From 7d969e296f4a8c39a8bdc642a3234b0957531201 Mon Sep 17 00:00:00 2001
From: Anderson Toshiyuki Sasaki <ansasaki@redhat.com>
Date: Wed, 20 May 2020 10:51:37 +0200
Subject: [PATCH] accelerated: Enable Intel CET

Signed-off-by: Anderson Toshiyuki Sasaki <ansasaki@redhat.com>
---
 lib/accelerated/x86/coff/aes-ssse3-x86.s      |  13 +
 lib/accelerated/x86/coff/aes-ssse3-x86_64.s   |   5 +
 lib/accelerated/x86/coff/aesni-gcm-x86_64.s   |   8 +
 lib/accelerated/x86/coff/aesni-x86.s          |  22 ++
 lib/accelerated/x86/coff/aesni-x86_64.s       |  29 +-
 lib/accelerated/x86/coff/e_padlock-x86.s      | 276 +++++++++-------
 lib/accelerated/x86/coff/e_padlock-x86_64.s   | 218 ++++++++-----
 lib/accelerated/x86/coff/ghash-x86_64.s       |   6 +
 lib/accelerated/x86/coff/sha1-ssse3-x86.s     |   1 +
 lib/accelerated/x86/coff/sha1-ssse3-x86_64.s  |   2 +-
 lib/accelerated/x86/coff/sha256-ssse3-x86.s   |   1 +
 .../x86/coff/sha256-ssse3-x86_64.s            |  18 +-
 lib/accelerated/x86/coff/sha512-ssse3-x86.s   |   1 +
 .../x86/coff/sha512-ssse3-x86_64.s            |  20 +-
 lib/accelerated/x86/elf/aes-ssse3-x86.s       |  30 ++
 lib/accelerated/x86/elf/aes-ssse3-x86_64.s    |  26 ++
 lib/accelerated/x86/elf/aesni-gcm-x86_64.s    |  29 ++
 lib/accelerated/x86/elf/aesni-x86.s           |  39 +++
 lib/accelerated/x86/elf/aesni-x86_64.s        |  50 ++-
 lib/accelerated/x86/elf/e_padlock-x86.s       | 306 ++++++++++--------
 lib/accelerated/x86/elf/e_padlock-x86_64.s    | 242 +++++++++-----
 lib/accelerated/x86/elf/ghash-x86_64.s        |  27 ++
 lib/accelerated/x86/elf/sha1-ssse3-x86.s      |  18 ++
 lib/accelerated/x86/elf/sha1-ssse3-x86_64.s   |  23 +-
 lib/accelerated/x86/elf/sha256-ssse3-x86.s    |  18 ++
 lib/accelerated/x86/elf/sha256-ssse3-x86_64.s |  51 ++-
 lib/accelerated/x86/elf/sha512-ssse3-x86.s    |  18 ++
 lib/accelerated/x86/elf/sha512-ssse3-x86_64.s |  49 ++-
 lib/accelerated/x86/macosx/aes-ssse3-x86.s    |  13 +
 lib/accelerated/x86/macosx/aes-ssse3-x86_64.s |   5 +
 lib/accelerated/x86/macosx/aesni-gcm-x86_64.s |   8 +
 lib/accelerated/x86/macosx/aesni-x86.s        |  22 ++
 lib/accelerated/x86/macosx/aesni-x86_64.s     |  29 +-
 lib/accelerated/x86/macosx/e_padlock-x86.s    | 288 +++++++++--------
 lib/accelerated/x86/macosx/e_padlock-x86_64.s | 218 ++++++++-----
 lib/accelerated/x86/macosx/ghash-x86_64.s     |   6 +
 lib/accelerated/x86/macosx/sha1-ssse3-x86.s   |   1 +
 .../x86/macosx/sha1-ssse3-x86_64.s            |   2 +-
 lib/accelerated/x86/macosx/sha256-ssse3-x86.s |   1 +
 .../x86/macosx/sha256-ssse3-x86_64.s          |  30 +-
 lib/accelerated/x86/macosx/sha512-ssse3-x86.s |   1 +
 .../x86/macosx/sha512-ssse3-x86_64.s          |  28 +-
 42 files changed, 1541 insertions(+), 657 deletions(-)

diff --git a/lib/accelerated/x86/coff/aes-ssse3-x86.s b/lib/accelerated/x86/coff/aes-ssse3-x86.s
index c58ea2359..1dced3b2a 100644
--- a/lib/accelerated/x86/coff/aes-ssse3-x86.s
+++ b/lib/accelerated/x86/coff/aes-ssse3-x86.s
@@ -71,6 +71,7 @@
 .def	__vpaes_preheat;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_preheat:
+.byte	243,15,30,251
 	addl	(%esp),%ebp
 	movdqa	-48(%ebp),%xmm7
 	movdqa	-16(%ebp),%xmm6
@@ -78,6 +79,7 @@ __vpaes_preheat:
 .def	__vpaes_encrypt_core;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_encrypt_core:
+.byte	243,15,30,251
 	movl	$16,%ecx
 	movl	240(%edx),%eax
 	movdqa	%xmm6,%xmm1
@@ -154,6 +156,7 @@ __vpaes_encrypt_core:
 .def	__vpaes_decrypt_core;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_decrypt_core:
+.byte	243,15,30,251
 	leal	608(%ebp),%ebx
 	movl	240(%edx),%eax
 	movdqa	%xmm6,%xmm1
@@ -241,6 +244,7 @@ __vpaes_decrypt_core:
 .def	__vpaes_schedule_core;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_schedule_core:
+.byte	243,15,30,251
 	addl	(%esp),%ebp
 	movdqu	(%esi),%xmm0
 	movdqa	320(%ebp),%xmm2
@@ -334,6 +338,7 @@ __vpaes_schedule_core:
 .def	__vpaes_schedule_192_smear;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_schedule_192_smear:
+.byte	243,15,30,251
 	pshufd	$128,%xmm6,%xmm1
 	pshufd	$254,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
@@ -345,6 +350,7 @@ __vpaes_schedule_192_smear:
 .def	__vpaes_schedule_round;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_schedule_round:
+.byte	243,15,30,251
 	movdqa	8(%esp),%xmm2
 	pxor	%xmm1,%xmm1
 .byte	102,15,58,15,202,15
@@ -393,6 +399,7 @@ __vpaes_schedule_round:
 .def	__vpaes_schedule_transform;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_schedule_transform:
+.byte	243,15,30,251
 	movdqa	-16(%ebp),%xmm2
 	movdqa	%xmm2,%xmm1
 	pandn	%xmm0,%xmm1
@@ -407,6 +414,7 @@ __vpaes_schedule_transform:
 .def	__vpaes_schedule_mangle;	.scl	3;	.type	32;	.endef
 .align	16
 __vpaes_schedule_mangle:
+.byte	243,15,30,251
 	movdqa	%xmm0,%xmm4
 	movdqa	128(%ebp),%xmm5
 	testl	%edi,%edi
@@ -467,6 +475,7 @@ __vpaes_schedule_mangle:
 .align	16
 _vpaes_set_encrypt_key:
 .L_vpaes_set_encrypt_key_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -499,6 +508,7 @@ _vpaes_set_encrypt_key:
 .align	16
 _vpaes_set_decrypt_key:
 .L_vpaes_set_decrypt_key_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -536,6 +546,7 @@ _vpaes_set_decrypt_key:
 .align	16
 _vpaes_encrypt:
 .L_vpaes_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -564,6 +575,7 @@ _vpaes_encrypt:
 .align	16
 _vpaes_decrypt:
 .L_vpaes_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -592,6 +604,7 @@ _vpaes_decrypt:
 .align	16
 _vpaes_cbc_encrypt:
 .L_vpaes_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/coff/aes-ssse3-x86_64.s b/lib/accelerated/x86/coff/aes-ssse3-x86_64.s
index 150c9921d..f3fee5629 100644
--- a/lib/accelerated/x86/coff/aes-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/aes-ssse3-x86_64.s
@@ -643,6 +643,7 @@ vpaes_set_encrypt_key:
 	movq	%r8,%rdx
 
 
+.byte	243,15,30,250
 	leaq	-184(%rsp),%rsp
 	movaps	%xmm6,16(%rsp)
 	movaps	%xmm7,32(%rsp)
@@ -695,6 +696,7 @@ vpaes_set_decrypt_key:
 	movq	%r8,%rdx
 
 
+.byte	243,15,30,250
 	leaq	-184(%rsp),%rsp
 	movaps	%xmm6,16(%rsp)
 	movaps	%xmm7,32(%rsp)
@@ -752,6 +754,7 @@ vpaes_encrypt:
 	movq	%r8,%rdx
 
 
+.byte	243,15,30,250
 	leaq	-184(%rsp),%rsp
 	movaps	%xmm6,16(%rsp)
 	movaps	%xmm7,32(%rsp)
@@ -799,6 +802,7 @@ vpaes_decrypt:
 	movq	%r8,%rdx
 
 
+.byte	243,15,30,250
 	leaq	-184(%rsp),%rsp
 	movaps	%xmm6,16(%rsp)
 	movaps	%xmm7,32(%rsp)
@@ -848,6 +852,7 @@ vpaes_cbc_encrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	xchgq	%rcx,%rdx
 	subq	$16,%rcx
 	jc	.Lcbc_abort
diff --git a/lib/accelerated/x86/coff/aesni-gcm-x86_64.s b/lib/accelerated/x86/coff/aesni-gcm-x86_64.s
index 7988004cb..5784e4bcf 100644
--- a/lib/accelerated/x86/coff/aesni-gcm-x86_64.s
+++ b/lib/accelerated/x86/coff/aesni-gcm-x86_64.s
@@ -42,6 +42,8 @@
 .def	_aesni_ctr32_ghash_6x;	.scl 3;	.type 32;	.endef
 .p2align	5
 _aesni_ctr32_ghash_6x:
+
+.byte	243,15,30,250
 	vmovdqu	32(%r11),%xmm2
 	subq	$6,%rdx
 	vpxor	%xmm4,%xmm4,%xmm4
@@ -350,6 +352,7 @@ _aesni_ctr32_ghash_6x:
 
 	.byte	0xf3,0xc3
 
+
 .globl	aesni_gcm_decrypt
 .def	aesni_gcm_decrypt;	.scl 2;	.type 32;	.endef
 .p2align	5
@@ -366,6 +369,7 @@ aesni_gcm_decrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	xorq	%r10,%r10
 	cmpq	$0x60,%rdx
 	jb	.Lgcm_dec_abort
@@ -490,6 +494,8 @@ aesni_gcm_decrypt:
 .def	_aesni_ctr32_6x;	.scl 3;	.type 32;	.endef
 .p2align	5
 _aesni_ctr32_6x:
+
+.byte	243,15,30,250
 	vmovdqu	0-128(%rcx),%xmm4
 	vmovdqu	32(%r11),%xmm2
 	leaq	-1(%rbp),%r13
@@ -578,6 +584,7 @@ _aesni_ctr32_6x:
 	jmp	.Loop_ctr32
 
 
+
 .globl	aesni_gcm_encrypt
 .def	aesni_gcm_encrypt;	.scl 2;	.type 32;	.endef
 .p2align	5
@@ -594,6 +601,7 @@ aesni_gcm_encrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	xorq	%r10,%r10
 	cmpq	$288,%rdx
 	jb	.Lgcm_enc_abort
diff --git a/lib/accelerated/x86/coff/aesni-x86.s b/lib/accelerated/x86/coff/aesni-x86.s
index c6aa1a1e2..577dc4af2 100644
--- a/lib/accelerated/x86/coff/aesni-x86.s
+++ b/lib/accelerated/x86/coff/aesni-x86.s
@@ -43,6 +43,7 @@
 .align	16
 _aesni_encrypt:
 .L_aesni_encrypt_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	12(%esp),%edx
 	movups	(%eax),%xmm2
@@ -69,6 +70,7 @@ _aesni_encrypt:
 .align	16
 _aesni_decrypt:
 .L_aesni_decrypt_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	12(%esp),%edx
 	movups	(%eax),%xmm2
@@ -93,6 +95,7 @@ _aesni_decrypt:
 .def	__aesni_encrypt2;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_encrypt2:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -119,6 +122,7 @@ __aesni_encrypt2:
 .def	__aesni_decrypt2;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_decrypt2:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -145,6 +149,7 @@ __aesni_decrypt2:
 .def	__aesni_encrypt3;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_encrypt3:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -176,6 +181,7 @@ __aesni_encrypt3:
 .def	__aesni_decrypt3;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_decrypt3:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -207,6 +213,7 @@ __aesni_decrypt3:
 .def	__aesni_encrypt4;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_encrypt4:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	movups	16(%edx),%xmm1
 	shll	$4,%ecx
@@ -244,6 +251,7 @@ __aesni_encrypt4:
 .def	__aesni_decrypt4;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_decrypt4:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	movups	16(%edx),%xmm1
 	shll	$4,%ecx
@@ -281,6 +289,7 @@ __aesni_decrypt4:
 .def	__aesni_encrypt6;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_encrypt6:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -334,6 +343,7 @@ __aesni_encrypt6:
 .def	__aesni_decrypt6;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_decrypt6:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -389,6 +399,7 @@ __aesni_decrypt6:
 .align	16
 _aesni_ecb_encrypt:
 .L_aesni_ecb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -623,6 +634,7 @@ _aesni_ecb_encrypt:
 .align	16
 _aesni_ccm64_encrypt_blocks:
 .L_aesni_ccm64_encrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -710,6 +722,7 @@ _aesni_ccm64_encrypt_blocks:
 .align	16
 _aesni_ccm64_decrypt_blocks:
 .L_aesni_ccm64_decrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -832,6 +845,7 @@ _aesni_ccm64_decrypt_blocks:
 .align	16
 _aesni_ctr32_encrypt_blocks:
 .L_aesni_ctr32_encrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1069,6 +1083,7 @@ _aesni_ctr32_encrypt_blocks:
 .align	16
 _aesni_xts_encrypt:
 .L_aesni_xts_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1428,6 +1443,7 @@ _aesni_xts_encrypt:
 .align	16
 _aesni_xts_decrypt:
 .L_aesni_xts_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1817,6 +1833,7 @@ _aesni_xts_decrypt:
 .align	16
 _aesni_ocb_encrypt:
 .L_aesni_ocb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2211,6 +2228,7 @@ _aesni_ocb_encrypt:
 .align	16
 _aesni_ocb_decrypt:
 .L_aesni_ocb_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2605,6 +2623,7 @@ _aesni_ocb_decrypt:
 .align	16
 _aesni_cbc_encrypt:
 .L_aesni_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2863,6 +2882,7 @@ _aesni_cbc_encrypt:
 .def	__aesni_set_encrypt_key;	.scl	3;	.type	32;	.endef
 .align	16
 __aesni_set_encrypt_key:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	testl	%eax,%eax
@@ -3197,6 +3217,7 @@ __aesni_set_encrypt_key:
 .align	16
 _aesni_set_encrypt_key:
 .L_aesni_set_encrypt_key_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	8(%esp),%ecx
 	movl	12(%esp),%edx
@@ -3207,6 +3228,7 @@ _aesni_set_encrypt_key:
 .align	16
 _aesni_set_decrypt_key:
 .L_aesni_set_decrypt_key_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	8(%esp),%ecx
 	movl	12(%esp),%edx
diff --git a/lib/accelerated/x86/coff/aesni-x86_64.s b/lib/accelerated/x86/coff/aesni-x86_64.s
index 4e8de065f..ba2992903 100644
--- a/lib/accelerated/x86/coff/aesni-x86_64.s
+++ b/lib/accelerated/x86/coff/aesni-x86_64.s
@@ -44,6 +44,7 @@
 .p2align	4
 aesni_encrypt:
 
+.byte	243,15,30,250
 	movups	(%rcx),%xmm2
 	movl	240(%r8),%eax
 	movups	(%r8),%xmm0
@@ -70,6 +71,7 @@ aesni_encrypt:
 .p2align	4
 aesni_decrypt:
 
+.byte	243,15,30,250
 	movups	(%rcx),%xmm2
 	movl	240(%r8),%eax
 	movups	(%r8),%xmm0
@@ -567,6 +569,7 @@ aesni_ecb_encrypt:
 	movq	40(%rsp),%r8
 
 
+.byte	243,15,30,250
 	leaq	-88(%rsp),%rsp
 	movaps	%xmm6,(%rsp)
 	movaps	%xmm7,16(%rsp)
@@ -939,6 +942,8 @@ aesni_ccm64_encrypt_blocks:
 	movq	40(%rsp),%r8
 	movq	48(%rsp),%r9
 
+
+.byte	243,15,30,250
 	leaq	-88(%rsp),%rsp
 	movaps	%xmm6,(%rsp)
 	movaps	%xmm7,16(%rsp)
@@ -1015,6 +1020,7 @@ aesni_ccm64_encrypt_blocks:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_aesni_ccm64_encrypt_blocks:
 .globl	aesni_ccm64_decrypt_blocks
 .def	aesni_ccm64_decrypt_blocks;	.scl 2;	.type 32;	.endef
@@ -1031,6 +1037,8 @@ aesni_ccm64_decrypt_blocks:
 	movq	40(%rsp),%r8
 	movq	48(%rsp),%r9
 
+
+.byte	243,15,30,250
 	leaq	-88(%rsp),%rsp
 	movaps	%xmm6,(%rsp)
 	movaps	%xmm7,16(%rsp)
@@ -1141,6 +1149,7 @@ aesni_ccm64_decrypt_blocks:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_aesni_ccm64_decrypt_blocks:
 .globl	aesni_ctr32_encrypt_blocks
 .def	aesni_ctr32_encrypt_blocks;	.scl 2;	.type 32;	.endef
@@ -1157,6 +1166,7 @@ aesni_ctr32_encrypt_blocks:
 	movq	40(%rsp),%r8
 
 
+.byte	243,15,30,250
 	cmpq	$1,%rdx
 	jne	.Lctr32_bulk
 
@@ -1769,6 +1779,7 @@ aesni_xts_encrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	leaq	(%rsp),%r11
 
 	pushq	%rbp
@@ -2273,6 +2284,7 @@ aesni_xts_decrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	leaq	(%rsp),%r11
 
 	pushq	%rbp
@@ -2814,6 +2826,7 @@ aesni_ocb_encrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	leaq	(%rsp),%rax
 	pushq	%rbx
 
@@ -3046,6 +3059,7 @@ aesni_ocb_encrypt:
 .def	__ocb_encrypt6;	.scl 3;	.type 32;	.endef
 .p2align	5
 __ocb_encrypt6:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3145,9 +3159,11 @@ __ocb_encrypt6:
 	.byte	0xf3,0xc3
 
 
+
 .def	__ocb_encrypt4;	.scl 3;	.type 32;	.endef
 .p2align	5
 __ocb_encrypt4:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3214,9 +3230,11 @@ __ocb_encrypt4:
 	.byte	0xf3,0xc3
 
 
+
 .def	__ocb_encrypt1;	.scl 3;	.type 32;	.endef
 .p2align	5
 __ocb_encrypt1:
+
 	pxor	%xmm15,%xmm7
 	pxor	%xmm9,%xmm7
 	pxor	%xmm2,%xmm8
@@ -3249,6 +3267,7 @@ __ocb_encrypt1:
 	.byte	0xf3,0xc3
 
 
+
 .globl	aesni_ocb_decrypt
 .def	aesni_ocb_decrypt;	.scl 2;	.type 32;	.endef
 .p2align	5
@@ -3265,6 +3284,7 @@ aesni_ocb_decrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	leaq	(%rsp),%rax
 	pushq	%rbx
 
@@ -3519,6 +3539,7 @@ aesni_ocb_decrypt:
 .def	__ocb_decrypt6;	.scl 3;	.type 32;	.endef
 .p2align	5
 __ocb_decrypt6:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3612,9 +3633,11 @@ __ocb_decrypt6:
 	.byte	0xf3,0xc3
 
 
+
 .def	__ocb_decrypt4;	.scl 3;	.type 32;	.endef
 .p2align	5
 __ocb_decrypt4:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3677,9 +3700,11 @@ __ocb_decrypt4:
 	.byte	0xf3,0xc3
 
 
+
 .def	__ocb_decrypt1;	.scl 3;	.type 32;	.endef
 .p2align	5
 __ocb_decrypt1:
+
 	pxor	%xmm15,%xmm7
 	pxor	%xmm9,%xmm7
 	pxor	%xmm7,%xmm2
@@ -3710,6 +3735,7 @@ __ocb_decrypt1:
 .byte	102,15,56,223,215
 	.byte	0xf3,0xc3
 
+
 .globl	aesni_cbc_encrypt
 .def	aesni_cbc_encrypt;	.scl 2;	.type 32;	.endef
 .p2align	4
@@ -3726,6 +3752,7 @@ aesni_cbc_encrypt:
 	movq	48(%rsp),%r9
 
 
+.byte	243,15,30,250
 	testq	%rdx,%rdx
 	jz	.Lcbc_ret
 
@@ -4687,7 +4714,6 @@ __aesni_set_encrypt_key:
 	addq	$8,%rsp
 
 	.byte	0xf3,0xc3
-
 .LSEH_end_set_encrypt_key:
 
