/*
* x86_64/AVX2/AES-NI assembler implementation of Camellia
*
* Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
*/
#include <linux/linkage.h>
#define CAMELLIA_TABLE_BYTE_LEN 272
/* struct camellia_ctx: */
#define key_table 0
#define key_length CAMELLIA_TABLE_BYTE_LEN
/* register macros */
#define CTX %rdi
#define RIO %r8
/**********************************************************************
helper macros
**********************************************************************/
#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 ymm0_x xmm0
#define ymm1_x xmm1
#define ymm2_x xmm2
#define ymm3_x xmm3
#define ymm4_x xmm4
#define ymm5_x xmm5
#define ymm6_x xmm6
#define ymm7_x xmm7
#define ymm8_x xmm8
#define ymm9_x xmm9
#define ymm10_x xmm10
#define ymm11_x xmm11
#define ymm12_x xmm12
#define ymm13_x xmm13
#define ymm14_x xmm14
#define ymm15_x xmm15
/*
* AES-NI instructions do not support ymmX registers, so we need splitting and
* merging.
*/
#define vaesenclast256(zero, yreg, tmp) \
vextracti128 $1, yreg, tmp##_x; \
vaesenclast zero##_x, yreg##_x, yreg##_x; \
vaesenclast zero##_x, tmp##_x, tmp##_x; \
vinserti128 $1, tmp##_x, yreg, yreg;
/**********************************************************************
32-way camellia
**********************************************************************/
/*
* IN:
* x0..x7: byte-sliced AB state
* mem_cd: register pointer storing CD state
* key: index for key material
* OUT:
* x0..x7: new byte-sliced CD state
*/
#define roundsm32(x0, x1, x2, x3, x4, x5, x6, x7, t0, t1, t2, t3, t4, t5, t6, \
t7, mem_cd, key) \
/* \
* S-function with AES subbytes \
*/ \
vbroadcasti128 .Linv_shift_row, t4; \
vpbroadcastb .L0f0f0f0f, t7; \
vbroadcasti128 .Lpre_tf_lo_s1, t0; \
vbroadcasti128 .Lpre_tf_hi_s1, t1; \
\
/* AES inverse shift rows */ \
vpshufb t4, x0, x0; \
vpshufb t4, x7, x7; \
vpshufb t4, x1, x1; \
vpshufb t4, x4, x4; \
vpshufb t4, x2, x2; \
vpshufb t4, x5, x5; \
vpshufb t4, x3, x3; \
vpshufb
