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_S_MP_SQR_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
 */

/* low level squaring, b = a*a, HAC pp.596-597, Algorithm 14.16 */
int s_mp_sqr(const mp_int *a, mp_int *b)
{
   mp_int  t;
   int     res, ix, iy, pa;
   mp_word r;
   mp_digit u, tmpx, *tmpt;

   pa = a->used;
   if ((res = mp_init_size(&t, (2 * pa) + 1)) != MP_OKAY) {
      return res;
   }

   /* default used is maximum possible size */
   t.used = (2 * pa) + 1;

   for (ix = 0; ix < pa; ix++) {
      /* first calculate the digit at 2*ix */
      /* calculate double precision result */
      r = (mp_word)t.dp[2*ix] +
          ((mp_word)a->dp[ix] * (mp_word)a->dp[ix]);

      /* store lower part in result */
      t.dp[ix+ix] = (mp_digit)(r & (mp_word)MP_MASK);

      /* get the carry */
      u           = (mp_digit)(r >> (mp_word)DIGIT_BIT);

      /* left hand side of A[ix] * A[iy] */
      tmpx        = a->dp[ix];

      /* alias for where to store the results */
      tmpt        = t.dp + ((2 * ix) + 1);

      for (iy = ix + 1; iy < pa; iy++) {
         /* first calculate the product */
         r       = (mp_word)tmpx * (mp_word)a->dp[iy];

         /* now calculate the double precision result, note we use
          * addition instead of *2 since it's easier to optimize
          */
         r       = (mp_word)*tmpt + r + r + (mp_word)u;

         /* store lower part */
         *tmpt++ = (mp_digit)(r & (mp_word)MP_MASK);

         /* get carry */
         u       = (mp_digit)(r >> (mp_word)DIGIT_BIT);
      }
      /* propagate upwards */
      while (u != 0uL) {
         r       = (mp_word)*tmpt + (mp_word)u;
         *tmpt++ = (mp_digit)(r & (mp_word)MP_MASK);
         u       = (mp_digit)(r >> (mp_word)DIGIT_BIT);
      }
   }

   mp_clamp(&t);
   mp_exch(&t, b);
   mp_clear(&t);
   return MP_OKAY;
}
#endif

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