deps: upgrade openssl to 1.0.2g

PR-URL: https://github.com/nodejs/node/pull/5507
Reviewed-By: Fedor Indutny <fedor@indutny.com>

deps/openssl/asm/x64-elf-gas/aes/aesni-mb-x86_64.s

@@ -6,14 +6,6 @@
 .type	aesni_multi_cbc_encrypt,@function
 .align	32
 aesni_multi_cbc_encrypt:
-	cmpl	$2,%edx
-	jb	.Lenc_non_avx
-	movl	OPENSSL_ia32cap_P+4(%rip),%ecx
-	testl	$268435456,%ecx
-	jnz	_avx_cbc_enc_shortcut
-	jmp	.Lenc_non_avx
-.align	16
-.Lenc_non_avx:
 	movq	%rsp,%rax
 	pushq	%rbx
 	pushq	%rbp
@@ -270,14 +262,6 @@ aesni_multi_cbc_encrypt:
 .type	aesni_multi_cbc_decrypt,@function
 .align	32
 aesni_multi_cbc_decrypt:
-	cmpl	$2,%edx
-	jb	.Ldec_non_avx
-	movl	OPENSSL_ia32cap_P+4(%rip),%ecx
-	testl	$268435456,%ecx
-	jnz	_avx_cbc_dec_shortcut
-	jmp	.Ldec_non_avx
-.align	16
-.Ldec_non_avx:
 	movq	%rsp,%rax
 	pushq	%rbx
 	pushq	%rbp
@@ -520,916 +504,3 @@ aesni_multi_cbc_decrypt:
 .Ldec4x_epilogue:
 	.byte	0xf3,0xc3
 .size	aesni_multi_cbc_decrypt,.-aesni_multi_cbc_decrypt
-.type	aesni_multi_cbc_encrypt_avx,@function
-.align	32
-aesni_multi_cbc_encrypt_avx:
-_avx_cbc_enc_shortcut:
-	movq	%rsp,%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-
-
-
-
-
-
-
-
-	subq	$192,%rsp
-	andq	$-128,%rsp
-	movq	%rax,16(%rsp)
-
-.Lenc8x_body:
-	vzeroupper
-	vmovdqu	(%rsi),%xmm15
-	leaq	120(%rsi),%rsi
-	leaq	160(%rdi),%rdi
-	shrl	$1,%edx
-
-.Lenc8x_loop_grande:
-
-	xorl	%edx,%edx
-	movl	-144(%rdi),%ecx
-	movq	-160(%rdi),%r8
-	cmpl	%edx,%ecx
-	movq	-152(%rdi),%rbx
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-136(%rdi),%xmm2
-	movl	%ecx,32(%rsp)
-	cmovleq	%rsp,%r8
-	subq	%r8,%rbx
-	movq	%rbx,64(%rsp)
-	movl	-104(%rdi),%ecx
-	movq	-120(%rdi),%r9
-	cmpl	%edx,%ecx
-	movq	-112(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-96(%rdi),%xmm3
-	movl	%ecx,36(%rsp)
-	cmovleq	%rsp,%r9
-	subq	%r9,%rbp
-	movq	%rbp,72(%rsp)
-	movl	-64(%rdi),%ecx
-	movq	-80(%rdi),%r10
-	cmpl	%edx,%ecx
-	movq	-72(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-56(%rdi),%xmm4
-	movl	%ecx,40(%rsp)
-	cmovleq	%rsp,%r10
-	subq	%r10,%rbp
-	movq	%rbp,80(%rsp)
-	movl	-24(%rdi),%ecx
-	movq	-40(%rdi),%r11
-	cmpl	%edx,%ecx
-	movq	-32(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-16(%rdi),%xmm5
-	movl	%ecx,44(%rsp)
-	cmovleq	%rsp,%r11
-	subq	%r11,%rbp
-	movq	%rbp,88(%rsp)
-	movl	16(%rdi),%ecx
-	movq	0(%rdi),%r12
-	cmpl	%edx,%ecx
-	movq	8(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	24(%rdi),%xmm6
-	movl	%ecx,48(%rsp)
-	cmovleq	%rsp,%r12
-	subq	%r12,%rbp
-	movq	%rbp,96(%rsp)
-	movl	56(%rdi),%ecx
-	movq	40(%rdi),%r13
-	cmpl	%edx,%ecx
-	movq	48(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	64(%rdi),%xmm7
-	movl	%ecx,52(%rsp)
-	cmovleq	%rsp,%r13
-	subq	%r13,%rbp
-	movq	%rbp,104(%rsp)
-	movl	96(%rdi),%ecx
-	movq	80(%rdi),%r14
-	cmpl	%edx,%ecx
-	movq	88(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	104(%rdi),%xmm8
-	movl	%ecx,56(%rsp)
-	cmovleq	%rsp,%r14
-	subq	%r14,%rbp
-	movq	%rbp,112(%rsp)
-	movl	136(%rdi),%ecx
-	movq	120(%rdi),%r15
-	cmpl	%edx,%ecx
-	movq	128(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	144(%rdi),%xmm9
-	movl	%ecx,60(%rsp)
-	cmovleq	%rsp,%r15
-	subq	%r15,%rbp
-	movq	%rbp,120(%rsp)
-	testl	%edx,%edx
-	jz	.Lenc8x_done
-
-	vmovups	16-120(%rsi),%xmm1
-	vmovups	32-120(%rsi),%xmm0
-	movl	240-120(%rsi),%eax
-
-	vpxor	(%r8),%xmm15,%xmm10
-	leaq	128(%rsp),%rbp
-	vpxor	(%r9),%xmm15,%xmm11
-	vpxor	(%r10),%xmm15,%xmm12
-	vpxor	(%r11),%xmm15,%xmm13
-	vpxor	%xmm10,%xmm2,%xmm2
-	vpxor	(%r12),%xmm15,%xmm10
-	vpxor	%xmm11,%xmm3,%xmm3
-	vpxor	(%r13),%xmm15,%xmm11
-	vpxor	%xmm12,%xmm4,%xmm4
-	vpxor	(%r14),%xmm15,%xmm12
-	vpxor	%xmm13,%xmm5,%xmm5
-	vpxor	(%r15),%xmm15,%xmm13
-	vpxor	%xmm10,%xmm6,%xmm6
-	movl	$1,%ecx
-	vpxor	%xmm11,%xmm7,%xmm7
-	vpxor	%xmm12,%xmm8,%xmm8
-	vpxor	%xmm13,%xmm9,%xmm9
-	jmp	.Loop_enc8x
-
-.align	32
-.Loop_enc8x:
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+0(%rsp),%ecx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r8)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r8,%rbx,1),%rbx
-	cmovgeq	%rsp,%r8
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r8,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r8),%xmm15,%xmm10
-	movq	%rbx,64+0(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	-72(%rsi),%xmm1
-	leaq	16(%r8,%rbx,1),%r8
-	vmovdqu	%xmm10,0(%rbp)
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+4(%rsp),%ecx
-	movq	64+8(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r9)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%r9,%rbx,1),%rbx
-	cmovgeq	%rsp,%r9
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r9,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r9),%xmm15,%xmm11
-	movq	%rbx,64+8(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	-56(%rsi),%xmm0
-	leaq	16(%r9,%rbx,1),%r9
-	vmovdqu	%xmm11,16(%rbp)
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+8(%rsp),%ecx
-	movq	64+16(%rsp),%rbx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r10)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r8)
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r10,%rbx,1),%rbx
-	cmovgeq	%rsp,%r10
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r10,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r10),%xmm15,%xmm12
-	movq	%rbx,64+16(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	-40(%rsi),%xmm1
-	leaq	16(%r10,%rbx,1),%r10
-	vmovdqu	%xmm12,32(%rbp)
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+12(%rsp),%ecx
-	movq	64+24(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r11)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r9)
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%r11,%rbx,1),%rbx
-	cmovgeq	%rsp,%r11
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r11,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r11),%xmm15,%xmm13
-	movq	%rbx,64+24(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	-24(%rsi),%xmm0
-	leaq	16(%r11,%rbx,1),%r11
-	vmovdqu	%xmm13,48(%rbp)
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+16(%rsp),%ecx
-	movq	64+32(%rsp),%rbx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r12)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r10)
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r12,%rbx,1),%rbx
-	cmovgeq	%rsp,%r12
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r12,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r12),%xmm15,%xmm10
-	movq	%rbx,64+32(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	-8(%rsi),%xmm1
-	leaq	16(%r12,%rbx,1),%r12
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+20(%rsp),%ecx
-	movq	64+40(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r13)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r11)
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%rbx,%r13,1),%rbx
-	cmovgeq	%rsp,%r13
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r13,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r13),%xmm15,%xmm11
-	movq	%rbx,64+40(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	8(%rsi),%xmm0
-	leaq	16(%r13,%rbx,1),%r13
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+24(%rsp),%ecx
-	movq	64+48(%rsp),%rbx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r14)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r12)
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r14,%rbx,1),%rbx
-	cmovgeq	%rsp,%r14
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r14,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r14),%xmm15,%xmm12
-	movq	%rbx,64+48(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	24(%rsi),%xmm1
-	leaq	16(%r14,%rbx,1),%r14
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+28(%rsp),%ecx
-	movq	64+56(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r15)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r13)
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%r15,%rbx,1),%rbx
-	cmovgeq	%rsp,%r15
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r15,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r15),%xmm15,%xmm13
-	movq	%rbx,64+56(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	40(%rsi),%xmm0
-	leaq	16(%r15,%rbx,1),%r15
-	vmovdqu	32(%rsp),%xmm14
-	prefetcht0	15(%r14)
-	prefetcht0	15(%r15)
-	cmpl	$11,%eax
-	jb	.Lenc8x_tail
-
-	vaesenc	%xmm1,%xmm2,%xmm2
-	vaesenc	%xmm1,%xmm3,%xmm3
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vaesenc	%xmm1,%xmm5,%xmm5
-	vaesenc	%xmm1,%xmm6,%xmm6
-	vaesenc	%xmm1,%xmm7,%xmm7
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	176-120(%rsi),%xmm1
-
-	vaesenc	%xmm0,%xmm2,%xmm2
-	vaesenc	%xmm0,%xmm3,%xmm3
-	vaesenc	%xmm0,%xmm4,%xmm4
-	vaesenc	%xmm0,%xmm5,%xmm5
-	vaesenc	%xmm0,%xmm6,%xmm6
-	vaesenc	%xmm0,%xmm7,%xmm7
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	192-120(%rsi),%xmm0
-	je	.Lenc8x_tail
-
-	vaesenc	%xmm1,%xmm2,%xmm2
-	vaesenc	%xmm1,%xmm3,%xmm3
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vaesenc	%xmm1,%xmm5,%xmm5
-	vaesenc	%xmm1,%xmm6,%xmm6
-	vaesenc	%xmm1,%xmm7,%xmm7
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	208-120(%rsi),%xmm1
-
-	vaesenc	%xmm0,%xmm2,%xmm2
-	vaesenc	%xmm0,%xmm3,%xmm3
-	vaesenc	%xmm0,%xmm4,%xmm4
-	vaesenc	%xmm0,%xmm5,%xmm5
-	vaesenc	%xmm0,%xmm6,%xmm6
-	vaesenc	%xmm0,%xmm7,%xmm7
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	224-120(%rsi),%xmm0
-
-.Lenc8x_tail:
-	vaesenc	%xmm1,%xmm2,%xmm2
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesenc	%xmm1,%xmm3,%xmm3
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesenc	%xmm1,%xmm5,%xmm5
-	vaesenc	%xmm1,%xmm6,%xmm6
-	vpaddd	%xmm14,%xmm15,%xmm15
-	vmovdqu	48(%rsp),%xmm14
-	vaesenc	%xmm1,%xmm7,%xmm7
-	movq	64(%rsp),%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	16-120(%rsi),%xmm1
-
-	vaesenclast	%xmm0,%xmm2,%xmm2
-	vmovdqa	%xmm15,32(%rsp)
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesenclast	%xmm0,%xmm3,%xmm3
-	vaesenclast	%xmm0,%xmm4,%xmm4
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesenclast	%xmm0,%xmm5,%xmm5
-	vaesenclast	%xmm0,%xmm6,%xmm6
-	vpaddd	%xmm15,%xmm14,%xmm14
-	vmovdqu	-120(%rsi),%xmm15
-	vaesenclast	%xmm0,%xmm7,%xmm7
-	vaesenclast	%xmm0,%xmm8,%xmm8
-	vmovdqa	%xmm14,48(%rsp)
-	vaesenclast	%xmm0,%xmm9,%xmm9
-	vmovups	32-120(%rsi),%xmm0
-
-	vmovups	%xmm2,-16(%r8)
-	subq	%rbx,%r8
-	vpxor	0(%rbp),%xmm2,%xmm2
-	vmovups	%xmm3,-16(%r9)
-	subq	72(%rsp),%r9
-	vpxor	16(%rbp),%xmm3,%xmm3
-	vmovups	%xmm4,-16(%r10)
-	subq	80(%rsp),%r10
-	vpxor	32(%rbp),%xmm4,%xmm4
-	vmovups	%xmm5,-16(%r11)
-	subq	88(%rsp),%r11
-	vpxor	48(%rbp),%xmm5,%xmm5
-	vmovups	%xmm6,-16(%r12)
-	subq	96(%rsp),%r12
-	vpxor	%xmm10,%xmm6,%xmm6
-	vmovups	%xmm7,-16(%r13)
-	subq	104(%rsp),%r13
-	vpxor	%xmm11,%xmm7,%xmm7
-	vmovups	%xmm8,-16(%r14)
-	subq	112(%rsp),%r14
-	vpxor	%xmm12,%xmm8,%xmm8
-	vmovups	%xmm9,-16(%r15)
-	subq	120(%rsp),%r15
-	vpxor	%xmm13,%xmm9,%xmm9
-
-	decl	%edx
-	jnz	.Loop_enc8x
-
-	movq	16(%rsp),%rax
-
-
-
-
-
-.Lenc8x_done:
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-.Lenc8x_epilogue:
-	.byte	0xf3,0xc3
-.size	aesni_multi_cbc_encrypt_avx,.-aesni_multi_cbc_encrypt_avx
-
-.type	aesni_multi_cbc_decrypt_avx,@function
-.align	32
-aesni_multi_cbc_decrypt_avx:
-_avx_cbc_dec_shortcut:
-	movq	%rsp,%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-
-
-
-
-
-
-
-
-
-	subq	$256,%rsp
-	andq	$-256,%rsp
-	subq	$192,%rsp
-	movq	%rax,16(%rsp)
-
-.Ldec8x_body:
-	vzeroupper
-	vmovdqu	(%rsi),%xmm15
-	leaq	120(%rsi),%rsi
-	leaq	160(%rdi),%rdi
-	shrl	$1,%edx
-
-.Ldec8x_loop_grande:
-
-	xorl	%edx,%edx
-	movl	-144(%rdi),%ecx
-	movq	-160(%rdi),%r8
-	cmpl	%edx,%ecx
-	movq	-152(%rdi),%rbx
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-136(%rdi),%xmm2
-	movl	%ecx,32(%rsp)
-	cmovleq	%rsp,%r8
-	subq	%r8,%rbx
-	movq	%rbx,64(%rsp)
-	vmovdqu	%xmm2,192(%rsp)
-	movl	-104(%rdi),%ecx
-	movq	-120(%rdi),%r9
-	cmpl	%edx,%ecx
-	movq	-112(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-96(%rdi),%xmm3
-	movl	%ecx,36(%rsp)
-	cmovleq	%rsp,%r9
-	subq	%r9,%rbp
-	movq	%rbp,72(%rsp)
-	vmovdqu	%xmm3,208(%rsp)
-	movl	-64(%rdi),%ecx
-	movq	-80(%rdi),%r10
-	cmpl	%edx,%ecx
-	movq	-72(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-56(%rdi),%xmm4
-	movl	%ecx,40(%rsp)
-	cmovleq	%rsp,%r10
-	subq	%r10,%rbp
-	movq	%rbp,80(%rsp)
-	vmovdqu	%xmm4,224(%rsp)
-	movl	-24(%rdi),%ecx
-	movq	-40(%rdi),%r11
-	cmpl	%edx,%ecx
-	movq	-32(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-16(%rdi),%xmm5
-	movl	%ecx,44(%rsp)
-	cmovleq	%rsp,%r11
-	subq	%r11,%rbp
-	movq	%rbp,88(%rsp)
-	vmovdqu	%xmm5,240(%rsp)
-	movl	16(%rdi),%ecx
-	movq	0(%rdi),%r12
-	cmpl	%edx,%ecx
-	movq	8(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	24(%rdi),%xmm6
-	movl	%ecx,48(%rsp)
-	cmovleq	%rsp,%r12
-	subq	%r12,%rbp
-	movq	%rbp,96(%rsp)
-	vmovdqu	%xmm6,256(%rsp)
-	movl	56(%rdi),%ecx
-	movq	40(%rdi),%r13
-	cmpl	%edx,%ecx
-	movq	48(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	64(%rdi),%xmm7
-	movl	%ecx,52(%rsp)
-	cmovleq	%rsp,%r13
-	subq	%r13,%rbp
-	movq	%rbp,104(%rsp)
-	vmovdqu	%xmm7,272(%rsp)
-	movl	96(%rdi),%ecx
-	movq	80(%rdi),%r14
-	cmpl	%edx,%ecx
-	movq	88(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	104(%rdi),%xmm8
-	movl	%ecx,56(%rsp)
-	cmovleq	%rsp,%r14
-	subq	%r14,%rbp
-	movq	%rbp,112(%rsp)
-	vmovdqu	%xmm8,288(%rsp)
-	movl	136(%rdi),%ecx
-	movq	120(%rdi),%r15
-	cmpl	%edx,%ecx
-	movq	128(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	144(%rdi),%xmm9
-	movl	%ecx,60(%rsp)
-	cmovleq	%rsp,%r15
-	subq	%r15,%rbp
-	movq	%rbp,120(%rsp)
-	vmovdqu	%xmm9,304(%rsp)
-	testl	%edx,%edx
-	jz	.Ldec8x_done
-
-	vmovups	16-120(%rsi),%xmm1
-	vmovups	32-120(%rsi),%xmm0
-	movl	240-120(%rsi),%eax
-	leaq	192+128(%rsp),%rbp
-
-	vmovdqu	(%r8),%xmm2
-	vmovdqu	(%r9),%xmm3
-	vmovdqu	(%r10),%xmm4
-	vmovdqu	(%r11),%xmm5
-	vmovdqu	(%r12),%xmm6
-	vmovdqu	(%r13),%xmm7
-	vmovdqu	(%r14),%xmm8
-	vmovdqu	(%r15),%xmm9
-	vmovdqu	%xmm2,0(%rbp)
-	vpxor	%xmm15,%xmm2,%xmm2
-	vmovdqu	%xmm3,16(%rbp)
-	vpxor	%xmm15,%xmm3,%xmm3
-	vmovdqu	%xmm4,32(%rbp)
-	vpxor	%xmm15,%xmm4,%xmm4
-	vmovdqu	%xmm5,48(%rbp)
-	vpxor	%xmm15,%xmm5,%xmm5
-	vmovdqu	%xmm6,64(%rbp)
-	vpxor	%xmm15,%xmm6,%xmm6
-	vmovdqu	%xmm7,80(%rbp)
-	vpxor	%xmm15,%xmm7,%xmm7
-	vmovdqu	%xmm8,96(%rbp)
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	%xmm9,112(%rbp)
-	vpxor	%xmm15,%xmm9,%xmm9
-	xorq	$128,%rbp
-	movl	$1,%ecx
-	jmp	.Loop_dec8x
-
-.align	32
-.Loop_dec8x:
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+0(%rsp),%ecx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r8)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r8,%rbx,1),%rbx
-	cmovgeq	%rsp,%r8
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r8,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r8),%xmm10
-	movq	%rbx,64+0(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	-72(%rsi),%xmm1
-	leaq	16(%r8,%rbx,1),%r8
-	vmovdqu	%xmm10,128(%rsp)
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+4(%rsp),%ecx
-	movq	64+8(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r9)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%r9,%rbx,1),%rbx
-	cmovgeq	%rsp,%r9
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r9,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r9),%xmm11
-	movq	%rbx,64+8(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	-56(%rsi),%xmm0
-	leaq	16(%r9,%rbx,1),%r9
-	vmovdqu	%xmm11,144(%rsp)
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+8(%rsp),%ecx
-	movq	64+16(%rsp),%rbx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r10)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r8)
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r10,%rbx,1),%rbx
-	cmovgeq	%rsp,%r10
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r10,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r10),%xmm12
-	movq	%rbx,64+16(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	-40(%rsi),%xmm1
-	leaq	16(%r10,%rbx,1),%r10
-	vmovdqu	%xmm12,160(%rsp)
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+12(%rsp),%ecx
-	movq	64+24(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r11)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r9)
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%r11,%rbx,1),%rbx
-	cmovgeq	%rsp,%r11
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r11,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r11),%xmm13
-	movq	%rbx,64+24(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	-24(%rsi),%xmm0
-	leaq	16(%r11,%rbx,1),%r11
-	vmovdqu	%xmm13,176(%rsp)
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+16(%rsp),%ecx
-	movq	64+32(%rsp),%rbx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r12)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r10)
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r12,%rbx,1),%rbx
-	cmovgeq	%rsp,%r12
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r12,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r12),%xmm10
-	movq	%rbx,64+32(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	-8(%rsi),%xmm1
-	leaq	16(%r12,%rbx,1),%r12
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+20(%rsp),%ecx
-	movq	64+40(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r13)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r11)
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%rbx,%r13,1),%rbx
-	cmovgeq	%rsp,%r13
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r13,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r13),%xmm11
-	movq	%rbx,64+40(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	8(%rsi),%xmm0
-	leaq	16(%r13,%rbx,1),%r13
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+24(%rsp),%ecx
-	movq	64+48(%rsp),%rbx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r14)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r12)
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r14,%rbx,1),%rbx
-	cmovgeq	%rsp,%r14
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r14,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r14),%xmm12
-	movq	%rbx,64+48(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	24(%rsi),%xmm1
-	leaq	16(%r14,%rbx,1),%r14
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+28(%rsp),%ecx
-	movq	64+56(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r15)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r13)
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%r15,%rbx,1),%rbx
-	cmovgeq	%rsp,%r15
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r15,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r15),%xmm13
-	movq	%rbx,64+56(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	40(%rsi),%xmm0
-	leaq	16(%r15,%rbx,1),%r15
-	vmovdqu	32(%rsp),%xmm14
-	prefetcht0	15(%r14)
-	prefetcht0	15(%r15)
-	cmpl	$11,%eax
-	jb	.Ldec8x_tail
-
-	vaesdec	%xmm1,%xmm2,%xmm2
-	vaesdec	%xmm1,%xmm3,%xmm3
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vaesdec	%xmm1,%xmm5,%xmm5
-	vaesdec	%xmm1,%xmm6,%xmm6
-	vaesdec	%xmm1,%xmm7,%xmm7
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	176-120(%rsi),%xmm1
-
-	vaesdec	%xmm0,%xmm2,%xmm2
-	vaesdec	%xmm0,%xmm3,%xmm3
-	vaesdec	%xmm0,%xmm4,%xmm4
-	vaesdec	%xmm0,%xmm5,%xmm5
-	vaesdec	%xmm0,%xmm6,%xmm6
-	vaesdec	%xmm0,%xmm7,%xmm7
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	192-120(%rsi),%xmm0
-	je	.Ldec8x_tail
-
-	vaesdec	%xmm1,%xmm2,%xmm2
-	vaesdec	%xmm1,%xmm3,%xmm3
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vaesdec	%xmm1,%xmm5,%xmm5
-	vaesdec	%xmm1,%xmm6,%xmm6
-	vaesdec	%xmm1,%xmm7,%xmm7
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	208-120(%rsi),%xmm1
-
-	vaesdec	%xmm0,%xmm2,%xmm2
-	vaesdec	%xmm0,%xmm3,%xmm3
-	vaesdec	%xmm0,%xmm4,%xmm4
-	vaesdec	%xmm0,%xmm5,%xmm5
-	vaesdec	%xmm0,%xmm6,%xmm6
-	vaesdec	%xmm0,%xmm7,%xmm7
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	224-120(%rsi),%xmm0
-
-.Ldec8x_tail:
-	vaesdec	%xmm1,%xmm2,%xmm2
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesdec	%xmm1,%xmm3,%xmm3
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesdec	%xmm1,%xmm5,%xmm5
-	vaesdec	%xmm1,%xmm6,%xmm6
-	vpaddd	%xmm14,%xmm15,%xmm15
-	vmovdqu	48(%rsp),%xmm14
-	vaesdec	%xmm1,%xmm7,%xmm7
-	movq	64(%rsp),%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	16-120(%rsi),%xmm1
-
-	vaesdeclast	%xmm0,%xmm2,%xmm2
-	vmovdqa	%xmm15,32(%rsp)
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesdeclast	%xmm0,%xmm3,%xmm3
-	vpxor	0(%rbp),%xmm2,%xmm2
-	vaesdeclast	%xmm0,%xmm4,%xmm4
-	vpxor	16(%rbp),%xmm3,%xmm3
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesdeclast	%xmm0,%xmm5,%xmm5
-	vpxor	32(%rbp),%xmm4,%xmm4
-	vaesdeclast	%xmm0,%xmm6,%xmm6
-	vpxor	48(%rbp),%xmm5,%xmm5
-	vpaddd	%xmm15,%xmm14,%xmm14
-	vmovdqu	-120(%rsi),%xmm15
-	vaesdeclast	%xmm0,%xmm7,%xmm7
-	vpxor	64(%rbp),%xmm6,%xmm6
-	vaesdeclast	%xmm0,%xmm8,%xmm8
-	vpxor	80(%rbp),%xmm7,%xmm7
-	vmovdqa	%xmm14,48(%rsp)
-	vaesdeclast	%xmm0,%xmm9,%xmm9
-	vpxor	96(%rbp),%xmm8,%xmm8
-	vmovups	32-120(%rsi),%xmm0
-
-	vmovups	%xmm2,-16(%r8)
-	subq	%rbx,%r8
-	vmovdqu	128+0(%rsp),%xmm2
-	vpxor	112(%rbp),%xmm9,%xmm9
-	vmovups	%xmm3,-16(%r9)
-	subq	72(%rsp),%r9
-	vmovdqu	%xmm2,0(%rbp)
-	vpxor	%xmm15,%xmm2,%xmm2
-	vmovdqu	128+16(%rsp),%xmm3
-	vmovups	%xmm4,-16(%r10)
-	subq	80(%rsp),%r10
-	vmovdqu	%xmm3,16(%rbp)
-	vpxor	%xmm15,%xmm3,%xmm3
-	vmovdqu	128+32(%rsp),%xmm4
-	vmovups	%xmm5,-16(%r11)
-	subq	88(%rsp),%r11
-	vmovdqu	%xmm4,32(%rbp)
-	vpxor	%xmm15,%xmm4,%xmm4
-	vmovdqu	128+48(%rsp),%xmm5
-	vmovups	%xmm6,-16(%r12)
-	subq	96(%rsp),%r12
-	vmovdqu	%xmm5,48(%rbp)
-	vpxor	%xmm15,%xmm5,%xmm5
-	vmovdqu	%xmm10,64(%rbp)
-	vpxor	%xmm10,%xmm15,%xmm6
-	vmovups	%xmm7,-16(%r13)
-	subq	104(%rsp),%r13
-	vmovdqu	%xmm11,80(%rbp)
-	vpxor	%xmm11,%xmm15,%xmm7
-	vmovups	%xmm8,-16(%r14)
-	subq	112(%rsp),%r14
-	vmovdqu	%xmm12,96(%rbp)
-	vpxor	%xmm12,%xmm15,%xmm8
-	vmovups	%xmm9,-16(%r15)
-	subq	120(%rsp),%r15
-	vmovdqu	%xmm13,112(%rbp)
-	vpxor	%xmm13,%xmm15,%xmm9
-
-	xorq	$128,%rbp
-	decl	%edx
-	jnz	.Loop_dec8x
-
-	movq	16(%rsp),%rax
-
-
-
-
-
-.Ldec8x_done:
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-.Ldec8x_epilogue:
-	.byte	0xf3,0xc3
-.size	aesni_multi_cbc_decrypt_avx,.-aesni_multi_cbc_decrypt_avx

deps/openssl/asm/x64-elf-gas/bn/x86_64-gf2m.s

@@ -242,7 +242,7 @@ bn_GF2m_mul_2x2:
 	movq	%rcx,56(%rsp)
 	movq	%r8,64(%rsp)
 
-	movq	$15,%r8
+	movq	$0xf,%r8
 	movq	%rsi,%rax
 	movq	%rcx,%rbp
 	call	_mul_1x1

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

@@ -10,7 +10,6 @@ bn_mul_mont:
 	jnz	.Lmul_enter
 	cmpl	$8,%r9d
 	jb	.Lmul_enter
-	movl	OPENSSL_ia32cap_P+8(%rip),%r11d
 	cmpq	%rsi,%rdx
 	jne	.Lmul4x_enter
 	testl	$7,%r9d
@@ -216,9 +215,6 @@ bn_mul_mont:
 .align	16
 bn_mul4x_mont:
 .Lmul4x_enter:
-	andl	$524544,%r11d
-	cmpl	$524544,%r11d
-	je	.Lmulx4x_enter
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
@@ -615,7 +611,6 @@ bn_mul4x_mont:
 .size	bn_mul4x_mont,.-bn_mul4x_mont
 
 
-
 .type	bn_sqr8x_mont,@function
 .align	32
 bn_sqr8x_mont:
@@ -638,20 +633,20 @@ bn_sqr8x_mont:
 
 
 
-	leaq	-64(%rsp,%r9,4),%r11
+	leaq	-64(%rsp,%r9,2),%r11
 	movq	(%r8),%r8
 	subq	%rsi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	.Lsqr8x_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	-64(%rsp,%r9,2),%rsp
 	jmp	.Lsqr8x_sp_done
 
 .align	32
 .Lsqr8x_sp_alt:
-	leaq	4096-64(,%r9,4),%r10
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	4096-64(,%r9,2),%r10
+	leaq	-64(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -661,385 +656,81 @@ bn_sqr8x_mont:
 	movq	%r9,%r10
 	negq	%r9
 
-	leaq	64(%rsp,%r9,2),%r11
 	movq	%r8,32(%rsp)
 	movq	%rax,40(%rsp)
 .Lsqr8x_body:
 
-	movq	%r9,%rbp
-.byte	102,73,15,110,211
-	shrq	$3+2,%rbp
-	movl	OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	.Lsqr8x_copy_n
-
-.align	32
-.Lsqr8x_copy_n:
-	movq	0(%rcx),%xmm0
-	movq	8(%rcx),%xmm1
-	movq	16(%rcx),%xmm3
-	movq	24(%rcx),%xmm4
-	leaq	32(%rcx),%rcx
-	movdqa	%xmm0,0(%r11)
-	movdqa	%xmm1,16(%r11)
-	movdqa	%xmm3,32(%r11)
-	movdqa	%xmm4,48(%r11)
-	leaq	64(%r11),%r11
-	decq	%rbp
-	jnz	.Lsqr8x_copy_n
-
+.byte	102,72,15,110,209
 	pxor	%xmm0,%xmm0
 .byte	102,72,15,110,207
 .byte	102,73,15,110,218
-	andl	$524544,%eax
-	cmpl	$524544,%eax
-	jne	.Lsqr8x_nox
-
-	call	bn_sqrx8x_internal
-
-	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
-	movq	40(%rsp),%rsi
-	jmp	.Lsqr8x_zero
-
-.align	32
-.Lsqr8x_nox:
 	call	bn_sqr8x_internal
 
-	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
-	movq	40(%rsp),%rsi
-	jmp	.Lsqr8x_zero
-
-.align	32
-.Lsqr8x_zero:
-	movdqa	%xmm0,0(%rax)
-	movdqa	%xmm0,16(%rax)
-	movdqa	%xmm0,32(%rax)
-	movdqa	%xmm0,48(%rax)
-	leaq	64(%rax),%rax
-	movdqa	%xmm0,0(%rdx)
-	movdqa	%xmm0,16(%rdx)
-	movdqa	%xmm0,32(%rdx)
-	movdqa	%xmm0,48(%rdx)
-	leaq	64(%rdx),%rdx
-	decq	%r9
-	jnz	.Lsqr8x_zero
-
-	movq	$1,%rax
-	movq	-48(%rsi),%r15
-	movq	-40(%rsi),%r14
-	movq	-32(%rsi),%r13
-	movq	-24(%rsi),%r12
-	movq	-16(%rsi),%rbp
-	movq	-8(%rsi),%rbx
-	leaq	(%rsi),%rsp
-.Lsqr8x_epilogue:
-	.byte	0xf3,0xc3
-.size	bn_sqr8x_mont,.-bn_sqr8x_mont
-.type	bn_mulx4x_mont,@function
-.align	32
-bn_mulx4x_mont:
-.Lmulx4x_enter:
-	movq	%rsp,%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-
-	shll	$3,%r9d
-.byte	0x67
-	xorq	%r10,%r10
-	subq	%r9,%r10
-	movq	(%r8),%r8
-	leaq	-72(%rsp,%r10,1),%rsp
-	leaq	(%rdx,%r9,1),%r10
-	andq	$-128,%rsp
-
 
 
 
-
-
-
-
-
-
-
-
-	movq	%r9,0(%rsp)
-	shrq	$5,%r9
-	movq	%r10,16(%rsp)
-	subq	$1,%r9
-	movq	%r8,24(%rsp)
-	movq	%rdi,32(%rsp)
-	movq	%rax,40(%rsp)
-	movq	%r9,48(%rsp)
-	jmp	.Lmulx4x_body
-
-.align	32
-.Lmulx4x_body:
-	leaq	8(%rdx),%rdi
-	movq	(%rdx),%rdx
-	leaq	64+32(%rsp),%rbx
-	movq	%rdx,%r9
-
-	mulxq	0(%rsi),%r8,%rax
-	mulxq	8(%rsi),%r11,%r14
-	addq	%rax,%r11
-	movq	%rdi,8(%rsp)
-	mulxq	16(%rsi),%r12,%r13
-	adcq	%r14,%r12
-	adcq	$0,%r13
-
-	movq	%r8,%rdi
-	imulq	24(%rsp),%r8
-	xorq	%rbp,%rbp
-
-	mulxq	24(%rsi),%rax,%r14
-	movq	%r8,%rdx
-	leaq	32(%rsi),%rsi
-	adcxq	%rax,%r13
-	adcxq	%rbp,%r14
-
-	mulxq	0(%rcx),%rax,%r10
-	adcxq	%rax,%rdi
-	adoxq	%r11,%r10
-	mulxq	8(%rcx),%rax,%r11
-	adcxq	%rax,%r10
-	adoxq	%r12,%r11
-.byte	0xc4,0x62,0xfb,0xf6,0xa1,0x10,0x00,0x00,0x00
-	movq	48(%rsp),%rdi
-	movq	%r10,-32(%rbx)
-	adcxq	%rax,%r11
-	adoxq	%r13,%r12
-	mulxq	24(%rcx),%rax,%r15
-	movq	%r9,%rdx
-	movq	%r11,-24(%rbx)
-	adcxq	%rax,%r12
-	adoxq	%rbp,%r15
-	leaq	32(%rcx),%rcx
-	movq	%r12,-16(%rbx)
-
-	jmp	.Lmulx4x_1st
-
-.align	32
-.Lmulx4x_1st:
-	adcxq	%rbp,%r15
-	mulxq	0(%rsi),%r10,%rax
-	adcxq	%r14,%r10
-	mulxq	8(%rsi),%r11,%r14
-	adcxq	%rax,%r11
-	mulxq	16(%rsi),%r12,%rax
-	adcxq	%r14,%r12
-	mulxq	24(%rsi),%r13,%r14
-.byte	0x67,0x67
-	movq	%r8,%rdx
-	adcxq	%rax,%r13
-	adcxq	%rbp,%r14
-	leaq	32(%rsi),%rsi
-	leaq	32(%rbx),%rbx
-
-	adoxq	%r15,%r10
-	mulxq	0(%rcx),%rax,%r15
-	adcxq	%rax,%r10
-	adoxq	%r15,%r11
-	mulxq	8(%rcx),%rax,%r15
-	adcxq	%rax,%r11
-	adoxq	%r15,%r12
-	mulxq	16(%rcx),%rax,%r15
-	movq	%r10,-40(%rbx)
-	adcxq	%rax,%r12
-	movq	%r11,-32(%rbx)
-	adoxq	%r15,%r13
-	mulxq	24(%rcx),%rax,%r15
-	movq	%r9,%rdx
-	movq	%r12,-24(%rbx)
-	adcxq	%rax,%r13
-	adoxq	%rbp,%r15
-	leaq	32(%rcx),%rcx
-	movq	%r13,-16(%rbx)
-
-	decq	%rdi
-	jnz	.Lmulx4x_1st
-
-	movq	0(%rsp),%rax
-	movq	8(%rsp),%rdi
-	adcq	%rbp,%r15
-	addq	%r15,%r14
-	sbbq	%r15,%r15
-	movq	%r14,-8(%rbx)
-	jmp	.Lmulx4x_outer
-
-.align	32
-.Lmulx4x_outer:
-	movq	(%rdi),%rdx
-	leaq	8(%rdi),%rdi
-	subq	%rax,%rsi
-	movq	%r15,(%rbx)
-	leaq	64+32(%rsp),%rbx
-	subq	%rax,%rcx
-
-	mulxq	0(%rsi),%r8,%r11
-	xorl	%ebp,%ebp
-	movq	%rdx,%r9
-	mulxq	8(%rsi),%r14,%r12
-	adoxq	-32(%rbx),%r8
-	adcxq	%r14,%r11
-	mulxq	16(%rsi),%r15,%r13
-	adoxq	-24(%rbx),%r11
-	adcxq	%r15,%r12
-	adoxq	%rbp,%r12
-	adcxq	%rbp,%r13
-
-	movq	%rdi,8(%rsp)
-.byte	0x67
-	movq	%r8,%r15
-	imulq	24(%rsp),%r8
-	xorl	%ebp,%ebp
-
-	mulxq	24(%rsi),%rax,%r14
-	movq	%r8,%rdx
-	adoxq	-16(%rbx),%r12
-	adcxq	%rax,%r13
-	adoxq	-8(%rbx),%r13
-	adcxq	%rbp,%r14
-	leaq	32(%rsi),%rsi
-	adoxq	%rbp,%r14
-
-	mulxq	0(%rcx),%rax,%r10
-	adcxq	%rax,%r15
-	adoxq	%r11,%r10
-	mulxq	8(%rcx),%rax,%r11
-	adcxq	%rax,%r10
-	adoxq	%r12,%r11
-	mulxq	16(%rcx),%rax,%r12
-	movq	%r10,-32(%rbx)
-	adcxq	%rax,%r11
-	adoxq	%r13,%r12
-	mulxq	24(%rcx),%rax,%r15
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
 	movq	%r9,%rdx
-	movq	%r11,-24(%rbx)
-	leaq	32(%rcx),%rcx
-	adcxq	%rax,%r12
-	adoxq	%rbp,%r15
-	movq	48(%rsp),%rdi
-	movq	%r12,-16(%rbx)
-
-	jmp	.Lmulx4x_inner
+.byte	102,72,15,126,207
+	sarq	$3+2,%rcx
+	jmp	.Lsqr8x_sub
 
 .align	32
-.Lmulx4x_inner:
-	mulxq	0(%rsi),%r10,%rax
-	adcxq	%rbp,%r15
-	adoxq	%r14,%r10
-	mulxq	8(%rsi),%r11,%r14
-	adcxq	0(%rbx),%r10
-	adoxq	%rax,%r11
-	mulxq	16(%rsi),%r12,%rax
-	adcxq	8(%rbx),%r11
-	adoxq	%r14,%r12
-	mulxq	24(%rsi),%r13,%r14
-	movq	%r8,%rdx
-	adcxq	16(%rbx),%r12
-	adoxq	%rax,%r13
-	adcxq	24(%rbx),%r13
-	adoxq	%rbp,%r14
-	leaq	32(%rsi),%rsi
+.Lsqr8x_sub:
+	movq	0(%rbx),%r12
+	movq	8(%rbx),%r13
+	movq	16(%rbx),%r14
+	movq	24(%rbx),%r15
 	leaq	32(%rbx),%rbx
-	adcxq	%rbp,%r14
-
-	adoxq	%r15,%r10
-	mulxq	0(%rcx),%rax,%r15
-	adcxq	%rax,%r10
-	adoxq	%r15,%r11
-	mulxq	8(%rcx),%rax,%r15
-	adcxq	%rax,%r11
-	adoxq	%r15,%r12
-	mulxq	16(%rcx),%rax,%r15
-	movq	%r10,-40(%rbx)
-	adcxq	%rax,%r12
-	adoxq	%r15,%r13
-	mulxq	24(%rcx),%rax,%r15
-	movq	%r9,%rdx
-	movq	%r11,-32(%rbx)
-	movq	%r12,-24(%rbx)
-	adcxq	%rax,%r13
-	adoxq	%rbp,%r15
-	leaq	32(%rcx),%rcx
-	movq	%r13,-16(%rbx)
-
-	decq	%rdi
-	jnz	.Lmulx4x_inner
+	sbbq	0(%rbp),%r12
+	sbbq	8(%rbp),%r13
+	sbbq	16(%rbp),%r14
+	sbbq	24(%rbp),%r15
+	leaq	32(%rbp),%rbp
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	leaq	32(%rdi),%rdi
+	incq	%rcx
+	jnz	.Lsqr8x_sub
 
-	movq	0(%rsp),%rax
-	movq	8(%rsp),%rdi
-	adcq	%rbp,%r15
-	subq	0(%rbx),%rbp
-	adcq	%r15,%r14
-	movq	-8(%rcx),%r8
-	sbbq	%r15,%r15
-	movq	%r14,-8(%rbx)
-
-	cmpq	16(%rsp),%rdi
-	jne	.Lmulx4x_outer
-
-	subq	%r14,%r8
-	sbbq	%r8,%r8
-	orq	%r8,%r15
-
-	negq	%rax
-	xorq	%rdx,%rdx
-	movq	32(%rsp),%rdi
-	leaq	64(%rsp),%rbx
+	sbbq	$0,%rax
+	leaq	(%rbx,%r9,1),%rbx
+	leaq	(%rdi,%r9,1),%rdi
 
+.byte	102,72,15,110,200
 	pxor	%xmm0,%xmm0
-	movq	0(%rcx,%rax,1),%r8
-	movq	8(%rcx,%rax,1),%r9
-	negq	%r8
-	jmp	.Lmulx4x_sub_entry
+	pshufd	$0,%xmm1,%xmm1
+	movq	40(%rsp),%rsi
+	jmp	.Lsqr8x_cond_copy
 
 .align	32
-.Lmulx4x_sub:
-	movq	0(%rcx,%rax,1),%r8
-	movq	8(%rcx,%rax,1),%r9
-	notq	%r8
-.Lmulx4x_sub_entry:
-	movq	16(%rcx,%rax,1),%r10
-	notq	%r9
-	andq	%r15,%r8
-	movq	24(%rcx,%rax,1),%r11
-	notq	%r10
-	andq	%r15,%r9
-	notq	%r11
-	andq	%r15,%r10
-	andq	%r15,%r11
-
-	negq	%rdx
-	adcq	0(%rbx),%r8
-	adcq	8(%rbx),%r9
-	movdqa	%xmm0,(%rbx)
-	adcq	16(%rbx),%r10
-	adcq	24(%rbx),%r11
-	movdqa	%xmm0,16(%rbx)
+.Lsqr8x_cond_copy:
+	movdqa	0(%rbx),%xmm2
+	movdqa	16(%rbx),%xmm3
 	leaq	32(%rbx),%rbx
-	sbbq	%rdx,%rdx
-
-	movq	%r8,0(%rdi)
-	movq	%r9,8(%rdi)
-	movq	%r10,16(%rdi)
-	movq	%r11,24(%rdi)
+	movdqu	0(%rdi),%xmm4
+	movdqu	16(%rdi),%xmm5
 	leaq	32(%rdi),%rdi
+	movdqa	%xmm0,-32(%rbx)
+	movdqa	%xmm0,-16(%rbx)
+	movdqa	%xmm0,-32(%rbx,%rdx,1)
+	movdqa	%xmm0,-16(%rbx,%rdx,1)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-32(%rdi)
+	movdqu	%xmm5,-16(%rdi)
+	addq	$32,%r9
+	jnz	.Lsqr8x_cond_copy
 
-	addq	$32,%rax
-	jnz	.Lmulx4x_sub
-
-	movq	40(%rsp),%rsi
 	movq	$1,%rax
 	movq	-48(%rsi),%r15
 	movq	-40(%rsi),%r14
@@ -1048,8 +739,8 @@ bn_mulx4x_mont:
 	movq	-16(%rsi),%rbp
 	movq	-8(%rsi),%rbx
 	leaq	(%rsi),%rsp
-.Lmulx4x_epilogue:
+.Lsqr8x_epilogue:
 	.byte	0xf3,0xc3
-.size	bn_mulx4x_mont,.-bn_mulx4x_mont
+.size	bn_sqr8x_mont,.-bn_sqr8x_mont
 .byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	16

