXP-RC4-MD5
- SSL_CK_RC2_128_CBC_WITH_MD5             RC2-MD5
- SSL_CK_RC2_128_CBC_EXPORT40_WITH_MD5    EXP-RC2-MD5
+ SSL_CK_RC4_128_EXPORT40_WITH_MD5        Not implemented.
+ SSL_CK_RC2_128_CBC_WITH_MD5             RC2-CBC-MD5
+ SSL_CK_RC2_128_CBC_EXPORT40_WITH_MD5    Not implemented.
  SSL_CK_IDEA_128_CBC_WITH_MD5            IDEA-CBC-MD5
- SSL_CK_DES_64_CBC_WITH_MD5              DES-CBC-MD5
+ SSL_CK_DES_64_CBC_WITH_MD5              Not implemented.
  SSL_CK_DES_192_EDE3_CBC_WITH_MD5        DES-CBC3-MD5
 
 =head1 NOTES

deps/openssl/openssl/doc/apps/s_client.pod

@@ -197,16 +197,11 @@ Use the PSK key B<key> when using a PSK cipher suite. The key is
 given as a hexadecimal number without leading 0x, for example -psk
 1a2b3c4d.
 
-=item B<-ssl2>, B<-ssl3>, B<-tls1>, B<-no_ssl2>, B<-no_ssl3>, B<-no_tls1>
+=item B<-ssl2>, B<-ssl3>, B<-tls1>, B<-tls1_1>, B<-tls1_2>, B<-no_ssl2>, B<-no_ssl3>, B<-no_tls1>, B<-no_tls1_1>, B<-no_tls1_2>
 
-these options disable the use of certain SSL or TLS protocols. By default
-the initial handshake uses a method which should be compatible with all
-servers and permit them to use SSL v3, SSL v2 or TLS as appropriate.
-
-Unfortunately there are a lot of ancient and broken servers in use which
-cannot handle this technique and will fail to connect. Some servers only
-work if TLS is turned off with the B<-no_tls> option others will only
-support SSL v2 and may need the B<-ssl2> option.
+These options require or disable the use of the specified SSL or TLS protocols.
+By default the initial handshake uses a I<version-flexible> method which will
+negotiate the highest mutually supported protocol version.
 
 =item B<-bugs>
 

deps/openssl/openssl/doc/apps/s_server.pod

@@ -221,11 +221,11 @@ Use the PSK key B<key> when using a PSK cipher suite. The key is
 given as a hexadecimal number without leading 0x, for example -psk
 1a2b3c4d.
 
-=item B<-ssl2>, B<-ssl3>, B<-tls1>, B<-no_ssl2>, B<-no_ssl3>, B<-no_tls1>
+=item B<-ssl2>, B<-ssl3>, B<-tls1>, B<-tls1_1>, B<-tls1_2>, B<-no_ssl2>, B<-no_ssl3>, B<-no_tls1>, B<-no_tls1_1>, B<-no_tls1_2>
 
-these options disable the use of certain SSL or TLS protocols. By default
-the initial handshake uses a method which should be compatible with all
-servers and permit them to use SSL v3, SSL v2 or TLS as appropriate.
+These options require or disable the use of the specified SSL or TLS protocols.
+By default the initial handshake uses a I<version-flexible> method which will
+negotiate the highest mutually supported protocol version.
 
 =item B<-bugs>
 

deps/openssl/openssl/doc/ssl/SSL_CTX_new.pod

@@ -2,13 +2,47 @@
 
 =head1 NAME
 
-SSL_CTX_new - create a new SSL_CTX object as framework for TLS/SSL enabled functions
+SSL_CTX_new,
+SSLv23_method, SSLv23_server_method, SSLv23_client_method,
+TLSv1_2_method, TLSv1_2_server_method, TLSv1_2_client_method,
+TLSv1_1_method, TLSv1_1_server_method, TLSv1_1_client_method,
+TLSv1_method, TLSv1_server_method, TLSv1_client_method,
+SSLv3_method, SSLv3_server_method, SSLv3_client_method,
+SSLv2_method, SSLv2_server_method, SSLv2_client_method,
+DTLSv1_method, DTLSv1_server_method, DTLSv1_client_method -
+create a new SSL_CTX object as framework for TLS/SSL enabled functions
 
 =head1 SYNOPSIS
 
  #include <openssl/ssl.h>
 
  SSL_CTX *SSL_CTX_new(const SSL_METHOD *method);
+ const SSL_METHOD *SSLv23_method(void);
+ const SSL_METHOD *SSLv23_server_method(void);
+ const SSL_METHOD *SSLv23_client_method(void);
+ const SSL_METHOD *TLSv1_2_method(void);
+ const SSL_METHOD *TLSv1_2_server_method(void);
+ const SSL_METHOD *TLSv1_2_client_method(void);
+ const SSL_METHOD *TLSv1_1_method(void);
+ const SSL_METHOD *TLSv1_1_server_method(void);
+ const SSL_METHOD *TLSv1_1_client_method(void);
+ const SSL_METHOD *TLSv1_method(void);
+ const SSL_METHOD *TLSv1_server_method(void);
+ const SSL_METHOD *TLSv1_client_method(void);
+ #ifndef OPENSSL_NO_SSL3_METHOD
+ const SSL_METHOD *SSLv3_method(void);
+ const SSL_METHOD *SSLv3_server_method(void);
+ const SSL_METHOD *SSLv3_client_method(void);
+ #endif
+ #ifndef OPENSSL_NO_SSL2
+ const SSL_METHOD *SSLv2_method(void);
+ const SSL_METHOD *SSLv2_server_method(void);
+ const SSL_METHOD *SSLv2_client_method(void);
+ #endif
+
+ const SSL_METHOD *DTLSv1_method(void);
+ const SSL_METHOD *DTLSv1_server_method(void);
+ const SSL_METHOD *DTLSv1_client_method(void);
 
 =head1 DESCRIPTION
 
@@ -23,65 +57,80 @@ client only type. B<method> can be of the following types:
 
