Remove old or redundant SHA2 files

We had three sha2.h headers in different places.
The FreeBSD version, the Linux version and the generic solaris version.

The only assembly used for acceleration was some old x86-64 openssl
implementation for sha256 within the icp module.

For FreeBSD the whole SHA2 files of FreeBSD were copied into OpenZFS,
these files got removed also.

Tested-by: Rich Ercolani <[email protected]>
Tested-by: Sebastian Gottschall <[email protected]>
Reviewed-by: Brian Behlendorf <[email protected]>
Signed-off-by: Tino Reichardt <[email protected]>
Closes #13741

13 files changed, 3 insertions, 6817 deletions

diff --git a/module/Kbuild.in b/module/Kbuild.in
index a1ea08cd4..6b1c9c48b 100644
--- a/module/Kbuild.in
+++ b/module/Kbuild.in
@@ -94,7 +94,6 @@ ICP_OBJS := \
 	algs/modes/gcm.o \
 	algs/modes/gcm_generic.o \
 	algs/modes/modes.o \
-	algs/sha2/sha2.o \
 	algs/skein/skein.o \
 	algs/skein/skein_block.o \
 	algs/skein/skein_iv.o \
@@ -122,9 +121,7 @@ ICP_OBJS_X86_64 := \
 	asm-x86_64/blake3/blake3_sse41.o \
 	asm-x86_64/modes/aesni-gcm-x86_64.o \
 	asm-x86_64/modes/gcm_pclmulqdq.o \
-	asm-x86_64/modes/ghash-x86_64.o \
-	asm-x86_64/sha2/sha256_impl.o \
-	asm-x86_64/sha2/sha512_impl.o
+	asm-x86_64/modes/ghash-x86_64.o
 
 
 ICP_OBJS_X86 := \
@@ -159,13 +156,6 @@ $(addprefix $(obj)/icp/,$(ICP_OBJS) $(ICP_OBJS_X86) $(ICP_OBJS_X86_64) \
 # Suppress objtool "return with modified stack frame" warnings.
 OBJECT_FILES_NON_STANDARD_aesni-gcm-x86_64.o := y
 
-# Suppress objtool "unsupported stack pointer realignment" warnings. We are
-# not using a DRAP register while aligning the stack to a 64 byte boundary.
-# See #6950 for the reasoning.
-OBJECT_FILES_NON_STANDARD_sha256_impl.o := y
-OBJECT_FILES_NON_STANDARD_sha512_impl.o := y
-
-
 LUA_OBJS := \
 	lapi.o \
 	lauxlib.o \
@@ -344,7 +334,7 @@ ZFS_OBJS := \
 	refcount.o \
 	rrwlock.o \
 	sa.o \
-	sha256.o \
+	sha2_zfs.o \
 	skein_zfs.o \
 	spa.o \
 	spa_checkpoint.o \
diff --git a/module/Makefile.bsd b/module/Makefile.bsd
index 999dc90ff..1663dcec6 100644
--- a/module/Makefile.bsd
+++ b/module/Makefile.bsd
@@ -141,8 +141,6 @@ SRCS+=	nvpair.c \
 SRCS+=	acl_common.c \
 	callb.c \
 	list.c \
-	sha256c.c \
-	sha512c.c \
 	spl_acl.c \
 	spl_cmn_err.c \
 	spl_dtrace.c \
@@ -268,7 +266,7 @@ SRCS+=	abd.c \
 	refcount.c \
 	rrwlock.c \
 	sa.c \
-	sha256.c \
+	sha2_zfs.c \
 	skein_zfs.c \
 	spa.c \
 	spa_checkpoint.c \
diff --git a/module/icp/algs/sha2/sha2.c b/module/icp/algs/sha2/sha2.c
deleted file mode 100644
index e6bbe34ea..000000000
--- a/module/icp/algs/sha2/sha2.c
+++ /dev/null
@@ -1,957 +0,0 @@
-/*
- * Copyright 2009 Sun Microsystems, Inc.  All rights reserved.
- * Use is subject to license terms.
- */
-/*
- * Copyright 2013 Saso Kiselkov.  All rights reserved.
- */
-
-/*
- * The basic framework for this code came from the reference
- * implementation for MD5.  That implementation is Copyright (C)
- * 1991-2, RSA Data Security, Inc. Created 1991. All rights reserved.
- *
- * License to copy and use this software is granted provided that it
- * is identified as the "RSA Data Security, Inc. MD5 Message-Digest
- * Algorithm" in all material mentioning or referencing this software
- * or this function.
- *
- * License is also granted to make and use derivative works provided
- * that such works are identified as "derived from the RSA Data
- * Security, Inc. MD5 Message-Digest Algorithm" in all material
- * mentioning or referencing the derived work.
- *
- * RSA Data Security, Inc. makes no representations concerning either
- * the merchantability of this software or the suitability of this
- * software for any particular purpose. It is provided "as is"
- * without express or implied warranty of any kind.
- *
- * These notices must be retained in any copies of any part of this
- * documentation and/or software.
- *
- * NOTE: Cleaned-up and optimized, version of SHA2, based on the FIPS 180-2
- * standard, available at
- * http://csrc.nist.gov/publications/fips/fips180-2/fips180-2.pdf
- * Not as fast as one would like -- further optimizations are encouraged
- * and appreciated.
- */
-
-#include <sys/zfs_context.h>
-#define	_SHA2_IMPL
-#include <sys/sha2.h>
-#include <sha2/sha2_consts.h>
-
-#define	_RESTRICT_KYWD
-
-#ifdef _ZFS_LITTLE_ENDIAN
-#include <sys/byteorder.h>
-#define	HAVE_HTONL
-#endif
-#include <sys/isa_defs.h>	/* for _ILP32 */
-#include <sys/asm_linkage.h>
-
-static void Encode(uint8_t *, uint32_t *, size_t);
-static void Encode64(uint8_t *, uint64_t *, size_t);
-
-/* userspace only supports the generic version */
-#if	defined(__amd64) && defined(_KERNEL)
-#define	SHA512Transform(ctx, in) SHA512TransformBlocks((ctx), (in), 1)
-#define	SHA256Transform(ctx, in) SHA256TransformBlocks((ctx), (in), 1)
-
-void ASMABI SHA512TransformBlocks(SHA2_CTX *ctx, const void *in, size_t num);
-void ASMABI SHA256TransformBlocks(SHA2_CTX *ctx, const void *in, size_t num);
-
-#else
-static void SHA256Transform(SHA2_CTX *, const uint8_t *);
-static void SHA512Transform(SHA2_CTX *, const uint8_t *);
-#endif	/* __amd64 && _KERNEL */
-
-static const uint8_t PADDING[128] = { 0x80, /* all zeros */ };
-
-/*
- * The low-level checksum routines use a lot of stack space. On systems where
- * small stacks are enforced (like 32-bit kernel builds), insert compiler memory
- * barriers to reduce stack frame size. This can reduce the SHA512Transform()
- * stack frame usage from 3k to <1k on ARM32, for example.
- */
-#if defined(_ILP32) || defined(__powerpc)	/* small stack */
-#define	SMALL_STACK_MEMORY_BARRIER	asm volatile("": : :"memory");
-#else
-#define	SMALL_STACK_MEMORY_BARRIER
-#endif
-
-/* Ch and Maj are the basic SHA2 functions. */
-#define	Ch(b, c, d)	(((b) & (c)) ^ ((~b) & (d)))
-#define	Maj(b, c, d)	(((b) & (c)) ^ ((b) & (d)) ^ ((c) & (d)))
-
-/* Rotates x right n bits. */
-#define	ROTR(x, n)	\
-	(((x) >> (n)) | ((x) << ((sizeof (x) * NBBY)-(n))))
-
-/* Shift x right n bits */
-#define	SHR(x, n)	((x) >> (n))
-
-/* SHA256 Functions */
-#define	BIGSIGMA0_256(x)	(ROTR((x), 2) ^ ROTR((x), 13) ^ ROTR((x), 22))
-#define	BIGSIGMA1_256(x)	(ROTR((x), 6) ^ ROTR((x), 11) ^ ROTR((x), 25))
-#define	SIGMA0_256(x)		(ROTR((x), 7) ^ ROTR((x), 18) ^ SHR((x), 3))
-#define	SIGMA1_256(x)		(ROTR((x), 17) ^ ROTR((x), 19) ^ SHR((x), 10))
-
-#define	SHA256ROUND(a, b, c, d, e, f, g, h, i, w)			\
-	T1 = h + BIGSIGMA1_256(e) + Ch(e, f, g) + SHA256_CONST(i) + w;	\
-	d += T1;							\
-	T2 = BIGSIGMA0_256(a) + Maj(a, b, c);				\
-	h = T1 + T2
-
-/* SHA384/512 Functions */
-#define	BIGSIGMA0(x)	(ROTR((x), 28) ^ ROTR((x), 34) ^ ROTR((x), 39))
-#define	BIGSIGMA1(x)	(ROTR((x), 14) ^ ROTR((x), 18) ^ ROTR((x), 41))
-#define	SIGMA0(x)	(ROTR((x), 1) ^ ROTR((x), 8) ^ SHR((x), 7))
-#define	SIGMA1(x)	(ROTR((x), 19) ^ ROTR((x), 61) ^ SHR((x), 6))
-#define	SHA512ROUND(a, b, c, d, e, f, g, h, i, w)			\
-	T1 = h + BIGSIGMA1(e) + Ch(e, f, g) + SHA512_CONST(i) + w;	\
-	d += T1;							\
-	T2 = BIGSIGMA0(a) + Maj(a, b, c);				\
-	h = T1 + T2;							\
-	SMALL_STACK_MEMORY_BARRIER;
-
-/*
- * sparc optimization:
- *
- * on the sparc, we can load big endian 32-bit data easily.  note that
- * special care must be taken to ensure the address is 32-bit aligned.
- * in the interest of speed, we don't check to make sure, since
- * careful programming can guarantee this for us.
- */
-
-#if	defined(_ZFS_BIG_ENDIAN)
-#define	LOAD_BIG_32(addr)	(*(uint32_t *)(addr))
-#define	LOAD_BIG_64(addr)	(*(uint64_t *)(addr))
-
-#elif	defined(HAVE_HTONL)
-#define	LOAD_BIG_32(addr) htonl(*((uint32_t *)(addr)))
-#define	LOAD_BIG_64(addr) htonll(*((uint64_t *)(addr)))
-
-#else
-/* little endian -- will work on big endian, but slowly */
-#define	LOAD_BIG_32(addr)	\
-	(((addr)[0] << 24) | ((addr)[1] << 16) | ((addr)[2] << 8) | (addr)[3])
-#define	LOAD_BIG_64(addr)	\
-	(((uint64_t)(addr)[0] << 56) | ((uint64_t)(addr)[1] << 48) |	\
-	    ((uint64_t)(addr)[2] << 40) | ((uint64_t)(addr)[3] << 32) |	\
-	    ((uint64_t)(addr)[4] << 24) | ((uint64_t)(addr)[5] << 16) |	\
-	    ((uint64_t)(addr)[6] << 8) | (uint64_t)(addr)[7])
-#endif	/* _BIG_ENDIAN */
-
-
-#if	!defined(__amd64) || !defined(_KERNEL)
-/* SHA256 Transform */
-
-static void
-SHA256Transform(SHA2_CTX *ctx, const uint8_t *blk)
-{
-	uint32_t a = ctx->state.s32[0];
-	uint32_t b = ctx->state.s32[1];
-	uint32_t c = ctx->state.s32[2];
-	uint32_t d = ctx->state.s32[3];
-	uint32_t e = ctx->state.s32[4];
-	uint32_t f = ctx->state.s32[5];
-	uint32_t g = ctx->state.s32[6];
-	uint32_t h = ctx->state.s32[7];
-
-	uint32_t w0, w1, w2, w3, w4, w5, w6, w7;
-	uint32_t w8, w9, w10, w11, w12, w13, w14, w15;
-	uint32_t T1, T2;
-
-#if	defined(__sparc)
-	static const uint32_t sha256_consts[] = {
-		SHA256_CONST_0, SHA256_CONST_1, SHA256_CONST_2,
-		SHA256_CONST_3, SHA256_CONST_4, SHA256_CONST_5,
-		SHA256_CONST_6, SHA256_CONST_7, SHA256_CONST_8,
-		SHA256_CONST_9, SHA256_CONST_10, SHA256_CONST_11,
-		SHA256_CONST_12, SHA256_CONST_13, SHA256_CONST_14,
-		SHA256_CONST_15, SHA256_CONST_16, SHA256_CONST_17,
-		SHA256_CONST_18, SHA256_CONST_19, SHA256_CONST_20,
-		SHA256_CONST_21, SHA256_CONST_22, SHA256_CONST_23,
-		SHA256_CONST_24, SHA256_CONST_25, SHA256_CONST_26,
-		SHA256_CONST_27, SHA256_CONST_28, SHA256_CONST_29,
-		SHA256_CONST_30, SHA256_CONST_31, SHA256_CONST_32,
-		SHA256_CONST_33, SHA256_CONST_34, SHA256_CONST_35,
-		SHA256_CONST_36, SHA256_CONST_37, SHA256_CONST_38,
-		SHA256_CONST_39, SHA256_CONST_40, SHA256_CONST_41,
-		SHA256_CONST_42, SHA256_CONST_43, SHA256_CONST_44,
-		SHA256_CONST_45, SHA256_CONST_46, SHA256_CONST_47,
-		SHA256_CONST_48, SHA256_CONST_49, SHA256_CONST_50,
-		SHA256_CONST_51, SHA256_CONST_52, SHA256_CONST_53,
-		SHA256_CONST_54, SHA256_CONST_55, SHA256_CONST_56,
-		SHA256_CONST_57, SHA256_CONST_58, SHA256_CONST_59,
-		SHA256_CONST_60, SHA256_CONST_61, SHA256_CONST_62,
-		SHA256_CONST_63
-	};
-#endif	/* __sparc */
-
-	if ((uintptr_t)blk & 0x3) {		/* not 4-byte aligned? */
-		memcpy(ctx->buf_un.buf32, blk, sizeof (ctx->buf_un.buf32));
-		blk = (uint8_t *)ctx->buf_un.buf32;
-	}
-
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w0 =  LOAD_BIG_32(blk + 4 * 0);
-	SHA256ROUND(a, b, c, d, e, f, g, h, 0, w0);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w1 =  LOAD_BIG_32(blk + 4 * 1);
-	SHA256ROUND(h, a, b, c, d, e, f, g, 1, w1);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w2 =  LOAD_BIG_32(blk + 4 * 2);
-	SHA256ROUND(g, h, a, b, c, d, e, f, 2, w2);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w3 =  LOAD_BIG_32(blk + 4 * 3);
-	SHA256ROUND(f, g, h, a, b, c, d, e, 3, w3);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w4 =  LOAD_BIG_32(blk + 4 * 4);
-	SHA256ROUND(e, f, g, h, a, b, c, d, 4, w4);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w5 =  LOAD_BIG_32(blk + 4 * 5);
-	SHA256ROUND(d, e, f, g, h, a, b, c, 5, w5);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w6 =  LOAD_BIG_32(blk + 4 * 6);
-	SHA256ROUND(c, d, e, f, g, h, a, b, 6, w6);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w7 =  LOAD_BIG_32(blk + 4 * 7);
-	SHA256ROUND(b, c, d, e, f, g, h, a, 7, w7);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w8 =  LOAD_BIG_32(blk + 4 * 8);
-	SHA256ROUND(a, b, c, d, e, f, g, h, 8, w8);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w9 =  LOAD_BIG_32(blk + 4 * 9);
-	SHA256ROUND(h, a, b, c, d, e, f, g, 9, w9);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w10 =  LOAD_BIG_32(blk + 4 * 10);
-	SHA256ROUND(g, h, a, b, c, d, e, f, 10, w10);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w11 =  LOAD_BIG_32(blk + 4 * 11);
-	SHA256ROUND(f, g, h, a, b, c, d, e, 11, w11);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w12 =  LOAD_BIG_32(blk + 4 * 12);
-	SHA256ROUND(e, f, g, h, a, b, c, d, 12, w12);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w13 =  LOAD_BIG_32(blk + 4 * 13);
-	SHA256ROUND(d, e, f, g, h, a, b, c, 13, w13);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w14 =  LOAD_BIG_32(blk + 4 * 14);
-	SHA256ROUND(c, d, e, f, g, h, a, b, 14, w14);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w15 =  LOAD_BIG_32(blk + 4 * 15);
-	SHA256ROUND(b, c, d, e, f, g, h, a, 15, w15);
-
-	w0 = SIGMA1_256(w14) + w9 + SIGMA0_256(w1) + w0;
-	SHA256ROUND(a, b, c, d, e, f, g, h, 16, w0);
-	w1 = SIGMA1_256(w15) + w10 + SIGMA0_256(w2) + w1;
-	SHA256ROUND(h, a, b, c, d, e, f, g, 17, w1);
-	w2 = SIGMA1_256(w0) + w11 + SIGMA0_256(w3) + w2;
-	SHA256ROUND(g, h, a, b, c, d, e, f, 18, w2);
-	w3 = SIGMA1_256(w1) + w12 + SIGMA0_256(w4) + w3;
-	SHA256ROUND(f, g, h, a, b, c, d, e, 19, w3);
-	w4 = SIGMA1_256(w2) + w13 + SIGMA0_256(w5) + w4;
-	SHA256ROUND(e, f, g, h, a, b, c, d, 20, w4);
-	w5 = SIGMA1_256(w3) + w14 + SIGMA0_256(w6) + w5;
-	SHA256ROUND(d, e, f, g, h, a, b, c, 21, w5);
-	w6 = SIGMA1_256(w4) + w15 + SIGMA0_256(w7) + w6;
-	SHA256ROUND(c, d, e, f, g, h, a, b, 22, w6);
-	w7 = SIGMA1_256(w5) + w0 + SIGMA0_256(w8) + w7;
-	SHA256ROUND(b, c, d, e, f, g, h, a, 23, w7);
-	w8 = SIGMA1_256(w6) + w1 + SIGMA0_256(w9) + w8;
-	SHA256ROUND(a, b, c, d, e, f, g, h, 24, w8);
-	w9 = SIGMA1_256(w7) + w2 + SIGMA0_256(w10) + w9;
-	SHA256ROUND(h, a, b, c, d, e, f, g, 25, w9);
-	w10 = SIGMA1_256(w8) + w3 + SIGMA0_256(w11) + w10;
-	SHA256ROUND(g, h, a, b, c, d, e, f, 26, w10);
-	w11 = SIGMA1_256(w9) + w4 + SIGMA0_256(w12) + w11;
-	SHA256ROUND(f, g, h, a, b, c, d, e, 27, w11);
-	w12 = SIGMA1_256(w10) + w5 + SIGMA0_256(w13) + w12;
-	SHA256ROUND(e, f, g, h, a, b, c, d, 28, w12);
-	w13 = SIGMA1_256(w11) + w6 + SIGMA0_256(w14) + w13;
-	SHA256ROUND(d, e, f, g, h, a, b, c, 29, w13);
-	w14 = SIGMA1_256(w12) + w7 + SIGMA0_256(w15) + w14;
-	SHA256ROUND(c, d, e, f, g, h, a, b, 30, w14);
-	w15 = SIGMA1_256(w13) + w8 + SIGMA0_256(w0) + w15;
-	SHA256ROUND(b, c, d, e, f, g, h, a, 31, w15);
-
-	w0 = SIGMA1_256(w14) + w9 + SIGMA0_256(w1) + w0;
-	SHA256ROUND(a, b, c, d, e, f, g, h, 32, w0);
-	w1 = SIGMA1_256(w15) + w10 + SIGMA0_256(w2) + w1;
-	SHA256ROUND(h, a, b, c, d, e, f, g, 33, w1);
-	w2 = SIGMA1_256(w0) + w11 + SIGMA0_256(w3) + w2;
-	SHA256ROUND(g, h, a, b, c, d, e, f, 34, w2);
-	w3 = SIGMA1_256(w1) + w12 + SIGMA0_256(w4) + w3;
-	SHA256ROUND(f, g, h, a, b, c, d, e, 35, w3);
-	w4 = SIGMA1_256(w2) + w13 + SIGMA0_256(w5) + w4;
-	SHA256ROUND(e, f, g, h, a, b, c, d, 36, w4);
-	w5 = SIGMA1_256(w3) + w14 + SIGMA0_256(w6) + w5;
-	SHA256ROUND(d, e, f, g, h, a, b, c, 37, w5);
-	w6 = SIGMA1_256(w4) + w15 + SIGMA0_256(w7) + w6;
-	SHA256ROUND(c, d, e, f, g, h, a, b, 38, w6);
-	w7 = SIGMA1_256(w5) + w0 + SIGMA0_256(w8) + w7;
-	SHA256ROUND(b, c, d, e, f, g, h, a, 39, w7);
-	w8 = SIGMA1_256(w6) + w1 + SIGMA0_256(w9) + w8;
-	SHA256ROUND(a, b, c, d, e, f, g, h, 40, w8);
-	w9 = SIGMA1_256(w7) + w2 + SIGMA0_256(w10) + w9;
-	SHA256ROUND(h, a, b, c, d, e, f, g, 41, w9);
-	w10 = SIGMA1_256(w8) + w3 + SIGMA0_256(w11) + w10;
-	SHA256ROUND(g, h, a, b, c, d, e, f, 42, w10);
-	w11 = SIGMA1_256(w9) + w4 + SIGMA0_256(w12) + w11;
-	SHA256ROUND(f, g, h, a, b, c, d, e, 43, w11);
-	w12 = SIGMA1_256(w10) + w5 + SIGMA0_256(w13) + w12;
-	SHA256ROUND(e, f, g, h, a, b, c, d, 44, w12);
-	w13 = SIGMA1_256(w11) + w6 + SIGMA0_256(w14) + w13;
-	SHA256ROUND(d, e, f, g, h, a, b, c, 45, w13);
-	w14 = SIGMA1_256(w12) + w7 + SIGMA0_256(w15) + w14;
-	SHA256ROUND(c, d, e, f, g, h, a, b, 46, w14);
-	w15 = SIGMA1_256(w13) + w8 + SIGMA0_256(w0) + w15;
-	SHA256ROUND(b, c, d, e, f, g, h, a, 47, w15);
-
-	w0 = SIGMA1_256(w14) + w9 + SIGMA0_256(w1) + w0;
-	SHA256ROUND(a, b, c, d, e, f, g, h, 48, w0);
-	w1 = SIGMA1_256(w15) + w10 + SIGMA0_256(w2) + w1;
-	SHA256ROUND(h, a, b, c, d, e, f, g, 49, w1);
-	w2 = SIGMA1_256(w0) + w11 + SIGMA0_256(w3) + w2;
-	SHA256ROUND(g, h, a, b, c, d, e, f, 50, w2);
-	w3 = SIGMA1_256(w1) + w12 + SIGMA0_256(w4) + w3;
-	SHA256ROUND(f, g, h, a, b, c, d, e, 51, w3);
-	w4 = SIGMA1_256(w2) + w13 + SIGMA0_256(w5) + w4;
-	SHA256ROUND(e, f, g, h, a, b, c, d, 52, w4);
-	w5 = SIGMA1_256(w3) + w14 + SIGMA0_256(w6) + w5;
-	SHA256ROUND(d, e, f, g, h, a, b, c, 53, w5);
-	w6 = SIGMA1_256(w4) + w15 + SIGMA0_256(w7) + w6;
-	SHA256ROUND(c, d, e, f, g, h, a, b, 54, w6);
-	w7 = SIGMA1_256(w5) + w0 + SIGMA0_256(w8) + w7;
-	SHA256ROUND(b, c, d, e, f, g, h, a, 55, w7);
-	w8 = SIGMA1_256(w6) + w1 + SIGMA0_256(w9) + w8;
-	SHA256ROUND(a, b, c, d, e, f, g, h, 56, w8);
-	w9 = SIGMA1_256(w7) + w2 + SIGMA0_256(w10) + w9;
-	SHA256ROUND(h, a, b, c, d, e, f, g, 57, w9);
-	w10 = SIGMA1_256(w8) + w3 + SIGMA0_256(w11) + w10;
-	SHA256ROUND(g, h, a, b, c, d, e, f, 58, w10);
-	w11 = SIGMA1_256(w9) + w4 + SIGMA0_256(w12) + w11;
-	SHA256ROUND(f, g, h, a, b, c, d, e, 59, w11);
-	w12 = SIGMA1_256(w10) + w5 + SIGMA0_256(w13) + w12;