 .p2align	4
@@ -4760,6 +4786,7 @@ __aesni_set_encrypt_key:
 	.byte	0xf3,0xc3
 
 
+
 .p2align	6
 .Lbswap_mask:
 .byte	15,14,13,12,11,10,9,8,7,6,5,4,3,2,1,0
diff --git a/lib/accelerated/x86/coff/e_padlock-x86.s b/lib/accelerated/x86/coff/e_padlock-x86.s
index 41f87b117..9e27b9324 100644
--- a/lib/accelerated/x86/coff/e_padlock-x86.s
+++ b/lib/accelerated/x86/coff/e_padlock-x86.s
@@ -1,4 +1,4 @@
-# Copyright (c) 2011-2013, Andy Polyakov <appro@openssl.org>
+# Copyright (c) 2011-2016, Andy Polyakov <appro@openssl.org>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -37,13 +37,13 @@
 #
 # *** This file is auto-generated ***
 #
-.file	"devel/perlasm/e_padlock-x86.s"
 .text
 .globl	_padlock_capability
 .def	_padlock_capability;	.scl	2;	.type	32;	.endef
 .align	16
 _padlock_capability:
 .L_padlock_capability_begin:
+.byte	243,15,30,251
 	pushl	%ebx
 	pushfl
 	popl	%eax
@@ -60,11 +60,20 @@ _padlock_capability:
 	.byte	0x0f,0xa2
 	xorl	%eax,%eax
 	cmpl	$0x746e6543,%ebx
-	jne	.L000noluck
+	jne	.L001zhaoxin
 	cmpl	$0x48727561,%edx
 	jne	.L000noluck
 	cmpl	$0x736c7561,%ecx
 	jne	.L000noluck
+	jmp	.L002zhaoxinEnd
+.L001zhaoxin:
+	cmpl	$0x68532020,%ebx
+	jne	.L000noluck
+	cmpl	$0x68676e61,%edx
+	jne	.L000noluck
+	cmpl	$0x20206961,%ecx
+	jne	.L000noluck
+.L002zhaoxinEnd:
 	movl	$3221225472,%eax
 	.byte	0x0f,0xa2
 	movl	%eax,%edx
@@ -94,38 +103,41 @@ _padlock_capability:
 .align	16
 _padlock_key_bswap:
 .L_padlock_key_bswap_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%edx
 	movl	240(%edx),%ecx
-.L001bswap_loop:
+.L003bswap_loop:
 	movl	(%edx),%eax
 	bswap	%eax
 	movl	%eax,(%edx)
 	leal	4(%edx),%edx
 	subl	$1,%ecx
-	jnz	.L001bswap_loop
+	jnz	.L003bswap_loop
 	ret
 .globl	_padlock_verify_context
 .def	_padlock_verify_context;	.scl	2;	.type	32;	.endef
 .align	16
 _padlock_verify_context:
 .L_padlock_verify_context_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%edx
 	leal	.Lpadlock_saved_context,%eax
 	pushfl
 	call	__padlock_verify_ctx
-.L002verify_pic_point:
+.L004verify_pic_point:
 	leal	4(%esp),%esp
 	ret
 .def	__padlock_verify_ctx;	.scl	3;	.type	32;	.endef
 .align	16
 __padlock_verify_ctx:
+.byte	243,15,30,251
 	btl	$30,4(%esp)
-	jnc	.L003verified
+	jnc	.L005verified
 	cmpl	(%eax),%edx
-	je	.L003verified
+	je	.L005verified
 	pushfl
 	popfl
-.L003verified:
+.L005verified:
 	movl	%edx,(%eax)
 	ret
 .globl	_padlock_reload_key
@@ -133,6 +145,7 @@ __padlock_verify_ctx:
 .align	16
 _padlock_reload_key:
 .L_padlock_reload_key_begin:
+.byte	243,15,30,251
 	pushfl
 	popfl
 	ret
@@ -141,6 +154,7 @@ _padlock_reload_key:
 .align	16
 _padlock_aes_block:
 .L_padlock_aes_block_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	pushl	%ebx
@@ -160,6 +174,7 @@ _padlock_aes_block:
 .align	16
 _padlock_ecb_encrypt:
 .L_padlock_ecb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -169,25 +184,25 @@ _padlock_ecb_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L004ecb_abort
+	jnz	.L006ecb_abort
 	testl	$15,%ecx
-	jnz	.L004ecb_abort
+	jnz	.L006ecb_abort
 	leal	.Lpadlock_saved_context,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-.L005ecb_pic_point:
+.L007ecb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L006ecb_aligned
+	jnz	.L008ecb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L006ecb_aligned
+	jnz	.L008ecb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -206,7 +221,7 @@ _padlock_ecb_encrypt:
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
 	cmpl	%ebx,%ecx
-	ja	.L007ecb_loop
+	ja	.L009ecb_loop
 	movl	%esi,%eax
 	cmpl	%esp,%ebp
 	cmovel	%edi,%eax
@@ -217,10 +232,10 @@ _padlock_ecb_encrypt:
 	movl	$-128,%eax
 	cmovael	%ebx,%eax
 	andl	%eax,%ebx
-	jz	.L008ecb_unaligned_tail
-	jmp	.L007ecb_loop
+	jz	.L010ecb_unaligned_tail
+	jmp	.L009ecb_loop
 .align	16
-.L007ecb_loop:
+.L009ecb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -229,13 +244,13 @@ _padlock_ecb_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L009ecb_inp_aligned
+	jz	.L011ecb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L009ecb_inp_aligned:
+.L011ecb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -243,23 +258,23 @@ _padlock_ecb_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L010ecb_out_aligned
+	jz	.L012ecb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L010ecb_out_aligned:
+.L012ecb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jz	.L011ecb_break
+	jz	.L013ecb_break
 	cmpl	%ebx,%ecx
-	jae	.L007ecb_loop
-.L008ecb_unaligned_tail:
+	jae	.L009ecb_loop
+.L010ecb_unaligned_tail:
 	xorl	%eax,%eax
 	cmpl	%ebp,%esp
 	cmovel	%ecx,%eax
@@ -272,24 +287,24 @@ _padlock_ecb_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L007ecb_loop
+	jmp	.L009ecb_loop
 .align	16
-.L011ecb_break:
+.L013ecb_break:
 	cmpl	%ebp,%esp
-	je	.L012ecb_done
+	je	.L014ecb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L013ecb_bzero:
+.L015ecb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L013ecb_bzero
-.L012ecb_done:
+	ja	.L015ecb_bzero
+.L014ecb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L014ecb_exit
+	jmp	.L016ecb_exit
 .align	16
-.L006ecb_aligned:
+.L008ecb_aligned:
 	leal	(%esi,%ecx,1),%ebp
 	negl	%ebp
 	andl	$4095,%ebp
@@ -299,14 +314,14 @@ _padlock_ecb_encrypt:
 	cmovael	%eax,%ebp
 	andl	%ecx,%ebp
 	subl	%ebp,%ecx
-	jz	.L015ecb_aligned_tail
+	jz	.L017ecb_aligned_tail
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,200
 	testl	%ebp,%ebp
-	jz	.L014ecb_exit
-.L015ecb_aligned_tail:
+	jz	.L016ecb_exit
+.L017ecb_aligned_tail:
 	movl	%ebp,%ecx
 	leal	-24(%esp),%ebp
 	movl	%ebp,%esp
@@ -323,11 +338,11 @@ _padlock_ecb_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L007ecb_loop
-.L014ecb_exit:
+	jmp	.L009ecb_loop
+.L016ecb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L004ecb_abort:
+.L006ecb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -338,6 +353,7 @@ _padlock_ecb_encrypt:
 .align	16
 _padlock_cbc_encrypt:
 .L_padlock_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -347,25 +363,25 @@ _padlock_cbc_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L016cbc_abort
+	jnz	.L018cbc_abort
 	testl	$15,%ecx
-	jnz	.L016cbc_abort
+	jnz	.L018cbc_abort
 	leal	.Lpadlock_saved_context,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-.L017cbc_pic_point:
+.L019cbc_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L018cbc_aligned
+	jnz	.L020cbc_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L018cbc_aligned
+	jnz	.L020cbc_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -384,7 +400,7 @@ _padlock_cbc_encrypt:
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
 	cmpl	%ebx,%ecx
-	ja	.L019cbc_loop
+	ja	.L021cbc_loop
 	movl	%esi,%eax
 	cmpl	%esp,%ebp
 	cmovel	%edi,%eax
@@ -395,10 +411,10 @@ _padlock_cbc_encrypt:
 	movl	$-64,%eax
 	cmovael	%ebx,%eax
 	andl	%eax,%ebx
-	jz	.L020cbc_unaligned_tail
-	jmp	.L019cbc_loop
+	jz	.L022cbc_unaligned_tail
+	jmp	.L021cbc_loop
 .align	16
-.L019cbc_loop:
+.L021cbc_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -407,13 +423,13 @@ _padlock_cbc_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L021cbc_inp_aligned
+	jz	.L023cbc_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L021cbc_inp_aligned:
+.L023cbc_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -423,23 +439,23 @@ _padlock_cbc_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L022cbc_out_aligned
+	jz	.L024cbc_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L022cbc_out_aligned:
+.L024cbc_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jz	.L023cbc_break
+	jz	.L025cbc_break
 	cmpl	%ebx,%ecx
-	jae	.L019cbc_loop
-.L020cbc_unaligned_tail:
+	jae	.L021cbc_loop
+.L022cbc_unaligned_tail:
 	xorl	%eax,%eax
 	cmpl	%ebp,%esp
 	cmovel	%ecx,%eax
@@ -452,24 +468,24 @@ _padlock_cbc_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L019cbc_loop
+	jmp	.L021cbc_loop
 .align	16
-.L023cbc_break:
+.L025cbc_break:
 	cmpl	%ebp,%esp
-	je	.L024cbc_done
+	je	.L026cbc_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L025cbc_bzero:
+.L027cbc_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L025cbc_bzero
-.L024cbc_done:
+	ja	.L027cbc_bzero
+.L026cbc_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L026cbc_exit
+	jmp	.L028cbc_exit
 .align	16
-.L018cbc_aligned:
+.L020cbc_aligned:
 	leal	(%esi,%ecx,1),%ebp
 	negl	%ebp
 	andl	$4095,%ebp
@@ -479,7 +495,7 @@ _padlock_cbc_encrypt:
 	cmovael	%eax,%ebp
 	andl	%ecx,%ebp
 	subl	%ebp,%ecx
-	jz	.L027cbc_aligned_tail
+	jz	.L029cbc_aligned_tail
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -487,8 +503,8 @@ _padlock_cbc_encrypt:
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
 	testl	%ebp,%ebp
-	jz	.L026cbc_exit
-.L027cbc_aligned_tail:
+	jz	.L028cbc_exit
+.L029cbc_aligned_tail:
 	movl	%ebp,%ecx
 	leal	-24(%esp),%ebp
 	movl	%ebp,%esp
@@ -505,11 +521,11 @@ _padlock_cbc_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L019cbc_loop
-.L026cbc_exit:
+	jmp	.L021cbc_loop
+.L028cbc_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L016cbc_abort:
+.L018cbc_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -520,6 +536,7 @@ _padlock_cbc_encrypt:
 .align	16
 _padlock_cfb_encrypt:
 .L_padlock_cfb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -529,25 +546,25 @@ _padlock_cfb_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L028cfb_abort
+	jnz	.L030cfb_abort
 	testl	$15,%ecx
-	jnz	.L028cfb_abort
+	jnz	.L030cfb_abort
 	leal	.Lpadlock_saved_context,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-.L029cfb_pic_point:
+.L031cfb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L030cfb_aligned
+	jnz	.L032cfb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L030cfb_aligned
+	jnz	.L032cfb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -565,9 +582,9 @@ _padlock_cfb_encrypt:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	.L031cfb_loop
+	jmp	.L033cfb_loop
 .align	16
-.L031cfb_loop:
+.L033cfb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -576,13 +593,13 @@ _padlock_cfb_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L032cfb_inp_aligned
+	jz	.L034cfb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L032cfb_inp_aligned:
+.L034cfb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -592,45 +609,45 @@ _padlock_cfb_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L033cfb_out_aligned
+	jz	.L035cfb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L033cfb_out_aligned:
+.L035cfb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	.L031cfb_loop
+	jnz	.L033cfb_loop
 	cmpl	%ebp,%esp
-	je	.L034cfb_done
+	je	.L036cfb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L035cfb_bzero:
+.L037cfb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L035cfb_bzero
-.L034cfb_done:
+	ja	.L037cfb_bzero
+.L036cfb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L036cfb_exit
+	jmp	.L038cfb_exit
 .align	16
-.L030cfb_aligned:
+.L032cfb_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,224
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
-.L036cfb_exit:
+.L038cfb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L028cfb_abort:
+.L030cfb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -641,6 +658,7 @@ _padlock_cfb_encrypt:
 .align	16
 _padlock_ofb_encrypt:
 .L_padlock_ofb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -650,25 +668,25 @@ _padlock_ofb_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L037ofb_abort
+	jnz	.L039ofb_abort
 	testl	$15,%ecx
-	jnz	.L037ofb_abort
+	jnz	.L039ofb_abort
 	leal	.Lpadlock_saved_context,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-.L038ofb_pic_point:
+.L040ofb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L039ofb_aligned
+	jnz	.L041ofb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L039ofb_aligned
+	jnz	.L041ofb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -686,9 +704,9 @@ _padlock_ofb_encrypt:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	.L040ofb_loop
+	jmp	.L042ofb_loop
 .align	16
-.L040ofb_loop:
+.L042ofb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -697,13 +715,13 @@ _padlock_ofb_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L041ofb_inp_aligned
+	jz	.L043ofb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L041ofb_inp_aligned:
+.L043ofb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -713,45 +731,45 @@ _padlock_ofb_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L042ofb_out_aligned
+	jz	.L044ofb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L042ofb_out_aligned:
+.L044ofb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	.L040ofb_loop
+	jnz	.L042ofb_loop
 	cmpl	%ebp,%esp
-	je	.L043ofb_done
+	je	.L045ofb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L044ofb_bzero:
+.L046ofb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L044ofb_bzero
-.L043ofb_done:
+	ja	.L046ofb_bzero
+.L045ofb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L045ofb_exit
+	jmp	.L047ofb_exit
 .align	16
-.L039ofb_aligned:
+.L041ofb_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,232
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
-.L045ofb_exit:
+.L047ofb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L037ofb_abort:
+.L039ofb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -762,6 +780,7 @@ _padlock_ofb_encrypt:
 .align	16
 _padlock_ctr32_encrypt:
 .L_padlock_ctr32_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -771,14 +790,14 @@ _padlock_ctr32_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L046ctr32_abort
+	jnz	.L048ctr32_abort
 	testl	$15,%ecx
-	jnz	.L046ctr32_abort
+	jnz	.L048ctr32_abort
 	leal	.Lpadlock_saved_context,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-.L047ctr32_pic_point:
+.L049ctr32_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	movq	-16(%edx),%mm0
@@ -798,9 +817,9 @@ _padlock_ctr32_encrypt:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	.L048ctr32_loop
+	jmp	.L050ctr32_loop
 .align	16
-.L048ctr32_loop:
+.L050ctr32_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -809,7 +828,7 @@ _padlock_ctr32_encrypt:
 	movl	-4(%edx),%ecx
 	xorl	%edi,%edi
 	movl	-8(%edx),%eax
-.L049ctr32_prepare:
+.L051ctr32_prepare:
 	movl	%ecx,12(%esp,%edi,1)
 	bswap	%ecx
 	movq	%mm0,(%esp,%edi,1)
@@ -818,7 +837,7 @@ _padlock_ctr32_encrypt:
 	bswap	%ecx
 	leal	16(%edi),%edi
 	cmpl	%ebx,%edi
-	jb	.L049ctr32_prepare
+	jb	.L051ctr32_prepare
 	movl	%ecx,-4(%edx)
 	leal	(%esp),%esi
 	leal	(%esp),%edi
@@ -831,33 +850,33 @@ _padlock_ctr32_encrypt:
 	movl	12(%ebp),%ebx
 	movl	4(%ebp),%esi
 	xorl	%ecx,%ecx
-.L050ctr32_xor:
+.L052ctr32_xor:
 	movups	(%esi,%ecx,1),%xmm1
 	leal	16(%ecx),%ecx
 	pxor	-16(%esp,%ecx,1),%xmm1
 	movups	%xmm1,-16(%edi,%ecx,1)
 	cmpl	%ebx,%ecx
-	jb	.L050ctr32_xor
+	jb	.L052ctr32_xor
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	.L048ctr32_loop
+	jnz	.L050ctr32_loop
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L051ctr32_bzero:
+.L053ctr32_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L051ctr32_bzero
-.L052ctr32_done:
+	ja	.L053ctr32_bzero
+.L054ctr32_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
 	movl	$1,%eax
 	leal	4(%esp),%esp
 	emms
-.L046ctr32_abort:
+.L048ctr32_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -868,6 +887,7 @@ _padlock_ctr32_encrypt:
 .align	16
 _padlock_xstore:
 .L_padlock_xstore_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	movl	8(%esp),%edi
 	movl	12(%esp),%edx
@@ -877,20 +897,22 @@ _padlock_xstore:
 .def	__win32_segv_handler;	.scl	3;	.type	32;	.endef
 .align	16
 __win32_segv_handler:
+.byte	243,15,30,251
 	movl	$1,%eax
 	movl	4(%esp),%edx
 	movl	12(%esp),%ecx
 	cmpl	$3221225477,(%edx)
-	jne	.L053ret
+	jne	.L055ret
 	addl	$4,184(%ecx)
 	movl	$0,%eax
-.L053ret:
+.L055ret:
 	ret
 .globl	_padlock_sha1_oneshot
 .def	_padlock_sha1_oneshot;	.scl	2;	.type	32;	.endef
 .align	16
 _padlock_sha1_oneshot:
 .L_padlock_sha1_oneshot_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	xorl	%eax,%eax
@@ -926,6 +948,7 @@ _padlock_sha1_oneshot:
 .align	16
 _padlock_sha1_blocks:
 .L_padlock_sha1_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -955,6 +978,7 @@ _padlock_sha1_blocks:
 .align	16
 _padlock_sha256_oneshot:
 .L_padlock_sha256_oneshot_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	xorl	%eax,%eax
@@ -990,6 +1014,7 @@ _padlock_sha256_oneshot:
 .align	16
 _padlock_sha256_blocks:
 .L_padlock_sha256_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -1019,6 +1044,7 @@ _padlock_sha256_blocks:
 .align	16
 _padlock_sha512_blocks:
 .L_padlock_sha512_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
diff --git a/lib/accelerated/x86/coff/e_padlock-x86_64.s b/lib/accelerated/x86/coff/e_padlock-x86_64.s
index 7edee19f5..71c9e1aea 100644
--- a/lib/accelerated/x86/coff/e_padlock-x86_64.s
+++ b/lib/accelerated/x86/coff/e_padlock-x86_64.s
@@ -1,4 +1,4 @@
-# Copyright (c) 2011-2013, Andy Polyakov <appro@openssl.org>
+# Copyright (c) 2011-2016, Andy Polyakov <appro@openssl.org>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -42,36 +42,50 @@
 .def	padlock_capability;	.scl 2;	.type 32;	.endef
 .p2align	4
 padlock_capability:
+
+.byte	243,15,30,250
 	movq	%rbx,%r8
 	xorl	%eax,%eax
 	cpuid
 	xorl	%eax,%eax
-	cmpl	$1953391939,%ebx
+	cmpl	$0x746e6543,%ebx
+	jne	.Lzhaoxin
+	cmpl	$0x48727561,%edx
+	jne	.Lnoluck
+	cmpl	$0x736c7561,%ecx
+	jne	.Lnoluck
+	jmp	.LzhaoxinEnd
+.Lzhaoxin:
+	cmpl	$0x68532020,%ebx
 	jne	.Lnoluck
-	cmpl	$1215460705,%edx
+	cmpl	$0x68676e61,%edx
 	jne	.Lnoluck
-	cmpl	$1936487777,%ecx
+	cmpl	$0x20206961,%ecx
 	jne	.Lnoluck
-	movl	$3221225472,%eax
+.LzhaoxinEnd:
+	movl	$0xC0000000,%eax
 	cpuid
 	movl	%eax,%edx
 	xorl	%eax,%eax
-	cmpl	$3221225473,%edx
+	cmpl	$0xC0000001,%edx
 	jb	.Lnoluck
-	movl	$3221225473,%eax
+	movl	$0xC0000001,%eax
 	cpuid
 	movl	%edx,%eax
-	andl	$4294967279,%eax
-	orl	$16,%eax
+	andl	$0xffffffef,%eax
+	orl	$0x10,%eax
 .Lnoluck:
 	movq	%r8,%rbx
 	.byte	0xf3,0xc3
 
 
+
 .globl	padlock_key_bswap
 .def	padlock_key_bswap;	.scl 2;	.type 32;	.endef
 .p2align	4
 padlock_key_bswap:
+
+.byte	243,15,30,250
 	movl	240(%rcx),%edx
 .Lbswap_loop:
 	movl	(%rcx),%eax
@@ -83,10 +97,13 @@ padlock_key_bswap:
 	.byte	0xf3,0xc3
 
 
+
 .globl	padlock_verify_context
 .def	padlock_verify_context;	.scl 2;	.type 32;	.endef
 .p2align	4
 padlock_verify_context:
+
+.byte	243,15,30,250
 	movq	%rcx,%rdx
 	pushf
 	leaq	.Lpadlock_saved_context(%rip),%rax
@@ -95,9 +112,12 @@ padlock_verify_context:
 	.byte	0xf3,0xc3
 
 
+
 .def	_padlock_verify_ctx;	.scl 3;	.type 32;	.endef
 .p2align	4
 _padlock_verify_ctx:
+
+.byte	243,15,30,250
 	movq	8(%rsp),%r8
 	btq	$30,%r8
 	jnc	.Lverified
@@ -110,15 +130,19 @@ _padlock_verify_ctx:
 	.byte	0xf3,0xc3
 
 
+
 .globl	padlock_reload_key
 .def	padlock_reload_key;	.scl 2;	.type 32;	.endef
 .p2align	4
 padlock_reload_key:
+
+.byte	243,15,30,250
 	pushf
 	popf
 	.byte	0xf3,0xc3
 
 
+
 .globl	padlock_aes_block
 .def	padlock_aes_block;	.scl 2;	.type 32;	.endef
 .p2align	4
@@ -131,15 +155,18 @@ padlock_aes_block:
 	movq	%rdx,%rsi
 	movq	%r8,%rdx
 
+
+.byte	243,15,30,250
 	movq	%rbx,%r8
 	movq	$1,%rcx
 	leaq	32(%rdx),%rbx
 	leaq	16(%rdx),%rdx
-.byte	0xf3,0x0f,0xa7,0xc8	
+.byte	0xf3,0x0f,0xa7,0xc8
 	movq	%r8,%rbx
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_aes_block:
 
 .globl	padlock_xstore
@@ -153,11 +180,14 @@ padlock_xstore:
 	movq	%rcx,%rdi
 	movq	%rdx,%rsi
 
+
+.byte	243,15,30,250
 	movl	%esi,%edx
-.byte	0x0f,0xa7,0xc0		
+.byte	0x0f,0xa7,0xc0
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_xstore:
 
 .globl	padlock_sha1_oneshot
@@ -172,6 +202,8 @@ padlock_sha1_oneshot:
 	movq	%rdx,%rsi
 	movq	%r8,%rdx
 
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -181,7 +213,7 @@ padlock_sha1_oneshot:
 	movq	%rsp,%rdi
 	movl	%eax,16(%rsp)
 	xorq	%rax,%rax
-.byte	0xf3,0x0f,0xa6,0xc8	
+.byte	0xf3,0x0f,0xa6,0xc8
 	movaps	(%rsp),%xmm0
 	movl	16(%rsp),%eax
 	addq	$128+8,%rsp
@@ -190,6 +222,7 @@ padlock_sha1_oneshot:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_sha1_oneshot:
 
 .globl	padlock_sha1_blocks
@@ -204,6 +237,8 @@ padlock_sha1_blocks:
 	movq	%rdx,%rsi
 	movq	%r8,%rdx
 
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -213,7 +248,7 @@ padlock_sha1_blocks:
 	movq	%rsp,%rdi
 	movl	%eax,16(%rsp)
 	movq	$-1,%rax
-.byte	0xf3,0x0f,0xa6,0xc8	
+.byte	0xf3,0x0f,0xa6,0xc8
 	movaps	(%rsp),%xmm0
 	movl	16(%rsp),%eax
 	addq	$128+8,%rsp
@@ -222,6 +257,7 @@ padlock_sha1_blocks:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_sha1_blocks:
 
 .globl	padlock_sha256_oneshot
@@ -236,6 +272,8 @@ padlock_sha256_oneshot:
 	movq	%rdx,%rsi
 	movq	%r8,%rdx
 
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -245,7 +283,7 @@ padlock_sha256_oneshot:
 	movq	%rsp,%rdi
 	movaps	%xmm1,16(%rsp)
 	xorq	%rax,%rax
-.byte	0xf3,0x0f,0xa6,0xd0	
+.byte	0xf3,0x0f,0xa6,0xd0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	addq	$128+8,%rsp
@@ -254,6 +292,7 @@ padlock_sha256_oneshot:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_sha256_oneshot:
 
 .globl	padlock_sha256_blocks
@@ -268,6 +307,8 @@ padlock_sha256_blocks:
 	movq	%rdx,%rsi
 	movq	%r8,%rdx
 
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -277,7 +318,7 @@ padlock_sha256_blocks:
 	movq	%rsp,%rdi
 	movaps	%xmm1,16(%rsp)
 	movq	$-1,%rax
-.byte	0xf3,0x0f,0xa6,0xd0	
+.byte	0xf3,0x0f,0xa6,0xd0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	addq	$128+8,%rsp
@@ -286,6 +327,7 @@ padlock_sha256_blocks:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_sha256_blocks:
 
 .globl	padlock_sha512_blocks
@@ -300,6 +342,8 @@ padlock_sha512_blocks:
 	movq	%rdx,%rsi
 	movq	%r8,%rdx
 