 =over 4
 
-=item SSLv2_method(void), SSLv2_server_method(void), SSLv2_client_method(void)
+=item SSLv23_method(), SSLv23_server_method(), SSLv23_client_method()
+
+These are the general-purpose I<version-flexible> SSL/TLS methods.
+The actual protocol version used will be negotiated to the highest version
+mutually supported by the client and the server.
+The supported protocols are SSLv2, SSLv3, TLSv1, TLSv1.1 and TLSv1.2.
+Most applications should use these method, and avoid the version specific
+methods described below.
+
+The list of protocols available can be further limited using the
+B<SSL_OP_NO_SSLv2>, B<SSL_OP_NO_SSLv3>, B<SSL_OP_NO_TLSv1>,
+B<SSL_OP_NO_TLSv1_1> and B<SSL_OP_NO_TLSv1_2> options of the
+L<SSL_CTX_set_options(3)> or L<SSL_set_options(3)> functions.
+Clients should avoid creating "holes" in the set of protocols they support,
+when disabling a protocol, make sure that you also disable either all previous
+or all subsequent protocol versions.
+In clients, when a protocol version is disabled without disabling I<all>
+previous protocol versions, the effect is to also disable all subsequent
+protocol versions.
+
+The SSLv2 and SSLv3 protocols are deprecated and should generally not be used.
+Applications should typically use L<SSL_CTX_set_options(3)> in combination with
+the B<SSL_OP_NO_SSLv3> flag to disable negotiation of SSLv3 via the above
+I<version-flexible> SSL/TLS methods.
+The B<SSL_OP_NO_SSLv2> option is set by default, and would need to be cleared
+via L<SSL_CTX_clear_options(3)> in order to enable negotiation of SSLv2.
+
+=item TLSv1_2_method(), TLSv1_2_server_method(), TLSv1_2_client_method()
 
-A TLS/SSL connection established with these methods will only understand
-the SSLv2 protocol. A client will send out SSLv2 client hello messages
-and will also indicate that it only understand SSLv2. A server will only
-understand SSLv2 client hello messages.
+A TLS/SSL connection established with these methods will only understand the
+TLSv1.2 protocol.  A client will send out TLSv1.2 client hello messages and
+will also indicate that it only understand TLSv1.2.  A server will only
+understand TLSv1.2 client hello messages.
 
-=item SSLv3_method(void), SSLv3_server_method(void), SSLv3_client_method(void)
+=item TLSv1_1_method(), TLSv1_1_server_method(), TLSv1_1_client_method()
 
 A TLS/SSL connection established with these methods will only understand the
-SSLv3 protocol. A client will send out SSLv3 client hello messages
-and will indicate that it only understands SSLv3. A server will only understand
-SSLv3 client hello messages. This especially means, that it will
-not understand SSLv2 client hello messages which are widely used for
-compatibility reasons, see SSLv23_*_method().
+TLSv1.1 protocol.  A client will send out TLSv1.1 client hello messages and
+will also indicate that it only understand TLSv1.1.  A server will only
+understand TLSv1.1 client hello messages.
 
-=item TLSv1_method(void), TLSv1_server_method(void), TLSv1_client_method(void)
+=item TLSv1_method(), TLSv1_server_method(), TLSv1_client_method()
 
 A TLS/SSL connection established with these methods will only understand the
-TLSv1 protocol. A client will send out TLSv1 client hello messages
-and will indicate that it only understands TLSv1. A server will only understand
-TLSv1 client hello messages. This especially means, that it will
-not understand SSLv2 client hello messages which are widely used for
-compatibility reasons, see SSLv23_*_method(). It will also not understand
-SSLv3 client hello messages.
-
-=item SSLv23_method(void), SSLv23_server_method(void), SSLv23_client_method(void)
-
-A TLS/SSL connection established with these methods may understand the SSLv2,
-SSLv3, TLSv1, TLSv1.1 and TLSv1.2 protocols.
-
-If the cipher list does not contain any SSLv2 ciphersuites (the default
-cipher list does not) or extensions are required (for example server name)
-a client will send out TLSv1 client hello messages including extensions and
-will indicate that it also understands TLSv1.1, TLSv1.2 and permits a
-fallback to SSLv3. A server will support SSLv3, TLSv1, TLSv1.1 and TLSv1.2
-protocols. This is the best choice when compatibility is a concern.
-
-If any SSLv2 ciphersuites are included in the cipher list and no extensions
-are required then SSLv2 compatible client hellos will be used by clients and
-SSLv2 will be accepted by servers. This is B<not> recommended due to the
-insecurity of SSLv2 and the limited nature of the SSLv2 client hello
-prohibiting the use of extensions.
+TLSv1 protocol.  A client will send out TLSv1 client hello messages and will
+indicate that it only understands TLSv1.  A server will only understand TLSv1
+client hello messages.
 
-=back
+=item SSLv3_method(), SSLv3_server_method(), SSLv3_client_method()
 
-The list of protocols available can later be limited using the SSL_OP_NO_SSLv2,
-SSL_OP_NO_SSLv3, SSL_OP_NO_TLSv1, SSL_OP_NO_TLSv1_1 and SSL_OP_NO_TLSv1_2
-options of the SSL_CTX_set_options() or SSL_set_options() functions.
-Using these options it is possible to choose e.g. SSLv23_server_method() and
-be able to negotiate with all possible clients, but to only allow newer
-protocols like TLSv1, TLSv1.1 or TLS v1.2.
+A TLS/SSL connection established with these methods will only understand the
+SSLv3 protocol.  A client will send out SSLv3 client hello messages and will
+indicate that it only understands SSLv3.  A server will only understand SSLv3
+client hello messages.  The SSLv3 protocol is deprecated and should not be
+used.
 
-Applications which never want to support SSLv2 (even is the cipher string
-is configured to use SSLv2 ciphersuites) can set SSL_OP_NO_SSLv2.
+=item SSLv2_method(), SSLv2_server_method(), SSLv2_client_method()
+
+A TLS/SSL connection established with these methods will only understand the
+SSLv2 protocol.  A client will send out SSLv2 client hello messages and will
+also indicate that it only understand SSLv2.  A server will only understand
+SSLv2 client hello messages.  The SSLv2 protocol offers little to no security
+and should not be used.
+As of OpenSSL 1.0.1s, EXPORT ciphers and 56-bit DES are no longer available
+with SSLv2.
+
+=item DTLSv1_method(), DTLSv1_server_method(), DTLSv1_client_method()
+
+These are the version-specific methods for DTLSv1.
+
+=back
 
-SSL_CTX_new() initializes the list of ciphers, the session cache setting,
-the callbacks, the keys and certificates and the options to its default
-values.
+SSL_CTX_new() initializes the list of ciphers, the session cache setting, the
+callbacks, the keys and certificates and the options to its default values.
 
 =head1 RETURN VALUES
 
@@ -91,8 +140,8 @@ The following return values can occur:
 
 =item NULL
 
-The creation of a new SSL_CTX object failed. Check the error stack to
-find out the reason.
+The creation of a new SSL_CTX object failed. Check the error stack to find out
+the reason.
 