deps/openssl/asm/x64-elf-gas/modes/aesni-gcm-x86_64.s

@@ -1,753 +1,15 @@
 .text
 
-.type	_aesni_ctr32_ghash_6x,@function
-.align	32
-_aesni_ctr32_ghash_6x:
-	vmovdqu	32(%r11),%xmm2
-	subq	$6,%rdx
-	vpxor	%xmm4,%xmm4,%xmm4
-	vmovdqu	0-128(%rcx),%xmm15
-	vpaddb	%xmm2,%xmm1,%xmm10
-	vpaddb	%xmm2,%xmm10,%xmm11
-	vpaddb	%xmm2,%xmm11,%xmm12
-	vpaddb	%xmm2,%xmm12,%xmm13
-	vpaddb	%xmm2,%xmm13,%xmm14
-	vpxor	%xmm15,%xmm1,%xmm9
-	vmovdqu	%xmm4,16+8(%rsp)
-	jmp	.Loop6x
-
-.align	32
-.Loop6x:
-	addl	$100663296,%ebx
-	jc	.Lhandle_ctr32
-	vmovdqu	0-32(%r9),%xmm3
-	vpaddb	%xmm2,%xmm14,%xmm1
-	vpxor	%xmm15,%xmm10,%xmm10
-	vpxor	%xmm15,%xmm11,%xmm11
-
-.Lresume_ctr32:
-	vmovdqu	%xmm1,(%r8)
-	vpclmulqdq	$16,%xmm3,%xmm7,%xmm5
-	vpxor	%xmm15,%xmm12,%xmm12
-	vmovups	16-128(%rcx),%xmm2
-	vpclmulqdq	$1,%xmm3,%xmm7,%xmm6
-	xorq	%r12,%r12
-	cmpq	%r14,%r15
-
-	vaesenc	%xmm2,%xmm9,%xmm9
-	vmovdqu	48+8(%rsp),%xmm0
-	vpxor	%xmm15,%xmm13,%xmm13
-	vpclmulqdq	$0,%xmm3,%xmm7,%xmm1
-	vaesenc	%xmm2,%xmm10,%xmm10
-	vpxor	%xmm15,%xmm14,%xmm14
-	setnc	%r12b
-	vpclmulqdq	$17,%xmm3,%xmm7,%xmm7
-	vaesenc	%xmm2,%xmm11,%xmm11
-	vmovdqu	16-32(%r9),%xmm3
-	negq	%r12
-	vaesenc	%xmm2,%xmm12,%xmm12
-	vpxor	%xmm5,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm3,%xmm0,%xmm5
-	vpxor	%xmm4,%xmm8,%xmm8
-	vaesenc	%xmm2,%xmm13,%xmm13
-	vpxor	%xmm5,%xmm1,%xmm4
-	andq	$96,%r12
-	vmovups	32-128(%rcx),%xmm15
-	vpclmulqdq	$16,%xmm3,%xmm0,%xmm1
-	vaesenc	%xmm2,%xmm14,%xmm14
-
-	vpclmulqdq	$1,%xmm3,%xmm0,%xmm2
-	leaq	(%r14,%r12,1),%r14
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	16+8(%rsp),%xmm8,%xmm8
-	vpclmulqdq	$17,%xmm3,%xmm0,%xmm3
-	vmovdqu	64+8(%rsp),%xmm0
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	88(%r14),%r13
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	80(%r14),%r12
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,32+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,40+8(%rsp)
-	vmovdqu	48-32(%r9),%xmm5
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	48-128(%rcx),%xmm15
-	vpxor	%xmm1,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm5,%xmm0,%xmm1
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm5,%xmm0,%xmm2
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpxor	%xmm3,%xmm7,%xmm7
-	vpclmulqdq	$1,%xmm5,%xmm0,%xmm3
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vpclmulqdq	$17,%xmm5,%xmm0,%xmm5
-	vmovdqu	80+8(%rsp),%xmm0
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vpxor	%xmm1,%xmm4,%xmm4
-	vmovdqu	64-32(%r9),%xmm1
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	64-128(%rcx),%xmm15
-	vpxor	%xmm2,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm1,%xmm0,%xmm2
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm3,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm1,%xmm0,%xmm3
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	72(%r14),%r13
-	vpxor	%xmm5,%xmm7,%xmm7
-	vpclmulqdq	$1,%xmm1,%xmm0,%xmm5
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	64(%r14),%r12
-	vpclmulqdq	$17,%xmm1,%xmm0,%xmm1
-	vmovdqu	96+8(%rsp),%xmm0
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,48+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,56+8(%rsp)
-	vpxor	%xmm2,%xmm4,%xmm4
-	vmovdqu	96-32(%r9),%xmm2
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	80-128(%rcx),%xmm15
-	vpxor	%xmm3,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm2,%xmm0,%xmm3
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm5,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm2,%xmm0,%xmm5
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	56(%r14),%r13
-	vpxor	%xmm1,%xmm7,%xmm7
-	vpclmulqdq	$1,%xmm2,%xmm0,%xmm1
-	vpxor	112+8(%rsp),%xmm8,%xmm8
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	48(%r14),%r12
-	vpclmulqdq	$17,%xmm2,%xmm0,%xmm2
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,64+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,72+8(%rsp)
-	vpxor	%xmm3,%xmm4,%xmm4
-	vmovdqu	112-32(%r9),%xmm3
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	96-128(%rcx),%xmm15
-	vpxor	%xmm5,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm3,%xmm8,%xmm5
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm1,%xmm6,%xmm6
-	vpclmulqdq	$1,%xmm3,%xmm8,%xmm1
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	40(%r14),%r13
-	vpxor	%xmm2,%xmm7,%xmm7
-	vpclmulqdq	$0,%xmm3,%xmm8,%xmm2
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	32(%r14),%r12
-	vpclmulqdq	$17,%xmm3,%xmm8,%xmm8
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,80+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,88+8(%rsp)
-	vpxor	%xmm5,%xmm6,%xmm6
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vpxor	%xmm1,%xmm6,%xmm6
-
-	vmovups	112-128(%rcx),%xmm15
-	vpslldq	$8,%xmm6,%xmm5
-	vpxor	%xmm2,%xmm4,%xmm4
-	vmovdqu	16(%r11),%xmm3
-
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm8,%xmm7,%xmm7
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpxor	%xmm5,%xmm4,%xmm4
-	movbeq	24(%r14),%r13
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	16(%r14),%r12
-	vpalignr	$8,%xmm4,%xmm4,%xmm0
-	vpclmulqdq	$16,%xmm3,%xmm4,%xmm4
-	movq	%r13,96+8(%rsp)
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r12,104+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vmovups	128-128(%rcx),%xmm1
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	144-128(%rcx),%xmm15
-	vaesenc	%xmm1,%xmm10,%xmm10
-	vpsrldq	$8,%xmm6,%xmm6
-	vaesenc	%xmm1,%xmm11,%xmm11
-	vpxor	%xmm6,%xmm7,%xmm7
-	vaesenc	%xmm1,%xmm12,%xmm12
-	vpxor	%xmm0,%xmm4,%xmm4
-	movbeq	8(%r14),%r13
-	vaesenc	%xmm1,%xmm13,%xmm13
-	movbeq	0(%r14),%r12
-	vaesenc	%xmm1,%xmm14,%xmm14
-	vmovups	160-128(%rcx),%xmm1
-	cmpl	$11,%ebp
-	jb	.Lenc_tail
-
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vaesenc	%xmm1,%xmm10,%xmm10
-	vaesenc	%xmm1,%xmm11,%xmm11
-	vaesenc	%xmm1,%xmm12,%xmm12
-	vaesenc	%xmm1,%xmm13,%xmm13
-	vmovups	176-128(%rcx),%xmm15
-	vaesenc	%xmm1,%xmm14,%xmm14
-	vmovups	192-128(%rcx),%xmm1
-	je	.Lenc_tail
-
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vaesenc	%xmm1,%xmm10,%xmm10
-	vaesenc	%xmm1,%xmm11,%xmm11
-	vaesenc	%xmm1,%xmm12,%xmm12
-	vaesenc	%xmm1,%xmm13,%xmm13
-	vmovups	208-128(%rcx),%xmm15
-	vaesenc	%xmm1,%xmm14,%xmm14
-	vmovups	224-128(%rcx),%xmm1
-	jmp	.Lenc_tail
-
-.align	32
-.Lhandle_ctr32:
-	vmovdqu	(%r11),%xmm0
-	vpshufb	%xmm0,%xmm1,%xmm6
-	vmovdqu	48(%r11),%xmm5
-	vpaddd	64(%r11),%xmm6,%xmm10
-	vpaddd	%xmm5,%xmm6,%xmm11
-	vmovdqu	0-32(%r9),%xmm3
-	vpaddd	%xmm5,%xmm10,%xmm12
-	vpshufb	%xmm0,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm11,%xmm13
-	vpshufb	%xmm0,%xmm11,%xmm11
-	vpxor	%xmm15,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm12,%xmm14
-	vpshufb	%xmm0,%xmm12,%xmm12
-	vpxor	%xmm15,%xmm11,%xmm11
-	vpaddd	%xmm5,%xmm13,%xmm1
-	vpshufb	%xmm0,%xmm13,%xmm13
-	vpshufb	%xmm0,%xmm14,%xmm14
-	vpshufb	%xmm0,%xmm1,%xmm1
-	jmp	.Lresume_ctr32
-
-.align	32
-.Lenc_tail:
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vmovdqu	%xmm7,16+8(%rsp)
-	vpalignr	$8,%xmm4,%xmm4,%xmm8
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpclmulqdq	$16,%xmm3,%xmm4,%xmm4
-	vpxor	0(%rdi),%xmm1,%xmm2
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vpxor	16(%rdi),%xmm1,%xmm0
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vpxor	32(%rdi),%xmm1,%xmm5
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vpxor	48(%rdi),%xmm1,%xmm6
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vpxor	64(%rdi),%xmm1,%xmm7
-	vpxor	80(%rdi),%xmm1,%xmm3
-	vmovdqu	(%r8),%xmm1
-
-	vaesenclast	%xmm2,%xmm9,%xmm9
-	vmovdqu	32(%r11),%xmm2
-	vaesenclast	%xmm0,%xmm10,%xmm10
-	vpaddb	%xmm2,%xmm1,%xmm0
-	movq	%r13,112+8(%rsp)
-	leaq	96(%rdi),%rdi
-	vaesenclast	%xmm5,%xmm11,%xmm11
-	vpaddb	%xmm2,%xmm0,%xmm5
-	movq	%r12,120+8(%rsp)
-	leaq	96(%rsi),%rsi
-	vmovdqu	0-128(%rcx),%xmm15
-	vaesenclast	%xmm6,%xmm12,%xmm12
-	vpaddb	%xmm2,%xmm5,%xmm6
-	vaesenclast	%xmm7,%xmm13,%xmm13
-	vpaddb	%xmm2,%xmm6,%xmm7
-	vaesenclast	%xmm3,%xmm14,%xmm14
-	vpaddb	%xmm2,%xmm7,%xmm3
-
-	addq	$96,%r10
-	subq	$6,%rdx
-	jc	.L6x_done
-
-	vmovups	%xmm9,-96(%rsi)
-	vpxor	%xmm15,%xmm1,%xmm9
-	vmovups	%xmm10,-80(%rsi)
-	vmovdqa	%xmm0,%xmm10
-	vmovups	%xmm11,-64(%rsi)
-	vmovdqa	%xmm5,%xmm11
-	vmovups	%xmm12,-48(%rsi)
-	vmovdqa	%xmm6,%xmm12
-	vmovups	%xmm13,-32(%rsi)
-	vmovdqa	%xmm7,%xmm13
-	vmovups	%xmm14,-16(%rsi)
-	vmovdqa	%xmm3,%xmm14
-	vmovdqu	32+8(%rsp),%xmm7
-	jmp	.Loop6x
-
-.L6x_done:
-	vpxor	16+8(%rsp),%xmm8,%xmm8
-	vpxor	%xmm4,%xmm8,%xmm8
-
+.globl	aesni_gcm_encrypt
+.type	aesni_gcm_encrypt,@function
+aesni_gcm_encrypt:
+	xorl	%eax,%eax
 	.byte	0xf3,0xc3
-.size	_aesni_ctr32_ghash_6x,.-_aesni_ctr32_ghash_6x
+.size	aesni_gcm_encrypt,.-aesni_gcm_encrypt
+
 .globl	aesni_gcm_decrypt
 .type	aesni_gcm_decrypt,@function
-.align	32
 aesni_gcm_decrypt:
-	xorq	%r10,%r10
-	cmpq	$96,%rdx
-	jb	.Lgcm_dec_abort
-
-	leaq	(%rsp),%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-	vzeroupper
-
-	vmovdqu	(%r8),%xmm1
-	addq	$-128,%rsp
-	movl	12(%r8),%ebx
-	leaq	.Lbswap_mask(%rip),%r11
-	leaq	-128(%rcx),%r14
-	movq	$3968,%r15
-	vmovdqu	(%r9),%xmm8
-	andq	$-128,%rsp
-	vmovdqu	(%r11),%xmm0
-	leaq	128(%rcx),%rcx
-	leaq	32+32(%r9),%r9
-	movl	240-128(%rcx),%ebp
-	vpshufb	%xmm0,%xmm8,%xmm8
-
-	andq	%r15,%r14
-	andq	%rsp,%r15
-	subq	%r14,%r15
-	jc	.Ldec_no_key_aliasing
-	cmpq	$768,%r15
-	jnc	.Ldec_no_key_aliasing
-	subq	%r15,%rsp
-.Ldec_no_key_aliasing:
-
-	vmovdqu	80(%rdi),%xmm7
-	leaq	(%rdi),%r14
-	vmovdqu	64(%rdi),%xmm4
-	leaq	-192(%rdi,%rdx,1),%r15
-	vmovdqu	48(%rdi),%xmm5
-	shrq	$4,%rdx
-	xorq	%r10,%r10
-	vmovdqu	32(%rdi),%xmm6
-	vpshufb	%xmm0,%xmm7,%xmm7
-	vmovdqu	16(%rdi),%xmm2
-	vpshufb	%xmm0,%xmm4,%xmm4
-	vmovdqu	(%rdi),%xmm3
-	vpshufb	%xmm0,%xmm5,%xmm5
-	vmovdqu	%xmm4,48(%rsp)
-	vpshufb	%xmm0,%xmm6,%xmm6
-	vmovdqu	%xmm5,64(%rsp)
-	vpshufb	%xmm0,%xmm2,%xmm2
-	vmovdqu	%xmm6,80(%rsp)
-	vpshufb	%xmm0,%xmm3,%xmm3
-	vmovdqu	%xmm2,96(%rsp)
-	vmovdqu	%xmm3,112(%rsp)
-
-	call	_aesni_ctr32_ghash_6x
-
-	vmovups	%xmm9,-96(%rsi)
-	vmovups	%xmm10,-80(%rsi)
-	vmovups	%xmm11,-64(%rsi)
-	vmovups	%xmm12,-48(%rsi)
-	vmovups	%xmm13,-32(%rsi)
-	vmovups	%xmm14,-16(%rsi)
-
-	vpshufb	(%r11),%xmm8,%xmm8
-	vmovdqu	%xmm8,-64(%r9)
-
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-.Lgcm_dec_abort:
-	movq	%r10,%rax
+	xorl	%eax,%eax
 	.byte	0xf3,0xc3
 .size	aesni_gcm_decrypt,.-aesni_gcm_decrypt
-.type	_aesni_ctr32_6x,@function
-.align	32
-_aesni_ctr32_6x:
-	vmovdqu	0-128(%rcx),%xmm4
-	vmovdqu	32(%r11),%xmm2
-	leaq	-1(%rbp),%r13
-	vmovups	16-128(%rcx),%xmm15
-	leaq	32-128(%rcx),%r12
-	vpxor	%xmm4,%xmm1,%xmm9
-	addl	$100663296,%ebx
-	jc	.Lhandle_ctr32_2
-	vpaddb	%xmm2,%xmm1,%xmm10
-	vpaddb	%xmm2,%xmm10,%xmm11
-	vpxor	%xmm4,%xmm10,%xmm10
-	vpaddb	%xmm2,%xmm11,%xmm12
-	vpxor	%xmm4,%xmm11,%xmm11
-	vpaddb	%xmm2,%xmm12,%xmm13
-	vpxor	%xmm4,%xmm12,%xmm12
-	vpaddb	%xmm2,%xmm13,%xmm14
-	vpxor	%xmm4,%xmm13,%xmm13
-	vpaddb	%xmm2,%xmm14,%xmm1
-	vpxor	%xmm4,%xmm14,%xmm14
-	jmp	.Loop_ctr32
-
-.align	16
-.Loop_ctr32:
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vmovups	(%r12),%xmm15
-	leaq	16(%r12),%r12
-	decl	%r13d
-	jnz	.Loop_ctr32
-
-	vmovdqu	(%r12),%xmm3
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	0(%rdi),%xmm3,%xmm4
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpxor	16(%rdi),%xmm3,%xmm5
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vpxor	32(%rdi),%xmm3,%xmm6
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vpxor	48(%rdi),%xmm3,%xmm8
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vpxor	64(%rdi),%xmm3,%xmm2
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vpxor	80(%rdi),%xmm3,%xmm3
-	leaq	96(%rdi),%rdi
-
-	vaesenclast	%xmm4,%xmm9,%xmm9
-	vaesenclast	%xmm5,%xmm10,%xmm10
-	vaesenclast	%xmm6,%xmm11,%xmm11
-	vaesenclast	%xmm8,%xmm12,%xmm12
-	vaesenclast	%xmm2,%xmm13,%xmm13
-	vaesenclast	%xmm3,%xmm14,%xmm14
-	vmovups	%xmm9,0(%rsi)
-	vmovups	%xmm10,16(%rsi)
-	vmovups	%xmm11,32(%rsi)
-	vmovups	%xmm12,48(%rsi)
-	vmovups	%xmm13,64(%rsi)
-	vmovups	%xmm14,80(%rsi)
-	leaq	96(%rsi),%rsi
-
-	.byte	0xf3,0xc3
-.align	32
-.Lhandle_ctr32_2:
-	vpshufb	%xmm0,%xmm1,%xmm6
-	vmovdqu	48(%r11),%xmm5
-	vpaddd	64(%r11),%xmm6,%xmm10
-	vpaddd	%xmm5,%xmm6,%xmm11
-	vpaddd	%xmm5,%xmm10,%xmm12
-	vpshufb	%xmm0,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm11,%xmm13
-	vpshufb	%xmm0,%xmm11,%xmm11
-	vpxor	%xmm4,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm12,%xmm14
-	vpshufb	%xmm0,%xmm12,%xmm12
-	vpxor	%xmm4,%xmm11,%xmm11
-	vpaddd	%xmm5,%xmm13,%xmm1
-	vpshufb	%xmm0,%xmm13,%xmm13
-	vpxor	%xmm4,%xmm12,%xmm12
-	vpshufb	%xmm0,%xmm14,%xmm14
-	vpxor	%xmm4,%xmm13,%xmm13
-	vpshufb	%xmm0,%xmm1,%xmm1
-	vpxor	%xmm4,%xmm14,%xmm14
-	jmp	.Loop_ctr32
-.size	_aesni_ctr32_6x,.-_aesni_ctr32_6x
-
-.globl	aesni_gcm_encrypt
-.type	aesni_gcm_encrypt,@function
-.align	32
-aesni_gcm_encrypt:
-	xorq	%r10,%r10
-	cmpq	$288,%rdx
-	jb	.Lgcm_enc_abort
-
-	leaq	(%rsp),%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-	vzeroupper
-
-	vmovdqu	(%r8),%xmm1
-	addq	$-128,%rsp
-	movl	12(%r8),%ebx
-	leaq	.Lbswap_mask(%rip),%r11
-	leaq	-128(%rcx),%r14
-	movq	$3968,%r15
-	leaq	128(%rcx),%rcx
-	vmovdqu	(%r11),%xmm0
-	andq	$-128,%rsp
-	movl	240-128(%rcx),%ebp
-
-	andq	%r15,%r14
-	andq	%rsp,%r15
-	subq	%r14,%r15
-	jc	.Lenc_no_key_aliasing
-	cmpq	$768,%r15
-	jnc	.Lenc_no_key_aliasing
-	subq	%r15,%rsp
-.Lenc_no_key_aliasing:
-
-	leaq	(%rsi),%r14
-	leaq	-192(%rsi,%rdx,1),%r15
-	shrq	$4,%rdx
-
-	call	_aesni_ctr32_6x
-	vpshufb	%xmm0,%xmm9,%xmm8
-	vpshufb	%xmm0,%xmm10,%xmm2
-	vmovdqu	%xmm8,112(%rsp)
-	vpshufb	%xmm0,%xmm11,%xmm4
-	vmovdqu	%xmm2,96(%rsp)
-	vpshufb	%xmm0,%xmm12,%xmm5
-	vmovdqu	%xmm4,80(%rsp)
-	vpshufb	%xmm0,%xmm13,%xmm6
-	vmovdqu	%xmm5,64(%rsp)
-	vpshufb	%xmm0,%xmm14,%xmm7
-	vmovdqu	%xmm6,48(%rsp)
-
-	call	_aesni_ctr32_6x
-
-	vmovdqu	(%r9),%xmm8
-	leaq	32+32(%r9),%r9
-	subq	$12,%rdx
-	movq	$192,%r10
-	vpshufb	%xmm0,%xmm8,%xmm8
-
-	call	_aesni_ctr32_ghash_6x
-	vmovdqu	32(%rsp),%xmm7
-	vmovdqu	(%r11),%xmm0
-	vmovdqu	0-32(%r9),%xmm3
-	vpunpckhqdq	%xmm7,%xmm7,%xmm1
-	vmovdqu	32-32(%r9),%xmm15
-	vmovups	%xmm9,-96(%rsi)
-	vpshufb	%xmm0,%xmm9,%xmm9
-	vpxor	%xmm7,%xmm1,%xmm1
-	vmovups	%xmm10,-80(%rsi)
-	vpshufb	%xmm0,%xmm10,%xmm10
-	vmovups	%xmm11,-64(%rsi)
-	vpshufb	%xmm0,%xmm11,%xmm11
-	vmovups	%xmm12,-48(%rsi)
-	vpshufb	%xmm0,%xmm12,%xmm12
-	vmovups	%xmm13,-32(%rsi)
-	vpshufb	%xmm0,%xmm13,%xmm13
-	vmovups	%xmm14,-16(%rsi)
-	vpshufb	%xmm0,%xmm14,%xmm14
-	vmovdqu	%xmm9,16(%rsp)
-	vmovdqu	48(%rsp),%xmm6
-	vmovdqu	16-32(%r9),%xmm0
-	vpunpckhqdq	%xmm6,%xmm6,%xmm2
-	vpclmulqdq	$0,%xmm3,%xmm7,%xmm5
-	vpxor	%xmm6,%xmm2,%xmm2
-	vpclmulqdq	$17,%xmm3,%xmm7,%xmm7
-	vpclmulqdq	$0,%xmm15,%xmm1,%xmm1
-
-	vmovdqu	64(%rsp),%xmm9
-	vpclmulqdq	$0,%xmm0,%xmm6,%xmm4
-	vmovdqu	48-32(%r9),%xmm3
-	vpxor	%xmm5,%xmm4,%xmm4
-	vpunpckhqdq	%xmm9,%xmm9,%xmm5
-	vpclmulqdq	$17,%xmm0,%xmm6,%xmm6
-	vpxor	%xmm9,%xmm5,%xmm5
-	vpxor	%xmm7,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm15,%xmm2,%xmm2
-	vmovdqu	80-32(%r9),%xmm15
-	vpxor	%xmm1,%xmm2,%xmm2
-
-	vmovdqu	80(%rsp),%xmm1
-	vpclmulqdq	$0,%xmm3,%xmm9,%xmm7
-	vmovdqu	64-32(%r9),%xmm0
-	vpxor	%xmm4,%xmm7,%xmm7
-	vpunpckhqdq	%xmm1,%xmm1,%xmm4
-	vpclmulqdq	$17,%xmm3,%xmm9,%xmm9
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpxor	%xmm6,%xmm9,%xmm9
-	vpclmulqdq	$0,%xmm15,%xmm5,%xmm5
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	96(%rsp),%xmm2
-	vpclmulqdq	$0,%xmm0,%xmm1,%xmm6
-	vmovdqu	96-32(%r9),%xmm3
-	vpxor	%xmm7,%xmm6,%xmm6
-	vpunpckhqdq	%xmm2,%xmm2,%xmm7
-	vpclmulqdq	$17,%xmm0,%xmm1,%xmm1
-	vpxor	%xmm2,%xmm7,%xmm7
-	vpxor	%xmm9,%xmm1,%xmm1
-	vpclmulqdq	$16,%xmm15,%xmm4,%xmm4
-	vmovdqu	128-32(%r9),%xmm15
-	vpxor	%xmm5,%xmm4,%xmm4
-
-	vpxor	112(%rsp),%xmm8,%xmm8
-	vpclmulqdq	$0,%xmm3,%xmm2,%xmm5
-	vmovdqu	112-32(%r9),%xmm0
-	vpunpckhqdq	%xmm8,%xmm8,%xmm9
-	vpxor	%xmm6,%xmm5,%xmm5
-	vpclmulqdq	$17,%xmm3,%xmm2,%xmm2
-	vpxor	%xmm8,%xmm9,%xmm9
-	vpxor	%xmm1,%xmm2,%xmm2
-	vpclmulqdq	$0,%xmm15,%xmm7,%xmm7
-	vpxor	%xmm4,%xmm7,%xmm4
-
-	vpclmulqdq	$0,%xmm0,%xmm8,%xmm6
-	vmovdqu	0-32(%r9),%xmm3
-	vpunpckhqdq	%xmm14,%xmm14,%xmm1
-	vpclmulqdq	$17,%xmm0,%xmm8,%xmm8
-	vpxor	%xmm14,%xmm1,%xmm1
-	vpxor	%xmm5,%xmm6,%xmm5
-	vpclmulqdq	$16,%xmm15,%xmm9,%xmm9
-	vmovdqu	32-32(%r9),%xmm15
-	vpxor	%xmm2,%xmm8,%xmm7
-	vpxor	%xmm4,%xmm9,%xmm6
-
-	vmovdqu	16-32(%r9),%xmm0
-	vpxor	%xmm5,%xmm7,%xmm9
-	vpclmulqdq	$0,%xmm3,%xmm14,%xmm4
-	vpxor	%xmm9,%xmm6,%xmm6
-	vpunpckhqdq	%xmm13,%xmm13,%xmm2
-	vpclmulqdq	$17,%xmm3,%xmm14,%xmm14
-	vpxor	%xmm13,%xmm2,%xmm2
-	vpslldq	$8,%xmm6,%xmm9
-	vpclmulqdq	$0,%xmm15,%xmm1,%xmm1
-	vpxor	%xmm9,%xmm5,%xmm8
-	vpsrldq	$8,%xmm6,%xmm6
-	vpxor	%xmm6,%xmm7,%xmm7
-
-	vpclmulqdq	$0,%xmm0,%xmm13,%xmm5
-	vmovdqu	48-32(%r9),%xmm3
-	vpxor	%xmm4,%xmm5,%xmm5
-	vpunpckhqdq	%xmm12,%xmm12,%xmm9
-	vpclmulqdq	$17,%xmm0,%xmm13,%xmm13
-	vpxor	%xmm12,%xmm9,%xmm9
-	vpxor	%xmm14,%xmm13,%xmm13
-	vpalignr	$8,%xmm8,%xmm8,%xmm14
-	vpclmulqdq	$16,%xmm15,%xmm2,%xmm2
-	vmovdqu	80-32(%r9),%xmm15
-	vpxor	%xmm1,%xmm2,%xmm2
-
-	vpclmulqdq	$0,%xmm3,%xmm12,%xmm4
-	vmovdqu	64-32(%r9),%xmm0
-	vpxor	%xmm5,%xmm4,%xmm4
-	vpunpckhqdq	%xmm11,%xmm11,%xmm1
-	vpclmulqdq	$17,%xmm3,%xmm12,%xmm12
-	vpxor	%xmm11,%xmm1,%xmm1
-	vpxor	%xmm13,%xmm12,%xmm12
-	vxorps	16(%rsp),%xmm7,%xmm7
-	vpclmulqdq	$0,%xmm15,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm9,%xmm9
-
-	vpclmulqdq	$16,16(%r11),%xmm8,%xmm8
-	vxorps	%xmm14,%xmm8,%xmm8
-
-	vpclmulqdq	$0,%xmm0,%xmm11,%xmm5
-	vmovdqu	96-32(%r9),%xmm3
-	vpxor	%xmm4,%xmm5,%xmm5
-	vpunpckhqdq	%xmm10,%xmm10,%xmm2
-	vpclmulqdq	$17,%xmm0,%xmm11,%xmm11
-	vpxor	%xmm10,%xmm2,%xmm2
-	vpalignr	$8,%xmm8,%xmm8,%xmm14
-	vpxor	%xmm12,%xmm11,%xmm11
-	vpclmulqdq	$16,%xmm15,%xmm1,%xmm1
-	vmovdqu	128-32(%r9),%xmm15
-	vpxor	%xmm9,%xmm1,%xmm1
-
-	vxorps	%xmm7,%xmm14,%xmm14
-	vpclmulqdq	$16,16(%r11),%xmm8,%xmm8
-	vxorps	%xmm14,%xmm8,%xmm8
-
-	vpclmulqdq	$0,%xmm3,%xmm10,%xmm4
-	vmovdqu	112-32(%r9),%xmm0
-	vpxor	%xmm5,%xmm4,%xmm4
-	vpunpckhqdq	%xmm8,%xmm8,%xmm9
-	vpclmulqdq	$17,%xmm3,%xmm10,%xmm10
-	vpxor	%xmm8,%xmm9,%xmm9
-	vpxor	%xmm11,%xmm10,%xmm10
-	vpclmulqdq	$0,%xmm15,%xmm2,%xmm2
-	vpxor	%xmm1,%xmm2,%xmm2
-
-	vpclmulqdq	$0,%xmm0,%xmm8,%xmm5
-	vpclmulqdq	$17,%xmm0,%xmm8,%xmm7
-	vpxor	%xmm4,%xmm5,%xmm5
-	vpclmulqdq	$16,%xmm15,%xmm9,%xmm6
-	vpxor	%xmm10,%xmm7,%xmm7
-	vpxor	%xmm2,%xmm6,%xmm6
-
-	vpxor	%xmm5,%xmm7,%xmm4
-	vpxor	%xmm4,%xmm6,%xmm6
-	vpslldq	$8,%xmm6,%xmm1
-	vmovdqu	16(%r11),%xmm3
-	vpsrldq	$8,%xmm6,%xmm6
-	vpxor	%xmm1,%xmm5,%xmm8
-	vpxor	%xmm6,%xmm7,%xmm7
-
-	vpalignr	$8,%xmm8,%xmm8,%xmm2
-	vpclmulqdq	$16,%xmm3,%xmm8,%xmm8
-	vpxor	%xmm2,%xmm8,%xmm8
-
-	vpalignr	$8,%xmm8,%xmm8,%xmm2
-	vpclmulqdq	$16,%xmm3,%xmm8,%xmm8
-	vpxor	%xmm7,%xmm2,%xmm2
-	vpxor	%xmm2,%xmm8,%xmm8
-	vpshufb	(%r11),%xmm8,%xmm8
-	vmovdqu	%xmm8,-64(%r9)
-
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-.Lgcm_enc_abort:
-	movq	%r10,%rax
-	.byte	0xf3,0xc3
-.size	aesni_gcm_encrypt,.-aesni_gcm_encrypt
-.align	64
-.Lbswap_mask:
-.byte	15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0
-.Lpoly:
-.byte	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0xc2
-.Lone_msb:
-.byte	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
-.Ltwo_lsb:
-.byte	2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-.Lone_lsb:
-.byte	1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-.byte	65,69,83,45,78,73,32,71,67,77,32,109,111,100,117,108,101,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.align	64

deps/openssl/asm/x64-elf-gas/modes/ghash-x86_64.s

@@ -20,14 +20,14 @@ gcm_gmult_4bit:
 	movq	$14,%rcx
 	movq	8(%rsi,%rax,1),%r8
 	movq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	movq	%r8,%rdx
 	jmp	.Loop1
 
 .align	16
 .Loop1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	movb	(%rdi,%rcx,1),%al
 	shrq	$4,%r9
@@ -43,13 +43,13 @@ gcm_gmult_4bit:
 	js	.Lbreak1
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
@@ -58,19 +58,19 @@ gcm_gmult_4bit:
 .align	16
 .Lbreak1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rbx,1),%r8
@@ -661,10 +661,10 @@ gcm_ghash_4bit:
 gcm_init_clmul:
 .L_init_clmul:
 	movdqu	(%rsi),%xmm2
-	pshufd	$78,%xmm2,%xmm2
+	pshufd	$0b01001110,%xmm2,%xmm2
 
 
-	pshufd	$255,%xmm2,%xmm4
+	pshufd	$0b11111111,%xmm2,%xmm4
 	movdqa	%xmm2,%xmm3
 	psllq	$1,%xmm2
 	pxor	%xmm5,%xmm5
@@ -678,11 +678,11 @@ gcm_init_clmul:
 	pxor	%xmm5,%xmm2
 
 
-	pshufd	$78,%xmm2,%xmm6
+	pshufd	$0b01001110,%xmm2,%xmm6
 	movdqa	%xmm2,%xmm0
 	pxor	%xmm2,%xmm6
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -718,8 +718,8 @@ gcm_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm2,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm2,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm2,%xmm3
 	movdqu	%xmm2,0(%rdi)
 	pxor	%xmm0,%xmm4
@@ -727,7 +727,7 @@ gcm_init_clmul:
 .byte	102,15,58,15,227,8
 	movdqu	%xmm4,32(%rdi)
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -765,7 +765,7 @@ gcm_init_clmul:
 	pxor	%xmm1,%xmm0
 	movdqa	%xmm0,%xmm5
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -801,8 +801,8 @@ gcm_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm5,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm5,%xmm3
 	movdqu	%xmm5,48(%rdi)
 	pxor	%xmm0,%xmm4
@@ -822,7 +822,7 @@ gcm_gmult_clmul:
 	movdqu	32(%rsi),%xmm4
 .byte	102,15,56,0,197
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -874,20 +874,20 @@ gcm_ghash_clmul:
 	movdqu	32(%rsi),%xmm7
 .byte	102,65,15,56,0,194
 
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	.Lodd_tail
 
 	movdqu	16(%rsi),%xmm6
 	movl	OPENSSL_ia32cap_P+4(%rip),%eax
-	cmpq	$48,%rcx
+	cmpq	$0x30,%rcx
 	jb	.Lskip4x
 
 	andl	$71303168,%eax
 	cmpl	$4194304,%eax
 	je	.Lskip4x
 
-	subq	$48,%rcx
-	movq	$11547335547999543296,%rax
+	subq	$0x30,%rcx
+	movq	$0xA040608020C0E000,%rax
 	movdqu	48(%rsi),%xmm14
 	movdqu	64(%rsi),%xmm15
 
@@ -899,14 +899,14 @@ gcm_ghash_clmul:
 .byte	102,65,15,56,0,218
 .byte	102,69,15,56,0,218
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
 .byte	102,15,58,68,231,0
 
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm11,%xmm12
 .byte	102,68,15,58,68,222,0
 .byte	102,68,15,58,68,238,17
@@ -921,12 +921,12 @@ gcm_ghash_clmul:
 .byte	102,69,15,56,0,218
 .byte	102,69,15,56,0,194
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm8,%xmm0
 	pxor	%xmm11,%xmm12
 .byte	102,69,15,58,68,222,0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 .byte	102,69,15,58,68,238,17
 .byte	102,68,15,58,68,231,0
@@ -934,7 +934,7 @@ gcm_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jc	.Ltail4x
 
 	jmp	.Lmod4_loop
@@ -949,14 +949,14 @@ gcm_ghash_clmul:
 	movdqu	32(%rdx),%xmm3
 	movdqa	%xmm11,%xmm13
 .byte	102,68,15,58,68,199,16
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	xorps	%xmm5,%xmm1
 	pxor	%xmm11,%xmm12
 .byte	102,65,15,56,0,218
 	movups	32(%rsi),%xmm7
 	xorps	%xmm4,%xmm8
 .byte	102,68,15,58,68,218,0
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 
 	pxor	%xmm0,%xmm8
 	movdqa	%xmm3,%xmm5
@@ -1000,7 +1000,7 @@ gcm_ghash_clmul:
 
 	movdqa	%xmm11,%xmm13
 	pxor	%xmm12,%xmm4
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm9,%xmm0
 	pxor	%xmm8,%xmm1
 	pxor	%xmm11,%xmm12
@@ -1010,14 +1010,14 @@ gcm_ghash_clmul:
 	movdqa	%xmm0,%xmm1
 .byte	102,69,15,58,68,238,17
 	xorps	%xmm11,%xmm3
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 
 .byte	102,68,15,58,68,231,0
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jnc	.Lmod4_loop
 
 .Ltail4x:
@@ -1061,10 +1061,10 @@ gcm_ghash_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	addq	$64,%rcx
+	addq	$0x40,%rcx
 	jz	.Ldone
 	movdqu	32(%rsi),%xmm7
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	.Lodd_tail
 .Lskip4x:
 
@@ -1079,7 +1079,7 @@ gcm_ghash_clmul:
 	pxor	%xmm8,%xmm0
 
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
@@ -1087,7 +1087,7 @@ gcm_ghash_clmul:
 
 	leaq	32(%rdx),%rdx
 	nop
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	jbe	.Leven_tail
 	nop
 	jmp	.Lmod_loop
@@ -1096,7 +1096,7 @@ gcm_ghash_clmul:
 .Lmod_loop:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1134,7 +1134,7 @@ gcm_ghash_clmul:
 	pslldq	$8,%xmm0
 	psrldq	$8,%xmm8
 	pxor	%xmm9,%xmm0
-	pshufd	$78,%xmm5,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm4
 	pxor	%xmm8,%xmm1
 	pxor	%xmm5,%xmm4
 
@@ -1150,13 +1150,13 @@ gcm_ghash_clmul:
 .byte	102,15,58,68,231,0
 	pxor	%xmm1,%xmm0
 
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	ja	.Lmod_loop
 
 .Leven_tail:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1204,7 +1204,7 @@ gcm_ghash_clmul:
 .byte	102,69,15,56,0,194
 	pxor	%xmm8,%xmm0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -1249,108 +1249,7 @@ gcm_ghash_clmul:
 .type	gcm_init_avx,@function
 .align	32
 gcm_init_avx:
-	vzeroupper
-
-	vmovdqu	(%rsi),%xmm2
-	vpshufd	$78,%xmm2,%xmm2
-
-
-	vpshufd	$255,%xmm2,%xmm4
-	vpsrlq	$63,%xmm2,%xmm3
-	vpsllq	$1,%xmm2,%xmm2
-	vpxor	%xmm5,%xmm5,%xmm5
-	vpcmpgtd	%xmm4,%xmm5,%xmm5
-	vpslldq	$8,%xmm3,%xmm3
-	vpor	%xmm3,%xmm2,%xmm2
-
-
-	vpand	.L0x1c2_polynomial(%rip),%xmm5,%xmm5
-	vpxor	%xmm5,%xmm2,%xmm2
-
-	vpunpckhqdq	%xmm2,%xmm2,%xmm6
-	vmovdqa	%xmm2,%xmm0
-	vpxor	%xmm2,%xmm6,%xmm6
-	movq	$4,%r10
-	jmp	.Linit_start_avx
-.align	32
-.Linit_loop_avx:
-	vpalignr	$8,%xmm3,%xmm4,%xmm5
-	vmovdqu	%xmm5,-16(%rdi)
-	vpunpckhqdq	%xmm0,%xmm0,%xmm3
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm2,%xmm0,%xmm1
-	vpclmulqdq	$0,%xmm2,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm3,%xmm3
-	vpxor	%xmm0,%xmm1,%xmm4
-	vpxor	%xmm4,%xmm3,%xmm3
-
-	vpslldq	$8,%xmm3,%xmm4
-	vpsrldq	$8,%xmm3,%xmm3
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpxor	%xmm3,%xmm1,%xmm1
-	vpsllq	$57,%xmm0,%xmm3
-	vpsllq	$62,%xmm0,%xmm4
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpsllq	$63,%xmm0,%xmm3
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpslldq	$8,%xmm4,%xmm3
-	vpsrldq	$8,%xmm4,%xmm4
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpxor	%xmm4,%xmm1,%xmm1
-
-	vpsrlq	$1,%xmm0,%xmm4
-	vpxor	%xmm0,%xmm1,%xmm1
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$5,%xmm4,%xmm4
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$1,%xmm0,%xmm0
-	vpxor	%xmm1,%xmm0,%xmm0
-.Linit_start_avx:
-	vmovdqa	%xmm0,%xmm5
-	vpunpckhqdq	%xmm0,%xmm0,%xmm3
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm2,%xmm0,%xmm1
-	vpclmulqdq	$0,%xmm2,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm3,%xmm3
-	vpxor	%xmm0,%xmm1,%xmm4
-	vpxor	%xmm4,%xmm3,%xmm3
-
-	vpslldq	$8,%xmm3,%xmm4
-	vpsrldq	$8,%xmm3,%xmm3
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpxor	%xmm3,%xmm1,%xmm1
-	vpsllq	$57,%xmm0,%xmm3
-	vpsllq	$62,%xmm0,%xmm4
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpsllq	$63,%xmm0,%xmm3
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpslldq	$8,%xmm4,%xmm3
-	vpsrldq	$8,%xmm4,%xmm4
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpxor	%xmm4,%xmm1,%xmm1
-
-	vpsrlq	$1,%xmm0,%xmm4
-	vpxor	%xmm0,%xmm1,%xmm1
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$5,%xmm4,%xmm4
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$1,%xmm0,%xmm0
-	vpxor	%xmm1,%xmm0,%xmm0
-	vpshufd	$78,%xmm5,%xmm3
-	vpshufd	$78,%xmm0,%xmm4
-	vpxor	%xmm5,%xmm3,%xmm3
-	vmovdqu	%xmm5,0(%rdi)
-	vpxor	%xmm0,%xmm4,%xmm4
-	vmovdqu	%xmm0,16(%rdi)
-	leaq	48(%rdi),%rdi
-	subq	$1,%r10
-	jnz	.Linit_loop_avx
-
-	vpalignr	$8,%xmm4,%xmm3,%xmm5
-	vmovdqu	%xmm5,-16(%rdi)
-
-	vzeroupper
-	.byte	0xf3,0xc3
+	jmp	.L_init_clmul
 .size	gcm_init_avx,.-gcm_init_avx
 .globl	gcm_gmult_avx
 .type	gcm_gmult_avx,@function
@@ -1362,377 +1261,7 @@ gcm_gmult_avx:
 .type	gcm_ghash_avx,@function
 .align	32
 gcm_ghash_avx:
-	vzeroupper
-
-	vmovdqu	(%rdi),%xmm10
-	leaq	.L0x1c2_polynomial(%rip),%r10
-	leaq	64(%rsi),%rsi
-	vmovdqu	.Lbswap_mask(%rip),%xmm13
-	vpshufb	%xmm13,%xmm10,%xmm10
-	cmpq	$128,%rcx
-	jb	.Lshort_avx
-	subq	$128,%rcx
-
-	vmovdqu	112(%rdx),%xmm14
-	vmovdqu	0-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vmovdqu	32-64(%rsi),%xmm7
-
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vmovdqu	96(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	16-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vmovdqu	80(%rdx),%xmm14
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	48-64(%rsi),%xmm6
-	vpxor	%xmm14,%xmm9,%xmm9
-	vmovdqu	64(%rdx),%xmm15
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	80-64(%rsi),%xmm7
-
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	64-64(%rsi),%xmm6
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-
-	vmovdqu	48(%rdx),%xmm14
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	96-64(%rsi),%xmm6
-	vpxor	%xmm5,%xmm2,%xmm2
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	128-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-
-	vmovdqu	32(%rdx),%xmm15
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	112-64(%rsi),%xmm6
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-
-	vmovdqu	16(%rdx),%xmm14
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	144-64(%rsi),%xmm6
-	vpxor	%xmm5,%xmm2,%xmm2
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	176-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-
-	vmovdqu	(%rdx),%xmm15
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	160-64(%rsi),%xmm6
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$16,%xmm7,%xmm9,%xmm2
-
-	leaq	128(%rdx),%rdx
-	cmpq	$128,%rcx
-	jb	.Ltail_avx
-
-	vpxor	%xmm10,%xmm15,%xmm15
-	subq	$128,%rcx
-	jmp	.Loop8x_avx
-
-.align	32
-.Loop8x_avx:
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vmovdqu	112(%rdx),%xmm14
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpxor	%xmm15,%xmm8,%xmm8
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm10
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm11
-	vmovdqu	0-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm12
-	vmovdqu	32-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-
-	vmovdqu	96(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm3,%xmm10,%xmm10
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vxorps	%xmm4,%xmm11,%xmm11
-	vmovdqu	16-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm5,%xmm12,%xmm12
-	vxorps	%xmm15,%xmm8,%xmm8
-
-	vmovdqu	80(%rdx),%xmm14
-	vpxor	%xmm10,%xmm12,%xmm12
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpxor	%xmm11,%xmm12,%xmm12
-	vpslldq	$8,%xmm12,%xmm9
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vpsrldq	$8,%xmm12,%xmm12
-	vpxor	%xmm9,%xmm10,%xmm10
-	vmovdqu	48-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vxorps	%xmm12,%xmm11,%xmm11
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	80-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	64(%rdx),%xmm15
-	vpalignr	$8,%xmm10,%xmm10,%xmm12
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	64-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vxorps	%xmm15,%xmm8,%xmm8
-	vpxor	%xmm5,%xmm2,%xmm2
-
-	vmovdqu	48(%rdx),%xmm14
-	vpclmulqdq	$16,(%r10),%xmm10,%xmm10
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	96-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	128-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	32(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	112-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-	vpxor	%xmm5,%xmm2,%xmm2
-	vxorps	%xmm12,%xmm10,%xmm10
-
-	vmovdqu	16(%rdx),%xmm14
-	vpalignr	$8,%xmm10,%xmm10,%xmm12
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	144-64(%rsi),%xmm6
-	vpclmulqdq	$16,(%r10),%xmm10,%xmm10
-	vxorps	%xmm11,%xmm12,%xmm12
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	176-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	160-64(%rsi),%xmm6
-	vpxor	%xmm12,%xmm15,%xmm15
-	vpclmulqdq	$16,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm10,%xmm15,%xmm15
-
-	leaq	128(%rdx),%rdx
-	subq	$128,%rcx
-	jnc	.Loop8x_avx
-
-	addq	$128,%rcx
-	jmp	.Ltail_no_xor_avx
-
-.align	32
-.Lshort_avx:
-	vmovdqu	-16(%rdx,%rcx,1),%xmm14
-	leaq	(%rdx,%rcx,1),%rdx
-	vmovdqu	0-64(%rsi),%xmm6
-	vmovdqu	32-64(%rsi),%xmm7
-	vpshufb	%xmm13,%xmm14,%xmm15
-
-	vmovdqa	%xmm0,%xmm3
-	vmovdqa	%xmm1,%xmm4
-	vmovdqa	%xmm2,%xmm5
-	subq	$16,%rcx
-	jz	.Ltail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-32(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	16-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vpsrldq	$8,%xmm7,%xmm7
-	subq	$16,%rcx
-	jz	.Ltail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-48(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	48-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vmovdqu	80-64(%rsi),%xmm7
-	subq	$16,%rcx
-	jz	.Ltail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-64(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	64-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vpsrldq	$8,%xmm7,%xmm7
-	subq	$16,%rcx
-	jz	.Ltail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-80(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	96-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vmovdqu	128-64(%rsi),%xmm7
-	subq	$16,%rcx
-	jz	.Ltail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-96(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	112-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vpsrldq	$8,%xmm7,%xmm7
-	subq	$16,%rcx
-	jz	.Ltail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-112(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	144-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vmovq	184-64(%rsi),%xmm7
-	subq	$16,%rcx
-	jmp	.Ltail_avx
-
-.align	32
-.Ltail_avx:
-	vpxor	%xmm10,%xmm15,%xmm15
-.Ltail_no_xor_avx:
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-
-	vmovdqu	(%r10),%xmm12
-
-	vpxor	%xmm0,%xmm3,%xmm10
-	vpxor	%xmm1,%xmm4,%xmm11
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vpxor	%xmm10,%xmm5,%xmm5
-	vpxor	%xmm11,%xmm5,%xmm5
-	vpslldq	$8,%xmm5,%xmm9
-	vpsrldq	$8,%xmm5,%xmm5
-	vpxor	%xmm9,%xmm10,%xmm10
-	vpxor	%xmm5,%xmm11,%xmm11
-
-	vpclmulqdq	$16,%xmm12,%xmm10,%xmm9
-	vpalignr	$8,%xmm10,%xmm10,%xmm10
-	vpxor	%xmm9,%xmm10,%xmm10
-
-	vpclmulqdq	$16,%xmm12,%xmm10,%xmm9
-	vpalignr	$8,%xmm10,%xmm10,%xmm10
-	vpxor	%xmm11,%xmm10,%xmm10
-	vpxor	%xmm9,%xmm10,%xmm10
-
-	cmpq	$0,%rcx
-	jne	.Lshort_avx
-
-	vpshufb	%xmm13,%xmm10,%xmm10
-	vmovdqu	%xmm10,(%rdi)
-	vzeroupper
-	.byte	0xf3,0xc3
+	jmp	.L_ghash_clmul
 .size	gcm_ghash_avx,.-gcm_ghash_avx
 .align	64
 .Lbswap_mask:

deps/openssl/asm/x64-macosx-gas/aes/aesni-mb-x86_64.s

@@ -6,14 +6,6 @@
 
 .p2align	5
 _aesni_multi_cbc_encrypt:
-	cmpl	$2,%edx
-	jb	L$enc_non_avx
-	movl	_OPENSSL_ia32cap_P+4(%rip),%ecx
-	testl	$268435456,%ecx
-	jnz	_avx_cbc_enc_shortcut
-	jmp	L$enc_non_avx
-.p2align	4
-L$enc_non_avx:
 	movq	%rsp,%rax
 	pushq	%rbx
 	pushq	%rbp
@@ -270,14 +262,6 @@ L$enc4x_epilogue:
 
 .p2align	5
 _aesni_multi_cbc_decrypt:
-	cmpl	$2,%edx
-	jb	L$dec_non_avx
-	movl	_OPENSSL_ia32cap_P+4(%rip),%ecx
-	testl	$268435456,%ecx
-	jnz	_avx_cbc_dec_shortcut
-	jmp	L$dec_non_avx
-.p2align	4
-L$dec_non_avx:
 	movq	%rsp,%rax
 	pushq	%rbx
 	pushq	%rbp
@@ -519,916 +503,3 @@ L$dec4x_done:
 	leaq	(%rax),%rsp
 L$dec4x_epilogue:
 	.byte	0xf3,0xc3
-
-
-.p2align	5
-aesni_multi_cbc_encrypt_avx:
-_avx_cbc_enc_shortcut:
-	movq	%rsp,%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-
-
-
-
-
-
-
-
-	subq	$192,%rsp
-	andq	$-128,%rsp
-	movq	%rax,16(%rsp)
-
-L$enc8x_body:
-	vzeroupper
-	vmovdqu	(%rsi),%xmm15
-	leaq	120(%rsi),%rsi
-	leaq	160(%rdi),%rdi
-	shrl	$1,%edx
-
-L$enc8x_loop_grande:
-
-	xorl	%edx,%edx
-	movl	-144(%rdi),%ecx
-	movq	-160(%rdi),%r8
-	cmpl	%edx,%ecx
-	movq	-152(%rdi),%rbx
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-136(%rdi),%xmm2
-	movl	%ecx,32(%rsp)
-	cmovleq	%rsp,%r8
-	subq	%r8,%rbx
-	movq	%rbx,64(%rsp)
-	movl	-104(%rdi),%ecx
-	movq	-120(%rdi),%r9
-	cmpl	%edx,%ecx
-	movq	-112(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-96(%rdi),%xmm3
-	movl	%ecx,36(%rsp)
-	cmovleq	%rsp,%r9
-	subq	%r9,%rbp
-	movq	%rbp,72(%rsp)
-	movl	-64(%rdi),%ecx
-	movq	-80(%rdi),%r10
-	cmpl	%edx,%ecx
-	movq	-72(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-56(%rdi),%xmm4
-	movl	%ecx,40(%rsp)
-	cmovleq	%rsp,%r10
-	subq	%r10,%rbp
-	movq	%rbp,80(%rsp)
-	movl	-24(%rdi),%ecx
-	movq	-40(%rdi),%r11
-	cmpl	%edx,%ecx
-	movq	-32(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-16(%rdi),%xmm5
-	movl	%ecx,44(%rsp)
-	cmovleq	%rsp,%r11
-	subq	%r11,%rbp
-	movq	%rbp,88(%rsp)
-	movl	16(%rdi),%ecx
-	movq	0(%rdi),%r12
-	cmpl	%edx,%ecx
-	movq	8(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	24(%rdi),%xmm6
-	movl	%ecx,48(%rsp)
-	cmovleq	%rsp,%r12
-	subq	%r12,%rbp
-	movq	%rbp,96(%rsp)
-	movl	56(%rdi),%ecx
-	movq	40(%rdi),%r13
-	cmpl	%edx,%ecx
-	movq	48(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	64(%rdi),%xmm7
-	movl	%ecx,52(%rsp)
-	cmovleq	%rsp,%r13
-	subq	%r13,%rbp
-	movq	%rbp,104(%rsp)
-	movl	96(%rdi),%ecx
-	movq	80(%rdi),%r14
-	cmpl	%edx,%ecx
-	movq	88(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	104(%rdi),%xmm8
-	movl	%ecx,56(%rsp)
-	cmovleq	%rsp,%r14
-	subq	%r14,%rbp
-	movq	%rbp,112(%rsp)
-	movl	136(%rdi),%ecx
-	movq	120(%rdi),%r15
-	cmpl	%edx,%ecx
-	movq	128(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	144(%rdi),%xmm9
-	movl	%ecx,60(%rsp)
-	cmovleq	%rsp,%r15
-	subq	%r15,%rbp
-	movq	%rbp,120(%rsp)
-	testl	%edx,%edx
-	jz	L$enc8x_done
-
-	vmovups	16-120(%rsi),%xmm1
-	vmovups	32-120(%rsi),%xmm0
-	movl	240-120(%rsi),%eax
-
-	vpxor	(%r8),%xmm15,%xmm10
-	leaq	128(%rsp),%rbp
-	vpxor	(%r9),%xmm15,%xmm11
-	vpxor	(%r10),%xmm15,%xmm12
-	vpxor	(%r11),%xmm15,%xmm13
-	vpxor	%xmm10,%xmm2,%xmm2
-	vpxor	(%r12),%xmm15,%xmm10
-	vpxor	%xmm11,%xmm3,%xmm3
-	vpxor	(%r13),%xmm15,%xmm11
-	vpxor	%xmm12,%xmm4,%xmm4
-	vpxor	(%r14),%xmm15,%xmm12
-	vpxor	%xmm13,%xmm5,%xmm5
-	vpxor	(%r15),%xmm15,%xmm13
-	vpxor	%xmm10,%xmm6,%xmm6
-	movl	$1,%ecx
-	vpxor	%xmm11,%xmm7,%xmm7
-	vpxor	%xmm12,%xmm8,%xmm8
-	vpxor	%xmm13,%xmm9,%xmm9
-	jmp	L$oop_enc8x
-
-.p2align	5
-L$oop_enc8x:
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+0(%rsp),%ecx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r8)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r8,%rbx,1),%rbx
-	cmovgeq	%rsp,%r8
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r8,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r8),%xmm15,%xmm10
-	movq	%rbx,64+0(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	-72(%rsi),%xmm1
-	leaq	16(%r8,%rbx,1),%r8
-	vmovdqu	%xmm10,0(%rbp)
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+4(%rsp),%ecx
-	movq	64+8(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r9)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%r9,%rbx,1),%rbx
-	cmovgeq	%rsp,%r9
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r9,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r9),%xmm15,%xmm11
-	movq	%rbx,64+8(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	-56(%rsi),%xmm0
-	leaq	16(%r9,%rbx,1),%r9
-	vmovdqu	%xmm11,16(%rbp)
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+8(%rsp),%ecx
-	movq	64+16(%rsp),%rbx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r10)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r8)
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r10,%rbx,1),%rbx
-	cmovgeq	%rsp,%r10
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r10,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r10),%xmm15,%xmm12
-	movq	%rbx,64+16(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	-40(%rsi),%xmm1
-	leaq	16(%r10,%rbx,1),%r10
-	vmovdqu	%xmm12,32(%rbp)
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+12(%rsp),%ecx
-	movq	64+24(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r11)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r9)
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%r11,%rbx,1),%rbx
-	cmovgeq	%rsp,%r11
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r11,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r11),%xmm15,%xmm13
-	movq	%rbx,64+24(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	-24(%rsi),%xmm0
-	leaq	16(%r11,%rbx,1),%r11
-	vmovdqu	%xmm13,48(%rbp)
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+16(%rsp),%ecx
-	movq	64+32(%rsp),%rbx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r12)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r10)
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r12,%rbx,1),%rbx
-	cmovgeq	%rsp,%r12
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r12,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r12),%xmm15,%xmm10
-	movq	%rbx,64+32(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	-8(%rsi),%xmm1
-	leaq	16(%r12,%rbx,1),%r12
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+20(%rsp),%ecx
-	movq	64+40(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r13)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r11)
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%rbx,%r13,1),%rbx
-	cmovgeq	%rsp,%r13
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r13,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r13),%xmm15,%xmm11
-	movq	%rbx,64+40(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	8(%rsi),%xmm0
-	leaq	16(%r13,%rbx,1),%r13
-	vaesenc	%xmm1,%xmm2,%xmm2
-	cmpl	32+24(%rsp),%ecx
-	movq	64+48(%rsp),%rbx
-	vaesenc	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r14)
-	vaesenc	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r12)
-	vaesenc	%xmm1,%xmm5,%xmm5
-	leaq	(%r14,%rbx,1),%rbx
-	cmovgeq	%rsp,%r14
-	vaesenc	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm1,%xmm7,%xmm7
-	subq	%r14,%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vpxor	16(%r14),%xmm15,%xmm12
-	movq	%rbx,64+48(%rsp)
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	24(%rsi),%xmm1
-	leaq	16(%r14,%rbx,1),%r14
-	vaesenc	%xmm0,%xmm2,%xmm2
-	cmpl	32+28(%rsp),%ecx
-	movq	64+56(%rsp),%rbx
-	vaesenc	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r15)
-	vaesenc	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r13)
-	vaesenc	%xmm0,%xmm5,%xmm5
-	leaq	(%r15,%rbx,1),%rbx
-	cmovgeq	%rsp,%r15
-	vaesenc	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesenc	%xmm0,%xmm7,%xmm7
-	subq	%r15,%rbx
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vpxor	16(%r15),%xmm15,%xmm13
-	movq	%rbx,64+56(%rsp)
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	40(%rsi),%xmm0
-	leaq	16(%r15,%rbx,1),%r15
-	vmovdqu	32(%rsp),%xmm14
-	prefetcht0	15(%r14)
-	prefetcht0	15(%r15)
-	cmpl	$11,%eax
-	jb	L$enc8x_tail
-
-	vaesenc	%xmm1,%xmm2,%xmm2
-	vaesenc	%xmm1,%xmm3,%xmm3
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vaesenc	%xmm1,%xmm5,%xmm5
-	vaesenc	%xmm1,%xmm6,%xmm6
-	vaesenc	%xmm1,%xmm7,%xmm7
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	176-120(%rsi),%xmm1
-
-	vaesenc	%xmm0,%xmm2,%xmm2
-	vaesenc	%xmm0,%xmm3,%xmm3
-	vaesenc	%xmm0,%xmm4,%xmm4
-	vaesenc	%xmm0,%xmm5,%xmm5
-	vaesenc	%xmm0,%xmm6,%xmm6
-	vaesenc	%xmm0,%xmm7,%xmm7
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	192-120(%rsi),%xmm0
-	je	L$enc8x_tail
-
-	vaesenc	%xmm1,%xmm2,%xmm2
-	vaesenc	%xmm1,%xmm3,%xmm3
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vaesenc	%xmm1,%xmm5,%xmm5
-	vaesenc	%xmm1,%xmm6,%xmm6
-	vaesenc	%xmm1,%xmm7,%xmm7
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	208-120(%rsi),%xmm1
-
-	vaesenc	%xmm0,%xmm2,%xmm2
-	vaesenc	%xmm0,%xmm3,%xmm3
-	vaesenc	%xmm0,%xmm4,%xmm4
-	vaesenc	%xmm0,%xmm5,%xmm5
-	vaesenc	%xmm0,%xmm6,%xmm6
-	vaesenc	%xmm0,%xmm7,%xmm7
-	vaesenc	%xmm0,%xmm8,%xmm8
-	vaesenc	%xmm0,%xmm9,%xmm9
-	vmovups	224-120(%rsi),%xmm0
-
-L$enc8x_tail:
-	vaesenc	%xmm1,%xmm2,%xmm2
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesenc	%xmm1,%xmm3,%xmm3
-	vaesenc	%xmm1,%xmm4,%xmm4
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesenc	%xmm1,%xmm5,%xmm5
-	vaesenc	%xmm1,%xmm6,%xmm6
-	vpaddd	%xmm14,%xmm15,%xmm15
-	vmovdqu	48(%rsp),%xmm14
-	vaesenc	%xmm1,%xmm7,%xmm7
-	movq	64(%rsp),%rbx
-	vaesenc	%xmm1,%xmm8,%xmm8
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	16-120(%rsi),%xmm1
-
-	vaesenclast	%xmm0,%xmm2,%xmm2
-	vmovdqa	%xmm15,32(%rsp)
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesenclast	%xmm0,%xmm3,%xmm3
-	vaesenclast	%xmm0,%xmm4,%xmm4
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesenclast	%xmm0,%xmm5,%xmm5
-	vaesenclast	%xmm0,%xmm6,%xmm6
-	vpaddd	%xmm15,%xmm14,%xmm14
-	vmovdqu	-120(%rsi),%xmm15
-	vaesenclast	%xmm0,%xmm7,%xmm7
-	vaesenclast	%xmm0,%xmm8,%xmm8
-	vmovdqa	%xmm14,48(%rsp)
-	vaesenclast	%xmm0,%xmm9,%xmm9
-	vmovups	32-120(%rsi),%xmm0
-
-	vmovups	%xmm2,-16(%r8)
-	subq	%rbx,%r8
-	vpxor	0(%rbp),%xmm2,%xmm2
-	vmovups	%xmm3,-16(%r9)
-	subq	72(%rsp),%r9
-	vpxor	16(%rbp),%xmm3,%xmm3
-	vmovups	%xmm4,-16(%r10)
-	subq	80(%rsp),%r10
-	vpxor	32(%rbp),%xmm4,%xmm4
-	vmovups	%xmm5,-16(%r11)
-	subq	88(%rsp),%r11
-	vpxor	48(%rbp),%xmm5,%xmm5
-	vmovups	%xmm6,-16(%r12)
-	subq	96(%rsp),%r12
-	vpxor	%xmm10,%xmm6,%xmm6
-	vmovups	%xmm7,-16(%r13)
-	subq	104(%rsp),%r13
-	vpxor	%xmm11,%xmm7,%xmm7
-	vmovups	%xmm8,-16(%r14)
-	subq	112(%rsp),%r14
-	vpxor	%xmm12,%xmm8,%xmm8
-	vmovups	%xmm9,-16(%r15)
-	subq	120(%rsp),%r15
-	vpxor	%xmm13,%xmm9,%xmm9
-
-	decl	%edx
-	jnz	L$oop_enc8x
-
-	movq	16(%rsp),%rax
-
-
-
-
-
-L$enc8x_done:
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-L$enc8x_epilogue:
-	.byte	0xf3,0xc3
-
-
-
-.p2align	5
-aesni_multi_cbc_decrypt_avx:
-_avx_cbc_dec_shortcut:
-	movq	%rsp,%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-
-
-
-
-
-
-
-
-
-	subq	$256,%rsp
-	andq	$-256,%rsp
-	subq	$192,%rsp
-	movq	%rax,16(%rsp)
-
-L$dec8x_body:
-	vzeroupper
-	vmovdqu	(%rsi),%xmm15
-	leaq	120(%rsi),%rsi
-	leaq	160(%rdi),%rdi
-	shrl	$1,%edx
-
-L$dec8x_loop_grande:
-
-	xorl	%edx,%edx
-	movl	-144(%rdi),%ecx
-	movq	-160(%rdi),%r8
-	cmpl	%edx,%ecx
-	movq	-152(%rdi),%rbx
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-136(%rdi),%xmm2
-	movl	%ecx,32(%rsp)
-	cmovleq	%rsp,%r8
-	subq	%r8,%rbx
-	movq	%rbx,64(%rsp)
-	vmovdqu	%xmm2,192(%rsp)
-	movl	-104(%rdi),%ecx
-	movq	-120(%rdi),%r9
-	cmpl	%edx,%ecx
-	movq	-112(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-96(%rdi),%xmm3
-	movl	%ecx,36(%rsp)
-	cmovleq	%rsp,%r9
-	subq	%r9,%rbp
-	movq	%rbp,72(%rsp)
-	vmovdqu	%xmm3,208(%rsp)
-	movl	-64(%rdi),%ecx
-	movq	-80(%rdi),%r10
-	cmpl	%edx,%ecx
-	movq	-72(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-56(%rdi),%xmm4
-	movl	%ecx,40(%rsp)
-	cmovleq	%rsp,%r10
-	subq	%r10,%rbp
-	movq	%rbp,80(%rsp)
-	vmovdqu	%xmm4,224(%rsp)
-	movl	-24(%rdi),%ecx
-	movq	-40(%rdi),%r11
-	cmpl	%edx,%ecx
-	movq	-32(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	-16(%rdi),%xmm5
-	movl	%ecx,44(%rsp)
-	cmovleq	%rsp,%r11
-	subq	%r11,%rbp
-	movq	%rbp,88(%rsp)
-	vmovdqu	%xmm5,240(%rsp)
-	movl	16(%rdi),%ecx
-	movq	0(%rdi),%r12
-	cmpl	%edx,%ecx
-	movq	8(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	24(%rdi),%xmm6
-	movl	%ecx,48(%rsp)
-	cmovleq	%rsp,%r12
-	subq	%r12,%rbp
-	movq	%rbp,96(%rsp)
-	vmovdqu	%xmm6,256(%rsp)
-	movl	56(%rdi),%ecx
-	movq	40(%rdi),%r13
-	cmpl	%edx,%ecx
-	movq	48(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	64(%rdi),%xmm7
-	movl	%ecx,52(%rsp)
-	cmovleq	%rsp,%r13
-	subq	%r13,%rbp
-	movq	%rbp,104(%rsp)
-	vmovdqu	%xmm7,272(%rsp)
-	movl	96(%rdi),%ecx
-	movq	80(%rdi),%r14
-	cmpl	%edx,%ecx
-	movq	88(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	104(%rdi),%xmm8
-	movl	%ecx,56(%rsp)
-	cmovleq	%rsp,%r14
-	subq	%r14,%rbp
-	movq	%rbp,112(%rsp)
-	vmovdqu	%xmm8,288(%rsp)
-	movl	136(%rdi),%ecx
-	movq	120(%rdi),%r15
-	cmpl	%edx,%ecx
-	movq	128(%rdi),%rbp
-	cmovgl	%ecx,%edx
-	testl	%ecx,%ecx
-	vmovdqu	144(%rdi),%xmm9
-	movl	%ecx,60(%rsp)
-	cmovleq	%rsp,%r15
-	subq	%r15,%rbp
-	movq	%rbp,120(%rsp)
-	vmovdqu	%xmm9,304(%rsp)
-	testl	%edx,%edx
-	jz	L$dec8x_done
-
-	vmovups	16-120(%rsi),%xmm1
-	vmovups	32-120(%rsi),%xmm0
-	movl	240-120(%rsi),%eax
-	leaq	192+128(%rsp),%rbp
-
-	vmovdqu	(%r8),%xmm2
-	vmovdqu	(%r9),%xmm3
-	vmovdqu	(%r10),%xmm4
-	vmovdqu	(%r11),%xmm5
-	vmovdqu	(%r12),%xmm6
-	vmovdqu	(%r13),%xmm7
-	vmovdqu	(%r14),%xmm8
-	vmovdqu	(%r15),%xmm9
-	vmovdqu	%xmm2,0(%rbp)
-	vpxor	%xmm15,%xmm2,%xmm2
-	vmovdqu	%xmm3,16(%rbp)
-	vpxor	%xmm15,%xmm3,%xmm3
-	vmovdqu	%xmm4,32(%rbp)
-	vpxor	%xmm15,%xmm4,%xmm4
-	vmovdqu	%xmm5,48(%rbp)
-	vpxor	%xmm15,%xmm5,%xmm5
-	vmovdqu	%xmm6,64(%rbp)
-	vpxor	%xmm15,%xmm6,%xmm6
-	vmovdqu	%xmm7,80(%rbp)
-	vpxor	%xmm15,%xmm7,%xmm7
-	vmovdqu	%xmm8,96(%rbp)
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	%xmm9,112(%rbp)
-	vpxor	%xmm15,%xmm9,%xmm9
-	xorq	$128,%rbp
-	movl	$1,%ecx
-	jmp	L$oop_dec8x
-
-.p2align	5
-L$oop_dec8x:
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+0(%rsp),%ecx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r8)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r8,%rbx,1),%rbx
-	cmovgeq	%rsp,%r8
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r8,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r8),%xmm10
-	movq	%rbx,64+0(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	-72(%rsi),%xmm1
-	leaq	16(%r8,%rbx,1),%r8
-	vmovdqu	%xmm10,128(%rsp)
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+4(%rsp),%ecx
-	movq	64+8(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r9)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%r9,%rbx,1),%rbx
-	cmovgeq	%rsp,%r9
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r9,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r9),%xmm11
-	movq	%rbx,64+8(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	-56(%rsi),%xmm0
-	leaq	16(%r9,%rbx,1),%r9
-	vmovdqu	%xmm11,144(%rsp)
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+8(%rsp),%ecx
-	movq	64+16(%rsp),%rbx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r10)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r8)
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r10,%rbx,1),%rbx
-	cmovgeq	%rsp,%r10
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r10,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r10),%xmm12
-	movq	%rbx,64+16(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	-40(%rsi),%xmm1
-	leaq	16(%r10,%rbx,1),%r10
-	vmovdqu	%xmm12,160(%rsp)
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+12(%rsp),%ecx
-	movq	64+24(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r11)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r9)
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%r11,%rbx,1),%rbx
-	cmovgeq	%rsp,%r11
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r11,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r11),%xmm13
-	movq	%rbx,64+24(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	-24(%rsi),%xmm0
-	leaq	16(%r11,%rbx,1),%r11
-	vmovdqu	%xmm13,176(%rsp)
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+16(%rsp),%ecx
-	movq	64+32(%rsp),%rbx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r12)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r10)
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r12,%rbx,1),%rbx
-	cmovgeq	%rsp,%r12
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r12,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r12),%xmm10
-	movq	%rbx,64+32(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	-8(%rsi),%xmm1
-	leaq	16(%r12,%rbx,1),%r12
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+20(%rsp),%ecx
-	movq	64+40(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r13)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r11)
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%rbx,%r13,1),%rbx
-	cmovgeq	%rsp,%r13
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r13,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r13),%xmm11
-	movq	%rbx,64+40(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	8(%rsi),%xmm0
-	leaq	16(%r13,%rbx,1),%r13
-	vaesdec	%xmm1,%xmm2,%xmm2
-	cmpl	32+24(%rsp),%ecx
-	movq	64+48(%rsp),%rbx
-	vaesdec	%xmm1,%xmm3,%xmm3
-	prefetcht0	31(%r14)
-	vaesdec	%xmm1,%xmm4,%xmm4
-	prefetcht0	15(%r12)
-	vaesdec	%xmm1,%xmm5,%xmm5
-	leaq	(%r14,%rbx,1),%rbx
-	cmovgeq	%rsp,%r14
-	vaesdec	%xmm1,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm1,%xmm7,%xmm7
-	subq	%r14,%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vmovdqu	16(%r14),%xmm12
-	movq	%rbx,64+48(%rsp)
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	24(%rsi),%xmm1
-	leaq	16(%r14,%rbx,1),%r14
-	vaesdec	%xmm0,%xmm2,%xmm2
-	cmpl	32+28(%rsp),%ecx
-	movq	64+56(%rsp),%rbx
-	vaesdec	%xmm0,%xmm3,%xmm3
-	prefetcht0	31(%r15)
-	vaesdec	%xmm0,%xmm4,%xmm4
-	prefetcht0	15(%r13)
-	vaesdec	%xmm0,%xmm5,%xmm5
-	leaq	(%r15,%rbx,1),%rbx
-	cmovgeq	%rsp,%r15
-	vaesdec	%xmm0,%xmm6,%xmm6
-	cmovgq	%rsp,%rbx
-	vaesdec	%xmm0,%xmm7,%xmm7
-	subq	%r15,%rbx
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vmovdqu	16(%r15),%xmm13
-	movq	%rbx,64+56(%rsp)
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	40(%rsi),%xmm0
-	leaq	16(%r15,%rbx,1),%r15
-	vmovdqu	32(%rsp),%xmm14
-	prefetcht0	15(%r14)
-	prefetcht0	15(%r15)
-	cmpl	$11,%eax
-	jb	L$dec8x_tail
-
-	vaesdec	%xmm1,%xmm2,%xmm2
-	vaesdec	%xmm1,%xmm3,%xmm3
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vaesdec	%xmm1,%xmm5,%xmm5
-	vaesdec	%xmm1,%xmm6,%xmm6
-	vaesdec	%xmm1,%xmm7,%xmm7
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	176-120(%rsi),%xmm1
-
-	vaesdec	%xmm0,%xmm2,%xmm2
-	vaesdec	%xmm0,%xmm3,%xmm3
-	vaesdec	%xmm0,%xmm4,%xmm4
-	vaesdec	%xmm0,%xmm5,%xmm5
-	vaesdec	%xmm0,%xmm6,%xmm6
-	vaesdec	%xmm0,%xmm7,%xmm7
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	192-120(%rsi),%xmm0
-	je	L$dec8x_tail
-
-	vaesdec	%xmm1,%xmm2,%xmm2
-	vaesdec	%xmm1,%xmm3,%xmm3
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vaesdec	%xmm1,%xmm5,%xmm5
-	vaesdec	%xmm1,%xmm6,%xmm6
-	vaesdec	%xmm1,%xmm7,%xmm7
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	208-120(%rsi),%xmm1
-
-	vaesdec	%xmm0,%xmm2,%xmm2
-	vaesdec	%xmm0,%xmm3,%xmm3
-	vaesdec	%xmm0,%xmm4,%xmm4
-	vaesdec	%xmm0,%xmm5,%xmm5
-	vaesdec	%xmm0,%xmm6,%xmm6
-	vaesdec	%xmm0,%xmm7,%xmm7
-	vaesdec	%xmm0,%xmm8,%xmm8
-	vaesdec	%xmm0,%xmm9,%xmm9
-	vmovups	224-120(%rsi),%xmm0
-
-L$dec8x_tail:
-	vaesdec	%xmm1,%xmm2,%xmm2
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesdec	%xmm1,%xmm3,%xmm3
-	vaesdec	%xmm1,%xmm4,%xmm4
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesdec	%xmm1,%xmm5,%xmm5
-	vaesdec	%xmm1,%xmm6,%xmm6
-	vpaddd	%xmm14,%xmm15,%xmm15
-	vmovdqu	48(%rsp),%xmm14
-	vaesdec	%xmm1,%xmm7,%xmm7
-	movq	64(%rsp),%rbx
-	vaesdec	%xmm1,%xmm8,%xmm8
-	vaesdec	%xmm1,%xmm9,%xmm9
-	vmovups	16-120(%rsi),%xmm1
-
-	vaesdeclast	%xmm0,%xmm2,%xmm2
-	vmovdqa	%xmm15,32(%rsp)
-	vpxor	%xmm15,%xmm15,%xmm15
-	vaesdeclast	%xmm0,%xmm3,%xmm3
-	vpxor	0(%rbp),%xmm2,%xmm2
-	vaesdeclast	%xmm0,%xmm4,%xmm4
-	vpxor	16(%rbp),%xmm3,%xmm3
-	vpcmpgtd	%xmm15,%xmm14,%xmm15
-	vaesdeclast	%xmm0,%xmm5,%xmm5
-	vpxor	32(%rbp),%xmm4,%xmm4
-	vaesdeclast	%xmm0,%xmm6,%xmm6
-	vpxor	48(%rbp),%xmm5,%xmm5
-	vpaddd	%xmm15,%xmm14,%xmm14
-	vmovdqu	-120(%rsi),%xmm15
-	vaesdeclast	%xmm0,%xmm7,%xmm7
-	vpxor	64(%rbp),%xmm6,%xmm6
-	vaesdeclast	%xmm0,%xmm8,%xmm8
-	vpxor	80(%rbp),%xmm7,%xmm7
-	vmovdqa	%xmm14,48(%rsp)
-	vaesdeclast	%xmm0,%xmm9,%xmm9
-	vpxor	96(%rbp),%xmm8,%xmm8
-	vmovups	32-120(%rsi),%xmm0
-
-	vmovups	%xmm2,-16(%r8)
-	subq	%rbx,%r8
-	vmovdqu	128+0(%rsp),%xmm2
-	vpxor	112(%rbp),%xmm9,%xmm9
-	vmovups	%xmm3,-16(%r9)
-	subq	72(%rsp),%r9
-	vmovdqu	%xmm2,0(%rbp)
-	vpxor	%xmm15,%xmm2,%xmm2
-	vmovdqu	128+16(%rsp),%xmm3
-	vmovups	%xmm4,-16(%r10)
-	subq	80(%rsp),%r10
-	vmovdqu	%xmm3,16(%rbp)
-	vpxor	%xmm15,%xmm3,%xmm3
-	vmovdqu	128+32(%rsp),%xmm4
-	vmovups	%xmm5,-16(%r11)
-	subq	88(%rsp),%r11
-	vmovdqu	%xmm4,32(%rbp)
-	vpxor	%xmm15,%xmm4,%xmm4
-	vmovdqu	128+48(%rsp),%xmm5
-	vmovups	%xmm6,-16(%r12)
-	subq	96(%rsp),%r12
-	vmovdqu	%xmm5,48(%rbp)
-	vpxor	%xmm15,%xmm5,%xmm5
-	vmovdqu	%xmm10,64(%rbp)
-	vpxor	%xmm10,%xmm15,%xmm6
-	vmovups	%xmm7,-16(%r13)
-	subq	104(%rsp),%r13
-	vmovdqu	%xmm11,80(%rbp)
-	vpxor	%xmm11,%xmm15,%xmm7
-	vmovups	%xmm8,-16(%r14)
-	subq	112(%rsp),%r14
-	vmovdqu	%xmm12,96(%rbp)
-	vpxor	%xmm12,%xmm15,%xmm8
-	vmovups	%xmm9,-16(%r15)
-	subq	120(%rsp),%r15
-	vmovdqu	%xmm13,112(%rbp)
-	vpxor	%xmm13,%xmm15,%xmm9
-
-	xorq	$128,%rbp
-	decl	%edx
-	jnz	L$oop_dec8x
-
-	movq	16(%rsp),%rax
-
-
-
-
-
-L$dec8x_done:
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-L$dec8x_epilogue:
-	.byte	0xf3,0xc3

