view libtommath/bn_fast_mp_invmod.c @ 1672:3a97f14c0235

Add Chacha20-Poly1305, AES128-GCM and AES256-GCM support (#93) * Add Chacha20-Poly1305 authenticated encryption * Add general AEAD approach. * Add [email protected] algo using LibTomCrypt chacha and poly1305 routines. Chacha20-Poly1305 is generally faster than AES256 on CPU w/o dedicated AES instructions, having the same key size. Compiling in will add ~5,5kB to binary size on x86-64. function old new delta chacha_crypt - 1397 +1397 _poly1305_block - 608 +608 poly1305_done - 595 +595 dropbear_chachapoly_crypt - 457 +457 .rodata 26976 27392 +416 poly1305_process - 290 +290 poly1305_init - 221 +221 chacha_setup - 218 +218 encrypt_packet 1068 1270 +202 dropbear_chachapoly_getlength - 147 +147 decrypt_packet 756 897 +141 chacha_ivctr64 - 137 +137 read_packet 543 637 +94 dropbear_chachapoly_start - 94 +94 read_kex_algos 792 880 +88 chacha_keystream - 69 +69 dropbear_mode_chachapoly - 48 +48 sshciphers 280 320 +40 dropbear_mode_none 24 48 +24 dropbear_mode_ctr 24 48 +24 dropbear_mode_cbc 24 48 +24 dropbear_chachapoly_mac - 24 +24 dropbear_chachapoly - 24 +24 gen_new_keys 848 854 +6 ------------------------------------------------------------------------------ (add/remove: 14/0 grow/shrink: 10/0 up/down: 5388/0) Total: 5388 bytes * Add AES128-GCM and AES256-GCM authenticated encryption * Add general AES-GCM mode. * Add [email protected] and [email protected] algo using LibTomCrypt gcm routines. AES-GCM is combination of AES CTR mode and GHASH, slower than AES-CTR on CPU w/o dedicated AES/GHASH instructions therefore disabled by default. Compiling in will add ~6kB to binary size on x86-64. function old new delta gcm_process - 1060 +1060 .rodata 26976 27808 +832 gcm_gf_mult - 820 +820 gcm_add_aad - 660 +660 gcm_shift_table - 512 +512 gcm_done - 471 +471 gcm_add_iv - 384 +384 gcm_init - 347 +347 dropbear_gcm_crypt - 309 +309 encrypt_packet 1068 1270 +202 decrypt_packet 756 897 +141 gcm_reset - 118 +118 read_packet 543 637 +94 read_kex_algos 792 880 +88 sshciphers 280 360 +80 gcm_mult_h - 80 +80 dropbear_gcm_start - 62 +62 dropbear_mode_gcm - 48 +48 dropbear_mode_none 24 48 +24 dropbear_mode_ctr 24 48 +24 dropbear_mode_cbc 24 48 +24 dropbear_ghash - 24 +24 dropbear_gcm_getlength - 24 +24 gen_new_keys 848 854 +6 ------------------------------------------------------------------------------ (add/remove: 14/0 grow/shrink: 10/0 up/down: 6434/0) Total: 6434 bytes
author Vladislav Grishenko <themiron@users.noreply.github.com>
date Mon, 25 May 2020 20:50:25 +0500
parents f52919ffd3b1
children
line wrap: on
line source

#include "tommath_private.h"
#ifdef BN_FAST_MP_INVMOD_C
/* LibTomMath, multiple-precision integer library -- Tom St Denis
 *
 * LibTomMath is a library that provides multiple-precision
 * integer arithmetic as well as number theoretic functionality.
 *
 * The library was designed directly after the MPI library by
 * Michael Fromberger but has been written from scratch with
 * additional optimizations in place.
 *
 * SPDX-License-Identifier: Unlicense
 */

/* computes the modular inverse via binary extended euclidean algorithm,
 * that is c = 1/a mod b
 *
 * Based on slow invmod except this is optimized for the case where b is
 * odd as per HAC Note 14.64 on pp. 610
 */
int fast_mp_invmod(const mp_int *a, const mp_int *b, mp_int *c)
{
   mp_int  x, y, u, v, B, D;
   int     res, neg;