-	SHA256ROUND(e, f, g, h, a, b, c, d, 60, w12);
-	w13 = SIGMA1_256(w11) + w6 + SIGMA0_256(w14) + w13;
-	SHA256ROUND(d, e, f, g, h, a, b, c, 61, w13);
-	w14 = SIGMA1_256(w12) + w7 + SIGMA0_256(w15) + w14;
-	SHA256ROUND(c, d, e, f, g, h, a, b, 62, w14);
-	w15 = SIGMA1_256(w13) + w8 + SIGMA0_256(w0) + w15;
-	SHA256ROUND(b, c, d, e, f, g, h, a, 63, w15);
-
-	ctx->state.s32[0] += a;
-	ctx->state.s32[1] += b;
-	ctx->state.s32[2] += c;
-	ctx->state.s32[3] += d;
-	ctx->state.s32[4] += e;
-	ctx->state.s32[5] += f;
-	ctx->state.s32[6] += g;
-	ctx->state.s32[7] += h;
-}
-
-
-/* SHA384 and SHA512 Transform */
-
-static void
-SHA512Transform(SHA2_CTX *ctx, const uint8_t *blk)
-{
-
-	uint64_t a = ctx->state.s64[0];
-	uint64_t b = ctx->state.s64[1];
-	uint64_t c = ctx->state.s64[2];
-	uint64_t d = ctx->state.s64[3];
-	uint64_t e = ctx->state.s64[4];
-	uint64_t f = ctx->state.s64[5];
-	uint64_t g = ctx->state.s64[6];
-	uint64_t h = ctx->state.s64[7];
-
-	uint64_t w0, w1, w2, w3, w4, w5, w6, w7;
-	uint64_t w8, w9, w10, w11, w12, w13, w14, w15;
-	uint64_t T1, T2;
-
-#if	defined(__sparc)
-	static const uint64_t sha512_consts[] = {
-		SHA512_CONST_0, SHA512_CONST_1, SHA512_CONST_2,
-		SHA512_CONST_3, SHA512_CONST_4, SHA512_CONST_5,
-		SHA512_CONST_6, SHA512_CONST_7, SHA512_CONST_8,
-		SHA512_CONST_9, SHA512_CONST_10, SHA512_CONST_11,
-		SHA512_CONST_12, SHA512_CONST_13, SHA512_CONST_14,
-		SHA512_CONST_15, SHA512_CONST_16, SHA512_CONST_17,
-		SHA512_CONST_18, SHA512_CONST_19, SHA512_CONST_20,
-		SHA512_CONST_21, SHA512_CONST_22, SHA512_CONST_23,
-		SHA512_CONST_24, SHA512_CONST_25, SHA512_CONST_26,
-		SHA512_CONST_27, SHA512_CONST_28, SHA512_CONST_29,
-		SHA512_CONST_30, SHA512_CONST_31, SHA512_CONST_32,
-		SHA512_CONST_33, SHA512_CONST_34, SHA512_CONST_35,
-		SHA512_CONST_36, SHA512_CONST_37, SHA512_CONST_38,
-		SHA512_CONST_39, SHA512_CONST_40, SHA512_CONST_41,
-		SHA512_CONST_42, SHA512_CONST_43, SHA512_CONST_44,
-		SHA512_CONST_45, SHA512_CONST_46, SHA512_CONST_47,
-		SHA512_CONST_48, SHA512_CONST_49, SHA512_CONST_50,
-		SHA512_CONST_51, SHA512_CONST_52, SHA512_CONST_53,
-		SHA512_CONST_54, SHA512_CONST_55, SHA512_CONST_56,
-		SHA512_CONST_57, SHA512_CONST_58, SHA512_CONST_59,
-		SHA512_CONST_60, SHA512_CONST_61, SHA512_CONST_62,
-		SHA512_CONST_63, SHA512_CONST_64, SHA512_CONST_65,
-		SHA512_CONST_66, SHA512_CONST_67, SHA512_CONST_68,
-		SHA512_CONST_69, SHA512_CONST_70, SHA512_CONST_71,
-		SHA512_CONST_72, SHA512_CONST_73, SHA512_CONST_74,
-		SHA512_CONST_75, SHA512_CONST_76, SHA512_CONST_77,
-		SHA512_CONST_78, SHA512_CONST_79
-	};
-#endif	/* __sparc */
-
-
-	if ((uintptr_t)blk & 0x7) {		/* not 8-byte aligned? */
-		memcpy(ctx->buf_un.buf64, blk, sizeof (ctx->buf_un.buf64));
-		blk = (uint8_t *)ctx->buf_un.buf64;
-	}
-
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w0 =  LOAD_BIG_64(blk + 8 * 0);
-	SHA512ROUND(a, b, c, d, e, f, g, h, 0, w0);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w1 =  LOAD_BIG_64(blk + 8 * 1);
-	SHA512ROUND(h, a, b, c, d, e, f, g, 1, w1);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w2 =  LOAD_BIG_64(blk + 8 * 2);
-	SHA512ROUND(g, h, a, b, c, d, e, f, 2, w2);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w3 =  LOAD_BIG_64(blk + 8 * 3);
-	SHA512ROUND(f, g, h, a, b, c, d, e, 3, w3);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w4 =  LOAD_BIG_64(blk + 8 * 4);
-	SHA512ROUND(e, f, g, h, a, b, c, d, 4, w4);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w5 =  LOAD_BIG_64(blk + 8 * 5);
-	SHA512ROUND(d, e, f, g, h, a, b, c, 5, w5);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w6 =  LOAD_BIG_64(blk + 8 * 6);
-	SHA512ROUND(c, d, e, f, g, h, a, b, 6, w6);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w7 =  LOAD_BIG_64(blk + 8 * 7);
-	SHA512ROUND(b, c, d, e, f, g, h, a, 7, w7);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w8 =  LOAD_BIG_64(blk + 8 * 8);
-	SHA512ROUND(a, b, c, d, e, f, g, h, 8, w8);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w9 =  LOAD_BIG_64(blk + 8 * 9);
-	SHA512ROUND(h, a, b, c, d, e, f, g, 9, w9);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w10 =  LOAD_BIG_64(blk + 8 * 10);
-	SHA512ROUND(g, h, a, b, c, d, e, f, 10, w10);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w11 =  LOAD_BIG_64(blk + 8 * 11);
-	SHA512ROUND(f, g, h, a, b, c, d, e, 11, w11);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w12 =  LOAD_BIG_64(blk + 8 * 12);
-	SHA512ROUND(e, f, g, h, a, b, c, d, 12, w12);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w13 =  LOAD_BIG_64(blk + 8 * 13);
-	SHA512ROUND(d, e, f, g, h, a, b, c, 13, w13);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w14 =  LOAD_BIG_64(blk + 8 * 14);
-	SHA512ROUND(c, d, e, f, g, h, a, b, 14, w14);
-	/* LINTED E_BAD_PTR_CAST_ALIGN */
-	w15 =  LOAD_BIG_64(blk + 8 * 15);
-	SHA512ROUND(b, c, d, e, f, g, h, a, 15, w15);
-
-	w0 = SIGMA1(w14) + w9 + SIGMA0(w1) + w0;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 16, w0);
-	w1 = SIGMA1(w15) + w10 + SIGMA0(w2) + w1;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 17, w1);
-	w2 = SIGMA1(w0) + w11 + SIGMA0(w3) + w2;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 18, w2);
-	w3 = SIGMA1(w1) + w12 + SIGMA0(w4) + w3;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 19, w3);
-	w4 = SIGMA1(w2) + w13 + SIGMA0(w5) + w4;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 20, w4);
-	w5 = SIGMA1(w3) + w14 + SIGMA0(w6) + w5;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 21, w5);
-	w6 = SIGMA1(w4) + w15 + SIGMA0(w7) + w6;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 22, w6);
-	w7 = SIGMA1(w5) + w0 + SIGMA0(w8) + w7;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 23, w7);
-	w8 = SIGMA1(w6) + w1 + SIGMA0(w9) + w8;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 24, w8);
-	w9 = SIGMA1(w7) + w2 + SIGMA0(w10) + w9;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 25, w9);
-	w10 = SIGMA1(w8) + w3 + SIGMA0(w11) + w10;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 26, w10);
-	w11 = SIGMA1(w9) + w4 + SIGMA0(w12) + w11;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 27, w11);
-	w12 = SIGMA1(w10) + w5 + SIGMA0(w13) + w12;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 28, w12);
-	w13 = SIGMA1(w11) + w6 + SIGMA0(w14) + w13;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 29, w13);
-	w14 = SIGMA1(w12) + w7 + SIGMA0(w15) + w14;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 30, w14);
-	w15 = SIGMA1(w13) + w8 + SIGMA0(w0) + w15;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 31, w15);
-
-	w0 = SIGMA1(w14) + w9 + SIGMA0(w1) + w0;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 32, w0);
-	w1 = SIGMA1(w15) + w10 + SIGMA0(w2) + w1;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 33, w1);
-	w2 = SIGMA1(w0) + w11 + SIGMA0(w3) + w2;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 34, w2);
-	w3 = SIGMA1(w1) + w12 + SIGMA0(w4) + w3;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 35, w3);
-	w4 = SIGMA1(w2) + w13 + SIGMA0(w5) + w4;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 36, w4);
-	w5 = SIGMA1(w3) + w14 + SIGMA0(w6) + w5;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 37, w5);
-	w6 = SIGMA1(w4) + w15 + SIGMA0(w7) + w6;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 38, w6);
-	w7 = SIGMA1(w5) + w0 + SIGMA0(w8) + w7;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 39, w7);
-	w8 = SIGMA1(w6) + w1 + SIGMA0(w9) + w8;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 40, w8);
-	w9 = SIGMA1(w7) + w2 + SIGMA0(w10) + w9;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 41, w9);
-	w10 = SIGMA1(w8) + w3 + SIGMA0(w11) + w10;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 42, w10);
-	w11 = SIGMA1(w9) + w4 + SIGMA0(w12) + w11;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 43, w11);
-	w12 = SIGMA1(w10) + w5 + SIGMA0(w13) + w12;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 44, w12);
-	w13 = SIGMA1(w11) + w6 + SIGMA0(w14) + w13;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 45, w13);
-	w14 = SIGMA1(w12) + w7 + SIGMA0(w15) + w14;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 46, w14);
-	w15 = SIGMA1(w13) + w8 + SIGMA0(w0) + w15;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 47, w15);
-
-	w0 = SIGMA1(w14) + w9 + SIGMA0(w1) + w0;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 48, w0);
-	w1 = SIGMA1(w15) + w10 + SIGMA0(w2) + w1;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 49, w1);
-	w2 = SIGMA1(w0) + w11 + SIGMA0(w3) + w2;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 50, w2);
-	w3 = SIGMA1(w1) + w12 + SIGMA0(w4) + w3;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 51, w3);
-	w4 = SIGMA1(w2) + w13 + SIGMA0(w5) + w4;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 52, w4);
-	w5 = SIGMA1(w3) + w14 + SIGMA0(w6) + w5;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 53, w5);
-	w6 = SIGMA1(w4) + w15 + SIGMA0(w7) + w6;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 54, w6);
-	w7 = SIGMA1(w5) + w0 + SIGMA0(w8) + w7;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 55, w7);
-	w8 = SIGMA1(w6) + w1 + SIGMA0(w9) + w8;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 56, w8);
-	w9 = SIGMA1(w7) + w2 + SIGMA0(w10) + w9;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 57, w9);
-	w10 = SIGMA1(w8) + w3 + SIGMA0(w11) + w10;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 58, w10);
-	w11 = SIGMA1(w9) + w4 + SIGMA0(w12) + w11;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 59, w11);
-	w12 = SIGMA1(w10) + w5 + SIGMA0(w13) + w12;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 60, w12);
-	w13 = SIGMA1(w11) + w6 + SIGMA0(w14) + w13;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 61, w13);
-	w14 = SIGMA1(w12) + w7 + SIGMA0(w15) + w14;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 62, w14);
-	w15 = SIGMA1(w13) + w8 + SIGMA0(w0) + w15;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 63, w15);
-
-	w0 = SIGMA1(w14) + w9 + SIGMA0(w1) + w0;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 64, w0);
-	w1 = SIGMA1(w15) + w10 + SIGMA0(w2) + w1;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 65, w1);
-	w2 = SIGMA1(w0) + w11 + SIGMA0(w3) + w2;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 66, w2);
-	w3 = SIGMA1(w1) + w12 + SIGMA0(w4) + w3;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 67, w3);
-	w4 = SIGMA1(w2) + w13 + SIGMA0(w5) + w4;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 68, w4);
-	w5 = SIGMA1(w3) + w14 + SIGMA0(w6) + w5;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 69, w5);
-	w6 = SIGMA1(w4) + w15 + SIGMA0(w7) + w6;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 70, w6);
-	w7 = SIGMA1(w5) + w0 + SIGMA0(w8) + w7;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 71, w7);
-	w8 = SIGMA1(w6) + w1 + SIGMA0(w9) + w8;
-	SHA512ROUND(a, b, c, d, e, f, g, h, 72, w8);
-	w9 = SIGMA1(w7) + w2 + SIGMA0(w10) + w9;
-	SHA512ROUND(h, a, b, c, d, e, f, g, 73, w9);
-	w10 = SIGMA1(w8) + w3 + SIGMA0(w11) + w10;
-	SHA512ROUND(g, h, a, b, c, d, e, f, 74, w10);
-	w11 = SIGMA1(w9) + w4 + SIGMA0(w12) + w11;
-	SHA512ROUND(f, g, h, a, b, c, d, e, 75, w11);
-	w12 = SIGMA1(w10) + w5 + SIGMA0(w13) + w12;
-	SHA512ROUND(e, f, g, h, a, b, c, d, 76, w12);
-	w13 = SIGMA1(w11) + w6 + SIGMA0(w14) + w13;
-	SHA512ROUND(d, e, f, g, h, a, b, c, 77, w13);
-	w14 = SIGMA1(w12) + w7 + SIGMA0(w15) + w14;
-	SHA512ROUND(c, d, e, f, g, h, a, b, 78, w14);
-	w15 = SIGMA1(w13) + w8 + SIGMA0(w0) + w15;
-	SHA512ROUND(b, c, d, e, f, g, h, a, 79, w15);
-
-	ctx->state.s64[0] += a;
-	ctx->state.s64[1] += b;
-	ctx->state.s64[2] += c;
-	ctx->state.s64[3] += d;
-	ctx->state.s64[4] += e;
-	ctx->state.s64[5] += f;
-	ctx->state.s64[6] += g;
-	ctx->state.s64[7] += h;
-
-}
-#endif	/* !__amd64 || !_KERNEL */
-
-
-/*
- * Encode()
- *
- * purpose: to convert a list of numbers from little endian to big endian
- *   input: uint8_t *	: place to store the converted big endian numbers
- *	    uint32_t *	: place to get numbers to convert from
- *          size_t	: the length of the input in bytes
- *  output: void
- */
-
-static void
-Encode(uint8_t *_RESTRICT_KYWD output, uint32_t *_RESTRICT_KYWD input,
-    size_t len)
-{
-	size_t		i, j;
-
-#if	defined(__sparc)
-	if (IS_P2ALIGNED(output, sizeof (uint32_t))) {
-		for (i = 0, j = 0; j < len; i++, j += 4) {
-			/* LINTED E_BAD_PTR_CAST_ALIGN */
-			*((uint32_t *)(output + j)) = input[i];
-		}
-	} else {
-#endif	/* little endian -- will work on big endian, but slowly */
-		for (i = 0, j = 0; j < len; i++, j += 4) {
-			output[j]	= (input[i] >> 24) & 0xff;
-			output[j + 1]	= (input[i] >> 16) & 0xff;
-			output[j + 2]	= (input[i] >>  8) & 0xff;
-			output[j + 3]	= input[i] & 0xff;
-		}
-#if	defined(__sparc)
-	}
-#endif
-}
-
-static void
-Encode64(uint8_t *_RESTRICT_KYWD output, uint64_t *_RESTRICT_KYWD input,
-    size_t len)
-{
-	size_t		i, j;
-
-#if	defined(__sparc)
-	if (IS_P2ALIGNED(output, sizeof (uint64_t))) {
-		for (i = 0, j = 0; j < len; i++, j += 8) {
-			/* LINTED E_BAD_PTR_CAST_ALIGN */
-			*((uint64_t *)(output + j)) = input[i];
-		}
-	} else {
-#endif	/* little endian -- will work on big endian, but slowly */
-		for (i = 0, j = 0; j < len; i++, j += 8) {
-
-			output[j]	= (input[i] >> 56) & 0xff;
-			output[j + 1]	= (input[i] >> 48) & 0xff;
-			output[j + 2]	= (input[i] >> 40) & 0xff;
-			output[j + 3]	= (input[i] >> 32) & 0xff;
-			output[j + 4]	= (input[i] >> 24) & 0xff;
-			output[j + 5]	= (input[i] >> 16) & 0xff;
-			output[j + 6]	= (input[i] >>  8) & 0xff;
-			output[j + 7]	= input[i] & 0xff;
-		}
-#if	defined(__sparc)
-	}
-#endif
-}
-
-
-void
-SHA2Init(uint64_t mech, SHA2_CTX *ctx)
-{
-
-	switch (mech) {
-	case SHA256_MECH_INFO_TYPE:
-	case SHA256_HMAC_MECH_INFO_TYPE:
-	case SHA256_HMAC_GEN_MECH_INFO_TYPE:
-		ctx->state.s32[0] = 0x6a09e667U;
-		ctx->state.s32[1] = 0xbb67ae85U;
-		ctx->state.s32[2] = 0x3c6ef372U;
-		ctx->state.s32[3] = 0xa54ff53aU;
-		ctx->state.s32[4] = 0x510e527fU;
-		ctx->state.s32[5] = 0x9b05688cU;
-		ctx->state.s32[6] = 0x1f83d9abU;
-		ctx->state.s32[7] = 0x5be0cd19U;
-		break;
-	case SHA384_MECH_INFO_TYPE:
-	case SHA384_HMAC_MECH_INFO_TYPE:
-	case SHA384_HMAC_GEN_MECH_INFO_TYPE:
-		ctx->state.s64[0] = 0xcbbb9d5dc1059ed8ULL;
-		ctx->state.s64[1] = 0x629a292a367cd507ULL;
-		ctx->state.s64[2] = 0x9159015a3070dd17ULL;
-		ctx->state.s64[3] = 0x152fecd8f70e5939ULL;
-		ctx->state.s64[4] = 0x67332667ffc00b31ULL;
-		ctx->state.s64[5] = 0x8eb44a8768581511ULL;
-		ctx->state.s64[6] = 0xdb0c2e0d64f98fa7ULL;
-		ctx->state.s64[7] = 0x47b5481dbefa4fa4ULL;
-		break;
-	case SHA512_MECH_INFO_TYPE:
-	case SHA512_HMAC_MECH_INFO_TYPE:
-	case SHA512_HMAC_GEN_MECH_INFO_TYPE:
-		ctx->state.s64[0] = 0x6a09e667f3bcc908ULL;
-		ctx->state.s64[1] = 0xbb67ae8584caa73bULL;
-		ctx->state.s64[2] = 0x3c6ef372fe94f82bULL;
-		ctx->state.s64[3] = 0xa54ff53a5f1d36f1ULL;
-		ctx->state.s64[4] = 0x510e527fade682d1ULL;
-		ctx->state.s64[5] = 0x9b05688c2b3e6c1fULL;
-		ctx->state.s64[6] = 0x1f83d9abfb41bd6bULL;
-		ctx->state.s64[7] = 0x5be0cd19137e2179ULL;
-		break;
-	case SHA512_224_MECH_INFO_TYPE:
-		ctx->state.s64[0] = 0x8C3D37C819544DA2ULL;
-		ctx->state.s64[1] = 0x73E1996689DCD4D6ULL;
-		ctx->state.s64[2] = 0x1DFAB7AE32FF9C82ULL;
-		ctx->state.s64[3] = 0x679DD514582F9FCFULL;
-		ctx->state.s64[4] = 0x0F6D2B697BD44DA8ULL;
-		ctx->state.s64[5] = 0x77E36F7304C48942ULL;
-		ctx->state.s64[6] = 0x3F9D85A86A1D36C8ULL;
-		ctx->state.s64[7] = 0x1112E6AD91D692A1ULL;
-		break;
-	case SHA512_256_MECH_INFO_TYPE:
-		ctx->state.s64[0] = 0x22312194FC2BF72CULL;
-		ctx->state.s64[1] = 0x9F555FA3C84C64C2ULL;
-		ctx->state.s64[2] = 0x2393B86B6F53B151ULL;
-		ctx->state.s64[3] = 0x963877195940EABDULL;
-		ctx->state.s64[4] = 0x96283EE2A88EFFE3ULL;
-		ctx->state.s64[5] = 0xBE5E1E2553863992ULL;
-		ctx->state.s64[6] = 0x2B0199FC2C85B8AAULL;
-		ctx->state.s64[7] = 0x0EB72DDC81C52CA2ULL;
-		break;
-#ifdef _KERNEL
-	default:
-		cmn_err(CE_PANIC,
-		    "sha2_init: failed to find a supported algorithm: 0x%x",
-		    (uint32_t)mech);
-
-#endif /* _KERNEL */
-	}
-
-	ctx->algotype = (uint32_t)mech;
-	ctx->count.c64[0] = ctx->count.c64[1] = 0;
-}
-
-#ifndef _KERNEL
-
-// #pragma inline(SHA256Init, SHA384Init, SHA512Init)
-void
-SHA256Init(SHA256_CTX *ctx)
-{
-	SHA2Init(SHA256, ctx);
-}
-
-void
-SHA384Init(SHA384_CTX *ctx)
-{
-	SHA2Init(SHA384, ctx);
-}
-
-void
-SHA512Init(SHA512_CTX *ctx)
-{
-	SHA2Init(SHA512, ctx);
-}
-
-#endif /* _KERNEL */
-
-/*
- * SHA2Update()
- *
- * purpose: continues an sha2 digest operation, using the message block
- *          to update the context.