deps/openssl/asm/x64-macosx-gas/bn/x86_64-gf2m.s

@@ -242,7 +242,7 @@ L$body_mul_2x2:
 	movq	%rcx,56(%rsp)
 	movq	%r8,64(%rsp)
 
-	movq	$15,%r8
+	movq	$0xf,%r8
 	movq	%rsi,%rax
 	movq	%rcx,%rbp
 	call	_mul_1x1

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

@@ -10,7 +10,6 @@ _bn_mul_mont:
 	jnz	L$mul_enter
 	cmpl	$8,%r9d
 	jb	L$mul_enter
-	movl	_OPENSSL_ia32cap_P+8(%rip),%r11d
 	cmpq	%rsi,%rdx
 	jne	L$mul4x_enter
 	testl	$7,%r9d
@@ -216,9 +215,6 @@ L$mul_epilogue:
 .p2align	4
 bn_mul4x_mont:
 L$mul4x_enter:
-	andl	$524544,%r11d
-	cmpl	$524544,%r11d
-	je	L$mulx4x_enter
 	pushq	%rbx
 	pushq	%rbp
 	pushq	%r12
@@ -616,7 +612,6 @@ L$mul4x_epilogue:
 
 
 
-
 .p2align	5
 bn_sqr8x_mont:
 L$sqr8x_enter:
@@ -638,20 +633,20 @@ L$sqr8x_enter:
 
 
 
-	leaq	-64(%rsp,%r9,4),%r11
+	leaq	-64(%rsp,%r9,2),%r11
 	movq	(%r8),%r8
 	subq	%rsi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	L$sqr8x_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	-64(%rsp,%r9,2),%rsp
 	jmp	L$sqr8x_sp_done
 
 .p2align	5
 L$sqr8x_sp_alt:
-	leaq	4096-64(,%r9,4),%r10
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	4096-64(,%r9,2),%r10
+	leaq	-64(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -661,385 +656,81 @@ L$sqr8x_sp_done:
 	movq	%r9,%r10
 	negq	%r9
 
-	leaq	64(%rsp,%r9,2),%r11
 	movq	%r8,32(%rsp)
 	movq	%rax,40(%rsp)
 L$sqr8x_body:
 
-	movq	%r9,%rbp
-.byte	102,73,15,110,211
-	shrq	$3+2,%rbp
-	movl	_OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	L$sqr8x_copy_n
-
-.p2align	5
-L$sqr8x_copy_n:
-	movq	0(%rcx),%xmm0
-	movq	8(%rcx),%xmm1
-	movq	16(%rcx),%xmm3
-	movq	24(%rcx),%xmm4
-	leaq	32(%rcx),%rcx
-	movdqa	%xmm0,0(%r11)
-	movdqa	%xmm1,16(%r11)
-	movdqa	%xmm3,32(%r11)
-	movdqa	%xmm4,48(%r11)
-	leaq	64(%r11),%r11
-	decq	%rbp
-	jnz	L$sqr8x_copy_n
-
+.byte	102,72,15,110,209
 	pxor	%xmm0,%xmm0
 .byte	102,72,15,110,207
 .byte	102,73,15,110,218
-	andl	$524544,%eax
-	cmpl	$524544,%eax
-	jne	L$sqr8x_nox
-
-	call	_bn_sqrx8x_internal
-
-	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
-	movq	40(%rsp),%rsi
-	jmp	L$sqr8x_zero
-
-.p2align	5
-L$sqr8x_nox:
 	call	_bn_sqr8x_internal
 
-	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
-	movq	40(%rsp),%rsi
-	jmp	L$sqr8x_zero
-
-.p2align	5
-L$sqr8x_zero:
-	movdqa	%xmm0,0(%rax)
-	movdqa	%xmm0,16(%rax)
-	movdqa	%xmm0,32(%rax)
-	movdqa	%xmm0,48(%rax)
-	leaq	64(%rax),%rax
-	movdqa	%xmm0,0(%rdx)
-	movdqa	%xmm0,16(%rdx)
-	movdqa	%xmm0,32(%rdx)
-	movdqa	%xmm0,48(%rdx)
-	leaq	64(%rdx),%rdx
-	decq	%r9
-	jnz	L$sqr8x_zero
-
-	movq	$1,%rax
-	movq	-48(%rsi),%r15
-	movq	-40(%rsi),%r14
-	movq	-32(%rsi),%r13
-	movq	-24(%rsi),%r12
-	movq	-16(%rsi),%rbp
-	movq	-8(%rsi),%rbx
-	leaq	(%rsi),%rsp
-L$sqr8x_epilogue:
-	.byte	0xf3,0xc3
-
-
-.p2align	5
-bn_mulx4x_mont:
-L$mulx4x_enter:
-	movq	%rsp,%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-
-	shll	$3,%r9d
-.byte	0x67
-	xorq	%r10,%r10
-	subq	%r9,%r10
-	movq	(%r8),%r8
-	leaq	-72(%rsp,%r10,1),%rsp
-	leaq	(%rdx,%r9,1),%r10
-	andq	$-128,%rsp
-
-
-
-
-
-
-
-
-
-
-
-
-	movq	%r9,0(%rsp)
-	shrq	$5,%r9
-	movq	%r10,16(%rsp)
-	subq	$1,%r9
-	movq	%r8,24(%rsp)
-	movq	%rdi,32(%rsp)
-	movq	%rax,40(%rsp)
-	movq	%r9,48(%rsp)
-	jmp	L$mulx4x_body
-
-.p2align	5
-L$mulx4x_body:
-	leaq	8(%rdx),%rdi
-	movq	(%rdx),%rdx
-	leaq	64+32(%rsp),%rbx
-	movq	%rdx,%r9
-
-	mulxq	0(%rsi),%r8,%rax
-	mulxq	8(%rsi),%r11,%r14
-	addq	%rax,%r11
-	movq	%rdi,8(%rsp)
-	mulxq	16(%rsi),%r12,%r13
-	adcq	%r14,%r12
-	adcq	$0,%r13
-
-	movq	%r8,%rdi
-	imulq	24(%rsp),%r8
-	xorq	%rbp,%rbp
-
-	mulxq	24(%rsi),%rax,%r14
-	movq	%r8,%rdx
-	leaq	32(%rsi),%rsi
-	adcxq	%rax,%r13
-	adcxq	%rbp,%r14
-
-	mulxq	0(%rcx),%rax,%r10
-	adcxq	%rax,%rdi
-	adoxq	%r11,%r10
-	mulxq	8(%rcx),%rax,%r11
-	adcxq	%rax,%r10
-	adoxq	%r12,%r11
-.byte	0xc4,0x62,0xfb,0xf6,0xa1,0x10,0x00,0x00,0x00
-	movq	48(%rsp),%rdi
-	movq	%r10,-32(%rbx)
-	adcxq	%rax,%r11
-	adoxq	%r13,%r12
-	mulxq	24(%rcx),%rax,%r15
-	movq	%r9,%rdx
-	movq	%r11,-24(%rbx)
-	adcxq	%rax,%r12
-	adoxq	%rbp,%r15
-	leaq	32(%rcx),%rcx
-	movq	%r12,-16(%rbx)
-
-	jmp	L$mulx4x_1st
-
-.p2align	5
-L$mulx4x_1st:
-	adcxq	%rbp,%r15
-	mulxq	0(%rsi),%r10,%rax
-	adcxq	%r14,%r10
-	mulxq	8(%rsi),%r11,%r14
-	adcxq	%rax,%r11
-	mulxq	16(%rsi),%r12,%rax
-	adcxq	%r14,%r12
-	mulxq	24(%rsi),%r13,%r14
-.byte	0x67,0x67
-	movq	%r8,%rdx
-	adcxq	%rax,%r13
-	adcxq	%rbp,%r14
-	leaq	32(%rsi),%rsi
-	leaq	32(%rbx),%rbx
 
-	adoxq	%r15,%r10
-	mulxq	0(%rcx),%rax,%r15
-	adcxq	%rax,%r10
-	adoxq	%r15,%r11
-	mulxq	8(%rcx),%rax,%r15
-	adcxq	%rax,%r11
-	adoxq	%r15,%r12
-	mulxq	16(%rcx),%rax,%r15
-	movq	%r10,-40(%rbx)
-	adcxq	%rax,%r12
-	movq	%r11,-32(%rbx)
-	adoxq	%r15,%r13
-	mulxq	24(%rcx),%rax,%r15
-	movq	%r9,%rdx
-	movq	%r12,-24(%rbx)
-	adcxq	%rax,%r13
-	adoxq	%rbp,%r15
-	leaq	32(%rcx),%rcx
-	movq	%r13,-16(%rbx)
 
-	decq	%rdi
-	jnz	L$mulx4x_1st
-
-	movq	0(%rsp),%rax
-	movq	8(%rsp),%rdi
-	adcq	%rbp,%r15
-	addq	%r15,%r14
-	sbbq	%r15,%r15
-	movq	%r14,-8(%rbx)
-	jmp	L$mulx4x_outer
 
-.p2align	5
-L$mulx4x_outer:
-	movq	(%rdi),%rdx
-	leaq	8(%rdi),%rdi
-	subq	%rax,%rsi
-	movq	%r15,(%rbx)
-	leaq	64+32(%rsp),%rbx
-	subq	%rax,%rcx
-
-	mulxq	0(%rsi),%r8,%r11
-	xorl	%ebp,%ebp
-	movq	%rdx,%r9
-	mulxq	8(%rsi),%r14,%r12
-	adoxq	-32(%rbx),%r8
-	adcxq	%r14,%r11
-	mulxq	16(%rsi),%r15,%r13
-	adoxq	-24(%rbx),%r11
-	adcxq	%r15,%r12
-	adoxq	%rbp,%r12
-	adcxq	%rbp,%r13
-
-	movq	%rdi,8(%rsp)
-.byte	0x67
-	movq	%r8,%r15
-	imulq	24(%rsp),%r8
-	xorl	%ebp,%ebp
-
-	mulxq	24(%rsi),%rax,%r14
-	movq	%r8,%rdx
-	adoxq	-16(%rbx),%r12
-	adcxq	%rax,%r13
-	adoxq	-8(%rbx),%r13
-	adcxq	%rbp,%r14
-	leaq	32(%rsi),%rsi
-	adoxq	%rbp,%r14
-
-	mulxq	0(%rcx),%rax,%r10
-	adcxq	%rax,%r15
-	adoxq	%r11,%r10
-	mulxq	8(%rcx),%rax,%r11
-	adcxq	%rax,%r10
-	adoxq	%r12,%r11
-	mulxq	16(%rcx),%rax,%r12
-	movq	%r10,-32(%rbx)
-	adcxq	%rax,%r11
-	adoxq	%r13,%r12
-	mulxq	24(%rcx),%rax,%r15
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
 	movq	%r9,%rdx
-	movq	%r11,-24(%rbx)
-	leaq	32(%rcx),%rcx
-	adcxq	%rax,%r12
-	adoxq	%rbp,%r15
-	movq	48(%rsp),%rdi
-	movq	%r12,-16(%rbx)
-
-	jmp	L$mulx4x_inner
+.byte	102,72,15,126,207
+	sarq	$3+2,%rcx
+	jmp	L$sqr8x_sub
 
 .p2align	5
-L$mulx4x_inner:
-	mulxq	0(%rsi),%r10,%rax
-	adcxq	%rbp,%r15
-	adoxq	%r14,%r10
-	mulxq	8(%rsi),%r11,%r14
-	adcxq	0(%rbx),%r10
-	adoxq	%rax,%r11
-	mulxq	16(%rsi),%r12,%rax
-	adcxq	8(%rbx),%r11
-	adoxq	%r14,%r12
-	mulxq	24(%rsi),%r13,%r14
-	movq	%r8,%rdx
-	adcxq	16(%rbx),%r12
-	adoxq	%rax,%r13
-	adcxq	24(%rbx),%r13
-	adoxq	%rbp,%r14
-	leaq	32(%rsi),%rsi
+L$sqr8x_sub:
+	movq	0(%rbx),%r12
+	movq	8(%rbx),%r13
+	movq	16(%rbx),%r14
+	movq	24(%rbx),%r15
 	leaq	32(%rbx),%rbx
-	adcxq	%rbp,%r14
-
-	adoxq	%r15,%r10
-	mulxq	0(%rcx),%rax,%r15
-	adcxq	%rax,%r10
-	adoxq	%r15,%r11
-	mulxq	8(%rcx),%rax,%r15
-	adcxq	%rax,%r11
-	adoxq	%r15,%r12
-	mulxq	16(%rcx),%rax,%r15
-	movq	%r10,-40(%rbx)
-	adcxq	%rax,%r12
-	adoxq	%r15,%r13
-	mulxq	24(%rcx),%rax,%r15
-	movq	%r9,%rdx
-	movq	%r11,-32(%rbx)
-	movq	%r12,-24(%rbx)
-	adcxq	%rax,%r13
-	adoxq	%rbp,%r15
-	leaq	32(%rcx),%rcx
-	movq	%r13,-16(%rbx)
-
-	decq	%rdi
-	jnz	L$mulx4x_inner
+	sbbq	0(%rbp),%r12
+	sbbq	8(%rbp),%r13
+	sbbq	16(%rbp),%r14
+	sbbq	24(%rbp),%r15
+	leaq	32(%rbp),%rbp
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	leaq	32(%rdi),%rdi
+	incq	%rcx
+	jnz	L$sqr8x_sub
 
-	movq	0(%rsp),%rax
-	movq	8(%rsp),%rdi
-	adcq	%rbp,%r15
-	subq	0(%rbx),%rbp
-	adcq	%r15,%r14
-	movq	-8(%rcx),%r8
-	sbbq	%r15,%r15
-	movq	%r14,-8(%rbx)
-
-	cmpq	16(%rsp),%rdi
-	jne	L$mulx4x_outer
-
-	subq	%r14,%r8
-	sbbq	%r8,%r8
-	orq	%r8,%r15
-
-	negq	%rax
-	xorq	%rdx,%rdx
-	movq	32(%rsp),%rdi
-	leaq	64(%rsp),%rbx
+	sbbq	$0,%rax
+	leaq	(%rbx,%r9,1),%rbx
+	leaq	(%rdi,%r9,1),%rdi
 
+.byte	102,72,15,110,200
 	pxor	%xmm0,%xmm0
-	movq	0(%rcx,%rax,1),%r8
-	movq	8(%rcx,%rax,1),%r9
-	negq	%r8
-	jmp	L$mulx4x_sub_entry
+	pshufd	$0,%xmm1,%xmm1
+	movq	40(%rsp),%rsi
+	jmp	L$sqr8x_cond_copy
 
 .p2align	5
-L$mulx4x_sub:
-	movq	0(%rcx,%rax,1),%r8
-	movq	8(%rcx,%rax,1),%r9
-	notq	%r8
-L$mulx4x_sub_entry:
-	movq	16(%rcx,%rax,1),%r10
-	notq	%r9
-	andq	%r15,%r8
-	movq	24(%rcx,%rax,1),%r11
-	notq	%r10
-	andq	%r15,%r9
-	notq	%r11
-	andq	%r15,%r10
-	andq	%r15,%r11
-
-	negq	%rdx
-	adcq	0(%rbx),%r8
-	adcq	8(%rbx),%r9
-	movdqa	%xmm0,(%rbx)
-	adcq	16(%rbx),%r10
-	adcq	24(%rbx),%r11
-	movdqa	%xmm0,16(%rbx)
+L$sqr8x_cond_copy:
+	movdqa	0(%rbx),%xmm2
+	movdqa	16(%rbx),%xmm3
 	leaq	32(%rbx),%rbx
-	sbbq	%rdx,%rdx
-
-	movq	%r8,0(%rdi)
-	movq	%r9,8(%rdi)
-	movq	%r10,16(%rdi)
-	movq	%r11,24(%rdi)
+	movdqu	0(%rdi),%xmm4
+	movdqu	16(%rdi),%xmm5
 	leaq	32(%rdi),%rdi
+	movdqa	%xmm0,-32(%rbx)
+	movdqa	%xmm0,-16(%rbx)
+	movdqa	%xmm0,-32(%rbx,%rdx,1)
+	movdqa	%xmm0,-16(%rbx,%rdx,1)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-32(%rdi)
+	movdqu	%xmm5,-16(%rdi)
+	addq	$32,%r9
+	jnz	L$sqr8x_cond_copy
 
-	addq	$32,%rax
-	jnz	L$mulx4x_sub
-
-	movq	40(%rsp),%rsi
 	movq	$1,%rax
 	movq	-48(%rsi),%r15
 	movq	-40(%rsi),%r14
@@ -1048,7 +739,7 @@ L$mulx4x_sub_entry:
 	movq	-16(%rsi),%rbp
 	movq	-8(%rsi),%rbx
 	leaq	(%rsi),%rsp
-L$mulx4x_epilogue:
+L$sqr8x_epilogue:
 	.byte	0xf3,0xc3
 
 .byte	77,111,110,116,103,111,109,101,114,121,32,77,117,108,116,105,112,108,105,99,97,116,105,111,110,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0

deps/openssl/asm/x64-macosx-gas/modes/aesni-gcm-x86_64.s

@@ -1,753 +1,14 @@
 .text
 
-
-.p2align	5
-_aesni_ctr32_ghash_6x:
-	vmovdqu	32(%r11),%xmm2
-	subq	$6,%rdx
-	vpxor	%xmm4,%xmm4,%xmm4
-	vmovdqu	0-128(%rcx),%xmm15
-	vpaddb	%xmm2,%xmm1,%xmm10
-	vpaddb	%xmm2,%xmm10,%xmm11
-	vpaddb	%xmm2,%xmm11,%xmm12
-	vpaddb	%xmm2,%xmm12,%xmm13
-	vpaddb	%xmm2,%xmm13,%xmm14
-	vpxor	%xmm15,%xmm1,%xmm9
-	vmovdqu	%xmm4,16+8(%rsp)
-	jmp	L$oop6x
-
-.p2align	5
-L$oop6x:
-	addl	$100663296,%ebx
-	jc	L$handle_ctr32
-	vmovdqu	0-32(%r9),%xmm3
-	vpaddb	%xmm2,%xmm14,%xmm1
-	vpxor	%xmm15,%xmm10,%xmm10
-	vpxor	%xmm15,%xmm11,%xmm11
-
-L$resume_ctr32:
-	vmovdqu	%xmm1,(%r8)
-	vpclmulqdq	$16,%xmm3,%xmm7,%xmm5
-	vpxor	%xmm15,%xmm12,%xmm12
-	vmovups	16-128(%rcx),%xmm2
-	vpclmulqdq	$1,%xmm3,%xmm7,%xmm6
-	xorq	%r12,%r12
-	cmpq	%r14,%r15
-
-	vaesenc	%xmm2,%xmm9,%xmm9
-	vmovdqu	48+8(%rsp),%xmm0
-	vpxor	%xmm15,%xmm13,%xmm13
-	vpclmulqdq	$0,%xmm3,%xmm7,%xmm1
-	vaesenc	%xmm2,%xmm10,%xmm10
-	vpxor	%xmm15,%xmm14,%xmm14
-	setnc	%r12b
-	vpclmulqdq	$17,%xmm3,%xmm7,%xmm7
-	vaesenc	%xmm2,%xmm11,%xmm11
-	vmovdqu	16-32(%r9),%xmm3
-	negq	%r12
-	vaesenc	%xmm2,%xmm12,%xmm12
-	vpxor	%xmm5,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm3,%xmm0,%xmm5
-	vpxor	%xmm4,%xmm8,%xmm8
-	vaesenc	%xmm2,%xmm13,%xmm13
-	vpxor	%xmm5,%xmm1,%xmm4
-	andq	$96,%r12
-	vmovups	32-128(%rcx),%xmm15
-	vpclmulqdq	$16,%xmm3,%xmm0,%xmm1
-	vaesenc	%xmm2,%xmm14,%xmm14
-
-	vpclmulqdq	$1,%xmm3,%xmm0,%xmm2
-	leaq	(%r14,%r12,1),%r14
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	16+8(%rsp),%xmm8,%xmm8
-	vpclmulqdq	$17,%xmm3,%xmm0,%xmm3
-	vmovdqu	64+8(%rsp),%xmm0
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	88(%r14),%r13
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	80(%r14),%r12
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,32+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,40+8(%rsp)
-	vmovdqu	48-32(%r9),%xmm5
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	48-128(%rcx),%xmm15
-	vpxor	%xmm1,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm5,%xmm0,%xmm1
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm5,%xmm0,%xmm2
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpxor	%xmm3,%xmm7,%xmm7
-	vpclmulqdq	$1,%xmm5,%xmm0,%xmm3
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vpclmulqdq	$17,%xmm5,%xmm0,%xmm5
-	vmovdqu	80+8(%rsp),%xmm0
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vpxor	%xmm1,%xmm4,%xmm4
-	vmovdqu	64-32(%r9),%xmm1
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	64-128(%rcx),%xmm15
-	vpxor	%xmm2,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm1,%xmm0,%xmm2
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm3,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm1,%xmm0,%xmm3
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	72(%r14),%r13
-	vpxor	%xmm5,%xmm7,%xmm7
-	vpclmulqdq	$1,%xmm1,%xmm0,%xmm5
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	64(%r14),%r12
-	vpclmulqdq	$17,%xmm1,%xmm0,%xmm1
-	vmovdqu	96+8(%rsp),%xmm0
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,48+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,56+8(%rsp)
-	vpxor	%xmm2,%xmm4,%xmm4
-	vmovdqu	96-32(%r9),%xmm2
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	80-128(%rcx),%xmm15
-	vpxor	%xmm3,%xmm6,%xmm6
-	vpclmulqdq	$0,%xmm2,%xmm0,%xmm3
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm5,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm2,%xmm0,%xmm5
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	56(%r14),%r13
-	vpxor	%xmm1,%xmm7,%xmm7
-	vpclmulqdq	$1,%xmm2,%xmm0,%xmm1
-	vpxor	112+8(%rsp),%xmm8,%xmm8
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	48(%r14),%r12
-	vpclmulqdq	$17,%xmm2,%xmm0,%xmm2
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,64+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,72+8(%rsp)
-	vpxor	%xmm3,%xmm4,%xmm4
-	vmovdqu	112-32(%r9),%xmm3
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vmovups	96-128(%rcx),%xmm15
-	vpxor	%xmm5,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm3,%xmm8,%xmm5
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm1,%xmm6,%xmm6
-	vpclmulqdq	$1,%xmm3,%xmm8,%xmm1
-	vaesenc	%xmm15,%xmm10,%xmm10
-	movbeq	40(%r14),%r13
-	vpxor	%xmm2,%xmm7,%xmm7
-	vpclmulqdq	$0,%xmm3,%xmm8,%xmm2
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	32(%r14),%r12
-	vpclmulqdq	$17,%xmm3,%xmm8,%xmm8
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r13,80+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	movq	%r12,88+8(%rsp)
-	vpxor	%xmm5,%xmm6,%xmm6
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vpxor	%xmm1,%xmm6,%xmm6
-
-	vmovups	112-128(%rcx),%xmm15
-	vpslldq	$8,%xmm6,%xmm5
-	vpxor	%xmm2,%xmm4,%xmm4
-	vmovdqu	16(%r11),%xmm3
-
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	%xmm8,%xmm7,%xmm7
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpxor	%xmm5,%xmm4,%xmm4
-	movbeq	24(%r14),%r13
-	vaesenc	%xmm15,%xmm11,%xmm11
-	movbeq	16(%r14),%r12
-	vpalignr	$8,%xmm4,%xmm4,%xmm0
-	vpclmulqdq	$16,%xmm3,%xmm4,%xmm4
-	movq	%r13,96+8(%rsp)
-	vaesenc	%xmm15,%xmm12,%xmm12
-	movq	%r12,104+8(%rsp)
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vmovups	128-128(%rcx),%xmm1
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vmovups	144-128(%rcx),%xmm15
-	vaesenc	%xmm1,%xmm10,%xmm10
-	vpsrldq	$8,%xmm6,%xmm6
-	vaesenc	%xmm1,%xmm11,%xmm11
-	vpxor	%xmm6,%xmm7,%xmm7
-	vaesenc	%xmm1,%xmm12,%xmm12
-	vpxor	%xmm0,%xmm4,%xmm4
-	movbeq	8(%r14),%r13
-	vaesenc	%xmm1,%xmm13,%xmm13
-	movbeq	0(%r14),%r12
-	vaesenc	%xmm1,%xmm14,%xmm14
-	vmovups	160-128(%rcx),%xmm1
-	cmpl	$11,%ebp
-	jb	L$enc_tail
-
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vaesenc	%xmm1,%xmm10,%xmm10
-	vaesenc	%xmm1,%xmm11,%xmm11
-	vaesenc	%xmm1,%xmm12,%xmm12
-	vaesenc	%xmm1,%xmm13,%xmm13
-	vmovups	176-128(%rcx),%xmm15
-	vaesenc	%xmm1,%xmm14,%xmm14
-	vmovups	192-128(%rcx),%xmm1
-	je	L$enc_tail
-
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vaesenc	%xmm15,%xmm14,%xmm14
-
-	vaesenc	%xmm1,%xmm9,%xmm9
-	vaesenc	%xmm1,%xmm10,%xmm10
-	vaesenc	%xmm1,%xmm11,%xmm11
-	vaesenc	%xmm1,%xmm12,%xmm12
-	vaesenc	%xmm1,%xmm13,%xmm13
-	vmovups	208-128(%rcx),%xmm15
-	vaesenc	%xmm1,%xmm14,%xmm14
-	vmovups	224-128(%rcx),%xmm1
-	jmp	L$enc_tail
-
-.p2align	5
-L$handle_ctr32:
-	vmovdqu	(%r11),%xmm0
-	vpshufb	%xmm0,%xmm1,%xmm6
-	vmovdqu	48(%r11),%xmm5
-	vpaddd	64(%r11),%xmm6,%xmm10
-	vpaddd	%xmm5,%xmm6,%xmm11
-	vmovdqu	0-32(%r9),%xmm3
-	vpaddd	%xmm5,%xmm10,%xmm12
-	vpshufb	%xmm0,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm11,%xmm13
-	vpshufb	%xmm0,%xmm11,%xmm11
-	vpxor	%xmm15,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm12,%xmm14
-	vpshufb	%xmm0,%xmm12,%xmm12
-	vpxor	%xmm15,%xmm11,%xmm11
-	vpaddd	%xmm5,%xmm13,%xmm1
-	vpshufb	%xmm0,%xmm13,%xmm13
-	vpshufb	%xmm0,%xmm14,%xmm14
-	vpshufb	%xmm0,%xmm1,%xmm1
-	jmp	L$resume_ctr32
-
-.p2align	5
-L$enc_tail:
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vmovdqu	%xmm7,16+8(%rsp)
-	vpalignr	$8,%xmm4,%xmm4,%xmm8
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpclmulqdq	$16,%xmm3,%xmm4,%xmm4
-	vpxor	0(%rdi),%xmm1,%xmm2
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vpxor	16(%rdi),%xmm1,%xmm0
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vpxor	32(%rdi),%xmm1,%xmm5
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vpxor	48(%rdi),%xmm1,%xmm6
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vpxor	64(%rdi),%xmm1,%xmm7
-	vpxor	80(%rdi),%xmm1,%xmm3
-	vmovdqu	(%r8),%xmm1
-
-	vaesenclast	%xmm2,%xmm9,%xmm9
-	vmovdqu	32(%r11),%xmm2
-	vaesenclast	%xmm0,%xmm10,%xmm10
-	vpaddb	%xmm2,%xmm1,%xmm0
-	movq	%r13,112+8(%rsp)
-	leaq	96(%rdi),%rdi
-	vaesenclast	%xmm5,%xmm11,%xmm11
-	vpaddb	%xmm2,%xmm0,%xmm5
-	movq	%r12,120+8(%rsp)
-	leaq	96(%rsi),%rsi
-	vmovdqu	0-128(%rcx),%xmm15
-	vaesenclast	%xmm6,%xmm12,%xmm12
-	vpaddb	%xmm2,%xmm5,%xmm6
-	vaesenclast	%xmm7,%xmm13,%xmm13
-	vpaddb	%xmm2,%xmm6,%xmm7
-	vaesenclast	%xmm3,%xmm14,%xmm14
-	vpaddb	%xmm2,%xmm7,%xmm3
-
-	addq	$96,%r10
-	subq	$6,%rdx
-	jc	L$6x_done
-
-	vmovups	%xmm9,-96(%rsi)
-	vpxor	%xmm15,%xmm1,%xmm9
-	vmovups	%xmm10,-80(%rsi)
-	vmovdqa	%xmm0,%xmm10
-	vmovups	%xmm11,-64(%rsi)
-	vmovdqa	%xmm5,%xmm11
-	vmovups	%xmm12,-48(%rsi)
-	vmovdqa	%xmm6,%xmm12
-	vmovups	%xmm13,-32(%rsi)
-	vmovdqa	%xmm7,%xmm13
-	vmovups	%xmm14,-16(%rsi)
-	vmovdqa	%xmm3,%xmm14
-	vmovdqu	32+8(%rsp),%xmm7
-	jmp	L$oop6x
-
-L$6x_done:
-	vpxor	16+8(%rsp),%xmm8,%xmm8
-	vpxor	%xmm4,%xmm8,%xmm8
-
-	.byte	0xf3,0xc3
-
-.globl	_aesni_gcm_decrypt
-
-.p2align	5
-_aesni_gcm_decrypt:
-	xorq	%r10,%r10
-	cmpq	$96,%rdx
-	jb	L$gcm_dec_abort
-
-	leaq	(%rsp),%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-	vzeroupper
-
-	vmovdqu	(%r8),%xmm1
-	addq	$-128,%rsp
-	movl	12(%r8),%ebx
-	leaq	L$bswap_mask(%rip),%r11
-	leaq	-128(%rcx),%r14
-	movq	$3968,%r15
-	vmovdqu	(%r9),%xmm8
-	andq	$-128,%rsp
-	vmovdqu	(%r11),%xmm0
-	leaq	128(%rcx),%rcx
-	leaq	32+32(%r9),%r9
-	movl	240-128(%rcx),%ebp
-	vpshufb	%xmm0,%xmm8,%xmm8
-
-	andq	%r15,%r14
-	andq	%rsp,%r15
-	subq	%r14,%r15
-	jc	L$dec_no_key_aliasing
-	cmpq	$768,%r15
-	jnc	L$dec_no_key_aliasing
-	subq	%r15,%rsp
-L$dec_no_key_aliasing:
-
-	vmovdqu	80(%rdi),%xmm7
-	leaq	(%rdi),%r14
-	vmovdqu	64(%rdi),%xmm4
-	leaq	-192(%rdi,%rdx,1),%r15
-	vmovdqu	48(%rdi),%xmm5
-	shrq	$4,%rdx
-	xorq	%r10,%r10
-	vmovdqu	32(%rdi),%xmm6
-	vpshufb	%xmm0,%xmm7,%xmm7
-	vmovdqu	16(%rdi),%xmm2
-	vpshufb	%xmm0,%xmm4,%xmm4
-	vmovdqu	(%rdi),%xmm3
-	vpshufb	%xmm0,%xmm5,%xmm5
-	vmovdqu	%xmm4,48(%rsp)
-	vpshufb	%xmm0,%xmm6,%xmm6
-	vmovdqu	%xmm5,64(%rsp)
-	vpshufb	%xmm0,%xmm2,%xmm2
-	vmovdqu	%xmm6,80(%rsp)
-	vpshufb	%xmm0,%xmm3,%xmm3
-	vmovdqu	%xmm2,96(%rsp)
-	vmovdqu	%xmm3,112(%rsp)
-
-	call	_aesni_ctr32_ghash_6x
-
-	vmovups	%xmm9,-96(%rsi)
-	vmovups	%xmm10,-80(%rsi)
-	vmovups	%xmm11,-64(%rsi)
-	vmovups	%xmm12,-48(%rsi)
-	vmovups	%xmm13,-32(%rsi)
-	vmovups	%xmm14,-16(%rsi)
-
-	vpshufb	(%r11),%xmm8,%xmm8
-	vmovdqu	%xmm8,-64(%r9)
-
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-L$gcm_dec_abort:
-	movq	%r10,%rax
-	.byte	0xf3,0xc3
-
-
-.p2align	5
-_aesni_ctr32_6x:
-	vmovdqu	0-128(%rcx),%xmm4
-	vmovdqu	32(%r11),%xmm2
-	leaq	-1(%rbp),%r13
-	vmovups	16-128(%rcx),%xmm15
-	leaq	32-128(%rcx),%r12
-	vpxor	%xmm4,%xmm1,%xmm9
-	addl	$100663296,%ebx
-	jc	L$handle_ctr32_2
-	vpaddb	%xmm2,%xmm1,%xmm10
-	vpaddb	%xmm2,%xmm10,%xmm11
-	vpxor	%xmm4,%xmm10,%xmm10
-	vpaddb	%xmm2,%xmm11,%xmm12
-	vpxor	%xmm4,%xmm11,%xmm11
-	vpaddb	%xmm2,%xmm12,%xmm13
-	vpxor	%xmm4,%xmm12,%xmm12
-	vpaddb	%xmm2,%xmm13,%xmm14
-	vpxor	%xmm4,%xmm13,%xmm13
-	vpaddb	%xmm2,%xmm14,%xmm1
-	vpxor	%xmm4,%xmm14,%xmm14
-	jmp	L$oop_ctr32
-
-.p2align	4
-L$oop_ctr32:
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vmovups	(%r12),%xmm15
-	leaq	16(%r12),%r12
-	decl	%r13d
-	jnz	L$oop_ctr32
-
-	vmovdqu	(%r12),%xmm3
-	vaesenc	%xmm15,%xmm9,%xmm9
-	vpxor	0(%rdi),%xmm3,%xmm4
-	vaesenc	%xmm15,%xmm10,%xmm10
-	vpxor	16(%rdi),%xmm3,%xmm5
-	vaesenc	%xmm15,%xmm11,%xmm11
-	vpxor	32(%rdi),%xmm3,%xmm6
-	vaesenc	%xmm15,%xmm12,%xmm12
-	vpxor	48(%rdi),%xmm3,%xmm8
-	vaesenc	%xmm15,%xmm13,%xmm13
-	vpxor	64(%rdi),%xmm3,%xmm2
-	vaesenc	%xmm15,%xmm14,%xmm14
-	vpxor	80(%rdi),%xmm3,%xmm3
-	leaq	96(%rdi),%rdi
-
-	vaesenclast	%xmm4,%xmm9,%xmm9
-	vaesenclast	%xmm5,%xmm10,%xmm10
-	vaesenclast	%xmm6,%xmm11,%xmm11
-	vaesenclast	%xmm8,%xmm12,%xmm12
-	vaesenclast	%xmm2,%xmm13,%xmm13
-	vaesenclast	%xmm3,%xmm14,%xmm14
-	vmovups	%xmm9,0(%rsi)
-	vmovups	%xmm10,16(%rsi)
-	vmovups	%xmm11,32(%rsi)
-	vmovups	%xmm12,48(%rsi)
-	vmovups	%xmm13,64(%rsi)
-	vmovups	%xmm14,80(%rsi)
-	leaq	96(%rsi),%rsi
-
-	.byte	0xf3,0xc3
-.p2align	5
-L$handle_ctr32_2:
-	vpshufb	%xmm0,%xmm1,%xmm6
-	vmovdqu	48(%r11),%xmm5
-	vpaddd	64(%r11),%xmm6,%xmm10
-	vpaddd	%xmm5,%xmm6,%xmm11
-	vpaddd	%xmm5,%xmm10,%xmm12
-	vpshufb	%xmm0,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm11,%xmm13
-	vpshufb	%xmm0,%xmm11,%xmm11
-	vpxor	%xmm4,%xmm10,%xmm10
-	vpaddd	%xmm5,%xmm12,%xmm14
-	vpshufb	%xmm0,%xmm12,%xmm12
-	vpxor	%xmm4,%xmm11,%xmm11
-	vpaddd	%xmm5,%xmm13,%xmm1
-	vpshufb	%xmm0,%xmm13,%xmm13
-	vpxor	%xmm4,%xmm12,%xmm12
-	vpshufb	%xmm0,%xmm14,%xmm14
-	vpxor	%xmm4,%xmm13,%xmm13
-	vpshufb	%xmm0,%xmm1,%xmm1
-	vpxor	%xmm4,%xmm14,%xmm14
-	jmp	L$oop_ctr32
-
-
 .globl	_aesni_gcm_encrypt
 
