/*-
 * Copyright 2009 Colin Percival
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. 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.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
 *
 * This file was originally written by Colin Percival as part of the Tarsnap
 * online backup system.
 */
#include <stdio.h>
#include <stdint.h>
#include <string.h>
#include <ByteOrder.h>
#include "pbkdf2.h"
#include "crypto_scrypt_smix.h"

static void blkcpy(void *, const void *, size_t);
static void blkxor(void *, const void *, size_t);
static void salsa20_8(uint32_t[16]);
static void blockmix_salsa8(const uint32_t *, uint32_t *, uint32_t *, size_t);
static uint64_t integerify(const void *, size_t);

static void
blkcpy(void * dest, const void * src, size_t len)
{
        size_t * D = (size_t *)dest;
        const size_t * S = (const size_t *)src;
        size_t L = len / sizeof(size_t);
        size_t i;

        for (i = 0; i < L; i++)
                D[i] = S[i];
}

static void
blkxor(void * dest, const void * src, size_t len)
{
        size_t * D = (size_t *)dest;
        const size_t * S = (const size_t *)src;
        size_t L = len / sizeof(size_t);
        size_t i;

        for (i = 0; i < L; i++)
                D[i] ^= S[i];
}

/**
 * salsa20_8(B):
 * Apply the salsa20/8 core to the provided block.
 */
static void
salsa20_8(uint32_t B[16])
{
        uint32_t x[16];
        size_t i;

        blkcpy(x, B, 64);
        for (i = 0; i < 8; i += 2) {
#define R(a,b) (((a) << (b)) | ((a) >> (32 - (b))))
                /* Operate on columns. */
                x[ 4] ^= R(x[ 0]+x[12], 7);  x[ 8] ^= R(x[ 4]+x[ 0], 9);
                x[12] ^= R(x[ 8]+x[ 4],13);  x[ 0] ^= R(x[12]+x[ 8],18);

                x[ 9] ^= R(x[ 5]+x[ 1], 7);  x[13] ^= R(x[ 9]+x[ 5], 9);
                x[ 1] ^= R(x[13]+x[ 9],13);  x[ 5] ^= R(x[ 1]+x[13],18);

                x[14] ^= R(x[10]+x[ 6], 7);  x[ 2] ^= R(x[14]+x[10], 9);
                x[ 6] ^= R(x[ 2]+x[14],13);  x[10] ^= R(x[ 6]+x[ 2],18);

                x[ 3] ^= R(x[15]+x[11], 7);  x[ 7] ^= R(x[ 3]+x[15], 9);
                x[11] ^= R(x[ 7]+x[ 3],13);  x[15] ^= R(x[11]+x[ 7],18);

                /* Operate on rows. */
                x[ 1] ^= R(x[ 0]+x[ 3], 7);  x[ 2] ^= R(x[ 1]+x[ 0], 9);
                x[ 3] ^= R(x[ 2]+x[ 1],13);  x[ 0] ^= R(x[ 3]+x[ 2],18);

                x[ 6] ^= R(x[ 5]+x[ 4], 7);  x[ 7] ^= R(x[ 6]+x[ 5], 9);
                x[ 4] ^= R(x[ 7]+x[ 6],13);  x[ 5] ^= R(x[ 4]+x[ 7],18);

                x[11] ^= R(x[10]+x[ 9], 7);  x[ 8] ^= R(x[11]+x[10], 9);
                x[ 9] ^= R(x[ 8]+x[11],13);  x[10] ^= R(x[ 9]+x[ 8],18);

                x[12] ^= R(x[15]+x[14], 7);  x[13] ^= R(x[12]+x[15], 9);
                x[14] ^= R(x[13]+x[12],13);  x[15] ^= R(x[14]+x[13],18);
#undef R
        }
        for (i = 0; i < 16; i++)
                B[i] += x[i];
}

/**
 * blockmix_salsa8(Bin, Bout, X, r):
 * Compute Bout = BlockMix_{salsa20/8, r}(Bin).  The input Bin must be 128r
 * bytes in length; the output Bout must also be the same size.  The
 * temporary space X must be 64 bytes.
 */
static void
blockmix_salsa8(const uint32_t * Bin, uint32_t * Bout, uint32_t * X, size_t r)
{
        size_t i;

