arch/x86/crypto/sha256_ni_asm.S - third_party/kernel - Git at Google

 /*
  * Intel SHA Extensions optimized implementation of a SHA-256 update function
  *
  * This file is provided under a dual BSD/GPLv2 license.  When using or
  * redistributing this file, you may do so under either license.
  *
  * GPL LICENSE SUMMARY
  *
  * Copyright(c) 2015 Intel Corporation.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of version 2 of the GNU General Public License as
  * published by the Free Software Foundation.
  *
  * This program is distributed in the hope that it will be useful, but
  * WITHOUT ANY WARRANTY; without even the implied warranty of
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
  * General Public License for more details.
  *
  * Contact Information:
  * 	Sean Gulley <sean.m.gulley@intel.com>
  * 	Tim Chen <tim.c.chen@linux.intel.com>
  *
  * BSD LICENSE
  *
  * Copyright(c) 2015 Intel Corporation.
  *
  * Redistribution and use in source and binary forms, with or without
  * modification, are permitted provided that the following conditions
  * are met:
  *
  * 	* Redistributions of source code must retain the above copyright
  * 	  notice, this list of conditions and the following disclaimer.
  * 	* 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.
  * 	* Neither the name of Intel Corporation nor the names of its
  * 	  contributors may be used to endorse or promote products derived
  * 	  from this software without specific prior written permission.
  *
  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT
  * OWNER 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 <linux/linkage.h>

 #define DIGEST_PTR	%rdi	/* 1st arg */
 #define DATA_PTR	%rsi	/* 2nd arg */
 #define NUM_BLKS	%rdx	/* 3rd arg */

 #define SHA256CONSTANTS	%rax

 #define MSG		%xmm0
 #define STATE0		%xmm1
 #define STATE1		%xmm2
 #define MSGTMP0		%xmm3
 #define MSGTMP1		%xmm4
 #define MSGTMP2		%xmm5
 #define MSGTMP3		%xmm6
 #define MSGTMP4		%xmm7

 #define SHUF_MASK	%xmm8

 #define ABEF_SAVE	%xmm9
 #define CDGH_SAVE	%xmm10

 /*
  * Intel SHA Extensions optimized implementation of a SHA-256 update function
  *
  * The function takes a pointer to the current hash values, a pointer to the
  * input data, and a number of 64 byte blocks to process.  Once all blocks have
  * been processed, the digest pointer is  updated with the resulting hash value.
  * The function only processes complete blocks, there is no functionality to
  * store partial blocks.  All message padding and hash value initialization must
  * be done outside the update function.
  *
  * The indented lines in the loop are instructions related to rounds processing.
  * The non-indented lines are instructions related to the message schedule.
  *
  * void sha256_ni_transform(uint32_t *digest, const void *data,
 		uint32_t numBlocks);
  * digest : pointer to digest
  * data: pointer to input data
  * numBlocks: Number of blocks to process
  */

 .text
 .align 32
 ENTRY(sha256_ni_transform)

 	shl		$6, NUM_BLKS		/*  convert to bytes */
 	jz		.Ldone_hash
 	add		DATA_PTR, NUM_BLKS	/* pointer to end of data */

 	/*
 	 * load initial hash values
 	 * Need to reorder these appropriately
 	 * DCBA, HGFE -> ABEF, CDGH
 	 */
 	movdqu		0*16(DIGEST_PTR), STATE0
 	movdqu		1*16(DIGEST_PTR), STATE1

 	pshufd		$0xB1, STATE0,  STATE0		/* CDAB */
 	pshufd		$0x1B, STATE1,  STATE1		/* EFGH */
 	movdqa		STATE0, MSGTMP4
 	palignr		$8, STATE1,  STATE0		/* ABEF */
 	pblendw		$0xF0, MSGTMP4, STATE1		/* CDGH */

 	movdqa		PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK
 	lea		K256(%rip), SHA256CONSTANTS

 .Lloop0:
 	/* Save hash values for addition after rounds */
 	movdqa		STATE0, ABEF_SAVE
 	movdqa		STATE1, CDGH_SAVE

