/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
* ARIA Cipher 16-way parallel algorithm (AVX)
*
* Copyright (c) 2022 Taehee Yoo <ap420073@gmail.com>
*
*/
#include <linux/linkage.h>
#include <linux/cfi_types.h>
#include <asm/asm-offsets.h>
#include <asm/frame.h>
/* register macros */
#define CTX %rdi
#define BV8(a0, a1, a2, a3, a4, a5, a6, a7) \
( (((a0) & 1) << 0) | \
(((a1) & 1) << 1) | \
(((a2) & 1) << 2) | \
(((a3) & 1) << 3) | \
(((a4) & 1) << 4) | \
(((a5) & 1) << 5) | \
(((a6) & 1) << 6) | \
(((a7) & 1) << 7) )
#define BM8X8(l0, l1, l2, l3, l4, l5, l6, l7) \
( ((l7) << (0 * 8)) | \
((l6) << (1 * 8)) | \
((l5) << (2 * 8)) | \
((l4) << (3 * 8)) | \
((l3) << (4 * 8)) | \
((l2) << (5 * 8)) | \
((l1) << (6 * 8)) | \
((l0) << (7 * 8)) )
#define inc_le128(x, minus_one, tmp) \
vpcmpeqq minus_one, x, tmp; \
vpsubq minus_one, x, x; \
vpslldq $8, tmp, tmp; \
vpsubq tmp, x, x;
#define filter_8bit(x, lo_t, hi_t, mask4bit, tmp0) \
vpand x, mask4bit, tmp0; \
vpandn x, mask4bit, x; \
vpsrld $4, x, x; \
\
vpshufb tmp0, lo_t, tmp0; \
vpshufb x, hi_t, x; \
vpxor tmp0, x, x;
#define transpose_4x4(x0, x1, x2, x3, t1, t2) \
vpunpckhdq x1, x0, t2; \
vpunpckldq x1, x0, x0; \
\
vpunpckldq x3, x2, t1; \
vpunpckhdq x3, x2, x2; \
\
vpunpckhqdq t1, x0, x1; \
vpunpcklqdq t1, x0, x0; \
\
vpunpckhqdq x2, t2, x3; \