 =item Pointer to an SSL_CTX object
 
@@ -102,6 +151,7 @@ The return value points to an allocated SSL_CTX object.
 
 =head1 SEE ALSO
 
+L<SSL_CTX_set_options(3)>, L<SSL_CTX_clear_options(3)>, L<SSL_set_options(3)>,
 L<SSL_CTX_free(3)|SSL_CTX_free(3)>, L<SSL_accept(3)|SSL_accept(3)>,
 L<ssl(3)|ssl(3)>,  L<SSL_set_connect_state(3)|SSL_set_connect_state(3)>
 

deps/openssl/openssl/doc/ssl/SSL_CTX_set_options.pod

@@ -189,15 +189,25 @@ browser has a cert, it will crash/hang.  Works for 3.x and 4.xbeta
 =item SSL_OP_NO_SSLv2
 
 Do not use the SSLv2 protocol.
+As of OpenSSL 1.0.1s the B<SSL_OP_NO_SSLv2> option is set by default.
 
 =item SSL_OP_NO_SSLv3
 
 Do not use the SSLv3 protocol.
+It is recommended that applications should set this option.
 
 =item SSL_OP_NO_TLSv1
 
 Do not use the TLSv1 protocol.
 
+=item SSL_OP_NO_TLSv1_1
+
+Do not use the TLSv1.1 protocol.
+
+=item SSL_OP_NO_TLSv1_2
+
+Do not use the TLSv1.2 protocol.
+
 =item SSL_OP_NO_SESSION_RESUMPTION_ON_RENEGOTIATION
 
 When performing renegotiation as a server, always start a new session

deps/openssl/openssl/doc/ssl/ssl.pod

@@ -130,41 +130,86 @@ protocol methods defined in B<SSL_METHOD> structures.
 
 =over 4
 
-=item const SSL_METHOD *B<SSLv2_client_method>(void);
+=item const SSL_METHOD *B<SSLv23_method>(void);
 
-Constructor for the SSLv2 SSL_METHOD structure for a dedicated client.
+Constructor for the I<version-flexible> SSL_METHOD structure for
+clients, servers or both.
+See L<SSL_CTX_new(3)> for details.
 
-=item const SSL_METHOD *B<SSLv2_server_method>(void);
+=item const SSL_METHOD *B<SSLv23_client_method>(void);
 
-Constructor for the SSLv2 SSL_METHOD structure for a dedicated server.
+Constructor for the I<version-flexible> SSL_METHOD structure for
+clients.
 
-=item const SSL_METHOD *B<SSLv2_method>(void);
+=item const SSL_METHOD *B<SSLv23_client_method>(void);
 
-Constructor for the SSLv2 SSL_METHOD structure for combined client and server.
+Constructor for the I<version-flexible> SSL_METHOD structure for
+servers.
 
-=item const SSL_METHOD *B<SSLv3_client_method>(void);
+=item const SSL_METHOD *B<TLSv1_2_method>(void);
 
-Constructor for the SSLv3 SSL_METHOD structure for a dedicated client.
+Constructor for the TLSv1.2 SSL_METHOD structure for clients, servers
+or both.
 
-=item const SSL_METHOD *B<SSLv3_server_method>(void);
+=item const SSL_METHOD *B<TLSv1_2_client_method>(void);
 
-Constructor for the SSLv3 SSL_METHOD structure for a dedicated server.
+Constructor for the TLSv1.2 SSL_METHOD structure for clients.
 
-=item const SSL_METHOD *B<SSLv3_method>(void);
+=item const SSL_METHOD *B<TLSv1_2_server_method>(void);
+
+Constructor for the TLSv1.2 SSL_METHOD structure for servers.
+
+=item const SSL_METHOD *B<TLSv1_1_method>(void);
 
-Constructor for the SSLv3 SSL_METHOD structure for combined client and server.
+Constructor for the TLSv1.1 SSL_METHOD structure for clients, servers
+or both.
+
+=item const SSL_METHOD *B<TLSv1_1_client_method>(void);
+
+Constructor for the TLSv1.1 SSL_METHOD structure for clients.
+
+=item const SSL_METHOD *B<TLSv1_1_server_method>(void);
+
+Constructor for the TLSv1.1 SSL_METHOD structure for servers.
+
+=item const SSL_METHOD *B<TLSv1_method>(void);
+
+Constructor for the TLSv1 SSL_METHOD structure for clients, servers
+or both.
 
 =item const SSL_METHOD *B<TLSv1_client_method>(void);
 
-Constructor for the TLSv1 SSL_METHOD structure for a dedicated client.
+Constructor for the TLSv1 SSL_METHOD structure for clients.
 
 =item const SSL_METHOD *B<TLSv1_server_method>(void);
 
-Constructor for the TLSv1 SSL_METHOD structure for a dedicated server.
+Constructor for the TLSv1 SSL_METHOD structure for servers.
 
-=item const SSL_METHOD *B<TLSv1_method>(void);
+=item const SSL_METHOD *B<SSLv3_method>(void);
+
+Constructor for the SSLv3 SSL_METHOD structure for clients, servers
+or both.
+
+=item const SSL_METHOD *B<SSLv3_client_method>(void);
+
+Constructor for the SSLv3 SSL_METHOD structure for clients.
+
+=item const SSL_METHOD *B<SSLv3_server_method>(void);
+
+Constructor for the SSLv3 SSL_METHOD structure for servers.
+
+=item const SSL_METHOD *B<SSLv2_method>(void);
+
+Constructor for the SSLv2 SSL_METHOD structure for clients, servers
+or both.
+
+=item const SSL_METHOD *B<SSLv2_client_method>(void);
+
+Constructor for the SSLv2 SSL_METHOD structure for clients.
+
+=item const SSL_METHOD *B<SSLv2_server_method>(void);
 
-Constructor for the TLSv1 SSL_METHOD structure for combined client and server.
+Constructor for the SSLv2 SSL_METHOD structure for servers.
 