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -312,7 +356,7 @@ padlock_sha512_blocks:
 	movaps	%xmm1,16(%rsp)
 	movaps	%xmm2,32(%rsp)
 	movaps	%xmm3,48(%rsp)
-.byte	0xf3,0x0f,0xa6,0xe0	
+.byte	0xf3,0x0f,0xa6,0xe0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	movaps	32(%rsp),%xmm2
@@ -325,6 +369,7 @@ padlock_sha512_blocks:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_sha512_blocks:
 .globl	padlock_ecb_encrypt
 .def	padlock_ecb_encrypt;	.scl 2;	.type 32;	.endef
@@ -339,6 +384,8 @@ padlock_ecb_encrypt:
 	movq	%r8,%rdx
 	movq	%r9,%rcx
 
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -356,9 +403,9 @@ padlock_ecb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lecb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lecb_aligned
@@ -382,7 +429,7 @@ padlock_ecb_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$128,%rax
 	movq	$-128,%rax
 	cmovaeq	%rbx,%rax
@@ -398,12 +445,12 @@ padlock_ecb_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lecb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -411,15 +458,15 @@ padlock_ecb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,200	
+.byte	0xf3,0x0f,0xa7,200
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lecb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lecb_out_aligned:
 	movq	%r9,%rsi
@@ -440,7 +487,7 @@ padlock_ecb_encrypt:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -466,7 +513,7 @@ padlock_ecb_encrypt:
 .Lecb_aligned:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$128,%rbp
 	movq	$128-1,%rbp
@@ -477,7 +524,7 @@ padlock_ecb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,200	
+.byte	0xf3,0x0f,0xa7,200
 	testq	%rbp,%rbp
 	jz	.Lecb_exit
 
@@ -489,7 +536,7 @@ padlock_ecb_encrypt:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -503,6 +550,7 @@ padlock_ecb_encrypt:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_ecb_encrypt:
 .globl	padlock_cbc_encrypt
 .def	padlock_cbc_encrypt;	.scl 2;	.type 32;	.endef
@@ -517,6 +565,8 @@ padlock_cbc_encrypt:
 	movq	%r8,%rdx
 	movq	%r9,%rcx
 
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -534,9 +584,9 @@ padlock_cbc_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lcbc_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lcbc_aligned
@@ -560,7 +610,7 @@ padlock_cbc_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$64,%rax
 	movq	$-64,%rax
 	cmovaeq	%rbx,%rax
@@ -576,12 +626,12 @@ padlock_cbc_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lcbc_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -589,17 +639,17 @@ padlock_cbc_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,208	
+.byte	0xf3,0x0f,0xa7,208
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lcbc_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lcbc_out_aligned:
 	movq	%r9,%rsi
@@ -620,7 +670,7 @@ padlock_cbc_encrypt:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -646,7 +696,7 @@ padlock_cbc_encrypt:
 .Lcbc_aligned:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$64,%rbp
 	movq	$64-1,%rbp
@@ -657,7 +707,7 @@ padlock_cbc_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,208	
+.byte	0xf3,0x0f,0xa7,208
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	testq	%rbp,%rbp
@@ -671,7 +721,7 @@ padlock_cbc_encrypt:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -685,6 +735,7 @@ padlock_cbc_encrypt:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_cbc_encrypt:
 .globl	padlock_cfb_encrypt
 .def	padlock_cfb_encrypt;	.scl 2;	.type 32;	.endef
@@ -699,6 +750,8 @@ padlock_cfb_encrypt:
 	movq	%r8,%rdx
 	movq	%r9,%rcx
 
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -716,9 +769,9 @@ padlock_cfb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lcfb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lcfb_aligned
@@ -745,12 +798,12 @@ padlock_cfb_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lcfb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -758,17 +811,17 @@ padlock_cfb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,224	
+.byte	0xf3,0x0f,0xa7,224
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lcfb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lcfb_out_aligned:
 	movq	%r9,%rsi
@@ -798,7 +851,7 @@ padlock_cfb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,224	
+.byte	0xf3,0x0f,0xa7,224
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 .Lcfb_exit:
@@ -810,6 +863,7 @@ padlock_cfb_encrypt:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_cfb_encrypt:
 .globl	padlock_ofb_encrypt
 .def	padlock_ofb_encrypt;	.scl 2;	.type 32;	.endef
@@ -824,6 +878,8 @@ padlock_ofb_encrypt:
 	movq	%r8,%rdx
 	movq	%r9,%rcx
 
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -841,9 +897,9 @@ padlock_ofb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lofb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lofb_aligned
@@ -870,12 +926,12 @@ padlock_ofb_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lofb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -883,17 +939,17 @@ padlock_ofb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,232	
+.byte	0xf3,0x0f,0xa7,232
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lofb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lofb_out_aligned:
 	movq	%r9,%rsi
@@ -923,7 +979,7 @@ padlock_ofb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,232	
+.byte	0xf3,0x0f,0xa7,232
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 .Lofb_exit:
@@ -935,6 +991,7 @@ padlock_ofb_encrypt:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_ofb_encrypt:
 .globl	padlock_ctr32_encrypt
 .def	padlock_ctr32_encrypt;	.scl 2;	.type 32;	.endef
@@ -949,6 +1006,8 @@ padlock_ctr32_encrypt:
 	movq	%r8,%rdx
 	movq	%r9,%rcx
 
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -966,9 +1025,9 @@ padlock_ctr32_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lctr32_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lctr32_aligned
@@ -1003,7 +1062,7 @@ padlock_ctr32_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$32,%rax
 	movq	$-32,%rax
 	cmovaeq	%rbx,%rax
@@ -1019,12 +1078,12 @@ padlock_ctr32_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lctr32_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -1032,23 +1091,23 @@ padlock_ctr32_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 	movl	-4(%rdx),%eax
-	testl	$4294901760,%eax
+	testl	$0xffff0000,%eax
 	jnz	.Lctr32_no_carry
 	bswapl	%eax
-	addl	$65536,%eax
+	addl	$0x10000,%eax
 	bswapl	%eax
 	movl	%eax,-4(%rdx)
 .Lctr32_no_carry:
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lctr32_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lctr32_out_aligned:
 	movq	%r9,%rsi
@@ -1066,7 +1125,7 @@ padlock_ctr32_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$32,%rax
 	movq	$-32,%rax
 	cmovaeq	%rbx,%rax
@@ -1081,7 +1140,7 @@ padlock_ctr32_encrypt:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -1108,7 +1167,7 @@ padlock_ctr32_encrypt:
 	movl	-4(%rdx),%eax
 	bswapl	%eax
 	negl	%eax
-	andl	$65535,%eax
+	andl	$0xffff,%eax
 	movq	$1048576,%rbx
 	shll	$4,%eax
 	cmovzq	%rbx,%rax
@@ -1125,11 +1184,11 @@ padlock_ctr32_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 
 	movl	-4(%rdx),%eax
 	bswapl	%eax
-	addl	$65536,%eax
+	addl	$0x10000,%eax
 	bswapl	%eax
 	movl	%eax,-4(%rdx)
 
@@ -1143,7 +1202,7 @@ padlock_ctr32_encrypt:
 .Lctr32_aligned_skip:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$32,%rbp
 	movq	$32-1,%rbp
@@ -1154,7 +1213,7 @@ padlock_ctr32_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 	testq	%rbp,%rbp
 	jz	.Lctr32_exit
 
@@ -1166,7 +1225,7 @@ padlock_ctr32_encrypt:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -1180,6 +1239,7 @@ padlock_ctr32_encrypt:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_padlock_ctr32_encrypt:
 .byte	86,73,65,32,80,97,100,108,111,99,107,32,120,56,54,95,54,52,32,109,111,100,117,108,101,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .p2align	4
diff --git a/lib/accelerated/x86/coff/ghash-x86_64.s b/lib/accelerated/x86/coff/ghash-x86_64.s
index de207e400..cfe24252f 100644
--- a/lib/accelerated/x86/coff/ghash-x86_64.s
+++ b/lib/accelerated/x86/coff/ghash-x86_64.s
@@ -52,6 +52,7 @@ gcm_gmult_4bit:
 	movq	%rdx,%rsi
 
 
+.byte	243,15,30,250
 	pushq	%rbx
 
 	pushq	%rbp
@@ -168,6 +169,7 @@ gcm_ghash_4bit:
 	movq	%r9,%rcx
 
 
+.byte	243,15,30,250
 	pushq	%rbx
 
 	pushq	%rbp
@@ -918,6 +920,7 @@ gcm_init_clmul:
 .p2align	4
 gcm_gmult_clmul:
 
+.byte	243,15,30,250
 .L_gmult_clmul:
 	movdqu	(%rcx),%xmm0
 	movdqa	.Lbswap_mask(%rip),%xmm5
@@ -971,6 +974,7 @@ gcm_gmult_clmul:
 .p2align	5
 gcm_ghash_clmul:
 
+.byte	243,15,30,250
 .L_ghash_clmul:
 	leaq	-136(%rsp),%rax
 .LSEH_begin_gcm_ghash_clmul:
@@ -1498,6 +1502,7 @@ gcm_init_avx:
 .p2align	5
 gcm_gmult_avx:
 
+.byte	243,15,30,250
 	jmp	.L_gmult_clmul
 
 
@@ -1506,6 +1511,7 @@ gcm_gmult_avx:
 .p2align	5
 gcm_ghash_avx:
 
+.byte	243,15,30,250
 	leaq	-136(%rsp),%rax
 .LSEH_begin_gcm_ghash_avx:
 
diff --git a/lib/accelerated/x86/coff/sha1-ssse3-x86.s b/lib/accelerated/x86/coff/sha1-ssse3-x86.s
index 30f9ded21..34b33601e 100644
--- a/lib/accelerated/x86/coff/sha1-ssse3-x86.s
+++ b/lib/accelerated/x86/coff/sha1-ssse3-x86.s
@@ -43,6 +43,7 @@
 .align	16
 _sha1_block_data_order:
 .L_sha1_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s b/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s
index cdfc88254..79f841f1a 100644
--- a/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/sha1-ssse3-x86_64.s
@@ -1490,10 +1490,10 @@ _shaext_shortcut:
 	movaps	-8-16(%rax),%xmm9
 	movq	%rax,%rsp
 .Lepilogue_shaext:
-
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_sha1_block_data_order_shaext:
 .def	sha1_block_data_order_ssse3;	.scl 3;	.type 32;	.endef
 .p2align	4
diff --git a/lib/accelerated/x86/coff/sha256-ssse3-x86.s b/lib/accelerated/x86/coff/sha256-ssse3-x86.s
index 05cd61d1b..8109c6b51 100644
--- a/lib/accelerated/x86/coff/sha256-ssse3-x86.s
+++ b/lib/accelerated/x86/coff/sha256-ssse3-x86.s
@@ -43,6 +43,7 @@
 .align	16
 _sha256_block_data_order:
 .L_sha256_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s b/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s
index d2fc1957e..78fae2a62 100644
--- a/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/sha256-ssse3-x86_64.s
@@ -1832,6 +1832,7 @@ sha256_block_data_order_shaext:
 	movq	%r8,%rdx
 
 _shaext_shortcut:
+
 	leaq	-88(%rsp),%rsp
 	movaps	%xmm6,-8-80(%rax)
 	movaps	%xmm7,-8-64(%rax)
@@ -2050,6 +2051,7 @@ _shaext_shortcut:
 	movq	8(%rsp),%rdi
 	movq	16(%rsp),%rsi
 	.byte	0xf3,0xc3
+
 .LSEH_end_sha256_block_data_order_shaext:
 .def	sha256_block_data_order_ssse3;	.scl 3;	.type 32;	.endef
 .p2align	6
@@ -5501,6 +5503,8 @@ sha256_block_data_order_avx2:
 
 	leaq	448(%rsp),%rsp
 
+
+
 	addl	0(%rdi),%eax
 	addl	4(%rdi),%ebx
 	addl	8(%rdi),%ecx
@@ -5526,15 +5530,17 @@ sha256_block_data_order_avx2:
 	jbe	.Loop_avx2
 	leaq	(%rsp),%rbp
 
+
+
+
 .Ldone_avx2:
-	leaq	(%rbp),%rsp
-	movq	88(%rsp),%rsi
+	movq	88(%rbp),%rsi
 
 	vzeroupper
-	movaps	64+32(%rsp),%xmm6
-	movaps	64+48(%rsp),%xmm7
-	movaps	64+64(%rsp),%xmm8
-	movaps	64+80(%rsp),%xmm9
+	movaps	64+32(%rbp),%xmm6
+	movaps	64+48(%rbp),%xmm7
+	movaps	64+64(%rbp),%xmm8
+	movaps	64+80(%rbp),%xmm9
 	movq	-48(%rsi),%r15
 
 	movq	-40(%rsi),%r14
diff --git a/lib/accelerated/x86/coff/sha512-ssse3-x86.s b/lib/accelerated/x86/coff/sha512-ssse3-x86.s
index 72a7f73d7..321a18541 100644
--- a/lib/accelerated/x86/coff/sha512-ssse3-x86.s
+++ b/lib/accelerated/x86/coff/sha512-ssse3-x86.s
@@ -43,6 +43,7 @@
 .align	16
 _sha512_block_data_order:
 .L_sha512_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s b/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s
index 419fa2a98..836e0cf66 100644
--- a/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s
+++ b/lib/accelerated/x86/coff/sha512-ssse3-x86_64.s
@@ -5494,6 +5494,8 @@ sha512_block_data_order_avx2:
 
 	leaq	1152(%rsp),%rsp
 
+
+
 	addq	0(%rdi),%rax
 	addq	8(%rdi),%rbx
 	addq	16(%rdi),%rcx
@@ -5519,17 +5521,19 @@ sha512_block_data_order_avx2:
 	jbe	.Loop_avx2
 	leaq	(%rsp),%rbp
 
+
+
+
 .Ldone_avx2:
-	leaq	(%rbp),%rsp
-	movq	152(%rsp),%rsi
+	movq	152(%rbp),%rsi
 
 	vzeroupper
-	movaps	128+32(%rsp),%xmm6
-	movaps	128+48(%rsp),%xmm7
-	movaps	128+64(%rsp),%xmm8
-	movaps	128+80(%rsp),%xmm9
-	movaps	128+96(%rsp),%xmm10
-	movaps	128+112(%rsp),%xmm11
+	movaps	128+32(%rbp),%xmm6
+	movaps	128+48(%rbp),%xmm7
+	movaps	128+64(%rbp),%xmm8
+	movaps	128+80(%rbp),%xmm9
+	movaps	128+96(%rbp),%xmm10
+	movaps	128+112(%rbp),%xmm11
 	movq	-48(%rsi),%r15
 
 	movq	-40(%rsi),%r14
diff --git a/lib/accelerated/x86/elf/aes-ssse3-x86.s b/lib/accelerated/x86/elf/aes-ssse3-x86.s
index 265e28a7e..7be53059f 100644
--- a/lib/accelerated/x86/elf/aes-ssse3-x86.s
+++ b/lib/accelerated/x86/elf/aes-ssse3-x86.s
@@ -71,6 +71,7 @@
 .type	_vpaes_preheat,@function
 .align	16
 _vpaes_preheat:
+.byte	243,15,30,251
 	addl	(%esp),%ebp
 	movdqa	-48(%ebp),%xmm7
 	movdqa	-16(%ebp),%xmm6
@@ -79,6 +80,7 @@ _vpaes_preheat:
 .type	_vpaes_encrypt_core,@function
 .align	16
 _vpaes_encrypt_core:
+.byte	243,15,30,251
 	movl	$16,%ecx
 	movl	240(%edx),%eax
 	movdqa	%xmm6,%xmm1
@@ -156,6 +158,7 @@ _vpaes_encrypt_core:
 .type	_vpaes_decrypt_core,@function
 .align	16
 _vpaes_decrypt_core:
+.byte	243,15,30,251
 	leal	608(%ebp),%ebx
 	movl	240(%edx),%eax
 	movdqa	%xmm6,%xmm1
@@ -244,6 +247,7 @@ _vpaes_decrypt_core:
 .type	_vpaes_schedule_core,@function
 .align	16
 _vpaes_schedule_core:
+.byte	243,15,30,251
 	addl	(%esp),%ebp
 	movdqu	(%esi),%xmm0
 	movdqa	320(%ebp),%xmm2
@@ -338,6 +342,7 @@ _vpaes_schedule_core:
 .type	_vpaes_schedule_192_smear,@function
 .align	16
 _vpaes_schedule_192_smear:
+.byte	243,15,30,251
 	pshufd	$128,%xmm6,%xmm1
 	pshufd	$254,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
@@ -350,6 +355,7 @@ _vpaes_schedule_192_smear:
 .type	_vpaes_schedule_round,@function
 .align	16
 _vpaes_schedule_round:
+.byte	243,15,30,251
 	movdqa	8(%esp),%xmm2
 	pxor	%xmm1,%xmm1
 .byte	102,15,58,15,202,15
@@ -399,6 +405,7 @@ _vpaes_schedule_round:
 .type	_vpaes_schedule_transform,@function
 .align	16
 _vpaes_schedule_transform:
+.byte	243,15,30,251
 	movdqa	-16(%ebp),%xmm2
 	movdqa	%xmm2,%xmm1
 	pandn	%xmm0,%xmm1
@@ -414,6 +421,7 @@ _vpaes_schedule_transform:
 .type	_vpaes_schedule_mangle,@function
 .align	16
 _vpaes_schedule_mangle:
+.byte	243,15,30,251
 	movdqa	%xmm0,%xmm4
 	movdqa	128(%ebp),%xmm5
 	testl	%edi,%edi
@@ -475,6 +483,7 @@ _vpaes_schedule_mangle:
 .align	16
 vpaes_set_encrypt_key:
 .L_vpaes_set_encrypt_key_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -508,6 +517,7 @@ vpaes_set_encrypt_key:
 .align	16
 vpaes_set_decrypt_key:
 .L_vpaes_set_decrypt_key_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -546,6 +556,7 @@ vpaes_set_decrypt_key:
 .align	16
 vpaes_encrypt:
 .L_vpaes_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -575,6 +586,7 @@ vpaes_encrypt:
 .align	16
 vpaes_decrypt:
 .L_vpaes_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -604,6 +616,7 @@ vpaes_decrypt:
 .align	16
 vpaes_cbc_encrypt:
 .L_vpaes_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -671,4 +684,21 @@ vpaes_cbc_encrypt:
 	ret
 .size	vpaes_cbc_encrypt,.-.L_vpaes_cbc_encrypt_begin
 
+	.section ".note.gnu.property", "a"
+	.p2align 2
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 2
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 2
+4:
+
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/aes-ssse3-x86_64.s b/lib/accelerated/x86/elf/aes-ssse3-x86_64.s
index ea1216baf..5a3f336f2 100644
--- a/lib/accelerated/x86/elf/aes-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/aes-ssse3-x86_64.s
@@ -635,6 +635,7 @@ _vpaes_schedule_mangle:
 .align	16
 vpaes_set_encrypt_key:
 .cfi_startproc	
+.byte	243,15,30,250
 	movl	%esi,%eax
 	shrl	$5,%eax
 	addl	$5,%eax
@@ -653,6 +654,7 @@ vpaes_set_encrypt_key:
 .align	16
 vpaes_set_decrypt_key:
 .cfi_startproc	
+.byte	243,15,30,250
 	movl	%esi,%eax
 	shrl	$5,%eax
 	addl	$5,%eax
@@ -676,6 +678,7 @@ vpaes_set_decrypt_key:
 .align	16
 vpaes_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	movdqu	(%rdi),%xmm0
 	call	_vpaes_preheat
 	call	_vpaes_encrypt_core
@@ -689,6 +692,7 @@ vpaes_encrypt:
 .align	16
 vpaes_decrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	movdqu	(%rdi),%xmm0
 	call	_vpaes_preheat
 	call	_vpaes_decrypt_core
@@ -701,6 +705,7 @@ vpaes_decrypt:
 .align	16
 vpaes_cbc_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	xchgq	%rcx,%rdx
 	subq	$16,%rcx
 	jc	.Lcbc_abort
@@ -863,5 +868,26 @@ _vpaes_consts:
 .byte	86,101,99,116,111,114,32,80,101,114,109,117,116,97,116,105,111,110,32,65,69,83,32,102,111,114,32,120,56,54,95,54,52,47,83,83,83,69,51,44,32,77,105,107,101,32,72,97,109,98,117,114,103,32,40,83,116,97,110,102,111,114,100,32,85,110,105,118,101,114,115,105,116,121,41,0
 .align	64
 .size	_vpaes_consts,.-_vpaes_consts
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/aesni-gcm-x86_64.s b/lib/accelerated/x86/elf/aesni-gcm-x86_64.s
index e26d18d69..1a11222e7 100644
--- a/lib/accelerated/x86/elf/aesni-gcm-x86_64.s
+++ b/lib/accelerated/x86/elf/aesni-gcm-x86_64.s
@@ -42,6 +42,8 @@
 .type	_aesni_ctr32_ghash_6x,@function
 .align	32
 _aesni_ctr32_ghash_6x:
+.cfi_startproc	
+.byte	243,15,30,250
 	vmovdqu	32(%r11),%xmm2
 	subq	$6,%rdx
 	vpxor	%xmm4,%xmm4,%xmm4
@@ -349,12 +351,14 @@ _aesni_ctr32_ghash_6x:
 	vpxor	%xmm4,%xmm8,%xmm8
 
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	_aesni_ctr32_ghash_6x,.-_aesni_ctr32_ghash_6x
 .globl	aesni_gcm_decrypt
 .type	aesni_gcm_decrypt,@function
 .align	32
 aesni_gcm_decrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	xorq	%r10,%r10
 	cmpq	$0x60,%rdx
 	jb	.Lgcm_dec_abort
@@ -455,6 +459,8 @@ aesni_gcm_decrypt:
 .type	_aesni_ctr32_6x,@function
 .align	32
 _aesni_ctr32_6x:
+.cfi_startproc	
+.byte	243,15,30,250
 	vmovdqu	0-128(%rcx),%xmm4
 	vmovdqu	32(%r11),%xmm2
 	leaq	-1(%rbp),%r13
@@ -541,6 +547,7 @@ _aesni_ctr32_6x:
 	vpshufb	%xmm0,%xmm1,%xmm1
 	vpxor	%xmm4,%xmm14,%xmm14
 	jmp	.Loop_ctr32
+.cfi_endproc	
 .size	_aesni_ctr32_6x,.-_aesni_ctr32_6x
 
