shake.c

#include "../firmware.h"

/*
 * Copyright (c) 2015 Markku-Juhani O. Saarinen
 * The MIT License (MIT)
 */

#ifndef KECCAKF_ROUNDS
#define KECCAKF_ROUNDS 24
#endif

#ifndef ROTL64
#define ROTL64(x, y) (((x) << (y)) | ((x) >> (64 - (y))))
#endif

// update the state with given number of rounds

static void sha3_keccakf(uint64_t st[25])
{
    // constants
    const uint64_t keccakf_rndc[24] = {
        0x0000000000000001, 0x0000000000008082, 0x800000000000808a,
        0x8000000080008000, 0x000000000000808b, 0x0000000080000001,
        0x8000000080008081, 0x8000000000008009, 0x000000000000008a,
        0x0000000000000088, 0x0000000080008009, 0x000000008000000a,
        0x000000008000808b, 0x800000000000008b, 0x8000000000008089,
        0x8000000000008003, 0x8000000000008002, 0x8000000000000080,
        0x000000000000800a, 0x800000008000000a, 0x8000000080008081,
        0x8000000000008080, 0x0000000080000001, 0x8000000080008008
    };
    const int keccakf_rotc[24] = {
        1,  3,  6,  10, 15, 21, 28, 36, 45, 55, 2,  14,
        27, 41, 56, 8,  25, 43, 62, 18, 39, 61, 20, 44
    };
    const int keccakf_piln[24] = {
        10, 7,  11, 17, 18, 3, 5,  16, 8,  21, 24, 4,
        15, 23, 19, 13, 12, 2, 20, 14, 22, 9,  6,  1
    };

    // variables
    int i, j, r;
    uint64_t t, bc[5];

#if __BYTE_ORDER__ != __ORDER_LITTLE_ENDIAN__
    uint8_t *v;

    // endianess conversion. this is redundant on little-endian targets
    for (i = 0; i < 25; i++) {
        v = (uint8_t *) &st[i];
        st[i] = ((uint64_t) v[0])     | (((uint64_t) v[1]) << 8) |
            (((uint64_t) v[2]) << 16) | (((uint64_t) v[3]) << 24) |
            (((uint64_t) v[4]) << 32) | (((uint64_t) v[5]) << 40) |
            (((uint64_t) v[6]) << 48) | (((uint64_t) v[7]) << 56);
    }
#endif

    // actual iteration
    for (r = 0; r < KECCAKF_ROUNDS; r++) {

        // Theta
        for (i = 0; i < 5; i++)
            bc[i] = st[i] ^ st[i + 5] ^ st[i + 10] ^ st[i + 15] ^ st[i + 20];

        for (i = 0; i < 5; i++) {
            t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1);
            for (j = 0; j < 25; j += 5)
                st[j + i] ^= t;
        }

        // Rho Pi
        t = st[1];
        for (i = 0; i < 24; i++) {
            j = keccakf_piln[i];
            bc[0] = st[j];
            st[j] = ROTL64(t, keccakf_rotc[i]);
            t = bc[0];
        }

        //  Chi
        for (j = 0; j < 25; j += 5) {
            for (i = 0; i < 5; i++)
                bc[i] = st[j + i];
            for (i = 0; i < 5; i++)
                st[j + i] ^= (~bc[(i + 1) % 5]) & bc[(i + 2) % 5];
        }

        //  Iota
        st[0] ^= keccakf_rndc[r];
    }

#if __BYTE_ORDER__ != __ORDER_LITTLE_ENDIAN__
    // endianess conversion. this is redundant on little-endian targets
    for (i = 0; i < 25; i++) {
        v = (uint8_t *) &st[i];
        t = st[i];
        v[0] = t & 0xFF;
        v[1] = (t >> 8) & 0xFF;
        v[2] = (t >> 16) & 0xFF;
        v[3] = (t >> 24) & 0xFF;
        v[4] = (t >> 32) & 0xFF;
        v[5] = (t >> 40) & 0xFF;
        v[6] = (t >> 48) & 0xFF;
        v[7] = (t >> 56) & 0xFF;
    }
#endif
}

void Util_shake_init(util_shake_ctx_t *c, uint8_t output_length)
{
    uint8_t i;

    for (i = 0; i < 25; i++)
    {
        c->st.q[i] = 0;
    }
    c->mdlen = output_length;
    c->rsiz = 200 - 2 * output_length;
    c->pt = 0;
}

void Util_shake_update(util_shake_ctx_t *c, const uint8_t *data, uint32_t data_length)
{
    uint32_t i;
    int32_t j;

    j = c->pt;
    for (i = 0; i < data_length; i++)
    {
        c->st.b[j++] ^= data[i];
        if (j >= c->rsiz)
        {
            sha3_keccakf(c->st.q);
            j = 0;
        }
    }
    c->pt = j;
}

void Util_shake_out(util_shake_ctx_t *c, uint8_t *output)
{
    uint32_t i;
    int32_t j;

    /* XOF function */
    c->st.b[c->pt] ^= 0x1F;
    c->st.b[c->rsiz - 1] ^= 0x80;
    sha3_keccakf(c->st.q);
    c->pt = 0;

    /* Export output */
    j = c->pt;
    for (i = 0; i < c->mdlen; i++)
    {
        if (j >= c->rsiz)
        {
            sha3_keccakf(c->st.q);
            j = 0;
        }
        output[i] = c->st.b[j++];
    }
    c->pt = j;
}