 =back
 

deps/openssl/openssl/include/openssl/bio.h

@@ -478,7 +478,7 @@ struct bio_dgram_sctp_prinfo {
 # define BIO_get_conn_hostname(b)  BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,0)
 # define BIO_get_conn_port(b)      BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,1)
 # define BIO_get_conn_ip(b)               BIO_ptr_ctrl(b,BIO_C_GET_CONNECT,2)
-# define BIO_get_conn_int_port(b) BIO_ctrl(b,BIO_C_GET_CONNECT,3,0,NULL)
+# define BIO_get_conn_int_port(b) BIO_ctrl(b,BIO_C_GET_CONNECT,3,NULL)
 
 # define BIO_set_nbio(b,n)       BIO_ctrl(b,BIO_C_SET_NBIO,(n),NULL)
 

deps/openssl/openssl/include/openssl/bn.h

@@ -125,6 +125,7 @@
 #ifndef HEADER_BN_H
 # define HEADER_BN_H
 
+# include <limits.h>
 # include <openssl/e_os2.h>
 # ifndef OPENSSL_NO_FP_API
 #  include <stdio.h>            /* FILE */
@@ -739,8 +740,17 @@ const BIGNUM *BN_get0_nist_prime_521(void);
 
 /* library internal functions */
 
-# define bn_expand(a,bits) ((((((bits+BN_BITS2-1))/BN_BITS2)) <= (a)->dmax)?\
-        (a):bn_expand2((a),(bits+BN_BITS2-1)/BN_BITS2))
+# define bn_expand(a,bits) \
+    ( \
+        bits > (INT_MAX - BN_BITS2 + 1) ? \
+            NULL \
+        : \
+            (((bits+BN_BITS2-1)/BN_BITS2) <= (a)->dmax) ? \
+                (a) \
+            : \
+                bn_expand2((a),(bits+BN_BITS2-1)/BN_BITS2) \
+    )
+
 # define bn_wexpand(a,words) (((words) <= (a)->dmax)?(a):bn_expand2((a),(words)))
 BIGNUM *bn_expand2(BIGNUM *a, int words);
 # ifndef OPENSSL_NO_DEPRECATED

deps/openssl/openssl/include/openssl/opensslv.h

@@ -30,11 +30,11 @@ extern "C" {
  * (Prior to 0.9.5a beta1, a different scheme was used: MMNNFFRBB for
  *  major minor fix final patch/beta)
  */
-# define OPENSSL_VERSION_NUMBER  0x1000112fL
+# define OPENSSL_VERSION_NUMBER  0x1000113fL
 # ifdef OPENSSL_FIPS
-#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1r-fips  28 Jan 2016"
+#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1s-fips  1 Mar 2016"
 # else
-#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1r  28 Jan 2016"
+#  define OPENSSL_VERSION_TEXT    "OpenSSL 1.0.1s  1 Mar 2016"
 # endif
 # define OPENSSL_VERSION_PTEXT   " part of " OPENSSL_VERSION_TEXT
 

deps/openssl/openssl/include/openssl/srp.h

@@ -82,16 +82,21 @@ typedef struct SRP_gN_cache_st {
 DECLARE_STACK_OF(SRP_gN_cache)
 
 typedef struct SRP_user_pwd_st {
+    /* Owned by us. */
     char *id;
     BIGNUM *s;
     BIGNUM *v;
+    /* Not owned by us. */
     const BIGNUM *g;
     const BIGNUM *N;
+    /* Owned by us. */
     char *info;
 } SRP_user_pwd;
 
 DECLARE_STACK_OF(SRP_user_pwd)
 
+void SRP_user_pwd_free(SRP_user_pwd *user_pwd);
+
 typedef struct SRP_VBASE_st {
     STACK_OF(SRP_user_pwd) *users_pwd;
     STACK_OF(SRP_gN_cache) *gN_cache;
@@ -115,7 +120,12 @@ DECLARE_STACK_OF(SRP_gN)
 SRP_VBASE *SRP_VBASE_new(char *seed_key);
 int SRP_VBASE_free(SRP_VBASE *vb);
 int SRP_VBASE_init(SRP_VBASE *vb, char *verifier_file);
+
+/* This method ignores the configured seed and fails for an unknown user. */
 SRP_user_pwd *SRP_VBASE_get_by_user(SRP_VBASE *vb, char *username);
+/* NOTE: unlike in SRP_VBASE_get_by_user, caller owns the returned pointer.*/
+SRP_user_pwd *SRP_VBASE_get1_by_user(SRP_VBASE *vb, char *username);
+
 char *SRP_create_verifier(const char *user, const char *pass, char **salt,
                           char **verifier, const char *N, const char *g);
 int SRP_create_verifier_BN(const char *user, const char *pass, BIGNUM **salt,

deps/openssl/openssl/ms/uplink-x86.pl

@@ -14,11 +14,11 @@ require "uplink-common.pl";
 for ($i=1;$i<=$N;$i++) {
 &function_begin_B("_\$lazy${i}");
 	&lea	("eax",&DWP(&label("OPENSSL_UplinkTable")));
-	&push	("eax");
 	&push	($i);
+	&push	("eax");
 	&call	(&label("OPENSSL_Uplink"));
-	&add	("esp",8);
 	&pop	("eax");
+	&add	("esp",4);
 	&jmp_ptr(&DWP(4*$i,"eax"));
 &function_end_B("_\$lazy${i}");
 }

deps/openssl/openssl/openssl.spec

@@ -7,7 +7,7 @@ Release: 1
 Summary: Secure Sockets Layer and cryptography libraries and tools
 Name: openssl
 #Version: %{libmaj}.%{libmin}.%{librel}
-Version: 1.0.1r
+Version: 1.0.1s
 Source0: ftp://ftp.openssl.org/source/%{name}-%{version}.tar.gz
 License: OpenSSL
 Group: System Environment/Libraries

