diff mbox

[1/2] crypto: arm/sha512 - accelerated SHA-512 using ARM generic ASM and NEON

Message ID 1431074782-22141-1-git-send-email-ard.biesheuvel@linaro.org (mailing list archive)
State Accepted
Delegated to: Herbert Xu
Headers show

Commit Message

Ard Biesheuvel May 8, 2015, 8:46 a.m. UTC
This replaces the SHA-512 NEON module with the faster and more
versatile implementation from the OpenSSL project. It consists
of both a NEON and a generic ASM version of the core SHA-512
transform, where the NEON version reverts to the ASM version
when invoked in non-process context.

This patch is based on the OpenSSL upstream version b1a5d1c65208
of sha512-armv4.pl, which can be found here:

  https://git.openssl.org/gitweb/?p=openssl.git;h=b1a5d1c65208

Performance relative to the generic implementation (measured
using tcrypt.ko mode=306 sec=1 running on a Cortex-A57 under
KVM):

  input size	block size	asm	neon	old neon

  16		16		1.39	2.54	2.21
  64		16		1.32	2.33	2.09
  64		64		1.38	2.53	2.19
  256		16		1.31	2.28	2.06
  256		64		1.38	2.54	2.25
  256		256		1.40	2.77	2.39
  1024		16		1.29	2.22	2.01
  1024		256		1.40	2.82	2.45
  1024		1024		1.41	2.93	2.53
  2048		16		1.33	2.21	2.00
  2048		256		1.40	2.84	2.46
  2048		1024		1.41	2.96	2.55
  2048		2048		1.41	2.98	2.56
  4096		16		1.34	2.20	1.99
  4096		256		1.40	2.84	2.46
  4096		1024		1.41	2.97	2.56
  4096		4096		1.41	3.01	2.58
  8192		16		1.34	2.19	1.99
  8192		256		1.40	2.85	2.47
  8192		1024		1.41	2.98	2.56
  8192		4096		1.41	2.71	2.59
  8192		8192		1.51	3.51	2.69

Acked-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
---

As agreed, I am resending this now for the next merge window.

 arch/arm/crypto/Kconfig               |   16 +-
 arch/arm/crypto/Makefile              |   10 +-
 arch/arm/crypto/sha512-armv4.pl       |  649 ++++++++++++
 arch/arm/crypto/sha512-armv7-neon.S   |  455 --------
 arch/arm/crypto/sha512-core.S_shipped | 1861 +++++++++++++++++++++++++++++++++
 arch/arm/crypto/sha512-glue.c         |  121 +++
 arch/arm/crypto/sha512-neon-glue.c    |   98 ++
 arch/arm/crypto/sha512.h              |    8 +
 arch/arm/crypto/sha512_neon_glue.c    |  305 ------
 9 files changed, 2749 insertions(+), 774 deletions(-)
 create mode 100644 arch/arm/crypto/sha512-armv4.pl
 delete mode 100644 arch/arm/crypto/sha512-armv7-neon.S
 create mode 100644 arch/arm/crypto/sha512-core.S_shipped
 create mode 100644 arch/arm/crypto/sha512-glue.c
 create mode 100644 arch/arm/crypto/sha512-neon-glue.c
 create mode 100644 arch/arm/crypto/sha512.h
 delete mode 100644 arch/arm/crypto/sha512_neon_glue.c

Comments

Ard Biesheuvel May 8, 2015, 9:04 a.m. UTC | #1
On 8 May 2015 at 10:46, Ard Biesheuvel <ard.biesheuvel@linaro.org> wrote:
> This replaces the SHA-512 NEON module with the faster and more
> versatile implementation from the OpenSSL project. It consists
> of both a NEON and a generic ASM version of the core SHA-512
> transform, where the NEON version reverts to the ASM version
> when invoked in non-process context.
>
> This patch is based on the OpenSSL upstream version b1a5d1c65208
> of sha512-armv4.pl, which can be found here:
>
>   https://git.openssl.org/gitweb/?p=openssl.git;h=b1a5d1c65208
>
> Performance relative to the generic implementation (measured
> using tcrypt.ko mode=306 sec=1 running on a Cortex-A57 under
> KVM):
>
>   input size    block size      asm     neon    old neon
>
>   16            16              1.39    2.54    2.21
>   64            16              1.32    2.33    2.09
>   64            64              1.38    2.53    2.19
>   256           16              1.31    2.28    2.06
>   256           64              1.38    2.54    2.25
>   256           256             1.40    2.77    2.39
>   1024          16              1.29    2.22    2.01
>   1024          256             1.40    2.82    2.45
>   1024          1024            1.41    2.93    2.53
>   2048          16              1.33    2.21    2.00
>   2048          256             1.40    2.84    2.46
>   2048          1024            1.41    2.96    2.55
>   2048          2048            1.41    2.98    2.56
>   4096          16              1.34    2.20    1.99
>   4096          256             1.40    2.84    2.46
>   4096          1024            1.41    2.97    2.56
>   4096          4096            1.41    3.01    2.58
>   8192          16              1.34    2.19    1.99
>   8192          256             1.40    2.85    2.47
>   8192          1024            1.41    2.98    2.56
>   8192          4096            1.41    2.71    2.59
>   8192          8192            1.51    3.51    2.69
>
> Acked-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>
> Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
> ---
>
> As agreed, I am resending this now for the next merge window.
>

In case the patch size is a concern again:
https://git.linaro.org/people/ard.biesheuvel/linux-arm.git/shortlog/refs/heads/arm-crypto

[...]
--
To unsubscribe from this list: send the line "unsubscribe linux-crypto" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Herbert Xu May 11, 2015, 6:59 a.m. UTC | #2
On Fri, May 08, 2015 at 10:46:21AM +0200, Ard Biesheuvel wrote:
>
> diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
> index 8da2207b0072..08b5fb85bff5 100644
> --- a/arch/arm/crypto/Kconfig
> +++ b/arch/arm/crypto/Kconfig
> @@ -53,20 +53,14 @@ config CRYPTO_SHA256_ARM
>  	  SHA-256 secure hash standard (DFIPS 180-2) implemented
>  	  using optimized ARM assembler and NEON, when available.
>  
> -config CRYPTO_SHA512_ARM_NEON
> -	tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
> -	depends on KERNEL_MODE_NEON
> -	select CRYPTO_SHA512
> +config CRYPTO_SHA512_ARM
> +	tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)"
> +	depends on !CPU_V7M
>  	select CRYPTO_HASH
> +	depends on !CPU_V7M

This looks like a duplicate, no?
Ard Biesheuvel May 11, 2015, 7 a.m. UTC | #3
On 11 May 2015 at 08:59, Herbert Xu <herbert@gondor.apana.org.au> wrote:
> On Fri, May 08, 2015 at 10:46:21AM +0200, Ard Biesheuvel wrote:
>>
>> diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
>> index 8da2207b0072..08b5fb85bff5 100644
>> --- a/arch/arm/crypto/Kconfig
>> +++ b/arch/arm/crypto/Kconfig
>> @@ -53,20 +53,14 @@ config CRYPTO_SHA256_ARM
>>         SHA-256 secure hash standard (DFIPS 180-2) implemented
>>         using optimized ARM assembler and NEON, when available.
>>
>> -config CRYPTO_SHA512_ARM_NEON
>> -     tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
>> -     depends on KERNEL_MODE_NEON
>> -     select CRYPTO_SHA512
>> +config CRYPTO_SHA512_ARM
>> +     tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)"
>> +     depends on !CPU_V7M
>>       select CRYPTO_HASH
>> +     depends on !CPU_V7M
>
> This looks like a duplicate, no?

Yes, you are right. Let me figure out what's going on and send you a
new version.
--
To unsubscribe from this list: send the line "unsubscribe linux-crypto" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Herbert Xu May 11, 2015, 7:20 a.m. UTC | #4
On Mon, May 11, 2015 at 09:00:49AM +0200, Ard Biesheuvel wrote:
>
> Yes, you are right. Let me figure out what's going on and send you a
> new version.

Don't worry.  I fixed it up while applying the patch.

Cheers,
Ard Biesheuvel May 11, 2015, 7:23 a.m. UTC | #5
On 11 May 2015 at 09:20, Herbert Xu <herbert@gondor.apana.org.au> wrote:
> On Mon, May 11, 2015 at 09:00:49AM +0200, Ard Biesheuvel wrote:
>>
>> Yes, you are right. Let me figure out what's going on and send you a
>> new version.
>
> Don't worry.  I fixed it up while applying the patch.
>

OK, thanks!
--
To unsubscribe from this list: send the line "unsubscribe linux-crypto" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 8da2207b0072..08b5fb85bff5 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -53,20 +53,14 @@  config CRYPTO_SHA256_ARM
 	  SHA-256 secure hash standard (DFIPS 180-2) implemented
 	  using optimized ARM assembler and NEON, when available.
 
-config CRYPTO_SHA512_ARM_NEON
-	tristate "SHA384 and SHA512 digest algorithm (ARM NEON)"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_SHA512
+config CRYPTO_SHA512_ARM
+	tristate "SHA-384/512 digest algorithm (ARM-asm and NEON)"
+	depends on !CPU_V7M
 	select CRYPTO_HASH
+	depends on !CPU_V7M
 	help
 	  SHA-512 secure hash standard (DFIPS 180-2) implemented
-	  using ARM NEON instructions, when available.
-
-	  This version of SHA implements a 512 bit hash with 256 bits of
-	  security against collision attacks.
-
-	  This code also includes SHA-384, a 384 bit hash with 192 bits
-	  of security against collision attacks.
+	  using optimized ARM assembler and NEON, when available.
 
 config CRYPTO_AES_ARM
 	tristate "AES cipher algorithms (ARM-asm)"
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 6ea828241fcb..fc5150702b64 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -7,7 +7,7 @@  obj-$(CONFIG_CRYPTO_AES_ARM_BS) += aes-arm-bs.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
-obj-$(CONFIG_CRYPTO_SHA512_ARM_NEON) += sha512-arm-neon.o
+obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -30,7 +30,8 @@  sha1-arm-y	:= sha1-armv4-large.o sha1_glue.o
 sha1-arm-neon-y	:= sha1-armv7-neon.o sha1_neon_glue.o
 sha256-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha256_neon_glue.o
 sha256-arm-y	:= sha256-core.o sha256_glue.o $(sha256-arm-neon-y)
-sha512-arm-neon-y := sha512-armv7-neon.o sha512_neon_glue.o
+sha512-arm-neon-$(CONFIG_KERNEL_MODE_NEON) := sha512-neon-glue.o
+sha512-arm-y	:= sha512-core.o sha512-glue.o $(sha512-arm-neon-y)
 sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
@@ -45,4 +46,7 @@  $(src)/aesbs-core.S_shipped: $(src)/bsaes-armv7.pl
 $(src)/sha256-core.S_shipped: $(src)/sha256-armv4.pl
 	$(call cmd,perl)
 
