_ Git - BearSSL/blob - src/int/i32_montmul.c

   1 /*
   2  * Copyright (c) 2016 Thomas Pornin <pornin@bolet.org>
   3  *
   4  * Permission is hereby granted, free of charge, to any person obtaining
   5  * a copy of this software and associated documentation files (the
   6  * "Software"), to deal in the Software without restriction, including
   7  * without limitation the rights to use, copy, modify, merge, publish,
   8  * distribute, sublicense, and/or sell copies of the Software, and to
   9  * permit persons to whom the Software is furnished to do so, subject to
  10  * the following conditions:
  11  *
  12  * The above copyright notice and this permission notice shall be
  13  * included in all copies or substantial portions of the Software.
  14  *
  15  * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
  16  * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
  17  * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
  18  * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
  19  * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
  20  * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
  21  * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
  22  * SOFTWARE.
  23  */
  24
  25 #include "inner.h"
  26
  27 /* see inner.h */
  28 void
  29 br_i32_montymul(uint32_t *d, const uint32_t *x, const uint32_t *y,
  30         const uint32_t *m, uint32_t m0i)
  31 {
  32         size_t len, u, v;
  33         uint64_t dh;
  34
  35         len = (m[0] + 31) >> 5;
  36         br_i32_zero(d, m[0]);
  37         dh = 0;
  38         for (u = 0; u < len; u ++) {
  39                 uint32_t f, xu;
  40                 uint64_t r1, r2, zh;
  41
  42                 xu = x[u + 1];
  43                 f = (d[1] + x[u + 1] * y[1]) * m0i;
  44                 r1 = 0;
  45                 r2 = 0;
  46                 for (v = 0; v < len; v ++) {
  47                         uint64_t z;
  48                         uint32_t t;
  49
  50                         z = (uint64_t)d[v + 1] + MUL(xu, y[v + 1]) + r1;
  51                         r1 = z >> 32;
  52                         t = (uint32_t)z;
  53                         z = (uint64_t)t + MUL(f, m[v + 1]) + r2;
  54                         r2 = z >> 32;
  55                         if (v != 0) {
  56                                 d[v] = (uint32_t)z;
  57                         }
  58                 }
  59                 zh = dh + r1 + r2;
  60                 d[len] = (uint32_t)zh;
  61                 dh = zh >> 32;
  62         }
  63
  64         /*
  65          * d[] may still be greater than m[] at that point; notably, the
  66          * 'dh' word may be non-zero.
  67          */
  68         br_i32_sub(d, m, NEQ(dh, 0) | NOT(br_i32_sub(d, m, 0)));
  69 }