/**************************************************************
  Copyright (c) 2021 Linaro Ltd.

  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 Huawei 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.
**********************************************************************/
.text
.align		6
.arch		armv8-a+sve

#include "../include/aarch64_label.h"

.global cdecl(gf_vect_mul_sve)
#ifndef __APPLE__
.type gf_vect_mul_sve, %function
#endif

/* Refer to include/gf_vect_mul.h
 *
 * @param len   Length of vector in bytes. Must be aligned to 32B.
 * @param gftbl Pointer to 32-byte array of pre-calculated constants based on C.
 * @param src   Pointer to src data array. Must be aligned to 32B.
 * @param dest  Pointer to destination data array. Must be aligned to 32B.
 * @returns 0 pass, other fail
 *
 * int gf_vect_mul(int len, unsigned char *gftbl, void *src, void *dest);
 */

/* arguments */
x_len		.req	x0
x_tbl		.req	x1
x_src		.req	x2
x_dest		.req	x3

/* returns */
w_ret		.req	w0

/* local variables */
x_pos		.req	x4

/* vectors */
z_mask0f	.req	z0

z_src		.req	z1
z_src_lo	.req	z2
z_src_hi	.req	z_src	/* reuse */

z_dest		.req	z3
z_tmp1_lo	.req	z4
z_tmp1_hi	.req	z_dest	/* reuse */

z_gft1_lo	.req	z6
z_gft1_hi	.req	z7
q_gft1_lo	.req	q6
q_gft1_hi	.req	q7

cdecl(gf_vect_mul_sve):
	/* less than 32 bytes, return_fail */
	cmp	x_len, #32
	blt	.return_fail

	mov	z_mask0f.b, #0x0f		/* z_mask0f = 0x0F0F...0F */
	mov	x_pos, #0

	/* Load with NEON instruction ldp */
	ldp	q_gft1_lo, q_gft1_hi, [x_tbl]

	/* vector length agnostic */
.Lloopsve_vl:
	whilelo	p0.b, x_pos, x_len
	b.none	.return_pass

	/* load src data, governed by p0 */
	ld1b	z_src.b,  p0/z, [x_src, x_pos]

	/* split 4-bit lo; 4-bit hi */
	and	z_src_lo.d, z_src.d, z_mask0f.d
	lsr	z_src_hi.b, z_src.b, #4

	/* table indexing, ie. gf(2^8) multiplication */
	tbl	z_tmp1_lo.b, {z_gft1_lo.b}, z_src_lo.b
	tbl	z_tmp1_hi.b, {z_gft1_hi.b}, z_src_hi.b
	/* exclusive or, ie. gf(2^8) add */
	eor	z_dest.d, z_tmp1_hi.d, z_tmp1_lo.d

	/* store dest data, governed by p0 */
	st1b	z_dest.b, p0, [x_dest, x_pos]
	/* increment one vector length */
	incb	x_pos

	b	.Lloopsve_vl

.return_pass:
	mov	w_ret, #0
	ret

.return_fail:
	mov	w_ret, #1
	ret