-.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S
+$(src)/sha512-core.S_shipped: $(src)/sha512-armv4.pl
+	$(call cmd,perl)
+
+.PRECIOUS: $(obj)/aesbs-core.S $(obj)/sha256-core.S $(obj)/sha512-core.S
diff --git a/arch/arm/crypto/sha512-armv4.pl b/arch/arm/crypto/sha512-armv4.pl
new file mode 100644
index 000000000000..a2b11a844357
--- /dev/null
+++ b/arch/arm/crypto/sha512-armv4.pl
@@ -0,0 +1,649 @@ 
+#!/usr/bin/env perl
+
+# ====================================================================
+# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+# project. The module is, however, dual licensed under OpenSSL and
+# CRYPTOGAMS licenses depending on where you obtain it. For further
+# details see http://www.openssl.org/~appro/cryptogams/.
+#
+# Permission to use under GPL terms is granted.
+# ====================================================================
+
+# SHA512 block procedure for ARMv4. September 2007.
+
+# This code is ~4.5 (four and a half) times faster than code generated
+# by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+# Xscale PXA250 core].
+#
+# July 2010.
+#
+# Rescheduling for dual-issue pipeline resulted in 6% improvement on
+# Cortex A8 core and ~40 cycles per processed byte.
+
+# February 2011.
+#
+# Profiler-assisted and platform-specific optimization resulted in 7%
+# improvement on Coxtex A8 core and ~38 cycles per byte.
+
+# March 2011.
+#
+# Add NEON implementation. On Cortex A8 it was measured to process
+# one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+# August 2012.
+#
+# Improve NEON performance by 12% on Snapdragon S4. In absolute
+# terms it's 22.6 cycles per byte, which is disappointing result.
+# Technical writers asserted that 3-way S4 pipeline can sustain
+# multiple NEON instructions per cycle, but dual NEON issue could
+# not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+# for further details. On side note Cortex-A15 processes one byte in
+# 16 cycles.
+
+# Byte order [in]dependence. =========================================
+#
+# Originally caller was expected to maintain specific *dword* order in
+# h[0-7], namely with most significant dword at *lower* address, which
+# was reflected in below two parameters as 0 and 4. Now caller is
+# expected to maintain native byte order for whole 64-bit values.
+$hi="HI";
+$lo="LO";
+# ====================================================================
+
+while (($output=shift) && ($output!~/^\w[\w\-]*\.\w+$/)) {}
+open STDOUT,">$output";
+
+$ctx="r0";	# parameter block
+$inp="r1";
+$len="r2";
+
+$Tlo="r3";
+$Thi="r4";
+$Alo="r5";
+$Ahi="r6";
+$Elo="r7";
+$Ehi="r8";
+$t0="r9";
+$t1="r10";
+$t2="r11";
+$t3="r12";
+############	r13 is stack pointer
+$Ktbl="r14";
+############	r15 is program counter
+
+$Aoff=8*0;
+$Boff=8*1;
+$Coff=8*2;
+$Doff=8*3;
+$Eoff=8*4;
+$Foff=8*5;
+$Goff=8*6;
+$Hoff=8*7;
+$Xoff=8*8;
+
+sub BODY_00_15() {
+my $magic = shift;
+$code.=<<___;
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	$t0,$Elo,lsr#14
+	str	$Tlo,[sp,#$Xoff+0]
+	mov	$t1,$Ehi,lsr#14
+	str	$Thi,[sp,#$Xoff+4]
+	eor	$t0,$t0,$Ehi,lsl#18
+	ldr	$t2,[sp,#$Hoff+0]	@ h.lo
+	eor	$t1,$t1,$Elo,lsl#18
+	ldr	$t3,[sp,#$Hoff+4]	@ h.hi
+	eor	$t0,$t0,$Elo,lsr#18
+	eor	$t1,$t1,$Ehi,lsr#18
+	eor	$t0,$t0,$Ehi,lsl#14
+	eor	$t1,$t1,$Elo,lsl#14
+	eor	$t0,$t0,$Ehi,lsr#9
+	eor	$t1,$t1,$Elo,lsr#9
+	eor	$t0,$t0,$Elo,lsl#23
+	eor	$t1,$t1,$Ehi,lsl#23	@ Sigma1(e)
+	adds	$Tlo,$Tlo,$t0
+	ldr	$t0,[sp,#$Foff+0]	@ f.lo
+	adc	$Thi,$Thi,$t1		@ T += Sigma1(e)
+	ldr	$t1,[sp,#$Foff+4]	@ f.hi
+	adds	$Tlo,$Tlo,$t2
+	ldr	$t2,[sp,#$Goff+0]	@ g.lo
+	adc	$Thi,$Thi,$t3		@ T += h
+	ldr	$t3,[sp,#$Goff+4]	@ g.hi
+
+	eor	$t0,$t0,$t2
+	str	$Elo,[sp,#$Eoff+0]
+	eor	$t1,$t1,$t3
+	str	$Ehi,[sp,#$Eoff+4]
+	and	$t0,$t0,$Elo
+	str	$Alo,[sp,#$Aoff+0]
+	and	$t1,$t1,$Ehi
+	str	$Ahi,[sp,#$Aoff+4]
+	eor	$t0,$t0,$t2
+	ldr	$t2,[$Ktbl,#$lo]	@ K[i].lo
+	eor	$t1,$t1,$t3		@ Ch(e,f,g)
+	ldr	$t3,[$Ktbl,#$hi]	@ K[i].hi
+
+	adds	$Tlo,$Tlo,$t0
+	ldr	$Elo,[sp,#$Doff+0]	@ d.lo
+	adc	$Thi,$Thi,$t1		@ T += Ch(e,f,g)
+	ldr	$Ehi,[sp,#$Doff+4]	@ d.hi
+	adds	$Tlo,$Tlo,$t2
+	and	$t0,$t2,#0xff
+	adc	$Thi,$Thi,$t3		@ T += K[i]
+	adds	$Elo,$Elo,$Tlo
+	ldr	$t2,[sp,#$Boff+0]	@ b.lo
+	adc	$Ehi,$Ehi,$Thi		@ d += T
+	teq	$t0,#$magic
+
+	ldr	$t3,[sp,#$Coff+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	$Ktbl,$Ktbl,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	$t0,$Alo,lsr#28
+	mov	$t1,$Ahi,lsr#28
+	eor	$t0,$t0,$Ahi,lsl#4
+	eor	$t1,$t1,$Alo,lsl#4
+	eor	$t0,$t0,$Ahi,lsr#2
+	eor	$t1,$t1,$Alo,lsr#2
+	eor	$t0,$t0,$Alo,lsl#30
+	eor	$t1,$t1,$Ahi,lsl#30
+	eor	$t0,$t0,$Ahi,lsr#7
+	eor	$t1,$t1,$Alo,lsr#7
+	eor	$t0,$t0,$Alo,lsl#25
+	eor	$t1,$t1,$Ahi,lsl#25	@ Sigma0(a)
+	adds	$Tlo,$Tlo,$t0
+	and	$t0,$Alo,$t2
+	adc	$Thi,$Thi,$t1		@ T += Sigma0(a)
+
+	ldr	$t1,[sp,#$Boff+4]	@ b.hi
+	orr	$Alo,$Alo,$t2
+	ldr	$t2,[sp,#$Coff+4]	@ c.hi
+	and	$Alo,$Alo,$t3
+	and	$t3,$Ahi,$t1
+	orr	$Ahi,$Ahi,$t1
+	orr	$Alo,$Alo,$t0		@ Maj(a,b,c).lo
+	and	$Ahi,$Ahi,$t2
+	adds	$Alo,$Alo,$Tlo
+	orr	$Ahi,$Ahi,$t3		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	$Ahi,$Ahi,$Thi		@ h += T
+	tst	$Ktbl,#1
+	add	$Ktbl,$Ktbl,#8
+___
+}
+$code=<<___;
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K512,%object
+.align	5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size	K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha512_block_data_order
+.skip	32-4
+#else
+.skip	32
+#endif
+
+.global	sha512_block_data_order
+.type	sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha512_block_data_order
+#else
+	adr	r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#1
+	bne	.LNEON
+#endif
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	stmdb	sp!,{r4-r12,lr}
+	sub	$Ktbl,r3,#672		@ K512
+	sub	sp,sp,#9*8
+
+	ldr	$Elo,[$ctx,#$Eoff+$lo]
+	ldr	$Ehi,[$ctx,#$Eoff+$hi]
+	ldr	$t0, [$ctx,#$Goff+$lo]
+	ldr	$t1, [$ctx,#$Goff+$hi]
+	ldr	$t2, [$ctx,#$Hoff+$lo]
+	ldr	$t3, [$ctx,#$Hoff+$hi]
+.Loop:
+	str	$t0, [sp,#$Goff+0]
+	str	$t1, [sp,#$Goff+4]
+	str	$t2, [sp,#$Hoff+0]
+	str	$t3, [sp,#$Hoff+4]
+	ldr	$Alo,[$ctx,#$Aoff+$lo]
+	ldr	$Ahi,[$ctx,#$Aoff+$hi]
+	ldr	$Tlo,[$ctx,#$Boff+$lo]
+	ldr	$Thi,[$ctx,#$Boff+$hi]
+	ldr	$t0, [$ctx,#$Coff+$lo]
+	ldr	$t1, [$ctx,#$Coff+$hi]
+	ldr	$t2, [$ctx,#$Doff+$lo]
+	ldr	$t3, [$ctx,#$Doff+$hi]
+	str	$Tlo,[sp,#$Boff+0]
+	str	$Thi,[sp,#$Boff+4]
+	str	$t0, [sp,#$Coff+0]
+	str	$t1, [sp,#$Coff+4]
+	str	$t2, [sp,#$Doff+0]
+	str	$t3, [sp,#$Doff+4]
+	ldr	$Tlo,[$ctx,#$Foff+$lo]
+	ldr	$Thi,[$ctx,#$Foff+$hi]
+	str	$Tlo,[sp,#$Foff+0]
+	str	$Thi,[sp,#$Foff+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+	ldrb	$Tlo,[$inp,#7]
+	ldrb	$t0, [$inp,#6]
+	ldrb	$t1, [$inp,#5]
+	ldrb	$t2, [$inp,#4]
+	ldrb	$Thi,[$inp,#3]
+	ldrb	$t3, [$inp,#2]
+	orr	$Tlo,$Tlo,$t0,lsl#8
+	ldrb	$t0, [$inp,#1]
+	orr	$Tlo,$Tlo,$t1,lsl#16
+	ldrb	$t1, [$inp],#8
+	orr	$Tlo,$Tlo,$t2,lsl#24
+	orr	$Thi,$Thi,$t3,lsl#8
+	orr	$Thi,$Thi,$t0,lsl#16
+	orr	$Thi,$Thi,$t1,lsl#24
+#else
+	ldr	$Tlo,[$inp,#4]
+	ldr	$Thi,[$inp],#8
+#ifdef __ARMEL__
+	rev	$Tlo,$Tlo
+	rev	$Thi,$Thi
+#endif
+#endif
+___
+	&BODY_00_15(0x94);
+$code.=<<___;
+	tst	$Ktbl,#1
+	beq	.L00_15
+	ldr	$t0,[sp,#`$Xoff+8*(16-1)`+0]
+	ldr	$t1,[sp,#`$Xoff+8*(16-1)`+4]
+	bic	$Ktbl,$Ktbl,#1
+.L16_79:
+	@ sigma0(x)	(ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+	@ LO		lo>>1^hi<<31  ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+	@ HI		hi>>1^lo<<31  ^ hi>>8^lo<<24 ^ hi>>7
+	mov	$Tlo,$t0,lsr#1
+	ldr	$t2,[sp,#`$Xoff+8*(16-14)`+0]
+	mov	$Thi,$t1,lsr#1
+	ldr	$t3,[sp,#`$Xoff+8*(16-14)`+4]
+	eor	$Tlo,$Tlo,$t1,lsl#31
+	eor	$Thi,$Thi,$t0,lsl#31
+	eor	$Tlo,$Tlo,$t0,lsr#8
+	eor	$Thi,$Thi,$t1,lsr#8
+	eor	$Tlo,$Tlo,$t1,lsl#24
+	eor	$Thi,$Thi,$t0,lsl#24
+	eor	$Tlo,$Tlo,$t0,lsr#7
+	eor	$Thi,$Thi,$t1,lsr#7
+	eor	$Tlo,$Tlo,$t1,lsl#25
+
+	@ sigma1(x)	(ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+	@ LO		lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+	@ HI		hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+	mov	$t0,$t2,lsr#19
+	mov	$t1,$t3,lsr#19
+	eor	$t0,$t0,$t3,lsl#13
+	eor	$t1,$t1,$t2,lsl#13
+	eor	$t0,$t0,$t3,lsr#29
+	eor	$t1,$t1,$t2,lsr#29
+	eor	$t0,$t0,$t2,lsl#3
+	eor	$t1,$t1,$t3,lsl#3
+	eor	$t0,$t0,$t2,lsr#6
+	eor	$t1,$t1,$t3,lsr#6
+	ldr	$t2,[sp,#`$Xoff+8*(16-9)`+0]
+	eor	$t0,$t0,$t3,lsl#26
+
+	ldr	$t3,[sp,#`$Xoff+8*(16-9)`+4]
+	adds	$Tlo,$Tlo,$t0
+	ldr	$t0,[sp,#`$Xoff+8*16`+0]
+	adc	$Thi,$Thi,$t1
+
+	ldr	$t1,[sp,#`$Xoff+8*16`+4]
+	adds	$Tlo,$Tlo,$t2
+	adc	$Thi,$Thi,$t3
+	adds	$Tlo,$Tlo,$t0
+	adc	$Thi,$Thi,$t1
+___
+	&BODY_00_15(0x17);
+$code.=<<___;
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	$t0,[sp,#`$Xoff+8*(16-1)`+0]
+	ldreq	$t1,[sp,#`$Xoff+8*(16-1)`+4]
+	beq	.L16_79
+	bic	$Ktbl,$Ktbl,#1
+
+	ldr	$Tlo,[sp,#$Boff+0]
+	ldr	$Thi,[sp,#$Boff+4]
+	ldr	$t0, [$ctx,#$Aoff+$lo]
+	ldr	$t1, [$ctx,#$Aoff+$hi]
+	ldr	$t2, [$ctx,#$Boff+$lo]
+	ldr	$t3, [$ctx,#$Boff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Aoff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Aoff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Boff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Boff+$hi]
+
+	ldr	$Alo,[sp,#$Coff+0]
+	ldr	$Ahi,[sp,#$Coff+4]
+	ldr	$Tlo,[sp,#$Doff+0]
+	ldr	$Thi,[sp,#$Doff+4]
+	ldr	$t0, [$ctx,#$Coff+$lo]
+	ldr	$t1, [$ctx,#$Coff+$hi]
+	ldr	$t2, [$ctx,#$Doff+$lo]
+	ldr	$t3, [$ctx,#$Doff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Coff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Coff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Doff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Doff+$hi]
+
+	ldr	$Tlo,[sp,#$Foff+0]
+	ldr	$Thi,[sp,#$Foff+4]
+	ldr	$t0, [$ctx,#$Eoff+$lo]
+	ldr	$t1, [$ctx,#$Eoff+$hi]
+	ldr	$t2, [$ctx,#$Foff+$lo]
+	ldr	$t3, [$ctx,#$Foff+$hi]
+	adds	$Elo,$Elo,$t0
+	str	$Elo,[$ctx,#$Eoff+$lo]
+	adc	$Ehi,$Ehi,$t1
+	str	$Ehi,[$ctx,#$Eoff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Foff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Foff+$hi]
+
+	ldr	$Alo,[sp,#$Goff+0]
+	ldr	$Ahi,[sp,#$Goff+4]
+	ldr	$Tlo,[sp,#$Hoff+0]
+	ldr	$Thi,[sp,#$Hoff+4]
+	ldr	$t0, [$ctx,#$Goff+$lo]
+	ldr	$t1, [$ctx,#$Goff+$hi]
+	ldr	$t2, [$ctx,#$Hoff+$lo]
+	ldr	$t3, [$ctx,#$Hoff+$hi]
+	adds	$t0,$Alo,$t0
+	str	$t0, [$ctx,#$Goff+$lo]
+	adc	$t1,$Ahi,$t1
+	str	$t1, [$ctx,#$Goff+$hi]
+	adds	$t2,$Tlo,$t2
+	str	$t2, [$ctx,#$Hoff+$lo]
+	adc	$t3,$Thi,$t3
+	str	$t3, [$ctx,#$Hoff+$hi]
+
+	add	sp,sp,#640
+	sub	$Ktbl,$Ktbl,#640
+
+	teq	$inp,$len
+	bne	.Loop
+
