/*
 * Intel SHA Extensions optimized implementation of a SHA-1 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>
#include <linux/cfi_types.h>

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

/* gcc conversion */
#define FRAME_SIZE	32	/* space for 2x16 bytes */

#define ABCD		%xmm0
#define E0		%xmm1	/* Need two E's b/c they ping pong */
#define E1		%xmm2
#define MSG0		%xmm3
#define MSG1		%xmm4
#define MSG2		%xmm5
#define MSG3		%xmm6
#define SHUF_MASK	%xmm7


/*
 * Intel SHA Extensions optimized implementation of a SHA-1 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 sha1_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
SYM_TYPED_FUNC_START(sha1_ni_transform)
	push		%rbp
	mov		%rsp, %rbp
	sub		$FRAME_SIZE, %rsp
	and		$~0xF, %rsp

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

	/* load initial hash values */
	pinsrd		$3, 1*16(DIGEST_PTR), E0
	movdqu		0*16(DIGEST_PTR), ABCD
	pand		UPPER_WORD_MASK(%rip), E0
	pshufd		$0x1B, ABCD, ABCD

	movdqa		PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK

.Lloop0:
	/* Save hash values for addition after rounds */
	movdqa		E0, (0*16)(%rsp)
	movdqa		ABCD, (1*16)(%rsp)

	/* Rounds 0-3 */
	movdqu		0*16(DATA_PTR), MSG0
	pshufb		SHUF_MASK, MSG0
		paddd		MSG0, E0
		movdqa		ABCD, E1
		sha1rnds4	$0, E0, ABCD

	/* Rounds 4-7 */
	movdqu		1*16(DATA_PTR), MSG1
	pshufb		SHUF_MASK, MSG1
		sha1nexte	MSG1, E1
		movdqa		ABCD, E0
		sha1rnds4	$0, E1, ABCD
	sha1msg1	MSG1, MSG0

	/* Rounds 8-11 */
	movdqu		2*16(DATA_PTR), MSG2
	pshufb		SHUF_MASK, MSG2
		sha1nexte	MSG2, E0
		movdqa		ABCD, E1
		sha1rnds4	$0, E0, ABCD
	sha1msg1	MSG2, MSG1
	pxor		MSG2, MSG0

	/* Rounds 12-15 */
	movdqu		3*16(DATA_PTR), MSG3
	pshufb		SHUF_MASK, MSG3
		sha1nexte	MSG3, E1
		movdqa		ABCD, E0
	sha1msg2	MSG3, MSG0
		sha1rnds4	$0, E1, ABCD
	sha1msg1	MSG3, MSG2
	pxor		MSG3, MSG1

	/* Rounds 16-19 */
		sha1nexte	MSG0, E0
		movdqa		ABCD, E1
	sha1msg2	MSG0, MSG1
		sha1rnds4	$0, E0, ABCD
	sha1msg1	MSG0, MSG3
	pxor		MSG0, MSG2

	/* Rounds 20-23 */
		sha1nexte	MSG1, E1
		movdqa		ABCD, E0
	sha1msg2	MSG1, MSG2
		sha1rnds4	$1, E1, ABCD
	sha1msg1	MSG1, MSG0
	pxor		MSG1, MSG3

	/* Rounds 24-27 */
		sha1nexte	MSG2, E0
		movdqa		ABCD, E1
	sha1msg2	MSG2, MSG3
		sha1rnds4	$1, E0, ABCD
	sha1msg1	MSG2, MSG1
	pxor		MSG2, MSG0

	/* Rounds 28-31 */
		sha1nexte	MSG3, E1
		movdqa		ABCD, E0
	sha1msg2	MSG3, MSG0
		sha1rnds4	$1, E1, ABCD
	sha1msg1	MSG3, MSG2
	pxor		MSG3, MSG1