 .globl	aesni_gcm_encrypt
@@ -548,6 +555,7 @@ _aesni_ctr32_6x:
 .align	32
 aesni_gcm_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	xorq	%r10,%r10
 	cmpq	$288,%rdx
 	jb	.Lgcm_enc_abort
@@ -822,5 +830,26 @@ aesni_gcm_encrypt:
 .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
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/aesni-x86.s b/lib/accelerated/x86/elf/aesni-x86.s
index 6e4860209..f41d5f9ef 100644
--- a/lib/accelerated/x86/elf/aesni-x86.s
+++ b/lib/accelerated/x86/elf/aesni-x86.s
@@ -43,6 +43,7 @@
 .align	16
 aesni_encrypt:
 .L_aesni_encrypt_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	12(%esp),%edx
 	movups	(%eax),%xmm2
@@ -70,6 +71,7 @@ aesni_encrypt:
 .align	16
 aesni_decrypt:
 .L_aesni_decrypt_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	12(%esp),%edx
 	movups	(%eax),%xmm2
@@ -95,6 +97,7 @@ aesni_decrypt:
 .type	_aesni_encrypt2,@function
 .align	16
 _aesni_encrypt2:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -122,6 +125,7 @@ _aesni_encrypt2:
 .type	_aesni_decrypt2,@function
 .align	16
 _aesni_decrypt2:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -149,6 +153,7 @@ _aesni_decrypt2:
 .type	_aesni_encrypt3,@function
 .align	16
 _aesni_encrypt3:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -181,6 +186,7 @@ _aesni_encrypt3:
 .type	_aesni_decrypt3,@function
 .align	16
 _aesni_decrypt3:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -213,6 +219,7 @@ _aesni_decrypt3:
 .type	_aesni_encrypt4,@function
 .align	16
 _aesni_encrypt4:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	movups	16(%edx),%xmm1
 	shll	$4,%ecx
@@ -251,6 +258,7 @@ _aesni_encrypt4:
 .type	_aesni_decrypt4,@function
 .align	16
 _aesni_decrypt4:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	movups	16(%edx),%xmm1
 	shll	$4,%ecx
@@ -289,6 +297,7 @@ _aesni_decrypt4:
 .type	_aesni_encrypt6,@function
 .align	16
 _aesni_encrypt6:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -343,6 +352,7 @@ _aesni_encrypt6:
 .type	_aesni_decrypt6,@function
 .align	16
 _aesni_decrypt6:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -399,6 +409,7 @@ _aesni_decrypt6:
 .align	16
 aesni_ecb_encrypt:
 .L_aesni_ecb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -634,6 +645,7 @@ aesni_ecb_encrypt:
 .align	16
 aesni_ccm64_encrypt_blocks:
 .L_aesni_ccm64_encrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -722,6 +734,7 @@ aesni_ccm64_encrypt_blocks:
 .align	16
 aesni_ccm64_decrypt_blocks:
 .L_aesni_ccm64_decrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -845,6 +858,7 @@ aesni_ccm64_decrypt_blocks:
 .align	16
 aesni_ctr32_encrypt_blocks:
 .L_aesni_ctr32_encrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1083,6 +1097,7 @@ aesni_ctr32_encrypt_blocks:
 .align	16
 aesni_xts_encrypt:
 .L_aesni_xts_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1443,6 +1458,7 @@ aesni_xts_encrypt:
 .align	16
 aesni_xts_decrypt:
 .L_aesni_xts_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1833,6 +1849,7 @@ aesni_xts_decrypt:
 .align	16
 aesni_ocb_encrypt:
 .L_aesni_ocb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2228,6 +2245,7 @@ aesni_ocb_encrypt:
 .align	16
 aesni_ocb_decrypt:
 .L_aesni_ocb_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2623,6 +2641,7 @@ aesni_ocb_decrypt:
 .align	16
 aesni_cbc_encrypt:
 .L_aesni_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2882,6 +2901,7 @@ aesni_cbc_encrypt:
 .type	_aesni_set_encrypt_key,@function
 .align	16
 _aesni_set_encrypt_key:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	testl	%eax,%eax
@@ -3217,6 +3237,7 @@ _aesni_set_encrypt_key:
 .align	16
 aesni_set_encrypt_key:
 .L_aesni_set_encrypt_key_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	8(%esp),%ecx
 	movl	12(%esp),%edx
@@ -3228,6 +3249,7 @@ aesni_set_encrypt_key:
 .align	16
 aesni_set_decrypt_key:
 .L_aesni_set_decrypt_key_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	8(%esp),%ecx
 	movl	12(%esp),%edx
@@ -3275,4 +3297,21 @@ aesni_set_decrypt_key:
 .byte	115,108,46,111,114,103,62,0
 .comm	_gnutls_x86_cpuid_s,16,4
 
+	.section ".note.gnu.property", "a"
+	.p2align 2
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 2
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 2
+4:
+
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/aesni-x86_64.s b/lib/accelerated/x86/elf/aesni-x86_64.s
index 43cf4e68d..e3f9d5a99 100644
--- a/lib/accelerated/x86/elf/aesni-x86_64.s
+++ b/lib/accelerated/x86/elf/aesni-x86_64.s
@@ -44,6 +44,7 @@
 .align	16
 aesni_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	movups	(%rdi),%xmm2
 	movl	240(%rdx),%eax
 	movups	(%rdx),%xmm0
@@ -70,6 +71,7 @@ aesni_encrypt:
 .align	16
 aesni_decrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	movups	(%rdi),%xmm2
 	movl	240(%rdx),%eax
 	movups	(%rdx),%xmm0
@@ -557,6 +559,7 @@ _aesni_decrypt8:
 .align	16
 aesni_ecb_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	andq	$-16,%rdx
 	jz	.Lecb_ret
 
@@ -900,6 +903,8 @@ aesni_ecb_encrypt:
 .type	aesni_ccm64_encrypt_blocks,@function
 .align	16
 aesni_ccm64_encrypt_blocks:
+.cfi_startproc	
+.byte	243,15,30,250
 	movl	240(%rcx),%eax
 	movdqu	(%r8),%xmm6
 	movdqa	.Lincrement64(%rip),%xmm9
@@ -958,11 +963,14 @@ aesni_ccm64_encrypt_blocks:
 	pxor	%xmm8,%xmm8
 	pxor	%xmm6,%xmm6
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_ccm64_encrypt_blocks,.-aesni_ccm64_encrypt_blocks
 .globl	aesni_ccm64_decrypt_blocks
 .type	aesni_ccm64_decrypt_blocks,@function
 .align	16
 aesni_ccm64_decrypt_blocks:
+.cfi_startproc	
+.byte	243,15,30,250
 	movl	240(%rcx),%eax
 	movups	(%r8),%xmm6
 	movdqu	(%r9),%xmm3
@@ -1055,12 +1063,14 @@ aesni_ccm64_decrypt_blocks:
 	pxor	%xmm8,%xmm8
 	pxor	%xmm6,%xmm6
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_ccm64_decrypt_blocks,.-aesni_ccm64_decrypt_blocks
 .globl	aesni_ctr32_encrypt_blocks
 .type	aesni_ctr32_encrypt_blocks,@function
 .align	16
 aesni_ctr32_encrypt_blocks:
 .cfi_startproc	
+.byte	243,15,30,250
 	cmpq	$1,%rdx
 	jne	.Lctr32_bulk
 
@@ -1639,6 +1649,7 @@ aesni_ctr32_encrypt_blocks:
 .align	16
 aesni_xts_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	leaq	(%rsp),%r11
 .cfi_def_cfa_register	%r11
 	pushq	%rbp
@@ -2109,6 +2120,7 @@ aesni_xts_encrypt:
 .align	16
 aesni_xts_decrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	leaq	(%rsp),%r11
 .cfi_def_cfa_register	%r11
 	pushq	%rbp
@@ -2616,6 +2628,7 @@ aesni_xts_decrypt:
 .align	32
 aesni_ocb_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	leaq	(%rsp),%rax
 	pushq	%rbx
 .cfi_adjust_cfa_offset	8
@@ -2829,6 +2842,7 @@ aesni_ocb_encrypt:
 .type	__ocb_encrypt6,@function
 .align	32
 __ocb_encrypt6:
+.cfi_startproc	
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -2926,11 +2940,13 @@ __ocb_encrypt6:
 .byte	102,65,15,56,221,246
 .byte	102,65,15,56,221,255
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	__ocb_encrypt6,.-__ocb_encrypt6
 
 .type	__ocb_encrypt4,@function
 .align	32
 __ocb_encrypt4:
+.cfi_startproc	
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -2995,11 +3011,13 @@ __ocb_encrypt4:
 .byte	102,65,15,56,221,228
 .byte	102,65,15,56,221,237
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	__ocb_encrypt4,.-__ocb_encrypt4
 
 .type	__ocb_encrypt1,@function
 .align	32
 __ocb_encrypt1:
+.cfi_startproc	
 	pxor	%xmm15,%xmm7
 	pxor	%xmm9,%xmm7
 	pxor	%xmm2,%xmm8
@@ -3030,6 +3048,7 @@ __ocb_encrypt1:
 
 .byte	102,15,56,221,215
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	__ocb_encrypt1,.-__ocb_encrypt1
 
 .globl	aesni_ocb_decrypt
@@ -3037,6 +3056,7 @@ __ocb_encrypt1:
 .align	32
 aesni_ocb_decrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	leaq	(%rsp),%rax
 	pushq	%rbx
 .cfi_adjust_cfa_offset	8
@@ -3272,6 +3292,7 @@ aesni_ocb_decrypt:
 .type	__ocb_decrypt6,@function
 .align	32
 __ocb_decrypt6:
+.cfi_startproc	
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3363,11 +3384,13 @@ __ocb_decrypt6:
 .byte	102,65,15,56,223,246
 .byte	102,65,15,56,223,255
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	__ocb_decrypt6,.-__ocb_decrypt6
 
 .type	__ocb_decrypt4,@function
 .align	32
 __ocb_decrypt4:
+.cfi_startproc	
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3428,11 +3451,13 @@ __ocb_decrypt4:
 .byte	102,65,15,56,223,228
 .byte	102,65,15,56,223,237
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	__ocb_decrypt4,.-__ocb_decrypt4
 
 .type	__ocb_decrypt1,@function
 .align	32
 __ocb_decrypt1:
+.cfi_startproc	
 	pxor	%xmm15,%xmm7
 	pxor	%xmm9,%xmm7
 	pxor	%xmm7,%xmm2
@@ -3462,12 +3487,14 @@ __ocb_decrypt1:
 
 .byte	102,15,56,223,215
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	__ocb_decrypt1,.-__ocb_decrypt1
 .globl	aesni_cbc_encrypt
 .type	aesni_cbc_encrypt,@function
 .align	16
 aesni_cbc_encrypt:
 .cfi_startproc	
+.byte	243,15,30,250
 	testq	%rdx,%rdx
 	jz	.Lcbc_ret
 
@@ -4400,7 +4427,6 @@ __aesni_set_encrypt_key:
 	addq	$8,%rsp
 .cfi_adjust_cfa_offset	-8
 	.byte	0xf3,0xc3
-.cfi_endproc	
 .LSEH_end_set_encrypt_key:
 
 .align	16
@@ -4471,6 +4497,7 @@ __aesni_set_encrypt_key:
 	shufps	$170,%xmm1,%xmm1
 	xorps	%xmm1,%xmm2
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	aesni_set_encrypt_key,.-aesni_set_encrypt_key
 .size	__aesni_set_encrypt_key,.-__aesni_set_encrypt_key
 .align	64
@@ -4495,5 +4522,26 @@ __aesni_set_encrypt_key:
 
 .byte	65,69,83,32,102,111,114,32,73,110,116,101,108,32,65,69,83,45,78,73,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	64
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/e_padlock-x86.s b/lib/accelerated/x86/elf/e_padlock-x86.s
index ed8681ee4..dd56518f6 100644
--- a/lib/accelerated/x86/elf/e_padlock-x86.s
+++ b/lib/accelerated/x86/elf/e_padlock-x86.s
@@ -1,4 +1,4 @@
-# Copyright (c) 2011-2013, Andy Polyakov <appro@openssl.org>
+# Copyright (c) 2011-2016, Andy Polyakov <appro@openssl.org>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -37,13 +37,13 @@
 #
 # *** This file is auto-generated ***
 #
-.file	"devel/perlasm/e_padlock-x86.s"
 .text
 .globl	padlock_capability
 .type	padlock_capability,@function
 .align	16
 padlock_capability:
 .L_padlock_capability_begin:
+.byte	243,15,30,251
 	pushl	%ebx
 	pushfl
 	popl	%eax
@@ -60,11 +60,20 @@ padlock_capability:
 	.byte	0x0f,0xa2
 	xorl	%eax,%eax
 	cmpl	$0x746e6543,%ebx
-	jne	.L000noluck
+	jne	.L001zhaoxin
 	cmpl	$0x48727561,%edx
 	jne	.L000noluck
 	cmpl	$0x736c7561,%ecx
 	jne	.L000noluck
+	jmp	.L002zhaoxinEnd
+.L001zhaoxin:
+	cmpl	$0x68532020,%ebx
+	jne	.L000noluck
+	cmpl	$0x68676e61,%edx
+	jne	.L000noluck
+	cmpl	$0x20206961,%ecx
+	jne	.L000noluck
+.L002zhaoxinEnd:
 	movl	$3221225472,%eax
 	.byte	0x0f,0xa2
 	movl	%eax,%edx
@@ -95,15 +104,16 @@ padlock_capability:
 .align	16
 padlock_key_bswap:
 .L_padlock_key_bswap_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%edx
 	movl	240(%edx),%ecx
-.L001bswap_loop:
+.L003bswap_loop:
 	movl	(%edx),%eax
 	bswap	%eax
 	movl	%eax,(%edx)
 	leal	4(%edx),%edx
 	subl	$1,%ecx
-	jnz	.L001bswap_loop
+	jnz	.L003bswap_loop
 	ret
 .size	padlock_key_bswap,.-.L_padlock_key_bswap_begin
 .globl	padlock_verify_context
@@ -111,25 +121,27 @@ padlock_key_bswap:
 .align	16
 padlock_verify_context:
 .L_padlock_verify_context_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%edx
-	leal	.Lpadlock_saved_context-.L002verify_pic_point,%eax
+	leal	.Lpadlock_saved_context-.L004verify_pic_point,%eax
 	pushfl
 	call	_padlock_verify_ctx
-.L002verify_pic_point:
+.L004verify_pic_point:
 	leal	4(%esp),%esp
 	ret
 .size	padlock_verify_context,.-.L_padlock_verify_context_begin
 .type	_padlock_verify_ctx,@function
 .align	16
 _padlock_verify_ctx:
+.byte	243,15,30,251
 	addl	(%esp),%eax
 	btl	$30,4(%esp)
-	jnc	.L003verified
+	jnc	.L005verified
 	cmpl	(%eax),%edx
-	je	.L003verified
+	je	.L005verified
 	pushfl
 	popfl
-.L003verified:
+.L005verified:
 	movl	%edx,(%eax)
 	ret
 .size	_padlock_verify_ctx,.-_padlock_verify_ctx
@@ -138,6 +150,7 @@ _padlock_verify_ctx:
 .align	16
 padlock_reload_key:
 .L_padlock_reload_key_begin:
+.byte	243,15,30,251
 	pushfl
 	popfl
 	ret
@@ -147,6 +160,7 @@ padlock_reload_key:
 .align	16
 padlock_aes_block:
 .L_padlock_aes_block_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	pushl	%ebx
@@ -167,6 +181,7 @@ padlock_aes_block:
 .align	16
 padlock_ecb_encrypt:
 .L_padlock_ecb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -176,25 +191,25 @@ padlock_ecb_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L004ecb_abort
+	jnz	.L006ecb_abort
 	testl	$15,%ecx
-	jnz	.L004ecb_abort
-	leal	.Lpadlock_saved_context-.L005ecb_pic_point,%eax
+	jnz	.L006ecb_abort
+	leal	.Lpadlock_saved_context-.L007ecb_pic_point,%eax
 	pushfl
 	cld
 	call	_padlock_verify_ctx
-.L005ecb_pic_point:
+.L007ecb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L006ecb_aligned
+	jnz	.L008ecb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L006ecb_aligned
+	jnz	.L008ecb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -213,7 +228,7 @@ padlock_ecb_encrypt:
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
 	cmpl	%ebx,%ecx
-	ja	.L007ecb_loop
+	ja	.L009ecb_loop
 	movl	%esi,%eax
 	cmpl	%esp,%ebp
 	cmovel	%edi,%eax
@@ -224,10 +239,10 @@ padlock_ecb_encrypt:
 	movl	$-128,%eax
 	cmovael	%ebx,%eax
 	andl	%eax,%ebx
-	jz	.L008ecb_unaligned_tail
-	jmp	.L007ecb_loop
+	jz	.L010ecb_unaligned_tail
+	jmp	.L009ecb_loop
 .align	16
-.L007ecb_loop:
+.L009ecb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -236,13 +251,13 @@ padlock_ecb_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L009ecb_inp_aligned
+	jz	.L011ecb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L009ecb_inp_aligned:
+.L011ecb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -250,23 +265,23 @@ padlock_ecb_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L010ecb_out_aligned
+	jz	.L012ecb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L010ecb_out_aligned:
+.L012ecb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jz	.L011ecb_break
+	jz	.L013ecb_break
 	cmpl	%ebx,%ecx
-	jae	.L007ecb_loop
-.L008ecb_unaligned_tail:
+	jae	.L009ecb_loop
+.L010ecb_unaligned_tail:
 	xorl	%eax,%eax
 	cmpl	%ebp,%esp
 	cmovel	%ecx,%eax
@@ -279,24 +294,24 @@ padlock_ecb_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L007ecb_loop
+	jmp	.L009ecb_loop
 .align	16
-.L011ecb_break:
+.L013ecb_break:
 	cmpl	%ebp,%esp
-	je	.L012ecb_done
+	je	.L014ecb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L013ecb_bzero:
+.L015ecb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L013ecb_bzero
-.L012ecb_done:
+	ja	.L015ecb_bzero
+.L014ecb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L014ecb_exit
+	jmp	.L016ecb_exit
 .align	16
-.L006ecb_aligned:
+.L008ecb_aligned:
 	leal	(%esi,%ecx,1),%ebp
 	negl	%ebp
 	andl	$4095,%ebp
@@ -306,14 +321,14 @@ padlock_ecb_encrypt:
 	cmovael	%eax,%ebp
 	andl	%ecx,%ebp
 	subl	%ebp,%ecx
-	jz	.L015ecb_aligned_tail
+	jz	.L017ecb_aligned_tail
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,200
 	testl	%ebp,%ebp
-	jz	.L014ecb_exit
-.L015ecb_aligned_tail:
+	jz	.L016ecb_exit
+.L017ecb_aligned_tail:
 	movl	%ebp,%ecx
 	leal	-24(%esp),%ebp
 	movl	%ebp,%esp
@@ -330,11 +345,11 @@ padlock_ecb_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L007ecb_loop
-.L014ecb_exit:
+	jmp	.L009ecb_loop
+.L016ecb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L004ecb_abort:
+.L006ecb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -346,6 +361,7 @@ padlock_ecb_encrypt:
 .align	16
 padlock_cbc_encrypt:
 .L_padlock_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -355,25 +371,25 @@ padlock_cbc_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L016cbc_abort
+	jnz	.L018cbc_abort
 	testl	$15,%ecx
-	jnz	.L016cbc_abort
-	leal	.Lpadlock_saved_context-.L017cbc_pic_point,%eax
+	jnz	.L018cbc_abort
+	leal	.Lpadlock_saved_context-.L019cbc_pic_point,%eax
 	pushfl
 	cld
 	call	_padlock_verify_ctx
-.L017cbc_pic_point:
+.L019cbc_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L018cbc_aligned
+	jnz	.L020cbc_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L018cbc_aligned
+	jnz	.L020cbc_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -392,7 +408,7 @@ padlock_cbc_encrypt:
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
 	cmpl	%ebx,%ecx
-	ja	.L019cbc_loop
+	ja	.L021cbc_loop
 	movl	%esi,%eax
 	cmpl	%esp,%ebp
 	cmovel	%edi,%eax
@@ -403,10 +419,10 @@ padlock_cbc_encrypt:
 	movl	$-64,%eax
 	cmovael	%ebx,%eax
 	andl	%eax,%ebx
-	jz	.L020cbc_unaligned_tail
-	jmp	.L019cbc_loop
+	jz	.L022cbc_unaligned_tail
+	jmp	.L021cbc_loop
 .align	16
-.L019cbc_loop:
+.L021cbc_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -415,13 +431,13 @@ padlock_cbc_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L021cbc_inp_aligned
+	jz	.L023cbc_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L021cbc_inp_aligned:
+.L023cbc_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -431,23 +447,23 @@ padlock_cbc_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L022cbc_out_aligned
+	jz	.L024cbc_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L022cbc_out_aligned:
+.L024cbc_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jz	.L023cbc_break
+	jz	.L025cbc_break
 	cmpl	%ebx,%ecx
-	jae	.L019cbc_loop
-.L020cbc_unaligned_tail:
+	jae	.L021cbc_loop
+.L022cbc_unaligned_tail:
 	xorl	%eax,%eax
 	cmpl	%ebp,%esp
 	cmovel	%ecx,%eax
@@ -460,24 +476,24 @@ padlock_cbc_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L019cbc_loop
+	jmp	.L021cbc_loop
 .align	16
-.L023cbc_break:
+.L025cbc_break:
 	cmpl	%ebp,%esp
-	je	.L024cbc_done
+	je	.L026cbc_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L025cbc_bzero:
+.L027cbc_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L025cbc_bzero
-.L024cbc_done:
+	ja	.L027cbc_bzero
+.L026cbc_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L026cbc_exit
+	jmp	.L028cbc_exit
 .align	16
-.L018cbc_aligned:
+.L020cbc_aligned:
 	leal	(%esi,%ecx,1),%ebp
 	negl	%ebp
 	andl	$4095,%ebp
@@ -487,7 +503,7 @@ padlock_cbc_encrypt:
 	cmovael	%eax,%ebp
 	andl	%ecx,%ebp
 	subl	%ebp,%ecx
-	jz	.L027cbc_aligned_tail
+	jz	.L029cbc_aligned_tail
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -495,8 +511,8 @@ padlock_cbc_encrypt:
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
 	testl	%ebp,%ebp
-	jz	.L026cbc_exit
-.L027cbc_aligned_tail:
+	jz	.L028cbc_exit
+.L029cbc_aligned_tail:
 	movl	%ebp,%ecx
 	leal	-24(%esp),%ebp
 	movl	%ebp,%esp
@@ -513,11 +529,11 @@ padlock_cbc_encrypt:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	.L019cbc_loop
-.L026cbc_exit:
+	jmp	.L021cbc_loop
+.L028cbc_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L016cbc_abort:
+.L018cbc_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -529,6 +545,7 @@ padlock_cbc_encrypt:
 .align	16
 padlock_cfb_encrypt:
 .L_padlock_cfb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -538,25 +555,25 @@ padlock_cfb_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L028cfb_abort
+	jnz	.L030cfb_abort
 	testl	$15,%ecx
-	jnz	.L028cfb_abort
-	leal	.Lpadlock_saved_context-.L029cfb_pic_point,%eax
+	jnz	.L030cfb_abort
+	leal	.Lpadlock_saved_context-.L031cfb_pic_point,%eax
 	pushfl
 	cld
 	call	_padlock_verify_ctx
-.L029cfb_pic_point:
+.L031cfb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L030cfb_aligned
+	jnz	.L032cfb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L030cfb_aligned
+	jnz	.L032cfb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -574,9 +591,9 @@ padlock_cfb_encrypt:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	.L031cfb_loop
+	jmp	.L033cfb_loop
 .align	16
-.L031cfb_loop:
+.L033cfb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -585,13 +602,13 @@ padlock_cfb_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L032cfb_inp_aligned
+	jz	.L034cfb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L032cfb_inp_aligned:
+.L034cfb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -601,45 +618,45 @@ padlock_cfb_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L033cfb_out_aligned
+	jz	.L035cfb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L033cfb_out_aligned:
+.L035cfb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	.L031cfb_loop
+	jnz	.L033cfb_loop
 	cmpl	%ebp,%esp
-	je	.L034cfb_done
+	je	.L036cfb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L035cfb_bzero:
+.L037cfb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L035cfb_bzero
-.L034cfb_done:
+	ja	.L037cfb_bzero
+.L036cfb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L036cfb_exit
+	jmp	.L038cfb_exit
 .align	16
-.L030cfb_aligned:
+.L032cfb_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,224
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
-.L036cfb_exit:
+.L038cfb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L028cfb_abort:
+.L030cfb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -651,6 +668,7 @@ padlock_cfb_encrypt:
 .align	16
 padlock_ofb_encrypt:
 .L_padlock_ofb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -660,25 +678,25 @@ padlock_ofb_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L037ofb_abort
+	jnz	.L039ofb_abort
 	testl	$15,%ecx
-	jnz	.L037ofb_abort
-	leal	.Lpadlock_saved_context-.L038ofb_pic_point,%eax
+	jnz	.L039ofb_abort
+	leal	.Lpadlock_saved_context-.L040ofb_pic_point,%eax
 	pushfl
 	cld
 	call	_padlock_verify_ctx
-.L038ofb_pic_point:
+.L040ofb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	.L039ofb_aligned
+	jnz	.L041ofb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	.L039ofb_aligned
+	jnz	.L041ofb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -696,9 +714,9 @@ padlock_ofb_encrypt:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	.L040ofb_loop
+	jmp	.L042ofb_loop
 .align	16
-.L040ofb_loop:
+.L042ofb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -707,13 +725,13 @@ padlock_ofb_encrypt:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	.L041ofb_inp_aligned
+	jz	.L043ofb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-.L041ofb_inp_aligned:
+.L043ofb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -723,45 +741,45 @@ padlock_ofb_encrypt:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	.L042ofb_out_aligned
+	jz	.L044ofb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-.L042ofb_out_aligned:
+.L044ofb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	.L040ofb_loop
+	jnz	.L042ofb_loop
 	cmpl	%ebp,%esp
-	je	.L043ofb_done
+	je	.L045ofb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L044ofb_bzero:
+.L046ofb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L044ofb_bzero
-.L043ofb_done:
+	ja	.L046ofb_bzero
+.L045ofb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	.L045ofb_exit
+	jmp	.L047ofb_exit
 .align	16
-.L039ofb_aligned:
+.L041ofb_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,232
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
-.L045ofb_exit:
+.L047ofb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-.L037ofb_abort:
+.L039ofb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -773,6 +791,7 @@ padlock_ofb_encrypt:
 .align	16
 padlock_ctr32_encrypt:
 .L_padlock_ctr32_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -782,14 +801,14 @@ padlock_ctr32_encrypt:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	.L046ctr32_abort
+	jnz	.L048ctr32_abort
 	testl	$15,%ecx
-	jnz	.L046ctr32_abort
-	leal	.Lpadlock_saved_context-.L047ctr32_pic_point,%eax
+	jnz	.L048ctr32_abort
+	leal	.Lpadlock_saved_context-.L049ctr32_pic_point,%eax
 	pushfl
 	cld
 	call	_padlock_verify_ctx
-.L047ctr32_pic_point:
+.L049ctr32_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	movq	-16(%edx),%mm0
@@ -809,9 +828,9 @@ padlock_ctr32_encrypt:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	.L048ctr32_loop
+	jmp	.L050ctr32_loop
 .align	16
-.L048ctr32_loop:
+.L050ctr32_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -820,7 +839,7 @@ padlock_ctr32_encrypt:
 	movl	-4(%edx),%ecx
 	xorl	%edi,%edi
 	movl	-8(%edx),%eax
-.L049ctr32_prepare:
+.L051ctr32_prepare:
 	movl	%ecx,12(%esp,%edi,1)
 	bswap	%ecx
 	movq	%mm0,(%esp,%edi,1)
@@ -829,7 +848,7 @@ padlock_ctr32_encrypt:
 	bswap	%ecx
 	leal	16(%edi),%edi
 	cmpl	%ebx,%edi
-	jb	.L049ctr32_prepare
+	jb	.L051ctr32_prepare
 	movl	%ecx,-4(%edx)
 	leal	(%esp),%esi
 	leal	(%esp),%edi
@@ -842,33 +861,33 @@ padlock_ctr32_encrypt:
 	movl	12(%ebp),%ebx
 	movl	4(%ebp),%esi
 	xorl	%ecx,%ecx
-.L050ctr32_xor:
+.L052ctr32_xor:
 	movups	(%esi,%ecx,1),%xmm1
 	leal	16(%ecx),%ecx
 	pxor	-16(%esp,%ecx,1),%xmm1
 	movups	%xmm1,-16(%edi,%ecx,1)
 	cmpl	%ebx,%ecx
-	jb	.L050ctr32_xor
+	jb	.L052ctr32_xor
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	.L048ctr32_loop
+	jnz	.L050ctr32_loop
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-.L051ctr32_bzero:
+.L053ctr32_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	.L051ctr32_bzero
-.L052ctr32_done:
+	ja	.L053ctr32_bzero
+.L054ctr32_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
 	movl	$1,%eax
 	leal	4(%esp),%esp
 	emms
-.L046ctr32_abort:
+.L048ctr32_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -880,6 +899,7 @@ padlock_ctr32_encrypt:
 .align	16
 padlock_xstore:
 .L_padlock_xstore_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	movl	8(%esp),%edi
 	movl	12(%esp),%edx
@@ -890,14 +910,15 @@ padlock_xstore:
 .type	_win32_segv_handler,@function
 .align	16
 _win32_segv_handler:
+.byte	243,15,30,251
 	movl	$1,%eax
 	movl	4(%esp),%edx
 	movl	12(%esp),%ecx
 	cmpl	$3221225477,(%edx)
-	jne	.L053ret
+	jne	.L055ret
 	addl	$4,184(%ecx)
 	movl	$0,%eax
-.L053ret:
+.L055ret:
 	ret
 .size	_win32_segv_handler,.-_win32_segv_handler
 .globl	padlock_sha1_oneshot
@@ -905,6 +926,7 @@ _win32_segv_handler:
 .align	16
 padlock_sha1_oneshot:
 .L_padlock_sha1_oneshot_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	xorl	%eax,%eax
@@ -936,6 +958,7 @@ padlock_sha1_oneshot:
 .align	16
 padlock_sha1_blocks:
 .L_padlock_sha1_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -966,6 +989,7 @@ padlock_sha1_blocks:
 .align	16
 padlock_sha256_oneshot:
 .L_padlock_sha256_oneshot_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	xorl	%eax,%eax
@@ -997,6 +1021,7 @@ padlock_sha256_oneshot:
 .align	16
 padlock_sha256_blocks:
 .L_padlock_sha256_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -1027,6 +1052,7 @@ padlock_sha256_blocks:
 .align	16
 padlock_sha512_blocks:
 .L_padlock_sha512_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -1069,7 +1095,21 @@ padlock_sha512_blocks:
 .Lpadlock_saved_context:
 .long	0
 