+	add	sp,sp,#8*9		@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r12,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	bx	lr			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha512_block_data_order,.-sha512_block_data_order
+___
+
+{
+my @Sigma0=(28,34,39);
+my @Sigma1=(14,18,41);
+my @sigma0=(1, 8, 7);
+my @sigma1=(19,61,6);
+
+my $Ktbl="r3";
+my $cnt="r12";	# volatile register known as ip, intra-procedure-call scratch
+
+my @X=map("d$_",(0..15));
+my @V=($A,$B,$C,$D,$E,$F,$G,$H)=map("d$_",(16..23));
+
+sub NEON_00_15() {
+my $i=shift;
+my ($a,$b,$c,$d,$e,$f,$g,$h)=@_;
+my ($t0,$t1,$t2,$T1,$K,$Ch,$Maj)=map("d$_",(24..31));	# temps
+
+$code.=<<___ if ($i<16 || $i&1);
+	vshr.u64	$t0,$e,#@Sigma1[0]	@ $i
+#if $i<16
+	vld1.64		{@X[$i%16]},[$inp]!	@ handles unaligned
+#endif
+	vshr.u64	$t1,$e,#@Sigma1[1]
+#if $i>0
+	 vadd.i64	$a,$Maj			@ h+=Maj from the past
+#endif
+	vshr.u64	$t2,$e,#@Sigma1[2]
+___
+$code.=<<___;
+	vld1.64		{$K},[$Ktbl,:64]!	@ K[i++]
+	vsli.64		$t0,$e,#`64-@Sigma1[0]`
+	vsli.64		$t1,$e,#`64-@Sigma1[1]`
+	vmov		$Ch,$e
+	vsli.64		$t2,$e,#`64-@Sigma1[2]`
+#if $i<16 && defined(__ARMEL__)
+	vrev64.8	@X[$i],@X[$i]
+#endif
+	veor		$t1,$t0
+	vbsl		$Ch,$f,$g		@ Ch(e,f,g)
+	vshr.u64	$t0,$a,#@Sigma0[0]
+	veor		$t2,$t1			@ Sigma1(e)
+	vadd.i64	$T1,$Ch,$h
+	vshr.u64	$t1,$a,#@Sigma0[1]
+	vsli.64		$t0,$a,#`64-@Sigma0[0]`
+	vadd.i64	$T1,$t2
+	vshr.u64	$t2,$a,#@Sigma0[2]
+	vadd.i64	$K,@X[$i%16]
+	vsli.64		$t1,$a,#`64-@Sigma0[1]`
+	veor		$Maj,$a,$b
+	vsli.64		$t2,$a,#`64-@Sigma0[2]`
+	veor		$h,$t0,$t1
+	vadd.i64	$T1,$K
+	vbsl		$Maj,$c,$b		@ Maj(a,b,c)
+	veor		$h,$t2			@ Sigma0(a)
+	vadd.i64	$d,$T1
+	vadd.i64	$Maj,$T1
+	@ vadd.i64	$h,$Maj
+___
+}
+
+sub NEON_16_79() {
+my $i=shift;
+
+if ($i&1)	{ &NEON_00_15($i,@_); return; }
+
+# 2x-vectorized, therefore runs every 2nd round
+my @X=map("q$_",(0..7));			# view @X as 128-bit vector
+my ($t0,$t1,$s0,$s1) = map("q$_",(12..15));	# temps
+my ($d0,$d1,$d2) = map("d$_",(24..26));		# temps from NEON_00_15
+my $e=@_[4];					# $e from NEON_00_15
+$i /= 2;
+$code.=<<___;
+	vshr.u64	$t0,@X[($i+7)%8],#@sigma1[0]
+	vshr.u64	$t1,@X[($i+7)%8],#@sigma1[1]
+	 vadd.i64	@_[0],d30			@ h+=Maj from the past
+	vshr.u64	$s1,@X[($i+7)%8],#@sigma1[2]
+	vsli.64		$t0,@X[($i+7)%8],#`64-@sigma1[0]`
+	vext.8		$s0,@X[$i%8],@X[($i+1)%8],#8	@ X[i+1]
+	vsli.64		$t1,@X[($i+7)%8],#`64-@sigma1[1]`
+	veor		$s1,$t0
+	vshr.u64	$t0,$s0,#@sigma0[0]
+	veor		$s1,$t1				@ sigma1(X[i+14])
+	vshr.u64	$t1,$s0,#@sigma0[1]
+	vadd.i64	@X[$i%8],$s1
+	vshr.u64	$s1,$s0,#@sigma0[2]
+	vsli.64		$t0,$s0,#`64-@sigma0[0]`
+	vsli.64		$t1,$s0,#`64-@sigma0[1]`
+	vext.8		$s0,@X[($i+4)%8],@X[($i+5)%8],#8	@ X[i+9]
+	veor		$s1,$t0
+	vshr.u64	$d0,$e,#@Sigma1[0]		@ from NEON_00_15
+	vadd.i64	@X[$i%8],$s0
+	vshr.u64	$d1,$e,#@Sigma1[1]		@ from NEON_00_15
+	veor		$s1,$t1				@ sigma0(X[i+1])
+	vshr.u64	$d2,$e,#@Sigma1[2]		@ from NEON_00_15
+	vadd.i64	@X[$i%8],$s1
+___
+	&NEON_00_15(2*$i,@_);
+}
+
+$code.=<<___;
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
+.align	4
+sha512_block_data_order_neon:
+.LNEON:
+	dmb				@ errata #451034 on early Cortex A8
+	add	$len,$inp,$len,lsl#7	@ len to point at the end of inp
+	VFP_ABI_PUSH
+	adrl	$Ktbl,K512
+	vldmia	$ctx,{$A-$H}		@ load context
+.Loop_neon:
+___
+for($i=0;$i<16;$i++)	{ &NEON_00_15($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	mov		$cnt,#4
+.L16_79_neon:
+	subs		$cnt,#1
+___
+for(;$i<32;$i++)	{ &NEON_16_79($i,@V); unshift(@V,pop(@V)); }
+$code.=<<___;
+	bne		.L16_79_neon
+
+	 vadd.i64	$A,d30		@ h+=Maj from the past
+	vldmia		$ctx,{d24-d31}	@ load context to temp
+	vadd.i64	q8,q12		@ vectorized accumulate
+	vadd.i64	q9,q13
+	vadd.i64	q10,q14
+	vadd.i64	q11,q15
+	vstmia		$ctx,{$A-$H}	@ save context
+	teq		$inp,$len
+	sub		$Ktbl,#640	@ rewind K512
+	bne		.Loop_neon
+
+	VFP_ABI_POP
+	ret				@ bx lr
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+___
+}
+$code.=<<___;
+.asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro\@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm	OPENSSL_armcap_P,4,4
+#endif
+___
+
+$code =~ s/\`([^\`]*)\`/eval $1/gem;
+$code =~ s/\bbx\s+lr\b/.word\t0xe12fff1e/gm;	# make it possible to compile with -march=armv4
+$code =~ s/\bret\b/bx	lr/gm;
+
+open SELF,$0;
+while(<SELF>) {
+	next if (/^#!/);
+	last if (!s/^#/@/ and !/^$/);
+	print;
+}
+close SELF;
+
+print $code;
+close STDOUT; # enforce flush
diff --git a/arch/arm/crypto/sha512-armv7-neon.S b/arch/arm/crypto/sha512-armv7-neon.S
deleted file mode 100644
index fe99472e507c..000000000000
--- a/arch/arm/crypto/sha512-armv7-neon.S
+++ /dev/null
@@ -1,455 +0,0 @@ 
-/* sha512-armv7-neon.S  -  ARM/NEON assembly implementation of SHA-512 transform
- *
- * Copyright © 2013-2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- */
-
-#include <linux/linkage.h>
-
-
-.syntax unified
-.code   32
-.fpu neon
-
-.text
-
-/* structure of SHA512_CONTEXT */
-#define hd_a 0
-#define hd_b ((hd_a) + 8)
-#define hd_c ((hd_b) + 8)
-#define hd_d ((hd_c) + 8)
-#define hd_e ((hd_d) + 8)
-#define hd_f ((hd_e) + 8)
-#define hd_g ((hd_f) + 8)
-
-/* register macros */
-#define RK %r2
-
-#define RA d0
-#define RB d1
-#define RC d2
-#define RD d3
-#define RE d4
-#define RF d5
-#define RG d6
-#define RH d7
-
-#define RT0 d8
-#define RT1 d9
-#define RT2 d10
-#define RT3 d11
-#define RT4 d12
-#define RT5 d13
-#define RT6 d14
-#define RT7 d15
-
-#define RT01q q4
-#define RT23q q5
-#define RT45q q6
-#define RT67q q7
-
-#define RW0 d16
-#define RW1 d17
-#define RW2 d18
-#define RW3 d19
-#define RW4 d20
-#define RW5 d21
-#define RW6 d22
-#define RW7 d23
-#define RW8 d24
-#define RW9 d25
-#define RW10 d26
-#define RW11 d27
-#define RW12 d28
-#define RW13 d29
-#define RW14 d30
-#define RW15 d31
-
-#define RW01q q8
-#define RW23q q9
-#define RW45q q10
-#define RW67q q11
-#define RW89q q12
-#define RW1011q q13
-#define RW1213q q14
-#define RW1415q q15
-
-/***********************************************************************
- * ARM assembly implementation of sha512 transform
- ***********************************************************************/
-#define rounds2_0_63(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, rw01q, rw2, \
-                     rw23q, rw1415q, rw9, rw10, interleave_op, arg1) \
-	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
-	vshr.u64 RT2, re, #14; \
-	vshl.u64 RT3, re, #64 - 14; \
-	interleave_op(arg1); \
-	vshr.u64 RT4, re, #18; \
-	vshl.u64 RT5, re, #64 - 18; \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, re, #41; \
-	vshl.u64 RT5, re, #64 - 41; \
-	vadd.u64 RT0, RT0, rw0; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, re; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, rf, rg; \
-	\
-	vadd.u64 RT1, RT1, rh; \
-	vshr.u64 RT2, ra, #28; \
-	vshl.u64 RT3, ra, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, ra, #34; \
-	vshl.u64 RT5, ra, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* h = Sum0 (a) + Maj (a, b, c); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, ra, #39; \
-	vshl.u64 RT5, ra, #64 - 39; \
-	veor.64 RT0, ra, rb; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rc, rb; \
-	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
-	veor.64 rh, RT2, RT3; \
-	\
-	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
-	vshr.u64 RT2, rd, #14; \
-	vshl.u64 RT3, rd, #64 - 14; \
-	vadd.u64 rh, rh, RT0; \
-	vshr.u64 RT4, rd, #18; \
-	vshl.u64 RT5, rd, #64 - 18; \
-	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rd, #41; \
-	vshl.u64 RT5, rd, #64 - 41; \
-	vadd.u64 RT0, RT0, rw1; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, rd; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, re, rf; \
-	\
-	vadd.u64 RT1, RT1, rg; \
-	vshr.u64 RT2, rh, #28; \
-	vshl.u64 RT3, rh, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, rh, #34; \
-	vshl.u64 RT5, rh, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* g = Sum0 (h) + Maj (h, a, b); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rh, #39; \
-	vshl.u64 RT5, rh, #64 - 39; \
-	veor.64 RT0, rh, ra; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rb, ra; \
-	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
-	veor.64 rg, RT2, RT3; \
-	\
-	/* w[0] += S1 (w[14]) + w[9] + S0 (w[1]); */ \
-	/* w[1] += S1 (w[15]) + w[10] + S0 (w[2]); */ \
-	\
-	/**** S0(w[1:2]) */ \
-	\
-	/* w[0:1] += w[9:10] */ \
-	/* RT23q = rw1:rw2 */ \
-	vext.u64 RT23q, rw01q, rw23q, #1; \
-	vadd.u64 rw0, rw9; \
-	vadd.u64 rg, rg, RT0; \
-	vadd.u64 rw1, rw10;\
-	vadd.u64 rg, rg, RT1; /* g+=t1; */ \
-	\
-	vshr.u64 RT45q, RT23q, #1; \
-	vshl.u64 RT67q, RT23q, #64 - 1; \
-	vshr.u64 RT01q, RT23q, #8; \
-	veor.u64 RT45q, RT45q, RT67q; \
-	vshl.u64 RT67q, RT23q, #64 - 8; \
-	veor.u64 RT45q, RT45q, RT01q; \
-	vshr.u64 RT01q, RT23q, #7; \
-	veor.u64 RT45q, RT45q, RT67q; \
-	\
-	/**** S1(w[14:15]) */ \
-	vshr.u64 RT23q, rw1415q, #6; \
-	veor.u64 RT01q, RT01q, RT45q; \
-	vshr.u64 RT45q, rw1415q, #19; \
-	vshl.u64 RT67q, rw1415q, #64 - 19; \
-	veor.u64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT45q, rw1415q, #61; \
-	veor.u64 RT23q, RT23q, RT67q; \
-	vshl.u64 RT67q, rw1415q, #64 - 61; \
-	veor.u64 RT23q, RT23q, RT45q; \
-	vadd.u64 rw01q, RT01q; /* w[0:1] += S(w[1:2]) */ \
-	veor.u64 RT01q, RT23q, RT67q;
-#define vadd_RT01q(rw01q) \
-	/* w[0:1] += S(w[14:15]) */ \
-	vadd.u64 rw01q, RT01q;
-
-#define dummy(_) /*_*/
-
-#define rounds2_64_79(ra, rb, rc, rd, re, rf, rg, rh, rw0, rw1, \
-	              interleave_op1, arg1, interleave_op2, arg2) \
-	/* t1 = h + Sum1 (e) + Ch (e, f, g) + k[t] + w[t]; */ \
-	vshr.u64 RT2, re, #14; \
-	vshl.u64 RT3, re, #64 - 14; \
-	interleave_op1(arg1); \
-	vshr.u64 RT4, re, #18; \
-	vshl.u64 RT5, re, #64 - 18; \
-	interleave_op2(arg2); \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, re, #41; \
-	vshl.u64 RT5, re, #64 - 41; \
-	vadd.u64 RT0, RT0, rw0; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, re; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, rf, rg; \
-	\
-	vadd.u64 RT1, RT1, rh; \
-	vshr.u64 RT2, ra, #28; \
-	vshl.u64 RT3, ra, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, ra, #34; \
-	vshl.u64 RT5, ra, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* h = Sum0 (a) + Maj (a, b, c); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, ra, #39; \
-	vshl.u64 RT5, ra, #64 - 39; \
-	veor.64 RT0, ra, rb; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rc, rb; \
-	vadd.u64 rd, rd, RT1; /* d+=t1; */ \
-	veor.64 rh, RT2, RT3; \
-	\
-	/* t1 = g + Sum1 (d) + Ch (d, e, f) + k[t] + w[t]; */ \
-	vshr.u64 RT2, rd, #14; \