- *   input: SHA2_CTX *	: the context to update
- *          void *	: the message block
- *          size_t      : the length of the message block, in bytes
- *  output: void
- */
-
-void
-SHA2Update(SHA2_CTX *ctx, const void *inptr, size_t input_len)
-{
-	uint32_t	i, buf_index, buf_len, buf_limit;
-	const uint8_t	*input = inptr;
-	uint32_t	algotype = ctx->algotype;
-
-	/* check for noop */
-	if (input_len == 0)
-		return;
-
-	if (algotype <= SHA256_HMAC_GEN_MECH_INFO_TYPE) {
-		buf_limit = 64;
-
-		/* compute number of bytes mod 64 */
-		buf_index = (ctx->count.c32[1] >> 3) & 0x3F;
-
-		/* update number of bits */
-		if ((ctx->count.c32[1] += (input_len << 3)) < (input_len << 3))
-			ctx->count.c32[0]++;
-
-		ctx->count.c32[0] += (input_len >> 29);
-
-	} else {
-		buf_limit = 128;
-
-		/* compute number of bytes mod 128 */
-		buf_index = (ctx->count.c64[1] >> 3) & 0x7F;
-
-		/* update number of bits */
-		if ((ctx->count.c64[1] += (input_len << 3)) < (input_len << 3))
-			ctx->count.c64[0]++;
-
-		ctx->count.c64[0] += (input_len >> 29);
-	}
-
-	buf_len = buf_limit - buf_index;
-
-	/* transform as many times as possible */
-	i = 0;
-	if (input_len >= buf_len) {
-
-		/*
-		 * general optimization:
-		 *
-		 * only do initial memcpy() and SHA2Transform() if
-		 * buf_index != 0.  if buf_index == 0, we're just
-		 * wasting our time doing the memcpy() since there
-		 * wasn't any data left over from a previous call to
-		 * SHA2Update().
-		 */
-		if (buf_index) {
-			memcpy(&ctx->buf_un.buf8[buf_index], input, buf_len);
-			if (algotype <= SHA256_HMAC_GEN_MECH_INFO_TYPE)
-				SHA256Transform(ctx, ctx->buf_un.buf8);
-			else
-				SHA512Transform(ctx, ctx->buf_un.buf8);
-
-			i = buf_len;
-		}
-
-#if !defined(__amd64) || !defined(_KERNEL)
-		if (algotype <= SHA256_HMAC_GEN_MECH_INFO_TYPE) {
-			for (; i + buf_limit - 1 < input_len; i += buf_limit) {
-				SHA256Transform(ctx, &input[i]);
-			}
-		} else {
-			for (; i + buf_limit - 1 < input_len; i += buf_limit) {
-				SHA512Transform(ctx, &input[i]);
-			}
-		}
-
-#else
-		uint32_t block_count;
-		if (algotype <= SHA256_HMAC_GEN_MECH_INFO_TYPE) {
-			block_count = (input_len - i) >> 6;
-			if (block_count > 0) {
-				SHA256TransformBlocks(ctx, &input[i],
-				    block_count);
-				i += block_count << 6;
-			}
-		} else {
-			block_count = (input_len - i) >> 7;
-			if (block_count > 0) {
-				SHA512TransformBlocks(ctx, &input[i],
-				    block_count);
-				i += block_count << 7;
-			}
-		}
-#endif	/* !__amd64 || !_KERNEL */
-
-		/*
-		 * general optimization:
-		 *
-		 * if i and input_len are the same, return now instead
-		 * of calling memcpy(), since the memcpy() in this case
-		 * will be an expensive noop.
-		 */
-
-		if (input_len == i)
-			return;
-
-		buf_index = 0;
-	}
-
-	/* buffer remaining input */
-	memcpy(&ctx->buf_un.buf8[buf_index], &input[i], input_len - i);
-}
-
-
-/*
- * SHA2Final()
- *
- * purpose: ends an sha2 digest operation, finalizing the message digest and
- *          zeroing the context.
- *   input: uchar_t *	: a buffer to store the digest
- *			: The function actually uses void* because many
- *			: callers pass things other than uchar_t here.
- *          SHA2_CTX *  : the context to finalize, save, and zero
- *  output: void
- */
-
-void
-SHA2Final(void *digest, SHA2_CTX *ctx)
-{
-	uint8_t		bitcount_be[sizeof (ctx->count.c32)];
-	uint8_t		bitcount_be64[sizeof (ctx->count.c64)];
-	uint32_t	index;
-	uint32_t	algotype = ctx->algotype;
-
-	if (algotype <= SHA256_HMAC_GEN_MECH_INFO_TYPE) {
-		index  = (ctx->count.c32[1] >> 3) & 0x3f;
-		Encode(bitcount_be, ctx->count.c32, sizeof (bitcount_be));
-		SHA2Update(ctx, PADDING, ((index < 56) ? 56 : 120) - index);
-		SHA2Update(ctx, bitcount_be, sizeof (bitcount_be));
-		Encode(digest, ctx->state.s32, sizeof (ctx->state.s32));
-	} else {
-		index  = (ctx->count.c64[1] >> 3) & 0x7f;
-		Encode64(bitcount_be64, ctx->count.c64,
-		    sizeof (bitcount_be64));
-		SHA2Update(ctx, PADDING, ((index < 112) ? 112 : 240) - index);
-		SHA2Update(ctx, bitcount_be64, sizeof (bitcount_be64));
-		if (algotype <= SHA384_HMAC_GEN_MECH_INFO_TYPE) {
-			ctx->state.s64[6] = ctx->state.s64[7] = 0;
-			Encode64(digest, ctx->state.s64,
-			    sizeof (uint64_t) * 6);
-		} else if (algotype == SHA512_224_MECH_INFO_TYPE) {
-			uint8_t last[sizeof (uint64_t)];
-			/*
-			 * Since SHA-512/224 doesn't align well to 64-bit
-			 * boundaries, we must do the encoding in three steps:
-			 * 1) encode the three 64-bit words that fit neatly
-			 * 2) encode the last 64-bit word to a temp buffer
-			 * 3) chop out the lower 32-bits from the temp buffer
-			 *    and append them to the digest
-			 */
-			Encode64(digest, ctx->state.s64, sizeof (uint64_t) * 3);
-			Encode64(last, &ctx->state.s64[3], sizeof (uint64_t));
-			memcpy((uint8_t *)digest + 24, last, 4);
-		} else if (algotype == SHA512_256_MECH_INFO_TYPE) {
-			Encode64(digest, ctx->state.s64, sizeof (uint64_t) * 4);
-		} else {
-			Encode64(digest, ctx->state.s64,
-			    sizeof (ctx->state.s64));
-		}
-	}
-
-	/* zeroize sensitive information */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-#ifdef _KERNEL
-EXPORT_SYMBOL(SHA2Init);
-EXPORT_SYMBOL(SHA2Update);
-EXPORT_SYMBOL(SHA2Final);
-#endif
diff --git a/module/icp/asm-x86_64/sha2/sha256_impl.S b/module/icp/asm-x86_64/sha2/sha256_impl.S
deleted file mode 100644
index f1fde51c1..000000000
--- a/module/icp/asm-x86_64/sha2/sha256_impl.S
+++ /dev/null
@@ -1,2090 +0,0 @@
-/*
- * ====================================================================
- * Written by Andy Polyakov <[email protected]> for the OpenSSL
- * project. Rights for redistribution and usage in source and binary
- * forms are granted according to the OpenSSL license.
- * ====================================================================
- *
- * sha256/512_block procedure for x86_64.
- *
- * 40% improvement over compiler-generated code on Opteron. On EM64T
- * sha256 was observed to run >80% faster and sha512 - >40%. No magical
- * tricks, just straight implementation... I really wonder why gcc
- * [being armed with inline assembler] fails to generate as fast code.
- * The only thing which is cool about this module is that it's very
- * same instruction sequence used for both SHA-256 and SHA-512. In
- * former case the instructions operate on 32-bit operands, while in
- * latter - on 64-bit ones. All I had to do is to get one flavor right,
- * the other one passed the test right away:-)
- *
- * sha256_block runs in ~1005 cycles on Opteron, which gives you
- * asymptotic performance of 64*1000/1005=63.7MBps times CPU clock
- * frequency in GHz. sha512_block runs in ~1275 cycles, which results
- * in 128*1000/1275=100MBps per GHz. Is there room for improvement?
- * Well, if you compare it to IA-64 implementation, which maintains
- * X[16] in register bank[!], tends to 4 instructions per CPU clock
- * cycle and runs in 1003 cycles, 1275 is very good result for 3-way
- * issue Opteron pipeline and X[16] maintained in memory. So that *if*
- * there is a way to improve it, *then* the only way would be to try to
- * offload X[16] updates to SSE unit, but that would require "deeper"
- * loop unroll, which in turn would naturally cause size blow-up, not
- * to mention increased complexity! And once again, only *if* it's
- * actually possible to noticeably improve overall ILP, instruction
- * level parallelism, on a given CPU implementation in this case.
- *
- * Special note on Intel EM64T. While Opteron CPU exhibits perfect
- * performance ratio of 1.5 between 64- and 32-bit flavors [see above],
- * [currently available] EM64T CPUs apparently are far from it. On the
- * contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit
- * sha256_block:-( This is presumably because 64-bit shifts/rotates
- * apparently are not atomic instructions, but implemented in microcode.
- */
-
-/*
- * OpenSolaris OS modifications
- *
- * Sun elects to use this software under the BSD license.
- *
- * This source originates from OpenSSL file sha512-x86_64.pl at
- * ftp://ftp.openssl.org/snapshot/openssl-0.9.8-stable-SNAP-20080131.tar.gz
- * (presumably for future OpenSSL release 0.9.8h), with these changes:
- *
- * 1. Added perl "use strict" and declared variables.
- *
- * 2. Added OpenSolaris ENTRY_NP/SET_SIZE macros from
- * /usr/include/sys/asm_linkage.h, .ident keywords, and lint(1B) guards.
- *
- * 3. Removed x86_64-xlate.pl script (not needed for as(1) or gas(1)
- * assemblers).  Replaced the .picmeup macro with assembler code.
- *
- * 4. Added 8 to $ctx, as OpenSolaris OS has an extra 4-byte field, "algotype",
- * at the beginning of SHA2_CTX (the next field is 8-byte aligned).
- */
-
-/*
- * This file was generated by a perl script (sha512-x86_64.pl) that were
- * used to generate sha256 and sha512 variants from the same code base.
- * The comments from the original file have been pasted above.
- */
-
-#if defined(lint) || defined(__lint)
-#include <sys/stdint.h>
-#include <sha2/sha2.h>
-
-void
-SHA256TransformBlocks(SHA2_CTX *ctx, const void *in, size_t num)
-{
-	(void) ctx, (void) in, (void) num;
-}
-
-
-#else
-#define _ASM
-#include <sys/asm_linkage.h>
-
-ENTRY_NP(SHA256TransformBlocks)
-.cfi_startproc
-	ENDBR
-	movq	%rsp, %rax
-.cfi_def_cfa_register %rax
-	push	%rbx
-.cfi_offset	%rbx,-16
-	push	%rbp
-.cfi_offset	%rbp,-24
-	push	%r12
-.cfi_offset	%r12,-32
-	push	%r13
-.cfi_offset	%r13,-40
-	push	%r14
-.cfi_offset	%r14,-48
-	push	%r15
-.cfi_offset	%r15,-56
-	mov	%rsp,%rbp		# copy %rsp
-	shl	$4,%rdx		# num*16
-	sub	$16*4+4*8,%rsp
-	lea	(%rsi,%rdx,4),%rdx	# inp+num*16*4
-	and	$-64,%rsp		# align stack frame
-	add	$8,%rdi		# Skip OpenSolaris field, "algotype"
-	mov	%rdi,16*4+0*8(%rsp)		# save ctx, 1st arg
-	mov	%rsi,16*4+1*8(%rsp)		# save inp, 2nd arg
-	mov	%rdx,16*4+2*8(%rsp)		# save end pointer, "3rd" arg
-	mov	%rbp,16*4+3*8(%rsp)		# save copy of %rsp
-# echo ".cfi_cfa_expression %rsp+88,deref,+56" |
-#	openssl/crypto/perlasm/x86_64-xlate.pl
-.cfi_escape	0x0f,0x06,0x77,0xd8,0x00,0x06,0x23,0x38
-
-	#.picmeup %rbp
-	# The .picmeup pseudo-directive, from perlasm/x86_64_xlate.pl, puts
-	# the address of the "next" instruction into the target register
-	# (%rbp).  This generates these 2 instructions:
-	lea	.Llea(%rip),%rbp
-	#nop	# .picmeup generates a nop for mod 8 alignment--not needed here
-
-.Llea:
-	lea	K256-.(%rbp),%rbp
-
-	mov	4*0(%rdi),%eax
-	mov	4*1(%rdi),%ebx
-	mov	4*2(%rdi),%ecx
-	mov	4*3(%rdi),%edx
-	mov	4*4(%rdi),%r8d
-	mov	4*5(%rdi),%r9d
-	mov	4*6(%rdi),%r10d
-	mov	4*7(%rdi),%r11d
-	jmp	.Lloop
-
-.balign	16
-.Lloop:
-	xor	%rdi,%rdi
-	mov	4*0(%rsi),%r12d
-	bswap	%r12d
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-	mov	%r9d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r10d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r8d,%r15d			# (f^g)&e
-	mov	%r12d,0(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r10d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11d,%r12d			# T1+=h
-
-	mov	%eax,%r11d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-
-	ror	$2,%r11d
-	ror	$13,%r13d
-	mov	%eax,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r11d
-	ror	$9,%r13d
-	or	%ecx,%r14d			# a|c
-
-	xor	%r13d,%r11d			# h=Sigma0(a)
-	and	%ecx,%r15d			# a&c
-	add	%r12d,%edx			# d+=T1
-
-	and	%ebx,%r14d			# (a|c)&b
-	add	%r12d,%r11d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r11d			# h+=Maj(a,b,c)
-	mov	4*1(%rsi),%r12d
-	bswap	%r12d
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-	mov	%r8d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r9d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%edx,%r15d			# (f^g)&e
-	mov	%r12d,4(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r9d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10d,%r12d			# T1+=h
-
-	mov	%r11d,%r10d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-
-	ror	$2,%r10d
-	ror	$13,%r13d
-	mov	%r11d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r10d
-	ror	$9,%r13d
-	or	%ebx,%r14d			# a|c
-
-	xor	%r13d,%r10d			# h=Sigma0(a)
-	and	%ebx,%r15d			# a&c
-	add	%r12d,%ecx			# d+=T1
-
-	and	%eax,%r14d			# (a|c)&b
-	add	%r12d,%r10d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r10d			# h+=Maj(a,b,c)
-	mov	4*2(%rsi),%r12d
-	bswap	%r12d
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-	mov	%edx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r8d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ecx,%r15d			# (f^g)&e
-	mov	%r12d,8(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r8d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9d,%r12d			# T1+=h
-
-	mov	%r10d,%r9d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-
-	ror	$2,%r9d
-	ror	$13,%r13d
-	mov	%r10d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r9d
-	ror	$9,%r13d
-	or	%eax,%r14d			# a|c
-
-	xor	%r13d,%r9d			# h=Sigma0(a)
-	and	%eax,%r15d			# a&c
-	add	%r12d,%ebx			# d+=T1
-
-	and	%r11d,%r14d			# (a|c)&b
-	add	%r12d,%r9d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r9d			# h+=Maj(a,b,c)
-	mov	4*3(%rsi),%r12d
-	bswap	%r12d
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-	mov	%ecx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%edx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ebx,%r15d			# (f^g)&e
-	mov	%r12d,12(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%edx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8d,%r12d			# T1+=h
-
-	mov	%r9d,%r8d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-
-	ror	$2,%r8d
-	ror	$13,%r13d
-	mov	%r9d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r8d
-	ror	$9,%r13d
-	or	%r11d,%r14d			# a|c
-
-	xor	%r13d,%r8d			# h=Sigma0(a)
-	and	%r11d,%r15d			# a&c
-	add	%r12d,%eax			# d+=T1
-
-	and	%r10d,%r14d			# (a|c)&b
-	add	%r12d,%r8d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r8d			# h+=Maj(a,b,c)
-	mov	4*4(%rsi),%r12d
-	bswap	%r12d
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-	mov	%ebx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ecx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%eax,%r15d			# (f^g)&e
-	mov	%r12d,16(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ecx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%edx,%r12d			# T1+=h
-
-	mov	%r8d,%edx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-
-	ror	$2,%edx
-	ror	$13,%r13d
-	mov	%r8d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%edx
-	ror	$9,%r13d
-	or	%r10d,%r14d			# a|c
-
-	xor	%r13d,%edx			# h=Sigma0(a)
-	and	%r10d,%r15d			# a&c
-	add	%r12d,%r11d			# d+=T1
-
-	and	%r9d,%r14d			# (a|c)&b
-	add	%r12d,%edx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%edx			# h+=Maj(a,b,c)
-	mov	4*5(%rsi),%r12d
-	bswap	%r12d
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-	mov	%eax,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ebx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r11d,%r15d			# (f^g)&e
-	mov	%r12d,20(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ebx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ecx,%r12d			# T1+=h
-
-	mov	%edx,%ecx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-
-	ror	$2,%ecx
-	ror	$13,%r13d
-	mov	%edx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ecx
-	ror	$9,%r13d
-	or	%r9d,%r14d			# a|c
-
-	xor	%r13d,%ecx			# h=Sigma0(a)
-	and	%r9d,%r15d			# a&c
-	add	%r12d,%r10d			# d+=T1
-
-	and	%r8d,%r14d			# (a|c)&b
-	add	%r12d,%ecx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ecx			# h+=Maj(a,b,c)
-	mov	4*6(%rsi),%r12d
-	bswap	%r12d
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-	mov	%r11d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%eax,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r10d,%r15d			# (f^g)&e
-	mov	%r12d,24(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%eax,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ebx,%r12d			# T1+=h
-
-	mov	%ecx,%ebx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-
-	ror	$2,%ebx
-	ror	$13,%r13d
-	mov	%ecx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ebx
-	ror	$9,%r13d
-	or	%r8d,%r14d			# a|c
-
-	xor	%r13d,%ebx			# h=Sigma0(a)
-	and	%r8d,%r15d			# a&c
-	add	%r12d,%r9d			# d+=T1
-
-	and	%edx,%r14d			# (a|c)&b
-	add	%r12d,%ebx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ebx			# h+=Maj(a,b,c)
-	mov	4*7(%rsi),%r12d
-	bswap	%r12d
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-	mov	%r10d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r11d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r9d,%r15d			# (f^g)&e
-	mov	%r12d,28(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r11d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%eax,%r12d			# T1+=h
-
-	mov	%ebx,%eax
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-
-	ror	$2,%eax
-	ror	$13,%r13d
-	mov	%ebx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%eax
-	ror	$9,%r13d
-	or	%edx,%r14d			# a|c
-
-	xor	%r13d,%eax			# h=Sigma0(a)
-	and	%edx,%r15d			# a&c
-	add	%r12d,%r8d			# d+=T1
-
-	and	%ecx,%r14d			# (a|c)&b
-	add	%r12d,%eax			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%eax			# h+=Maj(a,b,c)
-	mov	4*8(%rsi),%r12d
-	bswap	%r12d
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-	mov	%r9d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r10d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r8d,%r15d			# (f^g)&e
-	mov	%r12d,32(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r10d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11d,%r12d			# T1+=h
-
-	mov	%eax,%r11d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-
-	ror	$2,%r11d
-	ror	$13,%r13d
-	mov	%eax,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r11d
-	ror	$9,%r13d
-	or	%ecx,%r14d			# a|c
-
-	xor	%r13d,%r11d			# h=Sigma0(a)
-	and	%ecx,%r15d			# a&c
-	add	%r12d,%edx			# d+=T1
-
-	and	%ebx,%r14d			# (a|c)&b
-	add	%r12d,%r11d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r11d			# h+=Maj(a,b,c)
-	mov	4*9(%rsi),%r12d
-	bswap	%r12d
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-	mov	%r8d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r9d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%edx,%r15d			# (f^g)&e
-	mov	%r12d,36(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r9d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10d,%r12d			# T1+=h
-
-	mov	%r11d,%r10d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-
-	ror	$2,%r10d
-	ror	$13,%r13d
-	mov	%r11d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r10d
-	ror	$9,%r13d
-	or	%ebx,%r14d			# a|c
-
-	xor	%r13d,%r10d			# h=Sigma0(a)
-	and	%ebx,%r15d			# a&c
-	add	%r12d,%ecx			# d+=T1
-
-	and	%eax,%r14d			# (a|c)&b
-	add	%r12d,%r10d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r10d			# h+=Maj(a,b,c)
-	mov	4*10(%rsi),%r12d
-	bswap	%r12d
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-	mov	%edx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r8d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ecx,%r15d			# (f^g)&e
-	mov	%r12d,40(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r8d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9d,%r12d			# T1+=h
-
-	mov	%r10d,%r9d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-
-	ror	$2,%r9d
-	ror	$13,%r13d
-	mov	%r10d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r9d
-	ror	$9,%r13d
-	or	%eax,%r14d			# a|c
-
-	xor	%r13d,%r9d			# h=Sigma0(a)
-	and	%eax,%r15d			# a&c
-	add	%r12d,%ebx			# d+=T1
-
-	and	%r11d,%r14d			# (a|c)&b
-	add	%r12d,%r9d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r9d			# h+=Maj(a,b,c)
-	mov	4*11(%rsi),%r12d
-	bswap	%r12d
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-	mov	%ecx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%edx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ebx,%r15d			# (f^g)&e
-	mov	%r12d,44(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%edx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8d,%r12d			# T1+=h
-
-	mov	%r9d,%r8d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-
-	ror	$2,%r8d
-	ror	$13,%r13d
-	mov	%r9d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r8d
-	ror	$9,%r13d
-	or	%r11d,%r14d			# a|c
-
-	xor	%r13d,%r8d			# h=Sigma0(a)
-	and	%r11d,%r15d			# a&c
-	add	%r12d,%eax			# d+=T1
-
-	and	%r10d,%r14d			# (a|c)&b
-	add	%r12d,%r8d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r8d			# h+=Maj(a,b,c)
-	mov	4*12(%rsi),%r12d
-	bswap	%r12d
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-	mov	%ebx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ecx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%eax,%r15d			# (f^g)&e
-	mov	%r12d,48(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ecx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%edx,%r12d			# T1+=h
-
-	mov	%r8d,%edx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-
-	ror	$2,%edx
-	ror	$13,%r13d
-	mov	%r8d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%edx
-	ror	$9,%r13d
-	or	%r10d,%r14d			# a|c
-
-	xor	%r13d,%edx			# h=Sigma0(a)
-	and	%r10d,%r15d			# a&c
-	add	%r12d,%r11d			# d+=T1
-
-	and	%r9d,%r14d			# (a|c)&b
-	add	%r12d,%edx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%edx			# h+=Maj(a,b,c)
-	mov	4*13(%rsi),%r12d
-	bswap	%r12d
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-	mov	%eax,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ebx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r11d,%r15d			# (f^g)&e
-	mov	%r12d,52(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ebx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ecx,%r12d			# T1+=h
-
-	mov	%edx,%ecx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-
-	ror	$2,%ecx
-	ror	$13,%r13d
-	mov	%edx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ecx
-	ror	$9,%r13d
-	or	%r9d,%r14d			# a|c
-
-	xor	%r13d,%ecx			# h=Sigma0(a)
-	and	%r9d,%r15d			# a&c
-	add	%r12d,%r10d			# d+=T1
-
-	and	%r8d,%r14d			# (a|c)&b
-	add	%r12d,%ecx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ecx			# h+=Maj(a,b,c)
-	mov	4*14(%rsi),%r12d
-	bswap	%r12d