-.p2align	5
 _aesni_gcm_encrypt:
-	xorq	%r10,%r10
-	cmpq	$288,%rdx
-	jb	L$gcm_enc_abort
-
-	leaq	(%rsp),%rax
-	pushq	%rbx
-	pushq	%rbp
-	pushq	%r12
-	pushq	%r13
-	pushq	%r14
-	pushq	%r15
-	vzeroupper
-
-	vmovdqu	(%r8),%xmm1
-	addq	$-128,%rsp
-	movl	12(%r8),%ebx
-	leaq	L$bswap_mask(%rip),%r11
-	leaq	-128(%rcx),%r14
-	movq	$3968,%r15
-	leaq	128(%rcx),%rcx
-	vmovdqu	(%r11),%xmm0
-	andq	$-128,%rsp
-	movl	240-128(%rcx),%ebp
-
-	andq	%r15,%r14
-	andq	%rsp,%r15
-	subq	%r14,%r15
-	jc	L$enc_no_key_aliasing
-	cmpq	$768,%r15
-	jnc	L$enc_no_key_aliasing
-	subq	%r15,%rsp
-L$enc_no_key_aliasing:
-
-	leaq	(%rsi),%r14
-	leaq	-192(%rsi,%rdx,1),%r15
-	shrq	$4,%rdx
-
-	call	_aesni_ctr32_6x
-	vpshufb	%xmm0,%xmm9,%xmm8
-	vpshufb	%xmm0,%xmm10,%xmm2
-	vmovdqu	%xmm8,112(%rsp)
-	vpshufb	%xmm0,%xmm11,%xmm4
-	vmovdqu	%xmm2,96(%rsp)
-	vpshufb	%xmm0,%xmm12,%xmm5
-	vmovdqu	%xmm4,80(%rsp)
-	vpshufb	%xmm0,%xmm13,%xmm6
-	vmovdqu	%xmm5,64(%rsp)
-	vpshufb	%xmm0,%xmm14,%xmm7
-	vmovdqu	%xmm6,48(%rsp)
-
-	call	_aesni_ctr32_6x
-
-	vmovdqu	(%r9),%xmm8
-	leaq	32+32(%r9),%r9
-	subq	$12,%rdx
-	movq	$192,%r10
-	vpshufb	%xmm0,%xmm8,%xmm8
-
-	call	_aesni_ctr32_ghash_6x
-	vmovdqu	32(%rsp),%xmm7
-	vmovdqu	(%r11),%xmm0
-	vmovdqu	0-32(%r9),%xmm3
-	vpunpckhqdq	%xmm7,%xmm7,%xmm1
-	vmovdqu	32-32(%r9),%xmm15
-	vmovups	%xmm9,-96(%rsi)
-	vpshufb	%xmm0,%xmm9,%xmm9
-	vpxor	%xmm7,%xmm1,%xmm1
-	vmovups	%xmm10,-80(%rsi)
-	vpshufb	%xmm0,%xmm10,%xmm10
-	vmovups	%xmm11,-64(%rsi)
-	vpshufb	%xmm0,%xmm11,%xmm11
-	vmovups	%xmm12,-48(%rsi)
-	vpshufb	%xmm0,%xmm12,%xmm12
-	vmovups	%xmm13,-32(%rsi)
-	vpshufb	%xmm0,%xmm13,%xmm13
-	vmovups	%xmm14,-16(%rsi)
-	vpshufb	%xmm0,%xmm14,%xmm14
-	vmovdqu	%xmm9,16(%rsp)
-	vmovdqu	48(%rsp),%xmm6
-	vmovdqu	16-32(%r9),%xmm0
-	vpunpckhqdq	%xmm6,%xmm6,%xmm2
-	vpclmulqdq	$0,%xmm3,%xmm7,%xmm5
-	vpxor	%xmm6,%xmm2,%xmm2
-	vpclmulqdq	$17,%xmm3,%xmm7,%xmm7
-	vpclmulqdq	$0,%xmm15,%xmm1,%xmm1
-
-	vmovdqu	64(%rsp),%xmm9
-	vpclmulqdq	$0,%xmm0,%xmm6,%xmm4
-	vmovdqu	48-32(%r9),%xmm3
-	vpxor	%xmm5,%xmm4,%xmm4
-	vpunpckhqdq	%xmm9,%xmm9,%xmm5
-	vpclmulqdq	$17,%xmm0,%xmm6,%xmm6
-	vpxor	%xmm9,%xmm5,%xmm5
-	vpxor	%xmm7,%xmm6,%xmm6
-	vpclmulqdq	$16,%xmm15,%xmm2,%xmm2
-	vmovdqu	80-32(%r9),%xmm15
-	vpxor	%xmm1,%xmm2,%xmm2
-
-	vmovdqu	80(%rsp),%xmm1
-	vpclmulqdq	$0,%xmm3,%xmm9,%xmm7
-	vmovdqu	64-32(%r9),%xmm0
-	vpxor	%xmm4,%xmm7,%xmm7
-	vpunpckhqdq	%xmm1,%xmm1,%xmm4
-	vpclmulqdq	$17,%xmm3,%xmm9,%xmm9
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpxor	%xmm6,%xmm9,%xmm9
-	vpclmulqdq	$0,%xmm15,%xmm5,%xmm5
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	96(%rsp),%xmm2
-	vpclmulqdq	$0,%xmm0,%xmm1,%xmm6
-	vmovdqu	96-32(%r9),%xmm3
-	vpxor	%xmm7,%xmm6,%xmm6
-	vpunpckhqdq	%xmm2,%xmm2,%xmm7
-	vpclmulqdq	$17,%xmm0,%xmm1,%xmm1
-	vpxor	%xmm2,%xmm7,%xmm7
-	vpxor	%xmm9,%xmm1,%xmm1
-	vpclmulqdq	$16,%xmm15,%xmm4,%xmm4
-	vmovdqu	128-32(%r9),%xmm15
-	vpxor	%xmm5,%xmm4,%xmm4
-
-	vpxor	112(%rsp),%xmm8,%xmm8
-	vpclmulqdq	$0,%xmm3,%xmm2,%xmm5
-	vmovdqu	112-32(%r9),%xmm0
-	vpunpckhqdq	%xmm8,%xmm8,%xmm9
-	vpxor	%xmm6,%xmm5,%xmm5
-	vpclmulqdq	$17,%xmm3,%xmm2,%xmm2
-	vpxor	%xmm8,%xmm9,%xmm9
-	vpxor	%xmm1,%xmm2,%xmm2
-	vpclmulqdq	$0,%xmm15,%xmm7,%xmm7
-	vpxor	%xmm4,%xmm7,%xmm4
-
-	vpclmulqdq	$0,%xmm0,%xmm8,%xmm6
-	vmovdqu	0-32(%r9),%xmm3
-	vpunpckhqdq	%xmm14,%xmm14,%xmm1
-	vpclmulqdq	$17,%xmm0,%xmm8,%xmm8
-	vpxor	%xmm14,%xmm1,%xmm1
-	vpxor	%xmm5,%xmm6,%xmm5
-	vpclmulqdq	$16,%xmm15,%xmm9,%xmm9
-	vmovdqu	32-32(%r9),%xmm15
-	vpxor	%xmm2,%xmm8,%xmm7
-	vpxor	%xmm4,%xmm9,%xmm6
-
-	vmovdqu	16-32(%r9),%xmm0
-	vpxor	%xmm5,%xmm7,%xmm9
-	vpclmulqdq	$0,%xmm3,%xmm14,%xmm4
-	vpxor	%xmm9,%xmm6,%xmm6
-	vpunpckhqdq	%xmm13,%xmm13,%xmm2
-	vpclmulqdq	$17,%xmm3,%xmm14,%xmm14
-	vpxor	%xmm13,%xmm2,%xmm2
-	vpslldq	$8,%xmm6,%xmm9
-	vpclmulqdq	$0,%xmm15,%xmm1,%xmm1
-	vpxor	%xmm9,%xmm5,%xmm8
-	vpsrldq	$8,%xmm6,%xmm6
-	vpxor	%xmm6,%xmm7,%xmm7
-
-	vpclmulqdq	$0,%xmm0,%xmm13,%xmm5
-	vmovdqu	48-32(%r9),%xmm3
-	vpxor	%xmm4,%xmm5,%xmm5
-	vpunpckhqdq	%xmm12,%xmm12,%xmm9
-	vpclmulqdq	$17,%xmm0,%xmm13,%xmm13
-	vpxor	%xmm12,%xmm9,%xmm9
-	vpxor	%xmm14,%xmm13,%xmm13
-	vpalignr	$8,%xmm8,%xmm8,%xmm14
-	vpclmulqdq	$16,%xmm15,%xmm2,%xmm2
-	vmovdqu	80-32(%r9),%xmm15
-	vpxor	%xmm1,%xmm2,%xmm2
-
-	vpclmulqdq	$0,%xmm3,%xmm12,%xmm4
-	vmovdqu	64-32(%r9),%xmm0
-	vpxor	%xmm5,%xmm4,%xmm4
-	vpunpckhqdq	%xmm11,%xmm11,%xmm1
-	vpclmulqdq	$17,%xmm3,%xmm12,%xmm12
-	vpxor	%xmm11,%xmm1,%xmm1
-	vpxor	%xmm13,%xmm12,%xmm12
-	vxorps	16(%rsp),%xmm7,%xmm7
-	vpclmulqdq	$0,%xmm15,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm9,%xmm9
-
-	vpclmulqdq	$16,16(%r11),%xmm8,%xmm8
-	vxorps	%xmm14,%xmm8,%xmm8
-
-	vpclmulqdq	$0,%xmm0,%xmm11,%xmm5
-	vmovdqu	96-32(%r9),%xmm3
-	vpxor	%xmm4,%xmm5,%xmm5
-	vpunpckhqdq	%xmm10,%xmm10,%xmm2
-	vpclmulqdq	$17,%xmm0,%xmm11,%xmm11
-	vpxor	%xmm10,%xmm2,%xmm2
-	vpalignr	$8,%xmm8,%xmm8,%xmm14
-	vpxor	%xmm12,%xmm11,%xmm11
-	vpclmulqdq	$16,%xmm15,%xmm1,%xmm1
-	vmovdqu	128-32(%r9),%xmm15
-	vpxor	%xmm9,%xmm1,%xmm1
-
-	vxorps	%xmm7,%xmm14,%xmm14
-	vpclmulqdq	$16,16(%r11),%xmm8,%xmm8
-	vxorps	%xmm14,%xmm8,%xmm8
-
-	vpclmulqdq	$0,%xmm3,%xmm10,%xmm4
-	vmovdqu	112-32(%r9),%xmm0
-	vpxor	%xmm5,%xmm4,%xmm4
-	vpunpckhqdq	%xmm8,%xmm8,%xmm9
-	vpclmulqdq	$17,%xmm3,%xmm10,%xmm10
-	vpxor	%xmm8,%xmm9,%xmm9
-	vpxor	%xmm11,%xmm10,%xmm10
-	vpclmulqdq	$0,%xmm15,%xmm2,%xmm2
-	vpxor	%xmm1,%xmm2,%xmm2
-
-	vpclmulqdq	$0,%xmm0,%xmm8,%xmm5
-	vpclmulqdq	$17,%xmm0,%xmm8,%xmm7
-	vpxor	%xmm4,%xmm5,%xmm5
-	vpclmulqdq	$16,%xmm15,%xmm9,%xmm6
-	vpxor	%xmm10,%xmm7,%xmm7
-	vpxor	%xmm2,%xmm6,%xmm6
-
-	vpxor	%xmm5,%xmm7,%xmm4
-	vpxor	%xmm4,%xmm6,%xmm6
-	vpslldq	$8,%xmm6,%xmm1
-	vmovdqu	16(%r11),%xmm3
-	vpsrldq	$8,%xmm6,%xmm6
-	vpxor	%xmm1,%xmm5,%xmm8
-	vpxor	%xmm6,%xmm7,%xmm7
+	xorl	%eax,%eax
+	.byte	0xf3,0xc3
 
-	vpalignr	$8,%xmm8,%xmm8,%xmm2
-	vpclmulqdq	$16,%xmm3,%xmm8,%xmm8
-	vpxor	%xmm2,%xmm8,%xmm8
 
-	vpalignr	$8,%xmm8,%xmm8,%xmm2
-	vpclmulqdq	$16,%xmm3,%xmm8,%xmm8
-	vpxor	%xmm7,%xmm2,%xmm2
-	vpxor	%xmm2,%xmm8,%xmm8
-	vpshufb	(%r11),%xmm8,%xmm8
-	vmovdqu	%xmm8,-64(%r9)
+.globl	_aesni_gcm_decrypt
 
-	vzeroupper
-	movq	-48(%rax),%r15
-	movq	-40(%rax),%r14
-	movq	-32(%rax),%r13
-	movq	-24(%rax),%r12
-	movq	-16(%rax),%rbp
-	movq	-8(%rax),%rbx
-	leaq	(%rax),%rsp
-L$gcm_enc_abort:
-	movq	%r10,%rax
+_aesni_gcm_decrypt:
+	xorl	%eax,%eax
 	.byte	0xf3,0xc3
-
-.p2align	6
-L$bswap_mask:
-.byte	15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0
-L$poly:
-.byte	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0xc2
-L$one_msb:
-.byte	0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,1
-L$two_lsb:
-.byte	2,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-L$one_lsb:
-.byte	1,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
-.byte	65,69,83,45,78,73,32,71,67,77,32,109,111,100,117,108,101,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
-.p2align	6

deps/openssl/asm/x64-macosx-gas/modes/ghash-x86_64.s

@@ -20,14 +20,14 @@ L$gmult_prologue:
 	movq	$14,%rcx
 	movq	8(%rsi,%rax,1),%r8
 	movq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	movq	%r8,%rdx
 	jmp	L$oop1
 
 .p2align	4
 L$oop1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	movb	(%rdi,%rcx,1),%al
 	shrq	$4,%r9
@@ -43,13 +43,13 @@ L$oop1:
 	js	L$break1
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
@@ -58,19 +58,19 @@ L$oop1:
 .p2align	4
 L$break1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rbx,1),%r8
@@ -661,10 +661,10 @@ L$ghash_epilogue:
 _gcm_init_clmul:
 L$_init_clmul:
 	movdqu	(%rsi),%xmm2
-	pshufd	$78,%xmm2,%xmm2
+	pshufd	$0b01001110,%xmm2,%xmm2
 
 
-	pshufd	$255,%xmm2,%xmm4
+	pshufd	$0b11111111,%xmm2,%xmm4
 	movdqa	%xmm2,%xmm3
 	psllq	$1,%xmm2
 	pxor	%xmm5,%xmm5
@@ -678,11 +678,11 @@ L$_init_clmul:
 	pxor	%xmm5,%xmm2
 
 
-	pshufd	$78,%xmm2,%xmm6
+	pshufd	$0b01001110,%xmm2,%xmm6
 	movdqa	%xmm2,%xmm0
 	pxor	%xmm2,%xmm6
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -718,8 +718,8 @@ L$_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm2,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm2,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm2,%xmm3
 	movdqu	%xmm2,0(%rdi)
 	pxor	%xmm0,%xmm4
@@ -727,7 +727,7 @@ L$_init_clmul:
 .byte	102,15,58,15,227,8
 	movdqu	%xmm4,32(%rdi)
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -765,7 +765,7 @@ L$_init_clmul:
 	pxor	%xmm1,%xmm0
 	movdqa	%xmm0,%xmm5
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -801,8 +801,8 @@ L$_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm5,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm5,%xmm3
 	movdqu	%xmm5,48(%rdi)
 	pxor	%xmm0,%xmm4
@@ -822,7 +822,7 @@ L$_gmult_clmul:
 	movdqu	32(%rsi),%xmm4
 .byte	102,15,56,0,197
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -874,20 +874,20 @@ L$_ghash_clmul:
 	movdqu	32(%rsi),%xmm7
 .byte	102,65,15,56,0,194
 
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	L$odd_tail
 
 	movdqu	16(%rsi),%xmm6
 	movl	_OPENSSL_ia32cap_P+4(%rip),%eax
-	cmpq	$48,%rcx
+	cmpq	$0x30,%rcx
 	jb	L$skip4x
 
 	andl	$71303168,%eax
 	cmpl	$4194304,%eax
 	je	L$skip4x
 
-	subq	$48,%rcx
-	movq	$11547335547999543296,%rax
+	subq	$0x30,%rcx
+	movq	$0xA040608020C0E000,%rax
 	movdqu	48(%rsi),%xmm14
 	movdqu	64(%rsi),%xmm15
 
@@ -899,14 +899,14 @@ L$_ghash_clmul:
 .byte	102,65,15,56,0,218
 .byte	102,69,15,56,0,218
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
 .byte	102,15,58,68,231,0
 
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm11,%xmm12
 .byte	102,68,15,58,68,222,0
 .byte	102,68,15,58,68,238,17
@@ -921,12 +921,12 @@ L$_ghash_clmul:
 .byte	102,69,15,56,0,218
 .byte	102,69,15,56,0,194
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm8,%xmm0
 	pxor	%xmm11,%xmm12
 .byte	102,69,15,58,68,222,0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 .byte	102,69,15,58,68,238,17
 .byte	102,68,15,58,68,231,0
@@ -934,7 +934,7 @@ L$_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jc	L$tail4x
 
 	jmp	L$mod4_loop
@@ -949,14 +949,14 @@ L$mod4_loop:
 	movdqu	32(%rdx),%xmm3
 	movdqa	%xmm11,%xmm13
 .byte	102,68,15,58,68,199,16
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	xorps	%xmm5,%xmm1
 	pxor	%xmm11,%xmm12
 .byte	102,65,15,56,0,218
 	movups	32(%rsi),%xmm7
 	xorps	%xmm4,%xmm8
 .byte	102,68,15,58,68,218,0
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 
 	pxor	%xmm0,%xmm8
 	movdqa	%xmm3,%xmm5
@@ -1000,7 +1000,7 @@ L$mod4_loop:
 
 	movdqa	%xmm11,%xmm13
 	pxor	%xmm12,%xmm4
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm9,%xmm0
 	pxor	%xmm8,%xmm1
 	pxor	%xmm11,%xmm12
@@ -1010,14 +1010,14 @@ L$mod4_loop:
 	movdqa	%xmm0,%xmm1
 .byte	102,69,15,58,68,238,17
 	xorps	%xmm11,%xmm3
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 
 .byte	102,68,15,58,68,231,0
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jnc	L$mod4_loop
 
 L$tail4x:
@@ -1061,10 +1061,10 @@ L$tail4x:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	addq	$64,%rcx
+	addq	$0x40,%rcx
 	jz	L$done
 	movdqu	32(%rsi),%xmm7
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	L$odd_tail
 L$skip4x:
 
@@ -1079,7 +1079,7 @@ L$skip4x:
 	pxor	%xmm8,%xmm0
 
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
@@ -1087,7 +1087,7 @@ L$skip4x:
 
 	leaq	32(%rdx),%rdx
 	nop
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	jbe	L$even_tail
 	nop
 	jmp	L$mod_loop
@@ -1096,7 +1096,7 @@ L$skip4x:
 L$mod_loop:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1134,7 +1134,7 @@ L$mod_loop:
 	pslldq	$8,%xmm0
 	psrldq	$8,%xmm8
 	pxor	%xmm9,%xmm0
-	pshufd	$78,%xmm5,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm4
 	pxor	%xmm8,%xmm1
 	pxor	%xmm5,%xmm4
 
@@ -1150,13 +1150,13 @@ L$mod_loop:
 .byte	102,15,58,68,231,0
 	pxor	%xmm1,%xmm0
 
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	ja	L$mod_loop
 
 L$even_tail:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1204,7 +1204,7 @@ L$odd_tail:
 .byte	102,69,15,56,0,194
 	pxor	%xmm8,%xmm0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -1249,108 +1249,7 @@ L$done:
 
 .p2align	5
 _gcm_init_avx:
-	vzeroupper
-
-	vmovdqu	(%rsi),%xmm2
-	vpshufd	$78,%xmm2,%xmm2
-
-
-	vpshufd	$255,%xmm2,%xmm4
-	vpsrlq	$63,%xmm2,%xmm3
-	vpsllq	$1,%xmm2,%xmm2
-	vpxor	%xmm5,%xmm5,%xmm5
-	vpcmpgtd	%xmm4,%xmm5,%xmm5
-	vpslldq	$8,%xmm3,%xmm3
-	vpor	%xmm3,%xmm2,%xmm2
-
-
-	vpand	L$0x1c2_polynomial(%rip),%xmm5,%xmm5
-	vpxor	%xmm5,%xmm2,%xmm2
-
-	vpunpckhqdq	%xmm2,%xmm2,%xmm6
-	vmovdqa	%xmm2,%xmm0
-	vpxor	%xmm2,%xmm6,%xmm6
-	movq	$4,%r10
-	jmp	L$init_start_avx
-.p2align	5
-L$init_loop_avx:
-	vpalignr	$8,%xmm3,%xmm4,%xmm5
-	vmovdqu	%xmm5,-16(%rdi)
-	vpunpckhqdq	%xmm0,%xmm0,%xmm3
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm2,%xmm0,%xmm1
-	vpclmulqdq	$0,%xmm2,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm3,%xmm3
-	vpxor	%xmm0,%xmm1,%xmm4
-	vpxor	%xmm4,%xmm3,%xmm3
-
-	vpslldq	$8,%xmm3,%xmm4
-	vpsrldq	$8,%xmm3,%xmm3
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpxor	%xmm3,%xmm1,%xmm1
-	vpsllq	$57,%xmm0,%xmm3
-	vpsllq	$62,%xmm0,%xmm4
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpsllq	$63,%xmm0,%xmm3
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpslldq	$8,%xmm4,%xmm3
-	vpsrldq	$8,%xmm4,%xmm4
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpxor	%xmm4,%xmm1,%xmm1
-
-	vpsrlq	$1,%xmm0,%xmm4
-	vpxor	%xmm0,%xmm1,%xmm1
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$5,%xmm4,%xmm4
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$1,%xmm0,%xmm0
-	vpxor	%xmm1,%xmm0,%xmm0
-L$init_start_avx:
-	vmovdqa	%xmm0,%xmm5
-	vpunpckhqdq	%xmm0,%xmm0,%xmm3
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm2,%xmm0,%xmm1
-	vpclmulqdq	$0,%xmm2,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm3,%xmm3
-	vpxor	%xmm0,%xmm1,%xmm4
-	vpxor	%xmm4,%xmm3,%xmm3
-
-	vpslldq	$8,%xmm3,%xmm4
-	vpsrldq	$8,%xmm3,%xmm3
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpxor	%xmm3,%xmm1,%xmm1
-	vpsllq	$57,%xmm0,%xmm3
-	vpsllq	$62,%xmm0,%xmm4
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpsllq	$63,%xmm0,%xmm3
-	vpxor	%xmm3,%xmm4,%xmm4
-	vpslldq	$8,%xmm4,%xmm3
-	vpsrldq	$8,%xmm4,%xmm4
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpxor	%xmm4,%xmm1,%xmm1
-
-	vpsrlq	$1,%xmm0,%xmm4
-	vpxor	%xmm0,%xmm1,%xmm1
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$5,%xmm4,%xmm4
-	vpxor	%xmm4,%xmm0,%xmm0
-	vpsrlq	$1,%xmm0,%xmm0
-	vpxor	%xmm1,%xmm0,%xmm0
-	vpshufd	$78,%xmm5,%xmm3
-	vpshufd	$78,%xmm0,%xmm4
-	vpxor	%xmm5,%xmm3,%xmm3
-	vmovdqu	%xmm5,0(%rdi)
-	vpxor	%xmm0,%xmm4,%xmm4
-	vmovdqu	%xmm0,16(%rdi)
-	leaq	48(%rdi),%rdi
-	subq	$1,%r10
-	jnz	L$init_loop_avx
-
-	vpalignr	$8,%xmm4,%xmm3,%xmm5
-	vmovdqu	%xmm5,-16(%rdi)
-
-	vzeroupper
-	.byte	0xf3,0xc3
+	jmp	L$_init_clmul
 
 .globl	_gcm_gmult_avx
 
@@ -1362,377 +1261,7 @@ _gcm_gmult_avx:
 
 .p2align	5
 _gcm_ghash_avx:
-	vzeroupper
-
-	vmovdqu	(%rdi),%xmm10
-	leaq	L$0x1c2_polynomial(%rip),%r10
-	leaq	64(%rsi),%rsi
-	vmovdqu	L$bswap_mask(%rip),%xmm13
-	vpshufb	%xmm13,%xmm10,%xmm10
-	cmpq	$128,%rcx
-	jb	L$short_avx
-	subq	$128,%rcx
-
-	vmovdqu	112(%rdx),%xmm14
-	vmovdqu	0-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vmovdqu	32-64(%rsi),%xmm7
-
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vmovdqu	96(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	16-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vmovdqu	80(%rdx),%xmm14
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	48-64(%rsi),%xmm6
-	vpxor	%xmm14,%xmm9,%xmm9
-	vmovdqu	64(%rdx),%xmm15
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	80-64(%rsi),%xmm7
-
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	64-64(%rsi),%xmm6
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-
-	vmovdqu	48(%rdx),%xmm14
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	96-64(%rsi),%xmm6
-	vpxor	%xmm5,%xmm2,%xmm2
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	128-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-
-	vmovdqu	32(%rdx),%xmm15
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	112-64(%rsi),%xmm6
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-
-	vmovdqu	16(%rdx),%xmm14
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	144-64(%rsi),%xmm6
-	vpxor	%xmm5,%xmm2,%xmm2
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	176-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-
-	vmovdqu	(%rdx),%xmm15
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	160-64(%rsi),%xmm6
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$16,%xmm7,%xmm9,%xmm2
-
-	leaq	128(%rdx),%rdx
-	cmpq	$128,%rcx
-	jb	L$tail_avx
-
-	vpxor	%xmm10,%xmm15,%xmm15
-	subq	$128,%rcx
-	jmp	L$oop8x_avx
-
-.p2align	5
-L$oop8x_avx:
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vmovdqu	112(%rdx),%xmm14
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpxor	%xmm15,%xmm8,%xmm8
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm10
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm11
-	vmovdqu	0-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm12
-	vmovdqu	32-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-
-	vmovdqu	96(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpxor	%xmm3,%xmm10,%xmm10
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vxorps	%xmm4,%xmm11,%xmm11
-	vmovdqu	16-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm5,%xmm12,%xmm12
-	vxorps	%xmm15,%xmm8,%xmm8
-
-	vmovdqu	80(%rdx),%xmm14
-	vpxor	%xmm10,%xmm12,%xmm12
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpxor	%xmm11,%xmm12,%xmm12
-	vpslldq	$8,%xmm12,%xmm9
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vpsrldq	$8,%xmm12,%xmm12
-	vpxor	%xmm9,%xmm10,%xmm10
-	vmovdqu	48-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vxorps	%xmm12,%xmm11,%xmm11
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	80-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	64(%rdx),%xmm15
-	vpalignr	$8,%xmm10,%xmm10,%xmm12
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	64-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vxorps	%xmm15,%xmm8,%xmm8
-	vpxor	%xmm5,%xmm2,%xmm2
-
-	vmovdqu	48(%rdx),%xmm14
-	vpclmulqdq	$16,(%r10),%xmm10,%xmm10
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	96-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	128-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	32(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpxor	%xmm3,%xmm0,%xmm0
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	112-64(%rsi),%xmm6
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm4,%xmm1,%xmm1
-	vpclmulqdq	$0,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm15,%xmm8,%xmm8
-	vpxor	%xmm5,%xmm2,%xmm2
-	vxorps	%xmm12,%xmm10,%xmm10
-
-	vmovdqu	16(%rdx),%xmm14
-	vpalignr	$8,%xmm10,%xmm10,%xmm12
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm3
-	vpshufb	%xmm13,%xmm14,%xmm14
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm4
-	vmovdqu	144-64(%rsi),%xmm6
-	vpclmulqdq	$16,(%r10),%xmm10,%xmm10
-	vxorps	%xmm11,%xmm12,%xmm12
-	vpunpckhqdq	%xmm14,%xmm14,%xmm9
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$16,%xmm7,%xmm8,%xmm5
-	vmovdqu	176-64(%rsi),%xmm7
-	vpxor	%xmm14,%xmm9,%xmm9
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vmovdqu	(%rdx),%xmm15
-	vpclmulqdq	$0,%xmm6,%xmm14,%xmm0
-	vpshufb	%xmm13,%xmm15,%xmm15
-	vpclmulqdq	$17,%xmm6,%xmm14,%xmm1
-	vmovdqu	160-64(%rsi),%xmm6
-	vpxor	%xmm12,%xmm15,%xmm15
-	vpclmulqdq	$16,%xmm7,%xmm9,%xmm2
-	vpxor	%xmm10,%xmm15,%xmm15
-
-	leaq	128(%rdx),%rdx
-	subq	$128,%rcx
-	jnc	L$oop8x_avx
-
-	addq	$128,%rcx
-	jmp	L$tail_no_xor_avx
-
-.p2align	5
-L$short_avx:
-	vmovdqu	-16(%rdx,%rcx,1),%xmm14
-	leaq	(%rdx,%rcx,1),%rdx
-	vmovdqu	0-64(%rsi),%xmm6
-	vmovdqu	32-64(%rsi),%xmm7
-	vpshufb	%xmm13,%xmm14,%xmm15
-
-	vmovdqa	%xmm0,%xmm3
-	vmovdqa	%xmm1,%xmm4
-	vmovdqa	%xmm2,%xmm5
-	subq	$16,%rcx
-	jz	L$tail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-32(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	16-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vpsrldq	$8,%xmm7,%xmm7
-	subq	$16,%rcx
-	jz	L$tail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-48(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	48-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vmovdqu	80-64(%rsi),%xmm7
-	subq	$16,%rcx
-	jz	L$tail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-64(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	64-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vpsrldq	$8,%xmm7,%xmm7
-	subq	$16,%rcx
-	jz	L$tail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-80(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	96-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vmovdqu	128-64(%rsi),%xmm7
-	subq	$16,%rcx
-	jz	L$tail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-96(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	112-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vpsrldq	$8,%xmm7,%xmm7
-	subq	$16,%rcx
-	jz	L$tail_avx
-
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vmovdqu	-112(%rdx),%xmm14
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vmovdqu	144-64(%rsi),%xmm6
-	vpshufb	%xmm13,%xmm14,%xmm15
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-	vmovq	184-64(%rsi),%xmm7
-	subq	$16,%rcx
-	jmp	L$tail_avx
-
-.p2align	5
-L$tail_avx:
-	vpxor	%xmm10,%xmm15,%xmm15
-L$tail_no_xor_avx:
-	vpunpckhqdq	%xmm15,%xmm15,%xmm8
-	vpxor	%xmm0,%xmm3,%xmm3
-	vpclmulqdq	$0,%xmm6,%xmm15,%xmm0
-	vpxor	%xmm15,%xmm8,%xmm8
-	vpxor	%xmm1,%xmm4,%xmm4
-	vpclmulqdq	$17,%xmm6,%xmm15,%xmm1
-	vpxor	%xmm2,%xmm5,%xmm5
-	vpclmulqdq	$0,%xmm7,%xmm8,%xmm2
-
-	vmovdqu	(%r10),%xmm12
-
-	vpxor	%xmm0,%xmm3,%xmm10
-	vpxor	%xmm1,%xmm4,%xmm11
-	vpxor	%xmm2,%xmm5,%xmm5
-
-	vpxor	%xmm10,%xmm5,%xmm5
-	vpxor	%xmm11,%xmm5,%xmm5
-	vpslldq	$8,%xmm5,%xmm9
-	vpsrldq	$8,%xmm5,%xmm5
-	vpxor	%xmm9,%xmm10,%xmm10
-	vpxor	%xmm5,%xmm11,%xmm11
-
-	vpclmulqdq	$16,%xmm12,%xmm10,%xmm9
-	vpalignr	$8,%xmm10,%xmm10,%xmm10
-	vpxor	%xmm9,%xmm10,%xmm10
-
-	vpclmulqdq	$16,%xmm12,%xmm10,%xmm9
-	vpalignr	$8,%xmm10,%xmm10,%xmm10
-	vpxor	%xmm11,%xmm10,%xmm10
-	vpxor	%xmm9,%xmm10,%xmm10
-
-	cmpq	$0,%rcx
-	jne	L$short_avx
-
-	vpshufb	%xmm13,%xmm10,%xmm10
-	vmovdqu	%xmm10,(%rdi)
-	vzeroupper
-	.byte	0xf3,0xc3
+	jmp	L$_ghash_clmul
 
 .p2align	6
 L$bswap_mask:

deps/openssl/asm/x64-win32-masm/bn/rsaz-avx2.asm

@@ -1628,8 +1628,9 @@ PUBLIC	rsaz_1024_gather5_avx2
 
 ALIGN	32
 rsaz_1024_gather5_avx2	PROC PUBLIC
-	lea	rax,QWORD PTR[((-136))+rsp]
 	vzeroupper
+	mov	r11,rsp
+	lea	rax,QWORD PTR[((-136))+rsp]
 $L$SEH_begin_rsaz_1024_gather5::
 
 DB	048h,08dh,060h,0e0h
@@ -1643,66 +1644,125 @@ DB	0c5h,078h,029h,060h,040h
 DB	0c5h,078h,029h,068h,050h
 DB	0c5h,078h,029h,070h,060h
 DB	0c5h,078h,029h,078h,070h
-	lea	r11,QWORD PTR[$L$gather_table]
-	mov	eax,r8d
-	and	r8d,3
-	shr	eax,2
-	shl	r8d,4
-
-	vmovdqu	ymm7,YMMWORD PTR[((-32))+r11]
-	vpbroadcastb	xmm8,BYTE PTR[8+rax*1+r11]
-	vpbroadcastb	xmm9,BYTE PTR[7+rax*1+r11]
-	vpbroadcastb	xmm10,BYTE PTR[6+rax*1+r11]
-	vpbroadcastb	xmm11,BYTE PTR[5+rax*1+r11]
-	vpbroadcastb	xmm12,BYTE PTR[4+rax*1+r11]
-	vpbroadcastb	xmm13,BYTE PTR[3+rax*1+r11]
-	vpbroadcastb	xmm14,BYTE PTR[2+rax*1+r11]
-	vpbroadcastb	xmm15,BYTE PTR[1+rax*1+r11]
-
-	lea	rdx,QWORD PTR[64+r8*1+rdx]
-	mov	r11,64
-	mov	eax,9
-	jmp	$L$oop_gather_1024
+	lea	rsp,QWORD PTR[((-256))+rsp]
+	and	rsp,-32
+	lea	r10,QWORD PTR[$L$inc]
+	lea	rax,QWORD PTR[((-128))+rsp]
+
+	vmovd	xmm4,r8d
+	vmovdqa	ymm0,YMMWORD PTR[r10]
+	vmovdqa	ymm1,YMMWORD PTR[32+r10]
+	vmovdqa	ymm5,YMMWORD PTR[64+r10]
+	vpbroadcastd	ymm4,xmm4
+
+	vpaddd	ymm2,ymm0,ymm5
+	vpcmpeqd	ymm0,ymm0,ymm4
+	vpaddd	ymm3,ymm1,ymm5
+	vpcmpeqd	ymm1,ymm1,ymm4
+	vmovdqa	YMMWORD PTR[(0+128)+rax],ymm0
+	vpaddd	ymm0,ymm2,ymm5
+	vpcmpeqd	ymm2,ymm2,ymm4
+	vmovdqa	YMMWORD PTR[(32+128)+rax],ymm1
+	vpaddd	ymm1,ymm3,ymm5
+	vpcmpeqd	ymm3,ymm3,ymm4
+	vmovdqa	YMMWORD PTR[(64+128)+rax],ymm2
+	vpaddd	ymm2,ymm0,ymm5
+	vpcmpeqd	ymm0,ymm0,ymm4
+	vmovdqa	YMMWORD PTR[(96+128)+rax],ymm3
+	vpaddd	ymm3,ymm1,ymm5
+	vpcmpeqd	ymm1,ymm1,ymm4
+	vmovdqa	YMMWORD PTR[(128+128)+rax],ymm0
+	vpaddd	ymm8,ymm2,ymm5
+	vpcmpeqd	ymm2,ymm2,ymm4
+	vmovdqa	YMMWORD PTR[(160+128)+rax],ymm1
+	vpaddd	ymm9,ymm3,ymm5
+	vpcmpeqd	ymm3,ymm3,ymm4
+	vmovdqa	YMMWORD PTR[(192+128)+rax],ymm2
+	vpaddd	ymm10,ymm8,ymm5
+	vpcmpeqd	ymm8,ymm8,ymm4
+	vmovdqa	YMMWORD PTR[(224+128)+rax],ymm3
+	vpaddd	ymm11,ymm9,ymm5
+	vpcmpeqd	ymm9,ymm9,ymm4
+	vpaddd	ymm12,ymm10,ymm5
+	vpcmpeqd	ymm10,ymm10,ymm4
+	vpaddd	ymm13,ymm11,ymm5
+	vpcmpeqd	ymm11,ymm11,ymm4
+	vpaddd	ymm14,ymm12,ymm5
+	vpcmpeqd	ymm12,ymm12,ymm4
+	vpaddd	ymm15,ymm13,ymm5
+	vpcmpeqd	ymm13,ymm13,ymm4
+	vpcmpeqd	ymm14,ymm14,ymm4
+	vpcmpeqd	ymm15,ymm15,ymm4
+
+	vmovdqa	ymm7,YMMWORD PTR[((-32))+r10]
+	lea	rdx,QWORD PTR[128+rdx]
+	mov	r8d,9
 
-ALIGN	32
 $L$oop_gather_1024::
-	vpand	xmm0,xmm8,XMMWORD PTR[((-64))+rdx]
-	vpand	xmm1,xmm9,XMMWORD PTR[rdx]
-	vpand	xmm2,xmm10,XMMWORD PTR[64+rdx]
-	vpand	xmm3,xmm11,XMMWORD PTR[r11*2+rdx]
-	vpor	xmm1,xmm1,xmm0
-	vpand	xmm4,xmm12,XMMWORD PTR[64+r11*2+rdx]
-	vpor	xmm3,xmm3,xmm2
-	vpand	xmm5,xmm13,XMMWORD PTR[r11*4+rdx]
-	vpor	xmm3,xmm3,xmm1
-	vpand	xmm6,xmm14,XMMWORD PTR[64+r11*4+rdx]
+	vmovdqa	ymm0,YMMWORD PTR[((0-128))+rdx]
+	vmovdqa	ymm1,YMMWORD PTR[((32-128))+rdx]
+	vmovdqa	ymm2,YMMWORD PTR[((64-128))+rdx]
+	vmovdqa	ymm3,YMMWORD PTR[((96-128))+rdx]
+	vpand	ymm0,ymm0,YMMWORD PTR[((0+128))+rax]
+	vpand	ymm1,ymm1,YMMWORD PTR[((32+128))+rax]
+	vpand	ymm2,ymm2,YMMWORD PTR[((64+128))+rax]
+	vpor	ymm4,ymm1,ymm0
+	vpand	ymm3,ymm3,YMMWORD PTR[((96+128))+rax]
+	vmovdqa	ymm0,YMMWORD PTR[((128-128))+rdx]
+	vmovdqa	ymm1,YMMWORD PTR[((160-128))+rdx]
+	vpor	ymm5,ymm3,ymm2
+	vmovdqa	ymm2,YMMWORD PTR[((192-128))+rdx]
+	vmovdqa	ymm3,YMMWORD PTR[((224-128))+rdx]
+	vpand	ymm0,ymm0,YMMWORD PTR[((128+128))+rax]
+	vpand	ymm1,ymm1,YMMWORD PTR[((160+128))+rax]
+	vpand	ymm2,ymm2,YMMWORD PTR[((192+128))+rax]
+	vpor	ymm4,ymm4,ymm0
+	vpand	ymm3,ymm3,YMMWORD PTR[((224+128))+rax]
+	vpand	ymm0,ymm8,YMMWORD PTR[((256-128))+rdx]
+	vpor	ymm5,ymm5,ymm1
+	vpand	ymm1,ymm9,YMMWORD PTR[((288-128))+rdx]
+	vpor	ymm4,ymm4,ymm2
+	vpand	ymm2,ymm10,YMMWORD PTR[((320-128))+rdx]
+	vpor	ymm5,ymm5,ymm3
+	vpand	ymm3,ymm11,YMMWORD PTR[((352-128))+rdx]
+	vpor	ymm4,ymm4,ymm0
+	vpand	ymm0,ymm12,YMMWORD PTR[((384-128))+rdx]
+	vpor	ymm5,ymm5,ymm1
+	vpand	ymm1,ymm13,YMMWORD PTR[((416-128))+rdx]
+	vpor	ymm4,ymm4,ymm2
+	vpand	ymm2,ymm14,YMMWORD PTR[((448-128))+rdx]
+	vpor	ymm5,ymm5,ymm3
+	vpand	ymm3,ymm15,YMMWORD PTR[((480-128))+rdx]
+	lea	rdx,QWORD PTR[512+rdx]
+	vpor	ymm4,ymm4,ymm0
+	vpor	ymm5,ymm5,ymm1
+	vpor	ymm4,ymm4,ymm2
+	vpor	ymm5,ymm5,ymm3
+
+	vpor	ymm4,ymm4,ymm5
+	vextracti128	xmm5,ymm4,1
 	vpor	xmm5,xmm5,xmm4
-	vpand	xmm2,xmm15,XMMWORD PTR[((-128))+r11*8+rdx]
-	lea	rdx,QWORD PTR[r11*8+rdx]
-	vpor	xmm5,xmm5,xmm3
-	vpor	xmm6,xmm6,xmm2
-	vpor	xmm6,xmm6,xmm5
-	vpermd	ymm6,ymm7,ymm6
-	vmovdqu	YMMWORD PTR[rcx],ymm6
+	vpermd	ymm5,ymm7,ymm5
+	vmovdqu	YMMWORD PTR[rcx],ymm5
 	lea	rcx,QWORD PTR[32+rcx]
-	dec	eax
+	dec	r8d
 	jnz	$L$oop_gather_1024
 
 	vpxor	ymm0,ymm0,ymm0
 	vmovdqu	YMMWORD PTR[rcx],ymm0
 	vzeroupper
-	movaps	xmm6,XMMWORD PTR[rsp]
-	movaps	xmm7,XMMWORD PTR[16+rsp]
-	movaps	xmm8,XMMWORD PTR[32+rsp]
-	movaps	xmm9,XMMWORD PTR[48+rsp]
-	movaps	xmm10,XMMWORD PTR[64+rsp]
-	movaps	xmm11,XMMWORD PTR[80+rsp]
-	movaps	xmm12,XMMWORD PTR[96+rsp]
-	movaps	xmm13,XMMWORD PTR[112+rsp]
-	movaps	xmm14,XMMWORD PTR[128+rsp]
-	movaps	xmm15,XMMWORD PTR[144+rsp]
-	lea	rsp,QWORD PTR[168+rsp]
+	movaps	xmm6,XMMWORD PTR[((-168))+r11]
+	movaps	xmm7,XMMWORD PTR[((-152))+r11]
+	movaps	xmm8,XMMWORD PTR[((-136))+r11]
+	movaps	xmm9,XMMWORD PTR[((-120))+r11]
+	movaps	xmm10,XMMWORD PTR[((-104))+r11]
+	movaps	xmm11,XMMWORD PTR[((-88))+r11]
+	movaps	xmm12,XMMWORD PTR[((-72))+r11]
+	movaps	xmm13,XMMWORD PTR[((-56))+r11]
+	movaps	xmm14,XMMWORD PTR[((-40))+r11]
+	movaps	xmm15,XMMWORD PTR[((-24))+r11]
 $L$SEH_end_rsaz_1024_gather5::
+	lea	rsp,QWORD PTR[r11]
 	DB	0F3h,0C3h		;repret
 rsaz_1024_gather5_avx2	ENDP
 EXTERN	OPENSSL_ia32cap_P:NEAR
@@ -1728,8 +1788,10 @@ $L$scatter_permd::
 	DD	0,2,4,6,7,7,7,7
 $L$gather_permd::
 	DD	0,7,1,7,2,7,3,7
-$L$gather_table::
-DB	0,0,0,0,0,0,0,0,0ffh,0,0,0,0,0,0,0
+$L$inc::
+	DD	0,0,0,0,1,1,1,1
+	DD	2,2,2,2,3,3,3,3
+	DD	4,4,4,4,4,4,4,4
 ALIGN	64
 EXTERN	__imp_RtlVirtualUnwind:NEAR
 
@@ -1850,7 +1912,7 @@ DB	9,0,0,0
 	DD	imagerel rsaz_se_handler
 	DD	imagerel $L$mul_1024_body,imagerel $L$mul_1024_epilogue
 $L$SEH_info_rsaz_1024_gather5::
-DB	001h,033h,016h,000h
+DB	001h,036h,017h,00bh
 DB	036h,0f8h,009h,000h
 DB	031h,0e8h,008h,000h
 DB	02ch,0d8h,007h,000h
@@ -1862,6 +1924,7 @@ DB	013h,088h,002h,000h
 DB	00eh,078h,001h,000h
 DB	009h,068h,000h,000h
 DB	004h,001h,015h,000h
+DB	000h,0b3h,000h,000h
 
 .xdata	ENDS
 END

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

@@ -803,52 +803,108 @@ $L$SEH_begin_rsaz_512_mul_gather4::
 	push	r14
 	push	r15
 
-	mov	r9d,r9d
-	sub	rsp,128+24
+	sub	rsp,328
+	movaps	XMMWORD PTR[160+rsp],xmm6
+	movaps	XMMWORD PTR[176+rsp],xmm7
+	movaps	XMMWORD PTR[192+rsp],xmm8
+	movaps	XMMWORD PTR[208+rsp],xmm9
+	movaps	XMMWORD PTR[224+rsp],xmm10
+	movaps	XMMWORD PTR[240+rsp],xmm11
+	movaps	XMMWORD PTR[256+rsp],xmm12
+	movaps	XMMWORD PTR[272+rsp],xmm13
+	movaps	XMMWORD PTR[288+rsp],xmm14
+	movaps	XMMWORD PTR[304+rsp],xmm15
 $L$mul_gather4_body::
+	movd	xmm8,r9d
+	movdqa	xmm1,XMMWORD PTR[(($L$inc+16))]
+	movdqa	xmm0,XMMWORD PTR[$L$inc]
+
+	pshufd	xmm8,xmm8,0
+	movdqa	xmm7,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm8
+	movdqa	xmm3,xmm7
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm8
+	movdqa	xmm4,xmm7
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm8
+	movdqa	xmm5,xmm7
+	paddd	xmm4,xmm3
+	pcmpeqd	xmm3,xmm8
+	movdqa	xmm6,xmm7
+	paddd	xmm5,xmm4
+	pcmpeqd	xmm4,xmm8
+	paddd	xmm6,xmm5
+	pcmpeqd	xmm5,xmm8
+	paddd	xmm7,xmm6
+	pcmpeqd	xmm6,xmm8
+	pcmpeqd	xmm7,xmm8
+
+	movdqa	xmm8,XMMWORD PTR[rdx]
+	movdqa	xmm9,XMMWORD PTR[16+rdx]
+	movdqa	xmm10,XMMWORD PTR[32+rdx]
+	movdqa	xmm11,XMMWORD PTR[48+rdx]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rdx]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rdx]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rdx]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rdx]
+	lea	rbp,QWORD PTR[128+rdx]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
 	mov	r11d,080100h
 	and	r11d,DWORD PTR[((OPENSSL_ia32cap_P+8))]
 	cmp	r11d,080100h
 	je	$L$mulx_gather
-	mov	eax,DWORD PTR[64+r9*4+rdx]
-DB	102,72,15,110,199
-	mov	ebx,DWORD PTR[r9*4+rdx]
-DB	102,72,15,110,201
+DB	102,76,15,126,195
+
 	mov	QWORD PTR[128+rsp],r8
+	mov	QWORD PTR[((128+8))+rsp],rdi
+	mov	QWORD PTR[((128+16))+rsp],rcx
 
-	shl	rax,32
-	or	rbx,rax
 	mov	rax,QWORD PTR[rsi]
 	mov	rcx,QWORD PTR[8+rsi]
-	lea	rbp,QWORD PTR[128+r9*4+rdx]
 	mul	rbx
 	mov	QWORD PTR[rsp],rax
 	mov	rax,rcx
 	mov	r8,rdx
 
 	mul	rbx
-	movd	xmm4,DWORD PTR[rbp]
 	add	r8,rax
 	mov	rax,QWORD PTR[16+rsi]
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD PTR[64+rbp]
 	add	r9,rax
 	mov	rax,QWORD PTR[24+rsi]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
-	pslldq	xmm5,4
 	add	r10,rax
 	mov	rax,QWORD PTR[32+rsi]
 	mov	r11,rdx
 	adc	r11,0
 
 	mul	rbx
-	por	xmm4,xmm5
 	add	r11,rax
 	mov	rax,QWORD PTR[40+rsi]
 	mov	r12,rdx
@@ -861,14 +917,12 @@ DB	102,72,15,110,201
 	adc	r13,0
 
 	mul	rbx
-	lea	rbp,QWORD PTR[128+rbp]
 	add	r13,rax
 	mov	rax,QWORD PTR[56+rsi]
 	mov	r14,rdx
 	adc	r14,0
 
 	mul	rbx
-DB	102,72,15,126,227
 	add	r14,rax
 	mov	rax,QWORD PTR[rsi]
 	mov	r15,rdx
@@ -880,6 +934,35 @@ DB	102,72,15,126,227
 
 ALIGN	32
 $L$oop_mul_gather::
+	movdqa	xmm8,XMMWORD PTR[rbp]
+	movdqa	xmm9,XMMWORD PTR[16+rbp]
+	movdqa	xmm10,XMMWORD PTR[32+rbp]
+	movdqa	xmm11,XMMWORD PTR[48+rbp]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rbp]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rbp]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rbp]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rbp]
+	lea	rbp,QWORD PTR[128+rbp]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
+DB	102,76,15,126,195
+
 	mul	rbx
 	add	r8,rax
 	mov	rax,QWORD PTR[8+rsi]
@@ -888,7 +971,6 @@ $L$oop_mul_gather::
 	adc	r8,0
 
 	mul	rbx
-	movd	xmm4,DWORD PTR[rbp]
 	add	r9,rax
 	mov	rax,QWORD PTR[16+rsi]
 	adc	rdx,0
@@ -897,7 +979,6 @@ $L$oop_mul_gather::
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD PTR[64+rbp]
 	add	r10,rax
 	mov	rax,QWORD PTR[24+rsi]
 	adc	rdx,0
@@ -906,7 +987,6 @@ $L$oop_mul_gather::
 	adc	r10,0
 
 	mul	rbx
-	pslldq	xmm5,4
 	add	r11,rax
 	mov	rax,QWORD PTR[32+rsi]
 	adc	rdx,0
@@ -915,7 +995,6 @@ $L$oop_mul_gather::
 	adc	r11,0
 
 	mul	rbx
-	por	xmm4,xmm5
 	add	r12,rax
 	mov	rax,QWORD PTR[40+rsi]
 	adc	rdx,0
@@ -940,7 +1019,6 @@ $L$oop_mul_gather::
 	adc	r14,0
 
 	mul	rbx
-DB	102,72,15,126,227
 	add	r15,rax
 	mov	rax,QWORD PTR[rsi]
 	adc	rdx,0
@@ -948,7 +1026,6 @@ DB	102,72,15,126,227
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rbp,QWORD PTR[128+rbp]
 	lea	rdi,QWORD PTR[8+rdi]
 
 	dec	ecx
@@ -963,8 +1040,8 @@ DB	102,72,15,126,227
 	mov	QWORD PTR[48+rdi],r14
 	mov	QWORD PTR[56+rdi],r15
 
-DB	102,72,15,126,199
-DB	102,72,15,126,205
+	mov	rdi,QWORD PTR[((128+8))+rsp]
+	mov	rbp,QWORD PTR[((128+16))+rsp]
 
 	mov	r8,QWORD PTR[rsp]
 	mov	r9,QWORD PTR[8+rsp]
@@ -980,45 +1057,37 @@ DB	102,72,15,126,205
 
 ALIGN	32
 $L$mulx_gather::
-	mov	eax,DWORD PTR[64+r9*4+rdx]
-DB	102,72,15,110,199
-	lea	rbp,QWORD PTR[128+r9*4+rdx]
-	mov	edx,DWORD PTR[r9*4+rdx]
-DB	102,72,15,110,201
+DB	102,76,15,126,194
+
 	mov	QWORD PTR[128+rsp],r8
+	mov	QWORD PTR[((128+8))+rsp],rdi
+	mov	QWORD PTR[((128+16))+rsp],rcx
 
-	shl	rax,32
-	or	rdx,rax
 	mulx	r8,rbx,QWORD PTR[rsi]
 	mov	QWORD PTR[rsp],rbx
 	xor	edi,edi
 
 	mulx	r9,rax,QWORD PTR[8+rsi]
-	movd	xmm4,DWORD PTR[rbp]
 
 	mulx	r10,rbx,QWORD PTR[16+rsi]
-	movd	xmm5,DWORD PTR[64+rbp]
 	adcx	r8,rax
 
 	mulx	r11,rax,QWORD PTR[24+rsi]
-	pslldq	xmm5,4
 	adcx	r9,rbx
 
 	mulx	r12,rbx,QWORD PTR[32+rsi]
-	por	xmm4,xmm5
 	adcx	r10,rax
 
 	mulx	r13,rax,QWORD PTR[40+rsi]
 	adcx	r11,rbx
 
 	mulx	r14,rbx,QWORD PTR[48+rsi]
-	lea	rbp,QWORD PTR[128+rbp]
 	adcx	r12,rax
 
 	mulx	r15,rax,QWORD PTR[56+rsi]
-DB	102,72,15,126,226
 	adcx	r13,rbx
 	adcx	r14,rax
+DB	067h
 	mov	rbx,r8
 	adcx	r15,rdi
 
@@ -1027,24 +1096,48 @@ DB	102,72,15,126,226
 
 ALIGN	32
 $L$oop_mulx_gather::
-	mulx	r8,rax,QWORD PTR[rsi]
+	movdqa	xmm8,XMMWORD PTR[rbp]
+	movdqa	xmm9,XMMWORD PTR[16+rbp]
+	movdqa	xmm10,XMMWORD PTR[32+rbp]
+	movdqa	xmm11,XMMWORD PTR[48+rbp]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rbp]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rbp]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rbp]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rbp]
+	lea	rbp,QWORD PTR[128+rbp]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
+DB	102,76,15,126,194
+
+DB	0c4h,062h,0fbh,0f6h,086h,000h,000h,000h,000h
 	adcx	rbx,rax
 	adox	r8,r9
 
 	mulx	r9,rax,QWORD PTR[8+rsi]
-DB	066h,00fh,06eh,0a5h,000h,000h,000h,000h
 	adcx	r8,rax
 	adox	r9,r10
 
 	mulx	r10,rax,QWORD PTR[16+rsi]
-	movd	xmm5,DWORD PTR[64+rbp]
-	lea	rbp,QWORD PTR[128+rbp]
 	adcx	r9,rax
 	adox	r10,r11
 
 DB	0c4h,062h,0fbh,0f6h,09eh,018h,000h,000h,000h
-	pslldq	xmm5,4
-	por	xmm4,xmm5
 	adcx	r10,rax
 	adox	r11,r12
 
@@ -1058,10 +1151,10 @@ DB	0c4h,062h,0fbh,0f6h,09eh,018h,000h,000h,000h
 
 DB	0c4h,062h,0fbh,0f6h,0b6h,030h,000h,000h,000h
 	adcx	r13,rax
+DB	067h
 	adox	r14,r15
 
 	mulx	r15,rax,QWORD PTR[56+rsi]
-DB	102,72,15,126,226
 	mov	QWORD PTR[64+rcx*8+rsp],rbx
 	adcx	r14,rax
 	adox	r15,rdi
@@ -1080,10 +1173,10 @@ DB	102,72,15,126,226
 	mov	QWORD PTR[((64+48))+rsp],r14
 	mov	QWORD PTR[((64+56))+rsp],r15
 
-DB	102,72,15,126,199
-DB	102,72,15,126,205
-
 	mov	rdx,QWORD PTR[128+rsp]
+	mov	rdi,QWORD PTR[((128+8))+rsp]
+	mov	rbp,QWORD PTR[((128+16))+rsp]
+
 	mov	r8,QWORD PTR[rsp]
 	mov	r9,QWORD PTR[8+rsp]
 	mov	r10,QWORD PTR[16+rsp]
@@ -1109,6 +1202,17 @@ $L$mul_gather_tail::
 	call	__rsaz_512_subtract
 
 	lea	rax,QWORD PTR[((128+24+48))+rsp]
+	movaps	xmm6,XMMWORD PTR[((160-200))+rax]
+	movaps	xmm7,XMMWORD PTR[((176-200))+rax]
+	movaps	xmm8,XMMWORD PTR[((192-200))+rax]
+	movaps	xmm9,XMMWORD PTR[((208-200))+rax]
+	movaps	xmm10,XMMWORD PTR[((224-200))+rax]
+	movaps	xmm11,XMMWORD PTR[((240-200))+rax]
+	movaps	xmm12,XMMWORD PTR[((256-200))+rax]
+	movaps	xmm13,XMMWORD PTR[((272-200))+rax]
+	movaps	xmm14,XMMWORD PTR[((288-200))+rax]
+	movaps	xmm15,XMMWORD PTR[((304-200))+rax]
+	lea	rax,QWORD PTR[176+rax]
 	mov	r15,QWORD PTR[((-48))+rax]
 	mov	r14,QWORD PTR[((-40))+rax]
 	mov	r13,QWORD PTR[((-32))+rax]
@@ -1148,7 +1252,7 @@ $L$SEH_begin_rsaz_512_mul_scatter4::
 	mov	r9d,r9d
 	sub	rsp,128+24
 $L$mul_scatter4_body::
-	lea	r8,QWORD PTR[r9*4+r8]
+	lea	r8,QWORD PTR[r9*8+r8]
 DB	102,72,15,110,199
 DB	102,72,15,110,202
 DB	102,73,15,110,208
@@ -1211,30 +1315,14 @@ DB	102,72,15,126,214
 
 	call	__rsaz_512_subtract
 
-	mov	DWORD PTR[rsi],r8d
-	shr	r8,32
-	mov	DWORD PTR[128+rsi],r9d
-	shr	r9,32
-	mov	DWORD PTR[256+rsi],r10d
-	shr	r10,32
-	mov	DWORD PTR[384+rsi],r11d
-	shr	r11,32
-	mov	DWORD PTR[512+rsi],r12d
-	shr	r12,32
-	mov	DWORD PTR[640+rsi],r13d
-	shr	r13,32
-	mov	DWORD PTR[768+rsi],r14d
-	shr	r14,32
-	mov	DWORD PTR[896+rsi],r15d
-	shr	r15,32
-	mov	DWORD PTR[64+rsi],r8d
-	mov	DWORD PTR[192+rsi],r9d
-	mov	DWORD PTR[320+rsi],r10d
-	mov	DWORD PTR[448+rsi],r11d
-	mov	DWORD PTR[576+rsi],r12d
-	mov	DWORD PTR[704+rsi],r13d
-	mov	DWORD PTR[832+rsi],r14d
-	mov	DWORD PTR[960+rsi],r15d
+	mov	QWORD PTR[rsi],r8
+	mov	QWORD PTR[128+rsi],r9
+	mov	QWORD PTR[256+rsi],r10
+	mov	QWORD PTR[384+rsi],r11
+	mov	QWORD PTR[512+rsi],r12
+	mov	QWORD PTR[640+rsi],r13
+	mov	QWORD PTR[768+rsi],r14
+	mov	QWORD PTR[896+rsi],r15
 
 	lea	rax,QWORD PTR[((128+24+48))+rsp]
 	mov	r15,QWORD PTR[((-48))+rax]
@@ -1789,16 +1877,14 @@ PUBLIC	rsaz_512_scatter4
 