-	vshl.u64 RT3, rd, #64 - 14; \
-	vadd.u64 rh, rh, RT0; \
-	vshr.u64 RT4, rd, #18; \
-	vshl.u64 RT5, rd, #64 - 18; \
-	vadd.u64 rh, rh, RT1; /* h+=t1; */ \
-	vld1.64 {RT0}, [RK]!; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rd, #41; \
-	vshl.u64 RT5, rd, #64 - 41; \
-	vadd.u64 RT0, RT0, rw1; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vmov.64 RT7, rd; \
-	veor.64 RT1, RT2, RT3; \
-	vbsl.64 RT7, re, rf; \
-	\
-	vadd.u64 RT1, RT1, rg; \
-	vshr.u64 RT2, rh, #28; \
-	vshl.u64 RT3, rh, #64 - 28; \
-	vadd.u64 RT1, RT1, RT0; \
-	vshr.u64 RT4, rh, #34; \
-	vshl.u64 RT5, rh, #64 - 34; \
-	vadd.u64 RT1, RT1, RT7; \
-	\
-	/* g = Sum0 (h) + Maj (h, a, b); */ \
-	veor.64 RT23q, RT23q, RT45q; \
-	vshr.u64 RT4, rh, #39; \
-	vshl.u64 RT5, rh, #64 - 39; \
-	veor.64 RT0, rh, ra; \
-	veor.64 RT23q, RT23q, RT45q; \
-	vbsl.64 RT0, rb, ra; \
-	vadd.u64 rc, rc, RT1; /* c+=t1; */ \
-	veor.64 rg, RT2, RT3;
-#define vadd_rg_RT0(rg) \
-	vadd.u64 rg, rg, RT0;
-#define vadd_rg_RT1(rg) \
-	vadd.u64 rg, rg, RT1; /* g+=t1; */
-
-.align 3
-ENTRY(sha512_transform_neon)
-	/* Input:
-	 *	%r0: SHA512_CONTEXT
-	 *	%r1: data
-	 *	%r2: u64 k[] constants
-	 *	%r3: nblks
-	 */
-	push {%lr};
-
-	mov %lr, #0;
-
-	/* Load context to d0-d7 */
-	vld1.64 {RA-RD}, [%r0]!;
-	vld1.64 {RE-RH}, [%r0];
-	sub %r0, #(4*8);
-
-	/* Load input to w[16], d16-d31 */
-	/* NOTE: Assumes that on ARMv7 unaligned accesses are always allowed. */
-	vld1.64 {RW0-RW3}, [%r1]!;
-	vld1.64 {RW4-RW7}, [%r1]!;
-	vld1.64 {RW8-RW11}, [%r1]!;
-	vld1.64 {RW12-RW15}, [%r1]!;
-#ifdef __ARMEL__
-	/* byteswap */
-	vrev64.8 RW01q, RW01q;
-	vrev64.8 RW23q, RW23q;
-	vrev64.8 RW45q, RW45q;
-	vrev64.8 RW67q, RW67q;
-	vrev64.8 RW89q, RW89q;
-	vrev64.8 RW1011q, RW1011q;
-	vrev64.8 RW1213q, RW1213q;
-	vrev64.8 RW1415q, RW1415q;
-#endif
-
-	/* EABI says that d8-d15 must be preserved by callee. */
-	/*vpush {RT0-RT7};*/
-
-.Loop:
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
-		     RW23q, RW1415q, RW9, RW10, dummy, _);
-	b .Lenter_rounds;
-
-.Loop_rounds:
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1, RW01q, RW2,
-		     RW23q, RW1415q, RW9, RW10, vadd_RT01q, RW1415q);
-.Lenter_rounds:
-	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3, RW23q, RW4,
-		     RW45q, RW01q, RW11, RW12, vadd_RT01q, RW01q);
-	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5, RW45q, RW6,
-		     RW67q, RW23q, RW13, RW14, vadd_RT01q, RW23q);
-	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7, RW67q, RW8,
-		     RW89q, RW45q, RW15, RW0, vadd_RT01q, RW45q);
-	rounds2_0_63(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9, RW89q, RW10,
-		     RW1011q, RW67q, RW1, RW2, vadd_RT01q, RW67q);
-	rounds2_0_63(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11, RW1011q, RW12,
-		     RW1213q, RW89q, RW3, RW4, vadd_RT01q, RW89q);
-	add %lr, #16;
-	rounds2_0_63(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13, RW1213q, RW14,
-		     RW1415q, RW1011q, RW5, RW6, vadd_RT01q, RW1011q);
-	cmp %lr, #64;
-	rounds2_0_63(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15, RW1415q, RW0,
-		     RW01q, RW1213q, RW7, RW8, vadd_RT01q, RW1213q);
-	bne .Loop_rounds;
-
-	subs %r3, #1;
-
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW0, RW1,
-		      vadd_RT01q, RW1415q, dummy, _);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW2, RW3,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-	beq .Lhandle_tail;
-	vld1.64 {RW0-RW3}, [%r1]!;
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
-	vrev64.8 RW01q, RW01q;
-	vrev64.8 RW23q, RW23q;
-#endif
-	vld1.64 {RW4-RW7}, [%r1]!;
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
-		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-#ifdef __ARMEL__
-	vrev64.8 RW45q, RW45q;
-	vrev64.8 RW67q, RW67q;
-#endif
-	vld1.64 {RW8-RW11}, [%r1]!;
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-#ifdef __ARMEL__
-	vrev64.8 RW89q, RW89q;
-	vrev64.8 RW1011q, RW1011q;
-#endif
-	vld1.64 {RW12-RW15}, [%r1]!;
-	vadd_rg_RT0(RA);
-	vadd_rg_RT1(RA);
-
-	/* Load context */
-	vld1.64 {RT0-RT3}, [%r0]!;
-	vld1.64 {RT4-RT7}, [%r0];
-	sub %r0, #(4*8);
-
-#ifdef __ARMEL__
-	vrev64.8 RW1213q, RW1213q;
-	vrev64.8 RW1415q, RW1415q;
-#endif
-
-	vadd.u64 RA, RT0;
-	vadd.u64 RB, RT1;
-	vadd.u64 RC, RT2;
-	vadd.u64 RD, RT3;
-	vadd.u64 RE, RT4;
-	vadd.u64 RF, RT5;
-	vadd.u64 RG, RT6;
-	vadd.u64 RH, RT7;
-
-	/* Store the first half of context */
-	vst1.64 {RA-RD}, [%r0]!;
-	sub RK, $(8*80);
-	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
-	mov %lr, #0;
-	sub %r0, #(4*8);
-
-	b .Loop;
-
-.Lhandle_tail:
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW4, RW5,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW6, RW7,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-	rounds2_64_79(RA, RB, RC, RD, RE, RF, RG, RH, RW8, RW9,
-		      vadd_rg_RT0, RA, vadd_rg_RT1, RA);
-	rounds2_64_79(RG, RH, RA, RB, RC, RD, RE, RF, RW10, RW11,
-		      vadd_rg_RT0, RG, vadd_rg_RT1, RG);
-	rounds2_64_79(RE, RF, RG, RH, RA, RB, RC, RD, RW12, RW13,
-		      vadd_rg_RT0, RE, vadd_rg_RT1, RE);
-	rounds2_64_79(RC, RD, RE, RF, RG, RH, RA, RB, RW14, RW15,
-		      vadd_rg_RT0, RC, vadd_rg_RT1, RC);
-
-	/* Load context to d16-d23 */
-	vld1.64 {RW0-RW3}, [%r0]!;
-	vadd_rg_RT0(RA);
-	vld1.64 {RW4-RW7}, [%r0];
-	vadd_rg_RT1(RA);
-	sub %r0, #(4*8);
-
-	vadd.u64 RA, RW0;
-	vadd.u64 RB, RW1;
-	vadd.u64 RC, RW2;
-	vadd.u64 RD, RW3;
-	vadd.u64 RE, RW4;
-	vadd.u64 RF, RW5;
-	vadd.u64 RG, RW6;
-	vadd.u64 RH, RW7;
-
-	/* Store the first half of context */
-	vst1.64 {RA-RD}, [%r0]!;
-
-	/* Clear used registers */
-	/* d16-d31 */
-	veor.u64 RW01q, RW01q;
-	veor.u64 RW23q, RW23q;
-	veor.u64 RW45q, RW45q;
-	veor.u64 RW67q, RW67q;
-	vst1.64 {RE-RH}, [%r0]; /* Store the last half of context */
-	veor.u64 RW89q, RW89q;
-	veor.u64 RW1011q, RW1011q;
-	veor.u64 RW1213q, RW1213q;
-	veor.u64 RW1415q, RW1415q;
-	/* d8-d15 */
-	/*vpop {RT0-RT7};*/
-	/* d0-d7 (q0-q3) */
-	veor.u64 %q0, %q0;
-	veor.u64 %q1, %q1;
-	veor.u64 %q2, %q2;
-	veor.u64 %q3, %q3;
-
-	pop {%pc};
-ENDPROC(sha512_transform_neon)
diff --git a/arch/arm/crypto/sha512-core.S_shipped b/arch/arm/crypto/sha512-core.S_shipped
new file mode 100644
index 000000000000..3694c4d4ca2b
--- /dev/null
+++ b/arch/arm/crypto/sha512-core.S_shipped
@@ -0,0 +1,1861 @@ 
+
+@ ====================================================================
+@ Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
+@ project. The module is, however, dual licensed under OpenSSL and
+@ CRYPTOGAMS licenses depending on where you obtain it. For further
+@ details see http://www.openssl.org/~appro/cryptogams/.
+@
+@ Permission to use under GPL terms is granted.
+@ ====================================================================
+
+@ SHA512 block procedure for ARMv4. September 2007.
+
+@ This code is ~4.5 (four and a half) times faster than code generated
+@ by gcc 3.4 and it spends ~72 clock cycles per byte [on single-issue
+@ Xscale PXA250 core].
+@
+@ July 2010.
+@
+@ Rescheduling for dual-issue pipeline resulted in 6% improvement on
+@ Cortex A8 core and ~40 cycles per processed byte.
+
+@ February 2011.
+@
+@ Profiler-assisted and platform-specific optimization resulted in 7%
+@ improvement on Coxtex A8 core and ~38 cycles per byte.
+
+@ March 2011.
+@
+@ Add NEON implementation. On Cortex A8 it was measured to process
+@ one byte in 23.3 cycles or ~60% faster than integer-only code.
+
+@ August 2012.
+@
+@ Improve NEON performance by 12% on Snapdragon S4. In absolute
+@ terms it's 22.6 cycles per byte, which is disappointing result.
+@ Technical writers asserted that 3-way S4 pipeline can sustain
+@ multiple NEON instructions per cycle, but dual NEON issue could
+@ not be observed, see http://www.openssl.org/~appro/Snapdragon-S4.html
+@ for further details. On side note Cortex-A15 processes one byte in
+@ 16 cycles.
+
+@ Byte order [in]dependence. =========================================
+@
+@ Originally caller was expected to maintain specific *dword* order in
+@ h[0-7], namely with most significant dword at *lower* address, which
+@ was reflected in below two parameters as 0 and 4. Now caller is
+@ expected to maintain native byte order for whole 64-bit values.
+#ifndef __KERNEL__
+# include "arm_arch.h"
+# define VFP_ABI_PUSH	vstmdb	sp!,{d8-d15}
+# define VFP_ABI_POP	vldmia	sp!,{d8-d15}
+#else
+# define __ARM_ARCH__ __LINUX_ARM_ARCH__
+# define __ARM_MAX_ARCH__ 7
+# define VFP_ABI_PUSH
+# define VFP_ABI_POP
+#endif
+
+#ifdef __ARMEL__
+# define LO 0
+# define HI 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	lo0,hi0, lo1,hi1
+#else
+# define HI 0
+# define LO 4
+# define WORD64(hi0,lo0,hi1,lo1)	.word	hi0,lo0, hi1,lo1
+#endif
+
+.text
+#if __ARM_ARCH__<7
+.code	32
+#else
+.syntax unified
+# ifdef __thumb2__
+#  define adrl adr
+.thumb
+# else
+.code   32
+# endif
+#endif
+
+.type	K512,%object
+.align	5
+K512:
+WORD64(0x428a2f98,0xd728ae22, 0x71374491,0x23ef65cd)
+WORD64(0xb5c0fbcf,0xec4d3b2f, 0xe9b5dba5,0x8189dbbc)
+WORD64(0x3956c25b,0xf348b538, 0x59f111f1,0xb605d019)
+WORD64(0x923f82a4,0xaf194f9b, 0xab1c5ed5,0xda6d8118)
+WORD64(0xd807aa98,0xa3030242, 0x12835b01,0x45706fbe)
+WORD64(0x243185be,0x4ee4b28c, 0x550c7dc3,0xd5ffb4e2)
+WORD64(0x72be5d74,0xf27b896f, 0x80deb1fe,0x3b1696b1)
+WORD64(0x9bdc06a7,0x25c71235, 0xc19bf174,0xcf692694)
+WORD64(0xe49b69c1,0x9ef14ad2, 0xefbe4786,0x384f25e3)
+WORD64(0x0fc19dc6,0x8b8cd5b5, 0x240ca1cc,0x77ac9c65)
+WORD64(0x2de92c6f,0x592b0275, 0x4a7484aa,0x6ea6e483)
+WORD64(0x5cb0a9dc,0xbd41fbd4, 0x76f988da,0x831153b5)
+WORD64(0x983e5152,0xee66dfab, 0xa831c66d,0x2db43210)
+WORD64(0xb00327c8,0x98fb213f, 0xbf597fc7,0xbeef0ee4)
+WORD64(0xc6e00bf3,0x3da88fc2, 0xd5a79147,0x930aa725)
+WORD64(0x06ca6351,0xe003826f, 0x14292967,0x0a0e6e70)
+WORD64(0x27b70a85,0x46d22ffc, 0x2e1b2138,0x5c26c926)
+WORD64(0x4d2c6dfc,0x5ac42aed, 0x53380d13,0x9d95b3df)
+WORD64(0x650a7354,0x8baf63de, 0x766a0abb,0x3c77b2a8)
+WORD64(0x81c2c92e,0x47edaee6, 0x92722c85,0x1482353b)
+WORD64(0xa2bfe8a1,0x4cf10364, 0xa81a664b,0xbc423001)
+WORD64(0xc24b8b70,0xd0f89791, 0xc76c51a3,0x0654be30)
+WORD64(0xd192e819,0xd6ef5218, 0xd6990624,0x5565a910)
+WORD64(0xf40e3585,0x5771202a, 0x106aa070,0x32bbd1b8)
+WORD64(0x19a4c116,0xb8d2d0c8, 0x1e376c08,0x5141ab53)
+WORD64(0x2748774c,0xdf8eeb99, 0x34b0bcb5,0xe19b48a8)
+WORD64(0x391c0cb3,0xc5c95a63, 0x4ed8aa4a,0xe3418acb)
+WORD64(0x5b9cca4f,0x7763e373, 0x682e6ff3,0xd6b2b8a3)
+WORD64(0x748f82ee,0x5defb2fc, 0x78a5636f,0x43172f60)