   /* 2. [modified] b must be odd   */
   if (mp_iseven(b) == MP_YES) {
      return MP_VAL;
   }

   /* init all our temps */
   if ((res = mp_init_multi(&x, &y, &u, &v, &B, &D, NULL)) != MP_OKAY) {
      return res;
   }

   /* x == modulus, y == value to invert */
   if ((res = mp_copy(b, &x)) != MP_OKAY) {
      goto LBL_ERR;
   }

   /* we need y = |a| */
   if ((res = mp_mod(a, b, &y)) != MP_OKAY) {
      goto LBL_ERR;
   }

   /* if one of x,y is zero return an error! */
   if ((mp_iszero(&x) == MP_YES) || (mp_iszero(&y) == MP_YES)) {
      res = MP_VAL;
      goto LBL_ERR;
   }

   /* 3. u=x, v=y, A=1, B=0, C=0,D=1 */
   if ((res = mp_copy(&x, &u)) != MP_OKAY) {
      goto LBL_ERR;
   }
   if ((res = mp_copy(&y, &v)) != MP_OKAY) {
      goto LBL_ERR;
   }
   mp_set(&D, 1uL);

top:
   /* 4.  while u is even do */
   while (mp_iseven(&u) == MP_YES) {
      /* 4.1 u = u/2 */
      if ((res = mp_div_2(&u, &u)) != MP_OKAY) {
         goto LBL_ERR;
      }
      /* 4.2 if B is odd then */
      if (mp_isodd(&B) == MP_YES) {
         if ((res = mp_sub(&B, &x, &B)) != MP_OKAY) {
            goto LBL_ERR;
         }
      }
      /* B = B/2 */
      if ((res = mp_div_2(&B, &B)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   /* 5.  while v is even do */
   while (mp_iseven(&v) == MP_YES) {
      /* 5.1 v = v/2 */
      if ((res = mp_div_2(&v, &v)) != MP_OKAY) {
         goto LBL_ERR;
      }
      /* 5.2 if D is odd then */
      if (mp_isodd(&D) == MP_YES) {
         /* D = (D-x)/2 */
         if ((res = mp_sub(&D, &x, &D)) != MP_OKAY) {
            goto LBL_ERR;
         }
      }
      /* D = D/2 */
      if ((res = mp_div_2(&D, &D)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   /* 6.  if u >= v then */
   if (mp_cmp(&u, &v) != MP_LT) {
      /* u = u - v, B = B - D */
      if ((res = mp_sub(&u, &v, &u)) != MP_OKAY) {
         goto LBL_ERR;
      }

      if ((res = mp_sub(&B, &D, &B)) != MP_OKAY) {
         goto LBL_ERR;
      }
   } else {
      /* v - v - u, D = D - B */
      if ((res = mp_sub(&v, &u, &v)) != MP_OKAY) {
         goto LBL_ERR;
      }

      if ((res = mp_sub(&D, &B, &D)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   /* if not zero goto step 4 */
   if (mp_iszero(&u) == MP_NO) {
      goto top;
   }

   /* now a = C, b = D, gcd == g*v */

   /* if v != 1 then there is no inverse */
   if (mp_cmp_d(&v, 1uL) != MP_EQ) {
      res = MP_VAL;
      goto LBL_ERR;
   }

   /* b is now the inverse */
   neg = a->sign;
   while (D.sign == MP_NEG) {
      if ((res = mp_add(&D, b, &D)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   /* too big */
   while (mp_cmp_mag(&D, b) != MP_LT) {
      if ((res = mp_sub(&D, b, &D)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   mp_exch(&D, c);
   c->sign = neg;
   res = MP_OKAY;

LBL_ERR:
   mp_clear_multi(&x, &y, &u, &v, &B, &D, NULL);
   return res;
}
#endif

/* ref:         HEAD -> master, tag: v1.1.0 */
/* git commit:  08549ad6bc8b0cede0b357a9c341c5c6473a9c55 */
/* commit time: 2019-01-28 20:32:32 +0100 */