 	/* Rounds 0-3 */
 	movdqu		0*16(DATA_PTR), MSG
 	pshufb		SHUF_MASK, MSG
 	movdqa		MSG, MSGTMP0
 		paddd		0*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0

 	/* Rounds 4-7 */
 	movdqu		1*16(DATA_PTR), MSG
 	pshufb		SHUF_MASK, MSG
 	movdqa		MSG, MSGTMP1
 		paddd		1*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP1, MSGTMP0

 	/* Rounds 8-11 */
 	movdqu		2*16(DATA_PTR), MSG
 	pshufb		SHUF_MASK, MSG
 	movdqa		MSG, MSGTMP2
 		paddd		2*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP2, MSGTMP1

 	/* Rounds 12-15 */
 	movdqu		3*16(DATA_PTR), MSG
 	pshufb		SHUF_MASK, MSG
 	movdqa		MSG, MSGTMP3
 		paddd		3*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP3, MSGTMP4
 	palignr		$4, MSGTMP2, MSGTMP4
 	paddd		MSGTMP4, MSGTMP0
 	sha256msg2	MSGTMP3, MSGTMP0
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP3, MSGTMP2

 	/* Rounds 16-19 */
 	movdqa		MSGTMP0, MSG
 		paddd		4*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP0, MSGTMP4
 	palignr		$4, MSGTMP3, MSGTMP4
 	paddd		MSGTMP4, MSGTMP1
 	sha256msg2	MSGTMP0, MSGTMP1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP0, MSGTMP3

 	/* Rounds 20-23 */
 	movdqa		MSGTMP1, MSG
 		paddd		5*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP1, MSGTMP4
 	palignr		$4, MSGTMP0, MSGTMP4
 	paddd		MSGTMP4, MSGTMP2
 	sha256msg2	MSGTMP1, MSGTMP2
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP1, MSGTMP0

 	/* Rounds 24-27 */
 	movdqa		MSGTMP2, MSG
 		paddd		6*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP2, MSGTMP4
 	palignr		$4, MSGTMP1, MSGTMP4
 	paddd		MSGTMP4, MSGTMP3
 	sha256msg2	MSGTMP2, MSGTMP3
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP2, MSGTMP1

 	/* Rounds 28-31 */
 	movdqa		MSGTMP3, MSG
 		paddd		7*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP3, MSGTMP4
 	palignr		$4, MSGTMP2, MSGTMP4
 	paddd		MSGTMP4, MSGTMP0
 	sha256msg2	MSGTMP3, MSGTMP0
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP3, MSGTMP2

 	/* Rounds 32-35 */
 	movdqa		MSGTMP0, MSG
 		paddd		8*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP0, MSGTMP4
 	palignr		$4, MSGTMP3, MSGTMP4
 	paddd		MSGTMP4, MSGTMP1
 	sha256msg2	MSGTMP0, MSGTMP1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP0, MSGTMP3

 	/* Rounds 36-39 */
 	movdqa		MSGTMP1, MSG
 		paddd		9*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP1, MSGTMP4
 	palignr		$4, MSGTMP0, MSGTMP4
 	paddd		MSGTMP4, MSGTMP2
 	sha256msg2	MSGTMP1, MSGTMP2
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP1, MSGTMP0

 	/* Rounds 40-43 */
 	movdqa		MSGTMP2, MSG
 		paddd		10*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP2, MSGTMP4
 	palignr		$4, MSGTMP1, MSGTMP4
 	paddd		MSGTMP4, MSGTMP3
 	sha256msg2	MSGTMP2, MSGTMP3
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP2, MSGTMP1

 	/* Rounds 44-47 */
 	movdqa		MSGTMP3, MSG
 		paddd		11*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP3, MSGTMP4
 	palignr		$4, MSGTMP2, MSGTMP4
 	paddd		MSGTMP4, MSGTMP0
 	sha256msg2	MSGTMP3, MSGTMP0
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP3, MSGTMP2

 	/* Rounds 48-51 */
 	movdqa		MSGTMP0, MSG
 		paddd		12*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP0, MSGTMP4
 	palignr		$4, MSGTMP3, MSGTMP4
 	paddd		MSGTMP4, MSGTMP1
 	sha256msg2	MSGTMP0, MSGTMP1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0
 	sha256msg1	MSGTMP0, MSGTMP3