+WORD64(0x84c87814,0xa1f0ab72, 0x8cc70208,0x1a6439ec)
+WORD64(0x90befffa,0x23631e28, 0xa4506ceb,0xde82bde9)
+WORD64(0xbef9a3f7,0xb2c67915, 0xc67178f2,0xe372532b)
+WORD64(0xca273ece,0xea26619c, 0xd186b8c7,0x21c0c207)
+WORD64(0xeada7dd6,0xcde0eb1e, 0xf57d4f7f,0xee6ed178)
+WORD64(0x06f067aa,0x72176fba, 0x0a637dc5,0xa2c898a6)
+WORD64(0x113f9804,0xbef90dae, 0x1b710b35,0x131c471b)
+WORD64(0x28db77f5,0x23047d84, 0x32caab7b,0x40c72493)
+WORD64(0x3c9ebe0a,0x15c9bebc, 0x431d67c4,0x9c100d4c)
+WORD64(0x4cc5d4be,0xcb3e42b6, 0x597f299c,0xfc657e2a)
+WORD64(0x5fcb6fab,0x3ad6faec, 0x6c44198c,0x4a475817)
+.size	K512,.-K512
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.LOPENSSL_armcap:
+.word	OPENSSL_armcap_P-sha512_block_data_order
+.skip	32-4
+#else
+.skip	32
+#endif
+
+.global	sha512_block_data_order
+.type	sha512_block_data_order,%function
+sha512_block_data_order:
+#if __ARM_ARCH__<7
+	sub	r3,pc,#8		@ sha512_block_data_order
+#else
+	adr	r3,sha512_block_data_order
+#endif
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+	ldr	r12,.LOPENSSL_armcap
+	ldr	r12,[r3,r12]		@ OPENSSL_armcap_P
+	tst	r12,#1
+	bne	.LNEON
+#endif
+	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
+	stmdb	sp!,{r4-r12,lr}
+	sub	r14,r3,#672		@ K512
+	sub	sp,sp,#9*8
+
+	ldr	r7,[r0,#32+LO]
+	ldr	r8,[r0,#32+HI]
+	ldr	r9, [r0,#48+LO]
+	ldr	r10, [r0,#48+HI]
+	ldr	r11, [r0,#56+LO]
+	ldr	r12, [r0,#56+HI]
+.Loop:
+	str	r9, [sp,#48+0]
+	str	r10, [sp,#48+4]
+	str	r11, [sp,#56+0]
+	str	r12, [sp,#56+4]
+	ldr	r5,[r0,#0+LO]
+	ldr	r6,[r0,#0+HI]
+	ldr	r3,[r0,#8+LO]
+	ldr	r4,[r0,#8+HI]
+	ldr	r9, [r0,#16+LO]
+	ldr	r10, [r0,#16+HI]
+	ldr	r11, [r0,#24+LO]
+	ldr	r12, [r0,#24+HI]
+	str	r3,[sp,#8+0]
+	str	r4,[sp,#8+4]
+	str	r9, [sp,#16+0]
+	str	r10, [sp,#16+4]
+	str	r11, [sp,#24+0]
+	str	r12, [sp,#24+4]
+	ldr	r3,[r0,#40+LO]
+	ldr	r4,[r0,#40+HI]
+	str	r3,[sp,#40+0]
+	str	r4,[sp,#40+4]
+
+.L00_15:
+#if __ARM_ARCH__<7
+	ldrb	r3,[r1,#7]
+	ldrb	r9, [r1,#6]
+	ldrb	r10, [r1,#5]
+	ldrb	r11, [r1,#4]
+	ldrb	r4,[r1,#3]
+	ldrb	r12, [r1,#2]
+	orr	r3,r3,r9,lsl#8
+	ldrb	r9, [r1,#1]
+	orr	r3,r3,r10,lsl#16
+	ldrb	r10, [r1],#8
+	orr	r3,r3,r11,lsl#24
+	orr	r4,r4,r12,lsl#8
+	orr	r4,r4,r9,lsl#16
+	orr	r4,r4,r10,lsl#24
+#else
+	ldr	r3,[r1,#4]
+	ldr	r4,[r1],#8
+#ifdef __ARMEL__
+	rev	r3,r3
+	rev	r4,r4
+#endif
+#endif
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	r9,r7,lsr#14
+	str	r3,[sp,#64+0]
+	mov	r10,r8,lsr#14
+	str	r4,[sp,#64+4]
+	eor	r9,r9,r8,lsl#18
+	ldr	r11,[sp,#56+0]	@ h.lo
+	eor	r10,r10,r7,lsl#18
+	ldr	r12,[sp,#56+4]	@ h.hi
+	eor	r9,r9,r7,lsr#18
+	eor	r10,r10,r8,lsr#18
+	eor	r9,r9,r8,lsl#14
+	eor	r10,r10,r7,lsl#14
+	eor	r9,r9,r8,lsr#9
+	eor	r10,r10,r7,lsr#9
+	eor	r9,r9,r7,lsl#23
+	eor	r10,r10,r8,lsl#23	@ Sigma1(e)
+	adds	r3,r3,r9
+	ldr	r9,[sp,#40+0]	@ f.lo
+	adc	r4,r4,r10		@ T += Sigma1(e)
+	ldr	r10,[sp,#40+4]	@ f.hi
+	adds	r3,r3,r11
+	ldr	r11,[sp,#48+0]	@ g.lo
+	adc	r4,r4,r12		@ T += h
+	ldr	r12,[sp,#48+4]	@ g.hi
+
+	eor	r9,r9,r11
+	str	r7,[sp,#32+0]
+	eor	r10,r10,r12
+	str	r8,[sp,#32+4]
+	and	r9,r9,r7
+	str	r5,[sp,#0+0]
+	and	r10,r10,r8
+	str	r6,[sp,#0+4]
+	eor	r9,r9,r11
+	ldr	r11,[r14,#LO]	@ K[i].lo
+	eor	r10,r10,r12		@ Ch(e,f,g)
+	ldr	r12,[r14,#HI]	@ K[i].hi
+
+	adds	r3,r3,r9
+	ldr	r7,[sp,#24+0]	@ d.lo
+	adc	r4,r4,r10		@ T += Ch(e,f,g)
+	ldr	r8,[sp,#24+4]	@ d.hi
+	adds	r3,r3,r11
+	and	r9,r11,#0xff
+	adc	r4,r4,r12		@ T += K[i]
+	adds	r7,r7,r3
+	ldr	r11,[sp,#8+0]	@ b.lo
+	adc	r8,r8,r4		@ d += T
+	teq	r9,#148
+
+	ldr	r12,[sp,#16+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	r14,r14,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	r9,r5,lsr#28
+	mov	r10,r6,lsr#28
+	eor	r9,r9,r6,lsl#4
+	eor	r10,r10,r5,lsl#4
+	eor	r9,r9,r6,lsr#2
+	eor	r10,r10,r5,lsr#2
+	eor	r9,r9,r5,lsl#30
+	eor	r10,r10,r6,lsl#30
+	eor	r9,r9,r6,lsr#7
+	eor	r10,r10,r5,lsr#7
+	eor	r9,r9,r5,lsl#25
+	eor	r10,r10,r6,lsl#25	@ Sigma0(a)
+	adds	r3,r3,r9
+	and	r9,r5,r11
+	adc	r4,r4,r10		@ T += Sigma0(a)
+
+	ldr	r10,[sp,#8+4]	@ b.hi
+	orr	r5,r5,r11
+	ldr	r11,[sp,#16+4]	@ c.hi
+	and	r5,r5,r12
+	and	r12,r6,r10
+	orr	r6,r6,r10
+	orr	r5,r5,r9		@ Maj(a,b,c).lo
+	and	r6,r6,r11
+	adds	r5,r5,r3
+	orr	r6,r6,r12		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	r6,r6,r4		@ h += T
+	tst	r14,#1
+	add	r14,r14,#8
+	tst	r14,#1
+	beq	.L00_15
+	ldr	r9,[sp,#184+0]
+	ldr	r10,[sp,#184+4]
+	bic	r14,r14,#1
+.L16_79:
+	@ sigma0(x)	(ROTR((x),1)  ^ ROTR((x),8)  ^ ((x)>>7))
+	@ LO		lo>>1^hi<<31  ^ lo>>8^hi<<24 ^ lo>>7^hi<<25
+	@ HI		hi>>1^lo<<31  ^ hi>>8^lo<<24 ^ hi>>7
+	mov	r3,r9,lsr#1
+	ldr	r11,[sp,#80+0]
+	mov	r4,r10,lsr#1
+	ldr	r12,[sp,#80+4]
+	eor	r3,r3,r10,lsl#31
+	eor	r4,r4,r9,lsl#31
+	eor	r3,r3,r9,lsr#8
+	eor	r4,r4,r10,lsr#8
+	eor	r3,r3,r10,lsl#24
+	eor	r4,r4,r9,lsl#24
+	eor	r3,r3,r9,lsr#7
+	eor	r4,r4,r10,lsr#7
+	eor	r3,r3,r10,lsl#25
+
+	@ sigma1(x)	(ROTR((x),19) ^ ROTR((x),61) ^ ((x)>>6))
+	@ LO		lo>>19^hi<<13 ^ hi>>29^lo<<3 ^ lo>>6^hi<<26
+	@ HI		hi>>19^lo<<13 ^ lo>>29^hi<<3 ^ hi>>6
+	mov	r9,r11,lsr#19
+	mov	r10,r12,lsr#19
+	eor	r9,r9,r12,lsl#13
+	eor	r10,r10,r11,lsl#13
+	eor	r9,r9,r12,lsr#29
+	eor	r10,r10,r11,lsr#29
+	eor	r9,r9,r11,lsl#3
+	eor	r10,r10,r12,lsl#3
+	eor	r9,r9,r11,lsr#6
+	eor	r10,r10,r12,lsr#6
+	ldr	r11,[sp,#120+0]
+	eor	r9,r9,r12,lsl#26
+
+	ldr	r12,[sp,#120+4]
+	adds	r3,r3,r9
+	ldr	r9,[sp,#192+0]
+	adc	r4,r4,r10
+
+	ldr	r10,[sp,#192+4]
+	adds	r3,r3,r11
+	adc	r4,r4,r12
+	adds	r3,r3,r9
+	adc	r4,r4,r10
+	@ Sigma1(x)	(ROTR((x),14) ^ ROTR((x),18)  ^ ROTR((x),41))
+	@ LO		lo>>14^hi<<18 ^ lo>>18^hi<<14 ^ hi>>9^lo<<23
+	@ HI		hi>>14^lo<<18 ^ hi>>18^lo<<14 ^ lo>>9^hi<<23
+	mov	r9,r7,lsr#14
+	str	r3,[sp,#64+0]
+	mov	r10,r8,lsr#14
+	str	r4,[sp,#64+4]
+	eor	r9,r9,r8,lsl#18
+	ldr	r11,[sp,#56+0]	@ h.lo
+	eor	r10,r10,r7,lsl#18
+	ldr	r12,[sp,#56+4]	@ h.hi
+	eor	r9,r9,r7,lsr#18
+	eor	r10,r10,r8,lsr#18
+	eor	r9,r9,r8,lsl#14
+	eor	r10,r10,r7,lsl#14
+	eor	r9,r9,r8,lsr#9
+	eor	r10,r10,r7,lsr#9
+	eor	r9,r9,r7,lsl#23
+	eor	r10,r10,r8,lsl#23	@ Sigma1(e)
+	adds	r3,r3,r9
+	ldr	r9,[sp,#40+0]	@ f.lo
+	adc	r4,r4,r10		@ T += Sigma1(e)
+	ldr	r10,[sp,#40+4]	@ f.hi
+	adds	r3,r3,r11
+	ldr	r11,[sp,#48+0]	@ g.lo
+	adc	r4,r4,r12		@ T += h
+	ldr	r12,[sp,#48+4]	@ g.hi
+
+	eor	r9,r9,r11
+	str	r7,[sp,#32+0]
+	eor	r10,r10,r12
+	str	r8,[sp,#32+4]
+	and	r9,r9,r7
+	str	r5,[sp,#0+0]
+	and	r10,r10,r8
+	str	r6,[sp,#0+4]
+	eor	r9,r9,r11
+	ldr	r11,[r14,#LO]	@ K[i].lo
+	eor	r10,r10,r12		@ Ch(e,f,g)
+	ldr	r12,[r14,#HI]	@ K[i].hi
+
+	adds	r3,r3,r9
+	ldr	r7,[sp,#24+0]	@ d.lo
+	adc	r4,r4,r10		@ T += Ch(e,f,g)
+	ldr	r8,[sp,#24+4]	@ d.hi
+	adds	r3,r3,r11
+	and	r9,r11,#0xff
+	adc	r4,r4,r12		@ T += K[i]
+	adds	r7,r7,r3
+	ldr	r11,[sp,#8+0]	@ b.lo
+	adc	r8,r8,r4		@ d += T
+	teq	r9,#23
+
+	ldr	r12,[sp,#16+0]	@ c.lo
+#if __ARM_ARCH__>=7
+	it	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	orreq	r14,r14,#1
+	@ Sigma0(x)	(ROTR((x),28) ^ ROTR((x),34) ^ ROTR((x),39))
+	@ LO		lo>>28^hi<<4  ^ hi>>2^lo<<30 ^ hi>>7^lo<<25
+	@ HI		hi>>28^lo<<4  ^ lo>>2^hi<<30 ^ lo>>7^hi<<25
+	mov	r9,r5,lsr#28
+	mov	r10,r6,lsr#28
+	eor	r9,r9,r6,lsl#4
+	eor	r10,r10,r5,lsl#4
+	eor	r9,r9,r6,lsr#2
+	eor	r10,r10,r5,lsr#2
+	eor	r9,r9,r5,lsl#30
+	eor	r10,r10,r6,lsl#30
+	eor	r9,r9,r6,lsr#7
+	eor	r10,r10,r5,lsr#7
+	eor	r9,r9,r5,lsl#25
+	eor	r10,r10,r6,lsl#25	@ Sigma0(a)
+	adds	r3,r3,r9
+	and	r9,r5,r11
+	adc	r4,r4,r10		@ T += Sigma0(a)
+
+	ldr	r10,[sp,#8+4]	@ b.hi
+	orr	r5,r5,r11
+	ldr	r11,[sp,#16+4]	@ c.hi
+	and	r5,r5,r12
+	and	r12,r6,r10
+	orr	r6,r6,r10
+	orr	r5,r5,r9		@ Maj(a,b,c).lo
+	and	r6,r6,r11
+	adds	r5,r5,r3
+	orr	r6,r6,r12		@ Maj(a,b,c).hi
+	sub	sp,sp,#8
+	adc	r6,r6,r4		@ h += T
+	tst	r14,#1
+	add	r14,r14,#8
+#if __ARM_ARCH__>=7
+	ittt	eq			@ Thumb2 thing, sanity check in ARM
+#endif
+	ldreq	r9,[sp,#184+0]
+	ldreq	r10,[sp,#184+4]
+	beq	.L16_79
+	bic	r14,r14,#1
+
+	ldr	r3,[sp,#8+0]
+	ldr	r4,[sp,#8+4]
+	ldr	r9, [r0,#0+LO]
+	ldr	r10, [r0,#0+HI]
+	ldr	r11, [r0,#8+LO]
+	ldr	r12, [r0,#8+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#0+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#0+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#8+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#8+HI]
+
+	ldr	r5,[sp,#16+0]
+	ldr	r6,[sp,#16+4]
+	ldr	r3,[sp,#24+0]
+	ldr	r4,[sp,#24+4]
+	ldr	r9, [r0,#16+LO]
+	ldr	r10, [r0,#16+HI]
+	ldr	r11, [r0,#24+LO]
+	ldr	r12, [r0,#24+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#16+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#16+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#24+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#24+HI]
+
+	ldr	r3,[sp,#40+0]
+	ldr	r4,[sp,#40+4]
+	ldr	r9, [r0,#32+LO]
+	ldr	r10, [r0,#32+HI]
+	ldr	r11, [r0,#40+LO]
+	ldr	r12, [r0,#40+HI]
+	adds	r7,r7,r9
+	str	r7,[r0,#32+LO]
+	adc	r8,r8,r10
+	str	r8,[r0,#32+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#40+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#40+HI]
+
+	ldr	r5,[sp,#48+0]
+	ldr	r6,[sp,#48+4]
+	ldr	r3,[sp,#56+0]
+	ldr	r4,[sp,#56+4]
+	ldr	r9, [r0,#48+LO]
+	ldr	r10, [r0,#48+HI]
+	ldr	r11, [r0,#56+LO]
+	ldr	r12, [r0,#56+HI]
+	adds	r9,r5,r9
+	str	r9, [r0,#48+LO]
+	adc	r10,r6,r10
+	str	r10, [r0,#48+HI]
+	adds	r11,r3,r11
+	str	r11, [r0,#56+LO]
+	adc	r12,r4,r12
+	str	r12, [r0,#56+HI]
+
+	add	sp,sp,#640
+	sub	r14,r14,#640
+
+	teq	r1,r2
+	bne	.Loop
+
+	add	sp,sp,#8*9		@ destroy frame
+#if __ARM_ARCH__>=5
+	ldmia	sp!,{r4-r12,pc}
+#else
+	ldmia	sp!,{r4-r12,lr}
+	tst	lr,#1
+	moveq	pc,lr			@ be binary compatible with V4, yet
+	.word	0xe12fff1e			@ interoperable with Thumb ISA:-)
+#endif
+.size	sha512_block_data_order,.-sha512_block_data_order
+#if __ARM_MAX_ARCH__>=7
+.arch	armv7-a
+.fpu	neon
+
+.global	sha512_block_data_order_neon
+.type	sha512_block_data_order_neon,%function
+.align	4
+sha512_block_data_order_neon:
+.LNEON:
+	dmb				@ errata #451034 on early Cortex A8
+	add	r2,r1,r2,lsl#7	@ len to point at the end of inp
+	VFP_ABI_PUSH
+	adrl	r3,K512
+	vldmia	r0,{d16-d23}		@ load context
+.Loop_neon:
+	vshr.u64	d24,d20,#14	@ 0
+#if 0<16
+	vld1.64		{d0},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d20,#18
+#if 0>0
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d20,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 0<16 && defined(__ARMEL__)
+	vrev64.8	d0,d0
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d0
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 1
+#if 1<16
+	vld1.64		{d1},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 1>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 1<16 && defined(__ARMEL__)
+	vrev64.8	d1,d1
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d1