deps/openssl/openssl/ssl/Makefile

@@ -420,14 +420,14 @@ s2_clnt.o: ../include/openssl/obj_mac.h ../include/openssl/objects.h
 s2_clnt.o: ../include/openssl/opensslconf.h ../include/openssl/opensslv.h
 s2_clnt.o: ../include/openssl/ossl_typ.h ../include/openssl/pem.h
 s2_clnt.o: ../include/openssl/pem2.h ../include/openssl/pkcs7.h
-s2_clnt.o: ../include/openssl/pqueue.h ../include/openssl/rand.h
-s2_clnt.o: ../include/openssl/rsa.h ../include/openssl/safestack.h
-s2_clnt.o: ../include/openssl/sha.h ../include/openssl/srtp.h
-s2_clnt.o: ../include/openssl/ssl.h ../include/openssl/ssl2.h
-s2_clnt.o: ../include/openssl/ssl23.h ../include/openssl/ssl3.h
-s2_clnt.o: ../include/openssl/stack.h ../include/openssl/symhacks.h
-s2_clnt.o: ../include/openssl/tls1.h ../include/openssl/x509.h
-s2_clnt.o: ../include/openssl/x509_vfy.h s2_clnt.c ssl_locl.h
+s2_clnt.o: ../include/openssl/pqueue.h ../include/openssl/rsa.h
+s2_clnt.o: ../include/openssl/safestack.h ../include/openssl/sha.h
+s2_clnt.o: ../include/openssl/srtp.h ../include/openssl/ssl.h
+s2_clnt.o: ../include/openssl/ssl2.h ../include/openssl/ssl23.h
+s2_clnt.o: ../include/openssl/ssl3.h ../include/openssl/stack.h
+s2_clnt.o: ../include/openssl/symhacks.h ../include/openssl/tls1.h
+s2_clnt.o: ../include/openssl/x509.h ../include/openssl/x509_vfy.h s2_clnt.c
+s2_clnt.o: ssl_locl.h
 s2_enc.o: ../e_os.h ../include/openssl/asn1.h ../include/openssl/bio.h
 s2_enc.o: ../include/openssl/buffer.h ../include/openssl/comp.h
 s2_enc.o: ../include/openssl/crypto.h ../include/openssl/dsa.h
@@ -456,18 +456,18 @@ s2_lib.o: ../include/openssl/ec.h ../include/openssl/ecdh.h
 s2_lib.o: ../include/openssl/ecdsa.h ../include/openssl/err.h
 s2_lib.o: ../include/openssl/evp.h ../include/openssl/hmac.h
 s2_lib.o: ../include/openssl/kssl.h ../include/openssl/lhash.h
-s2_lib.o: ../include/openssl/md5.h ../include/openssl/obj_mac.h
-s2_lib.o: ../include/openssl/objects.h ../include/openssl/opensslconf.h
-s2_lib.o: ../include/openssl/opensslv.h ../include/openssl/ossl_typ.h
-s2_lib.o: ../include/openssl/pem.h ../include/openssl/pem2.h
-s2_lib.o: ../include/openssl/pkcs7.h ../include/openssl/pqueue.h
-s2_lib.o: ../include/openssl/rsa.h ../include/openssl/safestack.h
-s2_lib.o: ../include/openssl/sha.h ../include/openssl/srtp.h
-s2_lib.o: ../include/openssl/ssl.h ../include/openssl/ssl2.h
-s2_lib.o: ../include/openssl/ssl23.h ../include/openssl/ssl3.h
-s2_lib.o: ../include/openssl/stack.h ../include/openssl/symhacks.h
-s2_lib.o: ../include/openssl/tls1.h ../include/openssl/x509.h
-s2_lib.o: ../include/openssl/x509_vfy.h s2_lib.c ssl_locl.h
+s2_lib.o: ../include/openssl/obj_mac.h ../include/openssl/objects.h
+s2_lib.o: ../include/openssl/opensslconf.h ../include/openssl/opensslv.h
+s2_lib.o: ../include/openssl/ossl_typ.h ../include/openssl/pem.h
+s2_lib.o: ../include/openssl/pem2.h ../include/openssl/pkcs7.h
+s2_lib.o: ../include/openssl/pqueue.h ../include/openssl/rsa.h
+s2_lib.o: ../include/openssl/safestack.h ../include/openssl/sha.h
+s2_lib.o: ../include/openssl/srtp.h ../include/openssl/ssl.h
+s2_lib.o: ../include/openssl/ssl2.h ../include/openssl/ssl23.h
+s2_lib.o: ../include/openssl/ssl3.h ../include/openssl/stack.h
+s2_lib.o: ../include/openssl/symhacks.h ../include/openssl/tls1.h
+s2_lib.o: ../include/openssl/x509.h ../include/openssl/x509_vfy.h s2_lib.c
+s2_lib.o: ssl_locl.h
 s2_meth.o: ../e_os.h ../include/openssl/asn1.h ../include/openssl/bio.h
 s2_meth.o: ../include/openssl/buffer.h ../include/openssl/comp.h
 s2_meth.o: ../include/openssl/crypto.h ../include/openssl/dsa.h
@@ -508,20 +508,19 @@ s2_pkt.o: ../include/openssl/ssl3.h ../include/openssl/stack.h
 s2_pkt.o: ../include/openssl/symhacks.h ../include/openssl/tls1.h
 s2_pkt.o: ../include/openssl/x509.h ../include/openssl/x509_vfy.h s2_pkt.c
 s2_pkt.o: ssl_locl.h
-s2_srvr.o: ../crypto/constant_time_locl.h ../e_os.h ../include/openssl/asn1.h
-s2_srvr.o: ../include/openssl/bio.h ../include/openssl/buffer.h
-s2_srvr.o: ../include/openssl/comp.h ../include/openssl/crypto.h
-s2_srvr.o: ../include/openssl/dsa.h ../include/openssl/dtls1.h
-s2_srvr.o: ../include/openssl/e_os2.h ../include/openssl/ec.h
-s2_srvr.o: ../include/openssl/ecdh.h ../include/openssl/ecdsa.h
-s2_srvr.o: ../include/openssl/err.h ../include/openssl/evp.h
-s2_srvr.o: ../include/openssl/hmac.h ../include/openssl/kssl.h
-s2_srvr.o: ../include/openssl/lhash.h ../include/openssl/obj_mac.h
-s2_srvr.o: ../include/openssl/objects.h ../include/openssl/opensslconf.h
-s2_srvr.o: ../include/openssl/opensslv.h ../include/openssl/ossl_typ.h
-s2_srvr.o: ../include/openssl/pem.h ../include/openssl/pem2.h
-s2_srvr.o: ../include/openssl/pkcs7.h ../include/openssl/pqueue.h
-s2_srvr.o: ../include/openssl/rand.h ../include/openssl/rsa.h
+s2_srvr.o: ../e_os.h ../include/openssl/asn1.h ../include/openssl/bio.h
+s2_srvr.o: ../include/openssl/buffer.h ../include/openssl/comp.h
+s2_srvr.o: ../include/openssl/crypto.h ../include/openssl/dsa.h
+s2_srvr.o: ../include/openssl/dtls1.h ../include/openssl/e_os2.h
+s2_srvr.o: ../include/openssl/ec.h ../include/openssl/ecdh.h
+s2_srvr.o: ../include/openssl/ecdsa.h ../include/openssl/err.h
+s2_srvr.o: ../include/openssl/evp.h ../include/openssl/hmac.h
+s2_srvr.o: ../include/openssl/kssl.h ../include/openssl/lhash.h
+s2_srvr.o: ../include/openssl/obj_mac.h ../include/openssl/objects.h
+s2_srvr.o: ../include/openssl/opensslconf.h ../include/openssl/opensslv.h
+s2_srvr.o: ../include/openssl/ossl_typ.h ../include/openssl/pem.h
+s2_srvr.o: ../include/openssl/pem2.h ../include/openssl/pkcs7.h
+s2_srvr.o: ../include/openssl/pqueue.h ../include/openssl/rsa.h
 s2_srvr.o: ../include/openssl/safestack.h ../include/openssl/sha.h
 s2_srvr.o: ../include/openssl/srtp.h ../include/openssl/ssl.h
 s2_srvr.o: ../include/openssl/ssl2.h ../include/openssl/ssl23.h

deps/openssl/openssl/ssl/s2_lib.c

@@ -156,6 +156,7 @@ OPENSSL_GLOBAL const SSL_CIPHER ssl2_ciphers[] = {
      128,
      },
 