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-	mov	%r11d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%eax,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r10d,%r15d			# (f^g)&e
-	mov	%r12d,56(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%eax,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ebx,%r12d			# T1+=h
-
-	mov	%ecx,%ebx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-
-	ror	$2,%ebx
-	ror	$13,%r13d
-	mov	%ecx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ebx
-	ror	$9,%r13d
-	or	%r8d,%r14d			# a|c
-
-	xor	%r13d,%ebx			# h=Sigma0(a)
-	and	%r8d,%r15d			# a&c
-	add	%r12d,%r9d			# d+=T1
-
-	and	%edx,%r14d			# (a|c)&b
-	add	%r12d,%ebx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ebx			# h+=Maj(a,b,c)
-	mov	4*15(%rsi),%r12d
-	bswap	%r12d
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-	mov	%r10d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r11d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r9d,%r15d			# (f^g)&e
-	mov	%r12d,60(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r11d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%eax,%r12d			# T1+=h
-
-	mov	%ebx,%eax
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-
-	ror	$2,%eax
-	ror	$13,%r13d
-	mov	%ebx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%eax
-	ror	$9,%r13d
-	or	%edx,%r14d			# a|c
-
-	xor	%r13d,%eax			# h=Sigma0(a)
-	and	%edx,%r15d			# a&c
-	add	%r12d,%r8d			# d+=T1
-
-	and	%ecx,%r14d			# (a|c)&b
-	add	%r12d,%eax			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%eax			# h+=Maj(a,b,c)
-	jmp	.Lrounds_16_xx
-.balign	16
-.Lrounds_16_xx:
-	mov	4(%rsp),%r13d
-	mov	56(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	36(%rsp),%r12d
-
-	add	0(%rsp),%r12d
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-	mov	%r9d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r10d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r8d,%r15d			# (f^g)&e
-	mov	%r12d,0(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r10d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11d,%r12d			# T1+=h
-
-	mov	%eax,%r11d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-
-	ror	$2,%r11d
-	ror	$13,%r13d
-	mov	%eax,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r11d
-	ror	$9,%r13d
-	or	%ecx,%r14d			# a|c
-
-	xor	%r13d,%r11d			# h=Sigma0(a)
-	and	%ecx,%r15d			# a&c
-	add	%r12d,%edx			# d+=T1
-
-	and	%ebx,%r14d			# (a|c)&b
-	add	%r12d,%r11d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r11d			# h+=Maj(a,b,c)
-	mov	8(%rsp),%r13d
-	mov	60(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	40(%rsp),%r12d
-
-	add	4(%rsp),%r12d
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-	mov	%r8d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r9d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%edx,%r15d			# (f^g)&e
-	mov	%r12d,4(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r9d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10d,%r12d			# T1+=h
-
-	mov	%r11d,%r10d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-
-	ror	$2,%r10d
-	ror	$13,%r13d
-	mov	%r11d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r10d
-	ror	$9,%r13d
-	or	%ebx,%r14d			# a|c
-
-	xor	%r13d,%r10d			# h=Sigma0(a)
-	and	%ebx,%r15d			# a&c
-	add	%r12d,%ecx			# d+=T1
-
-	and	%eax,%r14d			# (a|c)&b
-	add	%r12d,%r10d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r10d			# h+=Maj(a,b,c)
-	mov	12(%rsp),%r13d
-	mov	0(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	44(%rsp),%r12d
-
-	add	8(%rsp),%r12d
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-	mov	%edx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r8d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ecx,%r15d			# (f^g)&e
-	mov	%r12d,8(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r8d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9d,%r12d			# T1+=h
-
-	mov	%r10d,%r9d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-
-	ror	$2,%r9d
-	ror	$13,%r13d
-	mov	%r10d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r9d
-	ror	$9,%r13d
-	or	%eax,%r14d			# a|c
-
-	xor	%r13d,%r9d			# h=Sigma0(a)
-	and	%eax,%r15d			# a&c
-	add	%r12d,%ebx			# d+=T1
-
-	and	%r11d,%r14d			# (a|c)&b
-	add	%r12d,%r9d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r9d			# h+=Maj(a,b,c)
-	mov	16(%rsp),%r13d
-	mov	4(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	48(%rsp),%r12d
-
-	add	12(%rsp),%r12d
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-	mov	%ecx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%edx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ebx,%r15d			# (f^g)&e
-	mov	%r12d,12(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%edx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8d,%r12d			# T1+=h
-
-	mov	%r9d,%r8d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-
-	ror	$2,%r8d
-	ror	$13,%r13d
-	mov	%r9d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r8d
-	ror	$9,%r13d
-	or	%r11d,%r14d			# a|c
-
-	xor	%r13d,%r8d			# h=Sigma0(a)
-	and	%r11d,%r15d			# a&c
-	add	%r12d,%eax			# d+=T1
-
-	and	%r10d,%r14d			# (a|c)&b
-	add	%r12d,%r8d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r8d			# h+=Maj(a,b,c)
-	mov	20(%rsp),%r13d
-	mov	8(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	52(%rsp),%r12d
-
-	add	16(%rsp),%r12d
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-	mov	%ebx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ecx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%eax,%r15d			# (f^g)&e
-	mov	%r12d,16(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ecx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%edx,%r12d			# T1+=h
-
-	mov	%r8d,%edx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-
-	ror	$2,%edx
-	ror	$13,%r13d
-	mov	%r8d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%edx
-	ror	$9,%r13d
-	or	%r10d,%r14d			# a|c
-
-	xor	%r13d,%edx			# h=Sigma0(a)
-	and	%r10d,%r15d			# a&c
-	add	%r12d,%r11d			# d+=T1
-
-	and	%r9d,%r14d			# (a|c)&b
-	add	%r12d,%edx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%edx			# h+=Maj(a,b,c)
-	mov	24(%rsp),%r13d
-	mov	12(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	56(%rsp),%r12d
-
-	add	20(%rsp),%r12d
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-	mov	%eax,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ebx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r11d,%r15d			# (f^g)&e
-	mov	%r12d,20(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ebx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ecx,%r12d			# T1+=h
-
-	mov	%edx,%ecx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-
-	ror	$2,%ecx
-	ror	$13,%r13d
-	mov	%edx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ecx
-	ror	$9,%r13d
-	or	%r9d,%r14d			# a|c
-
-	xor	%r13d,%ecx			# h=Sigma0(a)
-	and	%r9d,%r15d			# a&c
-	add	%r12d,%r10d			# d+=T1
-
-	and	%r8d,%r14d			# (a|c)&b
-	add	%r12d,%ecx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ecx			# h+=Maj(a,b,c)
-	mov	28(%rsp),%r13d
-	mov	16(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	60(%rsp),%r12d
-
-	add	24(%rsp),%r12d
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-	mov	%r11d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%eax,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r10d,%r15d			# (f^g)&e
-	mov	%r12d,24(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%eax,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ebx,%r12d			# T1+=h
-
-	mov	%ecx,%ebx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-
-	ror	$2,%ebx
-	ror	$13,%r13d
-	mov	%ecx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ebx
-	ror	$9,%r13d
-	or	%r8d,%r14d			# a|c
-
-	xor	%r13d,%ebx			# h=Sigma0(a)
-	and	%r8d,%r15d			# a&c
-	add	%r12d,%r9d			# d+=T1
-
-	and	%edx,%r14d			# (a|c)&b
-	add	%r12d,%ebx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ebx			# h+=Maj(a,b,c)
-	mov	32(%rsp),%r13d
-	mov	20(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	0(%rsp),%r12d
-
-	add	28(%rsp),%r12d
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-	mov	%r10d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r11d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r9d,%r15d			# (f^g)&e
-	mov	%r12d,28(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r11d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%eax,%r12d			# T1+=h
-
-	mov	%ebx,%eax
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-
-	ror	$2,%eax
-	ror	$13,%r13d
-	mov	%ebx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%eax
-	ror	$9,%r13d
-	or	%edx,%r14d			# a|c
-
-	xor	%r13d,%eax			# h=Sigma0(a)
-	and	%edx,%r15d			# a&c
-	add	%r12d,%r8d			# d+=T1
-
-	and	%ecx,%r14d			# (a|c)&b
-	add	%r12d,%eax			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%eax			# h+=Maj(a,b,c)
-	mov	36(%rsp),%r13d
-	mov	24(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	4(%rsp),%r12d
-
-	add	32(%rsp),%r12d
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-	mov	%r9d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r10d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r8d,%r15d			# (f^g)&e
-	mov	%r12d,32(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r10d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11d,%r12d			# T1+=h
-
-	mov	%eax,%r11d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-
-	ror	$2,%r11d
-	ror	$13,%r13d
-	mov	%eax,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r11d
-	ror	$9,%r13d
-	or	%ecx,%r14d			# a|c
-
-	xor	%r13d,%r11d			# h=Sigma0(a)
-	and	%ecx,%r15d			# a&c
-	add	%r12d,%edx			# d+=T1
-
-	and	%ebx,%r14d			# (a|c)&b
-	add	%r12d,%r11d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r11d			# h+=Maj(a,b,c)
-	mov	40(%rsp),%r13d
-	mov	28(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	8(%rsp),%r12d
-
-	add	36(%rsp),%r12d
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-	mov	%r8d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r9d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%edx,%r15d			# (f^g)&e
-	mov	%r12d,36(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r9d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10d,%r12d			# T1+=h
-
-	mov	%r11d,%r10d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-
-	ror	$2,%r10d
-	ror	$13,%r13d
-	mov	%r11d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r10d
-	ror	$9,%r13d
-	or	%ebx,%r14d			# a|c
-
-	xor	%r13d,%r10d			# h=Sigma0(a)
-	and	%ebx,%r15d			# a&c
-	add	%r12d,%ecx			# d+=T1
-
-	and	%eax,%r14d			# (a|c)&b
-	add	%r12d,%r10d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r10d			# h+=Maj(a,b,c)
-	mov	44(%rsp),%r13d
-	mov	32(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	12(%rsp),%r12d
-
-	add	40(%rsp),%r12d
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-	mov	%edx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r8d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ecx,%r15d			# (f^g)&e
-	mov	%r12d,40(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r8d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9d,%r12d			# T1+=h
-
-	mov	%r10d,%r9d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-
-	ror	$2,%r9d
-	ror	$13,%r13d
-	mov	%r10d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r9d
-	ror	$9,%r13d
-	or	%eax,%r14d			# a|c
-
-	xor	%r13d,%r9d			# h=Sigma0(a)
-	and	%eax,%r15d			# a&c
-	add	%r12d,%ebx			# d+=T1
-
-	and	%r11d,%r14d			# (a|c)&b
-	add	%r12d,%r9d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r9d			# h+=Maj(a,b,c)
-	mov	48(%rsp),%r13d
-	mov	36(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	16(%rsp),%r12d
-
-	add	44(%rsp),%r12d
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-	mov	%ecx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%edx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%ebx,%r15d			# (f^g)&e
-	mov	%r12d,44(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%edx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8d,%r12d			# T1+=h
-
-	mov	%r9d,%r8d
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-
-	ror	$2,%r8d
-	ror	$13,%r13d
-	mov	%r9d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%r8d
-	ror	$9,%r13d
-	or	%r11d,%r14d			# a|c
-
-	xor	%r13d,%r8d			# h=Sigma0(a)
-	and	%r11d,%r15d			# a&c
-	add	%r12d,%eax			# d+=T1
-
-	and	%r10d,%r14d			# (a|c)&b
-	add	%r12d,%r8d			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%r8d			# h+=Maj(a,b,c)
-	mov	52(%rsp),%r13d
-	mov	40(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	20(%rsp),%r12d
-
-	add	48(%rsp),%r12d
-	mov	%eax,%r13d
-	mov	%eax,%r14d
-	mov	%ebx,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ecx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%eax,%r15d			# (f^g)&e
-	mov	%r12d,48(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ecx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%edx,%r12d			# T1+=h
-
-	mov	%r8d,%edx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%r8d,%r13d
-	mov	%r8d,%r14d
-
-	ror	$2,%edx
-	ror	$13,%r13d
-	mov	%r8d,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%edx
-	ror	$9,%r13d
-	or	%r10d,%r14d			# a|c
-
-	xor	%r13d,%edx			# h=Sigma0(a)
-	and	%r10d,%r15d			# a&c
-	add	%r12d,%r11d			# d+=T1
-
-	and	%r9d,%r14d			# (a|c)&b
-	add	%r12d,%edx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%edx			# h+=Maj(a,b,c)
-	mov	56(%rsp),%r13d
-	mov	44(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	24(%rsp),%r12d
-
-	add	52(%rsp),%r12d
-	mov	%r11d,%r13d
-	mov	%r11d,%r14d
-	mov	%eax,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%ebx,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r11d,%r15d			# (f^g)&e
-	mov	%r12d,52(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%ebx,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ecx,%r12d			# T1+=h
-
-	mov	%edx,%ecx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%edx,%r13d
-	mov	%edx,%r14d
-
-	ror	$2,%ecx
-	ror	$13,%r13d
-	mov	%edx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ecx
-	ror	$9,%r13d
-	or	%r9d,%r14d			# a|c
-
-	xor	%r13d,%ecx			# h=Sigma0(a)
-	and	%r9d,%r15d			# a&c
-	add	%r12d,%r10d			# d+=T1
-
-	and	%r8d,%r14d			# (a|c)&b
-	add	%r12d,%ecx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ecx			# h+=Maj(a,b,c)
-	mov	60(%rsp),%r13d
-	mov	48(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	28(%rsp),%r12d
-
-	add	56(%rsp),%r12d
-	mov	%r10d,%r13d
-	mov	%r10d,%r14d
-	mov	%r11d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%eax,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r10d,%r15d			# (f^g)&e
-	mov	%r12d,56(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%eax,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%ebx,%r12d			# T1+=h
-
-	mov	%ecx,%ebx
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ecx,%r13d
-	mov	%ecx,%r14d
-
-	ror	$2,%ebx
-	ror	$13,%r13d
-	mov	%ecx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%ebx
-	ror	$9,%r13d
-	or	%r8d,%r14d			# a|c
-
-	xor	%r13d,%ebx			# h=Sigma0(a)
-	and	%r8d,%r15d			# a&c
-	add	%r12d,%r9d			# d+=T1
-
-	and	%edx,%r14d			# (a|c)&b
-	add	%r12d,%ebx			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%ebx			# h+=Maj(a,b,c)
-	mov	0(%rsp),%r13d
-	mov	52(%rsp),%r12d
-
-	mov	%r13d,%r15d
-
-	shr	$3,%r13d
-	ror	$7,%r15d
-
-	xor	%r15d,%r13d
-	ror	$11,%r15d
-
-	xor	%r15d,%r13d			# sigma0(X[(i+1)&0xf])
-	mov	%r12d,%r14d
-
-	shr	$10,%r12d
-	ror	$17,%r14d
-
-	xor	%r14d,%r12d
-	ror	$2,%r14d
-
-	xor	%r14d,%r12d			# sigma1(X[(i+14)&0xf])
-
-	add	%r13d,%r12d
-
-	add	32(%rsp),%r12d
-
-	add	60(%rsp),%r12d
-	mov	%r9d,%r13d
-	mov	%r9d,%r14d
-	mov	%r10d,%r15d
-
-	ror	$6,%r13d
-	ror	$11,%r14d
-	xor	%r11d,%r15d			# f^g
-
-	xor	%r14d,%r13d
-	ror	$14,%r14d
-	and	%r9d,%r15d			# (f^g)&e
-	mov	%r12d,60(%rsp)
-
-	xor	%r14d,%r13d			# Sigma1(e)
-	xor	%r11d,%r15d			# Ch(e,f,g)=((f^g)&e)^g
-	add	%eax,%r12d			# T1+=h
-
-	mov	%ebx,%eax
-	add	%r13d,%r12d			# T1+=Sigma1(e)
-
-	add	%r15d,%r12d			# T1+=Ch(e,f,g)
-	mov	%ebx,%r13d
-	mov	%ebx,%r14d
-
-	ror	$2,%eax
-	ror	$13,%r13d
-	mov	%ebx,%r15d
-	add	(%rbp,%rdi,4),%r12d	# T1+=K[round]
-
-	xor	%r13d,%eax
-	ror	$9,%r13d
-	or	%edx,%r14d			# a|c
-
-	xor	%r13d,%eax			# h=Sigma0(a)
-	and	%edx,%r15d			# a&c
-	add	%r12d,%r8d			# d+=T1
-
-	and	%ecx,%r14d			# (a|c)&b
-	add	%r12d,%eax			# h+=T1
-
-	or	%r15d,%r14d			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14d,%eax			# h+=Maj(a,b,c)
-	cmp	$64,%rdi
-	jb	.Lrounds_16_xx
-
-	mov	16*4+0*8(%rsp),%rdi
-	lea	16*4(%rsi),%rsi
-
-	add	4*0(%rdi),%eax
-	add	4*1(%rdi),%ebx
-	add	4*2(%rdi),%ecx
-	add	4*3(%rdi),%edx
-	add	4*4(%rdi),%r8d
-	add	4*5(%rdi),%r9d
-	add	4*6(%rdi),%r10d
-	add	4*7(%rdi),%r11d
-
-	cmp	16*4+2*8(%rsp),%rsi
-
-	mov	%eax,4*0(%rdi)
-	mov	%ebx,4*1(%rdi)
-	mov	%ecx,4*2(%rdi)
-	mov	%edx,4*3(%rdi)
-	mov	%r8d,4*4(%rdi)
-	mov	%r9d,4*5(%rdi)
-	mov	%r10d,4*6(%rdi)
-	mov	%r11d,4*7(%rdi)
-	jb	.Lloop
-
-	mov	16*4+3*8(%rsp),%rsp
-.cfi_def_cfa	%rsp,56
-	pop	%r15
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r15
-	pop	%r14
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r14
-	pop	%r13
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r13
-	pop	%r12
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r12
-	pop	%rbp
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%rbp
-	pop	%rbx
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%rbx
-
-	RET
-.cfi_endproc
-SET_SIZE(SHA256TransformBlocks)
-
-SECTION_STATIC
-.balign	64
-SET_OBJ(K256)
-K256:
-	.long	0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
-	.long	0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
-	.long	0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
-	.long	0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
-	.long	0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
-	.long	0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
-	.long	0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
-	.long	0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
-	.long	0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
-	.long	0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
-	.long	0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
-	.long	0xd192e819,0xd6990624,0xf40e3585,0x106aa070
-	.long	0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
-	.long	0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
-	.long	0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
-	.long	0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-#endif /* !lint && !__lint */
-
-#ifdef __ELF__
-.section .note.GNU-stack,"",%progbits
-#endif
diff --git a/module/icp/asm-x86_64/sha2/sha512_impl.S b/module/icp/asm-x86_64/sha2/sha512_impl.S
deleted file mode 100644
index b2f7d4863..000000000
--- a/module/icp/asm-x86_64/sha2/sha512_impl.S
+++ /dev/null
@@ -1,2115 +0,0 @@
-/*
- * ====================================================================
- * Written by Andy Polyakov <[email protected]> for the OpenSSL
- * project. Rights for redistribution and usage in source and binary
- * forms are granted according to the OpenSSL license.
- * ====================================================================
- *
- * sha256/512_block procedure for x86_64.
- *
- * 40% improvement over compiler-generated code on Opteron. On EM64T
- * sha256 was observed to run >80% faster and sha512 - >40%. No magical
- * tricks, just straight implementation... I really wonder why gcc
- * [being armed with inline assembler] fails to generate as fast code.
- * The only thing which is cool about this module is that it's very
- * same instruction sequence used for both SHA-256 and SHA-512. In
- * former case the instructions operate on 32-bit operands, while in
- * latter - on 64-bit ones. All I had to do is to get one flavor right,
- * the other one passed the test right away:-)
- *
- * sha256_block runs in ~1005 cycles on Opteron, which gives you
- * asymptotic performance of 64*1000/1005=63.7MBps times CPU clock
- * frequency in GHz. sha512_block runs in ~1275 cycles, which results
- * in 128*1000/1275=100MBps per GHz. Is there room for improvement?
- * Well, if you compare it to IA-64 implementation, which maintains
- * X[16] in register bank[!], tends to 4 instructions per CPU clock
- * cycle and runs in 1003 cycles, 1275 is very good result for 3-way
- * issue Opteron pipeline and X[16] maintained in memory. So that *if*
- * there is a way to improve it, *then* the only way would be to try to
- * offload X[16] updates to SSE unit, but that would require "deeper"
- * loop unroll, which in turn would naturally cause size blow-up, not
- * to mention increased complexity! And once again, only *if* it's
- * actually possible to noticeably improve overall ILP, instruction
- * level parallelism, on a given CPU implementation in this case.
- *
- * Special note on Intel EM64T. While Opteron CPU exhibits perfect
- * performance ratio of 1.5 between 64- and 32-bit flavors [see above],
- * [currently available] EM64T CPUs apparently are far from it. On the
- * contrary, 64-bit version, sha512_block, is ~30% *slower* than 32-bit
- * sha256_block:-( This is presumably because 64-bit shifts/rotates
- * apparently are not atomic instructions, but implemented in microcode.
- */
-
-/*
- * OpenSolaris OS modifications
- *
- * Sun elects to use this software under the BSD license.
- *
- * This source originates from OpenSSL file sha512-x86_64.pl at
- * ftp://ftp.openssl.org/snapshot/openssl-0.9.8-stable-SNAP-20080131.tar.gz
- * (presumably for future OpenSSL release 0.9.8h), with these changes:
- *
- * 1. Added perl "use strict" and declared variables.
- *
- * 2. Added OpenSolaris ENTRY_NP/SET_SIZE macros from
- * /usr/include/sys/asm_linkage.h, .ident keywords, and lint(1B) guards.
- *
- * 3. Removed x86_64-xlate.pl script (not needed for as(1) or gas(1)
- * assemblers).  Replaced the .picmeup macro with assembler code.
- *
- * 4. Added 8 to $ctx, as OpenSolaris OS has an extra 4-byte field, "algotype",
- * at the beginning of SHA2_CTX (the next field is 8-byte aligned).
- */
-
-/*
- * This file was generated by a perl script (sha512-x86_64.pl) that were
- * used to generate sha256 and sha512 variants from the same code base.
- * The comments from the original file have been pasted above.