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	d24,d18,#14	@ 2
+#if 2<16
+	vld1.64		{d2},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d18,#18
+#if 2>0
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d18,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 2<16 && defined(__ARMEL__)
+	vrev64.8	d2,d2
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d2
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 3
+#if 3<16
+	vld1.64		{d3},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 3>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 3<16 && defined(__ARMEL__)
+	vrev64.8	d3,d3
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d3
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	d24,d16,#14	@ 4
+#if 4<16
+	vld1.64		{d4},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d16,#18
+#if 4>0
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d16,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 4<16 && defined(__ARMEL__)
+	vrev64.8	d4,d4
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d4
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 5
+#if 5<16
+	vld1.64		{d5},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 5>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 5<16 && defined(__ARMEL__)
+	vrev64.8	d5,d5
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d5
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	d24,d22,#14	@ 6
+#if 6<16
+	vld1.64		{d6},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d22,#18
+#if 6>0
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d22,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 6<16 && defined(__ARMEL__)
+	vrev64.8	d6,d6
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d6
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 7
+#if 7<16
+	vld1.64		{d7},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 7>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 7<16 && defined(__ARMEL__)
+	vrev64.8	d7,d7
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d7
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	vshr.u64	d24,d20,#14	@ 8
+#if 8<16
+	vld1.64		{d8},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d20,#18
+#if 8>0
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d20,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 8<16 && defined(__ARMEL__)
+	vrev64.8	d8,d8
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d8
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 9
+#if 9<16
+	vld1.64		{d9},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 9>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 9<16 && defined(__ARMEL__)
+	vrev64.8	d9,d9
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d9
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	d24,d18,#14	@ 10
+#if 10<16
+	vld1.64		{d10},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d18,#18
+#if 10>0
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d18,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 10<16 && defined(__ARMEL__)
+	vrev64.8	d10,d10
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d10
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 11
+#if 11<16
+	vld1.64		{d11},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 11>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 11<16 && defined(__ARMEL__)
+	vrev64.8	d11,d11
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d11
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	d24,d16,#14	@ 12
+#if 12<16
+	vld1.64		{d12},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d16,#18
+#if 12>0
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d16,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 12<16 && defined(__ARMEL__)
+	vrev64.8	d12,d12
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d12
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 13
+#if 13<16
+	vld1.64		{d13},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 13>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 13<16 && defined(__ARMEL__)
+	vrev64.8	d13,d13
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d13
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	d24,d22,#14	@ 14
+#if 14<16
+	vld1.64		{d14},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d22,#18
+#if 14>0
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d22,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 14<16 && defined(__ARMEL__)
+	vrev64.8	d14,d14
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d14
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 15
+#if 15<16
+	vld1.64		{d15},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 15>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 15<16 && defined(__ARMEL__)
+	vrev64.8	d15,d15
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d15
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	mov		r12,#4
+.L16_79_neon:
+	subs		r12,#1
+	vshr.u64	q12,q7,#19
+	vshr.u64	q13,q7,#61
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+	vshr.u64	q15,q7,#6
+	vsli.64		q12,q7,#45
+	vext.8		q14,q0,q1,#8	@ X[i+1]
+	vsli.64		q13,q7,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q0,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q4,q5,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d20,#14		@ from NEON_00_15
+	vadd.i64	q0,q14
+	vshr.u64	d25,d20,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d20,#41		@ from NEON_00_15
+	vadd.i64	q0,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 16<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d0
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 17
+#if 17<16
+	vld1.64		{d1},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 17>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 17<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d1
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	q12,q0,#19
+	vshr.u64	q13,q0,#61
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+	vshr.u64	q15,q0,#6
+	vsli.64		q12,q0,#45
+	vext.8		q14,q1,q2,#8	@ X[i+1]
+	vsli.64		q13,q0,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q1,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q5,q6,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d18,#14		@ from NEON_00_15
+	vadd.i64	q1,q14
+	vshr.u64	d25,d18,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d18,#41		@ from NEON_00_15
+	vadd.i64	q1,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 18<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d2
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 19
+#if 19<16
+	vld1.64		{d3},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 19>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 19<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d3
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	q12,q1,#19
+	vshr.u64	q13,q1,#61
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+	vshr.u64	q15,q1,#6
+	vsli.64		q12,q1,#45
+	vext.8		q14,q2,q3,#8	@ X[i+1]
+	vsli.64		q13,q1,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q2,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q6,q7,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d16,#14		@ from NEON_00_15
+	vadd.i64	q2,q14
+	vshr.u64	d25,d16,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d16,#41		@ from NEON_00_15
+	vadd.i64	q2,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 20<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d4
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 21
+#if 21<16
+	vld1.64		{d5},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 21>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 21<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d5
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	q12,q2,#19
+	vshr.u64	q13,q2,#61
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+	vshr.u64	q15,q2,#6
+	vsli.64		q12,q2,#45
+	vext.8		q14,q3,q4,#8	@ X[i+1]
+	vsli.64		q13,q2,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q3,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q7,q0,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d22,#14		@ from NEON_00_15
+	vadd.i64	q3,q14
+	vshr.u64	d25,d22,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d22,#41		@ from NEON_00_15
+	vadd.i64	q3,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 22<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d6
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 23
+#if 23<16
+	vld1.64		{d7},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 23>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 23<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d7
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	vshr.u64	q12,q3,#19
+	vshr.u64	q13,q3,#61
+	 vadd.i64	d16,d30			@ h+=Maj from the past
+	vshr.u64	q15,q3,#6
+	vsli.64		q12,q3,#45
+	vext.8		q14,q4,q5,#8	@ X[i+1]
+	vsli.64		q13,q3,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q4,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q0,q1,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d20,#14		@ from NEON_00_15
+	vadd.i64	q4,q14
+	vshr.u64	d25,d20,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d20,#41		@ from NEON_00_15
+	vadd.i64	q4,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d20,#50
+	vsli.64		d25,d20,#46
+	vmov		d29,d20
+	vsli.64		d26,d20,#23
+#if 24<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d21,d22		@ Ch(e,f,g)
+	vshr.u64	d24,d16,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d23
+	vshr.u64	d25,d16,#34
+	vsli.64		d24,d16,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d16,#39
+	vadd.i64	d28,d8
+	vsli.64		d25,d16,#30
+	veor		d30,d16,d17
+	vsli.64		d26,d16,#25
+	veor		d23,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d18,d17		@ Maj(a,b,c)
+	veor		d23,d26			@ Sigma0(a)
+	vadd.i64	d19,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d23,d30
+	vshr.u64	d24,d19,#14	@ 25
+#if 25<16
+	vld1.64		{d9},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d19,#18
+#if 25>0
+	 vadd.i64	d23,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d19,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d19,#50
+	vsli.64		d25,d19,#46
+	vmov		d29,d19
+	vsli.64		d26,d19,#23
+#if 25<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d20,d21		@ Ch(e,f,g)
+	vshr.u64	d24,d23,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d22
+	vshr.u64	d25,d23,#34
+	vsli.64		d24,d23,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d23,#39
+	vadd.i64	d28,d9
+	vsli.64		d25,d23,#30
+	veor		d30,d23,d16
+	vsli.64		d26,d23,#25
+	veor		d22,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d17,d16		@ Maj(a,b,c)
