/*
  This file is for public-key generation
*/

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

#include "controlbits.h"
#include "benes.h"
#include "crypto_declassify.h"
#include "crypto_uint64.h"
#include "params.h"
#include "pk_gen.h"
#include "root.h"
#include "uint64_sort.h"
#include "util.h"

static crypto_uint64 uint64_is_equal_declassify(uint64_t t, uint64_t u) {
    crypto_uint64 mask = crypto_uint64_equal_mask(t, u);
    crypto_declassify(&mask, sizeof mask);
    return mask;
}

static crypto_uint64 uint64_is_zero_declassify(uint64_t t) {
    crypto_uint64 mask = crypto_uint64_zero_mask(t);
    crypto_declassify(&mask, sizeof mask);
    return mask;
}

#define min(a, b) (((a) < (b)) ? (a) : (b))

/* return number of trailing zeros of the non-zero input in */
static inline int ctz(uint64_t in) {
    int i, b, m = 0, r = 0;

    for (i = 0; i < 64; i++) {
        b = (in >> i) & 1;
        m |= b;
        r += (m ^ 1) & (b ^ 1);
    }

    return r;
}

static inline uint64_t same_mask(uint16_t x, uint16_t y) {
    uint64_t mask;

    mask = x ^ y;
    mask -= 1;
    mask >>= 63;
    mask = -mask;

    return mask;
}

static int mov_columns(uint8_t mat[][ SYS_N / 8 ], int16_t *pi, uint64_t *pivots) {
    int i, j, k, s, block_idx, row, tail;
    uint64_t buf[64], ctz_list[32], t, d, mask, one = 1;
    unsigned char tmp[9];

    row = PK_NROWS - 32;
    block_idx = row / 8;
    tail = row % 8;

    // extract the 32x64 matrix

    for (i = 0; i < 32; i++) {
        for (j = 0; j < 9; j++) {
            tmp[j] = mat[ row + i ][ block_idx + j ];
        }
        for (j = 0; j < 8; j++) {
            tmp[j] = (tmp[j] >> tail) | (tmp[j + 1] << (8 - tail));
        }

        buf[i] = load8( tmp );
    }

    // compute the column indices of pivots by Gaussian elimination.
    // the indices are stored in ctz_list

    *pivots = 0;

    for (i = 0; i < 32; i++) {
        t = buf[i];
        for (j = i + 1; j < 32; j++) {
            t |= buf[j];
        }

        if (uint64_is_zero_declassify(t)) {
            return -1;    // return if buf is not full rank
        }

        ctz_list[i] = s = ctz(t);
        *pivots |= one << ctz_list[i];

        for (j = i + 1; j < 32; j++) {
            mask = (buf[i] >> s) & 1;
            mask -= 1;
            buf[i] ^= buf[j] & mask;
        }
        for (j = i + 1; j < 32; j++) {
            mask = (buf[j] >> s) & 1;
            mask = -mask;
            buf[j] ^= buf[i] & mask;
        }
    }

    // updating permutation

    for (j = 0;   j < 32; j++) {
        for (k = j + 1; k < 64; k++) {
            d = pi[ row + j ] ^ pi[ row + k ];
            d &= same_mask((uint16_t)k, (uint16_t)ctz_list[j]);
            pi[ row + j ] ^= d;
            pi[ row + k ] ^= d;
        }
    }

    // moving columns of mat according to the column indices of pivots

    for (i = 0; i < PK_NROWS; i++) {

        for (k = 0; k < 9; k++) {
            tmp[k] = mat[ i ][ block_idx + k ];
        }
        for (k = 0; k < 8; k++) {
            tmp[k] = (tmp[k] >> tail) | (tmp[k + 1] << (8 - tail));
        }

        t = load8( tmp );

        for (j = 0; j < 32; j++) {
            d  = t >> j;
            d ^= t >> ctz_list[j];
            d &= 1;

            t ^= d << ctz_list[j];
            t ^= d << j;
        }

        store8( tmp, t );

        mat[ i ][ block_idx + 8 ] = (mat[ i ][ block_idx + 8 ] >> tail << tail) | (tmp[7] >> (8 - tail));
        mat[ i ][ block_idx + 0 ] = (tmp[0] << tail) | (mat[ i ][ block_idx ] << (8 - tail) >> (8 - tail));