 ALIGN	16
 rsaz_512_scatter4	PROC PUBLIC
-	lea	rcx,QWORD PTR[r8*4+rcx]
+	lea	rcx,QWORD PTR[r8*8+rcx]
 	mov	r9d,8
 	jmp	$L$oop_scatter
 ALIGN	16
 $L$oop_scatter::
 	mov	rax,QWORD PTR[rdx]
 	lea	rdx,QWORD PTR[8+rdx]
-	mov	DWORD PTR[rcx],eax
-	shr	rax,32
-	mov	DWORD PTR[64+rcx],eax
+	mov	QWORD PTR[rcx],rax
 	lea	rcx,QWORD PTR[128+rcx]
 	dec	r9d
 	jnz	$L$oop_scatter
@@ -1809,22 +1895,98 @@ PUBLIC	rsaz_512_gather4
 
 ALIGN	16
 rsaz_512_gather4	PROC PUBLIC
-	lea	rdx,QWORD PTR[r8*4+rdx]
+$L$SEH_begin_rsaz_512_gather4::
+DB	048h,081h,0ech,0a8h,000h,000h,000h
+DB	00fh,029h,034h,024h
+DB	00fh,029h,07ch,024h,010h
+DB	044h,00fh,029h,044h,024h,020h
+DB	044h,00fh,029h,04ch,024h,030h
+DB	044h,00fh,029h,054h,024h,040h
+DB	044h,00fh,029h,05ch,024h,050h
+DB	044h,00fh,029h,064h,024h,060h
+DB	044h,00fh,029h,06ch,024h,070h
+DB	044h,00fh,029h,0b4h,024h,080h,0,0,0
+DB	044h,00fh,029h,0bch,024h,090h,0,0,0
+	movd	xmm8,r8d
+	movdqa	xmm1,XMMWORD PTR[(($L$inc+16))]
+	movdqa	xmm0,XMMWORD PTR[$L$inc]
+
+	pshufd	xmm8,xmm8,0
+	movdqa	xmm7,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm8
+	movdqa	xmm3,xmm7
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm8
+	movdqa	xmm4,xmm7
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm8
+	movdqa	xmm5,xmm7
+	paddd	xmm4,xmm3
+	pcmpeqd	xmm3,xmm8
+	movdqa	xmm6,xmm7
+	paddd	xmm5,xmm4
+	pcmpeqd	xmm4,xmm8
+	paddd	xmm6,xmm5
+	pcmpeqd	xmm5,xmm8
+	paddd	xmm7,xmm6
+	pcmpeqd	xmm6,xmm8
+	pcmpeqd	xmm7,xmm8
 	mov	r9d,8
 	jmp	$L$oop_gather
 ALIGN	16
 $L$oop_gather::
-	mov	eax,DWORD PTR[rdx]
-	mov	r8d,DWORD PTR[64+rdx]
+	movdqa	xmm8,XMMWORD PTR[rdx]
+	movdqa	xmm9,XMMWORD PTR[16+rdx]
+	movdqa	xmm10,XMMWORD PTR[32+rdx]
+	movdqa	xmm11,XMMWORD PTR[48+rdx]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rdx]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rdx]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rdx]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rdx]
 	lea	rdx,QWORD PTR[128+rdx]
-	shl	r8,32
-	or	rax,r8
-	mov	QWORD PTR[rcx],rax
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
+	movq	QWORD PTR[rcx],xmm8
 	lea	rcx,QWORD PTR[8+rcx]
 	dec	r9d
 	jnz	$L$oop_gather
+	movaps	xmm6,XMMWORD PTR[rsp]
+	movaps	xmm7,XMMWORD PTR[16+rsp]
+	movaps	xmm8,XMMWORD PTR[32+rsp]
+	movaps	xmm9,XMMWORD PTR[48+rsp]
+	movaps	xmm10,XMMWORD PTR[64+rsp]
+	movaps	xmm11,XMMWORD PTR[80+rsp]
+	movaps	xmm12,XMMWORD PTR[96+rsp]
+	movaps	xmm13,XMMWORD PTR[112+rsp]
+	movaps	xmm14,XMMWORD PTR[128+rsp]
+	movaps	xmm15,XMMWORD PTR[144+rsp]
+	add	rsp,0a8h
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_rsaz_512_gather4::
 rsaz_512_gather4	ENDP
+
+ALIGN	64
+$L$inc::
+	DD	0,0,1,1
+	DD	2,2,2,2
 EXTERN	__imp_RtlVirtualUnwind:NEAR
 
 ALIGN	16
@@ -1860,6 +2022,18 @@ se_handler	PROC PRIVATE
 
 	lea	rax,QWORD PTR[((128+24+48))+rax]
 
+	lea	rbx,QWORD PTR[$L$mul_gather4_epilogue]
+	cmp	rbx,r10
+	jne	$L$se_not_in_mul_gather4
+
+	lea	rax,QWORD PTR[176+rax]
+
+	lea	rsi,QWORD PTR[((-48-168))+rax]
+	lea	rdi,QWORD PTR[512+r8]
+	mov	ecx,20
+	DD	0a548f3fch
+
+$L$se_not_in_mul_gather4::
 	mov	rbx,QWORD PTR[((-8))+rax]
 	mov	rbp,QWORD PTR[((-16))+rax]
 	mov	r12,QWORD PTR[((-24))+rax]
@@ -1936,6 +2110,10 @@ ALIGN	4
 	DD	imagerel $L$SEH_end_rsaz_512_mul_by_one
 	DD	imagerel $L$SEH_info_rsaz_512_mul_by_one
 
+	DD	imagerel $L$SEH_begin_rsaz_512_gather4
+	DD	imagerel $L$SEH_end_rsaz_512_gather4
+	DD	imagerel $L$SEH_info_rsaz_512_gather4
+
 .pdata	ENDS
 .xdata	SEGMENT READONLY ALIGN(8)
 ALIGN	8
@@ -1959,6 +2137,19 @@ $L$SEH_info_rsaz_512_mul_by_one::
 DB	9,0,0,0
 	DD	imagerel se_handler
 	DD	imagerel $L$mul_by_one_body,imagerel $L$mul_by_one_epilogue
+$L$SEH_info_rsaz_512_gather4::
+DB	001h,046h,016h,000h
+DB	046h,0f8h,009h,000h
+DB	03dh,0e8h,008h,000h
+DB	034h,0d8h,007h,000h
+DB	02eh,0c8h,006h,000h
+DB	028h,0b8h,005h,000h
+DB	022h,0a8h,004h,000h
+DB	01ch,098h,003h,000h
+DB	016h,088h,002h,000h
+DB	010h,078h,001h,000h
+DB	00bh,068h,000h,000h
+DB	007h,001h,015h,000h
 
 .xdata	ENDS
 END

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

@@ -681,20 +681,20 @@ $L$sqr8x_enter::
 
 
 
-	lea	r11,QWORD PTR[((-64))+r9*4+rsp]
+	lea	r11,QWORD PTR[((-64))+r9*2+rsp]
 	mov	r8,QWORD PTR[r8]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
 	jb	$L$sqr8x_sp_alt
 	sub	rsp,r11
-	lea	rsp,QWORD PTR[((-64))+r9*4+rsp]
+	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
 	jmp	$L$sqr8x_sp_done
 
 ALIGN	32
 $L$sqr8x_sp_alt::
-	lea	r10,QWORD PTR[((4096-64))+r9*4]
-	lea	rsp,QWORD PTR[((-64))+r9*4+rsp]
+	lea	r10,QWORD PTR[((4096-64))+r9*2]
+	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
@@ -704,73 +704,99 @@ $L$sqr8x_sp_done::
 	mov	r10,r9
 	neg	r9
 
-	lea	r11,QWORD PTR[64+r9*2+rsp]
 	mov	QWORD PTR[32+rsp],r8
 	mov	QWORD PTR[40+rsp],rax
 $L$sqr8x_body::
 
-	mov	rbp,r9
-DB	102,73,15,110,211
-	shr	rbp,3+2
-	mov	eax,DWORD PTR[((OPENSSL_ia32cap_P+8))]
-	jmp	$L$sqr8x_copy_n
-
-ALIGN	32
-$L$sqr8x_copy_n::
-	movq	xmm0,QWORD PTR[rcx]
-	movq	xmm1,QWORD PTR[8+rcx]
-	movq	xmm3,QWORD PTR[16+rcx]
-	movq	xmm4,QWORD PTR[24+rcx]
-	lea	rcx,QWORD PTR[32+rcx]
-	movdqa	XMMWORD PTR[r11],xmm0
-	movdqa	XMMWORD PTR[16+r11],xmm1
-	movdqa	XMMWORD PTR[32+r11],xmm3
-	movdqa	XMMWORD PTR[48+r11],xmm4
-	lea	r11,QWORD PTR[64+r11]
-	dec	rbp
-	jnz	$L$sqr8x_copy_n
-
+DB	102,72,15,110,209
 	pxor	xmm0,xmm0
 DB	102,72,15,110,207
 DB	102,73,15,110,218
+	mov	eax,DWORD PTR[((OPENSSL_ia32cap_P+8))]
 	and	eax,080100h
 	cmp	eax,080100h
 	jne	$L$sqr8x_nox
 
 	call	bn_sqrx8x_internal
 
-	pxor	xmm0,xmm0
-	lea	rax,QWORD PTR[48+rsp]
-	lea	rdx,QWORD PTR[64+r9*2+rsp]
-	shr	r9,3+2
-	mov	rsi,QWORD PTR[40+rsp]
-	jmp	$L$sqr8x_zero
+
+
+
+	lea	rbx,QWORD PTR[rcx*1+r8]
+	mov	r9,rcx
+	mov	rdx,rcx
+DB	102,72,15,126,207
+	sar	rcx,3+2
+	jmp	$L$sqr8x_sub
 
 ALIGN	32
 $L$sqr8x_nox::
 	call	bn_sqr8x_internal
 
+
+
+
+	lea	rbx,QWORD PTR[r9*1+rdi]
+	mov	rcx,r9
+	mov	rdx,r9
+DB	102,72,15,126,207
+	sar	rcx,3+2
+	jmp	$L$sqr8x_sub
+
+ALIGN	32
+$L$sqr8x_sub::
+	mov	r12,QWORD PTR[rbx]
+	mov	r13,QWORD PTR[8+rbx]
+	mov	r14,QWORD PTR[16+rbx]
+	mov	r15,QWORD PTR[24+rbx]
+	lea	rbx,QWORD PTR[32+rbx]
+	sbb	r12,QWORD PTR[rbp]
+	sbb	r13,QWORD PTR[8+rbp]
+	sbb	r14,QWORD PTR[16+rbp]
+	sbb	r15,QWORD PTR[24+rbp]
+	lea	rbp,QWORD PTR[32+rbp]
+	mov	QWORD PTR[rdi],r12
+	mov	QWORD PTR[8+rdi],r13
+	mov	QWORD PTR[16+rdi],r14
+	mov	QWORD PTR[24+rdi],r15
+	lea	rdi,QWORD PTR[32+rdi]
+	inc	rcx
+	jnz	$L$sqr8x_sub
+
+	sbb	rax,0
+	lea	rbx,QWORD PTR[r9*1+rbx]
+	lea	rdi,QWORD PTR[r9*1+rdi]
+
+DB	102,72,15,110,200
 	pxor	xmm0,xmm0
-	lea	rax,QWORD PTR[48+rsp]
-	lea	rdx,QWORD PTR[64+r9*2+rsp]
-	shr	r9,3+2
+	pshufd	xmm1,xmm1,0
 	mov	rsi,QWORD PTR[40+rsp]
-	jmp	$L$sqr8x_zero
+	jmp	$L$sqr8x_cond_copy
 
 ALIGN	32
-$L$sqr8x_zero::
-	movdqa	XMMWORD PTR[rax],xmm0
-	movdqa	XMMWORD PTR[16+rax],xmm0
-	movdqa	XMMWORD PTR[32+rax],xmm0
-	movdqa	XMMWORD PTR[48+rax],xmm0
-	lea	rax,QWORD PTR[64+rax]
-	movdqa	XMMWORD PTR[rdx],xmm0
-	movdqa	XMMWORD PTR[16+rdx],xmm0
-	movdqa	XMMWORD PTR[32+rdx],xmm0
-	movdqa	XMMWORD PTR[48+rdx],xmm0
-	lea	rdx,QWORD PTR[64+rdx]
-	dec	r9
-	jnz	$L$sqr8x_zero
+$L$sqr8x_cond_copy::
+	movdqa	xmm2,XMMWORD PTR[rbx]
+	movdqa	xmm3,XMMWORD PTR[16+rbx]
+	lea	rbx,QWORD PTR[32+rbx]
+	movdqu	xmm4,XMMWORD PTR[rdi]
+	movdqu	xmm5,XMMWORD PTR[16+rdi]
+	lea	rdi,QWORD PTR[32+rdi]
+	movdqa	XMMWORD PTR[(-32)+rbx],xmm0
+	movdqa	XMMWORD PTR[(-16)+rbx],xmm0
+	movdqa	XMMWORD PTR[(-32)+rdx*1+rbx],xmm0
+	movdqa	XMMWORD PTR[(-16)+rdx*1+rbx],xmm0
+	pcmpeqd	xmm0,xmm1
+	pand	xmm2,xmm1
+	pand	xmm3,xmm1
+	pand	xmm4,xmm0
+	pand	xmm5,xmm0
+	pxor	xmm0,xmm0
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqu	XMMWORD PTR[(-32)+rdi],xmm4
+	movdqu	XMMWORD PTR[(-16)+rdi],xmm5
+	add	r9,32
+	jnz	$L$sqr8x_cond_copy
 
 	mov	rax,1
 	mov	r15,QWORD PTR[((-48))+rsi]
@@ -1040,64 +1066,75 @@ $L$mulx4x_inner::
 	adc	r15,rbp
 	sub	rbp,QWORD PTR[rbx]
 	adc	r14,r15
-	mov	r8,QWORD PTR[((-8))+rcx]
 	sbb	r15,r15
 	mov	QWORD PTR[((-8))+rbx],r14
 
 	cmp	rdi,QWORD PTR[16+rsp]
 	jne	$L$mulx4x_outer
 
-	sub	r8,r14
-	sbb	r8,r8
-	or	r15,r8
-
-	neg	rax
-	xor	rdx,rdx
+	lea	rbx,QWORD PTR[64+rsp]
+	sub	rcx,rax
+	neg	r15
+	mov	rdx,rax
+	shr	rax,3+2
 	mov	rdi,QWORD PTR[32+rsp]
+	jmp	$L$mulx4x_sub
+
+ALIGN	32
+$L$mulx4x_sub::
+	mov	r11,QWORD PTR[rbx]
+	mov	r12,QWORD PTR[8+rbx]
+	mov	r13,QWORD PTR[16+rbx]
+	mov	r14,QWORD PTR[24+rbx]
+	lea	rbx,QWORD PTR[32+rbx]
+	sbb	r11,QWORD PTR[rcx]
+	sbb	r12,QWORD PTR[8+rcx]
+	sbb	r13,QWORD PTR[16+rcx]
+	sbb	r14,QWORD PTR[24+rcx]
+	lea	rcx,QWORD PTR[32+rcx]
+	mov	QWORD PTR[rdi],r11
+	mov	QWORD PTR[8+rdi],r12
+	mov	QWORD PTR[16+rdi],r13
+	mov	QWORD PTR[24+rdi],r14
+	lea	rdi,QWORD PTR[32+rdi]
+	dec	rax
+	jnz	$L$mulx4x_sub
+
+	sbb	r15,0
 	lea	rbx,QWORD PTR[64+rsp]
+	sub	rdi,rdx
 
+DB	102,73,15,110,207
 	pxor	xmm0,xmm0
-	mov	r8,QWORD PTR[rax*1+rcx]
-	mov	r9,QWORD PTR[8+rax*1+rcx]
-	neg	r8
-	jmp	$L$mulx4x_sub_entry
+	pshufd	xmm1,xmm1,0
+	mov	rsi,QWORD PTR[40+rsp]
+	jmp	$L$mulx4x_cond_copy
 
 ALIGN	32
-$L$mulx4x_sub::
-	mov	r8,QWORD PTR[rax*1+rcx]
-	mov	r9,QWORD PTR[8+rax*1+rcx]
-	not	r8
-$L$mulx4x_sub_entry::
-	mov	r10,QWORD PTR[16+rax*1+rcx]
-	not	r9
-	and	r8,r15
-	mov	r11,QWORD PTR[24+rax*1+rcx]
-	not	r10
-	and	r9,r15
-	not	r11
-	and	r10,r15
-	and	r11,r15
-
-	neg	rdx
-	adc	r8,QWORD PTR[rbx]
-	adc	r9,QWORD PTR[8+rbx]
-	movdqa	XMMWORD PTR[rbx],xmm0
-	adc	r10,QWORD PTR[16+rbx]
-	adc	r11,QWORD PTR[24+rbx]
-	movdqa	XMMWORD PTR[16+rbx],xmm0
+$L$mulx4x_cond_copy::
+	movdqa	xmm2,XMMWORD PTR[rbx]
+	movdqa	xmm3,XMMWORD PTR[16+rbx]
 	lea	rbx,QWORD PTR[32+rbx]
-	sbb	rdx,rdx
-
-	mov	QWORD PTR[rdi],r8
-	mov	QWORD PTR[8+rdi],r9
-	mov	QWORD PTR[16+rdi],r10
-	mov	QWORD PTR[24+rdi],r11
+	movdqu	xmm4,XMMWORD PTR[rdi]
+	movdqu	xmm5,XMMWORD PTR[16+rdi]
 	lea	rdi,QWORD PTR[32+rdi]
+	movdqa	XMMWORD PTR[(-32)+rbx],xmm0
+	movdqa	XMMWORD PTR[(-16)+rbx],xmm0
+	pcmpeqd	xmm0,xmm1
+	pand	xmm2,xmm1
+	pand	xmm3,xmm1
+	pand	xmm4,xmm0
+	pand	xmm5,xmm0
+	pxor	xmm0,xmm0
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqu	XMMWORD PTR[(-32)+rdi],xmm4
+	movdqu	XMMWORD PTR[(-16)+rdi],xmm5
+	sub	rdx,32
+	jnz	$L$mulx4x_cond_copy
 
-	add	rax,32
-	jnz	$L$mulx4x_sub
+	mov	QWORD PTR[rbx],rdx
 
-	mov	rsi,QWORD PTR[40+rsp]
 	mov	rax,1
 	mov	r15,QWORD PTR[((-48))+rsi]
 	mov	r14,QWORD PTR[((-40))+rsi]

deps/openssl/asm/x64-win32-masm/ec/ecp_nistz256-x86_64.asm

@@ -1813,6 +1813,7 @@ $L$SEH_begin_ecp_nistz256_point_double::
 	push	r15
 	sub	rsp,32*5+8
 
+$L$point_double_shortcutq::
 	movdqu	xmm0,XMMWORD PTR[rsi]
 	mov	rbx,rsi
 	movdqu	xmm1,XMMWORD PTR[16+rsi]
@@ -2091,6 +2092,7 @@ DB	102,72,15,110,199
 	mov	r14,QWORD PTR[((64+8))+rbx]
 	mov	r15,QWORD PTR[((64+16))+rbx]
 	mov	r8,QWORD PTR[((64+24))+rbx]
+DB	102,72,15,110,203
 
 	lea	rsi,QWORD PTR[((64-0))+rbx]
 	lea	rdi,QWORD PTR[32+rsp]
@@ -2182,7 +2184,7 @@ DB	102,73,15,126,217
 	test	r8,r8
 	jnz	$L$add_proceedq
 	test	r9,r9
-	jz	$L$add_proceedq
+	jz	$L$add_doubleq
 
 DB	102,72,15,126,199
 	pxor	xmm0,xmm0
@@ -2194,6 +2196,13 @@ DB	102,72,15,126,199
 	movdqu	XMMWORD PTR[80+rdi],xmm0
 	jmp	$L$add_doneq
 
+ALIGN	32
+$L$add_doubleq::
+DB	102,72,15,126,206
+DB	102,72,15,126,199
+	add	rsp,416
+	jmp	$L$point_double_shortcutq
+
 ALIGN	32
 $L$add_proceedq::
 	mov	rax,QWORD PTR[((0+64))+rsp]
@@ -2876,6 +2885,7 @@ $L$point_doublex::
 	push	r15
 	sub	rsp,32*5+8
 
+$L$point_double_shortcutx::
 	movdqu	xmm0,XMMWORD PTR[rsi]
 	mov	rbx,rsi
 	movdqu	xmm1,XMMWORD PTR[16+rsi]
@@ -3150,6 +3160,7 @@ DB	102,72,15,110,199
 	mov	r14,QWORD PTR[((64+8))+rbx]
 	mov	r15,QWORD PTR[((64+16))+rbx]
 	mov	r8,QWORD PTR[((64+24))+rbx]
+DB	102,72,15,110,203
 
 	lea	rsi,QWORD PTR[((64-128))+rbx]
 	lea	rdi,QWORD PTR[32+rsp]
@@ -3241,7 +3252,7 @@ DB	102,73,15,126,217
 	test	r8,r8
 	jnz	$L$add_proceedx
 	test	r9,r9
-	jz	$L$add_proceedx
+	jz	$L$add_doublex
 
 DB	102,72,15,126,199
 	pxor	xmm0,xmm0
@@ -3253,6 +3264,13 @@ DB	102,72,15,126,199
 	movdqu	XMMWORD PTR[80+rdi],xmm0
 	jmp	$L$add_donex
 
+ALIGN	32
+$L$add_doublex::
+DB	102,72,15,126,206
+DB	102,72,15,126,199
+	add	rsp,416
+	jmp	$L$point_double_shortcutx
+
 ALIGN	32
 $L$add_proceedx::
 	mov	rdx,QWORD PTR[((0+64))+rsp]

deps/openssl/asm/x64-win32-masm/modes/aesni-gcm-x86_64.asm

@@ -412,7 +412,7 @@ $L$dec_no_key_aliasing::
 
 	vzeroupper
 	movaps	xmm6,XMMWORD PTR[((-216))+rax]
-	movaps	xmm7,XMMWORD PTR[((-216))+rax]
+	movaps	xmm7,XMMWORD PTR[((-200))+rax]
 	movaps	xmm8,XMMWORD PTR[((-184))+rax]
 	movaps	xmm9,XMMWORD PTR[((-168))+rax]
 	movaps	xmm10,XMMWORD PTR[((-152))+rax]

deps/openssl/asm_obsolete/x64-elf-gas/aes/aes-x86_64.s

@@ -81,8 +81,8 @@ _x86_64_AES_encrypt:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$65280,%edi
-	andl	$65280,%ebp
+	andl	$0x0000ff00,%edi
+	andl	$0x0000ff00,%ebp
 
 	xorl	%edi,%r10d
 	xorl	%ebp,%r11d
@@ -94,8 +94,8 @@ _x86_64_AES_encrypt:
 	movl	0(%r14,%rsi,8),%esi
 	movl	0(%r14,%rdi,8),%edi
 
-	andl	$65280,%esi
-	andl	$65280,%edi
+	andl	$0x0000ff00,%esi
+	andl	$0x0000ff00,%edi
 	shrl	$16,%ebx
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -108,9 +108,9 @@ _x86_64_AES_encrypt:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$16711680,%edi
-	andl	$16711680,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0x00ff0000,%edi
+	andl	$0x00ff0000,%ebp
 
 	xorl	%esi,%r10d
 	xorl	%edi,%r11d
@@ -123,9 +123,9 @@ _x86_64_AES_encrypt:
 	movl	2(%r14,%rdi,8),%edi
 	movl	2(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$4278190080,%edi
-	andl	$4278190080,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0xff000000,%edi
+	andl	$0xff000000,%ebp
 
 	xorl	%esi,%r8d
 	xorl	%edi,%r10d
@@ -138,8 +138,8 @@ _x86_64_AES_encrypt:
 	movl	2(%r14,%rdi,8),%edi
 	movl	16+0(%r15),%eax
 
-	andl	$4278190080,%esi
-	andl	$4278190080,%edi
+	andl	$0xff000000,%esi
+	andl	$0xff000000,%edi
 
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -241,8 +241,8 @@ _x86_64_AES_encrypt_compact:
 	xorl	%r8d,%edx
 	cmpq	16(%rsp),%r15
 	je	.Lenc_compact_done
-	movl	$2155905152,%r10d
-	movl	$2155905152,%r11d
+	movl	$0x80808080,%r10d
+	movl	$0x80808080,%r11d
 	andl	%eax,%r10d
 	andl	%ebx,%r11d
 	movl	%r10d,%esi
@@ -253,10 +253,10 @@ _x86_64_AES_encrypt_compact:
 	leal	(%rbx,%rbx,1),%r9d
 	subl	%r10d,%esi
 	subl	%r11d,%edi
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%eax,%r10d
 	movl	%ebx,%r11d
 	xorl	%esi,%r8d
@@ -264,9 +264,9 @@ _x86_64_AES_encrypt_compact:
 
 	xorl	%r8d,%eax
 	xorl	%r9d,%ebx
-	movl	$2155905152,%r12d
+	movl	$0x80808080,%r12d
 	roll	$24,%eax
-	movl	$2155905152,%ebp
+	movl	$0x80808080,%ebp
 	roll	$24,%ebx
 	andl	%ecx,%r12d
 	andl	%edx,%ebp
@@ -289,10 +289,10 @@ _x86_64_AES_encrypt_compact:
 	xorl	%r10d,%eax
 	xorl	%r11d,%ebx
 
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%ecx,%r12d
 	movl	%edx,%ebp
 	xorl	%esi,%r8d
@@ -345,7 +345,7 @@ AES_encrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -370,7 +370,7 @@ AES_encrypt:
 	leaq	.LAES_Te+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 
 	call	_x86_64_AES_encrypt_compact
@@ -792,7 +792,7 @@ AES_decrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -817,7 +817,7 @@ AES_decrypt:
 	leaq	.LAES_Td+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 	shrq	$3,%rbp
 	addq	%rbp,%r14
@@ -1333,9 +1333,9 @@ AES_cbc_encrypt:
 	movq	%r14,%r10
 	leaq	2304(%r14),%r11
 	movq	%r15,%r12
-	andq	$4095,%r10
-	andq	$4095,%r11
-	andq	$4095,%r12
+	andq	$0xFFF,%r10
+	andq	$0xFFF,%r11
+	andq	$0xFFF,%r12
 
 	cmpq	%r11,%r12
 	jb	.Lcbc_te_break_out
@@ -1344,7 +1344,7 @@ AES_cbc_encrypt:
 	jmp	.Lcbc_te_ok
 .Lcbc_te_break_out:
 	subq	%r10,%r12
-	andq	$4095,%r12
+	andq	$0xFFF,%r12
 	addq	$320,%r12
 	subq	%r12,%r15
 .align	4
@@ -1370,7 +1370,7 @@ AES_cbc_encrypt:
 
 	movq	%r15,%r10
 	subq	%r14,%r10
-	andq	$4095,%r10
+	andq	$0xfff,%r10
 	cmpq	$2304,%r10
 	jb	.Lcbc_do_ecopy
 	cmpq	$4096-248,%r10
@@ -1557,7 +1557,7 @@ AES_cbc_encrypt:
 	leaq	-88-63(%rcx),%r10
 	subq	%rbp,%r10
 	negq	%r10
-	andq	$960,%r10
+	andq	$0x3c0,%r10
 	subq	%r10,%rbp
 
 	xchgq	%rsp,%rbp
@@ -1586,7 +1586,7 @@ AES_cbc_encrypt:
 	leaq	2048(%r14),%r14
 	leaq	768-8(%rsp),%rax
 	subq	%r14,%rax
-	andq	$768,%rax
+	andq	$0x300,%rax
 	leaq	(%r14,%rax,1),%r14
 
 	cmpq	$0,%rbx

deps/openssl/asm_obsolete/x64-elf-gas/aes/aesni-sha1-x86_64.s

@@ -1392,8 +1392,8 @@ aesni_cbc_sha1_enc_shaext:
 	movups	16(%rcx),%xmm0
 	leaq	112(%rcx),%rcx
 
-	pshufd	$27,%xmm8,%xmm8
-	pshufd	$27,%xmm9,%xmm9
+	pshufd	$0b00011011,%xmm8,%xmm8
+	pshufd	$0b00011011,%xmm9,%xmm9
 	jmp	.Loop_shaext
 
 .align	16
@@ -1672,8 +1672,8 @@ aesni_cbc_sha1_enc_shaext:
 	leaq	64(%rdi),%rdi
 	jnz	.Loop_shaext
 
-	pshufd	$27,%xmm8,%xmm8
-	pshufd	$27,%xmm9,%xmm9
+	pshufd	$0b00011011,%xmm8,%xmm8
+	pshufd	$0b00011011,%xmm9,%xmm9
 	movups	%xmm2,(%r8)
 	movdqu	%xmm8,(%r9)
 	movd	%xmm9,16(%r9)

deps/openssl/asm_obsolete/x64-elf-gas/aes/aesni-x86_64.s

@@ -503,7 +503,7 @@ aesni_ecb_encrypt:
 	testl	%r8d,%r8d
 	jz	.Lecb_decrypt
 
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	.Lecb_enc_tail
 
 	movdqu	(%rdi),%xmm2
@@ -515,7 +515,7 @@ aesni_ecb_encrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	.Lecb_enc_loop8_enter
 .align	16
 .Lecb_enc_loop8:
@@ -543,7 +543,7 @@ aesni_ecb_encrypt:
 
 	call	_aesni_encrypt8
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	.Lecb_enc_loop8
 
 	movups	%xmm2,(%rsi)
@@ -557,22 +557,22 @@ aesni_ecb_encrypt:
 	movups	%xmm8,96(%rsi)
 	movups	%xmm9,112(%rsi)
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	.Lecb_ret
 
 .Lecb_enc_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lecb_enc_one
 	movups	16(%rdi),%xmm3
 	je	.Lecb_enc_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lecb_enc_three
 	movups	48(%rdi),%xmm5
 	je	.Lecb_enc_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	.Lecb_enc_five
 	movups	80(%rdi),%xmm7
 	je	.Lecb_enc_six
@@ -646,7 +646,7 @@ aesni_ecb_encrypt:
 
 .align	16
 .Lecb_decrypt:
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	.Lecb_dec_tail
 
 	movdqu	(%rdi),%xmm2
@@ -658,7 +658,7 @@ aesni_ecb_encrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	.Lecb_dec_loop8_enter
 .align	16
 .Lecb_dec_loop8:
@@ -687,7 +687,7 @@ aesni_ecb_encrypt:
 	call	_aesni_decrypt8
 
 	movups	(%r11),%xmm0
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	.Lecb_dec_loop8
 
 	movups	%xmm2,(%rsi)
@@ -709,22 +709,22 @@ aesni_ecb_encrypt:
 	movups	%xmm9,112(%rsi)
 	pxor	%xmm9,%xmm9
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	.Lecb_ret
 
 .Lecb_dec_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lecb_dec_one
 	movups	16(%rdi),%xmm3
 	je	.Lecb_dec_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lecb_dec_three
 	movups	48(%rdi),%xmm5
 	je	.Lecb_dec_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	.Lecb_dec_five
 	movups	80(%rdi),%xmm7
 	je	.Lecb_dec_six
@@ -1598,7 +1598,7 @@ aesni_xts_encrypt:
 
 	movdqa	.Lxts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -1697,7 +1697,7 @@ aesni_xts_encrypt:
 .byte	102,15,56,220,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	.Lxts_enc_loop6
 .align	32
 .Lxts_enc_loop6:
@@ -1836,13 +1836,13 @@ aesni_xts_encrypt:
 	jz	.Lxts_enc_done
 
 	pxor	%xmm0,%xmm11
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lxts_enc_one
 	pxor	%xmm0,%xmm12
 	je	.Lxts_enc_two
 
 	pxor	%xmm0,%xmm13
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lxts_enc_three
 	pxor	%xmm0,%xmm14
 	je	.Lxts_enc_four
@@ -2069,7 +2069,7 @@ aesni_xts_decrypt:
 
 	movdqa	.Lxts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -2168,7 +2168,7 @@ aesni_xts_decrypt:
 .byte	102,15,56,222,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	.Lxts_dec_loop6
 .align	32
 .Lxts_dec_loop6:
@@ -2308,13 +2308,13 @@ aesni_xts_decrypt:
 	jz	.Lxts_dec_done
 
 	pxor	%xmm0,%xmm12
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	.Lxts_dec_one
 	pxor	%xmm0,%xmm13
 	je	.Lxts_dec_two
 
 	pxor	%xmm0,%xmm14
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	.Lxts_dec_three
 	je	.Lxts_dec_four
 
@@ -2345,7 +2345,7 @@ aesni_xts_decrypt:
 	pcmpgtd	%xmm15,%xmm14
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	pshufd	$19,%xmm14,%xmm11
+	pshufd	$0x13,%xmm14,%xmm11
 	andq	$15,%r9
 	jz	.Lxts_dec_ret
 
@@ -2634,7 +2634,7 @@ aesni_cbc_encrypt:
 	leaq	-8(%rax),%rbp
 	movups	(%r8),%xmm10
 	movl	%r10d,%eax
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	.Lcbc_dec_tail
 
 	movups	(%rcx),%xmm0
@@ -2650,14 +2650,14 @@ aesni_cbc_encrypt:
 	movdqu	80(%rdi),%xmm7
 	movdqa	%xmm6,%xmm15
 	movl	OPENSSL_ia32cap_P+4(%rip),%r9d
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	jbe	.Lcbc_dec_six_or_seven
 
 	andl	$71303168,%r9d
-	subq	$80,%rdx
+	subq	$0x50,%rdx
 	cmpl	$4194304,%r9d
 	je	.Lcbc_dec_loop6_enter
-	subq	$32,%rdx
+	subq	$0x20,%rdx
 	leaq	112(%rcx),%rcx
 	jmp	.Lcbc_dec_loop8_enter
 .align	16
@@ -2672,7 +2672,7 @@ aesni_cbc_encrypt:
 	movups	16-112(%rcx),%xmm1
 	pxor	%xmm0,%xmm4
 	xorq	%r11,%r11
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	pxor	%xmm0,%xmm5
 	pxor	%xmm0,%xmm6
 	pxor	%xmm0,%xmm7
@@ -2857,21 +2857,21 @@ aesni_cbc_encrypt:
 	movups	%xmm8,96(%rsi)
 	leaq	112(%rsi),%rsi
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	ja	.Lcbc_dec_loop8
 
 	movaps	%xmm9,%xmm2
 	leaq	-112(%rcx),%rcx
-	addq	$112,%rdx
+	addq	$0x70,%rdx
 	jle	.Lcbc_dec_clear_tail_collected
 	movups	%xmm9,(%rsi)
 	leaq	16(%rsi),%rsi
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	.Lcbc_dec_tail
 
 	movaps	%xmm11,%xmm2
 .Lcbc_dec_six_or_seven:
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	ja	.Lcbc_dec_seven
 
 	movaps	%xmm7,%xmm8
@@ -2964,33 +2964,33 @@ aesni_cbc_encrypt:
 	movl	%r10d,%eax
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	subq	$96,%rdx
+	subq	$0x60,%rdx
 	ja	.Lcbc_dec_loop6
 
 	movdqa	%xmm7,%xmm2
-	addq	$80,%rdx
+	addq	$0x50,%rdx
 	jle	.Lcbc_dec_clear_tail_collected
 	movups	%xmm7,(%rsi)
 	leaq	16(%rsi),%rsi
 
 .Lcbc_dec_tail:
 	movups	(%rdi),%xmm2
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_one
 
 	movups	16(%rdi),%xmm3
 	movaps	%xmm2,%xmm11
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_two
 
 	movups	32(%rdi),%xmm4
 	movaps	%xmm3,%xmm12
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_three
 
 	movups	48(%rdi),%xmm5
 	movaps	%xmm4,%xmm13
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	.Lcbc_dec_four
 
 	movups	64(%rdi),%xmm6
@@ -3015,7 +3015,7 @@ aesni_cbc_encrypt:
 	movdqa	%xmm6,%xmm2
 	pxor	%xmm6,%xmm6
 	pxor	%xmm7,%xmm7
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jmp	.Lcbc_dec_tail_collected
 
 .align	16
@@ -3332,7 +3332,7 @@ __aesni_set_encrypt_key:
 	pslldq	$4,%xmm0
 	pxor	%xmm3,%xmm0
 
-	pshufd	$255,%xmm0,%xmm3
+	pshufd	$0xff,%xmm0,%xmm3
 	pxor	%xmm1,%xmm3
 	pslldq	$4,%xmm1
 	pxor	%xmm1,%xmm3
@@ -3419,7 +3419,7 @@ __aesni_set_encrypt_key:
 	decl	%r10d
 	jz	.Ldone_key256
 
-	pshufd	$255,%xmm0,%xmm2
+	pshufd	$0xff,%xmm0,%xmm2
 	pxor	%xmm3,%xmm3
 .byte	102,15,56,221,211
 
@@ -3462,11 +3462,11 @@ __aesni_set_encrypt_key:
 	movups	%xmm0,(%rax)
 	leaq	16(%rax),%rax
 .Lkey_expansion_128_cold:
-	shufps	$16,%xmm0,%xmm4
+	shufps	$0b00010000,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$140,%xmm0,%xmm4
+	shufps	$0b10001100,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$255,%xmm1,%xmm1
+	shufps	$0b11111111,%xmm1,%xmm1
 	xorps	%xmm1,%xmm0
 	.byte	0xf3,0xc3
 
@@ -3477,25 +3477,25 @@ __aesni_set_encrypt_key:
 .Lkey_expansion_192a_cold:
 	movaps	%xmm2,%xmm5
 .Lkey_expansion_192b_warm:
-	shufps	$16,%xmm0,%xmm4
+	shufps	$0b00010000,%xmm0,%xmm4
 	movdqa	%xmm2,%xmm3
 	xorps	%xmm4,%xmm0
-	shufps	$140,%xmm0,%xmm4
+	shufps	$0b10001100,%xmm0,%xmm4
 	pslldq	$4,%xmm3
 	xorps	%xmm4,%xmm0
-	pshufd	$85,%xmm1,%xmm1
+	pshufd	$0b01010101,%xmm1,%xmm1
 	pxor	%xmm3,%xmm2
 	pxor	%xmm1,%xmm0
-	pshufd	$255,%xmm0,%xmm3
+	pshufd	$0b11111111,%xmm0,%xmm3
 	pxor	%xmm3,%xmm2
 	.byte	0xf3,0xc3
 
 .align	16
 .Lkey_expansion_192b:
 	movaps	%xmm0,%xmm3
-	shufps	$68,%xmm0,%xmm5
+	shufps	$0b01000100,%xmm0,%xmm5
 	movups	%xmm5,(%rax)
-	shufps	$78,%xmm2,%xmm3
+	shufps	$0b01001110,%xmm2,%xmm3
 	movups	%xmm3,16(%rax)
 	leaq	32(%rax),%rax
 	jmp	.Lkey_expansion_192b_warm
@@ -3505,11 +3505,11 @@ __aesni_set_encrypt_key:
 	movups	%xmm2,(%rax)
 	leaq	16(%rax),%rax
 .Lkey_expansion_256a_cold:
-	shufps	$16,%xmm0,%xmm4
+	shufps	$0b00010000,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$140,%xmm0,%xmm4
+	shufps	$0b10001100,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$255,%xmm1,%xmm1
+	shufps	$0b11111111,%xmm1,%xmm1
 	xorps	%xmm1,%xmm0
 	.byte	0xf3,0xc3
 
@@ -3518,11 +3518,11 @@ __aesni_set_encrypt_key:
 	movups	%xmm0,(%rax)
 	leaq	16(%rax),%rax
 
-	shufps	$16,%xmm2,%xmm4
+	shufps	$0b00010000,%xmm2,%xmm4
 	xorps	%xmm4,%xmm2
-	shufps	$140,%xmm2,%xmm4
+	shufps	$0b10001100,%xmm2,%xmm4
 	xorps	%xmm4,%xmm2
-	shufps	$170,%xmm1,%xmm1
+	shufps	$0b10101010,%xmm1,%xmm1
 	xorps	%xmm1,%xmm2
 	.byte	0xf3,0xc3
 .size	aesni_set_encrypt_key,.-aesni_set_encrypt_key

deps/openssl/asm_obsolete/x64-elf-gas/aes/bsaes-x86_64.s

@@ -324,45 +324,45 @@ _bsaes_encrypt8_bitslice:
 	pxor	%xmm2,%xmm5
 	decl	%r10d
 	jl	.Lenc_done
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm3,%xmm9
+	pshufd	$0x93,%xmm3,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm5,%xmm10
+	pshufd	$0x93,%xmm5,%xmm10
 	pxor	%xmm9,%xmm3
-	pshufd	$147,%xmm2,%xmm11
+	pshufd	$0x93,%xmm2,%xmm11
 	pxor	%xmm10,%xmm5
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm2
-	pshufd	$147,%xmm1,%xmm13
+	pshufd	$0x93,%xmm1,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm1
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm2,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm5,%xmm11
-	pshufd	$78,%xmm2,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm7
 	pxor	%xmm1,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm3,%xmm10
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm1,%xmm5
+	pshufd	$0x4E,%xmm1,%xmm5
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm12,%xmm8
 	pxor	%xmm10,%xmm2
 	pxor	%xmm14,%xmm6
@@ -796,24 +796,24 @@ _bsaes_decrypt8:
 	decl	%r10d
 	jl	.Ldec_done
 
-	pshufd	$78,%xmm15,%xmm7
-	pshufd	$78,%xmm2,%xmm13
+	pshufd	$0x4E,%xmm15,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm13
 	pxor	%xmm15,%xmm7
-	pshufd	$78,%xmm4,%xmm14
+	pshufd	$0x4E,%xmm4,%xmm14
 	pxor	%xmm2,%xmm13
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0x4E,%xmm0,%xmm8
 	pxor	%xmm4,%xmm14
-	pshufd	$78,%xmm5,%xmm9
+	pshufd	$0x4E,%xmm5,%xmm9
 	pxor	%xmm0,%xmm8
-	pshufd	$78,%xmm3,%xmm10
+	pshufd	$0x4E,%xmm3,%xmm10
 	pxor	%xmm5,%xmm9
 	pxor	%xmm13,%xmm15
 	pxor	%xmm13,%xmm0
-	pshufd	$78,%xmm1,%xmm11
+	pshufd	$0x4E,%xmm1,%xmm11
 	pxor	%xmm3,%xmm10
 	pxor	%xmm7,%xmm5
 	pxor	%xmm8,%xmm3
-	pshufd	$78,%xmm6,%xmm12
+	pshufd	$0x4E,%xmm6,%xmm12
 	pxor	%xmm1,%xmm11
 	pxor	%xmm14,%xmm0
 	pxor	%xmm9,%xmm1
@@ -827,45 +827,45 @@ _bsaes_decrypt8:
 	pxor	%xmm14,%xmm1
 	pxor	%xmm14,%xmm6
 	pxor	%xmm12,%xmm4
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm5,%xmm9
+	pshufd	$0x93,%xmm5,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm3,%xmm10
+	pshufd	$0x93,%xmm3,%xmm10
 	pxor	%xmm9,%xmm5
-	pshufd	$147,%xmm1,%xmm11
+	pshufd	$0x93,%xmm1,%xmm11
 	pxor	%xmm10,%xmm3
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm1
-	pshufd	$147,%xmm2,%xmm13
+	pshufd	$0x93,%xmm2,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm2
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm1,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm3,%xmm11
-	pshufd	$78,%xmm1,%xmm7
+	pshufd	$0x4E,%xmm1,%xmm7
 	pxor	%xmm2,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm5,%xmm10
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm2,%xmm3
+	pshufd	$0x4E,%xmm2,%xmm3
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm12,%xmm8
 	pxor	%xmm1,%xmm10
 	pxor	%xmm14,%xmm6
@@ -1552,20 +1552,20 @@ bsaes_xts_encrypt:
 	movdqa	%xmm7,(%rax)
 
 	andq	$-16,%r14
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	.Lxts_enc_short
 	jmp	.Lxts_enc_loop
 
 .align	16
 .Lxts_enc_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1573,7 +1573,7 @@ bsaes_xts_encrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1582,7 +1582,7 @@ bsaes_xts_encrypt:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1592,7 +1592,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1602,7 +1602,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1612,7 +1612,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1622,7 +1622,7 @@ bsaes_xts_encrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -1666,20 +1666,20 @@ bsaes_xts_encrypt:
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	.Lxts_enc_loop
 
 .Lxts_enc_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	.Lxts_enc_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1687,7 +1687,7 @@ bsaes_xts_encrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1698,7 +1698,7 @@ bsaes_xts_encrypt:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	.Lxts_enc_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1710,7 +1710,7 @@ bsaes_xts_encrypt:
 	cmpq	$32,%r14
 	je	.Lxts_enc_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1722,7 +1722,7 @@ bsaes_xts_encrypt:
 	cmpq	$48,%r14
 	je	.Lxts_enc_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1734,7 +1734,7 @@ bsaes_xts_encrypt:
 	cmpq	$64,%r14
 	je	.Lxts_enc_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1746,7 +1746,7 @@ bsaes_xts_encrypt:
 	cmpq	$80,%r14
 	je	.Lxts_enc_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2011,20 +2011,20 @@ bsaes_xts_decrypt:
 	shlq	$4,%rax
 	subq	%rax,%r14
 
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	.Lxts_dec_short
 	jmp	.Lxts_dec_loop
 
 .align	16
 .Lxts_dec_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2032,7 +2032,7 @@ bsaes_xts_decrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2041,7 +2041,7 @@ bsaes_xts_decrypt:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2051,7 +2051,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2061,7 +2061,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2071,7 +2071,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2081,7 +2081,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2125,20 +2125,20 @@ bsaes_xts_decrypt:
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	.Lxts_dec_loop
 
 .Lxts_dec_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	.Lxts_dec_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2146,7 +2146,7 @@ bsaes_xts_decrypt:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2157,7 +2157,7 @@ bsaes_xts_decrypt:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	.Lxts_dec_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2169,7 +2169,7 @@ bsaes_xts_decrypt:
 	cmpq	$32,%r14
 	je	.Lxts_dec_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2181,7 +2181,7 @@ bsaes_xts_decrypt:
 	cmpq	$48,%r14
 	je	.Lxts_dec_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2193,7 +2193,7 @@ bsaes_xts_decrypt:
 	cmpq	$64,%r14
 	je	.Lxts_dec_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2205,7 +2205,7 @@ bsaes_xts_decrypt:
 	cmpq	$80,%r14
 	je	.Lxts_dec_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2382,7 +2382,7 @@ bsaes_xts_decrypt:
 	pxor	%xmm14,%xmm14
 	movdqa	.Lxts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	movdqa	%xmm6,%xmm5
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13

deps/openssl/asm_obsolete/x64-elf-gas/aes/vpaes-x86_64.s

@@ -60,7 +60,7 @@ _vpaes_encrypt_core:
 	addq	$16,%r11
 	pxor	%xmm0,%xmm3
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	subq	$1,%rax
 	pxor	%xmm3,%xmm0
 
@@ -120,10 +120,10 @@ _vpaes_decrypt_core:
 	pand	%xmm9,%xmm0
 .byte	102,15,56,0,208
 	movdqa	.Lk_dipt+16(%rip),%xmm0
-	xorq	$48,%r11
+	xorq	$0x30,%r11
 	leaq	.Lk_dsbd(%rip),%r10
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	pxor	%xmm5,%xmm2
 	movdqa	.Lk_mc_forward+48(%rip),%xmm5
 	pxor	%xmm2,%xmm0
@@ -242,7 +242,7 @@ _vpaes_schedule_core:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	movdqu	%xmm3,(%rdx)
-	xorq	$48,%r8
+	xorq	$0x30,%r8
 
 .Lschedule_go:
 	cmpl	$192,%esi
@@ -332,7 +332,7 @@ _vpaes_schedule_core:
 	call	_vpaes_schedule_mangle
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 	movdqa	%xmm7,%xmm5
 	movdqa	%xmm6,%xmm7
 	call	_vpaes_schedule_low_round
@@ -399,8 +399,8 @@ _vpaes_schedule_core:
 .type	_vpaes_schedule_192_smear,@function
 .align	16
 _vpaes_schedule_192_smear:
-	pshufd	$128,%xmm6,%xmm1
-	pshufd	$254,%xmm7,%xmm0
+	pshufd	$0x80,%xmm6,%xmm1
+	pshufd	$0xFE,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
 	pxor	%xmm1,%xmm1
 	pxor	%xmm0,%xmm6
@@ -437,7 +437,7 @@ _vpaes_schedule_round:
 	pxor	%xmm1,%xmm7
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 .byte	102,15,58,15,192,1
 
 
@@ -596,7 +596,7 @@ _vpaes_schedule_mangle:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	addq	$-16,%r8
-	andq	$48,%r8
+	andq	$0x30,%r8
 	movdqu	%xmm3,(%rdx)
 	.byte	0xf3,0xc3
 .size	_vpaes_schedule_mangle,.-_vpaes_schedule_mangle
@@ -614,7 +614,7 @@ vpaes_set_encrypt_key:
 	movl	%eax,240(%rdx)
 
 	movl	$0,%ecx
-	movl	$48,%r8d
+	movl	$0x30,%r8d
 	call	_vpaes_schedule_core
 	xorl	%eax,%eax
 	.byte	0xf3,0xc3

deps/openssl/asm_obsolete/x64-elf-gas/bn/rsaz-x86_64.s

@@ -461,48 +461,94 @@ rsaz_512_mul_gather4:
 	pushq	%r14
 	pushq	%r15
 
-	movl	%r9d,%r9d
-	subq	$128+24,%rsp
+	subq	$152,%rsp
 .Lmul_gather4_body:
-	movl	64(%rdx,%r9,4),%eax
-.byte	102,72,15,110,199
-	movl	(%rdx,%r9,4),%ebx
-.byte	102,72,15,110,201
+	movd	%r9d,%xmm8
+	movdqa	.Linc+16(%rip),%xmm1
+	movdqa	.Linc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
+
+	movdqa	0(%rdx),%xmm8
+	movdqa	16(%rdx),%xmm9
+	movdqa	32(%rdx),%xmm10
+	movdqa	48(%rdx),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rdx),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rdx),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rdx),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rdx),%xmm15
+	leaq	128(%rdx),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
 	movq	%r8,128(%rsp)
+	movq	%rdi,128+8(%rsp)
+	movq	%rcx,128+16(%rsp)
 
-	shlq	$32,%rax
-	orq	%rax,%rbx
 	movq	(%rsi),%rax
 	movq	8(%rsi),%rcx
-	leaq	128(%rdx,%r9,4),%rbp
 	mulq	%rbx
 	movq	%rax,(%rsp)
 	movq	%rcx,%rax
 	movq	%rdx,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r8
 	movq	16(%rsi),%rax
 	movq	%rdx,%r9
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r9
 	movq	24(%rsi),%rax
 	movq	%rdx,%r10
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r10
 	movq	32(%rsi),%rax
 	movq	%rdx,%r11
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r11
 	movq	40(%rsi),%rax
 	movq	%rdx,%r12
@@ -515,14 +561,12 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r13
 
 	mulq	%rbx
-	leaq	128(%rbp),%rbp
 	addq	%rax,%r13
 	movq	56(%rsi),%rax
 	movq	%rdx,%r14
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r14
 	movq	(%rsi),%rax
 	movq	%rdx,%r15
@@ -534,6 +578,35 @@ rsaz_512_mul_gather4:
 
 .align	32
 .Loop_mul_gather:
+	movdqa	0(%rbp),%xmm8
+	movdqa	16(%rbp),%xmm9
+	movdqa	32(%rbp),%xmm10
+	movdqa	48(%rbp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rbp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rbp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rbp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rbp),%xmm15
+	leaq	128(%rbp),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
 	mulq	%rbx
 	addq	%rax,%r8
 	movq	8(%rsi),%rax
@@ -542,7 +615,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r9
 	movq	16(%rsi),%rax
 	adcq	$0,%rdx
@@ -551,7 +623,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r10
 	movq	24(%rsi),%rax
 	adcq	$0,%rdx
@@ -560,7 +631,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r11
 	movq	32(%rsi),%rax
 	adcq	$0,%rdx
@@ -569,7 +639,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r12
 	movq	40(%rsi),%rax
 	adcq	$0,%rdx
@@ -594,7 +663,6 @@ rsaz_512_mul_gather4:
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r15
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -602,7 +670,6 @@ rsaz_512_mul_gather4:
 	movq	%rdx,%r15
 	adcq	$0,%r15
 
-	leaq	128(%rbp),%rbp
 	leaq	8(%rdi),%rdi
 
 	decl	%ecx
@@ -617,8 +684,8 @@ rsaz_512_mul_gather4:
 	movq	%r14,48(%rdi)
 	movq	%r15,56(%rdi)
 
-.byte	102,72,15,126,199
-.byte	102,72,15,126,205
+	movq	128+8(%rsp),%rdi
+	movq	128+16(%rsp),%rbp
 
 	movq	(%rsp),%r8
 	movq	8(%rsp),%r9
@@ -667,7 +734,7 @@ rsaz_512_mul_scatter4:
 	movl	%r9d,%r9d
 	subq	$128+24,%rsp
 .Lmul_scatter4_body:
-	leaq	(%r8,%r9,4),%r8
+	leaq	(%r8,%r9,8),%r8
 .byte	102,72,15,110,199
 .byte	102,72,15,110,202
 .byte	102,73,15,110,208
@@ -703,30 +770,14 @@ rsaz_512_mul_scatter4:
 
 	call	__rsaz_512_subtract
 
-	movl	%r8d,0(%rsi)
-	shrq	$32,%r8
-	movl	%r9d,128(%rsi)
-	shrq	$32,%r9
-	movl	%r10d,256(%rsi)
-	shrq	$32,%r10
-	movl	%r11d,384(%rsi)
-	shrq	$32,%r11
-	movl	%r12d,512(%rsi)
-	shrq	$32,%r12
-	movl	%r13d,640(%rsi)
-	shrq	$32,%r13
-	movl	%r14d,768(%rsi)
-	shrq	$32,%r14
-	movl	%r15d,896(%rsi)
-	shrq	$32,%r15
-	movl	%r8d,64(%rsi)
-	movl	%r9d,192(%rsi)
-	movl	%r10d,320(%rsi)
-	movl	%r11d,448(%rsi)
-	movl	%r12d,576(%rsi)
-	movl	%r13d,704(%rsi)
-	movl	%r14d,832(%rsi)
-	movl	%r15d,960(%rsi)
+	movq	%r8,0(%rsi)
+	movq	%r9,128(%rsi)
+	movq	%r10,256(%rsi)
+	movq	%r11,384(%rsi)
+	movq	%r12,512(%rsi)
+	movq	%r13,640(%rsi)
+	movq	%r14,768(%rsi)
+	movq	%r15,896(%rsi)
 
 	leaq	128+24+48(%rsp),%rax
 	movq	-48(%rax),%r15
@@ -1079,16 +1130,14 @@ __rsaz_512_mul:
 .type	rsaz_512_scatter4,@function
 .align	16
 rsaz_512_scatter4:
-	leaq	(%rdi,%rdx,4),%rdi
+	leaq	(%rdi,%rdx,8),%rdi
 	movl	$8,%r9d
 	jmp	.Loop_scatter
 .align	16
 .Loop_scatter:
 	movq	(%rsi),%rax
 	leaq	8(%rsi),%rsi
-	movl	%eax,(%rdi)
-	shrq	$32,%rax
-	movl	%eax,64(%rdi)
+	movq	%rax,(%rdi)
 	leaq	128(%rdi),%rdi
 	decl	%r9d
 	jnz	.Loop_scatter
@@ -1099,19 +1148,72 @@ rsaz_512_scatter4:
 .type	rsaz_512_gather4,@function
 .align	16
 rsaz_512_gather4:
-	leaq	(%rsi,%rdx,4),%rsi
+	movd	%edx,%xmm8
+	movdqa	.Linc+16(%rip),%xmm1
+	movdqa	.Linc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
 	movl	$8,%r9d
 	jmp	.Loop_gather
 .align	16
 .Loop_gather:
-	movl	(%rsi),%eax
-	movl	64(%rsi),%r8d
+	movdqa	0(%rsi),%xmm8
+	movdqa	16(%rsi),%xmm9
+	movdqa	32(%rsi),%xmm10
+	movdqa	48(%rsi),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rsi),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rsi),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rsi),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rsi),%xmm15
 	leaq	128(%rsi),%rsi
-	shlq	$32,%r8
-	orq	%r8,%rax
-	movq	%rax,(%rdi)
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,(%rdi)
 	leaq	8(%rdi),%rdi
 	decl	%r9d
 	jnz	.Loop_gather
 	.byte	0xf3,0xc3
+.LSEH_end_rsaz_512_gather4:
 .size	rsaz_512_gather4,.-rsaz_512_gather4
+
+.align	64
+.Linc:
+.long	0,0, 1,1
+.long	2,2, 2,2

deps/openssl/asm_obsolete/x64-elf-gas/bn/x86_64-gf2m.s

@@ -242,7 +242,7 @@ bn_GF2m_mul_2x2:
 	movq	%rcx,56(%rsp)
 	movq	%r8,64(%rsp)
 