+	.section ".note.gnu.property", "a"
+	.p2align 2
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 2
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 2
+4:
 
 .section .note.GNU-stack,"",%progbits
-
-
diff --git a/lib/accelerated/x86/elf/e_padlock-x86_64.s b/lib/accelerated/x86/elf/e_padlock-x86_64.s
index c161f0a73..f92da756c 100644
--- a/lib/accelerated/x86/elf/e_padlock-x86_64.s
+++ b/lib/accelerated/x86/elf/e_padlock-x86_64.s
@@ -1,4 +1,4 @@
-# Copyright (c) 2011-2013, Andy Polyakov <appro@openssl.org>
+# Copyright (c) 2011-2016, Andy Polyakov <appro@openssl.org>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -42,36 +42,50 @@
 .type	padlock_capability,@function
 .align	16
 padlock_capability:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rbx,%r8
 	xorl	%eax,%eax
 	cpuid
 	xorl	%eax,%eax
-	cmpl	$1953391939,%ebx
+	cmpl	$0x746e6543,%ebx
+	jne	.Lzhaoxin
+	cmpl	$0x48727561,%edx
 	jne	.Lnoluck
-	cmpl	$1215460705,%edx
+	cmpl	$0x736c7561,%ecx
 	jne	.Lnoluck
-	cmpl	$1936487777,%ecx
+	jmp	.LzhaoxinEnd
+.Lzhaoxin:
+	cmpl	$0x68532020,%ebx
 	jne	.Lnoluck
-	movl	$3221225472,%eax
+	cmpl	$0x68676e61,%edx
+	jne	.Lnoluck
+	cmpl	$0x20206961,%ecx
+	jne	.Lnoluck
+.LzhaoxinEnd:
+	movl	$0xC0000000,%eax
 	cpuid
 	movl	%eax,%edx
 	xorl	%eax,%eax
-	cmpl	$3221225473,%edx
+	cmpl	$0xC0000001,%edx
 	jb	.Lnoluck
-	movl	$3221225473,%eax
+	movl	$0xC0000001,%eax
 	cpuid
 	movl	%edx,%eax
-	andl	$4294967279,%eax
-	orl	$16,%eax
+	andl	$0xffffffef,%eax
+	orl	$0x10,%eax
 .Lnoluck:
 	movq	%r8,%rbx
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_capability,.-padlock_capability
 
 .globl	padlock_key_bswap
 .type	padlock_key_bswap,@function
 .align	16
 padlock_key_bswap:
+.cfi_startproc	
+.byte	243,15,30,250
 	movl	240(%rdi),%edx
 .Lbswap_loop:
 	movl	(%rdi),%eax
@@ -81,23 +95,29 @@ padlock_key_bswap:
 	subl	$1,%edx
 	jnz	.Lbswap_loop
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_key_bswap,.-padlock_key_bswap
 
 .globl	padlock_verify_context
 .type	padlock_verify_context,@function
 .align	16
 padlock_verify_context:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rdi,%rdx
 	pushf
 	leaq	.Lpadlock_saved_context(%rip),%rax
 	call	_padlock_verify_ctx
 	leaq	8(%rsp),%rsp
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_verify_context,.-padlock_verify_context
 
 .type	_padlock_verify_ctx,@function
 .align	16
 _padlock_verify_ctx:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	8(%rsp),%r8
 	btq	$30,%r8
 	jnc	.Lverified
@@ -108,43 +128,55 @@ _padlock_verify_ctx:
 .Lverified:
 	movq	%rdx,(%rax)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	_padlock_verify_ctx,.-_padlock_verify_ctx
 
 .globl	padlock_reload_key
 .type	padlock_reload_key,@function
 .align	16
 padlock_reload_key:
+.cfi_startproc	
+.byte	243,15,30,250
 	pushf
 	popf
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_reload_key,.-padlock_reload_key
 
 .globl	padlock_aes_block
 .type	padlock_aes_block,@function
 .align	16
 padlock_aes_block:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rbx,%r8
 	movq	$1,%rcx
 	leaq	32(%rdx),%rbx
 	leaq	16(%rdx),%rdx
-.byte	0xf3,0x0f,0xa7,0xc8	
+.byte	0xf3,0x0f,0xa7,0xc8
 	movq	%r8,%rbx
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_aes_block,.-padlock_aes_block
 
 .globl	padlock_xstore
 .type	padlock_xstore,@function
 .align	16
 padlock_xstore:
+.cfi_startproc	
+.byte	243,15,30,250
 	movl	%esi,%edx
-.byte	0x0f,0xa7,0xc0		
+.byte	0x0f,0xa7,0xc0
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_xstore,.-padlock_xstore
 
 .globl	padlock_sha1_oneshot
 .type	padlock_sha1_oneshot,@function
 .align	16
 padlock_sha1_oneshot:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -154,19 +186,22 @@ padlock_sha1_oneshot:
 	movq	%rsp,%rdi
 	movl	%eax,16(%rsp)
 	xorq	%rax,%rax
-.byte	0xf3,0x0f,0xa6,0xc8	
+.byte	0xf3,0x0f,0xa6,0xc8
 	movaps	(%rsp),%xmm0
 	movl	16(%rsp),%eax
 	addq	$128+8,%rsp
 	movups	%xmm0,(%rdx)
 	movl	%eax,16(%rdx)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_sha1_oneshot,.-padlock_sha1_oneshot
 
 .globl	padlock_sha1_blocks
 .type	padlock_sha1_blocks,@function
 .align	16
 padlock_sha1_blocks:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -176,19 +211,22 @@ padlock_sha1_blocks:
 	movq	%rsp,%rdi
 	movl	%eax,16(%rsp)
 	movq	$-1,%rax
-.byte	0xf3,0x0f,0xa6,0xc8	
+.byte	0xf3,0x0f,0xa6,0xc8
 	movaps	(%rsp),%xmm0
 	movl	16(%rsp),%eax
 	addq	$128+8,%rsp
 	movups	%xmm0,(%rdx)
 	movl	%eax,16(%rdx)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_sha1_blocks,.-padlock_sha1_blocks
 
 .globl	padlock_sha256_oneshot
 .type	padlock_sha256_oneshot,@function
 .align	16
 padlock_sha256_oneshot:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -198,19 +236,22 @@ padlock_sha256_oneshot:
 	movq	%rsp,%rdi
 	movaps	%xmm1,16(%rsp)
 	xorq	%rax,%rax
-.byte	0xf3,0x0f,0xa6,0xd0	
+.byte	0xf3,0x0f,0xa6,0xd0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	addq	$128+8,%rsp
 	movups	%xmm0,(%rdx)
 	movups	%xmm1,16(%rdx)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_sha256_oneshot,.-padlock_sha256_oneshot
 
 .globl	padlock_sha256_blocks
 .type	padlock_sha256_blocks,@function
 .align	16
 padlock_sha256_blocks:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -220,19 +261,22 @@ padlock_sha256_blocks:
 	movq	%rsp,%rdi
 	movaps	%xmm1,16(%rsp)
 	movq	$-1,%rax
-.byte	0xf3,0x0f,0xa6,0xd0	
+.byte	0xf3,0x0f,0xa6,0xd0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	addq	$128+8,%rsp
 	movups	%xmm0,(%rdx)
 	movups	%xmm1,16(%rdx)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_sha256_blocks,.-padlock_sha256_blocks
 
 .globl	padlock_sha512_blocks
 .type	padlock_sha512_blocks,@function
 .align	16
 padlock_sha512_blocks:
+.cfi_startproc	
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -245,7 +289,7 @@ padlock_sha512_blocks:
 	movaps	%xmm1,16(%rsp)
 	movaps	%xmm2,32(%rsp)
 	movaps	%xmm3,48(%rsp)
-.byte	0xf3,0x0f,0xa6,0xe0	
+.byte	0xf3,0x0f,0xa6,0xe0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	movaps	32(%rsp),%xmm2
@@ -256,11 +300,14 @@ padlock_sha512_blocks:
 	movups	%xmm2,32(%rdx)
 	movups	%xmm3,48(%rdx)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_sha512_blocks,.-padlock_sha512_blocks
 .globl	padlock_ecb_encrypt
 .type	padlock_ecb_encrypt,@function
 .align	16
 padlock_ecb_encrypt:
+.cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -278,9 +325,9 @@ padlock_ecb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lecb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lecb_aligned
@@ -304,7 +351,7 @@ padlock_ecb_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$128,%rax
 	movq	$-128,%rax
 	cmovaeq	%rbx,%rax
@@ -320,12 +367,12 @@ padlock_ecb_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lecb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -333,15 +380,15 @@ padlock_ecb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,200	
+.byte	0xf3,0x0f,0xa7,200
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lecb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lecb_out_aligned:
 	movq	%r9,%rsi
@@ -362,7 +409,7 @@ padlock_ecb_encrypt:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -388,7 +435,7 @@ padlock_ecb_encrypt:
 .Lecb_aligned:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$128,%rbp
 	movq	$128-1,%rbp
@@ -399,7 +446,7 @@ padlock_ecb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,200	
+.byte	0xf3,0x0f,0xa7,200
 	testq	%rbp,%rbp
 	jz	.Lecb_exit
 
@@ -411,7 +458,7 @@ padlock_ecb_encrypt:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -423,11 +470,14 @@ padlock_ecb_encrypt:
 	popq	%rbx
 	popq	%rbp
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_ecb_encrypt,.-padlock_ecb_encrypt
 .globl	padlock_cbc_encrypt
 .type	padlock_cbc_encrypt,@function
 .align	16
 padlock_cbc_encrypt:
+.cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -445,9 +495,9 @@ padlock_cbc_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lcbc_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lcbc_aligned
@@ -471,7 +521,7 @@ padlock_cbc_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$64,%rax
 	movq	$-64,%rax
 	cmovaeq	%rbx,%rax
@@ -487,12 +537,12 @@ padlock_cbc_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lcbc_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -500,17 +550,17 @@ padlock_cbc_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,208	
+.byte	0xf3,0x0f,0xa7,208
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lcbc_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lcbc_out_aligned:
 	movq	%r9,%rsi
@@ -531,7 +581,7 @@ padlock_cbc_encrypt:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -557,7 +607,7 @@ padlock_cbc_encrypt:
 .Lcbc_aligned:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$64,%rbp
 	movq	$64-1,%rbp
@@ -568,7 +618,7 @@ padlock_cbc_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,208	
+.byte	0xf3,0x0f,0xa7,208
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	testq	%rbp,%rbp
@@ -582,7 +632,7 @@ padlock_cbc_encrypt:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -594,11 +644,14 @@ padlock_cbc_encrypt:
 	popq	%rbx
 	popq	%rbp
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_cbc_encrypt,.-padlock_cbc_encrypt
 .globl	padlock_cfb_encrypt
 .type	padlock_cfb_encrypt,@function
 .align	16
 padlock_cfb_encrypt:
+.cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -616,9 +669,9 @@ padlock_cfb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lcfb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lcfb_aligned
@@ -645,12 +698,12 @@ padlock_cfb_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lcfb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -658,17 +711,17 @@ padlock_cfb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,224	
+.byte	0xf3,0x0f,0xa7,224
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lcfb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lcfb_out_aligned:
 	movq	%r9,%rsi
@@ -698,7 +751,7 @@ padlock_cfb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,224	
+.byte	0xf3,0x0f,0xa7,224
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 .Lcfb_exit:
@@ -708,11 +761,14 @@ padlock_cfb_encrypt:
 	popq	%rbx
 	popq	%rbp
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_cfb_encrypt,.-padlock_cfb_encrypt
 .globl	padlock_ofb_encrypt
 .type	padlock_ofb_encrypt,@function
 .align	16
 padlock_ofb_encrypt:
+.cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -730,9 +786,9 @@ padlock_ofb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lofb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lofb_aligned
@@ -759,12 +815,12 @@ padlock_ofb_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lofb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -772,17 +828,17 @@ padlock_ofb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,232	
+.byte	0xf3,0x0f,0xa7,232
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lofb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lofb_out_aligned:
 	movq	%r9,%rsi
@@ -812,7 +868,7 @@ padlock_ofb_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,232	
+.byte	0xf3,0x0f,0xa7,232
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 .Lofb_exit:
@@ -822,11 +878,14 @@ padlock_ofb_encrypt:
 	popq	%rbx
 	popq	%rbp
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_ofb_encrypt,.-padlock_ofb_encrypt
 .globl	padlock_ctr32_encrypt
 .type	padlock_ctr32_encrypt,@function
 .align	16
 padlock_ctr32_encrypt:
+.cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -844,9 +903,9 @@ padlock_ctr32_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	.Lctr32_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	.Lctr32_aligned
@@ -881,7 +940,7 @@ padlock_ctr32_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$32,%rax
 	movq	$-32,%rax
 	cmovaeq	%rbx,%rax
@@ -897,12 +956,12 @@ padlock_ctr32_encrypt:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	.Lctr32_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -910,23 +969,23 @@ padlock_ctr32_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 	movl	-4(%rdx),%eax
-	testl	$4294901760,%eax
+	testl	$0xffff0000,%eax
 	jnz	.Lctr32_no_carry
 	bswapl	%eax
-	addl	$65536,%eax
+	addl	$0x10000,%eax
 	bswapl	%eax
 	movl	%eax,-4(%rdx)
 .Lctr32_no_carry:
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	.Lctr32_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 .Lctr32_out_aligned:
 	movq	%r9,%rsi
@@ -944,7 +1003,7 @@ padlock_ctr32_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$32,%rax
 	movq	$-32,%rax
 	cmovaeq	%rbx,%rax
@@ -959,7 +1018,7 @@ padlock_ctr32_encrypt:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -986,7 +1045,7 @@ padlock_ctr32_encrypt:
 	movl	-4(%rdx),%eax
 	bswapl	%eax
 	negl	%eax
-	andl	$65535,%eax
+	andl	$0xffff,%eax
 	movq	$1048576,%rbx
 	shll	$4,%eax
 	cmovzq	%rbx,%rax
@@ -1003,11 +1062,11 @@ padlock_ctr32_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 
 	movl	-4(%rdx),%eax
 	bswapl	%eax
-	addl	$65536,%eax
+	addl	$0x10000,%eax
 	bswapl	%eax
 	movl	%eax,-4(%rdx)
 
@@ -1021,7 +1080,7 @@ padlock_ctr32_encrypt:
 .Lctr32_aligned_skip:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$32,%rbp
 	movq	$32-1,%rbp
@@ -1032,7 +1091,7 @@ padlock_ctr32_encrypt:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 	testq	%rbp,%rbp
 	jz	.Lctr32_exit
 
@@ -1044,7 +1103,7 @@ padlock_ctr32_encrypt:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -1056,6 +1115,7 @@ padlock_ctr32_encrypt:
 	popq	%rbx
 	popq	%rbp
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	padlock_ctr32_encrypt,.-padlock_ctr32_encrypt
 .byte	86,73,65,32,80,97,100,108,111,99,107,32,120,56,54,95,54,52,32,109,111,100,117,108,101,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	16
@@ -1063,8 +1123,26 @@ padlock_ctr32_encrypt:
 .align	8
 .Lpadlock_saved_context:
 .quad	0
-
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
-
-
diff --git a/lib/accelerated/x86/elf/ghash-x86_64.s b/lib/accelerated/x86/elf/ghash-x86_64.s
index 1e4d18b34..8da3f294c 100644
--- a/lib/accelerated/x86/elf/ghash-x86_64.s
+++ b/lib/accelerated/x86/elf/ghash-x86_64.s
@@ -45,6 +45,7 @@
 .align	16
 gcm_gmult_4bit:
 .cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbx
 .cfi_adjust_cfa_offset	8
 .cfi_offset	%rbx,-16
@@ -156,6 +157,7 @@ gcm_gmult_4bit:
 .align	16
 gcm_ghash_4bit:
 .cfi_startproc	
+.byte	243,15,30,250
 	pushq	%rbx
 .cfi_adjust_cfa_offset	8
 .cfi_offset	%rbx,-16
@@ -903,6 +905,7 @@ gcm_init_clmul:
 .align	16
 gcm_gmult_clmul:
 .cfi_startproc	
+.byte	243,15,30,250
 .L_gmult_clmul:
 	movdqu	(%rdi),%xmm0
 	movdqa	.Lbswap_mask(%rip),%xmm5
@@ -956,6 +959,7 @@ gcm_gmult_clmul:
 .align	32
 gcm_ghash_clmul:
 .cfi_startproc	
+.byte	243,15,30,250
 .L_ghash_clmul:
 	movdqa	.Lbswap_mask(%rip),%xmm10
 
@@ -1450,6 +1454,7 @@ gcm_init_avx:
 .align	32
 gcm_gmult_avx:
 .cfi_startproc	
+.byte	243,15,30,250
 	jmp	.L_gmult_clmul
 .cfi_endproc	
 .size	gcm_gmult_avx,.-gcm_gmult_avx
@@ -1458,6 +1463,7 @@ gcm_gmult_avx:
 .align	32
 gcm_ghash_avx:
 .cfi_startproc	
+.byte	243,15,30,250
 	vzeroupper
 
 	vmovdqu	(%rdi),%xmm10
@@ -1884,5 +1890,26 @@ gcm_ghash_avx:
 
