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

/* LibTomCrypt, modular cryptographic library -- Tom St Denis
 *
 * LibTomCrypt is a library that provides various cryptographic
 * algorithms in a highly modular and flexible manner.
 *
 * The library is free for all purposes without any express
 * guarantee it works.
 */
#include "tomcrypt.h"

/**
   @file lrw_process.c
   LRW_MODE implementation, Encrypt/decrypt blocks, Tom St Denis
*/

#ifdef LTC_LRW_MODE

/**
  Process blocks with LRW, since decrypt/encrypt are largely the same they share this code.
  @param pt        The "input" data
  @param ct        [out] The "output" data
  @param len       The length of the input, must be a multiple of 128-bits (16 octets)
  @param mode      LRW_ENCRYPT or LRW_DECRYPT
  @param lrw       The LRW state
  @return  CRYPT_OK if successful
*/
int lrw_process(const unsigned char *pt, unsigned char *ct, unsigned long len, int mode, symmetric_LRW *lrw)
{
   unsigned char prod[16];
   int           x, err;
#ifdef LTC_LRW_TABLES
   int           y;
#endif

   LTC_ARGCHK(pt  != NULL);
   LTC_ARGCHK(ct  != NULL);
   LTC_ARGCHK(lrw != NULL);

   if (len & 15) {
      return CRYPT_INVALID_ARG;
   }

   while (len) {
      /* copy pad */
      XMEMCPY(prod, lrw->pad, 16);

      /* increment IV */
      for (x = 15; x >= 0; x--) {
          lrw->IV[x] = (lrw->IV[x] + 1) & 255;
          if (lrw->IV[x]) {
              break;
          }
      }

      /* update pad */
#ifdef LTC_LRW_TABLES
      /* for each byte changed we undo it's affect on the pad then add the new product */
      for (; x < 16; x++) {
#ifdef LTC_FAST
          for (y = 0; y < 16; y += sizeof(LTC_FAST_TYPE)) {
              *(LTC_FAST_TYPE_PTR_CAST(lrw->pad + y)) ^= *(LTC_FAST_TYPE_PTR_CAST(&lrw->PC[x][lrw->IV[x]][y])) ^ *(LTC_FAST_TYPE_PTR_CAST(&lrw->PC[x][(lrw->IV[x]-1)&255][y]));
          }
#else
          for (y = 0; y < 16; y++) {
              lrw->pad[y] ^= lrw->PC[x][lrw->IV[x]][y] ^ lrw->PC[x][(lrw->IV[x]-1)&255][y];
          }
#endif
      }
#else
      gcm_gf_mult(lrw->tweak, lrw->IV, lrw->pad);
#endif

      /* xor prod */
#ifdef LTC_FAST
      for (x = 0; x < 16; x += sizeof(LTC_FAST_TYPE)) {
           *(LTC_FAST_TYPE_PTR_CAST(ct + x)) = *(LTC_FAST_TYPE_PTR_CAST(pt + x)) ^ *(LTC_FAST_TYPE_PTR_CAST(prod + x));
      }
#else
      for (x = 0; x < 16; x++) {
         ct[x] = pt[x] ^ prod[x];
      }
#endif

      /* send through cipher */
      if (mode == LRW_ENCRYPT) {
         if ((err = cipher_descriptor[lrw->cipher].ecb_encrypt(ct, ct, &lrw->key)) != CRYPT_OK) {
            return err;
         }
      } else {
         if ((err = cipher_descriptor[lrw->cipher].ecb_decrypt(ct, ct, &lrw->key)) != CRYPT_OK) {
            return err;
         }
      }

      /* xor prod */
#ifdef LTC_FAST
      for (x = 0; x < 16; x += sizeof(LTC_FAST_TYPE)) {
           *(LTC_FAST_TYPE_PTR_CAST(ct + x)) = *(LTC_FAST_TYPE_PTR_CAST(ct + x)) ^ *(LTC_FAST_TYPE_PTR_CAST(prod + x));
      }
#else
      for (x = 0; x < 16; x++) {
         ct[x] = ct[x] ^ prod[x];
      }
#endif

      /* move to next */
      pt  += 16;
      ct  += 16;
      len -= 16;
   }

   return CRYPT_OK;
}

#endif
/* ref:         $Format:%D$ */
/* git commit:  $Format:%H$ */
/* commit time: $Format:%ai$ */