	/* Rounds 32-35 */
		sha1nexte	MSG0, E0
		movdqa		ABCD, E1
	sha1msg2	MSG0, MSG1
		sha1rnds4	$1, E0, ABCD
	sha1msg1	MSG0, MSG3
	pxor		MSG0, MSG2

	/* Rounds 36-39 */
		sha1nexte	MSG1, E1
		movdqa		ABCD, E0
	sha1msg2	MSG1, MSG2
		sha1rnds4	$1, E1, ABCD
	sha1msg1	MSG1, MSG0
	pxor		MSG1, MSG3

	/* Rounds 40-43 */
		sha1nexte	MSG2, E0
		movdqa		ABCD, E1
	sha1msg2	MSG2, MSG3
		sha1rnds4	$2, E0, ABCD
	sha1msg1	MSG2, MSG1
	pxor		MSG2, MSG0

	/* Rounds 44-47 */
		sha1nexte	MSG3, E1
		movdqa		ABCD, E0
	sha1msg2	MSG3, MSG0
		sha1rnds4	$2, E1, ABCD
	sha1msg1	MSG3, MSG2
	pxor		MSG3, MSG1

	/* Rounds 48-51 */
		sha1nexte	MSG0, E0
		movdqa		ABCD, E1
	sha1msg2	MSG0, MSG1
		sha1rnds4	$2, E0, ABCD
	sha1msg1	MSG0, MSG3
	pxor		MSG0, MSG2

	/* Rounds 52-55 */
		sha1nexte	MSG1, E1
		movdqa		ABCD, E0
	sha1msg2	MSG1, MSG2
		sha1rnds4	$2, E1, ABCD
	sha1msg1	MSG1, MSG0
	pxor		MSG1, MSG3

	/* Rounds 56-59 */
		sha1nexte	MSG2, E0
		movdqa		ABCD, E1
	sha1msg2	MSG2, MSG3
		sha1rnds4	$2, E0, ABCD
	sha1msg1	MSG2, MSG1
	pxor		MSG2, MSG0

	/* Rounds 60-63 */
		sha1nexte	MSG3, E1
		movdqa		ABCD, E0
	sha1msg2	MSG3, MSG0
		sha1rnds4	$3, E1, ABCD
	sha1msg1	MSG3, MSG2
	pxor		MSG3, MSG1

	/* Rounds 64-67 */
		sha1nexte	MSG0, E0
		movdqa		ABCD, E1
	sha1msg2	MSG0, MSG1
		sha1rnds4	$3, E0, ABCD
	sha1msg1	MSG0, MSG3
	pxor		MSG0, MSG2

	/* Rounds 68-71 */
		sha1nexte	MSG1, E1
		movdqa		ABCD, E0
	sha1msg2	MSG1, MSG2
		sha1rnds4	$3, E1, ABCD
	pxor		MSG1, MSG3

	/* Rounds 72-75 */
		sha1nexte	MSG2, E0
		movdqa		ABCD, E1
	sha1msg2	MSG2, MSG3
		sha1rnds4	$3, E0, ABCD

	/* Rounds 76-79 */
		sha1nexte	MSG3, E1
		movdqa		ABCD, E0
		sha1rnds4	$3, E1, ABCD

	/* Add current hash values with previously saved */
	sha1nexte	(0*16)(%rsp), E0
	paddd		(1*16)(%rsp), ABCD

	/* 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, ABCD, ABCD
	movdqu		ABCD, 0*16(DIGEST_PTR)
	pextrd		$3, E0, 1*16(DIGEST_PTR)

.Ldone_hash:
	mov		%rbp, %rsp
	pop		%rbp

	RET
SYM_FUNC_END(sha1_ni_transform)

.section	.rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
.align 16
PSHUFFLE_BYTE_FLIP_MASK:
	.octa 0x000102030405060708090a0b0c0d0e0f

.section	.rodata.cst16.UPPER_WORD_MASK, "aM", @progbits, 16
.align 16
UPPER_WORD_MASK:
	.octa 0xFFFFFFFF000000000000000000000000