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_GCD_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
 */

/* Greatest Common Divisor using the binary method */
int mp_gcd(const mp_int *a, const mp_int *b, mp_int *c)
{
   mp_int  u, v;
   int     k, u_lsb, v_lsb, res;

   /* either zero than gcd is the largest */
   if (mp_iszero(a) == MP_YES) {
      return mp_abs(b, c);
   }
   if (mp_iszero(b) == MP_YES) {
      return mp_abs(a, c);
   }

   /* get copies of a and b we can modify */
   if ((res = mp_init_copy(&u, a)) != MP_OKAY) {
      return res;
   }

   if ((res = mp_init_copy(&v, b)) != MP_OKAY) {
      goto LBL_U;
   }

   /* must be positive for the remainder of the algorithm */
   u.sign = v.sign = MP_ZPOS;

   /* B1.  Find the common power of two for u and v */
   u_lsb = mp_cnt_lsb(&u);
   v_lsb = mp_cnt_lsb(&v);
   k     = MIN(u_lsb, v_lsb);

   if (k > 0) {
      /* divide the power of two out */
      if ((res = mp_div_2d(&u, k, &u, NULL)) != MP_OKAY) {
         goto LBL_V;
      }

      if ((res = mp_div_2d(&v, k, &v, NULL)) != MP_OKAY) {
         goto LBL_V;
      }
   }

   /* divide any remaining factors of two out */
   if (u_lsb != k) {
      if ((res = mp_div_2d(&u, u_lsb - k, &u, NULL)) != MP_OKAY) {
         goto LBL_V;
      }
   }

   if (v_lsb != k) {
      if ((res = mp_div_2d(&v, v_lsb - k, &v, NULL)) != MP_OKAY) {
         goto LBL_V;
      }
   }

   while (mp_iszero(&v) == MP_NO) {
      /* make sure v is the largest */
      if (mp_cmp_mag(&u, &v) == MP_GT) {
         /* swap u and v to make sure v is >= u */
         mp_exch(&u, &v);
      }

      /* subtract smallest from largest */
      if ((res = s_mp_sub(&v, &u, &v)) != MP_OKAY) {
         goto LBL_V;
      }

      /* Divide out all factors of two */
      if ((res = mp_div_2d(&v, mp_cnt_lsb(&v), &v, NULL)) != MP_OKAY) {
         goto LBL_V;
      }
   }

   /* multiply by 2**k which we divided out at the beginning */
   if ((res = mp_mul_2d(&u, k, c)) != MP_OKAY) {
      goto LBL_V;
   }
   c->sign = MP_ZPOS;
   res = MP_OKAY;
LBL_V:
   mp_clear(&u);
LBL_U:
   mp_clear(&v);
   return res;
}
#endif

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