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_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
 */

/* reduces x mod m, assumes 0 < x < m**2, mu is
 * precomputed via mp_reduce_setup.
 * From HAC pp.604 Algorithm 14.42
 */
int mp_reduce(mp_int *x, const mp_int *m, const mp_int *mu)
{
   mp_int  q;
   int     res, um = m->used;

   /* q = x */
   if ((res = mp_init_copy(&q, x)) != MP_OKAY) {
      return res;
   }

   /* q1 = x / b**(k-1)  */
   mp_rshd(&q, um - 1);

   /* according to HAC this optimization is ok */
   if ((mp_digit)um > ((mp_digit)1 << (DIGIT_BIT - 1))) {
      if ((res = mp_mul(&q, mu, &q)) != MP_OKAY) {
         goto CLEANUP;
      }
   } else {
#ifdef BN_S_MP_MUL_HIGH_DIGS_C
      if ((res = s_mp_mul_high_digs(&q, mu, &q, um)) != MP_OKAY) {
         goto CLEANUP;
      }
#elif defined(BN_FAST_S_MP_MUL_HIGH_DIGS_C)
      if ((res = fast_s_mp_mul_high_digs(&q, mu, &q, um)) != MP_OKAY) {
         goto CLEANUP;
      }
#else
      {
         res = MP_VAL;
         goto CLEANUP;
      }
#endif
   }

   /* q3 = q2 / b**(k+1) */
   mp_rshd(&q, um + 1);

   /* x = x mod b**(k+1), quick (no division) */
   if ((res = mp_mod_2d(x, DIGIT_BIT * (um + 1), x)) != MP_OKAY) {
      goto CLEANUP;
   }

   /* q = q * m mod b**(k+1), quick (no division) */
   if ((res = s_mp_mul_digs(&q, m, &q, um + 1)) != MP_OKAY) {
      goto CLEANUP;
   }

   /* x = x - q */
   if ((res = mp_sub(x, &q, x)) != MP_OKAY) {
      goto CLEANUP;
   }

   /* If x < 0, add b**(k+1) to it */
   if (mp_cmp_d(x, 0uL) == MP_LT) {
      mp_set(&q, 1uL);
      if ((res = mp_lshd(&q, um + 1)) != MP_OKAY)
         goto CLEANUP;
      if ((res = mp_add(x, &q, x)) != MP_OKAY)
         goto CLEANUP;
   }

   /* Back off if it's too big */
   while (mp_cmp(x, m) != MP_LT) {
      if ((res = s_mp_sub(x, m, x)) != MP_OKAY) {
         goto CLEANUP;
      }
   }

CLEANUP:
   mp_clear(&q);

   return res;
}
#endif

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