tweakey.c 4.01 KB
Newer Older
lwc-tester committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177
/*
Implementation of the Lilliput-AE tweakable block cipher.

Authors, hereby denoted as "the implementer":
    Kévin Le Gouguec,
    2019.

For more information, feedback or questions, refer to our website:
https://paclido.fr/lilliput-ae

To the extent possible under law, the implementer has waived all copyright
and related or neighboring rights to the source code in this file.
http://creativecommons.org/publicdomain/zero/1.0/

---

This file provides an implementation of Lilliput-TBC's tweakey schedule,
where multiplications by matrices M and M_R to the power n are performed
by functions expressing the exponentiated matrices with shifts and XORs.
*/

#include <stdint.h>
#include <string.h>

#include "constants.h"
#include "tweakey.h"


#define LANE_BITS  64
#define LANE_BYTES (LANE_BITS/8)
#define LANES_NB   (TWEAKEY_BYTES/LANE_BYTES)


void tweakey_state_init(
    uint8_t TK[TWEAKEY_BYTES],
    const uint8_t key[KEY_BYTES],
    const uint8_t tweak[TWEAK_BYTES]
)
{
    memcpy(TK,             tweak, TWEAK_BYTES);
    memcpy(TK+TWEAK_BYTES, key,   KEY_BYTES);
}


void tweakey_state_extract(
    const uint8_t TK[TWEAKEY_BYTES],
    uint8_t round_constant,
    uint8_t round_tweakey[ROUND_TWEAKEY_BYTES]
)
{
    memset(round_tweakey, 0, ROUND_TWEAKEY_BYTES);

    for (size_t j=0; j<LANES_NB; j++)
    {
        const uint8_t *TKj = TK + j*LANE_BYTES;

        for (size_t k=0; k<LANE_BYTES; k++)
        {
            round_tweakey[k] ^= TKj[k];
        }
    }

    round_tweakey[0] ^= round_constant;
}


static void _multiply_M(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES])
{
    y[7] = x[6];
    y[6] = x[5];
    y[5] = x[5]<<3 ^ x[4];
    y[4] = x[4]>>3 ^ x[3];
    y[3] = x[2];
    y[2] = x[6]<<2 ^ x[1];
    y[1] = x[0];
    y[0] = x[7];
}

static void _multiply_M2(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES])
{
    uint8_t x_M_5 = x[5]<<3 ^ x[4];
    uint8_t x_M_4 = x[4]>>3 ^ x[3];

    y[7] = x[5];
    y[6] = x_M_5;
    y[5] = x_M_5<<3 ^ x_M_4;
    y[4] = x_M_4>>3 ^ x[2];
    y[3] = x[6]<<2  ^ x[1];
    y[2] = x[5]<<2  ^ x[0];
    y[1] = x[7];
    y[0] = x[6];
}

static void _multiply_M3(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES])
{
    uint8_t x_M_5  = x[5]<<3  ^ x[4];
    uint8_t x_M_4  = x[4]>>3  ^ x[3];
    uint8_t x_M2_5 = x_M_5<<3 ^ x_M_4;
    uint8_t x_M2_4 = x_M_4>>3 ^ x[2];

    y[7] = x_M_5;
    y[6] = x_M2_5;
    y[5] = x_M2_5<<3 ^ x_M2_4;
    y[4] = x_M2_4>>3 ^ x[6]<<2 ^ x[1];
    y[3] = x[5]<<2   ^ x[0];
    y[2] = x_M_5<<2  ^ x[7];
    y[1] = x[6];
    y[0] = x[5];
}

static void _multiply_MR(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES])
{
    y[0] = x[1];
    y[1] = x[2];
    y[2] = x[3]    ^ x[4]>>3;
    y[3] = x[4];
    y[4] = x[5]    ^ x[6]<<3;
    y[5] = x[3]<<2 ^ x[6];
    y[6] = x[7];
    y[7] = x[0];
}

static void _multiply_MR2(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES])
{
    uint8_t x_MR_4 = x[5] ^ x[6]<<3;

    y[0] = x[2];
    y[1] = x[3]    ^ x[4]>>3;
    y[2] = x[4]    ^ x_MR_4>>3;
    y[3] = x_MR_4;
    y[4] = x[3]<<2 ^ x[6]      ^ x[7]<<3;
    y[5] = x[4]<<2 ^ x[7];
    y[6] = x[0];
    y[7] = x[1];
}

static void _multiply_MR3(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES])
{
    uint8_t x_MR_4  = x[5]    ^ x[6]<<3;
    uint8_t x_MR2_4 = x[3]<<2 ^ x[6]    ^ x[7]<<3;

    y[0] = x[3]      ^ x[4]>>3;
    y[1] = x[4]      ^ x_MR_4>>3;
    y[2] = x_MR_4    ^ x_MR2_4>>3;
    y[3] = x_MR2_4;
    y[4] = x[0]<<3   ^ x[4]<<2   ^ x[7];
    y[5] = x_MR_4<<2 ^ x[0];
    y[6] = x[1];
    y[7] = x[2];
}

typedef void (*matrix_multiplication)(const uint8_t x[LANE_BYTES], uint8_t y[LANE_BYTES]);

static const matrix_multiplication ALPHAS[6] = {
    _multiply_M,
    _multiply_M2,
    _multiply_M3,
    _multiply_MR,
    _multiply_MR2,
    _multiply_MR3
};


void tweakey_state_update(uint8_t TK[TWEAKEY_BYTES])
{
    /* Skip lane 0, as it is multiplied by the identity matrix. */

    for (size_t j=1; j<LANES_NB; j++)
    {
        uint8_t *TKj = TK + j*LANE_BYTES;

        uint8_t TKj_old[LANE_BYTES];
        memcpy(TKj_old, TKj, LANE_BYTES);

        ALPHAS[j-1](TKj_old, TKj);
    }
}