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

#include "tommath_private.h"
#ifdef BN_MP_DR_REDUCE_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
 */

/* reduce "x" in place modulo "n" using the Diminished Radix algorithm.
 *
 * Based on algorithm from the paper
 *
 * "Generating Efficient Primes for Discrete Log Cryptosystems"
 *                 Chae Hoon Lim, Pil Joong Lee,
 *          POSTECH Information Research Laboratories
 *
 * The modulus must be of a special format [see manual]
 *
 * Has been modified to use algorithm 7.10 from the LTM book instead
 *
 * Input x must be in the range 0 <= x <= (n-1)**2
 */
int mp_dr_reduce(mp_int *x, const mp_int *n, mp_digit k)
{
   int      err, i, m;
   mp_word  r;
   mp_digit mu, *tmpx1, *tmpx2;

   /* m = digits in modulus */
   m = n->used;

   /* ensure that "x" has at least 2m digits */
   if (x->alloc < (m + m)) {
      if ((err = mp_grow(x, m + m)) != MP_OKAY) {
         return err;
      }
   }

   /* top of loop, this is where the code resumes if
    * another reduction pass is required.
    */
top:
   /* aliases for digits */
   /* alias for lower half of x */
   tmpx1 = x->dp;

   /* alias for upper half of x, or x/B**m */
   tmpx2 = x->dp + m;

   /* set carry to zero */
   mu = 0;

   /* compute (x mod B**m) + k * [x/B**m] inline and inplace */
   for (i = 0; i < m; i++) {
      r         = ((mp_word)*tmpx2++ * (mp_word)k) + *tmpx1 + mu;
      *tmpx1++  = (mp_digit)(r & MP_MASK);
      mu        = (mp_digit)(r >> ((mp_word)DIGIT_BIT));
   }

   /* set final carry */
   *tmpx1++ = mu;

   /* zero words above m */
   for (i = m + 1; i < x->used; i++) {
      *tmpx1++ = 0;
   }

   /* clamp, sub and return */
   mp_clamp(x);

   /* if x >= n then subtract and reduce again
    * Each successive "recursion" makes the input smaller and smaller.
    */
   if (mp_cmp_mag(x, n) != MP_LT) {
      if ((err = s_mp_sub(x, n, x)) != MP_OKAY) {
         return err;
      }
      goto top;
   }
   return MP_OKAY;
}
#endif

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