- */
-
-
-#if defined(lint) || defined(__lint)
-#include <sys/stdint.h>
-#include <sha2/sha2.h>
-
-void
-SHA512TransformBlocks(SHA2_CTX *ctx, const void *in, size_t num)
-{
-	(void) ctx, (void) in, (void) num;
-}
-
-
-#else
-#define _ASM
-#include <sys/asm_linkage.h>
-
-ENTRY_NP(SHA512TransformBlocks)
-.cfi_startproc
-	ENDBR
-	movq	%rsp, %rax
-.cfi_def_cfa_register %rax
-	push	%rbx
-.cfi_offset	%rbx,-16
-	push	%rbp
-.cfi_offset	%rbp,-24
-	push	%r12
-.cfi_offset	%r12,-32
-	push	%r13
-.cfi_offset	%r13,-40
-	push	%r14
-.cfi_offset	%r14,-48
-	push	%r15
-.cfi_offset	%r15,-56
-	mov	%rsp,%rbp		# copy %rsp
-	shl	$4,%rdx		# num*16
-	sub	$16*8+4*8,%rsp
-	lea	(%rsi,%rdx,8),%rdx	# inp+num*16*8
-	and	$-64,%rsp		# align stack frame
-	add	$8,%rdi		# Skip OpenSolaris field, "algotype"
-	mov	%rdi,16*8+0*8(%rsp)		# save ctx, 1st arg
-	mov	%rsi,16*8+1*8(%rsp)		# save inp, 2nd arg
-	mov	%rdx,16*8+2*8(%rsp)		# save end pointer, "3rd" arg
-	mov	%rbp,16*8+3*8(%rsp)		# save copy of %rsp
-# echo ".cfi_cfa_expression %rsp+152,deref,+56" |
-#	openssl/crypto/perlasm/x86_64-xlate.pl
-.cfi_escape	0x0f,0x06,0x77,0x98,0x01,0x06,0x23,0x38
-
-	#.picmeup %rbp
-	# The .picmeup pseudo-directive, from perlasm/x86_64_xlate.pl, puts
-	# the address of the "next" instruction into the target register
-	# (%rbp).  This generates these 2 instructions:
-	lea	.Llea(%rip),%rbp
-	#nop	# .picmeup generates a nop for mod 8 alignment--not needed here
-
-.Llea:
-	lea	K512-.(%rbp),%rbp
-
-	mov	8*0(%rdi),%rax
-	mov	8*1(%rdi),%rbx
-	mov	8*2(%rdi),%rcx
-	mov	8*3(%rdi),%rdx
-	mov	8*4(%rdi),%r8
-	mov	8*5(%rdi),%r9
-	mov	8*6(%rdi),%r10
-	mov	8*7(%rdi),%r11
-	jmp	.Lloop
-
-.balign	16
-.Lloop:
-	xor	%rdi,%rdi
-	mov	8*0(%rsi),%r12
-	bswap	%r12
-	mov	%r8,%r13
-	mov	%r8,%r14
-	mov	%r9,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r10,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r8,%r15			# (f^g)&e
-	mov	%r12,0(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11,%r12			# T1+=h
-
-	mov	%rax,%r11
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rax,%r13
-	mov	%rax,%r14
-
-	ror	$28,%r11
-	ror	$34,%r13
-	mov	%rax,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r11
-	ror	$5,%r13
-	or	%rcx,%r14			# a|c
-
-	xor	%r13,%r11			# h=Sigma0(a)
-	and	%rcx,%r15			# a&c
-	add	%r12,%rdx			# d+=T1
-
-	and	%rbx,%r14			# (a|c)&b
-	add	%r12,%r11			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r11			# h+=Maj(a,b,c)
-	mov	8*1(%rsi),%r12
-	bswap	%r12
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-	mov	%r8,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r9,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rdx,%r15			# (f^g)&e
-	mov	%r12,8(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10,%r12			# T1+=h
-
-	mov	%r11,%r10
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r11,%r13
-	mov	%r11,%r14
-
-	ror	$28,%r10
-	ror	$34,%r13
-	mov	%r11,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r10
-	ror	$5,%r13
-	or	%rbx,%r14			# a|c
-
-	xor	%r13,%r10			# h=Sigma0(a)
-	and	%rbx,%r15			# a&c
-	add	%r12,%rcx			# d+=T1
-
-	and	%rax,%r14			# (a|c)&b
-	add	%r12,%r10			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r10			# h+=Maj(a,b,c)
-	mov	8*2(%rsi),%r12
-	bswap	%r12
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-	mov	%rdx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r8,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rcx,%r15			# (f^g)&e
-	mov	%r12,16(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9,%r12			# T1+=h
-
-	mov	%r10,%r9
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r10,%r13
-	mov	%r10,%r14
-
-	ror	$28,%r9
-	ror	$34,%r13
-	mov	%r10,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r9
-	ror	$5,%r13
-	or	%rax,%r14			# a|c
-
-	xor	%r13,%r9			# h=Sigma0(a)
-	and	%rax,%r15			# a&c
-	add	%r12,%rbx			# d+=T1
-
-	and	%r11,%r14			# (a|c)&b
-	add	%r12,%r9			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r9			# h+=Maj(a,b,c)
-	mov	8*3(%rsi),%r12
-	bswap	%r12
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-	mov	%rcx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rdx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rbx,%r15			# (f^g)&e
-	mov	%r12,24(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8,%r12			# T1+=h
-
-	mov	%r9,%r8
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r9,%r13
-	mov	%r9,%r14
-
-	ror	$28,%r8
-	ror	$34,%r13
-	mov	%r9,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r8
-	ror	$5,%r13
-	or	%r11,%r14			# a|c
-
-	xor	%r13,%r8			# h=Sigma0(a)
-	and	%r11,%r15			# a&c
-	add	%r12,%rax			# d+=T1
-
-	and	%r10,%r14			# (a|c)&b
-	add	%r12,%r8			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r8			# h+=Maj(a,b,c)
-	mov	8*4(%rsi),%r12
-	bswap	%r12
-	mov	%rax,%r13
-	mov	%rax,%r14
-	mov	%rbx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rcx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rax,%r15			# (f^g)&e
-	mov	%r12,32(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rdx,%r12			# T1+=h
-
-	mov	%r8,%rdx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r8,%r13
-	mov	%r8,%r14
-
-	ror	$28,%rdx
-	ror	$34,%r13
-	mov	%r8,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rdx
-	ror	$5,%r13
-	or	%r10,%r14			# a|c
-
-	xor	%r13,%rdx			# h=Sigma0(a)
-	and	%r10,%r15			# a&c
-	add	%r12,%r11			# d+=T1
-
-	and	%r9,%r14			# (a|c)&b
-	add	%r12,%rdx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rdx			# h+=Maj(a,b,c)
-	mov	8*5(%rsi),%r12
-	bswap	%r12
-	mov	%r11,%r13
-	mov	%r11,%r14
-	mov	%rax,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rbx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r11,%r15			# (f^g)&e
-	mov	%r12,40(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rcx,%r12			# T1+=h
-
-	mov	%rdx,%rcx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-
-	ror	$28,%rcx
-	ror	$34,%r13
-	mov	%rdx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rcx
-	ror	$5,%r13
-	or	%r9,%r14			# a|c
-
-	xor	%r13,%rcx			# h=Sigma0(a)
-	and	%r9,%r15			# a&c
-	add	%r12,%r10			# d+=T1
-
-	and	%r8,%r14			# (a|c)&b
-	add	%r12,%rcx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rcx			# h+=Maj(a,b,c)
-	mov	8*6(%rsi),%r12
-	bswap	%r12
-	mov	%r10,%r13
-	mov	%r10,%r14
-	mov	%r11,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rax,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r10,%r15			# (f^g)&e
-	mov	%r12,48(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rbx,%r12			# T1+=h
-
-	mov	%rcx,%rbx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-
-	ror	$28,%rbx
-	ror	$34,%r13
-	mov	%rcx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rbx
-	ror	$5,%r13
-	or	%r8,%r14			# a|c
-
-	xor	%r13,%rbx			# h=Sigma0(a)
-	and	%r8,%r15			# a&c
-	add	%r12,%r9			# d+=T1
-
-	and	%rdx,%r14			# (a|c)&b
-	add	%r12,%rbx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rbx			# h+=Maj(a,b,c)
-	mov	8*7(%rsi),%r12
-	bswap	%r12
-	mov	%r9,%r13
-	mov	%r9,%r14
-	mov	%r10,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r11,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r9,%r15			# (f^g)&e
-	mov	%r12,56(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rax,%r12			# T1+=h
-
-	mov	%rbx,%rax
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-
-	ror	$28,%rax
-	ror	$34,%r13
-	mov	%rbx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rax
-	ror	$5,%r13
-	or	%rdx,%r14			# a|c
-
-	xor	%r13,%rax			# h=Sigma0(a)
-	and	%rdx,%r15			# a&c
-	add	%r12,%r8			# d+=T1
-
-	and	%rcx,%r14			# (a|c)&b
-	add	%r12,%rax			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rax			# h+=Maj(a,b,c)
-	mov	8*8(%rsi),%r12
-	bswap	%r12
-	mov	%r8,%r13
-	mov	%r8,%r14
-	mov	%r9,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r10,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r8,%r15			# (f^g)&e
-	mov	%r12,64(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11,%r12			# T1+=h
-
-	mov	%rax,%r11
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rax,%r13
-	mov	%rax,%r14
-
-	ror	$28,%r11
-	ror	$34,%r13
-	mov	%rax,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r11
-	ror	$5,%r13
-	or	%rcx,%r14			# a|c
-
-	xor	%r13,%r11			# h=Sigma0(a)
-	and	%rcx,%r15			# a&c
-	add	%r12,%rdx			# d+=T1
-
-	and	%rbx,%r14			# (a|c)&b
-	add	%r12,%r11			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r11			# h+=Maj(a,b,c)
-	mov	8*9(%rsi),%r12
-	bswap	%r12
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-	mov	%r8,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r9,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rdx,%r15			# (f^g)&e
-	mov	%r12,72(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10,%r12			# T1+=h
-
-	mov	%r11,%r10
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r11,%r13
-	mov	%r11,%r14
-
-	ror	$28,%r10
-	ror	$34,%r13
-	mov	%r11,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r10
-	ror	$5,%r13
-	or	%rbx,%r14			# a|c
-
-	xor	%r13,%r10			# h=Sigma0(a)
-	and	%rbx,%r15			# a&c
-	add	%r12,%rcx			# d+=T1
-
-	and	%rax,%r14			# (a|c)&b
-	add	%r12,%r10			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r10			# h+=Maj(a,b,c)
-	mov	8*10(%rsi),%r12
-	bswap	%r12
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-	mov	%rdx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r8,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rcx,%r15			# (f^g)&e
-	mov	%r12,80(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9,%r12			# T1+=h
-
-	mov	%r10,%r9
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r10,%r13
-	mov	%r10,%r14
-
-	ror	$28,%r9
-	ror	$34,%r13
-	mov	%r10,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r9
-	ror	$5,%r13
-	or	%rax,%r14			# a|c
-
-	xor	%r13,%r9			# h=Sigma0(a)
-	and	%rax,%r15			# a&c
-	add	%r12,%rbx			# d+=T1
-
-	and	%r11,%r14			# (a|c)&b
-	add	%r12,%r9			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r9			# h+=Maj(a,b,c)
-	mov	8*11(%rsi),%r12
-	bswap	%r12
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-	mov	%rcx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rdx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rbx,%r15			# (f^g)&e
-	mov	%r12,88(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8,%r12			# T1+=h
-
-	mov	%r9,%r8
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r9,%r13
-	mov	%r9,%r14
-
-	ror	$28,%r8
-	ror	$34,%r13
-	mov	%r9,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r8
-	ror	$5,%r13
-	or	%r11,%r14			# a|c
-
-	xor	%r13,%r8			# h=Sigma0(a)
-	and	%r11,%r15			# a&c
-	add	%r12,%rax			# d+=T1
-
-	and	%r10,%r14			# (a|c)&b
-	add	%r12,%r8			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r8			# h+=Maj(a,b,c)
-	mov	8*12(%rsi),%r12
-	bswap	%r12
-	mov	%rax,%r13
-	mov	%rax,%r14
-	mov	%rbx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rcx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rax,%r15			# (f^g)&e
-	mov	%r12,96(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rdx,%r12			# T1+=h
-
-	mov	%r8,%rdx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r8,%r13
-	mov	%r8,%r14
-
-	ror	$28,%rdx
-	ror	$34,%r13
-	mov	%r8,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rdx
-	ror	$5,%r13
-	or	%r10,%r14			# a|c
-
-	xor	%r13,%rdx			# h=Sigma0(a)
-	and	%r10,%r15			# a&c
-	add	%r12,%r11			# d+=T1
-
-	and	%r9,%r14			# (a|c)&b
-	add	%r12,%rdx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rdx			# h+=Maj(a,b,c)
-	mov	8*13(%rsi),%r12
-	bswap	%r12
-	mov	%r11,%r13
-	mov	%r11,%r14
-	mov	%rax,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rbx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r11,%r15			# (f^g)&e
-	mov	%r12,104(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rcx,%r12			# T1+=h
-
-	mov	%rdx,%rcx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-
-	ror	$28,%rcx
-	ror	$34,%r13
-	mov	%rdx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rcx
-	ror	$5,%r13
-	or	%r9,%r14			# a|c
-
-	xor	%r13,%rcx			# h=Sigma0(a)
-	and	%r9,%r15			# a&c
-	add	%r12,%r10			# d+=T1
-
-	and	%r8,%r14			# (a|c)&b
-	add	%r12,%rcx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rcx			# h+=Maj(a,b,c)
-	mov	8*14(%rsi),%r12
-	bswap	%r12
-	mov	%r10,%r13
-	mov	%r10,%r14
-	mov	%r11,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rax,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r10,%r15			# (f^g)&e
-	mov	%r12,112(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rbx,%r12			# T1+=h
-
-	mov	%rcx,%rbx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-
-	ror	$28,%rbx
-	ror	$34,%r13
-	mov	%rcx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rbx
-	ror	$5,%r13
-	or	%r8,%r14			# a|c
-
-	xor	%r13,%rbx			# h=Sigma0(a)
-	and	%r8,%r15			# a&c
-	add	%r12,%r9			# d+=T1
-
-	and	%rdx,%r14			# (a|c)&b
-	add	%r12,%rbx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rbx			# h+=Maj(a,b,c)
-	mov	8*15(%rsi),%r12
-	bswap	%r12
-	mov	%r9,%r13
-	mov	%r9,%r14
-	mov	%r10,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r11,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r9,%r15			# (f^g)&e
-	mov	%r12,120(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rax,%r12			# T1+=h
-
-	mov	%rbx,%rax
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-
-	ror	$28,%rax
-	ror	$34,%r13
-	mov	%rbx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rax
-	ror	$5,%r13
-	or	%rdx,%r14			# a|c
-
-	xor	%r13,%rax			# h=Sigma0(a)
-	and	%rdx,%r15			# a&c
-	add	%r12,%r8			# d+=T1
-
-	and	%rcx,%r14			# (a|c)&b
-	add	%r12,%rax			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rax			# h+=Maj(a,b,c)
-	jmp	.Lrounds_16_xx
-.balign	16
-.Lrounds_16_xx:
-	mov	8(%rsp),%r13
-	mov	112(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	72(%rsp),%r12
-
-	add	0(%rsp),%r12
-	mov	%r8,%r13
-	mov	%r8,%r14
-	mov	%r9,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r10,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r8,%r15			# (f^g)&e
-	mov	%r12,0(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11,%r12			# T1+=h
-
-	mov	%rax,%r11
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rax,%r13
-	mov	%rax,%r14
-
-	ror	$28,%r11
-	ror	$34,%r13
-	mov	%rax,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r11
-	ror	$5,%r13
-	or	%rcx,%r14			# a|c
-
-	xor	%r13,%r11			# h=Sigma0(a)
-	and	%rcx,%r15			# a&c
-	add	%r12,%rdx			# d+=T1
-
-	and	%rbx,%r14			# (a|c)&b
-	add	%r12,%r11			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r11			# h+=Maj(a,b,c)
-	mov	16(%rsp),%r13
-	mov	120(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	80(%rsp),%r12
-
-	add	8(%rsp),%r12
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-	mov	%r8,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r9,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rdx,%r15			# (f^g)&e
-	mov	%r12,8(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10,%r12			# T1+=h
-
-	mov	%r11,%r10
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r11,%r13
-	mov	%r11,%r14
-
-	ror	$28,%r10
-	ror	$34,%r13
-	mov	%r11,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r10
-	ror	$5,%r13
-	or	%rbx,%r14			# a|c
-
-	xor	%r13,%r10			# h=Sigma0(a)
-	and	%rbx,%r15			# a&c
-	add	%r12,%rcx			# d+=T1
-
-	and	%rax,%r14			# (a|c)&b
-	add	%r12,%r10			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r10			# h+=Maj(a,b,c)
-	mov	24(%rsp),%r13
-	mov	0(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	88(%rsp),%r12
-
-	add	16(%rsp),%r12
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-	mov	%rdx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r8,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rcx,%r15			# (f^g)&e
-	mov	%r12,16(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9,%r12			# T1+=h
-
-	mov	%r10,%r9
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r10,%r13
-	mov	%r10,%r14
-
-	ror	$28,%r9
-	ror	$34,%r13
-	mov	%r10,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r9
-	ror	$5,%r13
-	or	%rax,%r14			# a|c
-
-	xor	%r13,%r9			# h=Sigma0(a)
-	and	%rax,%r15			# a&c
-	add	%r12,%rbx			# d+=T1
-
-	and	%r11,%r14			# (a|c)&b
-	add	%r12,%r9			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r9			# h+=Maj(a,b,c)
-	mov	32(%rsp),%r13
-	mov	8(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	96(%rsp),%r12
-
-	add	24(%rsp),%r12
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-	mov	%rcx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rdx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rbx,%r15			# (f^g)&e
-	mov	%r12,24(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8,%r12			# T1+=h
-
-	mov	%r9,%r8
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r9,%r13
-	mov	%r9,%r14
-
-	ror	$28,%r8
-	ror	$34,%r13
-	mov	%r9,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r8
-	ror	$5,%r13
-	or	%r11,%r14			# a|c
-
-	xor	%r13,%r8			# h=Sigma0(a)
-	and	%r11,%r15			# a&c
-	add	%r12,%rax			# d+=T1
-
-	and	%r10,%r14			# (a|c)&b
-	add	%r12,%r8			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r8			# h+=Maj(a,b,c)
-	mov	40(%rsp),%r13
-	mov	16(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	104(%rsp),%r12
-
-	add	32(%rsp),%r12
-	mov	%rax,%r13
-	mov	%rax,%r14
-	mov	%rbx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rcx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rax,%r15			# (f^g)&e
-	mov	%r12,32(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rdx,%r12			# T1+=h
-
-	mov	%r8,%rdx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r8,%r13
-	mov	%r8,%r14
-
-	ror	$28,%rdx
-	ror	$34,%r13
-	mov	%r8,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rdx
-	ror	$5,%r13
-	or	%r10,%r14			# a|c
-
-	xor	%r13,%rdx			# h=Sigma0(a)
-	and	%r10,%r15			# a&c
-	add	%r12,%r11			# d+=T1
-
-	and	%r9,%r14			# (a|c)&b
-	add	%r12,%rdx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rdx			# h+=Maj(a,b,c)
-	mov	48(%rsp),%r13
-	mov	24(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	112(%rsp),%r12
-
-	add	40(%rsp),%r12
-	mov	%r11,%r13
-	mov	%r11,%r14
-	mov	%rax,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rbx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r11,%r15			# (f^g)&e
-	mov	%r12,40(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rcx,%r12			# T1+=h
-
-	mov	%rdx,%rcx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-
-	ror	$28,%rcx
-	ror	$34,%r13
-	mov	%rdx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rcx
-	ror	$5,%r13
-	or	%r9,%r14			# a|c
-
-	xor	%r13,%rcx			# h=Sigma0(a)
-	and	%r9,%r15			# a&c
-	add	%r12,%r10			# d+=T1
-
-	and	%r8,%r14			# (a|c)&b
-	add	%r12,%rcx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rcx			# h+=Maj(a,b,c)
-	mov	56(%rsp),%r13
-	mov	32(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	120(%rsp),%r12
-
-	add	48(%rsp),%r12
-	mov	%r10,%r13
-	mov	%r10,%r14
-	mov	%r11,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rax,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r10,%r15			# (f^g)&e
-	mov	%r12,48(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rbx,%r12			# T1+=h
-
-	mov	%rcx,%rbx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-
-	ror	$28,%rbx
-	ror	$34,%r13
-	mov	%rcx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rbx
-	ror	$5,%r13
-	or	%r8,%r14			# a|c
-
-	xor	%r13,%rbx			# h=Sigma0(a)
-	and	%r8,%r15			# a&c
-	add	%r12,%r9			# d+=T1
-
-	and	%rdx,%r14			# (a|c)&b
-	add	%r12,%rbx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rbx			# h+=Maj(a,b,c)
-	mov	64(%rsp),%r13
-	mov	40(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	0(%rsp),%r12
-
-	add	56(%rsp),%r12
-	mov	%r9,%r13