+	veor		d22,d26			@ Sigma0(a)
+	vadd.i64	d18,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d22,d30
+	vshr.u64	q12,q4,#19
+	vshr.u64	q13,q4,#61
+	 vadd.i64	d22,d30			@ h+=Maj from the past
+	vshr.u64	q15,q4,#6
+	vsli.64		q12,q4,#45
+	vext.8		q14,q5,q6,#8	@ X[i+1]
+	vsli.64		q13,q4,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q5,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q1,q2,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d18,#14		@ from NEON_00_15
+	vadd.i64	q5,q14
+	vshr.u64	d25,d18,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d18,#41		@ from NEON_00_15
+	vadd.i64	q5,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d18,#50
+	vsli.64		d25,d18,#46
+	vmov		d29,d18
+	vsli.64		d26,d18,#23
+#if 26<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d19,d20		@ Ch(e,f,g)
+	vshr.u64	d24,d22,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d21
+	vshr.u64	d25,d22,#34
+	vsli.64		d24,d22,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d22,#39
+	vadd.i64	d28,d10
+	vsli.64		d25,d22,#30
+	veor		d30,d22,d23
+	vsli.64		d26,d22,#25
+	veor		d21,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d16,d23		@ Maj(a,b,c)
+	veor		d21,d26			@ Sigma0(a)
+	vadd.i64	d17,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d21,d30
+	vshr.u64	d24,d17,#14	@ 27
+#if 27<16
+	vld1.64		{d11},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d17,#18
+#if 27>0
+	 vadd.i64	d21,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d17,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d17,#50
+	vsli.64		d25,d17,#46
+	vmov		d29,d17
+	vsli.64		d26,d17,#23
+#if 27<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d18,d19		@ Ch(e,f,g)
+	vshr.u64	d24,d21,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d20
+	vshr.u64	d25,d21,#34
+	vsli.64		d24,d21,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d21,#39
+	vadd.i64	d28,d11
+	vsli.64		d25,d21,#30
+	veor		d30,d21,d22
+	vsli.64		d26,d21,#25
+	veor		d20,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d23,d22		@ Maj(a,b,c)
+	veor		d20,d26			@ Sigma0(a)
+	vadd.i64	d16,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d20,d30
+	vshr.u64	q12,q5,#19
+	vshr.u64	q13,q5,#61
+	 vadd.i64	d20,d30			@ h+=Maj from the past
+	vshr.u64	q15,q5,#6
+	vsli.64		q12,q5,#45
+	vext.8		q14,q6,q7,#8	@ X[i+1]
+	vsli.64		q13,q5,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q6,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q2,q3,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d16,#14		@ from NEON_00_15
+	vadd.i64	q6,q14
+	vshr.u64	d25,d16,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d16,#41		@ from NEON_00_15
+	vadd.i64	q6,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d16,#50
+	vsli.64		d25,d16,#46
+	vmov		d29,d16
+	vsli.64		d26,d16,#23
+#if 28<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d17,d18		@ Ch(e,f,g)
+	vshr.u64	d24,d20,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d19
+	vshr.u64	d25,d20,#34
+	vsli.64		d24,d20,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d20,#39
+	vadd.i64	d28,d12
+	vsli.64		d25,d20,#30
+	veor		d30,d20,d21
+	vsli.64		d26,d20,#25
+	veor		d19,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d22,d21		@ Maj(a,b,c)
+	veor		d19,d26			@ Sigma0(a)
+	vadd.i64	d23,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d19,d30
+	vshr.u64	d24,d23,#14	@ 29
+#if 29<16
+	vld1.64		{d13},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d23,#18
+#if 29>0
+	 vadd.i64	d19,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d23,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d23,#50
+	vsli.64		d25,d23,#46
+	vmov		d29,d23
+	vsli.64		d26,d23,#23
+#if 29<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d16,d17		@ Ch(e,f,g)
+	vshr.u64	d24,d19,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d18
+	vshr.u64	d25,d19,#34
+	vsli.64		d24,d19,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d19,#39
+	vadd.i64	d28,d13
+	vsli.64		d25,d19,#30
+	veor		d30,d19,d20
+	vsli.64		d26,d19,#25
+	veor		d18,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d21,d20		@ Maj(a,b,c)
+	veor		d18,d26			@ Sigma0(a)
+	vadd.i64	d22,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d18,d30
+	vshr.u64	q12,q6,#19
+	vshr.u64	q13,q6,#61
+	 vadd.i64	d18,d30			@ h+=Maj from the past
+	vshr.u64	q15,q6,#6
+	vsli.64		q12,q6,#45
+	vext.8		q14,q7,q0,#8	@ X[i+1]
+	vsli.64		q13,q6,#3
+	veor		q15,q12
+	vshr.u64	q12,q14,#1
+	veor		q15,q13				@ sigma1(X[i+14])
+	vshr.u64	q13,q14,#8
+	vadd.i64	q7,q15
+	vshr.u64	q15,q14,#7
+	vsli.64		q12,q14,#63
+	vsli.64		q13,q14,#56
+	vext.8		q14,q3,q4,#8	@ X[i+9]
+	veor		q15,q12
+	vshr.u64	d24,d22,#14		@ from NEON_00_15
+	vadd.i64	q7,q14
+	vshr.u64	d25,d22,#18		@ from NEON_00_15
+	veor		q15,q13				@ sigma0(X[i+1])
+	vshr.u64	d26,d22,#41		@ from NEON_00_15
+	vadd.i64	q7,q15
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d22,#50
+	vsli.64		d25,d22,#46
+	vmov		d29,d22
+	vsli.64		d26,d22,#23
+#if 30<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d23,d16		@ Ch(e,f,g)
+	vshr.u64	d24,d18,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d17
+	vshr.u64	d25,d18,#34
+	vsli.64		d24,d18,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d18,#39
+	vadd.i64	d28,d14
+	vsli.64		d25,d18,#30
+	veor		d30,d18,d19
+	vsli.64		d26,d18,#25
+	veor		d17,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d20,d19		@ Maj(a,b,c)
+	veor		d17,d26			@ Sigma0(a)
+	vadd.i64	d21,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d17,d30
+	vshr.u64	d24,d21,#14	@ 31
+#if 31<16
+	vld1.64		{d15},[r1]!	@ handles unaligned
+#endif
+	vshr.u64	d25,d21,#18
+#if 31>0
+	 vadd.i64	d17,d30			@ h+=Maj from the past
+#endif
+	vshr.u64	d26,d21,#41
+	vld1.64		{d28},[r3,:64]!	@ K[i++]
+	vsli.64		d24,d21,#50
+	vsli.64		d25,d21,#46
+	vmov		d29,d21
+	vsli.64		d26,d21,#23
+#if 31<16 && defined(__ARMEL__)
+	vrev64.8	,
+#endif
+	veor		d25,d24
+	vbsl		d29,d22,d23		@ Ch(e,f,g)
+	vshr.u64	d24,d17,#28
+	veor		d26,d25			@ Sigma1(e)
+	vadd.i64	d27,d29,d16
+	vshr.u64	d25,d17,#34
+	vsli.64		d24,d17,#36
+	vadd.i64	d27,d26
+	vshr.u64	d26,d17,#39
+	vadd.i64	d28,d15
+	vsli.64		d25,d17,#30
+	veor		d30,d17,d18
+	vsli.64		d26,d17,#25
+	veor		d16,d24,d25
+	vadd.i64	d27,d28
+	vbsl		d30,d19,d18		@ Maj(a,b,c)
+	veor		d16,d26			@ Sigma0(a)
+	vadd.i64	d20,d27
+	vadd.i64	d30,d27
+	@ vadd.i64	d16,d30
+	bne		.L16_79_neon
+
+	 vadd.i64	d16,d30		@ h+=Maj from the past
+	vldmia		r0,{d24-d31}	@ load context to temp
+	vadd.i64	q8,q12		@ vectorized accumulate
+	vadd.i64	q9,q13
+	vadd.i64	q10,q14
+	vadd.i64	q11,q15
+	vstmia		r0,{d16-d23}	@ save context
+	teq		r1,r2
+	sub		r3,#640	@ rewind K512
+	bne		.Loop_neon
+
+	VFP_ABI_POP
+	bx	lr				@ .word	0xe12fff1e
+.size	sha512_block_data_order_neon,.-sha512_block_data_order_neon
+#endif
+.asciz	"SHA512 block transform for ARMv4/NEON, CRYPTOGAMS by <appro@openssl.org>"
+.align	2
+#if __ARM_MAX_ARCH__>=7 && !defined(__KERNEL__)
+.comm	OPENSSL_armcap_P,4,4
+#endif
diff --git a/arch/arm/crypto/sha512-glue.c b/arch/arm/crypto/sha512-glue.c
new file mode 100644
index 000000000000..269a394e4a53
--- /dev/null
+++ b/arch/arm/crypto/sha512-glue.c
@@ -0,0 +1,121 @@ 
+/*
+ * sha512-glue.c - accelerated SHA-384/512 for ARM
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/hwcap.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_DESCRIPTION("Accelerated SHA-384/SHA-512 secure hash for ARM");
+MODULE_AUTHOR("Ard Biesheuvel <ard.biesheuvel@linaro.org>");
+MODULE_LICENSE("GPL v2");
+
+MODULE_ALIAS_CRYPTO("sha384");
+MODULE_ALIAS_CRYPTO("sha512");
+MODULE_ALIAS_CRYPTO("sha384-arm");
+MODULE_ALIAS_CRYPTO("sha512-arm");
+
+asmlinkage void sha512_block_data_order(u64 *state, u8 const *src, int blocks);
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+		      unsigned int len)
+{
+	return sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order);
+}
+
+int sha512_arm_final(struct shash_desc *desc, u8 *out)
+{
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_base_finish(desc, out);
+}
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+		     unsigned int len, u8 *out)
+{
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order);
+	return sha512_arm_final(desc, out);
+}
+
+static struct shash_alg sha512_arm_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_arm_update,
+	.final			= sha512_arm_final,
+	.finup			= sha512_arm_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-arm",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_arm_update,
+	.final			= sha512_arm_final,
+	.finup			= sha512_arm_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-arm",
+		.cra_priority		= 250,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
+
+static int __init sha512_arm_mod_init(void)
+{
+	int err;
+
+	err = crypto_register_shashes(sha512_arm_algs,
+				      ARRAY_SIZE(sha512_arm_algs));
+	if (err)
+		return err;
+
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon()) {
+		err = crypto_register_shashes(sha512_neon_algs,
+					      ARRAY_SIZE(sha512_neon_algs));
+		if (err)
+			goto err_unregister;
+	}
+	return 0;
+
+err_unregister:
+	crypto_unregister_shashes(sha512_arm_algs,
+				  ARRAY_SIZE(sha512_arm_algs));
+
+	return err;
+}
+
+static void __exit sha512_arm_mod_fini(void)
+{
+	crypto_unregister_shashes(sha512_arm_algs,
+				  ARRAY_SIZE(sha512_arm_algs));
+	if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && cpu_has_neon())
+		crypto_unregister_shashes(sha512_neon_algs,
+					  ARRAY_SIZE(sha512_neon_algs));
+}
+
+module_init(sha512_arm_mod_init);
+module_exit(sha512_arm_mod_fini);
diff --git a/arch/arm/crypto/sha512-neon-glue.c b/arch/arm/crypto/sha512-neon-glue.c
new file mode 100644
index 000000000000..32693684a3ab
--- /dev/null
+++ b/arch/arm/crypto/sha512-neon-glue.c
@@ -0,0 +1,98 @@ 
+/*
+ * sha512-neon-glue.c - accelerated SHA-384/512 for ARM NEON
+ *
+ * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sha.h>
+#include <crypto/sha512_base.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+
+#include <asm/simd.h>
+#include <asm/neon.h>
+
+#include "sha512.h"
+
+MODULE_ALIAS_CRYPTO("sha384-neon");
+MODULE_ALIAS_CRYPTO("sha512-neon");
+
+asmlinkage void sha512_block_data_order_neon(u64 *state, u8 const *src,
+					     int blocks);
+
+static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len)
+{
+	struct sha512_state *sctx = shash_desc_ctx(desc);
+
+	if (!may_use_simd() ||
+	    (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
