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_EXTEUCLID_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
 */

/* Extended euclidean algorithm of (a, b) produces
   a*u1 + b*u2 = u3
 */
int mp_exteuclid(const mp_int *a, const mp_int *b, mp_int *U1, mp_int *U2, mp_int *U3)
{
   mp_int u1, u2, u3, v1, v2, v3, t1, t2, t3, q, tmp;
   int err;

   if ((err = mp_init_multi(&u1, &u2, &u3, &v1, &v2, &v3, &t1, &t2, &t3, &q, &tmp, NULL)) != MP_OKAY) {
      return err;
   }

   /* initialize, (u1,u2,u3) = (1,0,a) */
   mp_set(&u1, 1uL);
   if ((err = mp_copy(a, &u3)) != MP_OKAY) {
      goto LBL_ERR;
   }

   /* initialize, (v1,v2,v3) = (0,1,b) */
   mp_set(&v2, 1uL);
   if ((err = mp_copy(b, &v3)) != MP_OKAY) {
      goto LBL_ERR;
   }

   /* loop while v3 != 0 */
   while (mp_iszero(&v3) == MP_NO) {
      /* q = u3/v3 */
      if ((err = mp_div(&u3, &v3, &q, NULL)) != MP_OKAY) {
         goto LBL_ERR;
      }

      /* (t1,t2,t3) = (u1,u2,u3) - (v1,v2,v3)q */
      if ((err = mp_mul(&v1, &q, &tmp)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_sub(&u1, &tmp, &t1)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_mul(&v2, &q, &tmp)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_sub(&u2, &tmp, &t2)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_mul(&v3, &q, &tmp)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_sub(&u3, &tmp, &t3)) != MP_OKAY) {
         goto LBL_ERR;
      }

      /* (u1,u2,u3) = (v1,v2,v3) */
      if ((err = mp_copy(&v1, &u1)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_copy(&v2, &u2)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_copy(&v3, &u3)) != MP_OKAY) {
         goto LBL_ERR;
      }

      /* (v1,v2,v3) = (t1,t2,t3) */
      if ((err = mp_copy(&t1, &v1)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_copy(&t2, &v2)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_copy(&t3, &v3)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   /* make sure U3 >= 0 */
   if (u3.sign == MP_NEG) {
      if ((err = mp_neg(&u1, &u1)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_neg(&u2, &u2)) != MP_OKAY) {
         goto LBL_ERR;
      }
      if ((err = mp_neg(&u3, &u3)) != MP_OKAY) {
         goto LBL_ERR;
      }
   }

   /* copy result out */
   if (U1 != NULL) {
      mp_exch(U1, &u1);
   }
   if (U2 != NULL) {
      mp_exch(U2, &u2);
   }
   if (U3 != NULL) {
      mp_exch(U3, &u3);
   }

   err = MP_OKAY;
LBL_ERR:
   mp_clear_multi(&u1, &u2, &u3, &v1, &v2, &v3, &t1, &t2, &t3, &q, &tmp, NULL);
   return err;
}
#endif

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