 .byte	71,72,65,83,72,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	64
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/sha1-ssse3-x86.s b/lib/accelerated/x86/elf/sha1-ssse3-x86.s
index 8bfbcb6b3..57b6ba58f 100644
--- a/lib/accelerated/x86/elf/sha1-ssse3-x86.s
+++ b/lib/accelerated/x86/elf/sha1-ssse3-x86.s
@@ -43,6 +43,7 @@
 .align	16
 sha1_block_data_order:
 .L_sha1_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1417,4 +1418,21 @@ sha1_block_data_order:
 .byte	89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112
 .byte	114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 
+	.section ".note.gnu.property", "a"
+	.p2align 2
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 2
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 2
+4:
+
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s b/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s
index 1e6546e11..54095050c 100644
--- a/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/sha1-ssse3-x86_64.s
@@ -1460,8 +1460,8 @@ _shaext_shortcut:
 	pshufd	$27,%xmm1,%xmm1
 	movdqu	%xmm0,(%rdi)
 	movd	%xmm1,16(%rdi)
-.cfi_endproc	
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	sha1_block_data_order_shaext,.-sha1_block_data_order_shaext
 .type	sha1_block_data_order_ssse3,@function
 .align	16
@@ -5487,5 +5487,26 @@ K_XX_XX:
 .byte	0xf,0xe,0xd,0xc,0xb,0xa,0x9,0x8,0x7,0x6,0x5,0x4,0x3,0x2,0x1,0x0
 .byte	83,72,65,49,32,98,108,111,99,107,32,116,114,97,110,115,102,111,114,109,32,102,111,114,32,120,56,54,95,54,52,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .align	64
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/sha256-ssse3-x86.s b/lib/accelerated/x86/elf/sha256-ssse3-x86.s
index 8d9aaa4a8..6d16b9140 100644
--- a/lib/accelerated/x86/elf/sha256-ssse3-x86.s
+++ b/lib/accelerated/x86/elf/sha256-ssse3-x86.s
@@ -43,6 +43,7 @@
 .align	16
 sha256_block_data_order:
 .L_sha256_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -3384,4 +3385,21 @@ sha256_block_data_order:
 	ret
 .size	sha256_block_data_order,.-.L_sha256_block_data_order_begin
 
+	.section ".note.gnu.property", "a"
+	.p2align 2
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 2
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 2
+4:
+
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s b/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s
index 4b08e0c85..1514ee45c 100644
--- a/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/sha256-ssse3-x86_64.s
@@ -1814,6 +1814,7 @@ K256:
 .align	64
 sha256_block_data_order_shaext:
 _shaext_shortcut:
+.cfi_startproc	
 	leaq	K256+128(%rip),%rcx
 	movdqu	(%rdi),%xmm1
 	movdqu	16(%rdi),%xmm2
@@ -2016,6 +2017,7 @@ _shaext_shortcut:
 	movdqu	%xmm1,(%rdi)
 	movdqu	%xmm2,16(%rdi)
 	.byte	0xf3,0xc3
+.cfi_endproc	
 .size	sha256_block_data_order_shaext,.-sha256_block_data_order_shaext
 .type	sha256_block_data_order_ssse3,@function
 .align	64
@@ -4277,7 +4279,15 @@ sha256_block_data_order_avx2:
 	vmovdqa	%ymm4,0(%rsp)
 	xorl	%r14d,%r14d
 	vmovdqa	%ymm5,32(%rsp)
+
+	movq	88(%rsp),%rdi
+.cfi_def_cfa	%rdi,8
 	leaq	-64(%rsp),%rsp
+
+
+
+	movq	%rdi,-8(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x78,0x06,0x23,0x08
 	movl	%ebx,%edi
 	vmovdqa	%ymm6,0(%rsp)
 	xorl	%ecx,%edi
@@ -4289,6 +4299,12 @@ sha256_block_data_order_avx2:
 .align	16
 .Lavx2_00_47:
 	leaq	-64(%rsp),%rsp
+.cfi_escape	0x0f,0x05,0x77,0x38,0x06,0x23,0x08
+
+	pushq	64-8(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+	leaq	8(%rsp),%rsp
+.cfi_escape	0x0f,0x05,0x77,0x78,0x06,0x23,0x08
 	vpalignr	$4,%ymm0,%ymm1,%ymm4
 	addl	0+128(%rsp),%r11d
 	andl	%r8d,%r12d
@@ -4544,6 +4560,12 @@ sha256_block_data_order_avx2:
 	movl	%r9d,%r12d
 	vmovdqa	%ymm6,32(%rsp)
 	leaq	-64(%rsp),%rsp
+.cfi_escape	0x0f,0x05,0x77,0x38,0x06,0x23,0x08
+
+	pushq	64-8(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+	leaq	8(%rsp),%rsp
+.cfi_escape	0x0f,0x05,0x77,0x78,0x06,0x23,0x08
 	vpalignr	$4,%ymm2,%ymm3,%ymm4
 	addl	0+128(%rsp),%r11d
 	andl	%r8d,%r12d
@@ -5419,6 +5441,8 @@ sha256_block_data_order_avx2:
 
 	leaq	448(%rsp),%rsp
 
+.cfi_escape	0x0f,0x06,0x77,0xd8,0x00,0x06,0x23,0x08
+
 	addl	0(%rdi),%eax
 	addl	4(%rdi),%ebx
 	addl	8(%rdi),%ecx
@@ -5444,9 +5468,11 @@ sha256_block_data_order_avx2:
 	jbe	.Loop_avx2
 	leaq	(%rsp),%rbp
 
+
+.cfi_escape	0x0f,0x06,0x76,0xd8,0x00,0x06,0x23,0x08
+
 .Ldone_avx2:
-	leaq	(%rbp),%rsp
-	movq	88(%rsp),%rsi
+	movq	88(%rbp),%rsi
 .cfi_def_cfa	%rsi,8
 	vzeroupper
 	movq	-48(%rsi),%r15
@@ -5467,5 +5493,26 @@ sha256_block_data_order_avx2:
 	.byte	0xf3,0xc3
 .cfi_endproc	
 .size	sha256_block_data_order_avx2,.-sha256_block_data_order_avx2
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/sha512-ssse3-x86.s b/lib/accelerated/x86/elf/sha512-ssse3-x86.s
index 481c77715..afca4eae7 100644
--- a/lib/accelerated/x86/elf/sha512-ssse3-x86.s
+++ b/lib/accelerated/x86/elf/sha512-ssse3-x86.s
@@ -43,6 +43,7 @@
 .align	16
 sha512_block_data_order:
 .L_sha512_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -602,4 +603,21 @@ sha512_block_data_order:
 .byte	112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103
 .byte	62,0
 
+	.section ".note.gnu.property", "a"
+	.p2align 2
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	.asciz "GNU"
+1:
+	.p2align 2
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 2
+4:
+
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s b/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s
index e384d7e9e..a7be2cd44 100644
--- a/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s
+++ b/lib/accelerated/x86/elf/sha512-ssse3-x86_64.s
@@ -4204,7 +4204,15 @@ sha512_block_data_order_avx2:
 	vmovdqa	%ymm10,64(%rsp)
 	vpaddq	64(%rbp),%ymm6,%ymm10
 	vmovdqa	%ymm11,96(%rsp)
+
+	movq	152(%rsp),%rdi
+.cfi_def_cfa	%rdi,8
 	leaq	-128(%rsp),%rsp
+
+
+
+	movq	%rdi,-8(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x78,0x06,0x23,0x08
 	vpaddq	96(%rbp),%ymm7,%ymm11
 	vmovdqa	%ymm8,0(%rsp)
 	xorq	%r14,%r14
@@ -4220,6 +4228,12 @@ sha512_block_data_order_avx2:
 .align	16
 .Lavx2_00_47:
 	leaq	-128(%rsp),%rsp
+.cfi_escape	0x0f,0x06,0x77,0xf8,0x00,0x06,0x23,0x08
+
+	pushq	128-8(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+	leaq	8(%rsp),%rsp
+.cfi_escape	0x0f,0x05,0x77,0x78,0x06,0x23,0x08
 	vpalignr	$8,%ymm0,%ymm1,%ymm8
 	addq	0+256(%rsp),%r11
 	andq	%r8,%r12
@@ -4513,6 +4527,12 @@ sha512_block_data_order_avx2:
 	movq	%r9,%r12
 	vmovdqa	%ymm10,96(%rsp)
 	leaq	-128(%rsp),%rsp
+.cfi_escape	0x0f,0x06,0x77,0xf8,0x00,0x06,0x23,0x08
+
+	pushq	128-8(%rsp)
+.cfi_escape	0x0f,0x05,0x77,0x00,0x06,0x23,0x08
+	leaq	8(%rsp),%rsp
+.cfi_escape	0x0f,0x05,0x77,0x78,0x06,0x23,0x08
 	vpalignr	$8,%ymm4,%ymm5,%ymm8
 	addq	0+256(%rsp),%r11
 	andq	%r8,%r12
@@ -5426,6 +5446,8 @@ sha512_block_data_order_avx2:
 
 	leaq	1152(%rsp),%rsp
 
+.cfi_escape	0x0f,0x06,0x77,0x98,0x01,0x06,0x23,0x08
+
 	addq	0(%rdi),%rax
 	addq	8(%rdi),%rbx
 	addq	16(%rdi),%rcx
@@ -5451,9 +5473,11 @@ sha512_block_data_order_avx2:
 	jbe	.Loop_avx2
 	leaq	(%rsp),%rbp
 
+
+.cfi_escape	0x0f,0x06,0x76,0x98,0x01,0x06,0x23,0x08
+
 .Ldone_avx2:
-	leaq	(%rbp),%rsp
-	movq	152(%rsp),%rsi
+	movq	152(%rbp),%rsi
 .cfi_def_cfa	%rsi,8
 	vzeroupper
 	movq	-48(%rsi),%r15
@@ -5474,5 +5498,26 @@ sha512_block_data_order_avx2:
 	.byte	0xf3,0xc3
 .cfi_endproc	
 .size	sha512_block_data_order_avx2,.-sha512_block_data_order_avx2
+	.section ".note.gnu.property", "a"
+	.p2align 3
+	.long 1f - 0f
+	.long 4f - 1f
+	.long 5
+0:
+	# "GNU" encoded with .byte, since .asciz isn't supported
+	# on Solaris.
+	.byte 0x47
+	.byte 0x4e
+	.byte 0x55
+	.byte 0
+1:
+	.p2align 3
+	.long 0xc0000002
+	.long 3f - 2f
+2:
+	.long 3
+3:
+	.p2align 3
+4:
 
 .section .note.GNU-stack,"",%progbits
diff --git a/lib/accelerated/x86/macosx/aes-ssse3-x86.s b/lib/accelerated/x86/macosx/aes-ssse3-x86.s
index 4be899281..6cc2b0390 100644
--- a/lib/accelerated/x86/macosx/aes-ssse3-x86.s
+++ b/lib/accelerated/x86/macosx/aes-ssse3-x86.s
@@ -70,12 +70,14 @@ L_vpaes_consts:
 .align	6,0x90
 .align	4
 __vpaes_preheat:
+.byte	243,15,30,251
 	addl	(%esp),%ebp
 	movdqa	-48(%ebp),%xmm7
 	movdqa	-16(%ebp),%xmm6
 	ret
 .align	4
 __vpaes_encrypt_core:
+.byte	243,15,30,251
 	movl	$16,%ecx
 	movl	240(%edx),%eax
 	movdqa	%xmm6,%xmm1
@@ -151,6 +153,7 @@ L000enc_entry:
 	ret
 .align	4
 __vpaes_decrypt_core:
+.byte	243,15,30,251
 	leal	608(%ebp),%ebx
 	movl	240(%edx),%eax
 	movdqa	%xmm6,%xmm1
@@ -237,6 +240,7 @@ L002dec_entry:
 	ret
 .align	4
 __vpaes_schedule_core:
+.byte	243,15,30,251
 	addl	(%esp),%ebp
 	movdqu	(%esi),%xmm0
 	movdqa	320(%ebp),%xmm2
@@ -329,6 +333,7 @@ L013schedule_mangle_last_dec:
 	ret
 .align	4
 __vpaes_schedule_192_smear:
+.byte	243,15,30,251
 	pshufd	$128,%xmm6,%xmm1
 	pshufd	$254,%xmm7,%xmm0
 	pxor	%xmm1,%xmm6
@@ -339,6 +344,7 @@ __vpaes_schedule_192_smear:
 	ret
 .align	4
 __vpaes_schedule_round:
+.byte	243,15,30,251
 	movdqa	8(%esp),%xmm2
 	pxor	%xmm1,%xmm1
 .byte	102,15,58,15,202,15
@@ -386,6 +392,7 @@ L_vpaes_schedule_low_round:
 	ret
 .align	4
 __vpaes_schedule_transform:
+.byte	243,15,30,251
 	movdqa	-16(%ebp),%xmm2
 	movdqa	%xmm2,%xmm1
 	pandn	%xmm0,%xmm1
@@ -399,6 +406,7 @@ __vpaes_schedule_transform:
 	ret
 .align	4
 __vpaes_schedule_mangle:
+.byte	243,15,30,251
 	movdqa	%xmm0,%xmm4
 	movdqa	128(%ebp),%xmm5
 	testl	%edi,%edi
@@ -458,6 +466,7 @@ L015schedule_mangle_both:
 .align	4
 _vpaes_set_encrypt_key:
 L_vpaes_set_encrypt_key_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -489,6 +498,7 @@ L016pic_point:
 .align	4
 _vpaes_set_decrypt_key:
 L_vpaes_set_decrypt_key_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -525,6 +535,7 @@ L017pic_point:
 .align	4
 _vpaes_encrypt:
 L_vpaes_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -552,6 +563,7 @@ L018pic_point:
 .align	4
 _vpaes_decrypt:
 L_vpaes_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -579,6 +591,7 @@ L019pic_point:
 .align	4
 _vpaes_cbc_encrypt:
 L_vpaes_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/macosx/aes-ssse3-x86_64.s b/lib/accelerated/x86/macosx/aes-ssse3-x86_64.s
index 3d5c65226..c2e2f2e02 100644
--- a/lib/accelerated/x86/macosx/aes-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/aes-ssse3-x86_64.s
@@ -635,6 +635,7 @@ L$schedule_mangle_both:
 .p2align	4
 _vpaes_set_encrypt_key:
 
+.byte	243,15,30,250
 	movl	%esi,%eax
 	shrl	$5,%eax
 	addl	$5,%eax
@@ -653,6 +654,7 @@ _vpaes_set_encrypt_key:
 .p2align	4
 _vpaes_set_decrypt_key:
 
+.byte	243,15,30,250
 	movl	%esi,%eax
 	shrl	$5,%eax
 	addl	$5,%eax
@@ -676,6 +678,7 @@ _vpaes_set_decrypt_key:
 .p2align	4
 _vpaes_encrypt:
 
+.byte	243,15,30,250
 	movdqu	(%rdi),%xmm0
 	call	_vpaes_preheat
 	call	_vpaes_encrypt_core
@@ -689,6 +692,7 @@ _vpaes_encrypt:
 .p2align	4
 _vpaes_decrypt:
 
+.byte	243,15,30,250
 	movdqu	(%rdi),%xmm0
 	call	_vpaes_preheat
 	call	_vpaes_decrypt_core
@@ -701,6 +705,7 @@ _vpaes_decrypt:
 .p2align	4
 _vpaes_cbc_encrypt:
 
+.byte	243,15,30,250
 	xchgq	%rcx,%rdx
 	subq	$16,%rcx
 	jc	L$cbc_abort
diff --git a/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s b/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s
index d540930b5..be6d885d8 100644
--- a/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s
+++ b/lib/accelerated/x86/macosx/aesni-gcm-x86_64.s
@@ -42,6 +42,8 @@
 
 .p2align	5
 _aesni_ctr32_ghash_6x:
+
+.byte	243,15,30,250
 	vmovdqu	32(%r11),%xmm2
 	subq	$6,%rdx
 	vpxor	%xmm4,%xmm4,%xmm4
@@ -350,11 +352,13 @@ L$6x_done:
 
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_gcm_decrypt
 
 .p2align	5
 _aesni_gcm_decrypt:
 
+.byte	243,15,30,250
 	xorq	%r10,%r10
 	cmpq	$0x60,%rdx
 	jb	L$gcm_dec_abort
@@ -455,6 +459,8 @@ L$gcm_dec_abort:
 
 .p2align	5
 _aesni_ctr32_6x:
+
+.byte	243,15,30,250
 	vmovdqu	0-128(%rcx),%xmm4
 	vmovdqu	32(%r11),%xmm2
 	leaq	-1(%rbp),%r13
@@ -543,11 +549,13 @@ L$handle_ctr32_2:
 	jmp	L$oop_ctr32
 
 
+
 .globl	_aesni_gcm_encrypt
 
 .p2align	5
 _aesni_gcm_encrypt:
 
+.byte	243,15,30,250
 	xorq	%r10,%r10
 	cmpq	$288,%rdx
 	jb	L$gcm_enc_abort
diff --git a/lib/accelerated/x86/macosx/aesni-x86.s b/lib/accelerated/x86/macosx/aesni-x86.s
index ee5008914..64e4e52fc 100644
--- a/lib/accelerated/x86/macosx/aesni-x86.s
+++ b/lib/accelerated/x86/macosx/aesni-x86.s
@@ -42,6 +42,7 @@
 .align	4
 _aesni_encrypt:
 L_aesni_encrypt_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	12(%esp),%edx
 	movups	(%eax),%xmm2
@@ -67,6 +68,7 @@ L000enc1_loop_1:
 .align	4
 _aesni_decrypt:
 L_aesni_decrypt_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	12(%esp),%edx
 	movups	(%eax),%xmm2
@@ -90,6 +92,7 @@ L001dec1_loop_2:
 	ret
 .align	4
 __aesni_encrypt2:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -115,6 +118,7 @@ L002enc2_loop:
 	ret
 .align	4
 __aesni_decrypt2:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -140,6 +144,7 @@ L003dec2_loop:
 	ret
 .align	4
 __aesni_encrypt3:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -170,6 +175,7 @@ L004enc3_loop:
 	ret
 .align	4
 __aesni_decrypt3:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -200,6 +206,7 @@ L005dec3_loop:
 	ret
 .align	4
 __aesni_encrypt4:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	movups	16(%edx),%xmm1
 	shll	$4,%ecx
@@ -236,6 +243,7 @@ L006enc4_loop:
 	ret
 .align	4
 __aesni_decrypt4:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	movups	16(%edx),%xmm1
 	shll	$4,%ecx
@@ -272,6 +280,7 @@ L007dec4_loop:
 	ret
 .align	4
 __aesni_encrypt6:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -324,6 +333,7 @@ L_aesni_encrypt6_enter:
 	ret
 .align	4
 __aesni_decrypt6:
+.byte	243,15,30,251
 	movups	(%edx),%xmm0
 	shll	$4,%ecx
 	movups	16(%edx),%xmm1
@@ -378,6 +388,7 @@ L_aesni_decrypt6_enter:
 .align	4
 _aesni_ecb_encrypt:
 L_aesni_ecb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -611,6 +622,7 @@ L012ecb_ret:
 .align	4
 _aesni_ccm64_encrypt_blocks:
 L_aesni_ccm64_encrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -697,6 +709,7 @@ L031ccm64_enc2_loop:
 .align	4
 _aesni_ccm64_decrypt_blocks:
 L_aesni_ccm64_decrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -818,6 +831,7 @@ L036enc1_loop_6:
 .align	4
 _aesni_ctr32_encrypt_blocks:
 L_aesni_ctr32_encrypt_blocks_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1054,6 +1068,7 @@ L040ctr32_ret:
 .align	4
 _aesni_xts_encrypt:
 L_aesni_xts_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1412,6 +1427,7 @@ L056xts_enc_ret:
 .align	4
 _aesni_xts_decrypt:
 L_aesni_xts_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -1800,6 +1816,7 @@ L069xts_dec_ret:
 .align	4
 _aesni_ocb_encrypt:
 L_aesni_ocb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2193,6 +2210,7 @@ L078done:
 .align	4
 _aesni_ocb_decrypt:
 L_aesni_ocb_decrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2586,6 +2604,7 @@ L088done:
 .align	4
 _aesni_cbc_encrypt:
 L_aesni_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -2843,6 +2862,7 @@ L094cbc_abort:
 	ret
 .align	4
 __aesni_set_encrypt_key:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	testl	%eax,%eax
@@ -3176,6 +3196,7 @@ L115bad_keybits:
 .align	4
 _aesni_set_encrypt_key:
 L_aesni_set_encrypt_key_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	8(%esp),%ecx
 	movl	12(%esp),%edx
@@ -3185,6 +3206,7 @@ L_aesni_set_encrypt_key_begin:
 .align	4
 _aesni_set_decrypt_key:
 L_aesni_set_decrypt_key_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%eax
 	movl	8(%esp),%ecx
 	movl	12(%esp),%edx
diff --git a/lib/accelerated/x86/macosx/aesni-x86_64.s b/lib/accelerated/x86/macosx/aesni-x86_64.s
index f6145f166..484122c5e 100644
--- a/lib/accelerated/x86/macosx/aesni-x86_64.s
+++ b/lib/accelerated/x86/macosx/aesni-x86_64.s
@@ -44,6 +44,7 @@
 .p2align	4
 _aesni_encrypt:
 
+.byte	243,15,30,250
 	movups	(%rdi),%xmm2
 	movl	240(%rdx),%eax
 	movups	(%rdx),%xmm0
@@ -70,6 +71,7 @@ L$oop_enc1_1:
 .p2align	4
 _aesni_decrypt:
 
+.byte	243,15,30,250
 	movups	(%rdi),%xmm2
 	movl	240(%rdx),%eax
 	movups	(%rdx),%xmm0
@@ -557,6 +559,7 @@ L$dec_loop8_enter:
 .p2align	4
 _aesni_ecb_encrypt:
 
+.byte	243,15,30,250
 	andq	$-16,%rdx
 	jz	L$ecb_ret
 
@@ -900,6 +903,8 @@ L$ecb_ret:
 
 .p2align	4
 _aesni_ccm64_encrypt_blocks:
+
+.byte	243,15,30,250
 	movl	240(%rcx),%eax
 	movdqu	(%r8),%xmm6
 	movdqa	L$increment64(%rip),%xmm9
@@ -959,10 +964,13 @@ L$ccm64_enc2_loop:
 	pxor	%xmm6,%xmm6
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_ccm64_decrypt_blocks
 
 .p2align	4
 _aesni_ccm64_decrypt_blocks:
+
+.byte	243,15,30,250
 	movl	240(%rcx),%eax
 	movups	(%r8),%xmm6
 	movdqu	(%r9),%xmm3
@@ -1056,11 +1064,13 @@ L$oop_enc1_6:
 	pxor	%xmm6,%xmm6
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_ctr32_encrypt_blocks
 
 .p2align	4
 _aesni_ctr32_encrypt_blocks:
 
+.byte	243,15,30,250
 	cmpq	$1,%rdx
 	jne	L$ctr32_bulk
 
@@ -1639,6 +1649,7 @@ L$ctr32_epilogue:
 .p2align	4
 _aesni_xts_encrypt:
 
+.byte	243,15,30,250
 	leaq	(%rsp),%r11
 
 	pushq	%rbp
@@ -2109,6 +2120,7 @@ L$xts_enc_epilogue:
 .p2align	4
 _aesni_xts_decrypt:
 
+.byte	243,15,30,250
 	leaq	(%rsp),%r11
 
 	pushq	%rbp
@@ -2616,6 +2628,7 @@ L$xts_dec_epilogue:
 .p2align	5
 _aesni_ocb_encrypt:
 
+.byte	243,15,30,250
 	leaq	(%rsp),%rax
 	pushq	%rbx
 
@@ -2824,6 +2837,7 @@ L$ocb_enc_epilogue:
 
 .p2align	5
 __ocb_encrypt6:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -2924,8 +2938,10 @@ L$ocb_enc_loop6:
 