+		return sha512_arm_update(desc, data, len);
+
+	kernel_neon_begin();
+	sha512_base_do_update(desc, data, len,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return 0;
+}
+
+static int sha512_neon_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *out)
+{
+	if (!may_use_simd())
+		return sha512_arm_finup(desc, data, len, out);
+
+	kernel_neon_begin();
+	if (len)
+		sha512_base_do_update(desc, data, len,
+			(sha512_block_fn *)sha512_block_data_order_neon);
+	sha512_base_do_finalize(desc,
+		(sha512_block_fn *)sha512_block_data_order_neon);
+	kernel_neon_end();
+
+	return sha512_base_finish(desc, out);
+}
+
+static int sha512_neon_final(struct shash_desc *desc, u8 *out)
+{
+	return sha512_neon_finup(desc, NULL, 0, out);
+}
+
+struct shash_alg sha512_neon_algs[] = { {
+	.init			= sha384_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA384_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha384",
+		.cra_driver_name	= "sha384-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA384_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+
+	}
+},  {
+	.init			= sha512_base_init,
+	.update			= sha512_neon_update,
+	.final			= sha512_neon_final,
+	.finup			= sha512_neon_finup,
+	.descsize		= sizeof(struct sha512_state),
+	.digestsize		= SHA512_DIGEST_SIZE,
+	.base			= {
+		.cra_name		= "sha512",
+		.cra_driver_name	= "sha512-neon",
+		.cra_priority		= 300,
+		.cra_flags		= CRYPTO_ALG_TYPE_SHASH,
+		.cra_blocksize		= SHA512_BLOCK_SIZE,
+		.cra_module		= THIS_MODULE,
+	}
+} };
diff --git a/arch/arm/crypto/sha512.h b/arch/arm/crypto/sha512.h
new file mode 100644
index 000000000000..a75d9a82988a
--- /dev/null
+++ b/arch/arm/crypto/sha512.h
@@ -0,0 +1,8 @@ 
+
+int sha512_arm_update(struct shash_desc *desc, const u8 *data,
+		      unsigned int len);
+
+int sha512_arm_finup(struct shash_desc *desc, const u8 *data,
+		     unsigned int len, u8 *out);
+
+extern struct shash_alg sha512_neon_algs[2];
diff --git a/arch/arm/crypto/sha512_neon_glue.c b/arch/arm/crypto/sha512_neon_glue.c
deleted file mode 100644
index b124dce838d6..000000000000
--- a/arch/arm/crypto/sha512_neon_glue.c
+++ /dev/null
@@ -1,305 +0,0 @@ 
-/*
- * Glue code for the SHA512 Secure Hash Algorithm assembly implementation
- * using NEON instructions.
- *
- * Copyright © 2014 Jussi Kivilinna <jussi.kivilinna@iki.fi>
- *
- * This file is based on sha512_ssse3_glue.c:
- *   Copyright (C) 2013 Intel Corporation
- *   Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- */
-
-#include <crypto/internal/hash.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/cryptohash.h>
-#include <linux/types.h>
-#include <linux/string.h>
-#include <crypto/sha.h>
-#include <asm/byteorder.h>
-#include <asm/simd.h>
-#include <asm/neon.h>
-
-
-static const u64 sha512_k[] = {
-	0x428a2f98d728ae22ULL, 0x7137449123ef65cdULL,
-	0xb5c0fbcfec4d3b2fULL, 0xe9b5dba58189dbbcULL,
-	0x3956c25bf348b538ULL, 0x59f111f1b605d019ULL,
-	0x923f82a4af194f9bULL, 0xab1c5ed5da6d8118ULL,
-	0xd807aa98a3030242ULL, 0x12835b0145706fbeULL,
-	0x243185be4ee4b28cULL, 0x550c7dc3d5ffb4e2ULL,
-	0x72be5d74f27b896fULL, 0x80deb1fe3b1696b1ULL,
-	0x9bdc06a725c71235ULL, 0xc19bf174cf692694ULL,
-	0xe49b69c19ef14ad2ULL, 0xefbe4786384f25e3ULL,
-	0x0fc19dc68b8cd5b5ULL, 0x240ca1cc77ac9c65ULL,
-	0x2de92c6f592b0275ULL, 0x4a7484aa6ea6e483ULL,
-	0x5cb0a9dcbd41fbd4ULL, 0x76f988da831153b5ULL,
-	0x983e5152ee66dfabULL, 0xa831c66d2db43210ULL,
-	0xb00327c898fb213fULL, 0xbf597fc7beef0ee4ULL,
-	0xc6e00bf33da88fc2ULL, 0xd5a79147930aa725ULL,
-	0x06ca6351e003826fULL, 0x142929670a0e6e70ULL,
-	0x27b70a8546d22ffcULL, 0x2e1b21385c26c926ULL,
-	0x4d2c6dfc5ac42aedULL, 0x53380d139d95b3dfULL,
-	0x650a73548baf63deULL, 0x766a0abb3c77b2a8ULL,
-	0x81c2c92e47edaee6ULL, 0x92722c851482353bULL,
-	0xa2bfe8a14cf10364ULL, 0xa81a664bbc423001ULL,
-	0xc24b8b70d0f89791ULL, 0xc76c51a30654be30ULL,
-	0xd192e819d6ef5218ULL, 0xd69906245565a910ULL,
-	0xf40e35855771202aULL, 0x106aa07032bbd1b8ULL,
-	0x19a4c116b8d2d0c8ULL, 0x1e376c085141ab53ULL,
-	0x2748774cdf8eeb99ULL, 0x34b0bcb5e19b48a8ULL,
-	0x391c0cb3c5c95a63ULL, 0x4ed8aa4ae3418acbULL,
-	0x5b9cca4f7763e373ULL, 0x682e6ff3d6b2b8a3ULL,
-	0x748f82ee5defb2fcULL, 0x78a5636f43172f60ULL,
-	0x84c87814a1f0ab72ULL, 0x8cc702081a6439ecULL,
-	0x90befffa23631e28ULL, 0xa4506cebde82bde9ULL,
-	0xbef9a3f7b2c67915ULL, 0xc67178f2e372532bULL,
-	0xca273eceea26619cULL, 0xd186b8c721c0c207ULL,
-	0xeada7dd6cde0eb1eULL, 0xf57d4f7fee6ed178ULL,
-	0x06f067aa72176fbaULL, 0x0a637dc5a2c898a6ULL,
-	0x113f9804bef90daeULL, 0x1b710b35131c471bULL,
-	0x28db77f523047d84ULL, 0x32caab7b40c72493ULL,
-	0x3c9ebe0a15c9bebcULL, 0x431d67c49c100d4cULL,
-	0x4cc5d4becb3e42b6ULL, 0x597f299cfc657e2aULL,
-	0x5fcb6fab3ad6faecULL, 0x6c44198c4a475817ULL
-};
-
-
-asmlinkage void sha512_transform_neon(u64 *digest, const void *data,
-				      const u64 k[], unsigned int num_blks);
-
-
-static int sha512_neon_init(struct shash_desc *desc)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA512_H0;
-	sctx->state[1] = SHA512_H1;
-	sctx->state[2] = SHA512_H2;
-	sctx->state[3] = SHA512_H3;
-	sctx->state[4] = SHA512_H4;
-	sctx->state[5] = SHA512_H5;
-	sctx->state[6] = SHA512_H6;
-	sctx->state[7] = SHA512_H7;
-	sctx->count[0] = sctx->count[1] = 0;
-
-	return 0;
-}
-
-static int __sha512_neon_update(struct shash_desc *desc, const u8 *data,
-				unsigned int len, unsigned int partial)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int done = 0;
-
-	sctx->count[0] += len;
-	if (sctx->count[0] < len)
-		sctx->count[1]++;
-
-	if (partial) {
-		done = SHA512_BLOCK_SIZE - partial;
-		memcpy(sctx->buf + partial, data, done);
-		sha512_transform_neon(sctx->state, sctx->buf, sha512_k, 1);
-	}
-
-	if (len - done >= SHA512_BLOCK_SIZE) {
-		const unsigned int rounds = (len - done) / SHA512_BLOCK_SIZE;
-
-		sha512_transform_neon(sctx->state, data + done, sha512_k,
-				      rounds);
-
-		done += rounds * SHA512_BLOCK_SIZE;
-	}
-
-	memcpy(sctx->buf, data + done, len - done);
-
-	return 0;
-}
-
-static int sha512_neon_update(struct shash_desc *desc, const u8 *data,
-			     unsigned int len)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int partial = sctx->count[0] % SHA512_BLOCK_SIZE;
-	int res;
-
-	/* Handle the fast case right here */
-	if (partial + len < SHA512_BLOCK_SIZE) {
-		sctx->count[0] += len;
-		if (sctx->count[0] < len)
-			sctx->count[1]++;
-		memcpy(sctx->buf + partial, data, len);
-
-		return 0;
-	}
-
-	if (!may_use_simd()) {
-		res = crypto_sha512_update(desc, data, len);
-	} else {
-		kernel_neon_begin();
-		res = __sha512_neon_update(desc, data, len, partial);
-		kernel_neon_end();
-	}
-
-	return res;
-}
-
-
-/* Add padding and return the message digest. */
-static int sha512_neon_final(struct shash_desc *desc, u8 *out)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-	unsigned int i, index, padlen;
-	__be64 *dst = (__be64 *)out;
-	__be64 bits[2];
-	static const u8 padding[SHA512_BLOCK_SIZE] = { 0x80, };
-
-	/* save number of bits */
-	bits[1] = cpu_to_be64(sctx->count[0] << 3);
-	bits[0] = cpu_to_be64(sctx->count[1] << 3 | sctx->count[0] >> 61);
-
-	/* Pad out to 112 mod 128 and append length */
-	index = sctx->count[0] & 0x7f;
-	padlen = (index < 112) ? (112 - index) : ((128+112) - index);
-
-	if (!may_use_simd()) {
-		crypto_sha512_update(desc, padding, padlen);
-		crypto_sha512_update(desc, (const u8 *)&bits, sizeof(bits));
-	} else {
-		kernel_neon_begin();
-		/* We need to fill a whole block for __sha512_neon_update() */
-		if (padlen <= 112) {
-			sctx->count[0] += padlen;
-			if (sctx->count[0] < padlen)
-				sctx->count[1]++;
-			memcpy(sctx->buf + index, padding, padlen);
-		} else {
-			__sha512_neon_update(desc, padding, padlen, index);
-		}
-		__sha512_neon_update(desc, (const u8 *)&bits,
-					sizeof(bits), 112);
-		kernel_neon_end();
-	}
-
-	/* Store state in digest */
-	for (i = 0; i < 8; i++)
-		dst[i] = cpu_to_be64(sctx->state[i]);
-
-	/* Wipe context */
-	memset(sctx, 0, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha512_neon_export(struct shash_desc *desc, void *out)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(out, sctx, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha512_neon_import(struct shash_desc *desc, const void *in)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	memcpy(sctx, in, sizeof(*sctx));
-
-	return 0;
-}
-
-static int sha384_neon_init(struct shash_desc *desc)
-{
-	struct sha512_state *sctx = shash_desc_ctx(desc);
-
-	sctx->state[0] = SHA384_H0;
-	sctx->state[1] = SHA384_H1;
-	sctx->state[2] = SHA384_H2;
-	sctx->state[3] = SHA384_H3;
-	sctx->state[4] = SHA384_H4;
-	sctx->state[5] = SHA384_H5;
-	sctx->state[6] = SHA384_H6;
-	sctx->state[7] = SHA384_H7;
-
-	sctx->count[0] = sctx->count[1] = 0;
-
-	return 0;
-}
-
-static int sha384_neon_final(struct shash_desc *desc, u8 *hash)
-{
-	u8 D[SHA512_DIGEST_SIZE];
-
-	sha512_neon_final(desc, D);
-
-	memcpy(hash, D, SHA384_DIGEST_SIZE);
-	memzero_explicit(D, SHA512_DIGEST_SIZE);
-
-	return 0;
-}
-
-static struct shash_alg algs[] = { {
-	.digestsize	=	SHA512_DIGEST_SIZE,
-	.init		=	sha512_neon_init,
-	.update		=	sha512_neon_update,
-	.final		=	sha512_neon_final,
-	.export		=	sha512_neon_export,
-	.import		=	sha512_neon_import,
-	.descsize	=	sizeof(struct sha512_state),
-	.statesize	=	sizeof(struct sha512_state),
-	.base		=	{
-		.cra_name	=	"sha512",
-		.cra_driver_name =	"sha512-neon",
-		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA512_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-},  {
-	.digestsize	=	SHA384_DIGEST_SIZE,
-	.init		=	sha384_neon_init,
-	.update		=	sha512_neon_update,
-	.final		=	sha384_neon_final,
-	.export		=	sha512_neon_export,
-	.import		=	sha512_neon_import,
-	.descsize	=	sizeof(struct sha512_state),
-	.statesize	=	sizeof(struct sha512_state),
-	.base		=	{
-		.cra_name	=	"sha384",
-		.cra_driver_name =	"sha384-neon",
-		.cra_priority	=	250,
-		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,
-		.cra_blocksize	=	SHA384_BLOCK_SIZE,
-		.cra_module	=	THIS_MODULE,
-	}
-} };
-
-static int __init sha512_neon_mod_init(void)
-{
-	if (!cpu_has_neon())
-		return -ENODEV;
-
-	return crypto_register_shashes(algs, ARRAY_SIZE(algs));
-}
-
-static void __exit sha512_neon_mod_fini(void)
-{
-	crypto_unregister_shashes(algs, ARRAY_SIZE(algs));
-}
-
-module_init(sha512_neon_mod_init);
-module_exit(sha512_neon_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, NEON accelerated");
-
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha384");