 	/* Rounds 52-55 */
 	movdqa		MSGTMP1, MSG
 		paddd		13*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP1, MSGTMP4
 	palignr		$4, MSGTMP0, MSGTMP4
 	paddd		MSGTMP4, MSGTMP2
 	sha256msg2	MSGTMP1, MSGTMP2
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0

 	/* Rounds 56-59 */
 	movdqa		MSGTMP2, MSG
 		paddd		14*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 	movdqa		MSGTMP2, MSGTMP4
 	palignr		$4, MSGTMP1, MSGTMP4
 	paddd		MSGTMP4, MSGTMP3
 	sha256msg2	MSGTMP2, MSGTMP3
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0

 	/* Rounds 60-63 */
 	movdqa		MSGTMP3, MSG
 		paddd		15*16(SHA256CONSTANTS), MSG
 		sha256rnds2	STATE0, STATE1
 		pshufd 		$0x0E, MSG, MSG
 		sha256rnds2	STATE1, STATE0

 	/* Add current hash values with previously saved */
 	paddd		ABEF_SAVE, STATE0
 	paddd		CDGH_SAVE, STATE1

 	/* Increment data pointer and loop if more to process */
 	add		$64, DATA_PTR
 	cmp		NUM_BLKS, DATA_PTR
 	jne		.Lloop0

 	/* Write hash values back in the correct order */
 	pshufd		$0x1B, STATE0,  STATE0		/* FEBA */
 	pshufd		$0xB1, STATE1,  STATE1		/* DCHG */
 	movdqa		STATE0, MSGTMP4
 	pblendw		$0xF0, STATE1,  STATE0		/* DCBA */
 	palignr		$8, MSGTMP4, STATE1		/* HGFE */

 	movdqu		STATE0, 0*16(DIGEST_PTR)
 	movdqu		STATE1, 1*16(DIGEST_PTR)

 .Ldone_hash:

 	ret
 ENDPROC(sha256_ni_transform)

 .section	.rodata.cst256.K256, "aM", @progbits, 256
 .align 64
 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

 .section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
 .align 16
 PSHUFFLE_BYTE_FLIP_MASK:
 	.octa 0x0c0d0e0f08090a0b0405060700010203
	/*
	* Intel SHA Extensions optimized implementation of a SHA-256 update function
	*
	* This file is provided under a dual BSD/GPLv2 license. When using or
	* redistributing this file, you may do so under either license.
	*
	* GPL LICENSE SUMMARY
	*
	* Copyright(c) 2015 Intel Corporation.
	*
	* This program is free software; you can redistribute it and/or modify
	* it under the terms of version 2 of the GNU General Public License as
	* published by the Free Software Foundation.
	*
	* This program is distributed in the hope that it will be useful, but
	* WITHOUT ANY WARRANTY; without even the implied warranty of
	* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
	* General Public License for more details.
	*
	* Contact Information:
	* Sean Gulley <sean.m.gulley@intel.com>
	* Tim Chen <tim.c.chen@linux.intel.com>
	*
	* BSD LICENSE
	*
	* Copyright(c) 2015 Intel Corporation.
	*
	* Redistribution and use in source and binary forms, with or without
	* modification, are permitted provided that the following conditions
	* are met:
	*
	* * Redistributions of source code must retain the above copyright
	* notice, this list of conditions and the following disclaimer.
	* * 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.
	* * Neither the name of Intel Corporation nor the names of its
	* contributors may be used to endorse or promote products derived
	* from this software without specific prior written permission.
	*
	* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS 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 COPYRIGHT
	* OWNER 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 <linux/linkage.h>

	#define DIGEST_PTR %rdi /* 1st arg */
	#define DATA_PTR %rsi /* 2nd arg */
	#define NUM_BLKS %rdx /* 3rd arg */