        /* 1: X <-- B_{2r - 1} */
        blkcpy(X, &Bin[(2 * r - 1) * 16], 64);

        /* 2: for i = 0 to 2r - 1 do */
        for (i = 0; i < 2 * r; i += 2) {
                /* 3: X <-- H(X \xor B_i) */
                blkxor(X, &Bin[i * 16], 64);
                salsa20_8(X);

                /* 4: Y_i <-- X */
                /* 6: B' <-- (Y_0, Y_2 ... Y_{2r-2}, Y_1, Y_3 ... Y_{2r-1}) */
                blkcpy(&Bout[i * 8], X, 64);

                /* 3: X <-- H(X \xor B_i) */
                blkxor(X, &Bin[i * 16 + 16], 64);
                salsa20_8(X);

                /* 4: Y_i <-- X */
                /* 6: B' <-- (Y_0, Y_2 ... Y_{2r-2}, Y_1, Y_3 ... Y_{2r-1}) */
                blkcpy(&Bout[i * 8 + r * 16], X, 64);
        }
}

/**
 * integerify(B, r):
 * Return the result of parsing B_{2r-1} as a little-endian integer.
 */
static uint64_t
integerify(const void * B, size_t r)
{
        const uint32_t * X = (const uint32_t *)((uintptr_t)(B) + (2 * r - 1) * 64);

        return (((uint64_t)(X[1]) << 32) + X[0]);
}

/**
 * crypto_scrypt_smix(B, r, N, V, XY):
 * Compute B = SMix_r(B, N).  The input B must be 128r bytes in length;
 * the temporary storage V must be 128rN bytes in length; the temporary
 * storage XY must be 256r + 64 bytes in length.  The value N must be a
 * power of 2 greater than 1.  The arrays B, V, and XY must be aligned to a
 * multiple of 64 bytes.
 */
void
crypto_scrypt_smix(uint8_t * B, size_t r, uint64_t N, void * _V, void * XY)
{
        uint32_t * X = (uint32_t *)XY;
        uint32_t * Y = (uint32_t *)((uint8_t *)(XY) + 128 * r);
        uint32_t * Z = (uint32_t *)((uint8_t *)(XY) + 256 * r);
        uint32_t * V = (uint32_t *)_V;
        uint64_t i;
        uint64_t j;
        size_t k;

        /* 1: X <-- B */
        for (k = 0; k < 32 * r; k++) {
                X[k] = B_LENDIAN_TO_HOST_INT32(((uint32_t*)B)[k]);
        }

        /* 2: for i = 0 to N - 1 do */
        for (i = 0; i < N; i += 2) {
                /* 3: V_i <-- X */
                blkcpy(&V[i * (32 * r)], X, 128 * r);

                /* 4: X <-- H(X) */
                blockmix_salsa8(X, Y, Z, r);

                /* 3: V_i <-- X */
                blkcpy(&V[(i + 1) * (32 * r)], Y, 128 * r);

                /* 4: X <-- H(X) */
                blockmix_salsa8(Y, X, Z, r);
        }

        /* 6: for i = 0 to N - 1 do */
        for (i = 0; i < N; i += 2) {
                /* 7: j <-- Integerify(X) mod N */
                j = integerify(X, r) & (N - 1);

                /* 8: X <-- H(X \xor V_j) */
                blkxor(X, &V[j * (32 * r)], 128 * r);
                blockmix_salsa8(X, Y, Z, r);

                /* 7: j <-- Integerify(X) mod N */
                j = integerify(Y, r) & (N - 1);

                /* 8: X <-- H(X \xor V_j) */
                blkxor(Y, &V[j * (32 * r)], 128 * r);
                blockmix_salsa8(Y, X, Z, r);
        }

        /* 10: B' <-- X */
        for (k = 0; k < 32 * r; k++) {
                uint32_t* B32 = &(reinterpret_cast<uint32_t*>(B)[k]);
                *B32 = B_HOST_TO_LENDIAN_INT32(X[k]);
        }
}