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_KRONECKER_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
 */

/*
   Kronecker symbol (a|p)
   Straightforward implementation of algorithm 1.4.10 in
   Henri Cohen: "A Course in Computational Algebraic Number Theory"

   @book{cohen2013course,
     title={A course in computational algebraic number theory},
     author={Cohen, Henri},
     volume={138},
     year={2013},
     publisher={Springer Science \& Business Media}
    }
 */
int mp_kronecker(const mp_int *a, const mp_int *p, int *c)
{
   mp_int a1, p1, r;

   int e = MP_OKAY;
   int v, k;

   static const int table[8] = {0, 1, 0, -1, 0, -1, 0, 1};

   if (mp_iszero(p) != MP_NO) {
      if ((a->used == 1) && (a->dp[0] == 1u)) {
         *c = 1;
         return e;
      } else {
         *c = 0;
         return e;
      }
   }

   if ((mp_iseven(a) != MP_NO) && (mp_iseven(p) != MP_NO)) {
      *c = 0;
      return e;
   }

   if ((e = mp_init_copy(&a1, a)) != MP_OKAY) {
      return e;
   }
   if ((e = mp_init_copy(&p1, p)) != MP_OKAY) {
      goto LBL_KRON_0;
   }

   v = mp_cnt_lsb(&p1);
   if ((e = mp_div_2d(&p1, v, &p1, NULL)) != MP_OKAY) {
      goto LBL_KRON_1;
   }

   if ((v & 0x1) == 0) {
      k = 1;
   } else {
      k = table[a->dp[0] & 7u];
   }

   if (p1.sign == MP_NEG) {
      p1.sign = MP_ZPOS;
      if (a1.sign == MP_NEG) {
         k = -k;
      }
   }

   if ((e = mp_init(&r)) != MP_OKAY) {
      goto LBL_KRON_1;
   }

   for (;;) {
      if (mp_iszero(&a1) != MP_NO) {
         if (mp_cmp_d(&p1, 1uL) == MP_EQ) {
            *c = k;
            goto LBL_KRON;
         } else {
            *c = 0;
            goto LBL_KRON;
         }
      }

      v = mp_cnt_lsb(&a1);
      if ((e = mp_div_2d(&a1, v, &a1, NULL)) != MP_OKAY) {
         goto LBL_KRON;
      }

      if ((v & 0x1) == 1) {
         k = k * table[p1.dp[0] & 7u];
      }

      if (a1.sign == MP_NEG) {
         /*
          * Compute k = (-1)^((a1)*(p1-1)/4) * k
          * a1.dp[0] + 1 cannot overflow because the MSB
          * of the type mp_digit is not set by definition
          */
         if (((a1.dp[0] + 1u) & p1.dp[0] & 2u) != 0u) {
            k = -k;
         }
      } else {
         /* compute k = (-1)^((a1-1)*(p1-1)/4) * k */
         if ((a1.dp[0] & p1.dp[0] & 2u) != 0u) {
            k = -k;
         }
      }

      if ((e = mp_copy(&a1, &r)) != MP_OKAY) {
         goto LBL_KRON;
      }
      r.sign = MP_ZPOS;
      if ((e = mp_mod(&p1, &r, &a1)) != MP_OKAY) {
         goto LBL_KRON;
      }
      if ((e = mp_copy(&r, &p1)) != MP_OKAY) {
         goto LBL_KRON;
      }
   }

LBL_KRON:
   mp_clear(&r);
LBL_KRON_1:
   mp_clear(&p1);
LBL_KRON_0:
   mp_clear(&a1);

   return e;
}

#endif

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