+# if 0
 /* RC4_128_EXPORT40_WITH_MD5 */
     {
      1,
@@ -171,6 +172,7 @@ OPENSSL_GLOBAL const SSL_CIPHER ssl2_ciphers[] = {
      40,
      128,
      },
+# endif
 
 /* RC2_128_CBC_WITH_MD5 */
     {
@@ -188,6 +190,7 @@ OPENSSL_GLOBAL const SSL_CIPHER ssl2_ciphers[] = {
      128,
      },
 
+# if 0
 /* RC2_128_CBC_EXPORT40_WITH_MD5 */
     {
      1,
@@ -203,6 +206,7 @@ OPENSSL_GLOBAL const SSL_CIPHER ssl2_ciphers[] = {
      40,
      128,
      },
+# endif
 
 # ifndef OPENSSL_NO_IDEA
 /* IDEA_128_CBC_WITH_MD5 */
@@ -222,6 +226,7 @@ OPENSSL_GLOBAL const SSL_CIPHER ssl2_ciphers[] = {
      },
 # endif
 
+# if 0
 /* DES_64_CBC_WITH_MD5 */
     {
      1,
@@ -237,6 +242,7 @@ OPENSSL_GLOBAL const SSL_CIPHER ssl2_ciphers[] = {
      56,
      56,
      },
+# endif
 
 /* DES_192_EDE3_CBC_WITH_MD5 */
     {

deps/openssl/openssl/ssl/s3_lib.c

@@ -203,6 +203,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 03 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_RSA_RC4_40_MD5,
@@ -217,6 +218,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+#endif
 
 /* Cipher 04 */
     {
@@ -251,6 +253,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 06 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_RSA_RC2_40_MD5,
@@ -265,6 +268,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+#endif
 
 /* Cipher 07 */
 #ifndef OPENSSL_NO_IDEA
@@ -285,6 +289,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
 #endif
 
 /* Cipher 08 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_RSA_DES_40_CBC_SHA,
@@ -299,8 +304,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+#endif
 
 /* Cipher 09 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_RSA_DES_64_CBC_SHA,
@@ -315,6 +322,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+#endif
 
 /* Cipher 0A */
     {
@@ -334,6 +342,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
 
 /* The DH ciphers */
 /* Cipher 0B */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      0,
      SSL3_TXT_DH_DSS_DES_40_CBC_SHA,
@@ -348,8 +357,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+#endif
 
 /* Cipher 0C */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      0,                         /* not implemented (non-ephemeral DH) */
      SSL3_TXT_DH_DSS_DES_64_CBC_SHA,
@@ -364,6 +375,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+#endif
 
 /* Cipher 0D */
     {
@@ -382,6 +394,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 0E */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      0,                         /* not implemented (non-ephemeral DH) */
      SSL3_TXT_DH_RSA_DES_40_CBC_SHA,
@@ -396,8 +409,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+#endif
 
 /* Cipher 0F */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      0,                         /* not implemented (non-ephemeral DH) */
      SSL3_TXT_DH_RSA_DES_64_CBC_SHA,
@@ -412,6 +427,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+#endif
 
 /* Cipher 10 */
     {
@@ -431,6 +447,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
 
 /* The Ephemeral DH ciphers */
 /* Cipher 11 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_EDH_DSS_DES_40_CBC_SHA,
@@ -445,8 +462,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+#endif
 
 /* Cipher 12 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_EDH_DSS_DES_64_CBC_SHA,
@@ -461,6 +480,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+#endif
 
 /* Cipher 13 */
     {
@@ -479,6 +499,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 14 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_EDH_RSA_DES_40_CBC_SHA,
@@ -493,8 +514,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+#endif
 
 /* Cipher 15 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_EDH_RSA_DES_64_CBC_SHA,
@@ -509,6 +532,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+#endif
 
 /* Cipher 16 */
     {
@@ -527,6 +551,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 17 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_ADH_RC4_40_MD5,
@@ -541,6 +566,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+#endif
 
 /* Cipher 18 */
     {
@@ -559,6 +585,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 19 */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_ADH_DES_40_CBC_SHA,
@@ -573,8 +600,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+#endif
 
 /* Cipher 1A */
+#ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_ADH_DES_64_CBC_SHA,
@@ -589,6 +618,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+#endif
 
 /* Cipher 1B */
     {
@@ -660,6 +690,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
 #ifndef OPENSSL_NO_KRB5
 /* The Kerberos ciphers*/
 /* Cipher 1E */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_DES_64_CBC_SHA,
@@ -674,6 +705,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+# endif
 
 /* Cipher 1F */
     {
@@ -724,6 +756,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 22 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_DES_64_CBC_MD5,
@@ -738,6 +771,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+# endif
 
 /* Cipher 23 */
     {
@@ -788,6 +822,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      },
 
 /* Cipher 26 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_DES_40_CBC_SHA,
@@ -802,8 +837,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+# endif
 
 /* Cipher 27 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_RC2_40_CBC_SHA,
@@ -818,8 +855,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+# endif
 
 /* Cipher 28 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_RC4_40_SHA,
@@ -834,8 +873,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+# endif
 
 /* Cipher 29 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_DES_40_CBC_MD5,
@@ -850,8 +891,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      56,
      },
+# endif
 
 /* Cipher 2A */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_RC2_40_CBC_MD5,
@@ -866,8 +909,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+# endif
 
 /* Cipher 2B */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      SSL3_TXT_KRB5_RC4_40_MD5,
@@ -882,6 +927,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      40,
      128,
      },
+# endif
 #endif                          /* OPENSSL_NO_KRB5 */
 
 /* New AES ciphersuites */
@@ -1305,6 +1351,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
 # endif
 
     /* Cipher 62 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      TLS1_TXT_RSA_EXPORT1024_WITH_DES_CBC_SHA,
@@ -1319,8 +1366,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+# endif
 