-	mov	%r9,%r14
-	mov	%r10,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r11,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r9,%r15			# (f^g)&e
-	mov	%r12,56(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rax,%r12			# T1+=h
-
-	mov	%rbx,%rax
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-
-	ror	$28,%rax
-	ror	$34,%r13
-	mov	%rbx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rax
-	ror	$5,%r13
-	or	%rdx,%r14			# a|c
-
-	xor	%r13,%rax			# h=Sigma0(a)
-	and	%rdx,%r15			# a&c
-	add	%r12,%r8			# d+=T1
-
-	and	%rcx,%r14			# (a|c)&b
-	add	%r12,%rax			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rax			# h+=Maj(a,b,c)
-	mov	72(%rsp),%r13
-	mov	48(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	8(%rsp),%r12
-
-	add	64(%rsp),%r12
-	mov	%r8,%r13
-	mov	%r8,%r14
-	mov	%r9,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r10,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r8,%r15			# (f^g)&e
-	mov	%r12,64(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r10,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r11,%r12			# T1+=h
-
-	mov	%rax,%r11
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rax,%r13
-	mov	%rax,%r14
-
-	ror	$28,%r11
-	ror	$34,%r13
-	mov	%rax,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r11
-	ror	$5,%r13
-	or	%rcx,%r14			# a|c
-
-	xor	%r13,%r11			# h=Sigma0(a)
-	and	%rcx,%r15			# a&c
-	add	%r12,%rdx			# d+=T1
-
-	and	%rbx,%r14			# (a|c)&b
-	add	%r12,%r11			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r11			# h+=Maj(a,b,c)
-	mov	80(%rsp),%r13
-	mov	56(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	16(%rsp),%r12
-
-	add	72(%rsp),%r12
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-	mov	%r8,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r9,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rdx,%r15			# (f^g)&e
-	mov	%r12,72(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r9,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r10,%r12			# T1+=h
-
-	mov	%r11,%r10
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r11,%r13
-	mov	%r11,%r14
-
-	ror	$28,%r10
-	ror	$34,%r13
-	mov	%r11,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r10
-	ror	$5,%r13
-	or	%rbx,%r14			# a|c
-
-	xor	%r13,%r10			# h=Sigma0(a)
-	and	%rbx,%r15			# a&c
-	add	%r12,%rcx			# d+=T1
-
-	and	%rax,%r14			# (a|c)&b
-	add	%r12,%r10			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r10			# h+=Maj(a,b,c)
-	mov	88(%rsp),%r13
-	mov	64(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	24(%rsp),%r12
-
-	add	80(%rsp),%r12
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-	mov	%rdx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r8,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rcx,%r15			# (f^g)&e
-	mov	%r12,80(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r8,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r9,%r12			# T1+=h
-
-	mov	%r10,%r9
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r10,%r13
-	mov	%r10,%r14
-
-	ror	$28,%r9
-	ror	$34,%r13
-	mov	%r10,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r9
-	ror	$5,%r13
-	or	%rax,%r14			# a|c
-
-	xor	%r13,%r9			# h=Sigma0(a)
-	and	%rax,%r15			# a&c
-	add	%r12,%rbx			# d+=T1
-
-	and	%r11,%r14			# (a|c)&b
-	add	%r12,%r9			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r9			# h+=Maj(a,b,c)
-	mov	96(%rsp),%r13
-	mov	72(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	32(%rsp),%r12
-
-	add	88(%rsp),%r12
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-	mov	%rcx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rdx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rbx,%r15			# (f^g)&e
-	mov	%r12,88(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rdx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%r8,%r12			# T1+=h
-
-	mov	%r9,%r8
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r9,%r13
-	mov	%r9,%r14
-
-	ror	$28,%r8
-	ror	$34,%r13
-	mov	%r9,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%r8
-	ror	$5,%r13
-	or	%r11,%r14			# a|c
-
-	xor	%r13,%r8			# h=Sigma0(a)
-	and	%r11,%r15			# a&c
-	add	%r12,%rax			# d+=T1
-
-	and	%r10,%r14			# (a|c)&b
-	add	%r12,%r8			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%r8			# h+=Maj(a,b,c)
-	mov	104(%rsp),%r13
-	mov	80(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	40(%rsp),%r12
-
-	add	96(%rsp),%r12
-	mov	%rax,%r13
-	mov	%rax,%r14
-	mov	%rbx,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rcx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%rax,%r15			# (f^g)&e
-	mov	%r12,96(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rcx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rdx,%r12			# T1+=h
-
-	mov	%r8,%rdx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%r8,%r13
-	mov	%r8,%r14
-
-	ror	$28,%rdx
-	ror	$34,%r13
-	mov	%r8,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rdx
-	ror	$5,%r13
-	or	%r10,%r14			# a|c
-
-	xor	%r13,%rdx			# h=Sigma0(a)
-	and	%r10,%r15			# a&c
-	add	%r12,%r11			# d+=T1
-
-	and	%r9,%r14			# (a|c)&b
-	add	%r12,%rdx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rdx			# h+=Maj(a,b,c)
-	mov	112(%rsp),%r13
-	mov	88(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	48(%rsp),%r12
-
-	add	104(%rsp),%r12
-	mov	%r11,%r13
-	mov	%r11,%r14
-	mov	%rax,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rbx,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r11,%r15			# (f^g)&e
-	mov	%r12,104(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rbx,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rcx,%r12			# T1+=h
-
-	mov	%rdx,%rcx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rdx,%r13
-	mov	%rdx,%r14
-
-	ror	$28,%rcx
-	ror	$34,%r13
-	mov	%rdx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rcx
-	ror	$5,%r13
-	or	%r9,%r14			# a|c
-
-	xor	%r13,%rcx			# h=Sigma0(a)
-	and	%r9,%r15			# a&c
-	add	%r12,%r10			# d+=T1
-
-	and	%r8,%r14			# (a|c)&b
-	add	%r12,%rcx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rcx			# h+=Maj(a,b,c)
-	mov	120(%rsp),%r13
-	mov	96(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	56(%rsp),%r12
-
-	add	112(%rsp),%r12
-	mov	%r10,%r13
-	mov	%r10,%r14
-	mov	%r11,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%rax,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r10,%r15			# (f^g)&e
-	mov	%r12,112(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%rax,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rbx,%r12			# T1+=h
-
-	mov	%rcx,%rbx
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rcx,%r13
-	mov	%rcx,%r14
-
-	ror	$28,%rbx
-	ror	$34,%r13
-	mov	%rcx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rbx
-	ror	$5,%r13
-	or	%r8,%r14			# a|c
-
-	xor	%r13,%rbx			# h=Sigma0(a)
-	and	%r8,%r15			# a&c
-	add	%r12,%r9			# d+=T1
-
-	and	%rdx,%r14			# (a|c)&b
-	add	%r12,%rbx			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rbx			# h+=Maj(a,b,c)
-	mov	0(%rsp),%r13
-	mov	104(%rsp),%r12
-
-	mov	%r13,%r15
-
-	shr	$7,%r13
-	ror	$1,%r15
-
-	xor	%r15,%r13
-	ror	$7,%r15
-
-	xor	%r15,%r13			# sigma0(X[(i+1)&0xf])
-	mov	%r12,%r14
-
-	shr	$6,%r12
-	ror	$19,%r14
-
-	xor	%r14,%r12
-	ror	$42,%r14
-
-	xor	%r14,%r12			# sigma1(X[(i+14)&0xf])
-
-	add	%r13,%r12
-
-	add	64(%rsp),%r12
-
-	add	120(%rsp),%r12
-	mov	%r9,%r13
-	mov	%r9,%r14
-	mov	%r10,%r15
-
-	ror	$14,%r13
-	ror	$18,%r14
-	xor	%r11,%r15			# f^g
-
-	xor	%r14,%r13
-	ror	$23,%r14
-	and	%r9,%r15			# (f^g)&e
-	mov	%r12,120(%rsp)
-
-	xor	%r14,%r13			# Sigma1(e)
-	xor	%r11,%r15			# Ch(e,f,g)=((f^g)&e)^g
-	add	%rax,%r12			# T1+=h
-
-	mov	%rbx,%rax
-	add	%r13,%r12			# T1+=Sigma1(e)
-
-	add	%r15,%r12			# T1+=Ch(e,f,g)
-	mov	%rbx,%r13
-	mov	%rbx,%r14
-
-	ror	$28,%rax
-	ror	$34,%r13
-	mov	%rbx,%r15
-	add	(%rbp,%rdi,8),%r12	# T1+=K[round]
-
-	xor	%r13,%rax
-	ror	$5,%r13
-	or	%rdx,%r14			# a|c
-
-	xor	%r13,%rax			# h=Sigma0(a)
-	and	%rdx,%r15			# a&c
-	add	%r12,%r8			# d+=T1
-
-	and	%rcx,%r14			# (a|c)&b
-	add	%r12,%rax			# h+=T1
-
-	or	%r15,%r14			# Maj(a,b,c)=((a|c)&b)|(a&c)
-	lea	1(%rdi),%rdi	# round++
-
-	add	%r14,%rax			# h+=Maj(a,b,c)
-	cmp	$80,%rdi
-	jb	.Lrounds_16_xx
-
-	mov	16*8+0*8(%rsp),%rdi
-	lea	16*8(%rsi),%rsi
-
-	add	8*0(%rdi),%rax
-	add	8*1(%rdi),%rbx
-	add	8*2(%rdi),%rcx
-	add	8*3(%rdi),%rdx
-	add	8*4(%rdi),%r8
-	add	8*5(%rdi),%r9
-	add	8*6(%rdi),%r10
-	add	8*7(%rdi),%r11
-
-	cmp	16*8+2*8(%rsp),%rsi
-
-	mov	%rax,8*0(%rdi)
-	mov	%rbx,8*1(%rdi)
-	mov	%rcx,8*2(%rdi)
-	mov	%rdx,8*3(%rdi)
-	mov	%r8,8*4(%rdi)
-	mov	%r9,8*5(%rdi)
-	mov	%r10,8*6(%rdi)
-	mov	%r11,8*7(%rdi)
-	jb	.Lloop
-
-	mov	16*8+3*8(%rsp),%rsp
-.cfi_def_cfa	%rsp,56
-	pop	%r15
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r15
-	pop	%r14
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r14
-	pop	%r13
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r13
-	pop	%r12
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%r12
-	pop	%rbp
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%rbp
-	pop	%rbx
-.cfi_adjust_cfa_offset -8
-.cfi_restore	%rbx
-
-	RET
-.cfi_endproc
-SET_SIZE(SHA512TransformBlocks)
-
-SECTION_STATIC
-.balign	64
-SET_OBJ(K512)
-K512:
-	.quad	0x428a2f98d728ae22,0x7137449123ef65cd
-	.quad	0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
-	.quad	0x3956c25bf348b538,0x59f111f1b605d019
-	.quad	0x923f82a4af194f9b,0xab1c5ed5da6d8118
-	.quad	0xd807aa98a3030242,0x12835b0145706fbe
-	.quad	0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
-	.quad	0x72be5d74f27b896f,0x80deb1fe3b1696b1
-	.quad	0x9bdc06a725c71235,0xc19bf174cf692694
-	.quad	0xe49b69c19ef14ad2,0xefbe4786384f25e3
-	.quad	0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
-	.quad	0x2de92c6f592b0275,0x4a7484aa6ea6e483
-	.quad	0x5cb0a9dcbd41fbd4,0x76f988da831153b5
-	.quad	0x983e5152ee66dfab,0xa831c66d2db43210
-	.quad	0xb00327c898fb213f,0xbf597fc7beef0ee4
-	.quad	0xc6e00bf33da88fc2,0xd5a79147930aa725
-	.quad	0x06ca6351e003826f,0x142929670a0e6e70
-	.quad	0x27b70a8546d22ffc,0x2e1b21385c26c926
-	.quad	0x4d2c6dfc5ac42aed,0x53380d139d95b3df
-	.quad	0x650a73548baf63de,0x766a0abb3c77b2a8
-	.quad	0x81c2c92e47edaee6,0x92722c851482353b
-	.quad	0xa2bfe8a14cf10364,0xa81a664bbc423001
-	.quad	0xc24b8b70d0f89791,0xc76c51a30654be30
-	.quad	0xd192e819d6ef5218,0xd69906245565a910
-	.quad	0xf40e35855771202a,0x106aa07032bbd1b8
-	.quad	0x19a4c116b8d2d0c8,0x1e376c085141ab53
-	.quad	0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
-	.quad	0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
-	.quad	0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
-	.quad	0x748f82ee5defb2fc,0x78a5636f43172f60
-	.quad	0x84c87814a1f0ab72,0x8cc702081a6439ec
-	.quad	0x90befffa23631e28,0xa4506cebde82bde9
-	.quad	0xbef9a3f7b2c67915,0xc67178f2e372532b
-	.quad	0xca273eceea26619c,0xd186b8c721c0c207
-	.quad	0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
-	.quad	0x06f067aa72176fba,0x0a637dc5a2c898a6
-	.quad	0x113f9804bef90dae,0x1b710b35131c471b
-	.quad	0x28db77f523047d84,0x32caab7b40c72493
-	.quad	0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
-	.quad	0x4cc5d4becb3e42b6,0x597f299cfc657e2a
-	.quad	0x5fcb6fab3ad6faec,0x6c44198c4a475817
-#endif /* !lint && !__lint */
-
-#if defined(__ELF__)
-.section .note.GNU-stack,"",%progbits
-#endif
diff --git a/module/icp/include/sha2/sha2_consts.h b/module/icp/include/sha2/sha2_consts.h
deleted file mode 100644
index b33ddf821..000000000
--- a/module/icp/include/sha2/sha2_consts.h
+++ /dev/null
@@ -1,219 +0,0 @@
-/*
- * CDDL HEADER START
- *
- * The contents of this file are subject to the terms of the
- * Common Development and Distribution License, Version 1.0 only
- * (the "License").  You may not use this file except in compliance
- * with the License.
- *
- * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
- * or https://opensource.org/licenses/CDDL-1.0.
- * See the License for the specific language governing permissions
- * and limitations under the License.
- *
- * When distributing Covered Code, include this CDDL HEADER in each
- * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
- * If applicable, add the following below this CDDL HEADER, with the
- * fields enclosed by brackets "[]" replaced with your own identifying
- * information: Portions Copyright [yyyy] [name of copyright owner]
- *
- * CDDL HEADER END
- */
-/*
- * Copyright 2005 Sun Microsystems, Inc.  All rights reserved.
- * Use is subject to license terms.
- */
-
-#ifndef	_SYS_SHA2_CONSTS_H
-#define	_SYS_SHA2_CONSTS_H
-
-#ifdef	__cplusplus
-extern "C" {
-#endif
-
-/*
- * Loading 32-bit constants on a sparc is expensive since it involves both
- * a `sethi' and an `or'.  thus, we instead use `ld' to load the constants
- * from an array called `sha2_consts'.  however, on intel (and perhaps other
- * processors), it is cheaper to load the constant directly.  thus, the c
- * code in SHA transform functions uses the macro SHA2_CONST() which either
- * expands to a constant or an array reference, depending on
- * the architecture the code is being compiled for.
- *
- * SHA512 constants are used for SHA384
- */
-
-#include <sys/types.h>		/* uint32_t */
-
-extern	const uint32_t	sha256_consts[];
-extern	const uint64_t	sha512_consts[];
-
-#if	defined(__sparc)
-#define	SHA256_CONST(x)		(sha256_consts[x])
-#define	SHA512_CONST(x)		(sha512_consts[x])
-#else
-#define	SHA256_CONST(x)		(SHA256_CONST_ ## x)
-#define	SHA512_CONST(x)		(SHA512_CONST_ ## x)
-#endif
-
-/* constants, as provided in FIPS 180-2 */
-
-#define	SHA256_CONST_0		0x428a2f98U
-#define	SHA256_CONST_1		0x71374491U
-#define	SHA256_CONST_2		0xb5c0fbcfU
-#define	SHA256_CONST_3		0xe9b5dba5U
-#define	SHA256_CONST_4		0x3956c25bU
-#define	SHA256_CONST_5		0x59f111f1U
-#define	SHA256_CONST_6		0x923f82a4U
-#define	SHA256_CONST_7		0xab1c5ed5U
-
-#define	SHA256_CONST_8		0xd807aa98U
-#define	SHA256_CONST_9		0x12835b01U
-#define	SHA256_CONST_10		0x243185beU
-#define	SHA256_CONST_11		0x550c7dc3U
-#define	SHA256_CONST_12		0x72be5d74U
-#define	SHA256_CONST_13		0x80deb1feU
-#define	SHA256_CONST_14		0x9bdc06a7U
-#define	SHA256_CONST_15		0xc19bf174U
-
-#define	SHA256_CONST_16		0xe49b69c1U
-#define	SHA256_CONST_17		0xefbe4786U
-#define	SHA256_CONST_18		0x0fc19dc6U
-#define	SHA256_CONST_19		0x240ca1ccU
-#define	SHA256_CONST_20		0x2de92c6fU
-#define	SHA256_CONST_21		0x4a7484aaU
-#define	SHA256_CONST_22		0x5cb0a9dcU
-#define	SHA256_CONST_23		0x76f988daU
-
-#define	SHA256_CONST_24		0x983e5152U
-#define	SHA256_CONST_25		0xa831c66dU
-#define	SHA256_CONST_26		0xb00327c8U
-#define	SHA256_CONST_27		0xbf597fc7U
-#define	SHA256_CONST_28		0xc6e00bf3U
-#define	SHA256_CONST_29		0xd5a79147U
-#define	SHA256_CONST_30		0x06ca6351U
-#define	SHA256_CONST_31		0x14292967U
-
-#define	SHA256_CONST_32		0x27b70a85U
-#define	SHA256_CONST_33		0x2e1b2138U
-#define	SHA256_CONST_34		0x4d2c6dfcU
-#define	SHA256_CONST_35		0x53380d13U
-#define	SHA256_CONST_36		0x650a7354U
-#define	SHA256_CONST_37		0x766a0abbU
-#define	SHA256_CONST_38		0x81c2c92eU
-#define	SHA256_CONST_39		0x92722c85U
-
-#define	SHA256_CONST_40		0xa2bfe8a1U
-#define	SHA256_CONST_41		0xa81a664bU
-#define	SHA256_CONST_42		0xc24b8b70U
-#define	SHA256_CONST_43		0xc76c51a3U
-#define	SHA256_CONST_44		0xd192e819U
-#define	SHA256_CONST_45		0xd6990624U
-#define	SHA256_CONST_46		0xf40e3585U
-#define	SHA256_CONST_47		0x106aa070U
-
-#define	SHA256_CONST_48		0x19a4c116U
-#define	SHA256_CONST_49		0x1e376c08U
-#define	SHA256_CONST_50		0x2748774cU
-#define	SHA256_CONST_51		0x34b0bcb5U
-#define	SHA256_CONST_52		0x391c0cb3U
-#define	SHA256_CONST_53		0x4ed8aa4aU
-#define	SHA256_CONST_54		0x5b9cca4fU
-#define	SHA256_CONST_55		0x682e6ff3U
-
-#define	SHA256_CONST_56		0x748f82eeU
-#define	SHA256_CONST_57		0x78a5636fU
-#define	SHA256_CONST_58		0x84c87814U
-#define	SHA256_CONST_59		0x8cc70208U
-#define	SHA256_CONST_60		0x90befffaU
-#define	SHA256_CONST_61		0xa4506cebU
-#define	SHA256_CONST_62		0xbef9a3f7U
-#define	SHA256_CONST_63		0xc67178f2U
-
-#define	SHA512_CONST_0		0x428a2f98d728ae22ULL
-#define	SHA512_CONST_1		0x7137449123ef65cdULL
-#define	SHA512_CONST_2		0xb5c0fbcfec4d3b2fULL
-#define	SHA512_CONST_3		0xe9b5dba58189dbbcULL
-#define	SHA512_CONST_4		0x3956c25bf348b538ULL
-#define	SHA512_CONST_5		0x59f111f1b605d019ULL
-#define	SHA512_CONST_6		0x923f82a4af194f9bULL
-#define	SHA512_CONST_7		0xab1c5ed5da6d8118ULL
-#define	SHA512_CONST_8		0xd807aa98a3030242ULL
-#define	SHA512_CONST_9		0x12835b0145706fbeULL
-#define	SHA512_CONST_10		0x243185be4ee4b28cULL
-#define	SHA512_CONST_11		0x550c7dc3d5ffb4e2ULL
-#define	SHA512_CONST_12		0x72be5d74f27b896fULL
-#define	SHA512_CONST_13		0x80deb1fe3b1696b1ULL
-#define	SHA512_CONST_14		0x9bdc06a725c71235ULL
-#define	SHA512_CONST_15		0xc19bf174cf692694ULL
-#define	SHA512_CONST_16		0xe49b69c19ef14ad2ULL
-#define	SHA512_CONST_17		0xefbe4786384f25e3ULL
-#define	SHA512_CONST_18		0x0fc19dc68b8cd5b5ULL
-#define	SHA512_CONST_19		0x240ca1cc77ac9c65ULL
-#define	SHA512_CONST_20		0x2de92c6f592b0275ULL
-#define	SHA512_CONST_21		0x4a7484aa6ea6e483ULL
-#define	SHA512_CONST_22		0x5cb0a9dcbd41fbd4ULL
-#define	SHA512_CONST_23		0x76f988da831153b5ULL
-#define	SHA512_CONST_24		0x983e5152ee66dfabULL
-#define	SHA512_CONST_25		0xa831c66d2db43210ULL
-#define	SHA512_CONST_26		0xb00327c898fb213fULL
-#define	SHA512_CONST_27		0xbf597fc7beef0ee4ULL
-#define	SHA512_CONST_28		0xc6e00bf33da88fc2ULL
-#define	SHA512_CONST_29		0xd5a79147930aa725ULL
-#define	SHA512_CONST_30		0x06ca6351e003826fULL
-#define	SHA512_CONST_31		0x142929670a0e6e70ULL
-#define	SHA512_CONST_32		0x27b70a8546d22ffcULL
-#define	SHA512_CONST_33		0x2e1b21385c26c926ULL
-#define	SHA512_CONST_34		0x4d2c6dfc5ac42aedULL
-#define	SHA512_CONST_35		0x53380d139d95b3dfULL
-#define	SHA512_CONST_36		0x650a73548baf63deULL
-#define	SHA512_CONST_37		0x766a0abb3c77b2a8ULL
-#define	SHA512_CONST_38		0x81c2c92e47edaee6ULL
-#define	SHA512_CONST_39		0x92722c851482353bULL
-#define	SHA512_CONST_40		0xa2bfe8a14cf10364ULL
-#define	SHA512_CONST_41		0xa81a664bbc423001ULL
-#define	SHA512_CONST_42		0xc24b8b70d0f89791ULL
-#define	SHA512_CONST_43		0xc76c51a30654be30ULL
-#define	SHA512_CONST_44		0xd192e819d6ef5218ULL
-#define	SHA512_CONST_45		0xd69906245565a910ULL
-#define	SHA512_CONST_46		0xf40e35855771202aULL
-#define	SHA512_CONST_47		0x106aa07032bbd1b8ULL
-#define	SHA512_CONST_48		0x19a4c116b8d2d0c8ULL
-#define	SHA512_CONST_49		0x1e376c085141ab53ULL
-#define	SHA512_CONST_50		0x2748774cdf8eeb99ULL
-#define	SHA512_CONST_51		0x34b0bcb5e19b48a8ULL
-#define	SHA512_CONST_52		0x391c0cb3c5c95a63ULL
-#define	SHA512_CONST_53		0x4ed8aa4ae3418acbULL
-#define	SHA512_CONST_54		0x5b9cca4f7763e373ULL
-#define	SHA512_CONST_55		0x682e6ff3d6b2b8a3ULL
-#define	SHA512_CONST_56		0x748f82ee5defb2fcULL
-#define	SHA512_CONST_57		0x78a5636f43172f60ULL
-#define	SHA512_CONST_58		0x84c87814a1f0ab72ULL
-#define	SHA512_CONST_59		0x8cc702081a6439ecULL
-#define	SHA512_CONST_60		0x90befffa23631e28ULL
-#define	SHA512_CONST_61		0xa4506cebde82bde9ULL
-#define	SHA512_CONST_62		0xbef9a3f7b2c67915ULL
-#define	SHA512_CONST_63		0xc67178f2e372532bULL
-#define	SHA512_CONST_64		0xca273eceea26619cULL
-#define	SHA512_CONST_65		0xd186b8c721c0c207ULL
-#define	SHA512_CONST_66		0xeada7dd6cde0eb1eULL
-#define	SHA512_CONST_67		0xf57d4f7fee6ed178ULL
-#define	SHA512_CONST_68		0x06f067aa72176fbaULL
-#define	SHA512_CONST_69		0x0a637dc5a2c898a6ULL
-#define	SHA512_CONST_70		0x113f9804bef90daeULL
-#define	SHA512_CONST_71		0x1b710b35131c471bULL