 
 
+
 .p2align	5
 __ocb_encrypt4:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -2993,8 +3009,10 @@ L$ocb_enc_loop4:
 
 
 
+
 .p2align	5
 __ocb_encrypt1:
+
 	pxor	%xmm15,%xmm7
 	pxor	%xmm9,%xmm7
 	pxor	%xmm2,%xmm8
@@ -3027,11 +3045,13 @@ L$ocb_enc_loop1:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_aesni_ocb_decrypt
 
 .p2align	5
 _aesni_ocb_decrypt:
 
+.byte	243,15,30,250
 	leaq	(%rsp),%rax
 	pushq	%rbx
 
@@ -3262,6 +3282,7 @@ L$ocb_dec_epilogue:
 
 .p2align	5
 __ocb_decrypt6:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3356,8 +3377,10 @@ L$ocb_dec_loop6:
 
 
 
+
 .p2align	5
 __ocb_decrypt4:
+
 	pxor	%xmm9,%xmm15
 	movdqu	(%rbx,%r12,1),%xmm11
 	movdqa	%xmm10,%xmm12
@@ -3421,8 +3444,10 @@ L$ocb_dec_loop4:
 
 
 
+
 .p2align	5
 __ocb_decrypt1:
+
 	pxor	%xmm15,%xmm7
 	pxor	%xmm9,%xmm7
 	pxor	%xmm7,%xmm2
@@ -3453,11 +3478,13 @@ L$ocb_dec_loop1:
 .byte	102,15,56,223,215
 	.byte	0xf3,0xc3
 
+
 .globl	_aesni_cbc_encrypt
 
 .p2align	4
 _aesni_cbc_encrypt:
 
+.byte	243,15,30,250
 	testq	%rdx,%rdx
 	jz	L$cbc_ret
 
@@ -4390,7 +4417,6 @@ L$enc_key_ret:
 	addq	$8,%rsp
 
 	.byte	0xf3,0xc3
-
 L$SEH_end_set_encrypt_key:
 
 .p2align	4
@@ -4463,6 +4489,7 @@ L$key_expansion_256b:
 	.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
diff --git a/lib/accelerated/x86/macosx/e_padlock-x86.s b/lib/accelerated/x86/macosx/e_padlock-x86.s
index 367962c7c..9a72938fe 100644
--- a/lib/accelerated/x86/macosx/e_padlock-x86.s
+++ b/lib/accelerated/x86/macosx/e_padlock-x86.s
@@ -1,4 +1,4 @@
-# Copyright (c) 2011-2013, Andy Polyakov <appro@openssl.org>
+# Copyright (c) 2011-2016, Andy Polyakov <appro@openssl.org>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -37,12 +37,12 @@
 #
 # *** This file is auto-generated ***
 #
-.file	"devel/perlasm/e_padlock-x86.s"
 .text
 .globl	_padlock_capability
 .align	4
 _padlock_capability:
 L_padlock_capability_begin:
+.byte	243,15,30,251
 	pushl	%ebx
 	pushfl
 	popl	%eax
@@ -59,11 +59,20 @@ L_padlock_capability_begin:
 	.byte	0x0f,0xa2
 	xorl	%eax,%eax
 	cmpl	$0x746e6543,%ebx
-	jne	L000noluck
+	jne	L001zhaoxin
 	cmpl	$0x48727561,%edx
 	jne	L000noluck
 	cmpl	$0x736c7561,%ecx
 	jne	L000noluck
+	jmp	L002zhaoxinEnd
+L001zhaoxin:
+	cmpl	$0x68532020,%ebx
+	jne	L000noluck
+	cmpl	$0x68676e61,%edx
+	jne	L000noluck
+	cmpl	$0x20206961,%ecx
+	jne	L000noluck
+L002zhaoxinEnd:
 	movl	$3221225472,%eax
 	.byte	0x0f,0xa2
 	movl	%eax,%edx
@@ -92,43 +101,47 @@ L000noluck:
 .align	4
 _padlock_key_bswap:
 L_padlock_key_bswap_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%edx
 	movl	240(%edx),%ecx
-L001bswap_loop:
+L003bswap_loop:
 	movl	(%edx),%eax
 	bswap	%eax
 	movl	%eax,(%edx)
 	leal	4(%edx),%edx
 	subl	$1,%ecx
-	jnz	L001bswap_loop
+	jnz	L003bswap_loop
 	ret
 .globl	_padlock_verify_context
 .align	4
 _padlock_verify_context:
 L_padlock_verify_context_begin:
+.byte	243,15,30,251
 	movl	4(%esp),%edx
-	leal	Lpadlock_saved_context-L002verify_pic_point,%eax
+	leal	Lpadlock_saved_context-L004verify_pic_point,%eax
 	pushfl
 	call	__padlock_verify_ctx
-L002verify_pic_point:
+L004verify_pic_point:
 	leal	4(%esp),%esp
 	ret
 .align	4
 __padlock_verify_ctx:
+.byte	243,15,30,251
 	addl	(%esp),%eax
 	btl	$30,4(%esp)
-	jnc	L003verified
+	jnc	L005verified
 	cmpl	(%eax),%edx
-	je	L003verified
+	je	L005verified
 	pushfl
 	popfl
-L003verified:
+L005verified:
 	movl	%edx,(%eax)
 	ret
 .globl	_padlock_reload_key
 .align	4
 _padlock_reload_key:
 L_padlock_reload_key_begin:
+.byte	243,15,30,251
 	pushfl
 	popfl
 	ret
@@ -136,6 +149,7 @@ L_padlock_reload_key_begin:
 .align	4
 _padlock_aes_block:
 L_padlock_aes_block_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	pushl	%ebx
@@ -154,6 +168,7 @@ L_padlock_aes_block_begin:
 .align	4
 _padlock_ecb_encrypt:
 L_padlock_ecb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -163,25 +178,25 @@ L_padlock_ecb_encrypt_begin:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	L004ecb_abort
+	jnz	L006ecb_abort
 	testl	$15,%ecx
-	jnz	L004ecb_abort
-	leal	Lpadlock_saved_context-L005ecb_pic_point,%eax
+	jnz	L006ecb_abort
+	leal	Lpadlock_saved_context-L007ecb_pic_point,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-L005ecb_pic_point:
+L007ecb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	L006ecb_aligned
+	jnz	L008ecb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	L006ecb_aligned
+	jnz	L008ecb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -200,7 +215,7 @@ L005ecb_pic_point:
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
 	cmpl	%ebx,%ecx
-	ja	L007ecb_loop
+	ja	L009ecb_loop
 	movl	%esi,%eax
 	cmpl	%esp,%ebp
 	cmovel	%edi,%eax
@@ -211,10 +226,10 @@ L005ecb_pic_point:
 	movl	$-128,%eax
 	cmovael	%ebx,%eax
 	andl	%eax,%ebx
-	jz	L008ecb_unaligned_tail
-	jmp	L007ecb_loop
+	jz	L010ecb_unaligned_tail
+	jmp	L009ecb_loop
 .align	4,0x90
-L007ecb_loop:
+L009ecb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -223,13 +238,13 @@ L007ecb_loop:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	L009ecb_inp_aligned
+	jz	L011ecb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-L009ecb_inp_aligned:
+L011ecb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -237,23 +252,23 @@ L009ecb_inp_aligned:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	L010ecb_out_aligned
+	jz	L012ecb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-L010ecb_out_aligned:
+L012ecb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jz	L011ecb_break
+	jz	L013ecb_break
 	cmpl	%ebx,%ecx
-	jae	L007ecb_loop
-L008ecb_unaligned_tail:
+	jae	L009ecb_loop
+L010ecb_unaligned_tail:
 	xorl	%eax,%eax
 	cmpl	%ebp,%esp
 	cmovel	%ecx,%eax
@@ -266,24 +281,24 @@ L008ecb_unaligned_tail:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	L007ecb_loop
+	jmp	L009ecb_loop
 .align	4,0x90
-L011ecb_break:
+L013ecb_break:
 	cmpl	%ebp,%esp
-	je	L012ecb_done
+	je	L014ecb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-L013ecb_bzero:
+L015ecb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	L013ecb_bzero
-L012ecb_done:
+	ja	L015ecb_bzero
+L014ecb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	L014ecb_exit
+	jmp	L016ecb_exit
 .align	4,0x90
-L006ecb_aligned:
+L008ecb_aligned:
 	leal	(%esi,%ecx,1),%ebp
 	negl	%ebp
 	andl	$4095,%ebp
@@ -293,14 +308,14 @@ L006ecb_aligned:
 	cmovael	%eax,%ebp
 	andl	%ecx,%ebp
 	subl	%ebp,%ecx
-	jz	L015ecb_aligned_tail
+	jz	L017ecb_aligned_tail
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,200
 	testl	%ebp,%ebp
-	jz	L014ecb_exit
-L015ecb_aligned_tail:
+	jz	L016ecb_exit
+L017ecb_aligned_tail:
 	movl	%ebp,%ecx
 	leal	-24(%esp),%ebp
 	movl	%ebp,%esp
@@ -317,11 +332,11 @@ L015ecb_aligned_tail:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	L007ecb_loop
-L014ecb_exit:
+	jmp	L009ecb_loop
+L016ecb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-L004ecb_abort:
+L006ecb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -331,6 +346,7 @@ L004ecb_abort:
 .align	4
 _padlock_cbc_encrypt:
 L_padlock_cbc_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -340,25 +356,25 @@ L_padlock_cbc_encrypt_begin:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	L016cbc_abort
+	jnz	L018cbc_abort
 	testl	$15,%ecx
-	jnz	L016cbc_abort
-	leal	Lpadlock_saved_context-L017cbc_pic_point,%eax
+	jnz	L018cbc_abort
+	leal	Lpadlock_saved_context-L019cbc_pic_point,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-L017cbc_pic_point:
+L019cbc_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	L018cbc_aligned
+	jnz	L020cbc_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	L018cbc_aligned
+	jnz	L020cbc_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -377,7 +393,7 @@ L017cbc_pic_point:
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
 	cmpl	%ebx,%ecx
-	ja	L019cbc_loop
+	ja	L021cbc_loop
 	movl	%esi,%eax
 	cmpl	%esp,%ebp
 	cmovel	%edi,%eax
@@ -388,10 +404,10 @@ L017cbc_pic_point:
 	movl	$-64,%eax
 	cmovael	%ebx,%eax
 	andl	%eax,%ebx
-	jz	L020cbc_unaligned_tail
-	jmp	L019cbc_loop
+	jz	L022cbc_unaligned_tail
+	jmp	L021cbc_loop
 .align	4,0x90
-L019cbc_loop:
+L021cbc_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -400,13 +416,13 @@ L019cbc_loop:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	L021cbc_inp_aligned
+	jz	L023cbc_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-L021cbc_inp_aligned:
+L023cbc_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -416,23 +432,23 @@ L021cbc_inp_aligned:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	L022cbc_out_aligned
+	jz	L024cbc_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-L022cbc_out_aligned:
+L024cbc_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jz	L023cbc_break
+	jz	L025cbc_break
 	cmpl	%ebx,%ecx
-	jae	L019cbc_loop
-L020cbc_unaligned_tail:
+	jae	L021cbc_loop
+L022cbc_unaligned_tail:
 	xorl	%eax,%eax
 	cmpl	%ebp,%esp
 	cmovel	%ecx,%eax
@@ -445,24 +461,24 @@ L020cbc_unaligned_tail:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	L019cbc_loop
+	jmp	L021cbc_loop
 .align	4,0x90
-L023cbc_break:
+L025cbc_break:
 	cmpl	%ebp,%esp
-	je	L024cbc_done
+	je	L026cbc_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-L025cbc_bzero:
+L027cbc_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	L025cbc_bzero
-L024cbc_done:
+	ja	L027cbc_bzero
+L026cbc_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	L026cbc_exit
+	jmp	L028cbc_exit
 .align	4,0x90
-L018cbc_aligned:
+L020cbc_aligned:
 	leal	(%esi,%ecx,1),%ebp
 	negl	%ebp
 	andl	$4095,%ebp
@@ -472,7 +488,7 @@ L018cbc_aligned:
 	cmovael	%eax,%ebp
 	andl	%ecx,%ebp
 	subl	%ebp,%ecx
-	jz	L027cbc_aligned_tail
+	jz	L029cbc_aligned_tail
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -480,8 +496,8 @@ L018cbc_aligned:
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
 	testl	%ebp,%ebp
-	jz	L026cbc_exit
-L027cbc_aligned_tail:
+	jz	L028cbc_exit
+L029cbc_aligned_tail:
 	movl	%ebp,%ecx
 	leal	-24(%esp),%ebp
 	movl	%ebp,%esp
@@ -498,11 +514,11 @@ L027cbc_aligned_tail:
 	movl	%esp,%esi
 	movl	%eax,%edi
 	movl	%ebx,%ecx
-	jmp	L019cbc_loop
-L026cbc_exit:
+	jmp	L021cbc_loop
+L028cbc_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-L016cbc_abort:
+L018cbc_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -512,6 +528,7 @@ L016cbc_abort:
 .align	4
 _padlock_cfb_encrypt:
 L_padlock_cfb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -521,25 +538,25 @@ L_padlock_cfb_encrypt_begin:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	L028cfb_abort
+	jnz	L030cfb_abort
 	testl	$15,%ecx
-	jnz	L028cfb_abort
-	leal	Lpadlock_saved_context-L029cfb_pic_point,%eax
+	jnz	L030cfb_abort
+	leal	Lpadlock_saved_context-L031cfb_pic_point,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-L029cfb_pic_point:
+L031cfb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	L030cfb_aligned
+	jnz	L032cfb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	L030cfb_aligned
+	jnz	L032cfb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -557,9 +574,9 @@ L029cfb_pic_point:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	L031cfb_loop
+	jmp	L033cfb_loop
 .align	4,0x90
-L031cfb_loop:
+L033cfb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -568,13 +585,13 @@ L031cfb_loop:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	L032cfb_inp_aligned
+	jz	L034cfb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-L032cfb_inp_aligned:
+L034cfb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -584,45 +601,45 @@ L032cfb_inp_aligned:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	L033cfb_out_aligned
+	jz	L035cfb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-L033cfb_out_aligned:
+L035cfb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	L031cfb_loop
+	jnz	L033cfb_loop
 	cmpl	%ebp,%esp
-	je	L034cfb_done
+	je	L036cfb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-L035cfb_bzero:
+L037cfb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	L035cfb_bzero
-L034cfb_done:
+	ja	L037cfb_bzero
+L036cfb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	L036cfb_exit
+	jmp	L038cfb_exit
 .align	4,0x90
-L030cfb_aligned:
+L032cfb_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,224
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
-L036cfb_exit:
+L038cfb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-L028cfb_abort:
+L030cfb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -632,6 +649,7 @@ L028cfb_abort:
 .align	4
 _padlock_ofb_encrypt:
 L_padlock_ofb_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -641,25 +659,25 @@ L_padlock_ofb_encrypt_begin:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	L037ofb_abort
+	jnz	L039ofb_abort
 	testl	$15,%ecx
-	jnz	L037ofb_abort
-	leal	Lpadlock_saved_context-L038ofb_pic_point,%eax
+	jnz	L039ofb_abort
+	leal	Lpadlock_saved_context-L040ofb_pic_point,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-L038ofb_pic_point:
+L040ofb_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	xorl	%ebx,%ebx
 	testl	$32,(%edx)
-	jnz	L039ofb_aligned
+	jnz	L041ofb_aligned
 	testl	$15,%edi
 	setz	%al
 	testl	$15,%esi
 	setz	%bl
 	testl	%ebx,%eax
-	jnz	L039ofb_aligned
+	jnz	L041ofb_aligned
 	negl	%eax
 	movl	$512,%ebx
 	notl	%eax
@@ -677,9 +695,9 @@ L038ofb_pic_point:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	L040ofb_loop
+	jmp	L042ofb_loop
 .align	4,0x90
-L040ofb_loop:
+L042ofb_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -688,13 +706,13 @@ L040ofb_loop:
 	testl	$15,%edi
 	cmovnzl	%esp,%edi
 	testl	$15,%esi
-	jz	L041ofb_inp_aligned
+	jz	L043ofb_inp_aligned
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
 	movl	%ebx,%ecx
 	movl	%edi,%esi
-L041ofb_inp_aligned:
+L043ofb_inp_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
@@ -704,45 +722,45 @@ L041ofb_inp_aligned:
 	movl	(%ebp),%edi
 	movl	12(%ebp),%ebx
 	testl	$15,%edi
-	jz	L042ofb_out_aligned
+	jz	L044ofb_out_aligned
 	movl	%ebx,%ecx
 	leal	(%esp),%esi
 	shrl	$2,%ecx
 .byte	243,165
 	subl	%ebx,%edi
-L042ofb_out_aligned:
+L044ofb_out_aligned:
 	movl	4(%ebp),%esi
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	L040ofb_loop
+	jnz	L042ofb_loop
 	cmpl	%ebp,%esp
-	je	L043ofb_done
+	je	L045ofb_done
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-L044ofb_bzero:
+L046ofb_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	L044ofb_bzero
-L043ofb_done:
+	ja	L046ofb_bzero
+L045ofb_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
-	jmp	L045ofb_exit
+	jmp	L047ofb_exit
 .align	4,0x90
-L039ofb_aligned:
+L041ofb_aligned:
 	leal	-16(%edx),%eax
 	leal	16(%edx),%ebx
 	shrl	$4,%ecx
 .byte	243,15,167,232
 	movaps	(%eax),%xmm0
 	movaps	%xmm0,-16(%edx)
-L045ofb_exit:
+L047ofb_exit:
 	movl	$1,%eax
 	leal	4(%esp),%esp
-L037ofb_abort:
+L039ofb_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -752,6 +770,7 @@ L037ofb_abort:
 .align	4
 _padlock_ctr32_encrypt:
 L_padlock_ctr32_encrypt_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
@@ -761,14 +780,14 @@ L_padlock_ctr32_encrypt_begin:
 	movl	28(%esp),%edx
 	movl	32(%esp),%ecx
 	testl	$15,%edx
-	jnz	L046ctr32_abort
+	jnz	L048ctr32_abort
 	testl	$15,%ecx
-	jnz	L046ctr32_abort
-	leal	Lpadlock_saved_context-L047ctr32_pic_point,%eax
+	jnz	L048ctr32_abort
+	leal	Lpadlock_saved_context-L049ctr32_pic_point,%eax
 	pushfl
 	cld
 	call	__padlock_verify_ctx
-L047ctr32_pic_point:
+L049ctr32_pic_point:
 	leal	16(%edx),%edx
 	xorl	%eax,%eax
 	movq	-16(%edx),%mm0
@@ -788,9 +807,9 @@ L047ctr32_pic_point:
 	andl	$-16,%ebp
 	andl	$-16,%esp
 	movl	%eax,16(%ebp)
-	jmp	L048ctr32_loop
+	jmp	L050ctr32_loop
 .align	4,0x90
-L048ctr32_loop:
+L050ctr32_loop:
 	movl	%edi,(%ebp)
 	movl	%esi,4(%ebp)
 	movl	%ecx,8(%ebp)
@@ -799,7 +818,7 @@ L048ctr32_loop:
 	movl	-4(%edx),%ecx
 	xorl	%edi,%edi
 	movl	-8(%edx),%eax
-L049ctr32_prepare:
+L051ctr32_prepare:
 	movl	%ecx,12(%esp,%edi,1)
 	bswap	%ecx
 	movq	%mm0,(%esp,%edi,1)
@@ -808,7 +827,7 @@ L049ctr32_prepare:
 	bswap	%ecx
 	leal	16(%edi),%edi
 	cmpl	%ebx,%edi
-	jb	L049ctr32_prepare
+	jb	L051ctr32_prepare
 	movl	%ecx,-4(%edx)
 	leal	(%esp),%esi
 	leal	(%esp),%edi
@@ -821,33 +840,33 @@ L049ctr32_prepare:
 	movl	12(%ebp),%ebx
 	movl	4(%ebp),%esi
 	xorl	%ecx,%ecx
-L050ctr32_xor:
+L052ctr32_xor:
 	movups	(%esi,%ecx,1),%xmm1
 	leal	16(%ecx),%ecx
 	pxor	-16(%esp,%ecx,1),%xmm1
 	movups	%xmm1,-16(%edi,%ecx,1)
 	cmpl	%ebx,%ecx
-	jb	L050ctr32_xor
+	jb	L052ctr32_xor
 	movl	8(%ebp),%ecx
 	addl	%ebx,%edi
 	addl	%ebx,%esi
 	subl	%ebx,%ecx
 	movl	$512,%ebx
-	jnz	L048ctr32_loop
+	jnz	L050ctr32_loop
 	pxor	%xmm0,%xmm0
 	leal	(%esp),%eax
-L051ctr32_bzero:
+L053ctr32_bzero:
 	movaps	%xmm0,(%eax)
 	leal	16(%eax),%eax
 	cmpl	%eax,%ebp
-	ja	L051ctr32_bzero
-L052ctr32_done:
+	ja	L053ctr32_bzero
+L054ctr32_done:
 	movl	16(%ebp),%ebp
 	leal	24(%ebp),%esp
 	movl	$1,%eax
 	leal	4(%esp),%esp
 	emms
-L046ctr32_abort:
+L048ctr32_abort:
 	popl	%edi
 	popl	%esi
 	popl	%ebx
@@ -857,6 +876,7 @@ L046ctr32_abort:
 .align	4
 _padlock_xstore:
 L_padlock_xstore_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	movl	8(%esp),%edi
 	movl	12(%esp),%edx
@@ -865,19 +885,21 @@ L_padlock_xstore_begin:
 	ret
 .align	4
 __win32_segv_handler:
+.byte	243,15,30,251
 	movl	$1,%eax
 	movl	4(%esp),%edx
 	movl	12(%esp),%ecx
 	cmpl	$3221225477,(%edx)
-	jne	L053ret
+	jne	L055ret
 	addl	$4,184(%ecx)
 	movl	$0,%eax
-L053ret:
+L055ret:
 	ret
 .globl	_padlock_sha1_oneshot
 .align	4
 _padlock_sha1_oneshot:
 L_padlock_sha1_oneshot_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	xorl	%eax,%eax
@@ -907,6 +929,7 @@ L_padlock_sha1_oneshot_begin:
 .align	4
 _padlock_sha1_blocks:
 L_padlock_sha1_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -935,6 +958,7 @@ L_padlock_sha1_blocks_begin:
 .align	4
 _padlock_sha256_oneshot:
 L_padlock_sha256_oneshot_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	xorl	%eax,%eax
@@ -964,6 +988,7 @@ L_padlock_sha256_oneshot_begin:
 .align	4
 _padlock_sha256_blocks:
 L_padlock_sha256_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
@@ -992,6 +1017,7 @@ L_padlock_sha256_blocks_begin:
 .align	4
 _padlock_sha512_blocks:
 L_padlock_sha512_blocks_begin:
+.byte	243,15,30,251
 	pushl	%edi
 	pushl	%esi
 	movl	12(%esp),%edi
diff --git a/lib/accelerated/x86/macosx/e_padlock-x86_64.s b/lib/accelerated/x86/macosx/e_padlock-x86_64.s
index a73d7a6c1..64aff29fe 100644
--- a/lib/accelerated/x86/macosx/e_padlock-x86_64.s
+++ b/lib/accelerated/x86/macosx/e_padlock-x86_64.s
@@ -1,4 +1,4 @@
-# Copyright (c) 2011-2013, Andy Polyakov <appro@openssl.org>
+# Copyright (c) 2011-2016, Andy Polyakov <appro@openssl.org>
 # All rights reserved.
 #
 # Redistribution and use in source and binary forms, with or without
@@ -42,36 +42,50 @@
 