     /* Cipher 63 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      TLS1_TXT_DHE_DSS_EXPORT1024_WITH_DES_CBC_SHA,
@@ -1335,8 +1384,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      56,
      },
+# endif
 
     /* Cipher 64 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      TLS1_TXT_RSA_EXPORT1024_WITH_RC4_56_SHA,
@@ -1351,8 +1402,10 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      128,
      },
+# endif
 
     /* Cipher 65 */
+# ifndef OPENSSL_NO_WEAK_SSL_CIPHERS
     {
      1,
      TLS1_TXT_DHE_DSS_EXPORT1024_WITH_RC4_56_SHA,
@@ -1367,6 +1420,7 @@ OPENSSL_GLOBAL SSL_CIPHER ssl3_ciphers[] = {
      56,
      128,
      },
+# endif
 
     /* Cipher 66 */
     {

deps/openssl/openssl/ssl/ssl_lib.c

@@ -1896,6 +1896,13 @@ SSL_CTX *SSL_CTX_new(const SSL_METHOD *meth)
      */
     ret->options |= SSL_OP_LEGACY_SERVER_CONNECT;
 
+    /*
+     * Disable SSLv2 by default, callers that want to enable SSLv2 will have to
+     * explicitly clear this option via either of SSL_CTX_clear_options() or
+     * SSL_clear_options().
+     */
+    ret->options |= SSL_OP_NO_SSLv2;
+
     return (ret);
  err:
     SSLerr(SSL_F_SSL_CTX_NEW, ERR_R_MALLOC_FAILURE);

deps/openssl/openssl/util/libeay.num

@@ -1807,6 +1807,8 @@ ASN1_UTCTIME_get                        2350	NOEXIST::FUNCTION:
 X509_REQ_digest                         2362	EXIST::FUNCTION:EVP
 X509_CRL_digest                         2391	EXIST::FUNCTION:EVP
 ASN1_STRING_clear_free                  2392	EXIST::FUNCTION:
+SRP_VBASE_get1_by_user                  2393	EXIST::FUNCTION:SRP
+SRP_user_pwd_free                       2394	EXIST::FUNCTION:SRP
 d2i_ASN1_SET_OF_PKCS7                   2397	NOEXIST::FUNCTION:
 X509_ALGOR_cmp                          2398	EXIST::FUNCTION:
 EVP_CIPHER_CTX_set_key_length           2399	EXIST::FUNCTION:

deps/openssl/openssl/util/mk1mf.pl

@@ -281,6 +281,7 @@ $cflags.=" -DOPENSSL_NO_HW"   if $no_hw;
 $cflags.=" -DOPENSSL_FIPS"    if $fips;
 $cflags.=" -DOPENSSL_NO_JPAKE"    if $no_jpake;
 $cflags.=" -DOPENSSL_NO_EC2M"    if $no_ec2m;
+$cflags.=" -DOPENSSL_NO_WEAK_SSL_CIPHERS"   if $no_weak_ssl;
 $cflags.= " -DZLIB" if $zlib_opt;
 $cflags.= " -DZLIB_SHARED" if $zlib_opt == 2;
 
@@ -459,7 +460,7 @@ EX_LIBS=$ex_libs
 # The OpenSSL directory
 SRC_D=$src_dir
 
-LINK=$link
+LINK_CMD=$link
 LFLAGS=$lflags
 RSC=$rsc
 
@@ -1122,6 +1123,7 @@ sub read_options
 		"no-ec2m" => \$no_ec2m,
 		"no-jpake" => \$no_jpake,
 		"no-ec_nistp_64_gcc_128" => 0,
+		"no-weak-ssl-ciphers" => \$no_weak_ssl,
 		"no-err" => \$no_err,
 		"no-sock" => \$no_sock,
 		"no-krb5" => \$no_krb5,

deps/openssl/openssl/util/pl/BC-32.pl

@@ -118,7 +118,7 @@ ___
 		{
 		local($ex)=($target =~ /O_SSL/)?' $(L_CRYPTO)':'';
 		$ex.=' ws2_32.lib gdi32.lib';
-		$ret.="\t\$(LINK) \$(MLFLAGS) $efile$target /def:ms/${Name}.def @<<\n  \$(SHLIB_EX_OBJ) $objs $ex\n<<\n";
+		$ret.="\t\$(LINK_CMD) \$(MLFLAGS) $efile$target /def:ms/${Name}.def @<<\n  \$(SHLIB_EX_OBJ) $objs $ex\n<<\n";
 		}
 	$ret.="\n";
 	return($ret);
@@ -132,7 +132,7 @@ sub do_link_rule
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($target);
 	$ret.="$target: $files $dep_libs\n";
-	$ret.="\t\$(LINK) \$(LFLAGS) $files \$(APP_EX_OBJ), $target,, $libs\n\n";
+	$ret.="\t\$(LINK_CMD) \$(LFLAGS) $files \$(APP_EX_OBJ), $target,, $libs\n\n";
 	return($ret);
 	}
 

deps/openssl/openssl/util/pl/Mingw32.pl

@@ -98,7 +98,7 @@ sub do_link_rule
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($target);
 	$ret.="$target: $files $dep_libs\n";
-	$ret.="\t\$(LINK) ${efile}$target \$(LFLAGS) $files $libs\n\n";
+	$ret.="\t\$(LINK_CMD) ${efile}$target \$(LFLAGS) $files $libs\n\n";
 	return($ret);
 	}
 1;

deps/openssl/openssl/util/pl/OS2-EMX.pl

@@ -99,7 +99,7 @@ sub do_lib_rule
 		{
 		local($ex)=($target =~ /O_SSL/)?' $(L_CRYPTO)':'';
 		$ex.=' -lsocket';
-		$ret.="\t\$(LINK) \$(SHLIB_CFLAGS) \$(MLFLAGS) $efile$target \$(SHLIB_EX_OBJ) \$(${Name}OBJ) $ex os2/${Name}.def\n";
+		$ret.="\t\$(LINK_CMD) \$(SHLIB_CFLAGS) \$(MLFLAGS) $efile$target \$(SHLIB_EX_OBJ) \$(${Name}OBJ) $ex os2/${Name}.def\n";
 		$ret.="\temximp -o $out_def/$name.a os2/${Name}.def\n";
 		$ret.="\temximp -o $out_def/$name.lib os2/${Name}.def\n\n";
 		}
@@ -113,7 +113,7 @@ sub do_link_rule
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($target);
 	$ret.="$target: $files $dep_libs\n";
-	$ret.="\t\$(LINK) ${efile}$target \$(CFLAG) \$(LFLAGS) $files $libs\n\n";
+	$ret.="\t\$(LINK_CMD) ${efile}$target \$(CFLAG) \$(LFLAGS) $files $libs\n\n";
 	return($ret);
 	}
 