-#define	SHA512_CONST_72		0x28db77f523047d84ULL
-#define	SHA512_CONST_73		0x32caab7b40c72493ULL
-#define	SHA512_CONST_74		0x3c9ebe0a15c9bebcULL
-#define	SHA512_CONST_75		0x431d67c49c100d4cULL
-#define	SHA512_CONST_76		0x4cc5d4becb3e42b6ULL
-#define	SHA512_CONST_77		0x597f299cfc657e2aULL
-#define	SHA512_CONST_78		0x5fcb6fab3ad6faecULL
-#define	SHA512_CONST_79		0x6c44198c4a475817ULL
-
-
-#ifdef	__cplusplus
-}
-#endif
-
-#endif /* _SYS_SHA2_CONSTS_H */
diff --git a/module/os/freebsd/spl/sha224.h b/module/os/freebsd/spl/sha224.h
deleted file mode 100644
index 0abd43068..000000000
--- a/module/os/freebsd/spl/sha224.h
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * Copyright 2005 Colin Percival
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * $FreeBSD$
- */
-
-#ifndef	_SHA224_H_
-#define	_SHA224_H_
-
-#ifndef _KERNEL
-#include <sys/types.h>
-#endif
-
-#define	SHA224_BLOCK_LENGTH		64
-#define	SHA224_DIGEST_LENGTH		28
-#define	SHA224_DIGEST_STRING_LENGTH	(SHA224_DIGEST_LENGTH * 2 + 1)
-
-typedef struct SHA224Context {
-	uint32_t state[8];
-	uint64_t count;
-	uint8_t buf[SHA224_BLOCK_LENGTH];
-} SHA224_CTX;
-
-__BEGIN_DECLS
-
-/* Ensure libmd symbols do not clash with libcrypto */
-
-#ifndef SHA224_Init
-#define	SHA224_Init		_libmd_SHA224_Init
-#endif
-#ifndef SHA224_Update
-#define	SHA224_Update		_libmd_SHA224_Update
-#endif
-#ifndef SHA224_Final
-#define	SHA224_Final		_libmd_SHA224_Final
-#endif
-#ifndef SHA224_End
-#define	SHA224_End		_libmd_SHA224_End
-#endif
-#ifndef SHA224_Fd
-#define	SHA224_Fd		_libmd_SHA224_Fd
-#endif
-#ifndef SHA224_FdChunk
-#define	SHA224_FdChunk		_libmd_SHA224_FdChunk
-#endif
-#ifndef SHA224_File
-#define	SHA224_File		_libmd_SHA224_File
-#endif
-#ifndef SHA224_FileChunk
-#define	SHA224_FileChunk	_libmd_SHA224_FileChunk
-#endif
-#ifndef SHA224_Data
-#define	SHA224_Data		_libmd_SHA224_Data
-#endif
-
-#ifndef SHA224_version
-#define	SHA224_version		_libmd_SHA224_version
-#endif
-
-void	SHA224_Init(SHA224_CTX *);
-void	SHA224_Update(SHA224_CTX *, const void *, size_t);
-void	SHA224_Final(unsigned char [__min_size(SHA224_DIGEST_LENGTH)],
-    SHA224_CTX *);
-#ifndef _KERNEL
-char   *SHA224_End(SHA224_CTX *, char *);
-char   *SHA224_Data(const void *, unsigned int, char *);
-char   *SHA224_Fd(int, char *);
-char   *SHA224_FdChunk(int, char *, off_t, off_t);
-char   *SHA224_File(const char *, char *);
-char   *SHA224_FileChunk(const char *, char *, off_t, off_t);
-#endif
-__END_DECLS
-
-#endif /* !_SHA224_H_ */
diff --git a/module/os/freebsd/spl/sha256.h b/module/os/freebsd/spl/sha256.h
deleted file mode 100644
index 193c0c025..000000000
--- a/module/os/freebsd/spl/sha256.h
+++ /dev/null
@@ -1,99 +0,0 @@
-/*
- * Copyright 2005 Colin Percival
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * $FreeBSD$
- */
-
-#ifndef _SHA256_H_
-#define	_SHA256_H_
-
-#ifndef _KERNEL
-#include <sys/types.h>
-#endif
-
-#define	SHA256_BLOCK_LENGTH		64
-#define	SHA256_DIGEST_LENGTH		32
-#define	SHA256_DIGEST_STRING_LENGTH	(SHA256_DIGEST_LENGTH * 2 + 1)
-
-typedef struct SHA256Context {
-	uint32_t state[8];
-	uint64_t count;
-	uint8_t buf[SHA256_BLOCK_LENGTH];
-} SHA256_CTX;
-
-__BEGIN_DECLS
-
-/* Ensure libmd symbols do not clash with libcrypto */
-
-#ifndef SHA256_Init
-#define	SHA256_Init		_libmd_SHA256_Init
-#endif
-#ifndef SHA256_Update
-#define	SHA256_Update		_libmd_SHA256_Update
-#endif
-#ifndef SHA256_Final
-#define	SHA256_Final		_libmd_SHA256_Final
-#endif
-#ifndef SHA256_End
-#define	SHA256_End		_libmd_SHA256_End
-#endif
-#ifndef SHA256_Fd
-#define	SHA256_Fd		_libmd_SHA256_Fd
-#endif
-#ifndef SHA256_FdChunk
-#define	SHA256_FdChunk		_libmd_SHA256_FdChunk
-#endif
-#ifndef SHA256_File
-#define	SHA256_File		_libmd_SHA256_File
-#endif
-#ifndef SHA256_FileChunk
-#define	SHA256_FileChunk	_libmd_SHA256_FileChunk
-#endif
-#ifndef SHA256_Data
-#define	SHA256_Data		_libmd_SHA256_Data
-#endif
-
-#ifndef SHA256_Transform
-#define	SHA256_Transform	_libmd_SHA256_Transform
-#endif
-#ifndef SHA256_version
-#define	SHA256_version		_libmd_SHA256_version
-#endif
-
-void	SHA256_Init(SHA256_CTX *);
-void	SHA256_Update(SHA256_CTX *, const void *, size_t);
-void	SHA256_Final(unsigned char [__min_size(SHA256_DIGEST_LENGTH)],
-    SHA256_CTX *);
-#ifndef _KERNEL
-char   *SHA256_End(SHA256_CTX *, char *);
-char   *SHA256_Data(const void *, unsigned int, char *);
-char   *SHA256_Fd(int, char *);
-char   *SHA256_FdChunk(int, char *, off_t, off_t);
-char   *SHA256_File(const char *, char *);
-char   *SHA256_FileChunk(const char *, char *, off_t, off_t);
-#endif
-__END_DECLS
-
-#endif /* !_SHA256_H_ */
diff --git a/module/os/freebsd/spl/sha256c.c b/module/os/freebsd/spl/sha256c.c
deleted file mode 100644
index 52cf0df6c..000000000
--- a/module/os/freebsd/spl/sha256c.c
+++ /dev/null
@@ -1,378 +0,0 @@
-/*
- * Copyright 2005 Colin Percival
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#include <sys/cdefs.h>
-__FBSDID("$FreeBSD$");
-
-#include <sys/types.h>
-
-#ifdef _KERNEL
-#include <sys/systm.h>
-#else
-#include <string.h>
-#endif
-
-
-#include <sys/byteorder.h>
-#include <sys/endian.h>
-#include "sha224.h"
-#include "sha256.h"
-
-#if BYTE_ORDER == BIG_ENDIAN
-
-/* Copy a vector of big-endian uint32_t into a vector of bytes */
-#define	be32enc_vect(dst, src, len)	\
-	memcpy((void *)dst, (const void *)src, (size_t)len)
-
-/* Copy a vector of bytes into a vector of big-endian uint32_t */
-#define	be32dec_vect(dst, src, len)	\
-	memcpy((void *)dst, (const void *)src, (size_t)len)
-
-#else /* BYTE_ORDER != BIG_ENDIAN */
-
-/*
- * Encode a length len/4 vector of (uint32_t) into a length len vector of
- * (unsigned char) in big-endian form.  Assumes len is a multiple of 4.
- */
-static void
-be32enc_vect(unsigned char *dst, const uint32_t *src, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len / 4; i++)
-		be32enc(dst + i * 4, src[i]);
-}
-
-/*
- * Decode a big-endian length len vector of (unsigned char) into a length
- * len/4 vector of (uint32_t).  Assumes len is a multiple of 4.
- */
-static void
-be32dec_vect(uint32_t *dst, const unsigned char *src, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len / 4; i++)
-		dst[i] = be32dec(src + i * 4);
-}
-
-#endif /* BYTE_ORDER != BIG_ENDIAN */
-
-/* SHA256 round constants. */
-static const uint32_t K[64] = {
-	0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5,
-	0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5,
-	0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3,
-	0x72be5d74, 0x80deb1fe, 0x9bdc06a7, 0xc19bf174,
-	0xe49b69c1, 0xefbe4786, 0x0fc19dc6, 0x240ca1cc,
-	0x2de92c6f, 0x4a7484aa, 0x5cb0a9dc, 0x76f988da,
-	0x983e5152, 0xa831c66d, 0xb00327c8, 0xbf597fc7,
-	0xc6e00bf3, 0xd5a79147, 0x06ca6351, 0x14292967,
-	0x27b70a85, 0x2e1b2138, 0x4d2c6dfc, 0x53380d13,
-	0x650a7354, 0x766a0abb, 0x81c2c92e, 0x92722c85,
-	0xa2bfe8a1, 0xa81a664b, 0xc24b8b70, 0xc76c51a3,
-	0xd192e819, 0xd6990624, 0xf40e3585, 0x106aa070,
-	0x19a4c116, 0x1e376c08, 0x2748774c, 0x34b0bcb5,
-	0x391c0cb3, 0x4ed8aa4a, 0x5b9cca4f, 0x682e6ff3,
-	0x748f82ee, 0x78a5636f, 0x84c87814, 0x8cc70208,
-	0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2
-};
-
-/* Elementary functions used by SHA256 */
-#define	Ch(x, y, z)	((x & (y ^ z)) ^ z)
-#define	Maj(x, y, z)	((x & (y | z)) | (y & z))
-#define	SHR(x, n)	(x >> n)
-#define	ROTR(x, n)	((x >> n) | (x << (32 - n)))
-#define	S0(x)		(ROTR(x, 2) ^ ROTR(x, 13) ^ ROTR(x, 22))
-#define	S1(x)		(ROTR(x, 6) ^ ROTR(x, 11) ^ ROTR(x, 25))
-#define	s0(x)		(ROTR(x, 7) ^ ROTR(x, 18) ^ SHR(x, 3))
-#define	s1(x)		(ROTR(x, 17) ^ ROTR(x, 19) ^ SHR(x, 10))
-
-/* SHA256 round function */
-#define	RND(a, b, c, d, e, f, g, h, k)			\
-	h += S1(e) + Ch(e, f, g) + k;			\
-	d += h;						\
-	h += S0(a) + Maj(a, b, c);
-
-/* Adjusted round function for rotating state */
-#define	RNDr(S, W, i, ii)			\
-	RND(S[(64 - i) % 8], S[(65 - i) % 8],	\
-	    S[(66 - i) % 8], S[(67 - i) % 8],	\
-	    S[(68 - i) % 8], S[(69 - i) % 8],	\
-	    S[(70 - i) % 8], S[(71 - i) % 8],	\
-	    W[i + ii] + K[i + ii])
-
-/* Message schedule computation */
-#define	MSCH(W, ii, i)				\
-	W[i + ii + 16] = s1(W[i + ii + 14]) + W[i + ii + 9] +	\
-		s0(W[i + ii + 1]) + W[i + ii]
-
-/*
- * SHA256 block compression function.  The 256-bit state is transformed via
- * the 512-bit input block to produce a new state.
- */
-static void
-SHA256_Transform(uint32_t *state, const unsigned char block[64])
-{
-	uint32_t W[64];
-	uint32_t S[8];
-	int i;
-
-	/* 1. Prepare the first part of the message schedule W. */
-	be32dec_vect(W, block, 64);
-
-	/* 2. Initialize working variables. */
-	memcpy(S, state, 32);
-
-	/* 3. Mix. */
-	for (i = 0; i < 64; i += 16) {
-		RNDr(S, W, 0, i);
-		RNDr(S, W, 1, i);
-		RNDr(S, W, 2, i);
-		RNDr(S, W, 3, i);
-		RNDr(S, W, 4, i);
-		RNDr(S, W, 5, i);
-		RNDr(S, W, 6, i);
-		RNDr(S, W, 7, i);
-		RNDr(S, W, 8, i);
-		RNDr(S, W, 9, i);
-		RNDr(S, W, 10, i);
-		RNDr(S, W, 11, i);
-		RNDr(S, W, 12, i);
-		RNDr(S, W, 13, i);
-		RNDr(S, W, 14, i);
-		RNDr(S, W, 15, i);
-
-		if (i == 48)
-			break;
-		MSCH(W, 0, i);
-		MSCH(W, 1, i);
-		MSCH(W, 2, i);
-		MSCH(W, 3, i);
-		MSCH(W, 4, i);
-		MSCH(W, 5, i);
-		MSCH(W, 6, i);
-		MSCH(W, 7, i);
-		MSCH(W, 8, i);
-		MSCH(W, 9, i);
-		MSCH(W, 10, i);
-		MSCH(W, 11, i);
-		MSCH(W, 12, i);
-		MSCH(W, 13, i);
-		MSCH(W, 14, i);
-		MSCH(W, 15, i);
-	}
-
-	/* 4. Mix local working variables into global state */
-	for (i = 0; i < 8; i++)
-		state[i] += S[i];
-}
-
-static unsigned char PAD[64] = {
-	0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-};
-
-/* Add padding and terminating bit-count. */
-static void
-SHA256_Pad(SHA256_CTX * ctx)
-{
-	size_t r;
-
-	/* Figure out how many bytes we have buffered. */
-	r = (ctx->count >> 3) & 0x3f;
-
-	/* Pad to 56 mod 64, transforming if we finish a block en route. */
-	if (r < 56) {
-		/* Pad to 56 mod 64. */
-		memcpy(&ctx->buf[r], PAD, 56 - r);
-	} else {
-		/* Finish the current block and mix. */
-		memcpy(&ctx->buf[r], PAD, 64 - r);
-		SHA256_Transform(ctx->state, ctx->buf);
-
-		/* The start of the final block is all zeroes. */
-		memset(&ctx->buf[0], 0, 56);
-	}
-
-	/* Add the terminating bit-count. */
-	be64enc(&ctx->buf[56], ctx->count);
-
-	/* Mix in the final block. */
-	SHA256_Transform(ctx->state, ctx->buf);
-}
-
-/* SHA-256 initialization.  Begins a SHA-256 operation. */
-void
-SHA256_Init(SHA256_CTX * ctx)
-{
-
-	/* Zero bits processed so far */
-	ctx->count = 0;
-
-	/* Magic initialization constants */
-	ctx->state[0] = 0x6A09E667;
-	ctx->state[1] = 0xBB67AE85;
-	ctx->state[2] = 0x3C6EF372;
-	ctx->state[3] = 0xA54FF53A;
-	ctx->state[4] = 0x510E527F;
-	ctx->state[5] = 0x9B05688C;
-	ctx->state[6] = 0x1F83D9AB;
-	ctx->state[7] = 0x5BE0CD19;
-}
-
-/* Add bytes into the hash */
-void
-SHA256_Update(SHA256_CTX * ctx, const void *in, size_t len)
-{
-	uint64_t bitlen;
-	uint32_t r;
-	const unsigned char *src = in;
-
-	/* Number of bytes left in the buffer from previous updates */
-	r = (ctx->count >> 3) & 0x3f;
-
-	/* Convert the length into a number of bits */
-	bitlen = len << 3;
-
-	/* Update number of bits */
-	ctx->count += bitlen;
-
-	/* Handle the case where we don't need to perform any transforms */
-	if (len < 64 - r) {
-		memcpy(&ctx->buf[r], src, len);
-		return;
-	}
-
-	/* Finish the current block */
-	memcpy(&ctx->buf[r], src, 64 - r);
-	SHA256_Transform(ctx->state, ctx->buf);
-	src += 64 - r;
-	len -= 64 - r;
-
-	/* Perform complete blocks */
-	while (len >= 64) {
-		SHA256_Transform(ctx->state, src);
-		src += 64;
-		len -= 64;
-	}
-
-	/* Copy left over data into buffer */
-	memcpy(ctx->buf, src, len);
-}
-
-/*
- * SHA-256 finalization.  Pads the input data, exports the hash value,
- * and clears the context state.
- */
-void
-SHA256_Final(unsigned char digest[static SHA256_DIGEST_LENGTH], SHA256_CTX *ctx)
-{
-
-	/* Add padding */
-	SHA256_Pad(ctx);
-
-	/* Write the hash */
-	be32enc_vect(digest, ctx->state, SHA256_DIGEST_LENGTH);
-
-	/* Clear the context state */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-/* SHA-224: ******************************************************* */
-/*
- * the SHA224 and SHA256 transforms are identical
- */
-
-/* SHA-224 initialization.  Begins a SHA-224 operation. */
-void
-SHA224_Init(SHA224_CTX * ctx)
-{
-
-	/* Zero bits processed so far */
-	ctx->count = 0;
-
-	/* Magic initialization constants */
-	ctx->state[0] = 0xC1059ED8;
-	ctx->state[1] = 0x367CD507;
-	ctx->state[2] = 0x3070DD17;
-	ctx->state[3] = 0xF70E5939;
-	ctx->state[4] = 0xFFC00B31;
-	ctx->state[5] = 0x68581511;
-	ctx->state[6] = 0x64f98FA7;
-	ctx->state[7] = 0xBEFA4FA4;
-}
-
-/* Add bytes into the SHA-224 hash */
-void
-SHA224_Update(SHA224_CTX * ctx, const void *in, size_t len)
-{
-
-	SHA256_Update((SHA256_CTX *)ctx, in, len);
-}
-
-/*
- * SHA-224 finalization.  Pads the input data, exports the hash value,
- * and clears the context state.
- */
-void
-SHA224_Final(unsigned char digest[static SHA224_DIGEST_LENGTH], SHA224_CTX *ctx)
-{
-
-	/* Add padding */
-	SHA256_Pad((SHA256_CTX *)ctx);
-
-	/* Write the hash */
-	be32enc_vect(digest, ctx->state, SHA224_DIGEST_LENGTH);
-
-	/* Clear the context state */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-#ifdef WEAK_REFS
-/*
- * When building libmd, provide weak references. Note: this is not
- * activated in the context of compiling these sources for internal
- * use in libcrypt.
- */
-#undef SHA256_Init
-__weak_reference(_libmd_SHA256_Init, SHA256_Init);
-#undef SHA256_Update
-__weak_reference(_libmd_SHA256_Update, SHA256_Update);
-#undef SHA256_Final
-__weak_reference(_libmd_SHA256_Final, SHA256_Final);
-#undef SHA256_Transform
-__weak_reference(_libmd_SHA256_Transform, SHA256_Transform);
-
-#undef SHA224_Init
-__weak_reference(_libmd_SHA224_Init, SHA224_Init);
-#undef SHA224_Update
-__weak_reference(_libmd_SHA224_Update, SHA224_Update);
-#undef SHA224_Final
-__weak_reference(_libmd_SHA224_Final, SHA224_Final);
-#endif
diff --git a/module/os/freebsd/spl/sha384.h b/module/os/freebsd/spl/sha384.h
deleted file mode 100644
index 67250cee0..000000000
--- a/module/os/freebsd/spl/sha384.h
+++ /dev/null
@@ -1,96 +0,0 @@
-/*
- * Copyright 2005 Colin Percival
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * $FreeBSD$
- */
-
-#ifndef _SHA384_H_
-#define	_SHA384_H_
-
-#ifndef _KERNEL
-#include <sys/types.h>
-#endif
-
-#define	SHA384_BLOCK_LENGTH		128
-#define	SHA384_DIGEST_LENGTH		48
-#define	SHA384_DIGEST_STRING_LENGTH	(SHA384_DIGEST_LENGTH * 2 + 1)
-
-typedef struct SHA384Context {
-	uint64_t state[8];
-	uint64_t count[2];
-	uint8_t buf[SHA384_BLOCK_LENGTH];
-} SHA384_CTX;
-
-__BEGIN_DECLS
-
-/* Ensure libmd symbols do not clash with libcrypto */
-#ifndef SHA384_Init
-#define	SHA384_Init		_libmd_SHA384_Init
-#endif
-#ifndef SHA384_Update
-#define	SHA384_Update		_libmd_SHA384_Update
-#endif
-#ifndef SHA384_Final
-#define	SHA384_Final		_libmd_SHA384_Final
-#endif
-#ifndef SHA384_End
-#define	SHA384_End		_libmd_SHA384_End
-#endif
-#ifndef SHA384_Fd
-#define	SHA384_Fd		_libmd_SHA384_Fd
-#endif
-#ifndef SHA384_FdChunk
-#define	SHA384_FdChunk		_libmd_SHA384_FdChunk
-#endif
-#ifndef SHA384_File
-#define	SHA384_File		_libmd_SHA384_File
-#endif
-#ifndef SHA384_FileChunk
-#define	SHA384_FileChunk	_libmd_SHA384_FileChunk
-#endif
-#ifndef SHA384_Data
-#define	SHA384_Data		_libmd_SHA384_Data
-#endif
-
-#ifndef SHA384_version
-#define	SHA384_version		_libmd_SHA384_version
-#endif
-
-void	SHA384_Init(SHA384_CTX *);
-void	SHA384_Update(SHA384_CTX *, const void *, size_t);
-void	SHA384_Final(unsigned char [__min_size(SHA384_DIGEST_LENGTH)],
-    SHA384_CTX *);
-#ifndef _KERNEL
-char   *SHA384_End(SHA384_CTX *, char *);
-char   *SHA384_Data(const void *, unsigned int, char *);
-char   *SHA384_Fd(int, char *);
-char   *SHA384_FdChunk(int, char *, off_t, off_t);
-char   *SHA384_File(const char *, char *);
-char   *SHA384_FileChunk(const char *, char *, off_t, off_t);
-#endif
-
-__END_DECLS
-
-#endif /* !_SHA384_H_ */
diff --git a/module/os/freebsd/spl/sha512.h b/module/os/freebsd/spl/sha512.h
deleted file mode 100644
index b6fb733ca..000000000
--- a/module/os/freebsd/spl/sha512.h
+++ /dev/null
@@ -1,101 +0,0 @@
-/*
- * Copyright 2005 Colin Percival
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * $FreeBSD$
- */
-
-#ifndef _SHA512_H_
-#define	_SHA512_H_
-
-#ifndef _KERNEL
-#include <sys/types.h>
-#endif
-
-#define	SHA512_BLOCK_LENGTH		128
-#define	SHA512_DIGEST_LENGTH		64
-#define	SHA512_DIGEST_STRING_LENGTH	(SHA512_DIGEST_LENGTH * 2 + 1)
-
-typedef struct SHA512Context {
-	uint64_t state[8];
-	uint64_t count[2];
-	uint8_t buf[SHA512_BLOCK_LENGTH];
-} SHA512_CTX;
-
-__BEGIN_DECLS
-
-/* Ensure libmd symbols do not clash with libcrypto */
-#if 0
-#ifndef SHA512_Init
-#define	SHA512_Init		_libmd_SHA512_Init
-#endif
-#ifndef SHA512_Update
-#define	SHA512_Update		_libmd_SHA512_Update
-#endif
-#ifndef SHA512_Final
-#define	SHA512_Final		_libmd_SHA512_Final
-#endif
-#endif
-#ifndef SHA512_End
-#define	SHA512_End		_libmd_SHA512_End
-#endif
-#ifndef SHA512_Fd
-#define	SHA512_Fd		_libmd_SHA512_Fd
-#endif
-#ifndef SHA512_FdChunk
-#define	SHA512_FdChunk		_libmd_SHA512_FdChunk
-#endif
-#ifndef SHA512_File
-#define	SHA512_File		_libmd_SHA512_File
-#endif
-#ifndef SHA512_FileChunk
-#define	SHA512_FileChunk	_libmd_SHA512_FileChunk
-#endif
-#ifndef SHA512_Data
-#define	SHA512_Data		_libmd_SHA512_Data
-#endif
-
-#ifndef SHA512_Transform
-#define	SHA512_Transform	_libmd_SHA512_Transform
-#endif
-#ifndef SHA512_version
-#define	SHA512_version		_libmd_SHA512_version
-#endif
-
-void	SHA512_Init(SHA512_CTX *);
-void	SHA512_Update(SHA512_CTX *, const void *, size_t);
-void	SHA512_Final(unsigned char [__min_size(SHA512_DIGEST_LENGTH)],
-    SHA512_CTX *);
-#ifndef _KERNEL
-char   *SHA512_End(SHA512_CTX *, char *);
-char   *SHA512_Data(const void *, unsigned int, char *);
-char   *SHA512_Fd(int, char *);
-char   *SHA512_FdChunk(int, char *, off_t, off_t);
-char   *SHA512_File(const char *, char *);
-char   *SHA512_FileChunk(const char *, char *, off_t, off_t);
-#endif
-
-__END_DECLS
-
-#endif /* !_SHA512_H_ */
diff --git a/module/os/freebsd/spl/sha512c.c b/module/os/freebsd/spl/sha512c.c
deleted file mode 100644
index 254cc2156..000000000
--- a/module/os/freebsd/spl/sha512c.c
+++ /dev/null
@@ -1,508 +0,0 @@
-/*
- * Copyright 2005 Colin Percival
- * Copyright (c) 2015 Allan Jude <[email protected]>
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- */
-
-#include <sys/cdefs.h>
-__FBSDID("$FreeBSD$");
-
-#include <sys/endian.h>
-#include <sys/types.h>
-
-#ifdef _KERNEL
-#include <sys/systm.h>
-#else
-#include <string.h>
-#endif
-
-#include "sha512.h"
-#include "sha512t.h"
-#include "sha384.h"
-
-#if BYTE_ORDER == BIG_ENDIAN
-
-/* Copy a vector of big-endian uint64_t into a vector of bytes */
-#define	be64enc_vect(dst, src, len)	\
-	memcpy((void *)dst, (const void *)src, (size_t)len)
-
-/* Copy a vector of bytes into a vector of big-endian uint64_t */
-#define	be64dec_vect(dst, src, len)	\
-	memcpy((void *)dst, (const void *)src, (size_t)len)
-
-#else /* BYTE_ORDER != BIG_ENDIAN */
-
-/*
- * Encode a length len/4 vector of (uint64_t) into a length len vector of
- * (unsigned char) in big-endian form.  Assumes len is a multiple of 8.