-	movq	$15,%r8
+	movq	$0xf,%r8
 	movq	%rsi,%rax
 	movq	%rcx,%rbp
 	call	_mul_1x1

deps/openssl/asm_obsolete/x64-elf-gas/bn/x86_64-mont.s

@@ -633,20 +633,20 @@ bn_sqr8x_mont:
 
 
 
-	leaq	-64(%rsp,%r9,4),%r11
+	leaq	-64(%rsp,%r9,2),%r11
 	movq	(%r8),%r8
 	subq	%rsi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	.Lsqr8x_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	-64(%rsp,%r9,2),%rsp
 	jmp	.Lsqr8x_sp_done
 
 .align	32
 .Lsqr8x_sp_alt:
-	leaq	4096-64(,%r9,4),%r10
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	4096-64(,%r9,2),%r10
+	leaq	-64(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -656,58 +656,80 @@ bn_sqr8x_mont:
 	movq	%r9,%r10
 	negq	%r9
 
-	leaq	64(%rsp,%r9,2),%r11
 	movq	%r8,32(%rsp)
 	movq	%rax,40(%rsp)
 .Lsqr8x_body:
 
-	movq	%r9,%rbp
-.byte	102,73,15,110,211
-	shrq	$3+2,%rbp
-	movl	OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	.Lsqr8x_copy_n
-
-.align	32
-.Lsqr8x_copy_n:
-	movq	0(%rcx),%xmm0
-	movq	8(%rcx),%xmm1
-	movq	16(%rcx),%xmm3
-	movq	24(%rcx),%xmm4
-	leaq	32(%rcx),%rcx
-	movdqa	%xmm0,0(%r11)
-	movdqa	%xmm1,16(%r11)
-	movdqa	%xmm3,32(%r11)
-	movdqa	%xmm4,48(%r11)
-	leaq	64(%r11),%r11
-	decq	%rbp
-	jnz	.Lsqr8x_copy_n
-
+.byte	102,72,15,110,209
 	pxor	%xmm0,%xmm0
 .byte	102,72,15,110,207
 .byte	102,73,15,110,218
 	call	bn_sqr8x_internal
 
+
+
+
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
+	movq	%r9,%rdx
+.byte	102,72,15,126,207
+	sarq	$3+2,%rcx
+	jmp	.Lsqr8x_sub
+
+.align	32
+.Lsqr8x_sub:
+	movq	0(%rbx),%r12
+	movq	8(%rbx),%r13
+	movq	16(%rbx),%r14
+	movq	24(%rbx),%r15
+	leaq	32(%rbx),%rbx
+	sbbq	0(%rbp),%r12
+	sbbq	8(%rbp),%r13
+	sbbq	16(%rbp),%r14
+	sbbq	24(%rbp),%r15
+	leaq	32(%rbp),%rbp
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	leaq	32(%rdi),%rdi
+	incq	%rcx
+	jnz	.Lsqr8x_sub
+
+	sbbq	$0,%rax
+	leaq	(%rbx,%r9,1),%rbx
+	leaq	(%rdi,%r9,1),%rdi
+
+.byte	102,72,15,110,200
 	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
+	pshufd	$0,%xmm1,%xmm1
 	movq	40(%rsp),%rsi
-	jmp	.Lsqr8x_zero
+	jmp	.Lsqr8x_cond_copy
 
 .align	32
-.Lsqr8x_zero:
-	movdqa	%xmm0,0(%rax)
-	movdqa	%xmm0,16(%rax)
-	movdqa	%xmm0,32(%rax)
-	movdqa	%xmm0,48(%rax)
-	leaq	64(%rax),%rax
-	movdqa	%xmm0,0(%rdx)
-	movdqa	%xmm0,16(%rdx)
-	movdqa	%xmm0,32(%rdx)
-	movdqa	%xmm0,48(%rdx)
-	leaq	64(%rdx),%rdx
-	decq	%r9
-	jnz	.Lsqr8x_zero
+.Lsqr8x_cond_copy:
+	movdqa	0(%rbx),%xmm2
+	movdqa	16(%rbx),%xmm3
+	leaq	32(%rbx),%rbx
+	movdqu	0(%rdi),%xmm4
+	movdqu	16(%rdi),%xmm5
+	leaq	32(%rdi),%rdi
+	movdqa	%xmm0,-32(%rbx)
+	movdqa	%xmm0,-16(%rbx)
+	movdqa	%xmm0,-32(%rbx,%rdx,1)
+	movdqa	%xmm0,-16(%rbx,%rdx,1)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-32(%rdi)
+	movdqu	%xmm5,-16(%rdi)
+	addq	$32,%r9
+	jnz	.Lsqr8x_cond_copy
 
 	movq	$1,%rax
 	movq	-48(%rsi),%r15

deps/openssl/asm_obsolete/x64-elf-gas/camellia/cmll-x86_64.s

@@ -1624,7 +1624,7 @@ Camellia_cbc_encrypt:
 	leaq	-64-63(%rcx),%r10
 	subq	%rsp,%r10
 	negq	%r10
-	andq	$960,%r10
+	andq	$0x3C0,%r10
 	subq	%r10,%rsp
 
 

deps/openssl/asm_obsolete/x64-elf-gas/ec/ecp_nistz256-x86_64.s

@@ -1121,6 +1121,7 @@ ecp_nistz256_point_double:
 	pushq	%r15
 	subq	$160+8,%rsp
 
+.Lpoint_double_shortcutq:
 	movdqu	0(%rsi),%xmm0
 	movq	%rsi,%rbx
 	movdqu	16(%rsi),%xmm1
@@ -1341,7 +1342,7 @@ ecp_nistz256_point_add:
 	por	%xmm1,%xmm3
 
 	movdqu	0(%rsi),%xmm0
-	pshufd	$177,%xmm3,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm5
 	movdqu	16(%rsi),%xmm1
 	movdqu	32(%rsi),%xmm2
 	por	%xmm3,%xmm5
@@ -1351,7 +1352,7 @@ ecp_nistz256_point_add:
 	movq	64+16(%rsi),%r15
 	movq	64+24(%rsi),%r8
 	movdqa	%xmm0,480(%rsp)
-	pshufd	$30,%xmm5,%xmm4
+	pshufd	$0x1e,%xmm5,%xmm4
 	movdqa	%xmm1,480+16(%rsp)
 	por	%xmm0,%xmm1
 .byte	102,72,15,110,199
@@ -1371,10 +1372,10 @@ ecp_nistz256_point_add:
 	call	__ecp_nistz256_sqr_montq
 
 	pcmpeqd	%xmm4,%xmm5
-	pshufd	$177,%xmm3,%xmm4
+	pshufd	$0xb1,%xmm3,%xmm4
 	por	%xmm3,%xmm4
 	pshufd	$0,%xmm5,%xmm5
-	pshufd	$30,%xmm4,%xmm3
+	pshufd	$0x1e,%xmm4,%xmm3
 	por	%xmm3,%xmm4
 	pxor	%xmm3,%xmm3
 	pcmpeqd	%xmm3,%xmm4
@@ -1383,6 +1384,7 @@ ecp_nistz256_point_add:
 	movq	64+8(%rbx),%r14
 	movq	64+16(%rbx),%r15
 	movq	64+24(%rbx),%r8
+.byte	102,72,15,110,203
 
 	leaq	64-0(%rbx),%rsi
 	leaq	32(%rsp),%rdi
@@ -1474,7 +1476,7 @@ ecp_nistz256_point_add:
 	testq	%r8,%r8
 	jnz	.Ladd_proceedq
 	testq	%r9,%r9
-	jz	.Ladd_proceedq
+	jz	.Ladd_doubleq
 
 .byte	102,72,15,126,199
 	pxor	%xmm0,%xmm0
@@ -1486,6 +1488,13 @@ ecp_nistz256_point_add:
 	movdqu	%xmm0,80(%rdi)
 	jmp	.Ladd_doneq
 
+.align	32
+.Ladd_doubleq:
+.byte	102,72,15,126,206
+.byte	102,72,15,126,199
+	addq	$416,%rsp
+	jmp	.Lpoint_double_shortcutq
+
 .align	32
 .Ladd_proceedq:
 	movq	0+64(%rsp),%rax
@@ -1733,13 +1742,13 @@ ecp_nistz256_point_add_affine:
 	por	%xmm1,%xmm3
 
 	movdqu	0(%rbx),%xmm0
-	pshufd	$177,%xmm3,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm5
 	movdqu	16(%rbx),%xmm1
 	movdqu	32(%rbx),%xmm2
 	por	%xmm3,%xmm5
 	movdqu	48(%rbx),%xmm3
 	movdqa	%xmm0,416(%rsp)
-	pshufd	$30,%xmm5,%xmm4
+	pshufd	$0x1e,%xmm5,%xmm4
 	movdqa	%xmm1,416+16(%rsp)
 	por	%xmm0,%xmm1
 .byte	102,72,15,110,199
@@ -1755,13 +1764,13 @@ ecp_nistz256_point_add_affine:
 	call	__ecp_nistz256_sqr_montq
 
 	pcmpeqd	%xmm4,%xmm5
-	pshufd	$177,%xmm3,%xmm4
+	pshufd	$0xb1,%xmm3,%xmm4
 	movq	0(%rbx),%rax
 
 	movq	%r12,%r9
 	por	%xmm3,%xmm4
 	pshufd	$0,%xmm5,%xmm5
-	pshufd	$30,%xmm4,%xmm3
+	pshufd	$0x1e,%xmm4,%xmm3
 	movq	%r13,%r10
 	por	%xmm3,%xmm4
 	pxor	%xmm3,%xmm3

deps/openssl/asm_obsolete/x64-elf-gas/modes/ghash-x86_64.s

@@ -20,14 +20,14 @@ gcm_gmult_4bit:
 	movq	$14,%rcx
 	movq	8(%rsi,%rax,1),%r8
 	movq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	movq	%r8,%rdx
 	jmp	.Loop1
 
 .align	16
 .Loop1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	movb	(%rdi,%rcx,1),%al
 	shrq	$4,%r9
@@ -43,13 +43,13 @@ gcm_gmult_4bit:
 	js	.Lbreak1
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
@@ -58,19 +58,19 @@ gcm_gmult_4bit:
 .align	16
 .Lbreak1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rbx,1),%r8
@@ -661,10 +661,10 @@ gcm_ghash_4bit:
 gcm_init_clmul:
 .L_init_clmul:
 	movdqu	(%rsi),%xmm2
-	pshufd	$78,%xmm2,%xmm2
+	pshufd	$0b01001110,%xmm2,%xmm2
 
 
-	pshufd	$255,%xmm2,%xmm4
+	pshufd	$0b11111111,%xmm2,%xmm4
 	movdqa	%xmm2,%xmm3
 	psllq	$1,%xmm2
 	pxor	%xmm5,%xmm5
@@ -678,11 +678,11 @@ gcm_init_clmul:
 	pxor	%xmm5,%xmm2
 
 
-	pshufd	$78,%xmm2,%xmm6
+	pshufd	$0b01001110,%xmm2,%xmm6
 	movdqa	%xmm2,%xmm0
 	pxor	%xmm2,%xmm6
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -718,8 +718,8 @@ gcm_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm2,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm2,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm2,%xmm3
 	movdqu	%xmm2,0(%rdi)
 	pxor	%xmm0,%xmm4
@@ -727,7 +727,7 @@ gcm_init_clmul:
 .byte	102,15,58,15,227,8
 	movdqu	%xmm4,32(%rdi)
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -765,7 +765,7 @@ gcm_init_clmul:
 	pxor	%xmm1,%xmm0
 	movdqa	%xmm0,%xmm5
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -801,8 +801,8 @@ gcm_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm5,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm5,%xmm3
 	movdqu	%xmm5,48(%rdi)
 	pxor	%xmm0,%xmm4
@@ -822,7 +822,7 @@ gcm_gmult_clmul:
 	movdqu	32(%rsi),%xmm4
 .byte	102,15,56,0,197
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -874,20 +874,20 @@ gcm_ghash_clmul:
 	movdqu	32(%rsi),%xmm7
 .byte	102,65,15,56,0,194
 
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	.Lodd_tail
 
 	movdqu	16(%rsi),%xmm6
 	movl	OPENSSL_ia32cap_P+4(%rip),%eax
-	cmpq	$48,%rcx
+	cmpq	$0x30,%rcx
 	jb	.Lskip4x
 
 	andl	$71303168,%eax
 	cmpl	$4194304,%eax
 	je	.Lskip4x
 
-	subq	$48,%rcx
-	movq	$11547335547999543296,%rax
+	subq	$0x30,%rcx
+	movq	$0xA040608020C0E000,%rax
 	movdqu	48(%rsi),%xmm14
 	movdqu	64(%rsi),%xmm15
 
@@ -899,14 +899,14 @@ gcm_ghash_clmul:
 .byte	102,65,15,56,0,218
 .byte	102,69,15,56,0,218
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
 .byte	102,15,58,68,231,0
 
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm11,%xmm12
 .byte	102,68,15,58,68,222,0
 .byte	102,68,15,58,68,238,17
@@ -921,12 +921,12 @@ gcm_ghash_clmul:
 .byte	102,69,15,56,0,218
 .byte	102,69,15,56,0,194
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm8,%xmm0
 	pxor	%xmm11,%xmm12
 .byte	102,69,15,58,68,222,0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 .byte	102,69,15,58,68,238,17
 .byte	102,68,15,58,68,231,0
@@ -934,7 +934,7 @@ gcm_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jc	.Ltail4x
 
 	jmp	.Lmod4_loop
@@ -949,14 +949,14 @@ gcm_ghash_clmul:
 	movdqu	32(%rdx),%xmm3
 	movdqa	%xmm11,%xmm13
 .byte	102,68,15,58,68,199,16
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	xorps	%xmm5,%xmm1
 	pxor	%xmm11,%xmm12
 .byte	102,65,15,56,0,218
 	movups	32(%rsi),%xmm7
 	xorps	%xmm4,%xmm8
 .byte	102,68,15,58,68,218,0
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 
 	pxor	%xmm0,%xmm8
 	movdqa	%xmm3,%xmm5
@@ -1000,7 +1000,7 @@ gcm_ghash_clmul:
 
 	movdqa	%xmm11,%xmm13
 	pxor	%xmm12,%xmm4
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm9,%xmm0
 	pxor	%xmm8,%xmm1
 	pxor	%xmm11,%xmm12
@@ -1010,14 +1010,14 @@ gcm_ghash_clmul:
 	movdqa	%xmm0,%xmm1
 .byte	102,69,15,58,68,238,17
 	xorps	%xmm11,%xmm3
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 
 .byte	102,68,15,58,68,231,0
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jnc	.Lmod4_loop
 
 .Ltail4x:
@@ -1061,10 +1061,10 @@ gcm_ghash_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	addq	$64,%rcx
+	addq	$0x40,%rcx
 	jz	.Ldone
 	movdqu	32(%rsi),%xmm7
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	.Lodd_tail
 .Lskip4x:
 
@@ -1079,7 +1079,7 @@ gcm_ghash_clmul:
 	pxor	%xmm8,%xmm0
 
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
@@ -1087,7 +1087,7 @@ gcm_ghash_clmul:
 
 	leaq	32(%rdx),%rdx
 	nop
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	jbe	.Leven_tail
 	nop
 	jmp	.Lmod_loop
@@ -1096,7 +1096,7 @@ gcm_ghash_clmul:
 .Lmod_loop:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1134,7 +1134,7 @@ gcm_ghash_clmul:
 	pslldq	$8,%xmm0
 	psrldq	$8,%xmm8
 	pxor	%xmm9,%xmm0
-	pshufd	$78,%xmm5,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm4
 	pxor	%xmm8,%xmm1
 	pxor	%xmm5,%xmm4
 
@@ -1150,13 +1150,13 @@ gcm_ghash_clmul:
 .byte	102,15,58,68,231,0
 	pxor	%xmm1,%xmm0
 
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	ja	.Lmod_loop
 
 .Leven_tail:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1204,7 +1204,7 @@ gcm_ghash_clmul:
 .byte	102,69,15,56,0,194
 	pxor	%xmm8,%xmm0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17

deps/openssl/asm_obsolete/x64-elf-gas/sha/sha1-mb-x86_64.s

@@ -2599,10 +2599,10 @@ _shaext_shortcut:
 	punpcklqdq	%xmm5,%xmm0
 	punpckhqdq	%xmm5,%xmm8
 
-	pshufd	$63,%xmm7,%xmm1
-	pshufd	$127,%xmm7,%xmm9
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm8,%xmm8
+	pshufd	$0b00111111,%xmm7,%xmm1
+	pshufd	$0b01111111,%xmm7,%xmm9
+	pshufd	$0b00011011,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm8,%xmm8
 	jmp	.Loop_shaext
 
 .align	32
@@ -2857,8 +2857,8 @@ _shaext_shortcut:
 .byte	69,15,58,204,193,3
 .byte	69,15,56,200,214
 
-	pshufd	$0,%xmm6,%xmm11
-	pshufd	$85,%xmm6,%xmm12
+	pshufd	$0x00,%xmm6,%xmm11
+	pshufd	$0x55,%xmm6,%xmm12
 	movdqa	%xmm6,%xmm7
 	pcmpgtd	%xmm4,%xmm11
 	pcmpgtd	%xmm4,%xmm12
@@ -2888,8 +2888,8 @@ _shaext_shortcut:
 
 	movl	280(%rsp),%edx
 
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm8,%xmm8
+	pshufd	$0b00011011,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm8,%xmm8
 
 	movdqa	%xmm0,%xmm6
 	punpckldq	%xmm8,%xmm0

deps/openssl/asm_obsolete/x64-elf-gas/sha/sha1-x86_64.s

@@ -1240,9 +1240,9 @@ _shaext_shortcut:
 	movdqa	K_XX_XX+160(%rip),%xmm3
 
 	movdqu	(%rsi),%xmm4
-	pshufd	$27,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm0,%xmm0
 	movdqu	16(%rsi),%xmm5
-	pshufd	$27,%xmm1,%xmm1
+	pshufd	$0b00011011,%xmm1,%xmm1
 	movdqu	32(%rsi),%xmm6
 .byte	102,15,56,0,227
 	movdqu	48(%rsi),%xmm7
@@ -1392,8 +1392,8 @@ _shaext_shortcut:
 
 	jnz	.Loop_shaext
 
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm1,%xmm1
+	pshufd	$0b00011011,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm1,%xmm1
 	movdqu	%xmm0,(%rdi)
 	movd	%xmm1,16(%rdi)
 	.byte	0xf3,0xc3

deps/openssl/asm_obsolete/x64-elf-gas/sha/sha256-mb-x86_64.s

@@ -2677,10 +2677,10 @@ _shaext_shortcut:
 	punpckhqdq	%xmm8,%xmm14
 	punpckhqdq	%xmm10,%xmm15
 
-	pshufd	$27,%xmm12,%xmm12
-	pshufd	$27,%xmm13,%xmm13
-	pshufd	$27,%xmm14,%xmm14
-	pshufd	$27,%xmm15,%xmm15
+	pshufd	$0b00011011,%xmm12,%xmm12
+	pshufd	$0b00011011,%xmm13,%xmm13
+	pshufd	$0b00011011,%xmm14,%xmm14
+	pshufd	$0b00011011,%xmm15,%xmm15
 	jmp	.Loop_shaext
 
 .align	32
@@ -2712,11 +2712,11 @@ _shaext_shortcut:
 	movdqa	%xmm2,%xmm0
 	movdqa	%xmm15,112(%rsp)
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	pxor	%xmm12,%xmm4
 	movdqa	%xmm12,64(%rsp)
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	pxor	%xmm14,%xmm8
 	movdqa	%xmm14,96(%rsp)
 	movdqa	16-128(%rbp),%xmm1
@@ -2734,11 +2734,11 @@ _shaext_shortcut:
 .byte	102,68,15,56,0,211
 	prefetcht0	127(%r9)
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 .byte	102,68,15,56,0,219
 .byte	15,56,204,229
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	32-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -2751,14 +2751,14 @@ _shaext_shortcut:
 	movdqa	%xmm2,%xmm0
 	movdqa	%xmm7,%xmm3
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 .byte	102,15,58,15,222,4
 	paddd	%xmm3,%xmm4
 	movdqa	%xmm11,%xmm3
 .byte	102,65,15,58,15,218,4
 .byte	15,56,204,238
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	48-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 .byte	69,15,56,203,247
@@ -2775,13 +2775,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,223,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,195
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm5
 	movdqa	%xmm8,%xmm3
 .byte	102,65,15,58,15,219,4
 .byte	15,56,204,247
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	64-128(%rbp),%xmm1
 	paddd	%xmm4,%xmm1
 .byte	69,15,56,203,247
@@ -2797,13 +2797,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,220,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,200
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm6
 	movdqa	%xmm9,%xmm3
 .byte	102,65,15,58,15,216,4
 .byte	15,56,204,252
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	80-128(%rbp),%xmm1
 	paddd	%xmm5,%xmm1
 .byte	69,15,56,203,247
@@ -2819,13 +2819,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,221,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,209
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm10,%xmm3
 .byte	102,65,15,58,15,217,4
 .byte	15,56,204,229
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	96-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -2841,13 +2841,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,222,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,218
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm4
 	movdqa	%xmm11,%xmm3
 .byte	102,65,15,58,15,218,4
 .byte	15,56,204,238
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	112-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 .byte	69,15,56,203,247
@@ -2863,13 +2863,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,223,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,195
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm5
 	movdqa	%xmm8,%xmm3
 .byte	102,65,15,58,15,219,4
 .byte	15,56,204,247
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	128-128(%rbp),%xmm1
 	paddd	%xmm4,%xmm1
 .byte	69,15,56,203,247
@@ -2885,13 +2885,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,220,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,200
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm6
 	movdqa	%xmm9,%xmm3
 .byte	102,65,15,58,15,216,4
 .byte	15,56,204,252
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	144-128(%rbp),%xmm1
 	paddd	%xmm5,%xmm1
 .byte	69,15,56,203,247
@@ -2907,13 +2907,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,221,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,209
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm10,%xmm3
 .byte	102,65,15,58,15,217,4
 .byte	15,56,204,229
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	160-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -2929,13 +2929,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,222,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,218
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm4
 	movdqa	%xmm11,%xmm3
 .byte	102,65,15,58,15,218,4
 .byte	15,56,204,238
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	176-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 .byte	69,15,56,203,247
@@ -2951,13 +2951,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,223,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,195
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm5
 	movdqa	%xmm8,%xmm3
 .byte	102,65,15,58,15,219,4
 .byte	15,56,204,247
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	192-128(%rbp),%xmm1
 	paddd	%xmm4,%xmm1
 .byte	69,15,56,203,247
@@ -2973,13 +2973,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,220,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,200
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm6
 	movdqa	%xmm9,%xmm3
 .byte	102,65,15,58,15,216,4
 .byte	15,56,204,252
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	208-128(%rbp),%xmm1
 	paddd	%xmm5,%xmm1
 .byte	69,15,56,203,247
@@ -2995,13 +2995,13 @@ _shaext_shortcut:
 .byte	102,15,58,15,221,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,209
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm10,%xmm3
 .byte	102,65,15,58,15,217,4
 	nop
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	224-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -3018,13 +3018,13 @@ _shaext_shortcut:
 	pxor	%xmm6,%xmm6
 .byte	69,15,56,203,254
 .byte	69,15,56,205,218
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	movdqa	240-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 	movq	(%rbx),%xmm7
 	nop
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	240-128(%rbp),%xmm2
 	paddd	%xmm11,%xmm2
 .byte	69,15,56,203,247
@@ -3034,17 +3034,17 @@ _shaext_shortcut:
 	cmovgeq	%rsp,%r8
 	cmpl	4(%rbx),%ecx
 	cmovgeq	%rsp,%r9
-	pshufd	$0,%xmm7,%xmm9
+	pshufd	$0x00,%xmm7,%xmm9
 .byte	69,15,56,203,236
 	movdqa	%xmm2,%xmm0
-	pshufd	$85,%xmm7,%xmm10
+	pshufd	$0x55,%xmm7,%xmm10
 	movdqa	%xmm7,%xmm11
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	pcmpgtd	%xmm6,%xmm9
 	pcmpgtd	%xmm6,%xmm10
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	pcmpgtd	%xmm6,%xmm11
 	movdqa	K256_shaext-16(%rip),%xmm3
 .byte	69,15,56,203,247
@@ -3066,10 +3066,10 @@ _shaext_shortcut:
 
 	movl	280(%rsp),%edx
 
-	pshufd	$27,%xmm12,%xmm12
-	pshufd	$27,%xmm13,%xmm13
-	pshufd	$27,%xmm14,%xmm14
-	pshufd	$27,%xmm15,%xmm15
+	pshufd	$0b00011011,%xmm12,%xmm12
+	pshufd	$0b00011011,%xmm13,%xmm13
+	pshufd	$0b00011011,%xmm14,%xmm14
+	pshufd	$0b00011011,%xmm15,%xmm15
 
 	movdqa	%xmm12,%xmm5
 	movdqa	%xmm13,%xmm6

deps/openssl/asm_obsolete/x64-elf-gas/sha/sha256-x86_64.s

@@ -1754,9 +1754,9 @@ _shaext_shortcut:
 	movdqu	16(%rdi),%xmm2
 	movdqa	512-128(%rcx),%xmm7
 
-	pshufd	$27,%xmm1,%xmm0
-	pshufd	$177,%xmm1,%xmm1
-	pshufd	$27,%xmm2,%xmm2
+	pshufd	$0x1b,%xmm1,%xmm0
+	pshufd	$0xb1,%xmm1,%xmm1
+	pshufd	$0x1b,%xmm2,%xmm2
 	movdqa	%xmm7,%xmm8
 .byte	102,15,58,15,202,8
 	punpcklqdq	%xmm0,%xmm2
@@ -1775,7 +1775,7 @@ _shaext_shortcut:
 .byte	102,15,56,0,231
 	movdqa	%xmm2,%xmm10
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	nop
 	movdqa	%xmm1,%xmm9
 .byte	15,56,203,202
@@ -1784,7 +1784,7 @@ _shaext_shortcut:
 	paddd	%xmm4,%xmm0
 .byte	102,15,56,0,239
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	leaq	64(%rsi),%rsi
 .byte	15,56,204,220
 .byte	15,56,203,202
@@ -1793,7 +1793,7 @@ _shaext_shortcut:
 	paddd	%xmm5,%xmm0
 .byte	102,15,56,0,247
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm6,%xmm7
 .byte	102,15,58,15,253,4
 	nop
@@ -1805,7 +1805,7 @@ _shaext_shortcut:
 	paddd	%xmm6,%xmm0
 .byte	15,56,205,222
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm3,%xmm7
 .byte	102,15,58,15,254,4
 	nop
@@ -1816,7 +1816,7 @@ _shaext_shortcut:
 	paddd	%xmm3,%xmm0
 .byte	15,56,205,227
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm4,%xmm7
 .byte	102,15,58,15,251,4
 	nop
@@ -1827,7 +1827,7 @@ _shaext_shortcut:
 	paddd	%xmm4,%xmm0
 .byte	15,56,205,236
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm5,%xmm7
 .byte	102,15,58,15,252,4
 	nop
@@ -1838,7 +1838,7 @@ _shaext_shortcut:
 	paddd	%xmm5,%xmm0
 .byte	15,56,205,245
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm6,%xmm7
 .byte	102,15,58,15,253,4
 	nop
@@ -1849,7 +1849,7 @@ _shaext_shortcut:
 	paddd	%xmm6,%xmm0
 .byte	15,56,205,222
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm3,%xmm7
 .byte	102,15,58,15,254,4
 	nop
@@ -1860,7 +1860,7 @@ _shaext_shortcut:
 	paddd	%xmm3,%xmm0
 .byte	15,56,205,227
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm4,%xmm7
 .byte	102,15,58,15,251,4
 	nop
@@ -1871,7 +1871,7 @@ _shaext_shortcut:
 	paddd	%xmm4,%xmm0
 .byte	15,56,205,236
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm5,%xmm7
 .byte	102,15,58,15,252,4
 	nop
@@ -1882,7 +1882,7 @@ _shaext_shortcut:
 	paddd	%xmm5,%xmm0
 .byte	15,56,205,245
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm6,%xmm7
 .byte	102,15,58,15,253,4
 	nop
@@ -1893,7 +1893,7 @@ _shaext_shortcut:
 	paddd	%xmm6,%xmm0
 .byte	15,56,205,222
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm3,%xmm7
 .byte	102,15,58,15,254,4
 	nop
@@ -1904,7 +1904,7 @@ _shaext_shortcut:
 	paddd	%xmm3,%xmm0
 .byte	15,56,205,227
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm4,%xmm7
 .byte	102,15,58,15,251,4
 	nop
@@ -1915,7 +1915,7 @@ _shaext_shortcut:
 	paddd	%xmm4,%xmm0
 .byte	15,56,205,236
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm5,%xmm7
 .byte	102,15,58,15,252,4
 .byte	15,56,203,202
@@ -1924,7 +1924,7 @@ _shaext_shortcut:
 	movdqa	448-128(%rcx),%xmm0
 	paddd	%xmm5,%xmm0
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 .byte	15,56,205,245
 	movdqa	%xmm8,%xmm7
 .byte	15,56,203,202
@@ -1933,7 +1933,7 @@ _shaext_shortcut:
 	paddd	%xmm6,%xmm0
 	nop
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	decq	%rdx
 	nop
 .byte	15,56,203,202
@@ -1942,9 +1942,9 @@ _shaext_shortcut:
 	paddd	%xmm9,%xmm1
 	jnz	.Loop_shaext
 
-	pshufd	$177,%xmm2,%xmm2
-	pshufd	$27,%xmm1,%xmm7
-	pshufd	$177,%xmm1,%xmm1
+	pshufd	$0xb1,%xmm2,%xmm2
+	pshufd	$0x1b,%xmm1,%xmm7
+	pshufd	$0xb1,%xmm1,%xmm1
 	punpckhqdq	%xmm2,%xmm1
 .byte	102,15,58,15,215,8
 

deps/openssl/asm_obsolete/x64-elf-gas/x86_64cpuid.s

@@ -44,43 +44,43 @@ OPENSSL_ia32_cpuid:
 	movl	%eax,%r11d
 
 	xorl	%eax,%eax
-	cmpl	$1970169159,%ebx
+	cmpl	$0x756e6547,%ebx
 	setne	%al
 	movl	%eax,%r9d
-	cmpl	$1231384169,%edx
+	cmpl	$0x49656e69,%edx
 	setne	%al
 	orl	%eax,%r9d
-	cmpl	$1818588270,%ecx
+	cmpl	$0x6c65746e,%ecx
 	setne	%al
 	orl	%eax,%r9d
 	jz	.Lintel
 
-	cmpl	$1752462657,%ebx
+	cmpl	$0x68747541,%ebx
 	setne	%al
 	movl	%eax,%r10d
-	cmpl	$1769238117,%edx
+	cmpl	$0x69746E65,%edx
 	setne	%al
 	orl	%eax,%r10d
-	cmpl	$1145913699,%ecx
+	cmpl	$0x444D4163,%ecx
 	setne	%al
 	orl	%eax,%r10d
 	jnz	.Lintel
 
 
-	movl	$2147483648,%eax
+	movl	$0x80000000,%eax
 	cpuid
-	cmpl	$2147483649,%eax
+	cmpl	$0x80000001,%eax
 	jb	.Lintel
 	movl	%eax,%r10d
-	movl	$2147483649,%eax
+	movl	$0x80000001,%eax
 	cpuid
 	orl	%ecx,%r9d
-	andl	$2049,%r9d
+	andl	$0x00000801,%r9d
 
-	cmpl	$2147483656,%r10d
+	cmpl	$0x80000008,%r10d
 	jb	.Lintel
 
-	movl	$2147483656,%eax
+	movl	$0x80000008,%eax
 	cpuid
 	movzbq	%cl,%r10
 	incq	%r10
@@ -92,7 +92,7 @@ OPENSSL_ia32_cpuid:
 	shrl	$16,%ebx
 	cmpb	%r10b,%bl
 	ja	.Lgeneric
-	andl	$4026531839,%edx
+	andl	$0xefffffff,%edx
 	jmp	.Lgeneric
 
 .Lintel:
@@ -105,7 +105,7 @@ OPENSSL_ia32_cpuid:
 	cpuid
 	movl	%eax,%r10d
 	shrl	$14,%r10d
-	andl	$4095,%r10d
+	andl	$0xfff,%r10d
 
 	cmpl	$7,%r11d
 	jb	.Lnocacheinfo
@@ -118,29 +118,29 @@ OPENSSL_ia32_cpuid:
 .Lnocacheinfo:
 	movl	$1,%eax
 	cpuid
-	andl	$3220176895,%edx
+	andl	$0xbfefffff,%edx
 	cmpl	$0,%r9d
 	jne	.Lnotintel
-	orl	$1073741824,%edx
+	orl	$0x40000000,%edx
 	andb	$15,%ah
 	cmpb	$15,%ah
 	jne	.Lnotintel
-	orl	$1048576,%edx
+	orl	$0x00100000,%edx
 .Lnotintel:
 	btl	$28,%edx
 	jnc	.Lgeneric
-	andl	$4026531839,%edx
+	andl	$0xefffffff,%edx
 	cmpl	$0,%r10d
 	je	.Lgeneric
 
-	orl	$268435456,%edx
+	orl	$0x10000000,%edx
 	shrl	$16,%ebx
 	cmpb	$1,%bl
 	ja	.Lgeneric
-	andl	$4026531839,%edx
+	andl	$0xefffffff,%edx
 .Lgeneric:
-	andl	$2048,%r9d
-	andl	$4294965247,%ecx
+	andl	$0x00000800,%r9d
+	andl	$0xfffff7ff,%ecx
 	orl	%ecx,%r9d
 
 	movl	%edx,%r10d
@@ -152,9 +152,9 @@ OPENSSL_ia32_cpuid:
 	cmpl	$6,%eax
 	je	.Ldone
 .Lclear_avx:
-	movl	$4026525695,%eax
+	movl	$0xefffe7ff,%eax
 	andl	%eax,%r9d
-	andl	$4294967263,8(%rdi)
+	andl	$0xffffffdf,8(%rdi)
 .Ldone:
 	shlq	$32,%r9
 	movl	%r10d,%eax

deps/openssl/asm_obsolete/x64-macosx-gas/aes/aes-x86_64.s

@@ -81,8 +81,8 @@ L$enc_loop:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$65280,%edi
-	andl	$65280,%ebp
+	andl	$0x0000ff00,%edi
+	andl	$0x0000ff00,%ebp
 
 	xorl	%edi,%r10d
 	xorl	%ebp,%r11d
@@ -94,8 +94,8 @@ L$enc_loop:
 	movl	0(%r14,%rsi,8),%esi
 	movl	0(%r14,%rdi,8),%edi
 
-	andl	$65280,%esi
-	andl	$65280,%edi
+	andl	$0x0000ff00,%esi
+	andl	$0x0000ff00,%edi
 	shrl	$16,%ebx
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -108,9 +108,9 @@ L$enc_loop:
 	movl	0(%r14,%rdi,8),%edi
 	movl	0(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$16711680,%edi
-	andl	$16711680,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0x00ff0000,%edi
+	andl	$0x00ff0000,%ebp
 
 	xorl	%esi,%r10d
 	xorl	%edi,%r11d
@@ -123,9 +123,9 @@ L$enc_loop:
 	movl	2(%r14,%rdi,8),%edi
 	movl	2(%r14,%rbp,8),%ebp
 
-	andl	$16711680,%esi
-	andl	$4278190080,%edi
-	andl	$4278190080,%ebp
+	andl	$0x00ff0000,%esi
+	andl	$0xff000000,%edi
+	andl	$0xff000000,%ebp
 
 	xorl	%esi,%r8d
 	xorl	%edi,%r10d
@@ -138,8 +138,8 @@ L$enc_loop:
 	movl	2(%r14,%rdi,8),%edi
 	movl	16+0(%r15),%eax
 
-	andl	$4278190080,%esi
-	andl	$4278190080,%edi
+	andl	$0xff000000,%esi
+	andl	$0xff000000,%edi
 
 	xorl	%esi,%r12d
 	xorl	%edi,%r8d
@@ -241,8 +241,8 @@ L$enc_loop_compact:
 	xorl	%r8d,%edx
 	cmpq	16(%rsp),%r15
 	je	L$enc_compact_done
-	movl	$2155905152,%r10d
-	movl	$2155905152,%r11d
+	movl	$0x80808080,%r10d
+	movl	$0x80808080,%r11d
 	andl	%eax,%r10d
 	andl	%ebx,%r11d
 	movl	%r10d,%esi
@@ -253,10 +253,10 @@ L$enc_loop_compact:
 	leal	(%rbx,%rbx,1),%r9d
 	subl	%r10d,%esi
 	subl	%r11d,%edi
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%eax,%r10d
 	movl	%ebx,%r11d
 	xorl	%esi,%r8d
@@ -264,9 +264,9 @@ L$enc_loop_compact:
 
 	xorl	%r8d,%eax
 	xorl	%r9d,%ebx
-	movl	$2155905152,%r12d
+	movl	$0x80808080,%r12d
 	roll	$24,%eax
-	movl	$2155905152,%ebp
+	movl	$0x80808080,%ebp
 	roll	$24,%ebx
 	andl	%ecx,%r12d
 	andl	%edx,%ebp
@@ -289,10 +289,10 @@ L$enc_loop_compact:
 	xorl	%r10d,%eax
 	xorl	%r11d,%ebx
 
-	andl	$4278124286,%r8d
-	andl	$4278124286,%r9d
-	andl	$454761243,%esi
-	andl	$454761243,%edi
+	andl	$0xfefefefe,%r8d
+	andl	$0xfefefefe,%r9d
+	andl	$0x1b1b1b1b,%esi
+	andl	$0x1b1b1b1b,%edi
 	movl	%ecx,%r12d
 	movl	%edx,%ebp
 	xorl	%esi,%r8d
@@ -345,7 +345,7 @@ _AES_encrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -370,7 +370,7 @@ L$enc_prologue:
 	leaq	L$AES_Te+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 
 	call	_x86_64_AES_encrypt_compact
@@ -792,7 +792,7 @@ _AES_decrypt:
 	andq	$-64,%rsp
 	subq	%rsp,%rcx
 	negq	%rcx
-	andq	$960,%rcx
+	andq	$0x3c0,%rcx
 	subq	%rcx,%rsp
 	subq	$32,%rsp
 
@@ -817,7 +817,7 @@ L$dec_prologue:
 	leaq	L$AES_Td+2048(%rip),%r14
 	leaq	768(%rsp),%rbp
 	subq	%r14,%rbp
-	andq	$768,%rbp
+	andq	$0x300,%rbp
 	leaq	(%r14,%rbp,1),%r14
 	shrq	$3,%rbp
 	addq	%rbp,%r14
@@ -1333,9 +1333,9 @@ L$cbc_picked_te:
 	movq	%r14,%r10
 	leaq	2304(%r14),%r11
 	movq	%r15,%r12
-	andq	$4095,%r10
-	andq	$4095,%r11
-	andq	$4095,%r12
+	andq	$0xFFF,%r10
+	andq	$0xFFF,%r11
+	andq	$0xFFF,%r12
 
 	cmpq	%r11,%r12
 	jb	L$cbc_te_break_out
@@ -1344,7 +1344,7 @@ L$cbc_picked_te:
 	jmp	L$cbc_te_ok
 L$cbc_te_break_out:
 	subq	%r10,%r12
-	andq	$4095,%r12
+	andq	$0xFFF,%r12
 	addq	$320,%r12
 	subq	%r12,%r15
 .p2align	2
@@ -1370,7 +1370,7 @@ L$cbc_fast_body:
 
 	movq	%r15,%r10
 	subq	%r14,%r10
-	andq	$4095,%r10
+	andq	$0xfff,%r10
 	cmpq	$2304,%r10
 	jb	L$cbc_do_ecopy
 	cmpq	$4096-248,%r10
@@ -1557,7 +1557,7 @@ L$cbc_slow_prologue:
 	leaq	-88-63(%rcx),%r10
 	subq	%rbp,%r10
 	negq	%r10
-	andq	$960,%r10
+	andq	$0x3c0,%r10
 	subq	%r10,%rbp
 
 	xchgq	%rsp,%rbp
@@ -1586,7 +1586,7 @@ L$cbc_slow_body:
 	leaq	2048(%r14),%r14
 	leaq	768-8(%rsp),%rax
 	subq	%r14,%rax
-	andq	$768,%rax
+	andq	$0x300,%rax
 	leaq	(%r14,%rax,1),%r14
 
 	cmpq	$0,%rbx

deps/openssl/asm_obsolete/x64-macosx-gas/aes/aesni-sha1-x86_64.s

@@ -1392,8 +1392,8 @@ aesni_cbc_sha1_enc_shaext:
 	movups	16(%rcx),%xmm0
 	leaq	112(%rcx),%rcx
 
-	pshufd	$27,%xmm8,%xmm8
-	pshufd	$27,%xmm9,%xmm9
+	pshufd	$0b00011011,%xmm8,%xmm8
+	pshufd	$0b00011011,%xmm9,%xmm9
 	jmp	L$oop_shaext
 
 .p2align	4
@@ -1672,8 +1672,8 @@ L$aesenclast9:
 	leaq	64(%rdi),%rdi
 	jnz	L$oop_shaext
 
-	pshufd	$27,%xmm8,%xmm8
-	pshufd	$27,%xmm9,%xmm9
+	pshufd	$0b00011011,%xmm8,%xmm8
+	pshufd	$0b00011011,%xmm9,%xmm9
 	movups	%xmm2,(%r8)
 	movdqu	%xmm8,(%r9)
 	movd	%xmm9,16(%r9)

deps/openssl/asm_obsolete/x64-macosx-gas/aes/aesni-x86_64.s

@@ -503,7 +503,7 @@ _aesni_ecb_encrypt:
 	testl	%r8d,%r8d
 	jz	L$ecb_decrypt
 
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	L$ecb_enc_tail
 
 	movdqu	(%rdi),%xmm2
@@ -515,7 +515,7 @@ _aesni_ecb_encrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	L$ecb_enc_loop8_enter
 .p2align	4
 L$ecb_enc_loop8:
@@ -543,7 +543,7 @@ L$ecb_enc_loop8_enter:
 
 	call	_aesni_encrypt8
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	L$ecb_enc_loop8
 
 	movups	%xmm2,(%rsi)
@@ -557,22 +557,22 @@ L$ecb_enc_loop8_enter:
 	movups	%xmm8,96(%rsi)
 	movups	%xmm9,112(%rsi)
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	L$ecb_ret
 
 L$ecb_enc_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$ecb_enc_one
 	movups	16(%rdi),%xmm3
 	je	L$ecb_enc_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$ecb_enc_three
 	movups	48(%rdi),%xmm5
 	je	L$ecb_enc_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	L$ecb_enc_five
 	movups	80(%rdi),%xmm7
 	je	L$ecb_enc_six
@@ -646,7 +646,7 @@ L$ecb_enc_six:
 
 .p2align	4
 L$ecb_decrypt:
-	cmpq	$128,%rdx
+	cmpq	$0x80,%rdx
 	jb	L$ecb_dec_tail
 
 	movdqu	(%rdi),%xmm2
@@ -658,7 +658,7 @@ L$ecb_decrypt:
 	movdqu	96(%rdi),%xmm8
 	movdqu	112(%rdi),%xmm9
 	leaq	128(%rdi),%rdi
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jmp	L$ecb_dec_loop8_enter
 .p2align	4
 L$ecb_dec_loop8:
@@ -687,7 +687,7 @@ L$ecb_dec_loop8_enter:
 	call	_aesni_decrypt8
 
 	movups	(%r11),%xmm0
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	jnc	L$ecb_dec_loop8
 
 	movups	%xmm2,(%rsi)
@@ -709,22 +709,22 @@ L$ecb_dec_loop8_enter:
 	movups	%xmm9,112(%rsi)
 	pxor	%xmm9,%xmm9
 	leaq	128(%rsi),%rsi
-	addq	$128,%rdx
+	addq	$0x80,%rdx
 	jz	L$ecb_ret
 
 L$ecb_dec_tail:
 	movups	(%rdi),%xmm2
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$ecb_dec_one
 	movups	16(%rdi),%xmm3
 	je	L$ecb_dec_two
 	movups	32(%rdi),%xmm4
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$ecb_dec_three
 	movups	48(%rdi),%xmm5
 	je	L$ecb_dec_four
 	movups	64(%rdi),%xmm6
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	jb	L$ecb_dec_five
 	movups	80(%rdi),%xmm7
 	je	L$ecb_dec_six
@@ -1598,7 +1598,7 @@ L$oop_enc1_8:
 
 	movdqa	L$xts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -1697,7 +1697,7 @@ L$xts_enc_grandloop:
 .byte	102,15,56,220,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	L$xts_enc_loop6
 .p2align	5
 L$xts_enc_loop6:
@@ -1836,13 +1836,13 @@ L$xts_enc_short:
 	jz	L$xts_enc_done
 
 	pxor	%xmm0,%xmm11
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$xts_enc_one
 	pxor	%xmm0,%xmm12
 	je	L$xts_enc_two
 
 	pxor	%xmm0,%xmm13
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$xts_enc_three
 	pxor	%xmm0,%xmm14
 	je	L$xts_enc_four
@@ -2069,7 +2069,7 @@ L$oop_enc1_11:
 
 	movdqa	L$xts_magic(%rip),%xmm8
 	movdqa	%xmm2,%xmm15
-	pshufd	$95,%xmm2,%xmm9
+	pshufd	$0x5f,%xmm2,%xmm9
 	pxor	%xmm0,%xmm1
 	movdqa	%xmm9,%xmm14
 	paddd	%xmm9,%xmm9
@@ -2168,7 +2168,7 @@ L$xts_dec_grandloop:
 .byte	102,15,56,222,248
 	movups	64(%r11),%xmm0
 	movdqa	%xmm8,80(%rsp)
-	pshufd	$95,%xmm15,%xmm9
+	pshufd	$0x5f,%xmm15,%xmm9
 	jmp	L$xts_dec_loop6
 .p2align	5
 L$xts_dec_loop6:
@@ -2308,13 +2308,13 @@ L$xts_dec_short:
 	jz	L$xts_dec_done
 
 	pxor	%xmm0,%xmm12
-	cmpq	$32,%rdx
+	cmpq	$0x20,%rdx
 	jb	L$xts_dec_one
 	pxor	%xmm0,%xmm13
 	je	L$xts_dec_two
 
 	pxor	%xmm0,%xmm14
-	cmpq	$64,%rdx
+	cmpq	$0x40,%rdx
 	jb	L$xts_dec_three
 	je	L$xts_dec_four
 
@@ -2345,7 +2345,7 @@ L$xts_dec_short:
 	pcmpgtd	%xmm15,%xmm14
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	pshufd	$19,%xmm14,%xmm11
+	pshufd	$0x13,%xmm14,%xmm11
 	andq	$15,%r9
 	jz	L$xts_dec_ret
 
@@ -2634,7 +2634,7 @@ L$cbc_decrypt_bulk:
 	leaq	-8(%rax),%rbp
 	movups	(%r8),%xmm10
 	movl	%r10d,%eax
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	L$cbc_dec_tail
 
 	movups	(%rcx),%xmm0
@@ -2650,14 +2650,14 @@ L$cbc_decrypt_bulk:
 	movdqu	80(%rdi),%xmm7
 	movdqa	%xmm6,%xmm15
 	movl	_OPENSSL_ia32cap_P+4(%rip),%r9d
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	jbe	L$cbc_dec_six_or_seven
 
 	andl	$71303168,%r9d
-	subq	$80,%rdx
+	subq	$0x50,%rdx
 	cmpl	$4194304,%r9d
 	je	L$cbc_dec_loop6_enter
-	subq	$32,%rdx
+	subq	$0x20,%rdx
 	leaq	112(%rcx),%rcx
 	jmp	L$cbc_dec_loop8_enter
 .p2align	4
@@ -2672,7 +2672,7 @@ L$cbc_dec_loop8_enter:
 	movups	16-112(%rcx),%xmm1
 	pxor	%xmm0,%xmm4
 	xorq	%r11,%r11
-	cmpq	$112,%rdx
+	cmpq	$0x70,%rdx
 	pxor	%xmm0,%xmm5
 	pxor	%xmm0,%xmm6
 	pxor	%xmm0,%xmm7
@@ -2857,21 +2857,21 @@ L$cbc_dec_done:
 	movups	%xmm8,96(%rsi)
 	leaq	112(%rsi),%rsi
 
-	subq	$128,%rdx
+	subq	$0x80,%rdx
 	ja	L$cbc_dec_loop8
 
 	movaps	%xmm9,%xmm2
 	leaq	-112(%rcx),%rcx
-	addq	$112,%rdx
+	addq	$0x70,%rdx
 	jle	L$cbc_dec_clear_tail_collected
 	movups	%xmm9,(%rsi)
 	leaq	16(%rsi),%rsi
-	cmpq	$80,%rdx
+	cmpq	$0x50,%rdx
 	jbe	L$cbc_dec_tail
 
 	movaps	%xmm11,%xmm2
 L$cbc_dec_six_or_seven:
-	cmpq	$96,%rdx
+	cmpq	$0x60,%rdx
 	ja	L$cbc_dec_seven
 
 	movaps	%xmm7,%xmm8
@@ -2964,33 +2964,33 @@ L$cbc_dec_loop6_enter:
 	movl	%r10d,%eax
 	movdqu	%xmm6,64(%rsi)
 	leaq	80(%rsi),%rsi
-	subq	$96,%rdx
+	subq	$0x60,%rdx
 	ja	L$cbc_dec_loop6
 
 	movdqa	%xmm7,%xmm2
-	addq	$80,%rdx
+	addq	$0x50,%rdx
 	jle	L$cbc_dec_clear_tail_collected
 	movups	%xmm7,(%rsi)
 	leaq	16(%rsi),%rsi
 
 L$cbc_dec_tail:
 	movups	(%rdi),%xmm2
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_one
 
 	movups	16(%rdi),%xmm3
 	movaps	%xmm2,%xmm11
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_two
 
 	movups	32(%rdi),%xmm4
 	movaps	%xmm3,%xmm12
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_three
 
 	movups	48(%rdi),%xmm5
 	movaps	%xmm4,%xmm13
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jbe	L$cbc_dec_four
 
 	movups	64(%rdi),%xmm6
@@ -3015,7 +3015,7 @@ L$cbc_dec_tail:
 	movdqa	%xmm6,%xmm2
 	pxor	%xmm6,%xmm6
 	pxor	%xmm7,%xmm7
-	subq	$16,%rdx
+	subq	$0x10,%rdx
 	jmp	L$cbc_dec_tail_collected
 
 .p2align	4
@@ -3332,7 +3332,7 @@ L$oop_key192:
 	pslldq	$4,%xmm0
 	pxor	%xmm3,%xmm0
 
-	pshufd	$255,%xmm0,%xmm3
+	pshufd	$0xff,%xmm0,%xmm3
 	pxor	%xmm1,%xmm3
 	pslldq	$4,%xmm1
 	pxor	%xmm1,%xmm3
@@ -3419,7 +3419,7 @@ L$oop_key256:
 	decl	%r10d
 	jz	L$done_key256
 
-	pshufd	$255,%xmm0,%xmm2
+	pshufd	$0xff,%xmm0,%xmm2
 	pxor	%xmm3,%xmm3
 .byte	102,15,56,221,211
 
@@ -3462,11 +3462,11 @@ L$key_expansion_128:
 	movups	%xmm0,(%rax)
 	leaq	16(%rax),%rax
 L$key_expansion_128_cold:
-	shufps	$16,%xmm0,%xmm4
+	shufps	$0b00010000,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$140,%xmm0,%xmm4
+	shufps	$0b10001100,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$255,%xmm1,%xmm1
+	shufps	$0b11111111,%xmm1,%xmm1
 	xorps	%xmm1,%xmm0
 	.byte	0xf3,0xc3
 
@@ -3477,25 +3477,25 @@ L$key_expansion_192a:
 L$key_expansion_192a_cold:
 	movaps	%xmm2,%xmm5
 L$key_expansion_192b_warm:
-	shufps	$16,%xmm0,%xmm4
+	shufps	$0b00010000,%xmm0,%xmm4
 	movdqa	%xmm2,%xmm3
 	xorps	%xmm4,%xmm0
-	shufps	$140,%xmm0,%xmm4
+	shufps	$0b10001100,%xmm0,%xmm4
 	pslldq	$4,%xmm3
 	xorps	%xmm4,%xmm0
-	pshufd	$85,%xmm1,%xmm1
+	pshufd	$0b01010101,%xmm1,%xmm1
 	pxor	%xmm3,%xmm2
 	pxor	%xmm1,%xmm0
-	pshufd	$255,%xmm0,%xmm3
+	pshufd	$0b11111111,%xmm0,%xmm3
 	pxor	%xmm3,%xmm2
 	.byte	0xf3,0xc3
 