deps/openssl/openssl/util/pl/VC-32.pl

@@ -314,7 +314,7 @@ sub do_lib_rule
  		if ($fips && $target =~ /O_CRYPTO/)
 			{
 			$ret.="$target: $objs \$(PREMAIN_DSO_EXE)";
-			$ret.="\n\tSET FIPS_LINK=\$(LINK)\n";
+			$ret.="\n\tSET FIPS_LINK=\$(LINK_CMD)\n";
 			$ret.="\tSET FIPS_CC=\$(CC)\n";
 			$ret.="\tSET FIPS_CC_ARGS=/Fo\$(OBJ_D)${o}fips_premain.obj \$(SHLIB_CFLAGS) -c\n";
 			$ret.="\tSET PREMAIN_DSO_EXE=\$(PREMAIN_DSO_EXE)\n";
@@ -328,7 +328,7 @@ sub do_lib_rule
 		else
 			{
 			$ret.="$target: $objs";
-			$ret.="\n\t\$(LINK) \$(MLFLAGS) $efile$target $name @<<\n  \$(SHLIB_EX_OBJ) $objs $ex \$(EX_LIBS)\n<<\n";
+			$ret.="\n\t\$(LINK_CMD) \$(MLFLAGS) $efile$target $name @<<\n  \$(SHLIB_EX_OBJ) $objs $ex \$(EX_LIBS)\n<<\n";
 			}
 		$ret.="\tIF EXIST \$@.manifest mt -nologo -manifest \$@.manifest -outputresource:\$@;2\n\n";
 		}
@@ -347,7 +347,7 @@ sub do_link_rule
 		{
 		$ret.=" \$(OBJ_D)${o}applink.obj" if $shlib;
 		$ret.="\n";
-		$ret.="  \$(LINK) \$(LFLAGS) $efile$target @<<\n\t";
+		$ret.="  \$(LINK_CMD) \$(LFLAGS) $efile$target @<<\n\t";
 		if ($files =~ /O_FIPSCANISTER/ && !$fipscanisterbuild) {
 			$ret.= "\$(EX_LIBS) ";
 			$ret.= "\$(OBJ_D)${o}applink.obj " if $shlib;
@@ -357,7 +357,7 @@ sub do_link_rule
 	elsif ($standalone == 2)
 		{
 		$ret.="\n";
-		$ret.="\tSET FIPS_LINK=\$(LINK)\n";
+		$ret.="\tSET FIPS_LINK=\$(LINK_CMD)\n";
 		$ret.="\tSET FIPS_CC=\$(CC)\n";
 		$ret.="\tSET FIPS_CC_ARGS=/Fo\$(OBJ_D)${o}fips_premain.obj \$(SHLIB_CFLAGS) -c\n";
 		$ret.="\tSET PREMAIN_DSO_EXE=\n";
@@ -370,7 +370,7 @@ sub do_link_rule
 	else
 		{
 		$ret.="\n";
-		$ret.="\t\$(LINK) \$(LFLAGS) $efile$target @<<\n";
+		$ret.="\t\$(LINK_CMD) \$(LFLAGS) $efile$target @<<\n";
 		$ret.="\t\$(APP_EX_OBJ) $files $libs\n<<\n";
 		}
     	$ret.="\tIF EXIST \$@.manifest mt -nologo -manifest \$@.manifest -outputresource:\$@;1\n\n";

deps/openssl/openssl/util/pl/linux.pl

@@ -78,7 +78,7 @@ sub do_link_rule
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($target);
 	$ret.="$target: $files $dep_libs\n";
-	$ret.="\t\$(LINK) ${efile}$target \$(LFLAGS) $files $libs\n\n";
+	$ret.="\t\$(LINK_CMD) ${efile}$target \$(LFLAGS) $files $libs\n\n";
 	return($ret);
 	}
 

deps/openssl/openssl/util/pl/netware.pl

@@ -506,22 +506,22 @@ sub do_link_rule
       if ($gnuc)
       {
          $ret.="\t\$(MKLIB) $lib_flags \$(TMP_D)${o}\$(E_EXE).a \$(filter-out \$(TMP_D)${o}\$(E_EXE)${obj},$files)\n";
-         $ret.="\t\$(LINK) \$(LFLAGS) $def_file2\n";
+         $ret.="\t\$(LINK_CMD) \$(LFLAGS) $def_file2\n";
          $ret.="\t\@$mv \$(E_EXE)2.nlm \$(TEST_D)\n";
       }
       else
       {
-         $ret.="\t\$(LINK) \$(LFLAGS) $def_file2 $files \"$prelude\" $libs -o $target2\n";
+         $ret.="\t\$(LINK_CMD) \$(LFLAGS) $def_file2 $files \"$prelude\" $libs -o $target2\n";
       }
    }
    if ($gnuc)
    {
-      $ret.="\t\$(LINK) \$(LFLAGS) $def_file\n";
+      $ret.="\t\$(LINK_CMD) \$(LFLAGS) $def_file\n";
       $ret.="\t\@$mv \$(\@F) \$(TEST_D)\n";
    }
    else
    {
-      $ret.="\t\$(LINK) \$(LFLAGS) $def_file $files \"$prelude\" $libs -o $target\n";
+      $ret.="\t\$(LINK_CMD) \$(LFLAGS) $def_file $files \"$prelude\" $libs -o $target\n";
    }
 
    $ret.="\n";

deps/openssl/openssl/util/pl/ultrix.pl

@@ -31,7 +31,7 @@ sub do_link_rule
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($target);
 	$ret.="$target: $files $dep_libs\n";
-	$ret.="\t\$(LINK) ${efile}$target \$(LFLAGS) $files $libs\n\n";
+	$ret.="\t\$(LINK_CMD) ${efile}$target \$(LFLAGS) $files $libs\n\n";
 	return($ret);
 	}
 

deps/openssl/openssl/util/pl/unix.pl

@@ -76,7 +76,7 @@ sub do_link_rule
 	$file =~ s/\//$o/g if $o ne '/';
 	$n=&bname($target);
 	$ret.="$target: $files $dep_libs\n";
-	$ret.="\t\$(LINK) ${efile}$target \$(LFLAGS) $files $libs\n\n";
+	$ret.="\t\$(LINK_CMD) ${efile}$target \$(LFLAGS) $files $libs\n\n";
 	return($ret);
 	}