        for (k = 7; k >= 1; k--) {
            mat[ i ][ block_idx + k ] = (tmp[k] << tail) | (tmp[k - 1] >> (8 - tail));
        }
    }

    return 0;
}

/* input: secret key sk */
/* output: public key pk */
int pk_gen(unsigned char *pk, unsigned char *sk, const uint32_t *perm, int16_t *pi, uint64_t *pivots) {
    unsigned char *pk_ptr = pk;

    int i, j, k;
    int row, c, tail;

    uint64_t buf[ 1 << GFBITS ];

    unsigned char mat[ PK_NROWS ][ SYS_N / 8 ];
    unsigned char mask;
    unsigned char b;

    gf g[ SYS_T + 1 ]; // Goppa polynomial
    gf L[ SYS_N ]; // support
    gf inv[ SYS_N ];

    //

    g[ SYS_T ] = 1;

    for (i = 0; i < SYS_T; i++) {
        g[i] = load_gf(sk);
        sk += 2;
    }

    for (i = 0; i < (1 << GFBITS); i++) {
        buf[i] = perm[i];
        buf[i] <<= 31;
        buf[i] |= i;
    }

    uint64_sort(buf, 1 << GFBITS);

    for (i = 1; i < (1 << GFBITS); i++) {
        if (uint64_is_equal_declassify(buf[i - 1] >> 31, buf[i] >> 31)) {
            return -1;
        }
    }

    for (i = 0; i < (1 << GFBITS); i++) {
        pi[i] = buf[i] & GFMASK;
    }
    for (i = 0; i < SYS_N;         i++) {
        L[i] = bitrev(pi[i]);
    }

    // filling the matrix

    root(inv, g, L);

    for (i = 0; i < SYS_N; i++) {
        inv[i] = gf_inv(inv[i]);
    }

    for (i = 0; i < PK_NROWS; i++) {
        for (j = 0; j < SYS_N / 8; j++) {
            mat[i][j] = 0;
        }
    }

    for (i = 0; i < SYS_T; i++) {
        for (j = 0; j < SYS_N; j += 8) {
            for (k = 0; k < GFBITS;  k++) {
                b  = (inv[j + 7] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 6] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 5] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 4] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 3] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 2] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 1] >> k) & 1;
                b <<= 1;
                b |= (inv[j + 0] >> k) & 1;

                mat[ i * GFBITS + k ][ j / 8 ] = b;
            }
        }

        for (j = 0; j < SYS_N; j++) {
            inv[j] = gf_mul(inv[j], L[j]);
        }

    }

    // gaussian elimination

    for (i = 0; i < (PK_NROWS + 7) / 8; i++) {
        for (j = 0; j < 8; j++) {
            row = i * 8 + j;

            if (row >= PK_NROWS) {
                break;
            }

            if (row == PK_NROWS - 32) {
                if (mov_columns(mat, pi, pivots)) {
                    return -1;
                }
            }

            for (k = row + 1; k < PK_NROWS; k++) {
                mask = mat[ row ][ i ] ^ mat[ k ][ i ];
                mask >>= j;
                mask &= 1;
                mask = -mask;

                for (c = 0; c < SYS_N / 8; c++) {
                    mat[ row ][ c ] ^= mat[ k ][ c ] & mask;
                }
            }

            if ( uint64_is_zero_declassify((mat[ row ][ i ] >> j) & 1) ) { // return if not systematic
                return -1;
            }

            for (k = 0; k < PK_NROWS; k++) {
                if (k != row) {
                    mask = mat[ k ][ i ] >> j;
                    mask &= 1;
                    mask = -mask;

                    for (c = 0; c < SYS_N / 8; c++) {
                        mat[ k ][ c ] ^= mat[ row ][ c ] & mask;
                    }
                }
            }
        }
    }

    tail = PK_NROWS % 8;

    for (i = 0; i < PK_NROWS; i++) {
        for (j = (PK_NROWS - 1) / 8; j < SYS_N / 8 - 1; j++) {
            *pk_ptr++ = (mat[i][j] >> tail) | (mat[i][j + 1] << (8 - tail));
        }

        *pk_ptr++ = (mat[i][j] >> tail);
    }

    return 0;
}