 .p2align	4
 _padlock_capability:
+
+.byte	243,15,30,250
 	movq	%rbx,%r8
 	xorl	%eax,%eax
 	cpuid
 	xorl	%eax,%eax
-	cmpl	$1953391939,%ebx
+	cmpl	$0x746e6543,%ebx
+	jne	L$zhaoxin
+	cmpl	$0x48727561,%edx
+	jne	L$noluck
+	cmpl	$0x736c7561,%ecx
+	jne	L$noluck
+	jmp	L$zhaoxinEnd
+L$zhaoxin:
+	cmpl	$0x68532020,%ebx
 	jne	L$noluck
-	cmpl	$1215460705,%edx
+	cmpl	$0x68676e61,%edx
 	jne	L$noluck
-	cmpl	$1936487777,%ecx
+	cmpl	$0x20206961,%ecx
 	jne	L$noluck
-	movl	$3221225472,%eax
+L$zhaoxinEnd:
+	movl	$0xC0000000,%eax
 	cpuid
 	movl	%eax,%edx
 	xorl	%eax,%eax
-	cmpl	$3221225473,%edx
+	cmpl	$0xC0000001,%edx
 	jb	L$noluck
-	movl	$3221225473,%eax
+	movl	$0xC0000001,%eax
 	cpuid
 	movl	%edx,%eax
-	andl	$4294967279,%eax
-	orl	$16,%eax
+	andl	$0xffffffef,%eax
+	orl	$0x10,%eax
 L$noluck:
 	movq	%r8,%rbx
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_key_bswap
 
 .p2align	4
 _padlock_key_bswap:
+
+.byte	243,15,30,250
 	movl	240(%rdi),%edx
 L$bswap_loop:
 	movl	(%rdi),%eax
@@ -83,10 +97,13 @@ L$bswap_loop:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_verify_context
 
 .p2align	4
 _padlock_verify_context:
+
+.byte	243,15,30,250
 	movq	%rdi,%rdx
 	pushf
 	leaq	L$padlock_saved_context(%rip),%rax
@@ -96,8 +113,11 @@ _padlock_verify_context:
 
 
 
+
 .p2align	4
 _padlock_verify_ctx:
+
+.byte	243,15,30,250
 	movq	8(%rsp),%r8
 	btq	$30,%r8
 	jnc	L$verified
@@ -110,41 +130,53 @@ L$verified:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_reload_key
 
 .p2align	4
 _padlock_reload_key:
+
+.byte	243,15,30,250
 	pushf
 	popf
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_aes_block
 
 .p2align	4
 _padlock_aes_block:
+
+.byte	243,15,30,250
 	movq	%rbx,%r8
 	movq	$1,%rcx
 	leaq	32(%rdx),%rbx
 	leaq	16(%rdx),%rdx
-.byte	0xf3,0x0f,0xa7,0xc8	
+.byte	0xf3,0x0f,0xa7,0xc8
 	movq	%r8,%rbx
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_xstore
 
 .p2align	4
 _padlock_xstore:
+
+.byte	243,15,30,250
 	movl	%esi,%edx
-.byte	0x0f,0xa7,0xc0		
+.byte	0x0f,0xa7,0xc0
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_sha1_oneshot
 
 .p2align	4
 _padlock_sha1_oneshot:
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -154,7 +186,7 @@ _padlock_sha1_oneshot:
 	movq	%rsp,%rdi
 	movl	%eax,16(%rsp)
 	xorq	%rax,%rax
-.byte	0xf3,0x0f,0xa6,0xc8	
+.byte	0xf3,0x0f,0xa6,0xc8
 	movaps	(%rsp),%xmm0
 	movl	16(%rsp),%eax
 	addq	$128+8,%rsp
@@ -163,10 +195,13 @@ _padlock_sha1_oneshot:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_sha1_blocks
 
 .p2align	4
 _padlock_sha1_blocks:
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -176,7 +211,7 @@ _padlock_sha1_blocks:
 	movq	%rsp,%rdi
 	movl	%eax,16(%rsp)
 	movq	$-1,%rax
-.byte	0xf3,0x0f,0xa6,0xc8	
+.byte	0xf3,0x0f,0xa6,0xc8
 	movaps	(%rsp),%xmm0
 	movl	16(%rsp),%eax
 	addq	$128+8,%rsp
@@ -185,10 +220,13 @@ _padlock_sha1_blocks:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_sha256_oneshot
 
 .p2align	4
 _padlock_sha256_oneshot:
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -198,7 +236,7 @@ _padlock_sha256_oneshot:
 	movq	%rsp,%rdi
 	movaps	%xmm1,16(%rsp)
 	xorq	%rax,%rax
-.byte	0xf3,0x0f,0xa6,0xd0	
+.byte	0xf3,0x0f,0xa6,0xd0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	addq	$128+8,%rsp
@@ -207,10 +245,13 @@ _padlock_sha256_oneshot:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_sha256_blocks
 
 .p2align	4
 _padlock_sha256_blocks:
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -220,7 +261,7 @@ _padlock_sha256_blocks:
 	movq	%rsp,%rdi
 	movaps	%xmm1,16(%rsp)
 	movq	$-1,%rax
-.byte	0xf3,0x0f,0xa6,0xd0	
+.byte	0xf3,0x0f,0xa6,0xd0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	addq	$128+8,%rsp
@@ -229,10 +270,13 @@ _padlock_sha256_blocks:
 	.byte	0xf3,0xc3
 
 
+
 .globl	_padlock_sha512_blocks
 
 .p2align	4
 _padlock_sha512_blocks:
+
+.byte	243,15,30,250
 	movq	%rdx,%rcx
 	movq	%rdi,%rdx
 	movups	(%rdi),%xmm0
@@ -245,7 +289,7 @@ _padlock_sha512_blocks:
 	movaps	%xmm1,16(%rsp)
 	movaps	%xmm2,32(%rsp)
 	movaps	%xmm3,48(%rsp)
-.byte	0xf3,0x0f,0xa6,0xe0	
+.byte	0xf3,0x0f,0xa6,0xe0
 	movaps	(%rsp),%xmm0
 	movaps	16(%rsp),%xmm1
 	movaps	32(%rsp),%xmm2
@@ -257,10 +301,13 @@ _padlock_sha512_blocks:
 	movups	%xmm3,48(%rdx)
 	.byte	0xf3,0xc3
 
+
 .globl	_padlock_ecb_encrypt
 
 .p2align	4
 _padlock_ecb_encrypt:
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -278,9 +325,9 @@ _padlock_ecb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	L$ecb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	L$ecb_aligned
@@ -304,7 +351,7 @@ _padlock_ecb_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$128,%rax
 	movq	$-128,%rax
 	cmovaeq	%rbx,%rax
@@ -320,12 +367,12 @@ L$ecb_loop:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	L$ecb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -333,15 +380,15 @@ L$ecb_inp_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,200	
+.byte	0xf3,0x0f,0xa7,200
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	L$ecb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 L$ecb_out_aligned:
 	movq	%r9,%rsi
@@ -362,7 +409,7 @@ L$ecb_unaligned_tail:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -388,7 +435,7 @@ L$ecb_done:
 L$ecb_aligned:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$128,%rbp
 	movq	$128-1,%rbp
@@ -399,7 +446,7 @@ L$ecb_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,200	
+.byte	0xf3,0x0f,0xa7,200
 	testq	%rbp,%rbp
 	jz	L$ecb_exit
 
@@ -411,7 +458,7 @@ L$ecb_aligned_tail:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -424,10 +471,13 @@ L$ecb_abort:
 	popq	%rbp
 	.byte	0xf3,0xc3
 
+
 .globl	_padlock_cbc_encrypt
 
 .p2align	4
 _padlock_cbc_encrypt:
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -445,9 +495,9 @@ _padlock_cbc_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	L$cbc_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	L$cbc_aligned
@@ -471,7 +521,7 @@ _padlock_cbc_encrypt:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$64,%rax
 	movq	$-64,%rax
 	cmovaeq	%rbx,%rax
@@ -487,12 +537,12 @@ L$cbc_loop:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	L$cbc_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -500,17 +550,17 @@ L$cbc_inp_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,208	
+.byte	0xf3,0x0f,0xa7,208
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	L$cbc_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 L$cbc_out_aligned:
 	movq	%r9,%rsi
@@ -531,7 +581,7 @@ L$cbc_unaligned_tail:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -557,7 +607,7 @@ L$cbc_done:
 L$cbc_aligned:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$64,%rbp
 	movq	$64-1,%rbp
@@ -568,7 +618,7 @@ L$cbc_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,208	
+.byte	0xf3,0x0f,0xa7,208
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	testq	%rbp,%rbp
@@ -582,7 +632,7 @@ L$cbc_aligned_tail:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -595,10 +645,13 @@ L$cbc_abort:
 	popq	%rbp
 	.byte	0xf3,0xc3
 
+
 .globl	_padlock_cfb_encrypt
 
 .p2align	4
 _padlock_cfb_encrypt:
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -616,9 +669,9 @@ _padlock_cfb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	L$cfb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	L$cfb_aligned
@@ -645,12 +698,12 @@ L$cfb_loop:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	L$cfb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -658,17 +711,17 @@ L$cfb_inp_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,224	
+.byte	0xf3,0x0f,0xa7,224
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	L$cfb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 L$cfb_out_aligned:
 	movq	%r9,%rsi
@@ -698,7 +751,7 @@ L$cfb_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,224	
+.byte	0xf3,0x0f,0xa7,224
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 L$cfb_exit:
@@ -709,10 +762,13 @@ L$cfb_abort:
 	popq	%rbp
 	.byte	0xf3,0xc3
 
+
 .globl	_padlock_ofb_encrypt
 
 .p2align	4
 _padlock_ofb_encrypt:
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -730,9 +786,9 @@ _padlock_ofb_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	L$ofb_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	L$ofb_aligned
@@ -759,12 +815,12 @@ L$ofb_loop:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	L$ofb_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -772,17 +828,17 @@ L$ofb_inp_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,232	
+.byte	0xf3,0x0f,0xa7,232
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	L$ofb_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 L$ofb_out_aligned:
 	movq	%r9,%rsi
@@ -812,7 +868,7 @@ L$ofb_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,232	
+.byte	0xf3,0x0f,0xa7,232
 	movdqa	(%rax),%xmm0
 	movdqa	%xmm0,-16(%rdx)
 L$ofb_exit:
@@ -823,10 +879,13 @@ L$ofb_abort:
 	popq	%rbp
 	.byte	0xf3,0xc3
 
+
 .globl	_padlock_ctr32_encrypt
 
 .p2align	4
 _padlock_ctr32_encrypt:
+
+.byte	243,15,30,250
 	pushq	%rbp
 	pushq	%rbx
 
@@ -844,9 +903,9 @@ _padlock_ctr32_encrypt:
 	xorl	%ebx,%ebx
 	testl	$32,(%rdx)
 	jnz	L$ctr32_aligned
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	setz	%al
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	setz	%bl
 	testl	%ebx,%eax
 	jnz	L$ctr32_aligned
@@ -881,7 +940,7 @@ L$ctr32_reenter:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$32,%rax
 	movq	$-32,%rax
 	cmovaeq	%rbx,%rax
@@ -897,12 +956,12 @@ L$ctr32_loop:
 	movq	%rcx,%r10
 	movq	%rbx,%rcx
 	movq	%rbx,%r11
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	cmovnzq	%rsp,%rdi
-	testq	$15,%rsi
+	testq	$0x0f,%rsi
 	jz	L$ctr32_inp_aligned
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 	movq	%rbx,%rcx
 	movq	%rdi,%rsi
@@ -910,23 +969,23 @@ L$ctr32_inp_aligned:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 	movl	-4(%rdx),%eax
-	testl	$4294901760,%eax
+	testl	$0xffff0000,%eax
 	jnz	L$ctr32_no_carry
 	bswapl	%eax
-	addl	$65536,%eax
+	addl	$0x10000,%eax
 	bswapl	%eax
 	movl	%eax,-4(%rdx)
 L$ctr32_no_carry:
 	movq	%r8,%rdi
 	movq	%r11,%rbx
-	testq	$15,%rdi
+	testq	$0x0f,%rdi
 	jz	L$ctr32_out_aligned
 	movq	%rbx,%rcx
 	leaq	(%rsp),%rsi
 	shrq	$3,%rcx
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	subq	%rbx,%rdi
 L$ctr32_out_aligned:
 	movq	%r9,%rsi
@@ -944,7 +1003,7 @@ L$ctr32_out_aligned:
 	cmoveq	%rdi,%rax
 	addq	%rcx,%rax
 	negq	%rax
-	andq	$4095,%rax
+	andq	$0xfff,%rax
 	cmpq	$32,%rax
 	movq	$-32,%rax
 	cmovaeq	%rbx,%rax
@@ -959,7 +1018,7 @@ L$ctr32_unaligned_tail:
 	subq	%rax,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	movq	%rsp,%rsi
 	movq	%r8,%rdi
 	movq	%rbx,%rcx
@@ -986,7 +1045,7 @@ L$ctr32_aligned:
 	movl	-4(%rdx),%eax
 	bswapl	%eax
 	negl	%eax
-	andl	$65535,%eax
+	andl	$0xffff,%eax
 	movq	$1048576,%rbx
 	shll	$4,%eax
 	cmovzq	%rbx,%rax
@@ -1003,11 +1062,11 @@ L$ctr32_aligned_loop:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 
 	movl	-4(%rdx),%eax
 	bswapl	%eax
-	addl	$65536,%eax
+	addl	$0x10000,%eax
 	bswapl	%eax
 	movl	%eax,-4(%rdx)
 
@@ -1021,7 +1080,7 @@ L$ctr32_aligned_loop:
 L$ctr32_aligned_skip:
 	leaq	(%rsi,%rcx,1),%rbp
 	negq	%rbp
-	andq	$4095,%rbp
+	andq	$0xfff,%rbp
 	xorl	%eax,%eax
 	cmpq	$32,%rbp
 	movq	$32-1,%rbp
@@ -1032,7 +1091,7 @@ L$ctr32_aligned_skip:
 	leaq	-16(%rdx),%rax
 	leaq	16(%rdx),%rbx
 	shrq	$4,%rcx
-.byte	0xf3,0x0f,0xa7,216	
+.byte	0xf3,0x0f,0xa7,216
 	testq	%rbp,%rbp
 	jz	L$ctr32_exit
 
@@ -1044,7 +1103,7 @@ L$ctr32_aligned_tail:
 	subq	%rcx,%rsp
 	shrq	$3,%rcx
 	leaq	(%rsp),%rdi
-.byte	0xf3,0x48,0xa5		
+.byte	0xf3,0x48,0xa5
 	leaq	(%r8),%rdi
 	leaq	(%rsp),%rsi
 	movq	%rbx,%rcx
@@ -1057,6 +1116,7 @@ L$ctr32_abort:
 	popq	%rbp
 	.byte	0xf3,0xc3
 
+
 .byte	86,73,65,32,80,97,100,108,111,99,107,32,120,56,54,95,54,52,32,109,111,100,117,108,101,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0
 .p2align	4
 .data	
diff --git a/lib/accelerated/x86/macosx/ghash-x86_64.s b/lib/accelerated/x86/macosx/ghash-x86_64.s
index 5fd321675..974d34dc7 100644
--- a/lib/accelerated/x86/macosx/ghash-x86_64.s
+++ b/lib/accelerated/x86/macosx/ghash-x86_64.s
@@ -45,6 +45,7 @@
 .p2align	4
 _gcm_gmult_4bit:
 
+.byte	243,15,30,250
 	pushq	%rbx
 
 	pushq	%rbp
@@ -150,6 +151,7 @@ L$gmult_epilogue:
 .p2align	4
 _gcm_ghash_4bit:
 
+.byte	243,15,30,250
 	pushq	%rbx
 
 	pushq	%rbp
@@ -891,6 +893,7 @@ L$_init_clmul:
 .p2align	4
 _gcm_gmult_clmul:
 
+.byte	243,15,30,250
 L$_gmult_clmul:
 	movdqu	(%rdi),%xmm0
 	movdqa	L$bswap_mask(%rip),%xmm5
@@ -944,6 +947,7 @@ L$_gmult_clmul:
 .p2align	5
 _gcm_ghash_clmul:
 
+.byte	243,15,30,250
 L$_ghash_clmul:
 	movdqa	L$bswap_mask(%rip),%xmm10
 
@@ -1438,6 +1442,7 @@ L$init_start_avx:
 .p2align	5
 _gcm_gmult_avx:
 
+.byte	243,15,30,250
 	jmp	L$_gmult_clmul
 
 
@@ -1446,6 +1451,7 @@ _gcm_gmult_avx:
 .p2align	5
 _gcm_ghash_avx:
 
+.byte	243,15,30,250
 	vzeroupper
 
 	vmovdqu	(%rdi),%xmm10
diff --git a/lib/accelerated/x86/macosx/sha1-ssse3-x86.s b/lib/accelerated/x86/macosx/sha1-ssse3-x86.s
index 985d4af8d..f51c5a318 100644
--- a/lib/accelerated/x86/macosx/sha1-ssse3-x86.s
+++ b/lib/accelerated/x86/macosx/sha1-ssse3-x86.s
@@ -42,6 +42,7 @@
 .align	4
 _sha1_block_data_order:
 L_sha1_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s b/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s
index a576acc25..7b5d9dfc9 100644
--- a/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/sha1-ssse3-x86_64.s
@@ -1460,10 +1460,10 @@ L$oop_shaext:
 	pshufd	$27,%xmm1,%xmm1
 	movdqu	%xmm0,(%rdi)
 	movd	%xmm1,16(%rdi)
-
 	.byte	0xf3,0xc3
 
 
+
 .p2align	4
 sha1_block_data_order_ssse3:
 _ssse3_shortcut:
diff --git a/lib/accelerated/x86/macosx/sha256-ssse3-x86.s b/lib/accelerated/x86/macosx/sha256-ssse3-x86.s
index 8d257109c..36781d480 100644
--- a/lib/accelerated/x86/macosx/sha256-ssse3-x86.s
+++ b/lib/accelerated/x86/macosx/sha256-ssse3-x86.s
@@ -42,6 +42,7 @@
 .align	4
 _sha256_block_data_order:
 L_sha256_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s b/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s
index fd0c24735..9fed36b9c 100644
--- a/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/sha256-ssse3-x86_64.s
@@ -1814,6 +1814,7 @@ K256:
 .p2align	6
 sha256_block_data_order_shaext:
 _shaext_shortcut:
+
 	leaq	K256+128(%rip),%rcx
 	movdqu	(%rdi),%xmm1
 	movdqu	16(%rdi),%xmm2
@@ -2018,6 +2019,7 @@ L$oop_shaext:
 	.byte	0xf3,0xc3
 
 
+
 .p2align	6
 sha256_block_data_order_ssse3:
 
@@ -4277,7 +4279,15 @@ L$oop_avx2:
 	vmovdqa	%ymm4,0(%rsp)
 	xorl	%r14d,%r14d
 	vmovdqa	%ymm5,32(%rsp)
+
+	movq	88(%rsp),%rdi
+
 	leaq	-64(%rsp),%rsp
+
+
+
+	movq	%rdi,-8(%rsp)
+
 	movl	%ebx,%edi
 	vmovdqa	%ymm6,0(%rsp)
 	xorl	%ecx,%edi
@@ -4289,6 +4299,12 @@ L$oop_avx2:
 .p2align	4
 L$avx2_00_47:
 	leaq	-64(%rsp),%rsp
+
+
+	pushq	64-8(%rsp)
+
+	leaq	8(%rsp),%rsp
+
 	vpalignr	$4,%ymm0,%ymm1,%ymm4
 	addl	0+128(%rsp),%r11d
 	andl	%r8d,%r12d
@@ -4544,6 +4560,12 @@ L$avx2_00_47:
 	movl	%r9d,%r12d
 	vmovdqa	%ymm6,32(%rsp)
 	leaq	-64(%rsp),%rsp
+
+
+	pushq	64-8(%rsp)
+
+	leaq	8(%rsp),%rsp
+
 	vpalignr	$4,%ymm2,%ymm3,%ymm4
 	addl	0+128(%rsp),%r11d
 	andl	%r8d,%r12d
@@ -5419,6 +5441,8 @@ L$ower_avx2:
 
 	leaq	448(%rsp),%rsp
 
+
+
 	addl	0(%rdi),%eax
 	addl	4(%rdi),%ebx
 	addl	8(%rdi),%ecx
@@ -5444,9 +5468,11 @@ L$ower_avx2:
 	jbe	L$oop_avx2
 	leaq	(%rsp),%rbp
 
+
+
+
 L$done_avx2:
-	leaq	(%rbp),%rsp
-	movq	88(%rsp),%rsi
+	movq	88(%rbp),%rsi
 
 	vzeroupper
 	movq	-48(%rsi),%r15
diff --git a/lib/accelerated/x86/macosx/sha512-ssse3-x86.s b/lib/accelerated/x86/macosx/sha512-ssse3-x86.s
index 4e60bb45f..248a35ee1 100644
--- a/lib/accelerated/x86/macosx/sha512-ssse3-x86.s
+++ b/lib/accelerated/x86/macosx/sha512-ssse3-x86.s
@@ -42,6 +42,7 @@
 .align	4
 _sha512_block_data_order:
 L_sha512_block_data_order_begin:
+.byte	243,15,30,251
 	pushl	%ebp
 	pushl	%ebx
 	pushl	%esi
diff --git a/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s b/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s
index 8bf161601..e78d90f2d 100644
--- a/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s
+++ b/lib/accelerated/x86/macosx/sha512-ssse3-x86_64.s
@@ -4204,7 +4204,15 @@ L$oop_avx2:
 	vmovdqa	%ymm10,64(%rsp)
 	vpaddq	64(%rbp),%ymm6,%ymm10
 	vmovdqa	%ymm11,96(%rsp)
+
+	movq	152(%rsp),%rdi
+
 	leaq	-128(%rsp),%rsp
+
+
+
+	movq	%rdi,-8(%rsp)
+
 	vpaddq	96(%rbp),%ymm7,%ymm11
 	vmovdqa	%ymm8,0(%rsp)
 	xorq	%r14,%r14
@@ -4220,6 +4228,12 @@ L$oop_avx2:
 .p2align	4
 L$avx2_00_47:
 	leaq	-128(%rsp),%rsp
+
+
+	pushq	128-8(%rsp)
+
+	leaq	8(%rsp),%rsp
+
 	vpalignr	$8,%ymm0,%ymm1,%ymm8
 	addq	0+256(%rsp),%r11
 	andq	%r8,%r12
@@ -4513,6 +4527,12 @@ L$avx2_00_47:
 	movq	%r9,%r12
 	vmovdqa	%ymm10,96(%rsp)
 	leaq	-128(%rsp),%rsp
+
+
+	pushq	128-8(%rsp)
+
+	leaq	8(%rsp),%rsp
+
 	vpalignr	$8,%ymm4,%ymm5,%ymm8
 	addq	0+256(%rsp),%r11
 	andq	%r8,%r12
@@ -5426,6 +5446,8 @@ L$ower_avx2:
 
 	leaq	1152(%rsp),%rsp
 
+
+
 	addq	0(%rdi),%rax
 	addq	8(%rdi),%rbx
 	addq	16(%rdi),%rcx
@@ -5451,9 +5473,11 @@ L$ower_avx2:
 	jbe	L$oop_avx2
 	leaq	(%rsp),%rbp
 
+
+
+
 L$done_avx2:
-	leaq	(%rbp),%rsp
-	movq	152(%rsp),%rsi
+	movq	152(%rbp),%rsi
 
 	vzeroupper
 	movq	-48(%rsi),%r15
-- 
2.25.4