	#define SHA256CONSTANTS %rax

	#define MSG %xmm0
	#define STATE0 %xmm1
	#define STATE1 %xmm2
	#define MSGTMP0 %xmm3
	#define MSGTMP1 %xmm4
	#define MSGTMP2 %xmm5
	#define MSGTMP3 %xmm6
	#define MSGTMP4 %xmm7

	#define SHUF_MASK %xmm8

	#define ABEF_SAVE %xmm9
	#define CDGH_SAVE %xmm10

	/*
	* Intel SHA Extensions optimized implementation of a SHA-256 update function
	*
	* The function takes a pointer to the current hash values, a pointer to the
	* input data, and a number of 64 byte blocks to process. Once all blocks have
	* been processed, the digest pointer is updated with the resulting hash value.
	* The function only processes complete blocks, there is no functionality to
	* store partial blocks. All message padding and hash value initialization must
	* be done outside the update function.
	*
	* The indented lines in the loop are instructions related to rounds processing.
	* The non-indented lines are instructions related to the message schedule.
	*
	* void sha256_ni_transform(uint32_t digest, const void data,
	uint32_t numBlocks);
	* digest : pointer to digest
	* data: pointer to input data
	* numBlocks: Number of blocks to process
	*/

	.text
	.align 32
	ENTRY(sha256_ni_transform)

	shl $6, NUM_BLKS /* convert to bytes */
	jz .Ldone_hash
	add DATA_PTR, NUM_BLKS /* pointer to end of data */

	/*
	* load initial hash values
	* Need to reorder these appropriately
	* DCBA, HGFE -> ABEF, CDGH
	*/
	movdqu 0*16(DIGEST_PTR), STATE0
	movdqu 1*16(DIGEST_PTR), STATE1

	pshufd $0xB1, STATE0, STATE0 /* CDAB */
	pshufd $0x1B, STATE1, STATE1 /* EFGH */
	movdqa STATE0, MSGTMP4
	palignr $8, STATE1, STATE0 /* ABEF */
	pblendw $0xF0, MSGTMP4, STATE1 /* CDGH */

	movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK
	lea K256(%rip), SHA256CONSTANTS

	.Lloop0:
	/* Save hash values for addition after rounds */
	movdqa STATE0, ABEF_SAVE
	movdqa STATE1, CDGH_SAVE

	/* Rounds 0-3 */
	movdqu 0*16(DATA_PTR), MSG
	pshufb SHUF_MASK, MSG
	movdqa MSG, MSGTMP0
	paddd 0*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0

	/* Rounds 4-7 */
	movdqu 1*16(DATA_PTR), MSG
	pshufb SHUF_MASK, MSG
	movdqa MSG, MSGTMP1
	paddd 1*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP1, MSGTMP0

	/* Rounds 8-11 */
	movdqu 2*16(DATA_PTR), MSG
	pshufb SHUF_MASK, MSG
	movdqa MSG, MSGTMP2
	paddd 2*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP2, MSGTMP1

	/* Rounds 12-15 */
	movdqu 3*16(DATA_PTR), MSG
	pshufb SHUF_MASK, MSG
	movdqa MSG, MSGTMP3
	paddd 3*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP3, MSGTMP4
	palignr $4, MSGTMP2, MSGTMP4
	paddd MSGTMP4, MSGTMP0
	sha256msg2 MSGTMP3, MSGTMP0
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP3, MSGTMP2

	/* Rounds 16-19 */
	movdqa MSGTMP0, MSG
	paddd 4*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP0, MSGTMP4
	palignr $4, MSGTMP3, MSGTMP4
	paddd MSGTMP4, MSGTMP1
	sha256msg2 MSGTMP0, MSGTMP1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP0, MSGTMP3

	/* Rounds 20-23 */
	movdqa MSGTMP1, MSG
	paddd 5*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP1, MSGTMP4
	palignr $4, MSGTMP0, MSGTMP4
	paddd MSGTMP4, MSGTMP2
	sha256msg2 MSGTMP1, MSGTMP2
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP1, MSGTMP0

	/* Rounds 24-27 */
	movdqa MSGTMP2, MSG
	paddd 6*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP2, MSGTMP4
	palignr $4, MSGTMP1, MSGTMP4
	paddd MSGTMP4, MSGTMP3
	sha256msg2 MSGTMP2, MSGTMP3
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP2, MSGTMP1