 .p2align	4
 L$key_expansion_192b:
 	movaps	%xmm0,%xmm3
-	shufps	$68,%xmm0,%xmm5
+	shufps	$0b01000100,%xmm0,%xmm5
 	movups	%xmm5,(%rax)
-	shufps	$78,%xmm2,%xmm3
+	shufps	$0b01001110,%xmm2,%xmm3
 	movups	%xmm3,16(%rax)
 	leaq	32(%rax),%rax
 	jmp	L$key_expansion_192b_warm
@@ -3505,11 +3505,11 @@ L$key_expansion_256a:
 	movups	%xmm2,(%rax)
 	leaq	16(%rax),%rax
 L$key_expansion_256a_cold:
-	shufps	$16,%xmm0,%xmm4
+	shufps	$0b00010000,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$140,%xmm0,%xmm4
+	shufps	$0b10001100,%xmm0,%xmm4
 	xorps	%xmm4,%xmm0
-	shufps	$255,%xmm1,%xmm1
+	shufps	$0b11111111,%xmm1,%xmm1
 	xorps	%xmm1,%xmm0
 	.byte	0xf3,0xc3
 
@@ -3518,11 +3518,11 @@ L$key_expansion_256b:
 	movups	%xmm0,(%rax)
 	leaq	16(%rax),%rax
 
-	shufps	$16,%xmm2,%xmm4
+	shufps	$0b00010000,%xmm2,%xmm4
 	xorps	%xmm4,%xmm2
-	shufps	$140,%xmm2,%xmm4
+	shufps	$0b10001100,%xmm2,%xmm4
 	xorps	%xmm4,%xmm2
-	shufps	$170,%xmm1,%xmm1
+	shufps	$0b10101010,%xmm1,%xmm1
 	xorps	%xmm1,%xmm2
 	.byte	0xf3,0xc3
 

deps/openssl/asm_obsolete/x64-macosx-gas/aes/bsaes-x86_64.s

@@ -324,45 +324,45 @@ L$enc_sbox:
 	pxor	%xmm2,%xmm5
 	decl	%r10d
 	jl	L$enc_done
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm3,%xmm9
+	pshufd	$0x93,%xmm3,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm5,%xmm10
+	pshufd	$0x93,%xmm5,%xmm10
 	pxor	%xmm9,%xmm3
-	pshufd	$147,%xmm2,%xmm11
+	pshufd	$0x93,%xmm2,%xmm11
 	pxor	%xmm10,%xmm5
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm2
-	pshufd	$147,%xmm1,%xmm13
+	pshufd	$0x93,%xmm1,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm1
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm2,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm5,%xmm11
-	pshufd	$78,%xmm2,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm7
 	pxor	%xmm1,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm3,%xmm10
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm1,%xmm5
+	pshufd	$0x4E,%xmm1,%xmm5
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm12,%xmm8
 	pxor	%xmm10,%xmm2
 	pxor	%xmm14,%xmm6
@@ -796,24 +796,24 @@ L$dec_sbox:
 	decl	%r10d
 	jl	L$dec_done
 
-	pshufd	$78,%xmm15,%xmm7
-	pshufd	$78,%xmm2,%xmm13
+	pshufd	$0x4E,%xmm15,%xmm7
+	pshufd	$0x4E,%xmm2,%xmm13
 	pxor	%xmm15,%xmm7
-	pshufd	$78,%xmm4,%xmm14
+	pshufd	$0x4E,%xmm4,%xmm14
 	pxor	%xmm2,%xmm13
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0x4E,%xmm0,%xmm8
 	pxor	%xmm4,%xmm14
-	pshufd	$78,%xmm5,%xmm9
+	pshufd	$0x4E,%xmm5,%xmm9
 	pxor	%xmm0,%xmm8
-	pshufd	$78,%xmm3,%xmm10
+	pshufd	$0x4E,%xmm3,%xmm10
 	pxor	%xmm5,%xmm9
 	pxor	%xmm13,%xmm15
 	pxor	%xmm13,%xmm0
-	pshufd	$78,%xmm1,%xmm11
+	pshufd	$0x4E,%xmm1,%xmm11
 	pxor	%xmm3,%xmm10
 	pxor	%xmm7,%xmm5
 	pxor	%xmm8,%xmm3
-	pshufd	$78,%xmm6,%xmm12
+	pshufd	$0x4E,%xmm6,%xmm12
 	pxor	%xmm1,%xmm11
 	pxor	%xmm14,%xmm0
 	pxor	%xmm9,%xmm1
@@ -827,45 +827,45 @@ L$dec_sbox:
 	pxor	%xmm14,%xmm1
 	pxor	%xmm14,%xmm6
 	pxor	%xmm12,%xmm4
-	pshufd	$147,%xmm15,%xmm7
-	pshufd	$147,%xmm0,%xmm8
+	pshufd	$0x93,%xmm15,%xmm7
+	pshufd	$0x93,%xmm0,%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$147,%xmm5,%xmm9
+	pshufd	$0x93,%xmm5,%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$147,%xmm3,%xmm10
+	pshufd	$0x93,%xmm3,%xmm10
 	pxor	%xmm9,%xmm5
-	pshufd	$147,%xmm1,%xmm11
+	pshufd	$0x93,%xmm1,%xmm11
 	pxor	%xmm10,%xmm3
-	pshufd	$147,%xmm6,%xmm12
+	pshufd	$0x93,%xmm6,%xmm12
 	pxor	%xmm11,%xmm1
-	pshufd	$147,%xmm2,%xmm13
+	pshufd	$0x93,%xmm2,%xmm13
 	pxor	%xmm12,%xmm6
-	pshufd	$147,%xmm4,%xmm14
+	pshufd	$0x93,%xmm4,%xmm14
 	pxor	%xmm13,%xmm2
 	pxor	%xmm14,%xmm4
 
 	pxor	%xmm15,%xmm8
 	pxor	%xmm4,%xmm7
 	pxor	%xmm4,%xmm8
-	pshufd	$78,%xmm15,%xmm15
+	pshufd	$0x4E,%xmm15,%xmm15
 	pxor	%xmm0,%xmm9
-	pshufd	$78,%xmm0,%xmm0
+	pshufd	$0x4E,%xmm0,%xmm0
 	pxor	%xmm1,%xmm12
 	pxor	%xmm7,%xmm15
 	pxor	%xmm6,%xmm13
 	pxor	%xmm8,%xmm0
 	pxor	%xmm3,%xmm11
-	pshufd	$78,%xmm1,%xmm7
+	pshufd	$0x4E,%xmm1,%xmm7
 	pxor	%xmm2,%xmm14
-	pshufd	$78,%xmm6,%xmm8
+	pshufd	$0x4E,%xmm6,%xmm8
 	pxor	%xmm5,%xmm10
-	pshufd	$78,%xmm3,%xmm1
+	pshufd	$0x4E,%xmm3,%xmm1
 	pxor	%xmm4,%xmm10
-	pshufd	$78,%xmm4,%xmm6
+	pshufd	$0x4E,%xmm4,%xmm6
 	pxor	%xmm4,%xmm11
-	pshufd	$78,%xmm2,%xmm3
+	pshufd	$0x4E,%xmm2,%xmm3
 	pxor	%xmm11,%xmm7
-	pshufd	$78,%xmm5,%xmm2
+	pshufd	$0x4E,%xmm5,%xmm2
 	pxor	%xmm12,%xmm8
 	pxor	%xmm1,%xmm10
 	pxor	%xmm14,%xmm6
@@ -1552,20 +1552,20 @@ L$xts_enc_prologue:
 	movdqa	%xmm7,(%rax)
 
 	andq	$-16,%r14
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	L$xts_enc_short
 	jmp	L$xts_enc_loop
 
 .p2align	4
 L$xts_enc_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1573,7 +1573,7 @@ L$xts_enc_loop:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1582,7 +1582,7 @@ L$xts_enc_loop:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1592,7 +1592,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1602,7 +1602,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1612,7 +1612,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1622,7 +1622,7 @@ L$xts_enc_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -1666,20 +1666,20 @@ L$xts_enc_loop:
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	L$xts_enc_loop
 
 L$xts_enc_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	L$xts_enc_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -1687,7 +1687,7 @@ L$xts_enc_short:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -1698,7 +1698,7 @@ L$xts_enc_short:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	L$xts_enc_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -1710,7 +1710,7 @@ L$xts_enc_short:
 	cmpq	$32,%r14
 	je	L$xts_enc_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -1722,7 +1722,7 @@ L$xts_enc_short:
 	cmpq	$48,%r14
 	je	L$xts_enc_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -1734,7 +1734,7 @@ L$xts_enc_short:
 	cmpq	$64,%r14
 	je	L$xts_enc_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -1746,7 +1746,7 @@ L$xts_enc_short:
 	cmpq	$80,%r14
 	je	L$xts_enc_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2011,20 +2011,20 @@ L$xts_dec_prologue:
 	shlq	$4,%rax
 	subq	%rax,%r14
 
-	subq	$128,%rsp
+	subq	$0x80,%rsp
 	movdqa	32(%rbp),%xmm6
 
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jc	L$xts_dec_short
 	jmp	L$xts_dec_loop
 
 .p2align	4
 L$xts_dec_loop:
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2032,7 +2032,7 @@ L$xts_dec_loop:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2041,7 +2041,7 @@ L$xts_dec_loop:
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 	movdqu	0(%r12),%xmm7
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2051,7 +2051,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	16(%r12),%xmm8
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2061,7 +2061,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	32(%r12),%xmm9
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2071,7 +2071,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	48(%r12),%xmm10
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2081,7 +2081,7 @@ L$xts_dec_loop:
 	pxor	%xmm13,%xmm6
 	movdqu	64(%r12),%xmm11
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2125,20 +2125,20 @@ L$xts_dec_loop:
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
 
-	subq	$128,%r14
+	subq	$0x80,%r14
 	jnc	L$xts_dec_loop
 
 L$xts_dec_short:
-	addq	$128,%r14
+	addq	$0x80,%r14
 	jz	L$xts_dec_done
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm15
 	movdqa	%xmm6,0(%rsp)
@@ -2146,7 +2146,7 @@ L$xts_dec_short:
 	pand	%xmm12,%xmm13
 	pcmpgtd	%xmm6,%xmm14
 	pxor	%xmm13,%xmm6
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm0
 	movdqa	%xmm6,16(%rsp)
@@ -2157,7 +2157,7 @@ L$xts_dec_short:
 	movdqu	0(%r12),%xmm7
 	cmpq	$16,%r14
 	je	L$xts_dec_1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm1
 	movdqa	%xmm6,32(%rsp)
@@ -2169,7 +2169,7 @@ L$xts_dec_short:
 	cmpq	$32,%r14
 	je	L$xts_dec_2
 	pxor	%xmm7,%xmm15
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm2
 	movdqa	%xmm6,48(%rsp)
@@ -2181,7 +2181,7 @@ L$xts_dec_short:
 	cmpq	$48,%r14
 	je	L$xts_dec_3
 	pxor	%xmm8,%xmm0
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm3
 	movdqa	%xmm6,64(%rsp)
@@ -2193,7 +2193,7 @@ L$xts_dec_short:
 	cmpq	$64,%r14
 	je	L$xts_dec_4
 	pxor	%xmm9,%xmm1
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm4
 	movdqa	%xmm6,80(%rsp)
@@ -2205,7 +2205,7 @@ L$xts_dec_short:
 	cmpq	$80,%r14
 	je	L$xts_dec_5
 	pxor	%xmm10,%xmm2
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	pxor	%xmm14,%xmm14
 	movdqa	%xmm6,%xmm5
 	movdqa	%xmm6,96(%rsp)
@@ -2382,7 +2382,7 @@ L$xts_dec_done:
 	pxor	%xmm14,%xmm14
 	movdqa	L$xts_magic(%rip),%xmm12
 	pcmpgtd	%xmm6,%xmm14
-	pshufd	$19,%xmm14,%xmm13
+	pshufd	$0x13,%xmm14,%xmm13
 	movdqa	%xmm6,%xmm5
 	paddq	%xmm6,%xmm6
 	pand	%xmm12,%xmm13

deps/openssl/asm_obsolete/x64-macosx-gas/aes/vpaes-x86_64.s

@@ -60,7 +60,7 @@ L$enc_loop:
 	addq	$16,%r11
 	pxor	%xmm0,%xmm3
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	subq	$1,%rax
 	pxor	%xmm3,%xmm0
 
@@ -120,10 +120,10 @@ _vpaes_decrypt_core:
 	pand	%xmm9,%xmm0
 .byte	102,15,56,0,208
 	movdqa	L$k_dipt+16(%rip),%xmm0
-	xorq	$48,%r11
+	xorq	$0x30,%r11
 	leaq	L$k_dsbd(%rip),%r10
 .byte	102,15,56,0,193
-	andq	$48,%r11
+	andq	$0x30,%r11
 	pxor	%xmm5,%xmm2
 	movdqa	L$k_mc_forward+48(%rip),%xmm5
 	pxor	%xmm2,%xmm0
@@ -242,7 +242,7 @@ L$schedule_am_decrypting:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	movdqu	%xmm3,(%rdx)
-	xorq	$48,%r8
+	xorq	$0x30,%r8
 
 L$schedule_go:
 	cmpl	$192,%esi
@@ -332,7 +332,7 @@ L$oop_schedule_256:
 	call	_vpaes_schedule_mangle
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 	movdqa	%xmm7,%xmm5
 	movdqa	%xmm6,%xmm7
 	call	_vpaes_schedule_low_round
@@ -399,8 +399,8 @@ L$schedule_mangle_last_dec:
 
 .p2align	4
 _vpaes_schedule_192_smear:
-	pshufd	$128,%xmm6,%xmm1
-	pshufd	$254,%xmm7,%xmm0
+	pshufd	$0x80,%xmm6,%xmm1
+	pshufd	$0xFE,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
 	pxor	%xmm1,%xmm1
 	pxor	%xmm0,%xmm6
@@ -437,7 +437,7 @@ _vpaes_schedule_round:
 	pxor	%xmm1,%xmm7
 
 
-	pshufd	$255,%xmm0,%xmm0
+	pshufd	$0xFF,%xmm0,%xmm0
 .byte	102,15,58,15,192,1
 
 
@@ -596,7 +596,7 @@ L$schedule_mangle_both:
 	movdqa	(%r8,%r10,1),%xmm1
 .byte	102,15,56,0,217
 	addq	$-16,%r8
-	andq	$48,%r8
+	andq	$0x30,%r8
 	movdqu	%xmm3,(%rdx)
 	.byte	0xf3,0xc3
 
@@ -614,7 +614,7 @@ _vpaes_set_encrypt_key:
 	movl	%eax,240(%rdx)
 
 	movl	$0,%ecx
-	movl	$48,%r8d
+	movl	$0x30,%r8d
 	call	_vpaes_schedule_core
 	xorl	%eax,%eax
 	.byte	0xf3,0xc3

deps/openssl/asm_obsolete/x64-macosx-gas/bn/rsaz-x86_64.s

@@ -461,48 +461,94 @@ _rsaz_512_mul_gather4:
 	pushq	%r14
 	pushq	%r15
 
-	movl	%r9d,%r9d
-	subq	$128+24,%rsp
+	subq	$152,%rsp
 L$mul_gather4_body:
-	movl	64(%rdx,%r9,4),%eax
-.byte	102,72,15,110,199
-	movl	(%rdx,%r9,4),%ebx
-.byte	102,72,15,110,201
+	movd	%r9d,%xmm8
+	movdqa	L$inc+16(%rip),%xmm1
+	movdqa	L$inc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
+
+	movdqa	0(%rdx),%xmm8
+	movdqa	16(%rdx),%xmm9
+	movdqa	32(%rdx),%xmm10
+	movdqa	48(%rdx),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rdx),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rdx),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rdx),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rdx),%xmm15
+	leaq	128(%rdx),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
 	movq	%r8,128(%rsp)
+	movq	%rdi,128+8(%rsp)
+	movq	%rcx,128+16(%rsp)
 
-	shlq	$32,%rax
-	orq	%rax,%rbx
 	movq	(%rsi),%rax
 	movq	8(%rsi),%rcx
-	leaq	128(%rdx,%r9,4),%rbp
 	mulq	%rbx
 	movq	%rax,(%rsp)
 	movq	%rcx,%rax
 	movq	%rdx,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r8
 	movq	16(%rsi),%rax
 	movq	%rdx,%r9
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r9
 	movq	24(%rsi),%rax
 	movq	%rdx,%r10
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r10
 	movq	32(%rsi),%rax
 	movq	%rdx,%r11
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r11
 	movq	40(%rsi),%rax
 	movq	%rdx,%r12
@@ -515,14 +561,12 @@ L$mul_gather4_body:
 	adcq	$0,%r13
 
 	mulq	%rbx
-	leaq	128(%rbp),%rbp
 	addq	%rax,%r13
 	movq	56(%rsi),%rax
 	movq	%rdx,%r14
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r14
 	movq	(%rsi),%rax
 	movq	%rdx,%r15
@@ -534,6 +578,35 @@ L$mul_gather4_body:
 
 .p2align	5
 L$oop_mul_gather:
+	movdqa	0(%rbp),%xmm8
+	movdqa	16(%rbp),%xmm9
+	movdqa	32(%rbp),%xmm10
+	movdqa	48(%rbp),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rbp),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rbp),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rbp),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rbp),%xmm15
+	leaq	128(%rbp),%rbp
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+.byte	102,76,15,126,195
+
 	mulq	%rbx
 	addq	%rax,%r8
 	movq	8(%rsi),%rax
@@ -542,7 +615,6 @@ L$oop_mul_gather:
 	adcq	$0,%r8
 
 	mulq	%rbx
-	movd	(%rbp),%xmm4
 	addq	%rax,%r9
 	movq	16(%rsi),%rax
 	adcq	$0,%rdx
@@ -551,7 +623,6 @@ L$oop_mul_gather:
 	adcq	$0,%r9
 
 	mulq	%rbx
-	movd	64(%rbp),%xmm5
 	addq	%rax,%r10
 	movq	24(%rsi),%rax
 	adcq	$0,%rdx
@@ -560,7 +631,6 @@ L$oop_mul_gather:
 	adcq	$0,%r10
 
 	mulq	%rbx
-	pslldq	$4,%xmm5
 	addq	%rax,%r11
 	movq	32(%rsi),%rax
 	adcq	$0,%rdx
@@ -569,7 +639,6 @@ L$oop_mul_gather:
 	adcq	$0,%r11
 
 	mulq	%rbx
-	por	%xmm5,%xmm4
 	addq	%rax,%r12
 	movq	40(%rsi),%rax
 	adcq	$0,%rdx
@@ -594,7 +663,6 @@ L$oop_mul_gather:
 	adcq	$0,%r14
 
 	mulq	%rbx
-.byte	102,72,15,126,227
 	addq	%rax,%r15
 	movq	(%rsi),%rax
 	adcq	$0,%rdx
@@ -602,7 +670,6 @@ L$oop_mul_gather:
 	movq	%rdx,%r15
 	adcq	$0,%r15
 
-	leaq	128(%rbp),%rbp
 	leaq	8(%rdi),%rdi
 
 	decl	%ecx
@@ -617,8 +684,8 @@ L$oop_mul_gather:
 	movq	%r14,48(%rdi)
 	movq	%r15,56(%rdi)
 
-.byte	102,72,15,126,199
-.byte	102,72,15,126,205
+	movq	128+8(%rsp),%rdi
+	movq	128+16(%rsp),%rbp
 
 	movq	(%rsp),%r8
 	movq	8(%rsp),%r9
@@ -667,7 +734,7 @@ _rsaz_512_mul_scatter4:
 	movl	%r9d,%r9d
 	subq	$128+24,%rsp
 L$mul_scatter4_body:
-	leaq	(%r8,%r9,4),%r8
+	leaq	(%r8,%r9,8),%r8
 .byte	102,72,15,110,199
 .byte	102,72,15,110,202
 .byte	102,73,15,110,208
@@ -703,30 +770,14 @@ L$mul_scatter4_body:
 
 	call	__rsaz_512_subtract
 
-	movl	%r8d,0(%rsi)
-	shrq	$32,%r8
-	movl	%r9d,128(%rsi)
-	shrq	$32,%r9
-	movl	%r10d,256(%rsi)
-	shrq	$32,%r10
-	movl	%r11d,384(%rsi)
-	shrq	$32,%r11
-	movl	%r12d,512(%rsi)
-	shrq	$32,%r12
-	movl	%r13d,640(%rsi)
-	shrq	$32,%r13
-	movl	%r14d,768(%rsi)
-	shrq	$32,%r14
-	movl	%r15d,896(%rsi)
-	shrq	$32,%r15
-	movl	%r8d,64(%rsi)
-	movl	%r9d,192(%rsi)
-	movl	%r10d,320(%rsi)
-	movl	%r11d,448(%rsi)
-	movl	%r12d,576(%rsi)
-	movl	%r13d,704(%rsi)
-	movl	%r14d,832(%rsi)
-	movl	%r15d,960(%rsi)
+	movq	%r8,0(%rsi)
+	movq	%r9,128(%rsi)
+	movq	%r10,256(%rsi)
+	movq	%r11,384(%rsi)
+	movq	%r12,512(%rsi)
+	movq	%r13,640(%rsi)
+	movq	%r14,768(%rsi)
+	movq	%r15,896(%rsi)
 
 	leaq	128+24+48(%rsp),%rax
 	movq	-48(%rax),%r15
@@ -1079,16 +1130,14 @@ L$oop_mul:
 
 .p2align	4
 _rsaz_512_scatter4:
-	leaq	(%rdi,%rdx,4),%rdi
+	leaq	(%rdi,%rdx,8),%rdi
 	movl	$8,%r9d
 	jmp	L$oop_scatter
 .p2align	4
 L$oop_scatter:
 	movq	(%rsi),%rax
 	leaq	8(%rsi),%rsi
-	movl	%eax,(%rdi)
-	shrq	$32,%rax
-	movl	%eax,64(%rdi)
+	movq	%rax,(%rdi)
 	leaq	128(%rdi),%rdi
 	decl	%r9d
 	jnz	L$oop_scatter
@@ -1099,18 +1148,72 @@ L$oop_scatter:
 
 .p2align	4
 _rsaz_512_gather4:
-	leaq	(%rsi,%rdx,4),%rsi
+	movd	%edx,%xmm8
+	movdqa	L$inc+16(%rip),%xmm1
+	movdqa	L$inc(%rip),%xmm0
+
+	pshufd	$0,%xmm8,%xmm8
+	movdqa	%xmm1,%xmm7
+	movdqa	%xmm1,%xmm2
+	paddd	%xmm0,%xmm1
+	pcmpeqd	%xmm8,%xmm0
+	movdqa	%xmm7,%xmm3
+	paddd	%xmm1,%xmm2
+	pcmpeqd	%xmm8,%xmm1
+	movdqa	%xmm7,%xmm4
+	paddd	%xmm2,%xmm3
+	pcmpeqd	%xmm8,%xmm2
+	movdqa	%xmm7,%xmm5
+	paddd	%xmm3,%xmm4
+	pcmpeqd	%xmm8,%xmm3
+	movdqa	%xmm7,%xmm6
+	paddd	%xmm4,%xmm5
+	pcmpeqd	%xmm8,%xmm4
+	paddd	%xmm5,%xmm6
+	pcmpeqd	%xmm8,%xmm5
+	paddd	%xmm6,%xmm7
+	pcmpeqd	%xmm8,%xmm6
+	pcmpeqd	%xmm8,%xmm7
 	movl	$8,%r9d
 	jmp	L$oop_gather
 .p2align	4
 L$oop_gather:
-	movl	(%rsi),%eax
-	movl	64(%rsi),%r8d
+	movdqa	0(%rsi),%xmm8
+	movdqa	16(%rsi),%xmm9
+	movdqa	32(%rsi),%xmm10
+	movdqa	48(%rsi),%xmm11
+	pand	%xmm0,%xmm8
+	movdqa	64(%rsi),%xmm12
+	pand	%xmm1,%xmm9
+	movdqa	80(%rsi),%xmm13
+	pand	%xmm2,%xmm10
+	movdqa	96(%rsi),%xmm14
+	pand	%xmm3,%xmm11
+	movdqa	112(%rsi),%xmm15
 	leaq	128(%rsi),%rsi
-	shlq	$32,%r8
-	orq	%r8,%rax
-	movq	%rax,(%rdi)
+	pand	%xmm4,%xmm12
+	pand	%xmm5,%xmm13
+	pand	%xmm6,%xmm14
+	pand	%xmm7,%xmm15
+	por	%xmm10,%xmm8
+	por	%xmm11,%xmm9
+	por	%xmm12,%xmm8
+	por	%xmm13,%xmm9
+	por	%xmm14,%xmm8
+	por	%xmm15,%xmm9
+
+	por	%xmm9,%xmm8
+	pshufd	$0x4e,%xmm8,%xmm9
+	por	%xmm9,%xmm8
+	movq	%xmm8,(%rdi)
 	leaq	8(%rdi),%rdi
 	decl	%r9d
 	jnz	L$oop_gather
 	.byte	0xf3,0xc3
+L$SEH_end_rsaz_512_gather4:
+
+
+.p2align	6
+L$inc:
+.long	0,0, 1,1
+.long	2,2, 2,2

deps/openssl/asm_obsolete/x64-macosx-gas/bn/x86_64-gf2m.s

@@ -242,7 +242,7 @@ L$body_mul_2x2:
 	movq	%rcx,56(%rsp)
 	movq	%r8,64(%rsp)
 
-	movq	$15,%r8
+	movq	$0xf,%r8
 	movq	%rsi,%rax
 	movq	%rcx,%rbp
 	call	_mul_1x1

deps/openssl/asm_obsolete/x64-macosx-gas/bn/x86_64-mont.s

@@ -633,20 +633,20 @@ L$sqr8x_enter:
 
 
 
-	leaq	-64(%rsp,%r9,4),%r11
+	leaq	-64(%rsp,%r9,2),%r11
 	movq	(%r8),%r8
 	subq	%rsi,%r11
 	andq	$4095,%r11
 	cmpq	%r11,%r10
 	jb	L$sqr8x_sp_alt
 	subq	%r11,%rsp
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	-64(%rsp,%r9,2),%rsp
 	jmp	L$sqr8x_sp_done
 
 .p2align	5
 L$sqr8x_sp_alt:
-	leaq	4096-64(,%r9,4),%r10
-	leaq	-64(%rsp,%r9,4),%rsp
+	leaq	4096-64(,%r9,2),%r10
+	leaq	-64(%rsp,%r9,2),%rsp
 	subq	%r10,%r11
 	movq	$0,%r10
 	cmovcq	%r10,%r11
@@ -656,58 +656,80 @@ L$sqr8x_sp_done:
 	movq	%r9,%r10
 	negq	%r9
 
-	leaq	64(%rsp,%r9,2),%r11
 	movq	%r8,32(%rsp)
 	movq	%rax,40(%rsp)
 L$sqr8x_body:
 
-	movq	%r9,%rbp
-.byte	102,73,15,110,211
-	shrq	$3+2,%rbp
-	movl	_OPENSSL_ia32cap_P+8(%rip),%eax
-	jmp	L$sqr8x_copy_n
-
-.p2align	5
-L$sqr8x_copy_n:
-	movq	0(%rcx),%xmm0
-	movq	8(%rcx),%xmm1
-	movq	16(%rcx),%xmm3
-	movq	24(%rcx),%xmm4
-	leaq	32(%rcx),%rcx
-	movdqa	%xmm0,0(%r11)
-	movdqa	%xmm1,16(%r11)
-	movdqa	%xmm3,32(%r11)
-	movdqa	%xmm4,48(%r11)
-	leaq	64(%r11),%r11
-	decq	%rbp
-	jnz	L$sqr8x_copy_n
-
+.byte	102,72,15,110,209
 	pxor	%xmm0,%xmm0
 .byte	102,72,15,110,207
 .byte	102,73,15,110,218
 	call	_bn_sqr8x_internal
 
+
+
+
+	leaq	(%rdi,%r9,1),%rbx
+	movq	%r9,%rcx
+	movq	%r9,%rdx
+.byte	102,72,15,126,207
+	sarq	$3+2,%rcx
+	jmp	L$sqr8x_sub
+
+.p2align	5
+L$sqr8x_sub:
+	movq	0(%rbx),%r12
+	movq	8(%rbx),%r13
+	movq	16(%rbx),%r14
+	movq	24(%rbx),%r15
+	leaq	32(%rbx),%rbx
+	sbbq	0(%rbp),%r12
+	sbbq	8(%rbp),%r13
+	sbbq	16(%rbp),%r14
+	sbbq	24(%rbp),%r15
+	leaq	32(%rbp),%rbp
+	movq	%r12,0(%rdi)
+	movq	%r13,8(%rdi)
+	movq	%r14,16(%rdi)
+	movq	%r15,24(%rdi)
+	leaq	32(%rdi),%rdi
+	incq	%rcx
+	jnz	L$sqr8x_sub
+
+	sbbq	$0,%rax
+	leaq	(%rbx,%r9,1),%rbx
+	leaq	(%rdi,%r9,1),%rdi
+
+.byte	102,72,15,110,200
 	pxor	%xmm0,%xmm0
-	leaq	48(%rsp),%rax
-	leaq	64(%rsp,%r9,2),%rdx
-	shrq	$3+2,%r9
+	pshufd	$0,%xmm1,%xmm1
 	movq	40(%rsp),%rsi
-	jmp	L$sqr8x_zero
+	jmp	L$sqr8x_cond_copy
 
 .p2align	5
-L$sqr8x_zero:
-	movdqa	%xmm0,0(%rax)
-	movdqa	%xmm0,16(%rax)
-	movdqa	%xmm0,32(%rax)
-	movdqa	%xmm0,48(%rax)
-	leaq	64(%rax),%rax
-	movdqa	%xmm0,0(%rdx)
-	movdqa	%xmm0,16(%rdx)
-	movdqa	%xmm0,32(%rdx)
-	movdqa	%xmm0,48(%rdx)
-	leaq	64(%rdx),%rdx
-	decq	%r9
-	jnz	L$sqr8x_zero
+L$sqr8x_cond_copy:
+	movdqa	0(%rbx),%xmm2
+	movdqa	16(%rbx),%xmm3
+	leaq	32(%rbx),%rbx
+	movdqu	0(%rdi),%xmm4
+	movdqu	16(%rdi),%xmm5
+	leaq	32(%rdi),%rdi
+	movdqa	%xmm0,-32(%rbx)
+	movdqa	%xmm0,-16(%rbx)
+	movdqa	%xmm0,-32(%rbx,%rdx,1)
+	movdqa	%xmm0,-16(%rbx,%rdx,1)
+	pcmpeqd	%xmm1,%xmm0
+	pand	%xmm1,%xmm2
+	pand	%xmm1,%xmm3
+	pand	%xmm0,%xmm4
+	pand	%xmm0,%xmm5
+	pxor	%xmm0,%xmm0
+	por	%xmm2,%xmm4
+	por	%xmm3,%xmm5
+	movdqu	%xmm4,-32(%rdi)
+	movdqu	%xmm5,-16(%rdi)
+	addq	$32,%r9
+	jnz	L$sqr8x_cond_copy
 
 	movq	$1,%rax
 	movq	-48(%rsi),%r15

deps/openssl/asm_obsolete/x64-macosx-gas/camellia/cmll-x86_64.s

@@ -1624,7 +1624,7 @@ L$cbc_prologue:
 	leaq	-64-63(%rcx),%r10
 	subq	%rsp,%r10
 	negq	%r10
-	andq	$960,%r10
+	andq	$0x3C0,%r10
 	subq	%r10,%rsp
 
 

deps/openssl/asm_obsolete/x64-macosx-gas/ec/ecp_nistz256-x86_64.s

@@ -1121,6 +1121,7 @@ _ecp_nistz256_point_double:
 	pushq	%r15
 	subq	$160+8,%rsp
 
+L$point_double_shortcutq:
 	movdqu	0(%rsi),%xmm0
 	movq	%rsi,%rbx
 	movdqu	16(%rsi),%xmm1
@@ -1341,7 +1342,7 @@ _ecp_nistz256_point_add:
 	por	%xmm1,%xmm3
 
 	movdqu	0(%rsi),%xmm0
-	pshufd	$177,%xmm3,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm5
 	movdqu	16(%rsi),%xmm1
 	movdqu	32(%rsi),%xmm2
 	por	%xmm3,%xmm5
@@ -1351,7 +1352,7 @@ _ecp_nistz256_point_add:
 	movq	64+16(%rsi),%r15
 	movq	64+24(%rsi),%r8
 	movdqa	%xmm0,480(%rsp)
-	pshufd	$30,%xmm5,%xmm4
+	pshufd	$0x1e,%xmm5,%xmm4
 	movdqa	%xmm1,480+16(%rsp)
 	por	%xmm0,%xmm1
 .byte	102,72,15,110,199
@@ -1371,10 +1372,10 @@ _ecp_nistz256_point_add:
 	call	__ecp_nistz256_sqr_montq
 
 	pcmpeqd	%xmm4,%xmm5
-	pshufd	$177,%xmm3,%xmm4
+	pshufd	$0xb1,%xmm3,%xmm4
 	por	%xmm3,%xmm4
 	pshufd	$0,%xmm5,%xmm5
-	pshufd	$30,%xmm4,%xmm3
+	pshufd	$0x1e,%xmm4,%xmm3
 	por	%xmm3,%xmm4
 	pxor	%xmm3,%xmm3
 	pcmpeqd	%xmm3,%xmm4
@@ -1383,6 +1384,7 @@ _ecp_nistz256_point_add:
 	movq	64+8(%rbx),%r14
 	movq	64+16(%rbx),%r15
 	movq	64+24(%rbx),%r8
+.byte	102,72,15,110,203
 
 	leaq	64-0(%rbx),%rsi
 	leaq	32(%rsp),%rdi
@@ -1474,7 +1476,7 @@ _ecp_nistz256_point_add:
 	testq	%r8,%r8
 	jnz	L$add_proceedq
 	testq	%r9,%r9
-	jz	L$add_proceedq
+	jz	L$add_doubleq
 
 .byte	102,72,15,126,199
 	pxor	%xmm0,%xmm0
@@ -1486,6 +1488,13 @@ _ecp_nistz256_point_add:
 	movdqu	%xmm0,80(%rdi)
 	jmp	L$add_doneq
 
+.p2align	5
+L$add_doubleq:
+.byte	102,72,15,126,206
+.byte	102,72,15,126,199
+	addq	$416,%rsp
+	jmp	L$point_double_shortcutq
+
 .p2align	5
 L$add_proceedq:
 	movq	0+64(%rsp),%rax
@@ -1733,13 +1742,13 @@ _ecp_nistz256_point_add_affine:
 	por	%xmm1,%xmm3
 
 	movdqu	0(%rbx),%xmm0
-	pshufd	$177,%xmm3,%xmm5
+	pshufd	$0xb1,%xmm3,%xmm5
 	movdqu	16(%rbx),%xmm1
 	movdqu	32(%rbx),%xmm2
 	por	%xmm3,%xmm5
 	movdqu	48(%rbx),%xmm3
 	movdqa	%xmm0,416(%rsp)
-	pshufd	$30,%xmm5,%xmm4
+	pshufd	$0x1e,%xmm5,%xmm4
 	movdqa	%xmm1,416+16(%rsp)
 	por	%xmm0,%xmm1
 .byte	102,72,15,110,199
@@ -1755,13 +1764,13 @@ _ecp_nistz256_point_add_affine:
 	call	__ecp_nistz256_sqr_montq
 
 	pcmpeqd	%xmm4,%xmm5
-	pshufd	$177,%xmm3,%xmm4
+	pshufd	$0xb1,%xmm3,%xmm4
 	movq	0(%rbx),%rax
 
 	movq	%r12,%r9
 	por	%xmm3,%xmm4
 	pshufd	$0,%xmm5,%xmm5
-	pshufd	$30,%xmm4,%xmm3
+	pshufd	$0x1e,%xmm4,%xmm3
 	movq	%r13,%r10
 	por	%xmm3,%xmm4
 	pxor	%xmm3,%xmm3

deps/openssl/asm_obsolete/x64-macosx-gas/modes/ghash-x86_64.s

@@ -20,14 +20,14 @@ L$gmult_prologue:
 	movq	$14,%rcx
 	movq	8(%rsi,%rax,1),%r8
 	movq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	movq	%r8,%rdx
 	jmp	L$oop1
 
 .p2align	4
 L$oop1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	movb	(%rdi,%rcx,1),%al
 	shrq	$4,%r9
@@ -43,13 +43,13 @@ L$oop1:
 	js	L$break1
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
@@ -58,19 +58,19 @@ L$oop1:
 .p2align	4
 L$break1:
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rax,1),%r8
 	shlq	$60,%r10
 	xorq	(%rsi,%rax,1),%r9
-	andb	$240,%bl
+	andb	$0xf0,%bl
 	xorq	(%r11,%rdx,8),%r9
 	movq	%r8,%rdx
 	xorq	%r10,%r8
 
 	shrq	$4,%r8
-	andq	$15,%rdx
+	andq	$0xf,%rdx
 	movq	%r9,%r10
 	shrq	$4,%r9
 	xorq	8(%rsi,%rbx,1),%r8
@@ -661,10 +661,10 @@ L$ghash_epilogue:
 _gcm_init_clmul:
 L$_init_clmul:
 	movdqu	(%rsi),%xmm2
-	pshufd	$78,%xmm2,%xmm2
+	pshufd	$0b01001110,%xmm2,%xmm2
 
 
-	pshufd	$255,%xmm2,%xmm4
+	pshufd	$0b11111111,%xmm2,%xmm4
 	movdqa	%xmm2,%xmm3
 	psllq	$1,%xmm2
 	pxor	%xmm5,%xmm5
@@ -678,11 +678,11 @@ L$_init_clmul:
 	pxor	%xmm5,%xmm2
 
 
-	pshufd	$78,%xmm2,%xmm6
+	pshufd	$0b01001110,%xmm2,%xmm6
 	movdqa	%xmm2,%xmm0
 	pxor	%xmm2,%xmm6
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -718,8 +718,8 @@ L$_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm2,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm2,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm2,%xmm3
 	movdqu	%xmm2,0(%rdi)
 	pxor	%xmm0,%xmm4
@@ -727,7 +727,7 @@ L$_init_clmul:
 .byte	102,15,58,15,227,8
 	movdqu	%xmm4,32(%rdi)
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -765,7 +765,7 @@ L$_init_clmul:
 	pxor	%xmm1,%xmm0
 	movdqa	%xmm0,%xmm5
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -801,8 +801,8 @@ L$_init_clmul:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	pshufd	$78,%xmm5,%xmm3
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm5,%xmm3
 	movdqu	%xmm5,48(%rdi)
 	pxor	%xmm0,%xmm4
@@ -822,7 +822,7 @@ L$_gmult_clmul:
 	movdqu	32(%rsi),%xmm4
 .byte	102,15,56,0,197
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17
@@ -874,20 +874,20 @@ L$_ghash_clmul:
 	movdqu	32(%rsi),%xmm7
 .byte	102,65,15,56,0,194
 
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	L$odd_tail
 
 	movdqu	16(%rsi),%xmm6
 	movl	_OPENSSL_ia32cap_P+4(%rip),%eax
-	cmpq	$48,%rcx
+	cmpq	$0x30,%rcx
 	jb	L$skip4x
 
 	andl	$71303168,%eax
 	cmpl	$4194304,%eax
 	je	L$skip4x
 
-	subq	$48,%rcx
-	movq	$11547335547999543296,%rax
+	subq	$0x30,%rcx
+	movq	$0xA040608020C0E000,%rax
 	movdqu	48(%rsi),%xmm14
 	movdqu	64(%rsi),%xmm15
 
@@ -899,14 +899,14 @@ L$_ghash_clmul:
 .byte	102,65,15,56,0,218
 .byte	102,69,15,56,0,218
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
 .byte	102,15,58,68,231,0
 
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm11,%xmm12
 .byte	102,68,15,58,68,222,0
 .byte	102,68,15,58,68,238,17
@@ -921,12 +921,12 @@ L$_ghash_clmul:
 .byte	102,69,15,56,0,218
 .byte	102,69,15,56,0,194
 	movdqa	%xmm11,%xmm13
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm8,%xmm0
 	pxor	%xmm11,%xmm12
 .byte	102,69,15,58,68,222,0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 .byte	102,69,15,58,68,238,17
 .byte	102,68,15,58,68,231,0
@@ -934,7 +934,7 @@ L$_ghash_clmul:
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jc	L$tail4x
 
 	jmp	L$mod4_loop
@@ -949,14 +949,14 @@ L$mod4_loop:
 	movdqu	32(%rdx),%xmm3
 	movdqa	%xmm11,%xmm13
 .byte	102,68,15,58,68,199,16
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	xorps	%xmm5,%xmm1
 	pxor	%xmm11,%xmm12
 .byte	102,65,15,56,0,218
 	movups	32(%rsi),%xmm7
 	xorps	%xmm4,%xmm8
 .byte	102,68,15,58,68,218,0
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 
 	pxor	%xmm0,%xmm8
 	movdqa	%xmm3,%xmm5
@@ -1000,7 +1000,7 @@ L$mod4_loop:
 
 	movdqa	%xmm11,%xmm13
 	pxor	%xmm12,%xmm4
-	pshufd	$78,%xmm11,%xmm12
+	pshufd	$0b01001110,%xmm11,%xmm12
 	pxor	%xmm9,%xmm0
 	pxor	%xmm8,%xmm1
 	pxor	%xmm11,%xmm12
@@ -1010,14 +1010,14 @@ L$mod4_loop:
 	movdqa	%xmm0,%xmm1
 .byte	102,69,15,58,68,238,17
 	xorps	%xmm11,%xmm3
-	pshufd	$78,%xmm0,%xmm8
+	pshufd	$0b01001110,%xmm0,%xmm8
 	pxor	%xmm0,%xmm8
 
 .byte	102,68,15,58,68,231,0
 	xorps	%xmm13,%xmm5
 
 	leaq	64(%rdx),%rdx
-	subq	$64,%rcx
+	subq	$0x40,%rcx
 	jnc	L$mod4_loop
 
 L$tail4x:
@@ -1061,10 +1061,10 @@ L$tail4x:
 	pxor	%xmm4,%xmm0
 	psrlq	$1,%xmm0
 	pxor	%xmm1,%xmm0
-	addq	$64,%rcx
+	addq	$0x40,%rcx
 	jz	L$done
 	movdqu	32(%rsi),%xmm7
-	subq	$16,%rcx
+	subq	$0x10,%rcx
 	jz	L$odd_tail
 L$skip4x:
 
@@ -1079,7 +1079,7 @@ L$skip4x:
 	pxor	%xmm8,%xmm0
 
 	movdqa	%xmm3,%xmm5
-	pshufd	$78,%xmm3,%xmm4
+	pshufd	$0b01001110,%xmm3,%xmm4
 	pxor	%xmm3,%xmm4
 .byte	102,15,58,68,218,0
 .byte	102,15,58,68,234,17
@@ -1087,7 +1087,7 @@ L$skip4x:
 
 	leaq	32(%rdx),%rdx
 	nop
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	jbe	L$even_tail
 	nop
 	jmp	L$mod_loop
@@ -1096,7 +1096,7 @@ L$skip4x:
 L$mod_loop:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1134,7 +1134,7 @@ L$mod_loop:
 	pslldq	$8,%xmm0
 	psrldq	$8,%xmm8
 	pxor	%xmm9,%xmm0
-	pshufd	$78,%xmm5,%xmm4
+	pshufd	$0b01001110,%xmm5,%xmm4
 	pxor	%xmm8,%xmm1
 	pxor	%xmm5,%xmm4
 
@@ -1150,13 +1150,13 @@ L$mod_loop:
 .byte	102,15,58,68,231,0
 	pxor	%xmm1,%xmm0
 
-	subq	$32,%rcx
+	subq	$0x20,%rcx
 	ja	L$mod_loop
 
 L$even_tail:
 	movdqa	%xmm0,%xmm1
 	movdqa	%xmm4,%xmm8
-	pshufd	$78,%xmm0,%xmm4
+	pshufd	$0b01001110,%xmm0,%xmm4
 	pxor	%xmm0,%xmm4
 
 .byte	102,15,58,68,198,0
@@ -1204,7 +1204,7 @@ L$odd_tail:
 .byte	102,69,15,56,0,194
 	pxor	%xmm8,%xmm0
 	movdqa	%xmm0,%xmm1
-	pshufd	$78,%xmm0,%xmm3
+	pshufd	$0b01001110,%xmm0,%xmm3
 	pxor	%xmm0,%xmm3
 .byte	102,15,58,68,194,0
 .byte	102,15,58,68,202,17

deps/openssl/asm_obsolete/x64-macosx-gas/sha/sha1-mb-x86_64.s

@@ -2599,10 +2599,10 @@ L$oop_grande_shaext:
 	punpcklqdq	%xmm5,%xmm0
 	punpckhqdq	%xmm5,%xmm8
 
-	pshufd	$63,%xmm7,%xmm1
-	pshufd	$127,%xmm7,%xmm9
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm8,%xmm8
+	pshufd	$0b00111111,%xmm7,%xmm1
+	pshufd	$0b01111111,%xmm7,%xmm9
+	pshufd	$0b00011011,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm8,%xmm8
 	jmp	L$oop_shaext
 
 .p2align	5
@@ -2857,8 +2857,8 @@ L$oop_shaext:
 .byte	69,15,58,204,193,3
 .byte	69,15,56,200,214
 
-	pshufd	$0,%xmm6,%xmm11
-	pshufd	$85,%xmm6,%xmm12
+	pshufd	$0x00,%xmm6,%xmm11
+	pshufd	$0x55,%xmm6,%xmm12
 	movdqa	%xmm6,%xmm7
 	pcmpgtd	%xmm4,%xmm11
 	pcmpgtd	%xmm4,%xmm12
@@ -2888,8 +2888,8 @@ L$oop_shaext:
 
 	movl	280(%rsp),%edx
 
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm8,%xmm8
+	pshufd	$0b00011011,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm8,%xmm8
 
 	movdqa	%xmm0,%xmm6
 	punpckldq	%xmm8,%xmm0

deps/openssl/asm_obsolete/x64-macosx-gas/sha/sha1-x86_64.s

@@ -1240,9 +1240,9 @@ _shaext_shortcut:
 	movdqa	K_XX_XX+160(%rip),%xmm3
 
 	movdqu	(%rsi),%xmm4
-	pshufd	$27,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm0,%xmm0
 	movdqu	16(%rsi),%xmm5
-	pshufd	$27,%xmm1,%xmm1
+	pshufd	$0b00011011,%xmm1,%xmm1
 	movdqu	32(%rsi),%xmm6
 .byte	102,15,56,0,227
 	movdqu	48(%rsi),%xmm7
@@ -1392,8 +1392,8 @@ L$oop_shaext:
 
 	jnz	L$oop_shaext
 
-	pshufd	$27,%xmm0,%xmm0
-	pshufd	$27,%xmm1,%xmm1
+	pshufd	$0b00011011,%xmm0,%xmm0
+	pshufd	$0b00011011,%xmm1,%xmm1
 	movdqu	%xmm0,(%rdi)
 	movd	%xmm1,16(%rdi)
 	.byte	0xf3,0xc3

deps/openssl/asm_obsolete/x64-macosx-gas/sha/sha256-mb-x86_64.s

@@ -2677,10 +2677,10 @@ L$oop_grande_shaext:
 	punpckhqdq	%xmm8,%xmm14
 	punpckhqdq	%xmm10,%xmm15
 
-	pshufd	$27,%xmm12,%xmm12
-	pshufd	$27,%xmm13,%xmm13
-	pshufd	$27,%xmm14,%xmm14
-	pshufd	$27,%xmm15,%xmm15
+	pshufd	$0b00011011,%xmm12,%xmm12
+	pshufd	$0b00011011,%xmm13,%xmm13
+	pshufd	$0b00011011,%xmm14,%xmm14
+	pshufd	$0b00011011,%xmm15,%xmm15
 	jmp	L$oop_shaext
 
 .p2align	5
@@ -2712,11 +2712,11 @@ L$oop_shaext:
 	movdqa	%xmm2,%xmm0
 	movdqa	%xmm15,112(%rsp)
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	pxor	%xmm12,%xmm4
 	movdqa	%xmm12,64(%rsp)
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	pxor	%xmm14,%xmm8
 	movdqa	%xmm14,96(%rsp)
 	movdqa	16-128(%rbp),%xmm1
@@ -2734,11 +2734,11 @@ L$oop_shaext:
 .byte	102,68,15,56,0,211
 	prefetcht0	127(%r9)
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 .byte	102,68,15,56,0,219
 .byte	15,56,204,229
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	32-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -2751,14 +2751,14 @@ L$oop_shaext:
 	movdqa	%xmm2,%xmm0
 	movdqa	%xmm7,%xmm3
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 .byte	102,15,58,15,222,4
 	paddd	%xmm3,%xmm4
 	movdqa	%xmm11,%xmm3
 .byte	102,65,15,58,15,218,4
 .byte	15,56,204,238
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	48-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 .byte	69,15,56,203,247
@@ -2775,13 +2775,13 @@ L$oop_shaext:
 .byte	102,15,58,15,223,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,195
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm5
 	movdqa	%xmm8,%xmm3
 .byte	102,65,15,58,15,219,4
 .byte	15,56,204,247
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	64-128(%rbp),%xmm1
 	paddd	%xmm4,%xmm1
 .byte	69,15,56,203,247
@@ -2797,13 +2797,13 @@ L$oop_shaext:
 .byte	102,15,58,15,220,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,200
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm6
 	movdqa	%xmm9,%xmm3
 .byte	102,65,15,58,15,216,4
 .byte	15,56,204,252
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	80-128(%rbp),%xmm1
 	paddd	%xmm5,%xmm1
 .byte	69,15,56,203,247
@@ -2819,13 +2819,13 @@ L$oop_shaext:
 .byte	102,15,58,15,221,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,209
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm10,%xmm3
 .byte	102,65,15,58,15,217,4
 .byte	15,56,204,229
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	96-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -2841,13 +2841,13 @@ L$oop_shaext:
 .byte	102,15,58,15,222,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,218
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm4
 	movdqa	%xmm11,%xmm3
 .byte	102,65,15,58,15,218,4
 .byte	15,56,204,238
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	112-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 .byte	69,15,56,203,247
@@ -2863,13 +2863,13 @@ L$oop_shaext:
 .byte	102,15,58,15,223,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,195
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm5
 	movdqa	%xmm8,%xmm3
 .byte	102,65,15,58,15,219,4
 .byte	15,56,204,247
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	128-128(%rbp),%xmm1
 	paddd	%xmm4,%xmm1
 .byte	69,15,56,203,247
@@ -2885,13 +2885,13 @@ L$oop_shaext:
 .byte	102,15,58,15,220,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,200
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm6
 	movdqa	%xmm9,%xmm3
 .byte	102,65,15,58,15,216,4
 .byte	15,56,204,252
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	144-128(%rbp),%xmm1
 	paddd	%xmm5,%xmm1
 .byte	69,15,56,203,247
@@ -2907,13 +2907,13 @@ L$oop_shaext:
 .byte	102,15,58,15,221,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,209
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm10,%xmm3
 .byte	102,65,15,58,15,217,4
 .byte	15,56,204,229
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	160-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -2929,13 +2929,13 @@ L$oop_shaext:
 .byte	102,15,58,15,222,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,218
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm4
 	movdqa	%xmm11,%xmm3
 .byte	102,65,15,58,15,218,4
 .byte	15,56,204,238
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	176-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 .byte	69,15,56,203,247
@@ -2951,13 +2951,13 @@ L$oop_shaext:
 .byte	102,15,58,15,223,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,195
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm5
 	movdqa	%xmm8,%xmm3
 .byte	102,65,15,58,15,219,4
 .byte	15,56,204,247
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	192-128(%rbp),%xmm1
 	paddd	%xmm4,%xmm1
 .byte	69,15,56,203,247
@@ -2973,13 +2973,13 @@ L$oop_shaext:
 .byte	102,15,58,15,220,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,200
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm6
 	movdqa	%xmm9,%xmm3
 .byte	102,65,15,58,15,216,4
 .byte	15,56,204,252
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	208-128(%rbp),%xmm1
 	paddd	%xmm5,%xmm1
 .byte	69,15,56,203,247
@@ -2995,13 +2995,13 @@ L$oop_shaext:
 .byte	102,15,58,15,221,4
 .byte	69,15,56,203,254
 .byte	69,15,56,205,209
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	paddd	%xmm3,%xmm7
 	movdqa	%xmm10,%xmm3
 .byte	102,65,15,58,15,217,4
 	nop
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	224-128(%rbp),%xmm1
 	paddd	%xmm6,%xmm1
 .byte	69,15,56,203,247
@@ -3018,13 +3018,13 @@ L$oop_shaext:
 	pxor	%xmm6,%xmm6
 .byte	69,15,56,203,254
 .byte	69,15,56,205,218
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	movdqa	240-128(%rbp),%xmm1
 	paddd	%xmm7,%xmm1
 	movq	(%rbx),%xmm7
 	nop
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	movdqa	240-128(%rbp),%xmm2
 	paddd	%xmm11,%xmm2
 .byte	69,15,56,203,247
@@ -3034,17 +3034,17 @@ L$oop_shaext:
 	cmovgeq	%rsp,%r8
 	cmpl	4(%rbx),%ecx
 	cmovgeq	%rsp,%r9
-	pshufd	$0,%xmm7,%xmm9
+	pshufd	$0x00,%xmm7,%xmm9
 .byte	69,15,56,203,236
 	movdqa	%xmm2,%xmm0
-	pshufd	$85,%xmm7,%xmm10
+	pshufd	$0x55,%xmm7,%xmm10
 	movdqa	%xmm7,%xmm11
 .byte	69,15,56,203,254
-	pshufd	$14,%xmm1,%xmm0
+	pshufd	$0x0e,%xmm1,%xmm0
 	pcmpgtd	%xmm6,%xmm9
 	pcmpgtd	%xmm6,%xmm10
 .byte	69,15,56,203,229
-	pshufd	$14,%xmm2,%xmm0
+	pshufd	$0x0e,%xmm2,%xmm0
 	pcmpgtd	%xmm6,%xmm11
 	movdqa	K256_shaext-16(%rip),%xmm3
 .byte	69,15,56,203,247
@@ -3066,10 +3066,10 @@ L$oop_shaext:
 
 	movl	280(%rsp),%edx
 
-	pshufd	$27,%xmm12,%xmm12
-	pshufd	$27,%xmm13,%xmm13
-	pshufd	$27,%xmm14,%xmm14
-	pshufd	$27,%xmm15,%xmm15
+	pshufd	$0b00011011,%xmm12,%xmm12
+	pshufd	$0b00011011,%xmm13,%xmm13
+	pshufd	$0b00011011,%xmm14,%xmm14
+	pshufd	$0b00011011,%xmm15,%xmm15
 
 	movdqa	%xmm12,%xmm5
 	movdqa	%xmm13,%xmm6

deps/openssl/asm_obsolete/x64-macosx-gas/sha/sha256-x86_64.s

@@ -1754,9 +1754,9 @@ _shaext_shortcut:
 	movdqu	16(%rdi),%xmm2
 	movdqa	512-128(%rcx),%xmm7
 