- */
-static void
-be64enc_vect(unsigned char *dst, const uint64_t *src, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len / 8; i++)
-		be64enc(dst + i * 8, src[i]);
-}
-
-/*
- * Decode a big-endian length len vector of (unsigned char) into a length
- * len/4 vector of (uint64_t).  Assumes len is a multiple of 8.
- */
-static void
-be64dec_vect(uint64_t *dst, const unsigned char *src, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len / 8; i++)
-		dst[i] = be64dec(src + i * 8);
-}
-
-#endif /* BYTE_ORDER != BIG_ENDIAN */
-
-/* SHA512 round constants. */
-static const uint64_t K[80] = {
-	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
-};
-
-/* Elementary functions used by SHA512 */
-#define	Ch(x, y, z)	((x & (y ^ z)) ^ z)
-#define	Maj(x, y, z)	((x & (y | z)) | (y & z))
-#define	SHR(x, n)	(x >> n)
-#define	ROTR(x, n)	((x >> n) | (x << (64 - n)))
-#define	S0(x)		(ROTR(x, 28) ^ ROTR(x, 34) ^ ROTR(x, 39))
-#define	S1(x)		(ROTR(x, 14) ^ ROTR(x, 18) ^ ROTR(x, 41))
-#define	s0(x)		(ROTR(x, 1) ^ ROTR(x, 8) ^ SHR(x, 7))
-#define	s1(x)		(ROTR(x, 19) ^ ROTR(x, 61) ^ SHR(x, 6))
-
-/* SHA512 round function */
-#define	RND(a, b, c, d, e, f, g, h, k)			\
-	h += S1(e) + Ch(e, f, g) + k;			\
-	d += h;						\
-	h += S0(a) + Maj(a, b, c);
-
-/* Adjusted round function for rotating state */
-#define	RNDr(S, W, i, ii)			\
-	RND(S[(80 - i) % 8], S[(81 - i) % 8],	\
-	    S[(82 - i) % 8], S[(83 - i) % 8],	\
-	    S[(84 - i) % 8], S[(85 - i) % 8],	\
-	    S[(86 - i) % 8], S[(87 - i) % 8],	\
-	    W[i + ii] + K[i + ii])
-
-/* Message schedule computation */
-#define	MSCH(W, ii, i)				\
-	W[i + ii + 16] = s1(W[i + ii + 14]) + W[i + ii + 9] +	\
-		s0(W[i + ii + 1]) + W[i + ii]
-
-/*
- * SHA512 block compression function.  The 512-bit state is transformed via
- * the 512-bit input block to produce a new state.
- */
-static void
-SHA512_Transform(uint64_t *state,
-    const unsigned char block[SHA512_BLOCK_LENGTH])
-{
-	uint64_t W[80];
-	uint64_t S[8];
-	int i;
-
-	/* 1. Prepare the first part of the message schedule W. */
-	be64dec_vect(W, block, SHA512_BLOCK_LENGTH);
-
-	/* 2. Initialize working variables. */
-	memcpy(S, state, SHA512_DIGEST_LENGTH);
-
-	/* 3. Mix. */
-	for (i = 0; i < 80; i += 16) {
-		RNDr(S, W, 0, i);
-		RNDr(S, W, 1, i);
-		RNDr(S, W, 2, i);
-		RNDr(S, W, 3, i);
-		RNDr(S, W, 4, i);
-		RNDr(S, W, 5, i);
-		RNDr(S, W, 6, i);
-		RNDr(S, W, 7, i);
-		RNDr(S, W, 8, i);
-		RNDr(S, W, 9, i);
-		RNDr(S, W, 10, i);
-		RNDr(S, W, 11, i);
-		RNDr(S, W, 12, i);
-		RNDr(S, W, 13, i);
-		RNDr(S, W, 14, i);
-		RNDr(S, W, 15, i);
-
-		if (i == 64)
-			break;
-		MSCH(W, 0, i);
-		MSCH(W, 1, i);
-		MSCH(W, 2, i);
-		MSCH(W, 3, i);
-		MSCH(W, 4, i);
-		MSCH(W, 5, i);
-		MSCH(W, 6, i);
-		MSCH(W, 7, i);
-		MSCH(W, 8, i);
-		MSCH(W, 9, i);
-		MSCH(W, 10, i);
-		MSCH(W, 11, i);
-		MSCH(W, 12, i);
-		MSCH(W, 13, i);
-		MSCH(W, 14, i);
-		MSCH(W, 15, i);
-	}
-
-	/* 4. Mix local working variables into global state */
-	for (i = 0; i < 8; i++)
-		state[i] += S[i];
-}
-
-static unsigned char PAD[SHA512_BLOCK_LENGTH] = {
-	0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
-	0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-};
-
-/* Add padding and terminating bit-count. */
-static void
-SHA512_Pad(SHA512_CTX * ctx)
-{
-	size_t r;
-
-	/* Figure out how many bytes we have buffered. */
-	r = (ctx->count[1] >> 3) & 0x7f;
-
-	/* Pad to 112 mod 128, transforming if we finish a block en route. */
-	if (r < 112) {
-		/* Pad to 112 mod 128. */
-		memcpy(&ctx->buf[r], PAD, 112 - r);
-	} else {
-		/* Finish the current block and mix. */
-		memcpy(&ctx->buf[r], PAD, 128 - r);
-		SHA512_Transform(ctx->state, ctx->buf);
-
-		/* The start of the final block is all zeroes. */
-		memset(&ctx->buf[0], 0, 112);
-	}
-
-	/* Add the terminating bit-count. */
-	be64enc_vect(&ctx->buf[112], ctx->count, 16);
-
-	/* Mix in the final block. */
-	SHA512_Transform(ctx->state, ctx->buf);
-}
-
-/* SHA-512 initialization.  Begins a SHA-512 operation. */
-void
-SHA512_Init(SHA512_CTX * ctx)
-{
-
-	/* Zero bits processed so far */
-	ctx->count[0] = ctx->count[1] = 0;
-
-	/* Magic initialization constants */
-	ctx->state[0] = 0x6a09e667f3bcc908ULL;
-	ctx->state[1] = 0xbb67ae8584caa73bULL;
-	ctx->state[2] = 0x3c6ef372fe94f82bULL;
-	ctx->state[3] = 0xa54ff53a5f1d36f1ULL;
-	ctx->state[4] = 0x510e527fade682d1ULL;
-	ctx->state[5] = 0x9b05688c2b3e6c1fULL;
-	ctx->state[6] = 0x1f83d9abfb41bd6bULL;
-	ctx->state[7] = 0x5be0cd19137e2179ULL;
-}
-
-/* Add bytes into the hash */
-void
-SHA512_Update(SHA512_CTX * ctx, const void *in, size_t len)
-{
-	uint64_t bitlen[2];
-	uint64_t r;
-	const unsigned char *src = in;
-
-	/* Number of bytes left in the buffer from previous updates */
-	r = (ctx->count[1] >> 3) & 0x7f;
-
-	/* Convert the length into a number of bits */
-	bitlen[1] = ((uint64_t)len) << 3;
-	bitlen[0] = ((uint64_t)len) >> 61;
-
-	/* Update number of bits */
-	if ((ctx->count[1] += bitlen[1]) < bitlen[1])
-		ctx->count[0]++;
-	ctx->count[0] += bitlen[0];
-
-	/* Handle the case where we don't need to perform any transforms */
-	if (len < SHA512_BLOCK_LENGTH - r) {
-		memcpy(&ctx->buf[r], src, len);
-		return;
-	}
-
-	/* Finish the current block */
-	memcpy(&ctx->buf[r], src, SHA512_BLOCK_LENGTH - r);
-	SHA512_Transform(ctx->state, ctx->buf);
-	src += SHA512_BLOCK_LENGTH - r;
-	len -= SHA512_BLOCK_LENGTH - r;
-
-	/* Perform complete blocks */
-	while (len >= SHA512_BLOCK_LENGTH) {
-		SHA512_Transform(ctx->state, src);
-		src += SHA512_BLOCK_LENGTH;
-		len -= SHA512_BLOCK_LENGTH;
-	}
-
-	/* Copy left over data into buffer */
-	memcpy(ctx->buf, src, len);
-}
-
-/*
- * SHA-512 finalization.  Pads the input data, exports the hash value,
- * and clears the context state.
- */
-void
-SHA512_Final(unsigned char digest[static SHA512_DIGEST_LENGTH], SHA512_CTX *ctx)
-{
-
-	/* Add padding */
-	SHA512_Pad(ctx);
-
-	/* Write the hash */
-	be64enc_vect(digest, ctx->state, SHA512_DIGEST_LENGTH);
-
-	/* Clear the context state */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-/* SHA-512t: ******************************************************** */
-/*
- * the SHA512t transforms are identical to SHA512 so reuse the existing function
- */
-void
-SHA512_224_Init(SHA512_CTX * ctx)
-{
-
-	/* Zero bits processed so far */
-	ctx->count[0] = ctx->count[1] = 0;
-
-	/* Magic initialization constants */
-	ctx->state[0] = 0x8c3d37c819544da2ULL;
-	ctx->state[1] = 0x73e1996689dcd4d6ULL;
-	ctx->state[2] = 0x1dfab7ae32ff9c82ULL;
-	ctx->state[3] = 0x679dd514582f9fcfULL;
-	ctx->state[4] = 0x0f6d2b697bd44da8ULL;
-	ctx->state[5] = 0x77e36f7304c48942ULL;
-	ctx->state[6] = 0x3f9d85a86a1d36c8ULL;
-	ctx->state[7] = 0x1112e6ad91d692a1ULL;
-}
-
-void
-SHA512_224_Update(SHA512_CTX * ctx, const void *in, size_t len)
-{
-
-	SHA512_Update(ctx, in, len);
-}
-
-void
-SHA512_224_Final(unsigned char digest[static SHA512_224_DIGEST_LENGTH],
-    SHA512_CTX *ctx)
-{
-
-	/* Add padding */
-	SHA512_Pad(ctx);
-
-	/* Write the hash */
-	be64enc_vect(digest, ctx->state, SHA512_224_DIGEST_LENGTH);
-
-	/* Clear the context state */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-void
-SHA512_256_Init(SHA512_CTX * ctx)
-{
-
-	/* Zero bits processed so far */
-	ctx->count[0] = ctx->count[1] = 0;
-
-	/* Magic initialization constants */
-	ctx->state[0] = 0x22312194fc2bf72cULL;
-	ctx->state[1] = 0x9f555fa3c84c64c2ULL;
-	ctx->state[2] = 0x2393b86b6f53b151ULL;
-	ctx->state[3] = 0x963877195940eabdULL;
-	ctx->state[4] = 0x96283ee2a88effe3ULL;
-	ctx->state[5] = 0xbe5e1e2553863992ULL;
-	ctx->state[6] = 0x2b0199fc2c85b8aaULL;
-	ctx->state[7] = 0x0eb72ddc81c52ca2ULL;
-}
-
-void
-SHA512_256_Update(SHA512_CTX * ctx, const void *in, size_t len)
-{
-
-	SHA512_Update(ctx, in, len);
-}
-
-void
-SHA512_256_Final(unsigned char digest[static SHA512_256_DIGEST_LENGTH],
-    SHA512_CTX * ctx)
-{
-
-	/* Add padding */
-	SHA512_Pad(ctx);
-
-	/* Write the hash */
-	be64enc_vect(digest, ctx->state, SHA512_256_DIGEST_LENGTH);
-
-	/* Clear the context state */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-/* ** SHA-384: ******************************************************** */
-/*
- * the SHA384 and SHA512 transforms are identical, so SHA384 is skipped
- */
-
-/* SHA-384 initialization.  Begins a SHA-384 operation. */
-void
-SHA384_Init(SHA384_CTX * ctx)
-{
-
-	/* Zero bits processed so far */
-	ctx->count[0] = ctx->count[1] = 0;
-
-	/* Magic initialization constants */
-	ctx->state[0] = 0xcbbb9d5dc1059ed8ULL;
-	ctx->state[1] = 0x629a292a367cd507ULL;
-	ctx->state[2] = 0x9159015a3070dd17ULL;
-	ctx->state[3] = 0x152fecd8f70e5939ULL;
-	ctx->state[4] = 0x67332667ffc00b31ULL;
-	ctx->state[5] = 0x8eb44a8768581511ULL;
-	ctx->state[6] = 0xdb0c2e0d64f98fa7ULL;
-	ctx->state[7] = 0x47b5481dbefa4fa4ULL;
-}
-
-/* Add bytes into the SHA-384 hash */
-void
-SHA384_Update(SHA384_CTX * ctx, const void *in, size_t len)
-{
-
-	SHA512_Update((SHA512_CTX *)ctx, in, len);
-}
-
-/*
- * SHA-384 finalization.  Pads the input data, exports the hash value,
- * and clears the context state.
- */
-void
-SHA384_Final(unsigned char digest[static SHA384_DIGEST_LENGTH], SHA384_CTX *ctx)
-{
-
-	/* Add padding */
-	SHA512_Pad((SHA512_CTX *)ctx);
-
-	/* Write the hash */
-	be64enc_vect(digest, ctx->state, SHA384_DIGEST_LENGTH);
-
-	/* Clear the context state */
-	memset(ctx, 0, sizeof (*ctx));
-}
-
-#if 0
-/*
- * When building libmd, provide weak references. Note: this is not
- * activated in the context of compiling these sources for internal
- * use in libcrypt.
- */
-#undef SHA512_Init
-__weak_reference(_libmd_SHA512_Init, SHA512_Init);
-#undef SHA512_Update
-__weak_reference(_libmd_SHA512_Update, SHA512_Update);
-#undef SHA512_Final
-__weak_reference(_libmd_SHA512_Final, SHA512_Final);
-#undef SHA512_Transform
-__weak_reference(_libmd_SHA512_Transform, SHA512_Transform);
-
-#undef SHA512_224_Init
-__weak_reference(_libmd_SHA512_224_Init, SHA512_224_Init);
-#undef SHA512_224_Update
-__weak_reference(_libmd_SHA512_224_Update, SHA512_224_Update);
-#undef SHA512_224_Final
-__weak_reference(_libmd_SHA512_224_Final, SHA512_224_Final);
-
-#undef SHA512_256_Init
-__weak_reference(_libmd_SHA512_256_Init, SHA512_256_Init);
-#undef SHA512_256_Update
-__weak_reference(_libmd_SHA512_256_Update, SHA512_256_Update);
-#undef SHA512_256_Final
-__weak_reference(_libmd_SHA512_256_Final, SHA512_256_Final);
-
-#undef SHA384_Init
-__weak_reference(_libmd_SHA384_Init, SHA384_Init);
-#undef SHA384_Update
-__weak_reference(_libmd_SHA384_Update, SHA384_Update);
-#undef SHA384_Final
-__weak_reference(_libmd_SHA384_Final, SHA384_Final);
-#endif
diff --git a/module/os/freebsd/spl/sha512t.h b/module/os/freebsd/spl/sha512t.h
deleted file mode 100644
index 703867fc0..000000000
--- a/module/os/freebsd/spl/sha512t.h
+++ /dev/null
@@ -1,143 +0,0 @@
-/*
- * Copyright (c) 2015 Allan Jude <[email protected]>
- * All rights reserved.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- * 1. Redistributions of source code must retain the above copyright
- *    notice, this list of conditions and the following disclaimer.
- * 2. Redistributions in binary form must reproduce the above copyright
- *    notice, this list of conditions and the following disclaimer in the
- *    documentation and/or other materials provided with the distribution.
- *
- * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
- * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
- * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
- * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
- * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
- * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
- * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
- * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
- * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
- * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
- * SUCH DAMAGE.
- *
- * $FreeBSD$
- */
-
-#ifndef _SHA512T_H_
-#define	_SHA512T_H_
-
-#include "sha512.h"
-
-#ifndef _KERNEL
-#include <sys/types.h>
-#endif
-
-#define	SHA512_224_DIGEST_LENGTH	28
-#define	SHA512_224_DIGEST_STRING_LENGTH	(SHA512_224_DIGEST_LENGTH * 2 + 1)
-#define	SHA512_256_DIGEST_LENGTH	32
-#define	SHA512_256_DIGEST_STRING_LENGTH	(SHA512_256_DIGEST_LENGTH * 2 + 1)
-
-__BEGIN_DECLS
-
-/* Ensure libmd symbols do not clash with libcrypto */
-#ifndef SHA512_224_Init
-#define	SHA512_224_Init		_libmd_SHA512_224_Init
-#endif
-#ifndef SHA512_224_Update
-#define	SHA512_224_Update	_libmd_SHA512_224_Update
-#endif
-#ifndef SHA512_224_Final
-#define	SHA512_224_Final	_libmd_SHA512_224_Final
-#endif
-#ifndef SHA512_224_End
-#define	SHA512_224_End		_libmd_SHA512_224_End
-#endif
-#ifndef SHA512_224_Fd
-#define	SHA512_224_Fd		_libmd_SHA512_224_Fd
-#endif
-#ifndef SHA512_224_FdChunk
-#define	SHA512_224_FdChunk	_libmd_SHA512_224_FdChunk
-#endif
-#ifndef SHA512_224_File
-#define	SHA512_224_File		_libmd_SHA512_224_File
-#endif
-#ifndef SHA512_224_FileChunk
-#define	SHA512_224_FileChunk	_libmd_SHA512_224_FileChunk
-#endif
-#ifndef SHA512_224_Data
-#define	SHA512_224_Data		_libmd_SHA512_224_Data
-#endif
-
-#ifndef SHA512_224_Transform
-#define	SHA512_224_Transform	_libmd_SHA512_224_Transform
-#endif
-#ifndef SHA512_224_version
-#define	SHA512_224_version	_libmd_SHA512_224_version
-#endif
-
-#ifndef SHA512_256_Init
-#define	SHA512_256_Init		_libmd_SHA512_256_Init
-#endif
-#ifndef SHA512_256_Update
-#define	SHA512_256_Update	_libmd_SHA512_256_Update
-#endif
-#ifndef SHA512_256_Final
-#define	SHA512_256_Final	_libmd_SHA512_256_Final
-#endif
-#ifndef SHA512_256_End
-#define	SHA512_256_End		_libmd_SHA512_256_End
-#endif
-#ifndef SHA512_256_Fd
-#define	SHA512_256_Fd		_libmd_SHA512_256_Fd
-#endif
-#ifndef SHA512_256_FdChunk
-#define	SHA512_256_FdChunk	_libmd_SHA512_256_FdChunk
-#endif
-#ifndef SHA512_256_File
-#define	SHA512_256_File		_libmd_SHA512_256_File
-#endif
-#ifndef SHA512_256_FileChunk
-#define	SHA512_256_FileChunk	_libmd_SHA512_256_FileChunk
-#endif
-#ifndef SHA512_256_Data
-#define	SHA512_256_Data		_libmd_SHA512_256_Data
-#endif
-
-#ifndef SHA512_256_Transform
-#define	SHA512_256_Transform	_libmd_SHA512_256_Transform
-#endif
-#ifndef SHA512_256_version
-#define	SHA512_256_version	_libmd_SHA512_256_version
-#endif
-
-void	SHA512_224_Init(SHA512_CTX *);
-void	SHA512_224_Update(SHA512_CTX *, const void *, size_t);
-void	SHA512_224_Final(unsigned char [__min_size(SHA512_224_DIGEST_LENGTH)],
-    SHA512_CTX *);
-#ifndef _KERNEL
-char   *SHA512_224_End(SHA512_CTX *, char *);
-char   *SHA512_224_Data(const void *, unsigned int, char *);
-char   *SHA512_224_Fd(int, char *);
-char   *SHA512_224_FdChunk(int, char *, off_t, off_t);
-char   *SHA512_224_File(const char *, char *);
-char   *SHA512_224_FileChunk(const char *, char *, off_t, off_t);
-#endif
-void	SHA512_256_Init(SHA512_CTX *);
-void	SHA512_256_Update(SHA512_CTX *, const void *, size_t);
-void	SHA512_256_Final(unsigned char [__min_size(SHA512_256_DIGEST_LENGTH)],
-    SHA512_CTX *);
-#ifndef _KERNEL
-char   *SHA512_256_End(SHA512_CTX *, char *);
-char   *SHA512_256_Data(const void *, unsigned int, char *);
-char   *SHA512_256_Fd(int, char *);
-char   *SHA512_256_FdChunk(int, char *, off_t, off_t);
-char   *SHA512_256_File(const char *, char *);
-char   *SHA512_256_FileChunk(const char *, char *, off_t, off_t);
-#endif
-
-__END_DECLS
-
-#endif /* !_SHA512T_H_ */