	/* Rounds 28-31 */
	movdqa MSGTMP3, MSG
	paddd 7*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP3, MSGTMP4
	palignr $4, MSGTMP2, MSGTMP4
	paddd MSGTMP4, MSGTMP0
	sha256msg2 MSGTMP3, MSGTMP0
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP3, MSGTMP2

	/* Rounds 32-35 */
	movdqa MSGTMP0, MSG
	paddd 8*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP0, MSGTMP4
	palignr $4, MSGTMP3, MSGTMP4
	paddd MSGTMP4, MSGTMP1
	sha256msg2 MSGTMP0, MSGTMP1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP0, MSGTMP3

	/* Rounds 36-39 */
	movdqa MSGTMP1, MSG
	paddd 9*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP1, MSGTMP4
	palignr $4, MSGTMP0, MSGTMP4
	paddd MSGTMP4, MSGTMP2
	sha256msg2 MSGTMP1, MSGTMP2
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP1, MSGTMP0

	/* Rounds 40-43 */
	movdqa MSGTMP2, MSG
	paddd 10*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP2, MSGTMP4
	palignr $4, MSGTMP1, MSGTMP4
	paddd MSGTMP4, MSGTMP3
	sha256msg2 MSGTMP2, MSGTMP3
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP2, MSGTMP1

	/* Rounds 44-47 */
	movdqa MSGTMP3, MSG
	paddd 11*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP3, MSGTMP4
	palignr $4, MSGTMP2, MSGTMP4
	paddd MSGTMP4, MSGTMP0
	sha256msg2 MSGTMP3, MSGTMP0
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP3, MSGTMP2

	/* Rounds 48-51 */
	movdqa MSGTMP0, MSG
	paddd 12*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP0, MSGTMP4
	palignr $4, MSGTMP3, MSGTMP4
	paddd MSGTMP4, MSGTMP1
	sha256msg2 MSGTMP0, MSGTMP1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0
	sha256msg1 MSGTMP0, MSGTMP3

	/* Rounds 52-55 */
	movdqa MSGTMP1, MSG
	paddd 13*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP1, MSGTMP4
	palignr $4, MSGTMP0, MSGTMP4
	paddd MSGTMP4, MSGTMP2
	sha256msg2 MSGTMP1, MSGTMP2
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0

	/* Rounds 56-59 */
	movdqa MSGTMP2, MSG
	paddd 14*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	movdqa MSGTMP2, MSGTMP4
	palignr $4, MSGTMP1, MSGTMP4
	paddd MSGTMP4, MSGTMP3
	sha256msg2 MSGTMP2, MSGTMP3
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0

	/* Rounds 60-63 */
	movdqa MSGTMP3, MSG
	paddd 15*16(SHA256CONSTANTS), MSG
	sha256rnds2 STATE0, STATE1
	pshufd $0x0E, MSG, MSG
	sha256rnds2 STATE1, STATE0

	/* Add current hash values with previously saved */
	paddd ABEF_SAVE, STATE0
	paddd CDGH_SAVE, STATE1

	/* Increment data pointer and loop if more to process */
	add $64, DATA_PTR
	cmp NUM_BLKS, DATA_PTR
	jne .Lloop0

	/* Write hash values back in the correct order */
	pshufd $0x1B, STATE0, STATE0 /* FEBA */
	pshufd $0xB1, STATE1, STATE1 /* DCHG */
	movdqa STATE0, MSGTMP4
	pblendw $0xF0, STATE1, STATE0 /* DCBA */
	palignr $8, MSGTMP4, STATE1 /* HGFE */

	movdqu STATE0, 0*16(DIGEST_PTR)
	movdqu STATE1, 1*16(DIGEST_PTR)

	.Ldone_hash:

	ret
	ENDPROC(sha256_ni_transform)

	.section .rodata.cst256.K256, "aM", @progbits, 256
	.align 64
	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

	.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
	.align 16
	PSHUFFLE_BYTE_FLIP_MASK:
	.octa 0x0c0d0e0f08090a0b0405060700010203