-	pshufd	$27,%xmm1,%xmm0
-	pshufd	$177,%xmm1,%xmm1
-	pshufd	$27,%xmm2,%xmm2
+	pshufd	$0x1b,%xmm1,%xmm0
+	pshufd	$0xb1,%xmm1,%xmm1
+	pshufd	$0x1b,%xmm2,%xmm2
 	movdqa	%xmm7,%xmm8
 .byte	102,15,58,15,202,8
 	punpcklqdq	%xmm0,%xmm2
@@ -1775,7 +1775,7 @@ L$oop_shaext:
 .byte	102,15,56,0,231
 	movdqa	%xmm2,%xmm10
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	nop
 	movdqa	%xmm1,%xmm9
 .byte	15,56,203,202
@@ -1784,7 +1784,7 @@ L$oop_shaext:
 	paddd	%xmm4,%xmm0
 .byte	102,15,56,0,239
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	leaq	64(%rsi),%rsi
 .byte	15,56,204,220
 .byte	15,56,203,202
@@ -1793,7 +1793,7 @@ L$oop_shaext:
 	paddd	%xmm5,%xmm0
 .byte	102,15,56,0,247
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm6,%xmm7
 .byte	102,15,58,15,253,4
 	nop
@@ -1805,7 +1805,7 @@ L$oop_shaext:
 	paddd	%xmm6,%xmm0
 .byte	15,56,205,222
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm3,%xmm7
 .byte	102,15,58,15,254,4
 	nop
@@ -1816,7 +1816,7 @@ L$oop_shaext:
 	paddd	%xmm3,%xmm0
 .byte	15,56,205,227
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm4,%xmm7
 .byte	102,15,58,15,251,4
 	nop
@@ -1827,7 +1827,7 @@ L$oop_shaext:
 	paddd	%xmm4,%xmm0
 .byte	15,56,205,236
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm5,%xmm7
 .byte	102,15,58,15,252,4
 	nop
@@ -1838,7 +1838,7 @@ L$oop_shaext:
 	paddd	%xmm5,%xmm0
 .byte	15,56,205,245
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm6,%xmm7
 .byte	102,15,58,15,253,4
 	nop
@@ -1849,7 +1849,7 @@ L$oop_shaext:
 	paddd	%xmm6,%xmm0
 .byte	15,56,205,222
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm3,%xmm7
 .byte	102,15,58,15,254,4
 	nop
@@ -1860,7 +1860,7 @@ L$oop_shaext:
 	paddd	%xmm3,%xmm0
 .byte	15,56,205,227
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm4,%xmm7
 .byte	102,15,58,15,251,4
 	nop
@@ -1871,7 +1871,7 @@ L$oop_shaext:
 	paddd	%xmm4,%xmm0
 .byte	15,56,205,236
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm5,%xmm7
 .byte	102,15,58,15,252,4
 	nop
@@ -1882,7 +1882,7 @@ L$oop_shaext:
 	paddd	%xmm5,%xmm0
 .byte	15,56,205,245
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm6,%xmm7
 .byte	102,15,58,15,253,4
 	nop
@@ -1893,7 +1893,7 @@ L$oop_shaext:
 	paddd	%xmm6,%xmm0
 .byte	15,56,205,222
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm3,%xmm7
 .byte	102,15,58,15,254,4
 	nop
@@ -1904,7 +1904,7 @@ L$oop_shaext:
 	paddd	%xmm3,%xmm0
 .byte	15,56,205,227
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm4,%xmm7
 .byte	102,15,58,15,251,4
 	nop
@@ -1915,7 +1915,7 @@ L$oop_shaext:
 	paddd	%xmm4,%xmm0
 .byte	15,56,205,236
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	movdqa	%xmm5,%xmm7
 .byte	102,15,58,15,252,4
 .byte	15,56,203,202
@@ -1924,7 +1924,7 @@ L$oop_shaext:
 	movdqa	448-128(%rcx),%xmm0
 	paddd	%xmm5,%xmm0
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 .byte	15,56,205,245
 	movdqa	%xmm8,%xmm7
 .byte	15,56,203,202
@@ -1933,7 +1933,7 @@ L$oop_shaext:
 	paddd	%xmm6,%xmm0
 	nop
 .byte	15,56,203,209
-	pshufd	$14,%xmm0,%xmm0
+	pshufd	$0x0e,%xmm0,%xmm0
 	decq	%rdx
 	nop
 .byte	15,56,203,202
@@ -1942,9 +1942,9 @@ L$oop_shaext:
 	paddd	%xmm9,%xmm1
 	jnz	L$oop_shaext
 
-	pshufd	$177,%xmm2,%xmm2
-	pshufd	$27,%xmm1,%xmm7
-	pshufd	$177,%xmm1,%xmm1
+	pshufd	$0xb1,%xmm2,%xmm2
+	pshufd	$0x1b,%xmm1,%xmm7
+	pshufd	$0xb1,%xmm1,%xmm1
 	punpckhqdq	%xmm2,%xmm1
 .byte	102,15,58,15,215,8
 

deps/openssl/asm_obsolete/x64-macosx-gas/x86_64cpuid.s

@@ -45,43 +45,43 @@ _OPENSSL_ia32_cpuid:
 	movl	%eax,%r11d
 
 	xorl	%eax,%eax
-	cmpl	$1970169159,%ebx
+	cmpl	$0x756e6547,%ebx
 	setne	%al
 	movl	%eax,%r9d
-	cmpl	$1231384169,%edx
+	cmpl	$0x49656e69,%edx
 	setne	%al
 	orl	%eax,%r9d
-	cmpl	$1818588270,%ecx
+	cmpl	$0x6c65746e,%ecx
 	setne	%al
 	orl	%eax,%r9d
 	jz	L$intel
 
-	cmpl	$1752462657,%ebx
+	cmpl	$0x68747541,%ebx
 	setne	%al
 	movl	%eax,%r10d
-	cmpl	$1769238117,%edx
+	cmpl	$0x69746E65,%edx
 	setne	%al
 	orl	%eax,%r10d
-	cmpl	$1145913699,%ecx
+	cmpl	$0x444D4163,%ecx
 	setne	%al
 	orl	%eax,%r10d
 	jnz	L$intel
 
 
-	movl	$2147483648,%eax
+	movl	$0x80000000,%eax
 	cpuid
-	cmpl	$2147483649,%eax
+	cmpl	$0x80000001,%eax
 	jb	L$intel
 	movl	%eax,%r10d
-	movl	$2147483649,%eax
+	movl	$0x80000001,%eax
 	cpuid
 	orl	%ecx,%r9d
-	andl	$2049,%r9d
+	andl	$0x00000801,%r9d
 
-	cmpl	$2147483656,%r10d
+	cmpl	$0x80000008,%r10d
 	jb	L$intel
 
-	movl	$2147483656,%eax
+	movl	$0x80000008,%eax
 	cpuid
 	movzbq	%cl,%r10
 	incq	%r10
@@ -93,7 +93,7 @@ _OPENSSL_ia32_cpuid:
 	shrl	$16,%ebx
 	cmpb	%r10b,%bl
 	ja	L$generic
-	andl	$4026531839,%edx
+	andl	$0xefffffff,%edx
 	jmp	L$generic
 
 L$intel:
@@ -106,7 +106,7 @@ L$intel:
 	cpuid
 	movl	%eax,%r10d
 	shrl	$14,%r10d
-	andl	$4095,%r10d
+	andl	$0xfff,%r10d
 
 	cmpl	$7,%r11d
 	jb	L$nocacheinfo
@@ -119,29 +119,29 @@ L$intel:
 L$nocacheinfo:
 	movl	$1,%eax
 	cpuid
-	andl	$3220176895,%edx
+	andl	$0xbfefffff,%edx
 	cmpl	$0,%r9d
 	jne	L$notintel
-	orl	$1073741824,%edx
+	orl	$0x40000000,%edx
 	andb	$15,%ah
 	cmpb	$15,%ah
 	jne	L$notintel
-	orl	$1048576,%edx
+	orl	$0x00100000,%edx
 L$notintel:
 	btl	$28,%edx
 	jnc	L$generic
-	andl	$4026531839,%edx
+	andl	$0xefffffff,%edx
 	cmpl	$0,%r10d
 	je	L$generic
 
-	orl	$268435456,%edx
+	orl	$0x10000000,%edx
 	shrl	$16,%ebx
 	cmpb	$1,%bl
 	ja	L$generic
-	andl	$4026531839,%edx
+	andl	$0xefffffff,%edx
 L$generic:
-	andl	$2048,%r9d
-	andl	$4294965247,%ecx
+	andl	$0x00000800,%r9d
+	andl	$0xfffff7ff,%ecx
 	orl	%ecx,%r9d
 
 	movl	%edx,%r10d
@@ -153,9 +153,9 @@ L$generic:
 	cmpl	$6,%eax
 	je	L$done
 L$clear_avx:
-	movl	$4026525695,%eax
+	movl	$0xefffe7ff,%eax
 	andl	%eax,%r9d
-	andl	$4294967263,8(%rdi)
+	andl	$0xffffffdf,8(%rdi)
 L$done:
 	shlq	$32,%r9
 	movl	%r10d,%eax

deps/openssl/asm_obsolete/x64-win32-masm/bn/rsaz-x86_64.asm

@@ -502,48 +502,104 @@ $L$SEH_begin_rsaz_512_mul_gather4::
 	push	r14
 	push	r15
 
-	mov	r9d,r9d
-	sub	rsp,128+24
+	sub	rsp,328
+	movaps	XMMWORD PTR[160+rsp],xmm6
+	movaps	XMMWORD PTR[176+rsp],xmm7
+	movaps	XMMWORD PTR[192+rsp],xmm8
+	movaps	XMMWORD PTR[208+rsp],xmm9
+	movaps	XMMWORD PTR[224+rsp],xmm10
+	movaps	XMMWORD PTR[240+rsp],xmm11
+	movaps	XMMWORD PTR[256+rsp],xmm12
+	movaps	XMMWORD PTR[272+rsp],xmm13
+	movaps	XMMWORD PTR[288+rsp],xmm14
+	movaps	XMMWORD PTR[304+rsp],xmm15
 $L$mul_gather4_body::
-	mov	eax,DWORD PTR[64+r9*4+rdx]
-DB	102,72,15,110,199
-	mov	ebx,DWORD PTR[r9*4+rdx]
-DB	102,72,15,110,201
+	movd	xmm8,r9d
+	movdqa	xmm1,XMMWORD PTR[(($L$inc+16))]
+	movdqa	xmm0,XMMWORD PTR[$L$inc]
+
+	pshufd	xmm8,xmm8,0
+	movdqa	xmm7,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm8
+	movdqa	xmm3,xmm7
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm8
+	movdqa	xmm4,xmm7
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm8
+	movdqa	xmm5,xmm7
+	paddd	xmm4,xmm3
+	pcmpeqd	xmm3,xmm8
+	movdqa	xmm6,xmm7
+	paddd	xmm5,xmm4
+	pcmpeqd	xmm4,xmm8
+	paddd	xmm6,xmm5
+	pcmpeqd	xmm5,xmm8
+	paddd	xmm7,xmm6
+	pcmpeqd	xmm6,xmm8
+	pcmpeqd	xmm7,xmm8
+
+	movdqa	xmm8,XMMWORD PTR[rdx]
+	movdqa	xmm9,XMMWORD PTR[16+rdx]
+	movdqa	xmm10,XMMWORD PTR[32+rdx]
+	movdqa	xmm11,XMMWORD PTR[48+rdx]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rdx]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rdx]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rdx]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rdx]
+	lea	rbp,QWORD PTR[128+rdx]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
+DB	102,76,15,126,195
+
 	mov	QWORD PTR[128+rsp],r8
+	mov	QWORD PTR[((128+8))+rsp],rdi
+	mov	QWORD PTR[((128+16))+rsp],rcx
 
-	shl	rax,32
-	or	rbx,rax
 	mov	rax,QWORD PTR[rsi]
 	mov	rcx,QWORD PTR[8+rsi]
-	lea	rbp,QWORD PTR[128+r9*4+rdx]
 	mul	rbx
 	mov	QWORD PTR[rsp],rax
 	mov	rax,rcx
 	mov	r8,rdx
 
 	mul	rbx
-	movd	xmm4,DWORD PTR[rbp]
 	add	r8,rax
 	mov	rax,QWORD PTR[16+rsi]
 	mov	r9,rdx
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD PTR[64+rbp]
 	add	r9,rax
 	mov	rax,QWORD PTR[24+rsi]
 	mov	r10,rdx
 	adc	r10,0
 
 	mul	rbx
-	pslldq	xmm5,4
 	add	r10,rax
 	mov	rax,QWORD PTR[32+rsi]
 	mov	r11,rdx
 	adc	r11,0
 
 	mul	rbx
-	por	xmm4,xmm5
 	add	r11,rax
 	mov	rax,QWORD PTR[40+rsi]
 	mov	r12,rdx
@@ -556,14 +612,12 @@ DB	102,72,15,110,201
 	adc	r13,0
 
 	mul	rbx
-	lea	rbp,QWORD PTR[128+rbp]
 	add	r13,rax
 	mov	rax,QWORD PTR[56+rsi]
 	mov	r14,rdx
 	adc	r14,0
 
 	mul	rbx
-DB	102,72,15,126,227
 	add	r14,rax
 	mov	rax,QWORD PTR[rsi]
 	mov	r15,rdx
@@ -575,6 +629,35 @@ DB	102,72,15,126,227
 
 ALIGN	32
 $L$oop_mul_gather::
+	movdqa	xmm8,XMMWORD PTR[rbp]
+	movdqa	xmm9,XMMWORD PTR[16+rbp]
+	movdqa	xmm10,XMMWORD PTR[32+rbp]
+	movdqa	xmm11,XMMWORD PTR[48+rbp]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rbp]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rbp]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rbp]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rbp]
+	lea	rbp,QWORD PTR[128+rbp]
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
+DB	102,76,15,126,195
+
 	mul	rbx
 	add	r8,rax
 	mov	rax,QWORD PTR[8+rsi]
@@ -583,7 +666,6 @@ $L$oop_mul_gather::
 	adc	r8,0
 
 	mul	rbx
-	movd	xmm4,DWORD PTR[rbp]
 	add	r9,rax
 	mov	rax,QWORD PTR[16+rsi]
 	adc	rdx,0
@@ -592,7 +674,6 @@ $L$oop_mul_gather::
 	adc	r9,0
 
 	mul	rbx
-	movd	xmm5,DWORD PTR[64+rbp]
 	add	r10,rax
 	mov	rax,QWORD PTR[24+rsi]
 	adc	rdx,0
@@ -601,7 +682,6 @@ $L$oop_mul_gather::
 	adc	r10,0
 
 	mul	rbx
-	pslldq	xmm5,4
 	add	r11,rax
 	mov	rax,QWORD PTR[32+rsi]
 	adc	rdx,0
@@ -610,7 +690,6 @@ $L$oop_mul_gather::
 	adc	r11,0
 
 	mul	rbx
-	por	xmm4,xmm5
 	add	r12,rax
 	mov	rax,QWORD PTR[40+rsi]
 	adc	rdx,0
@@ -635,7 +714,6 @@ $L$oop_mul_gather::
 	adc	r14,0
 
 	mul	rbx
-DB	102,72,15,126,227
 	add	r15,rax
 	mov	rax,QWORD PTR[rsi]
 	adc	rdx,0
@@ -643,7 +721,6 @@ DB	102,72,15,126,227
 	mov	r15,rdx
 	adc	r15,0
 
-	lea	rbp,QWORD PTR[128+rbp]
 	lea	rdi,QWORD PTR[8+rdi]
 
 	dec	ecx
@@ -658,8 +735,8 @@ DB	102,72,15,126,227
 	mov	QWORD PTR[48+rdi],r14
 	mov	QWORD PTR[56+rdi],r15
 
-DB	102,72,15,126,199
-DB	102,72,15,126,205
+	mov	rdi,QWORD PTR[((128+8))+rsp]
+	mov	rbp,QWORD PTR[((128+16))+rsp]
 
 	mov	r8,QWORD PTR[rsp]
 	mov	r9,QWORD PTR[8+rsp]
@@ -684,6 +761,17 @@ DB	102,72,15,126,205
 	call	__rsaz_512_subtract
 
 	lea	rax,QWORD PTR[((128+24+48))+rsp]
+	movaps	xmm6,XMMWORD PTR[((160-200))+rax]
+	movaps	xmm7,XMMWORD PTR[((176-200))+rax]
+	movaps	xmm8,XMMWORD PTR[((192-200))+rax]
+	movaps	xmm9,XMMWORD PTR[((208-200))+rax]
+	movaps	xmm10,XMMWORD PTR[((224-200))+rax]
+	movaps	xmm11,XMMWORD PTR[((240-200))+rax]
+	movaps	xmm12,XMMWORD PTR[((256-200))+rax]
+	movaps	xmm13,XMMWORD PTR[((272-200))+rax]
+	movaps	xmm14,XMMWORD PTR[((288-200))+rax]
+	movaps	xmm15,XMMWORD PTR[((304-200))+rax]
+	lea	rax,QWORD PTR[176+rax]
 	mov	r15,QWORD PTR[((-48))+rax]
 	mov	r14,QWORD PTR[((-40))+rax]
 	mov	r13,QWORD PTR[((-32))+rax]
@@ -723,7 +811,7 @@ $L$SEH_begin_rsaz_512_mul_scatter4::
 	mov	r9d,r9d
 	sub	rsp,128+24
 $L$mul_scatter4_body::
-	lea	r8,QWORD PTR[r9*4+r8]
+	lea	r8,QWORD PTR[r9*8+r8]
 DB	102,72,15,110,199
 DB	102,72,15,110,202
 DB	102,73,15,110,208
@@ -759,30 +847,14 @@ DB	102,72,15,126,214
 
 	call	__rsaz_512_subtract
 
-	mov	DWORD PTR[rsi],r8d
-	shr	r8,32
-	mov	DWORD PTR[128+rsi],r9d
-	shr	r9,32
-	mov	DWORD PTR[256+rsi],r10d
-	shr	r10,32
-	mov	DWORD PTR[384+rsi],r11d
-	shr	r11,32
-	mov	DWORD PTR[512+rsi],r12d
-	shr	r12,32
-	mov	DWORD PTR[640+rsi],r13d
-	shr	r13,32
-	mov	DWORD PTR[768+rsi],r14d
-	shr	r14,32
-	mov	DWORD PTR[896+rsi],r15d
-	shr	r15,32
-	mov	DWORD PTR[64+rsi],r8d
-	mov	DWORD PTR[192+rsi],r9d
-	mov	DWORD PTR[320+rsi],r10d
-	mov	DWORD PTR[448+rsi],r11d
-	mov	DWORD PTR[576+rsi],r12d
-	mov	DWORD PTR[704+rsi],r13d
-	mov	DWORD PTR[832+rsi],r14d
-	mov	DWORD PTR[960+rsi],r15d
+	mov	QWORD PTR[rsi],r8
+	mov	QWORD PTR[128+rsi],r9
+	mov	QWORD PTR[256+rsi],r10
+	mov	QWORD PTR[384+rsi],r11
+	mov	QWORD PTR[512+rsi],r12
+	mov	QWORD PTR[640+rsi],r13
+	mov	QWORD PTR[768+rsi],r14
+	mov	QWORD PTR[896+rsi],r15
 
 	lea	rax,QWORD PTR[((128+24+48))+rsp]
 	mov	r15,QWORD PTR[((-48))+rax]
@@ -1151,16 +1223,14 @@ PUBLIC	rsaz_512_scatter4
 
 ALIGN	16
 rsaz_512_scatter4	PROC PUBLIC
-	lea	rcx,QWORD PTR[r8*4+rcx]
+	lea	rcx,QWORD PTR[r8*8+rcx]
 	mov	r9d,8
 	jmp	$L$oop_scatter
 ALIGN	16
 $L$oop_scatter::
 	mov	rax,QWORD PTR[rdx]
 	lea	rdx,QWORD PTR[8+rdx]
-	mov	DWORD PTR[rcx],eax
-	shr	rax,32
-	mov	DWORD PTR[64+rcx],eax
+	mov	QWORD PTR[rcx],rax
 	lea	rcx,QWORD PTR[128+rcx]
 	dec	r9d
 	jnz	$L$oop_scatter
@@ -1171,22 +1241,98 @@ PUBLIC	rsaz_512_gather4
 
 ALIGN	16
 rsaz_512_gather4	PROC PUBLIC
-	lea	rdx,QWORD PTR[r8*4+rdx]
+$L$SEH_begin_rsaz_512_gather4::
+DB	048h,081h,0ech,0a8h,000h,000h,000h
+DB	00fh,029h,034h,024h
+DB	00fh,029h,07ch,024h,010h
+DB	044h,00fh,029h,044h,024h,020h
+DB	044h,00fh,029h,04ch,024h,030h
+DB	044h,00fh,029h,054h,024h,040h
+DB	044h,00fh,029h,05ch,024h,050h
+DB	044h,00fh,029h,064h,024h,060h
+DB	044h,00fh,029h,06ch,024h,070h
+DB	044h,00fh,029h,0b4h,024h,080h,0,0,0
+DB	044h,00fh,029h,0bch,024h,090h,0,0,0
+	movd	xmm8,r8d
+	movdqa	xmm1,XMMWORD PTR[(($L$inc+16))]
+	movdqa	xmm0,XMMWORD PTR[$L$inc]
+
+	pshufd	xmm8,xmm8,0
+	movdqa	xmm7,xmm1
+	movdqa	xmm2,xmm1
+	paddd	xmm1,xmm0
+	pcmpeqd	xmm0,xmm8
+	movdqa	xmm3,xmm7
+	paddd	xmm2,xmm1
+	pcmpeqd	xmm1,xmm8
+	movdqa	xmm4,xmm7
+	paddd	xmm3,xmm2
+	pcmpeqd	xmm2,xmm8
+	movdqa	xmm5,xmm7
+	paddd	xmm4,xmm3
+	pcmpeqd	xmm3,xmm8
+	movdqa	xmm6,xmm7
+	paddd	xmm5,xmm4
+	pcmpeqd	xmm4,xmm8
+	paddd	xmm6,xmm5
+	pcmpeqd	xmm5,xmm8
+	paddd	xmm7,xmm6
+	pcmpeqd	xmm6,xmm8
+	pcmpeqd	xmm7,xmm8
 	mov	r9d,8
 	jmp	$L$oop_gather
 ALIGN	16
 $L$oop_gather::
-	mov	eax,DWORD PTR[rdx]
-	mov	r8d,DWORD PTR[64+rdx]
+	movdqa	xmm8,XMMWORD PTR[rdx]
+	movdqa	xmm9,XMMWORD PTR[16+rdx]
+	movdqa	xmm10,XMMWORD PTR[32+rdx]
+	movdqa	xmm11,XMMWORD PTR[48+rdx]
+	pand	xmm8,xmm0
+	movdqa	xmm12,XMMWORD PTR[64+rdx]
+	pand	xmm9,xmm1
+	movdqa	xmm13,XMMWORD PTR[80+rdx]
+	pand	xmm10,xmm2
+	movdqa	xmm14,XMMWORD PTR[96+rdx]
+	pand	xmm11,xmm3
+	movdqa	xmm15,XMMWORD PTR[112+rdx]
 	lea	rdx,QWORD PTR[128+rdx]
-	shl	r8,32
-	or	rax,r8
-	mov	QWORD PTR[rcx],rax
+	pand	xmm12,xmm4
+	pand	xmm13,xmm5
+	pand	xmm14,xmm6
+	pand	xmm15,xmm7
+	por	xmm8,xmm10
+	por	xmm9,xmm11
+	por	xmm8,xmm12
+	por	xmm9,xmm13
+	por	xmm8,xmm14
+	por	xmm9,xmm15
+
+	por	xmm8,xmm9
+	pshufd	xmm9,xmm8,04eh
+	por	xmm8,xmm9
+	movq	QWORD PTR[rcx],xmm8
 	lea	rcx,QWORD PTR[8+rcx]
 	dec	r9d
 	jnz	$L$oop_gather
+	movaps	xmm6,XMMWORD PTR[rsp]
+	movaps	xmm7,XMMWORD PTR[16+rsp]
+	movaps	xmm8,XMMWORD PTR[32+rsp]
+	movaps	xmm9,XMMWORD PTR[48+rsp]
+	movaps	xmm10,XMMWORD PTR[64+rsp]
+	movaps	xmm11,XMMWORD PTR[80+rsp]
+	movaps	xmm12,XMMWORD PTR[96+rsp]
+	movaps	xmm13,XMMWORD PTR[112+rsp]
+	movaps	xmm14,XMMWORD PTR[128+rsp]
+	movaps	xmm15,XMMWORD PTR[144+rsp]
+	add	rsp,0a8h
 	DB	0F3h,0C3h		;repret
+$L$SEH_end_rsaz_512_gather4::
 rsaz_512_gather4	ENDP
+
+ALIGN	64
+$L$inc::
+	DD	0,0,1,1
+	DD	2,2,2,2
 EXTERN	__imp_RtlVirtualUnwind:NEAR
 
 ALIGN	16
@@ -1222,6 +1368,18 @@ se_handler	PROC PRIVATE
 
 	lea	rax,QWORD PTR[((128+24+48))+rax]
 
+	lea	rbx,QWORD PTR[$L$mul_gather4_epilogue]
+	cmp	rbx,r10
+	jne	$L$se_not_in_mul_gather4
+
+	lea	rax,QWORD PTR[176+rax]
+
+	lea	rsi,QWORD PTR[((-48-168))+rax]
+	lea	rdi,QWORD PTR[512+r8]
+	mov	ecx,20
+	DD	0a548f3fch
+
+$L$se_not_in_mul_gather4::
 	mov	rbx,QWORD PTR[((-8))+rax]
 	mov	rbp,QWORD PTR[((-16))+rax]
 	mov	r12,QWORD PTR[((-24))+rax]
@@ -1298,6 +1456,10 @@ ALIGN	4
 	DD	imagerel $L$SEH_end_rsaz_512_mul_by_one
 	DD	imagerel $L$SEH_info_rsaz_512_mul_by_one
 
+	DD	imagerel $L$SEH_begin_rsaz_512_gather4
+	DD	imagerel $L$SEH_end_rsaz_512_gather4
+	DD	imagerel $L$SEH_info_rsaz_512_gather4
+
 .pdata	ENDS
 .xdata	SEGMENT READONLY ALIGN(8)
 ALIGN	8
@@ -1321,6 +1483,19 @@ $L$SEH_info_rsaz_512_mul_by_one::
 DB	9,0,0,0
 	DD	imagerel se_handler
 	DD	imagerel $L$mul_by_one_body,imagerel $L$mul_by_one_epilogue
+$L$SEH_info_rsaz_512_gather4::
+DB	001h,046h,016h,000h
+DB	046h,0f8h,009h,000h
+DB	03dh,0e8h,008h,000h
+DB	034h,0d8h,007h,000h
+DB	02eh,0c8h,006h,000h
+DB	028h,0b8h,005h,000h
+DB	022h,0a8h,004h,000h
+DB	01ch,098h,003h,000h
+DB	016h,088h,002h,000h
+DB	010h,078h,001h,000h
+DB	00bh,068h,000h,000h
+DB	007h,001h,015h,000h
 
 .xdata	ENDS
 END

deps/openssl/asm_obsolete/x64-win32-masm/bn/x86_64-mont.asm

@@ -676,20 +676,20 @@ $L$sqr8x_enter::
 
 
 
-	lea	r11,QWORD PTR[((-64))+r9*4+rsp]
+	lea	r11,QWORD PTR[((-64))+r9*2+rsp]
 	mov	r8,QWORD PTR[r8]
 	sub	r11,rsi
 	and	r11,4095
 	cmp	r10,r11
 	jb	$L$sqr8x_sp_alt
 	sub	rsp,r11
-	lea	rsp,QWORD PTR[((-64))+r9*4+rsp]
+	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
 	jmp	$L$sqr8x_sp_done
 
 ALIGN	32
 $L$sqr8x_sp_alt::
-	lea	r10,QWORD PTR[((4096-64))+r9*4]
-	lea	rsp,QWORD PTR[((-64))+r9*4+rsp]
+	lea	r10,QWORD PTR[((4096-64))+r9*2]
+	lea	rsp,QWORD PTR[((-64))+r9*2+rsp]
 	sub	r11,r10
 	mov	r10,0
 	cmovc	r11,r10
@@ -699,58 +699,80 @@ $L$sqr8x_sp_done::
 	mov	r10,r9
 	neg	r9
 
-	lea	r11,QWORD PTR[64+r9*2+rsp]
 	mov	QWORD PTR[32+rsp],r8
 	mov	QWORD PTR[40+rsp],rax
 $L$sqr8x_body::
 
-	mov	rbp,r9
-DB	102,73,15,110,211
-	shr	rbp,3+2
-	mov	eax,DWORD PTR[((OPENSSL_ia32cap_P+8))]
-	jmp	$L$sqr8x_copy_n
-
-ALIGN	32
-$L$sqr8x_copy_n::
-	movq	xmm0,QWORD PTR[rcx]
-	movq	xmm1,QWORD PTR[8+rcx]
-	movq	xmm3,QWORD PTR[16+rcx]
-	movq	xmm4,QWORD PTR[24+rcx]
-	lea	rcx,QWORD PTR[32+rcx]
-	movdqa	XMMWORD PTR[r11],xmm0
-	movdqa	XMMWORD PTR[16+r11],xmm1
-	movdqa	XMMWORD PTR[32+r11],xmm3
-	movdqa	XMMWORD PTR[48+r11],xmm4
-	lea	r11,QWORD PTR[64+r11]
-	dec	rbp
-	jnz	$L$sqr8x_copy_n
-
+DB	102,72,15,110,209
 	pxor	xmm0,xmm0
 DB	102,72,15,110,207
 DB	102,73,15,110,218
 	call	bn_sqr8x_internal
 
+
+
+
+	lea	rbx,QWORD PTR[r9*1+rdi]
+	mov	rcx,r9
+	mov	rdx,r9
+DB	102,72,15,126,207
+	sar	rcx,3+2
+	jmp	$L$sqr8x_sub
+
+ALIGN	32
+$L$sqr8x_sub::
+	mov	r12,QWORD PTR[rbx]
+	mov	r13,QWORD PTR[8+rbx]
+	mov	r14,QWORD PTR[16+rbx]
+	mov	r15,QWORD PTR[24+rbx]
+	lea	rbx,QWORD PTR[32+rbx]
+	sbb	r12,QWORD PTR[rbp]
+	sbb	r13,QWORD PTR[8+rbp]
+	sbb	r14,QWORD PTR[16+rbp]
+	sbb	r15,QWORD PTR[24+rbp]
+	lea	rbp,QWORD PTR[32+rbp]
+	mov	QWORD PTR[rdi],r12
+	mov	QWORD PTR[8+rdi],r13
+	mov	QWORD PTR[16+rdi],r14
+	mov	QWORD PTR[24+rdi],r15
+	lea	rdi,QWORD PTR[32+rdi]
+	inc	rcx
+	jnz	$L$sqr8x_sub
+
+	sbb	rax,0
+	lea	rbx,QWORD PTR[r9*1+rbx]
+	lea	rdi,QWORD PTR[r9*1+rdi]
+
+DB	102,72,15,110,200
 	pxor	xmm0,xmm0
-	lea	rax,QWORD PTR[48+rsp]
-	lea	rdx,QWORD PTR[64+r9*2+rsp]
-	shr	r9,3+2
+	pshufd	xmm1,xmm1,0
 	mov	rsi,QWORD PTR[40+rsp]
-	jmp	$L$sqr8x_zero
+	jmp	$L$sqr8x_cond_copy
 
 ALIGN	32
-$L$sqr8x_zero::
-	movdqa	XMMWORD PTR[rax],xmm0
-	movdqa	XMMWORD PTR[16+rax],xmm0
-	movdqa	XMMWORD PTR[32+rax],xmm0
-	movdqa	XMMWORD PTR[48+rax],xmm0
-	lea	rax,QWORD PTR[64+rax]
-	movdqa	XMMWORD PTR[rdx],xmm0
-	movdqa	XMMWORD PTR[16+rdx],xmm0
-	movdqa	XMMWORD PTR[32+rdx],xmm0
-	movdqa	XMMWORD PTR[48+rdx],xmm0
-	lea	rdx,QWORD PTR[64+rdx]
-	dec	r9
-	jnz	$L$sqr8x_zero
+$L$sqr8x_cond_copy::
+	movdqa	xmm2,XMMWORD PTR[rbx]
+	movdqa	xmm3,XMMWORD PTR[16+rbx]
+	lea	rbx,QWORD PTR[32+rbx]
+	movdqu	xmm4,XMMWORD PTR[rdi]
+	movdqu	xmm5,XMMWORD PTR[16+rdi]
+	lea	rdi,QWORD PTR[32+rdi]
+	movdqa	XMMWORD PTR[(-32)+rbx],xmm0
+	movdqa	XMMWORD PTR[(-16)+rbx],xmm0
+	movdqa	XMMWORD PTR[(-32)+rdx*1+rbx],xmm0
+	movdqa	XMMWORD PTR[(-16)+rdx*1+rbx],xmm0
+	pcmpeqd	xmm0,xmm1
+	pand	xmm2,xmm1
+	pand	xmm3,xmm1
+	pand	xmm4,xmm0
+	pand	xmm5,xmm0
+	pxor	xmm0,xmm0
+	por	xmm4,xmm2
+	por	xmm5,xmm3
+	movdqu	XMMWORD PTR[(-32)+rdi],xmm4
+	movdqu	XMMWORD PTR[(-16)+rdi],xmm5
+	add	r9,32
+	jnz	$L$sqr8x_cond_copy
 
 	mov	rax,1
 	mov	r15,QWORD PTR[((-48))+rsi]

deps/openssl/asm_obsolete/x64-win32-masm/ec/ecp_nistz256-x86_64.asm

@@ -1303,6 +1303,7 @@ $L$SEH_begin_ecp_nistz256_point_double::
 	push	r15
 	sub	rsp,32*5+8
 
+$L$point_double_shortcutq::
 	movdqu	xmm0,XMMWORD PTR[rsi]
 	mov	rbx,rsi
 	movdqu	xmm1,XMMWORD PTR[16+rsi]
@@ -1577,6 +1578,7 @@ DB	102,72,15,110,199
 	mov	r14,QWORD PTR[((64+8))+rbx]
 	mov	r15,QWORD PTR[((64+16))+rbx]
 	mov	r8,QWORD PTR[((64+24))+rbx]
+DB	102,72,15,110,203
 
 	lea	rsi,QWORD PTR[((64-0))+rbx]
 	lea	rdi,QWORD PTR[32+rsp]
@@ -1668,7 +1670,7 @@ DB	102,73,15,126,217
 	test	r8,r8
 	jnz	$L$add_proceedq
 	test	r9,r9
-	jz	$L$add_proceedq
+	jz	$L$add_doubleq
 
 DB	102,72,15,126,199
 	pxor	xmm0,xmm0
@@ -1680,6 +1682,13 @@ DB	102,72,15,126,199
 	movdqu	XMMWORD PTR[80+rdi],xmm0
 	jmp	$L$add_doneq
 
+ALIGN	32
+$L$add_doubleq::
+DB	102,72,15,126,206
+DB	102,72,15,126,199
+	add	rsp,416
+	jmp	$L$point_double_shortcutq
+
 ALIGN	32
 $L$add_proceedq::
 	mov	rax,QWORD PTR[((0+64))+rsp]

deps/openssl/openssl/CHANGES

@@ -2,6 +2,138 @@
  OpenSSL CHANGES
  _______________
 
+ Changes between 1.0.2f and 1.0.2g [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 1.0.2e and 1.0.2f [28 Jan 2016]
 
   *) DH small subgroups
@@ -105,7 +237,7 @@
      [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 1.0.2c and 1.0.2d [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 
@@ -781,11 +785,13 @@ my %disabled = ( # "what"         => "comment" [or special keyword "experimental
 		 "md2"            => "default",
 		 "rc5"            => "default",
 		 "rfc3779"	  => "default",
-		 "sctp"       => "default",
+		 "sctp"           => "default",
 		 "shared"         => "default",
 		 "ssl-trace"	  => "default",
+		 "ssl2"           => "default",
 		 "store"	  => "experimental",
 		 "unit-test"	  => "default",
+		 "weak-ssl-ciphers" => "default",
 		 "zlib"           => "default",
 		 "zlib-dynamic"   => "default"
 	       );

deps/openssl/openssl/Makefile.shared

@@ -272,7 +272,7 @@ link_o.cygwin:
 	SHLIB_SOVER=${LIBVERSION:+"-$(LIBVERSION)"}; \
 	ALLSYMSFLAGS='-Wl,--whole-archive'; \
 	NOALLSYMSFLAGS='-Wl,--no-whole-archive'; \
-	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base $$deffile -Wl,-s,-Bsymbolic"; \
+	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base $$deffile -Wl,-Bsymbolic"; \
 	$(LINK_SO_O)
 #for mingw target if def-file is in use dll-name should match library-name
 link_a.cygwin:
@@ -289,7 +289,7 @@ link_a.cygwin:
 		SHLIB_SOVER=32; \
 		extras="$(LIBNAME).def"; \
 		$(PERL) util/mkdef.pl 32 $$SHLIB > $$extras; \
-		base=; [ $(LIBNAME) = "crypto" ] && base=-Wl,--image-base,0x63000000; \
+		base=; [ $(LIBNAME) = "crypto" -a -n "$(FIPSCANLIB)" ] && base=-Wl,--image-base,0x63000000; \
 	fi; \
 	dll_name=$$SHLIB$$SHLIB_SOVER$$SHLIB_SUFFIX; \
 	$(PERL) util/mkrc.pl $$dll_name | \
@@ -297,7 +297,7 @@ link_a.cygwin:
 	extras="$$extras rc.o"; \
 	ALLSYMSFLAGS='-Wl,--whole-archive'; \
 	NOALLSYMSFLAGS='-Wl,--no-whole-archive'; \
-	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base -Wl,-s,-Bsymbolic -Wl,--out-implib,lib$(LIBNAME).dll.a $$extras"; \
+	SHAREDFLAGS="$(CFLAGS) $(SHARED_LDFLAGS) -shared $$base -Wl,-Bsymbolic -Wl,--out-implib,lib$(LIBNAME).dll.a $$extras"; \
 	[ -f apps/$$dll_name ] && rm apps/$$dll_name; \
 	[ -f test/$$dll_name ] && rm test/$$dll_name; \
 	$(LINK_SO_A) || exit 1; \

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 1.0.2f and OpenSSL 1.0.2g [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 1.0.2e and OpenSSL 1.0.2f [28 Jan 2016]
 
       o DH small subgroups (CVE-2016-0701)

deps/openssl/openssl/README

@@ -1,5 +1,5 @@
 
- OpenSSL 1.0.2f 28 Jan 2016
+ OpenSSL 1.0.2g 1 Mar 2016
 
  Copyright (c) 1998-2015 The OpenSSL Project
  Copyright (c) 1995-1998 Eric A. Young, Tim J. Hudson

deps/openssl/openssl/apps/apps.c

@@ -2442,7 +2442,11 @@ int bio_to_mem(unsigned char **out, int maxlen, BIO *in)
         else
             len = 1024;
         len = BIO_read(in, tbuf, len);
-        if (len <= 0)
+        if (len < 0) {
+            BIO_free(mem);
+            return -1;
+        }
+        if (len == 0)
             break;
         if (BIO_write(mem, tbuf, len) != len) {
             BIO_free(mem);
@@ -2459,7 +2463,7 @@ int bio_to_mem(unsigned char **out, int maxlen, BIO *in)
     return ret;
 }
 
-int pkey_ctrl_string(EVP_PKEY_CTX *ctx, char *value)
+int pkey_ctrl_string(EVP_PKEY_CTX *ctx, const char *value)
 {
     int rv;
     char *stmp, *vtmp = NULL;

deps/openssl/openssl/apps/apps.h

@@ -321,7 +321,7 @@ int args_verify(char ***pargs, int *pargc,
                 int *badarg, BIO *err, X509_VERIFY_PARAM **pm);
 void policies_print(BIO *out, X509_STORE_CTX *ctx);
 int bio_to_mem(unsigned char **out, int maxlen, BIO *in);
-int pkey_ctrl_string(EVP_PKEY_CTX *ctx, char *value);
+int pkey_ctrl_string(EVP_PKEY_CTX *ctx, const char *value);
 int init_gen_str(BIO *err, EVP_PKEY_CTX **pctx,
                  const char *algname, ENGINE *e, int do_param);
 int do_X509_sign(BIO *err, X509 *x, EVP_PKEY *pkey, const EVP_MD *md,

deps/openssl/openssl/apps/pkeyutl.c

@@ -73,7 +73,7 @@ static void usage(void);
 #define PROG pkeyutl_main
 
 static EVP_PKEY_CTX *init_ctx(int *pkeysize,
-                              char *keyfile, int keyform, int key_type,
+                              const char *keyfile, int keyform, int key_type,
                               char *passargin, int pkey_op, ENGINE *e,
                               int   impl);
 
@@ -99,10 +99,12 @@ int MAIN(int argc, char **argv)
     char *passargin = NULL;
     int keysize = -1;
     int engine_impl = 0;
-
     unsigned char *buf_in = NULL, *buf_out = NULL, *sig = NULL;
-    size_t buf_outlen;
+    size_t buf_outlen = 0;
     int buf_inlen = 0, siglen = -1;
+    const char *inkey = NULL;
+    const char *peerkey = NULL;
+    STACK_OF(OPENSSL_STRING) *pkeyopts = NULL;
 
     int ret = 1, rv = -1;
 
@@ -136,21 +138,13 @@ int MAIN(int argc, char **argv)
         } else if (!strcmp(*argv, "-inkey")) {
             if (--argc < 1)
                 badarg = 1;
-            else {
-                ctx = init_ctx(&keysize,
-                               *(++argv), keyform, key_type,
-                               passargin, pkey_op, e, engine_impl);
-                if (!ctx) {
-                    BIO_puts(bio_err, "Error initializing context\n");
-                    ERR_print_errors(bio_err);
-                    badarg = 1;
-                }
-            }
+            else
+                inkey = *++argv;
         } else if (!strcmp(*argv, "-peerkey")) {
             if (--argc < 1)
                 badarg = 1;
-            else if (!setup_peer(bio_err, ctx, peerform, *(++argv), e))
-                badarg = 1;
+            else
+                peerkey = *++argv;
         } else if (!strcmp(*argv, "-passin")) {
             if (--argc < 1)
                 badarg = 1;
@@ -191,23 +185,21 @@ int MAIN(int argc, char **argv)
             pkey_op = EVP_PKEY_OP_VERIFY;
         else if (!strcmp(*argv, "-verifyrecover"))
             pkey_op = EVP_PKEY_OP_VERIFYRECOVER;
-        else if (!strcmp(*argv, "-rev"))
-            rev = 1;
         else if (!strcmp(*argv, "-encrypt"))
             pkey_op = EVP_PKEY_OP_ENCRYPT;
         else if (!strcmp(*argv, "-decrypt"))
             pkey_op = EVP_PKEY_OP_DECRYPT;
         else if (!strcmp(*argv, "-derive"))
             pkey_op = EVP_PKEY_OP_DERIVE;
+        else if (!strcmp(*argv, "-rev"))
+            rev = 1;
         else if (strcmp(*argv, "-pkeyopt") == 0) {
             if (--argc < 1)
                 badarg = 1;
-            else if (!ctx) {
-                BIO_puts(bio_err, "-pkeyopt command before -inkey\n");
-                badarg = 1;
-            } else if (pkey_ctrl_string(ctx, *(++argv)) <= 0) {
-                BIO_puts(bio_err, "parameter setting error\n");
-                ERR_print_errors(bio_err);
+            else if ((pkeyopts == NULL &&
+                     (pkeyopts = sk_OPENSSL_STRING_new_null()) == NULL) ||
+                    sk_OPENSSL_STRING_push(pkeyopts, *++argv) == 0) {
+                BIO_puts(bio_err, "out of memory\n");
                 goto end;
             }
         } else
@@ -220,10 +212,37 @@ int MAIN(int argc, char **argv)
         argv++;
     }
 
-    if (!ctx) {
+    if (inkey == NULL ||
+        (peerkey != NULL && pkey_op != EVP_PKEY_OP_DERIVE)) {
         usage();
         goto end;
     }
+    ctx = init_ctx(&keysize, inkey, keyform, key_type,
+                   passargin, pkey_op, e, engine_impl);
+    if (!ctx) {
+        BIO_puts(bio_err, "Error initializing context\n");
+        ERR_print_errors(bio_err);
+        goto end;
+    }
+    if (peerkey != NULL && !setup_peer(bio_err, ctx, peerform, peerkey, e)) {
+        BIO_puts(bio_err, "Error setting up peer key\n");
+        ERR_print_errors(bio_err);
+        goto end;
+    }
+    if (pkeyopts != NULL) {
+        int num = sk_OPENSSL_STRING_num(pkeyopts);
+        int i;
+
+        for (i = 0; i < num; ++i) {
+            const char *opt = sk_OPENSSL_STRING_value(pkeyopts, i);
+
+            if (pkey_ctrl_string(ctx, opt) <= 0) {
+                BIO_puts(bio_err, "parameter setting error\n");
+                ERR_print_errors(bio_err);
+                goto end;
+            }
+        }
+    }
 
     if (sigfile && (pkey_op != EVP_PKEY_OP_VERIFY)) {
         BIO_puts(bio_err, "Signature file specified for non verify\n");
@@ -273,7 +292,7 @@ int MAIN(int argc, char **argv)
         }
         siglen = bio_to_mem(&sig, keysize * 10, sigbio);
         BIO_free(sigbio);
-        if (siglen <= 0) {
+        if (siglen < 0) {
             BIO_printf(bio_err, "Error reading signature data\n");
             goto end;
         }
@@ -282,7 +301,7 @@ int MAIN(int argc, char **argv)
     if (in) {
         /* Read the input data */
         buf_inlen = bio_to_mem(&buf_in, keysize * 10, in);
-        if (buf_inlen <= 0) {
+        if (buf_inlen < 0) {
             BIO_printf(bio_err, "Error reading input Data\n");
             exit(1);
         }
@@ -310,7 +329,7 @@ int MAIN(int argc, char **argv)
     } else {
         rv = do_keyop(ctx, pkey_op, NULL, (size_t *)&buf_outlen,
                       buf_in, (size_t)buf_inlen);
-        if (rv > 0) {
+        if (rv > 0 && buf_outlen != 0) {
             buf_out = OPENSSL_malloc(buf_outlen);
             if (!buf_out)
                 rv = -1;
@@ -340,12 +359,14 @@ int MAIN(int argc, char **argv)
         EVP_PKEY_CTX_free(ctx);
     BIO_free(in);
     BIO_free_all(out);
-    if (buf_in)
+    if (buf_in != NULL)
         OPENSSL_free(buf_in);
-    if (buf_out)
+    if (buf_out != NULL)
         OPENSSL_free(buf_out);
-    if (sig)
+    if (sig != NULL)
         OPENSSL_free(sig);
+    if (pkeyopts != NULL)
+        sk_OPENSSL_STRING_free(pkeyopts);
     return ret;
 }
 
@@ -380,7 +401,7 @@ static void usage()
 }
 
 static EVP_PKEY_CTX *init_ctx(int *pkeysize,
-                              char *keyfile, int keyform, int key_type,
+                              const char *keyfile, int keyform, int key_type,
                               char *passargin, int pkey_op, ENGINE *e,
                               int   engine_impl)
 {
@@ -484,14 +505,9 @@ static int setup_peer(BIO *err, EVP_PKEY_CTX *ctx, int peerform,
     EVP_PKEY *peer = NULL;
     ENGINE* engine = NULL;
     int ret;
-    if (!ctx) {
-        BIO_puts(err, "-peerkey command before -inkey\n");
-        return 0;
-    }
 
     if (peerform == FORMAT_ENGINE)
-      engine = e;
-
+        engine = e;
     peer = load_pubkey(bio_err, file, peerform, 0, NULL, engine, "Peer Key");
 
     if (!peer) {

deps/openssl/openssl/apps/req.c

@@ -101,8 +101,8 @@
 #define STRING_MASK     "string_mask"
 #define UTF8_IN         "utf8"
 
-#define DEFAULT_KEY_LENGTH      512
-#define MIN_KEY_LENGTH          384
+#define DEFAULT_KEY_LENGTH      2048
+#define MIN_KEY_LENGTH          512
 
 #undef PROG
 #define PROG    req_main

deps/openssl/openssl/apps/rsautl.c

@@ -250,7 +250,7 @@ int MAIN(int argc, char **argv)
 
     if (outfile) {
         if (!(out = BIO_new_file(outfile, "wb"))) {
-            BIO_printf(bio_err, "Error Reading Output File\n");
+            BIO_printf(bio_err, "Error Writing Output File\n");
             ERR_print_errors(bio_err);
             goto end;
         }
@@ -276,7 +276,7 @@ int MAIN(int argc, char **argv)
 
     /* Read the input data */
     rsa_inlen = BIO_read(in, rsa_in, keysize * 2);
-    if (rsa_inlen <= 0) {
+    if (rsa_inlen < 0) {
         BIO_printf(bio_err, "Error reading input Data\n");
         exit(1);
     }
@@ -311,7 +311,7 @@ int MAIN(int argc, char **argv)
 
     }
 
-    if (rsa_outlen <= 0) {
+    if (rsa_outlen < 0) {
         BIO_printf(bio_err, "RSA operation error\n");
         ERR_print_errors(bio_err);
         goto end;

deps/openssl/openssl/apps/s_client.c

@@ -398,8 +398,6 @@ static void sc_usage(void)
                " -no_tls1_2/-no_tls1_1/-no_tls1/-no_ssl3/-no_ssl2 - turn off that protocol\n");
     BIO_printf(bio_err,
                " -bugs         - Switch on all SSL implementation bug workarounds\n");
-    BIO_printf(bio_err,
-               " -serverpref   - Use server's cipher preferences (only SSLv2)\n");
     BIO_printf(bio_err,
                " -cipher       - preferred cipher to use, use the 'openssl ciphers'\n");
     BIO_printf(bio_err,

deps/openssl/openssl/apps/s_server.c

@@ -429,6 +429,8 @@ 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);
@@ -437,21 +439,25 @@ 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
@@ -2452,9 +2458,10 @@ static int sv_body(char *hostname, int s, int stype, 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);
@@ -2508,9 +2515,10 @@ static int sv_body(char *hostname, int s, int stype, 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);
@@ -2605,9 +2613,10 @@ 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);
@@ -2849,9 +2858,10 @@ static int www_body(char *hostname, int s, int stype, 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);
@@ -2891,9 +2901,10 @@ static int www_body(char *hostname, int s, int stype, 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);
@@ -3236,9 +3247,10 @@ static int rev_body(char *hostname, int s, int stype, 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 accept\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);
@@ -3264,9 +3276,10 @@ static int rev_body(char *hostname, int s, int stype, 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/config

@@ -852,7 +852,8 @@ case "$GUESSOS" in
   # *-dgux) OUT="dgux" ;;
   mips-sony-newsos4) OUT="newsos4-gcc" ;;
   *-*-cygwin_pre1.3) OUT="Cygwin-pre1.3" ;;
-  *-*-cygwin) OUT="Cygwin" ;;
+  i[3456]86-*-cygwin) OUT="Cygwin" ;;
+  *-*-cygwin) OUT="Cygwin-${MACHINE}" ;;
   t3e-cray-unicosmk) OUT="cray-t3e" ;;
   j90-cray-unicos) OUT="cray-j90" ;;
   nsr-tandem-nsk) OUT="tandem-c89" ;;

deps/openssl/openssl/crypto/asn1/tasn_dec.c

@@ -717,7 +717,7 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
     long plen;
     char cst, inf, free_cont = 0;
     const unsigned char *p;
-    BUF_MEM buf;
+    BUF_MEM buf = { 0, NULL, 0 };
     const unsigned char *cont = NULL;
     long len;
     if (!pval) {
@@ -793,7 +793,6 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
         } else {
             len = p - cont + plen;
             p += plen;
-            buf.data = NULL;
         }
     } else if (cst) {
         if (utype == V_ASN1_NULL || utype == V_ASN1_BOOLEAN
@@ -802,9 +801,9 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
             ASN1err(ASN1_F_ASN1_D2I_EX_PRIMITIVE, ASN1_R_TYPE_NOT_PRIMITIVE);
             return 0;
         }
-        buf.length = 0;
-        buf.max = 0;
-        buf.data = NULL;
+
+        /* Free any returned 'buf' content */
+        free_cont = 1;
         /*
          * Should really check the internal tags are correct but some things
          * may get this wrong. The relevant specs say that constructed string
@@ -812,18 +811,16 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
          * So instead just check for UNIVERSAL class and ignore the tag.
          */
         if (!asn1_collect(&buf, &p, plen, inf, -1, V_ASN1_UNIVERSAL, 0)) {
-            free_cont = 1;
             goto err;
         }
         len = buf.length;
         /* Append a final null to string */
         if (!BUF_MEM_grow_clean(&buf, len + 1)) {
             ASN1err(ASN1_F_ASN1_D2I_EX_PRIMITIVE, ERR_R_MALLOC_FAILURE);
-            return 0;
+            goto err;
         }
         buf.data[len] = 0;
         cont = (const unsigned char *)buf.data;
-        free_cont = 1;
     } else {
         cont = p;
         len = plen;
@@ -831,6 +828,7 @@ static int asn1_d2i_ex_primitive(ASN1_VALUE **pval,
     }
 
     /* We now have content length and type: translate into a structure */
+    /* asn1_ex_c2i may reuse allocated buffer, and so sets free_cont to 0 */
     if (!asn1_ex_c2i(pval, cont, len, utype, &free_cont, it))
         goto err;
 

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

@@ -479,7 +479,7 @@ 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)
 
@@ -689,7 +689,7 @@ long BIO_debug_callback(BIO *bio, int cmd, const char *argp, int argi,
                         long argl, long ret);
 
 BIO_METHOD *BIO_s_mem(void);
-BIO *BIO_new_mem_buf(void *buf, int len);
+BIO *BIO_new_mem_buf(const void *buf, int len);
 BIO_METHOD *BIO_s_socket(void);
 BIO_METHOD *BIO_s_connect(void);
 BIO_METHOD *BIO_s_accept(void);

deps/openssl/openssl/crypto/bio/bss_mem.c

@@ -91,7 +91,8 @@ BIO_METHOD *BIO_s_mem(void)
     return (&mem_method);
 }
 
-BIO *BIO_new_mem_buf(void *buf, int len)
+
+BIO *BIO_new_mem_buf(const void *buf, int len)
 {
     BIO *ret;
     BUF_MEM *b;
@@ -105,7 +106,8 @@ BIO *BIO_new_mem_buf(void *buf, int len)
     if (!(ret = BIO_new(BIO_s_mem())))
         return NULL;
     b = (BUF_MEM *)ret->ptr;
-    b->data = buf;
+    /* Cast away const and trust in the MEM_RDONLY flag. */
+    b->data = (void *)buf;
     b->length = sz;
     b->max = sz;
     ret->flags |= BIO_FLAGS_MEM_RDONLY;

deps/openssl/openssl/crypto/bn/Makefile

@@ -252,8 +252,8 @@ 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: rsaz_exp.h
+bn_exp.o: ../../include/openssl/symhacks.h ../constant_time_locl.h
+bn_exp.o: ../cryptlib.h bn_exp.c bn_lcl.h rsaz_exp.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