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

/* 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
 */
#ifndef TOMMATH_PRIV_H_
#define TOMMATH_PRIV_H_

#include "tommath.h"
#include <ctype.h>

#ifndef MIN
#define MIN(x, y) (((x) < (y)) ? (x) : (y))
#endif

#ifndef MAX
#define MAX(x, y) (((x) > (y)) ? (x) : (y))
#endif

#ifdef __cplusplus
extern "C" {

/* C++ compilers don't like assigning void * to mp_digit * */
#define OPT_CAST(x) (x *)

#else

/* C on the other hand doesn't care */
#define OPT_CAST(x)

#endif

/* define heap macros */
#ifndef XMALLOC
/* default to libc stuff */
#   define XMALLOC   malloc
#   define XFREE     free
#   define XREALLOC  realloc
#   define XCALLOC   calloc
#else
/* prototypes for our heap functions */
extern void *XMALLOC(size_t n);
extern void *XREALLOC(void *p, size_t n);
extern void *XCALLOC(size_t n, size_t s);
extern void XFREE(void *p);
#endif

/* lowlevel functions, do not call! */
int s_mp_add(const mp_int *a, const mp_int *b, mp_int *c);
int s_mp_sub(const mp_int *a, const mp_int *b, mp_int *c);
#define s_mp_mul(a, b, c) s_mp_mul_digs(a, b, c, (a)->used + (b)->used + 1)
int fast_s_mp_mul_digs(const mp_int *a, const mp_int *b, mp_int *c, int digs);
int s_mp_mul_digs(const mp_int *a, const mp_int *b, mp_int *c, int digs);
int fast_s_mp_mul_high_digs(const mp_int *a, const mp_int *b, mp_int *c, int digs);
int s_mp_mul_high_digs(const mp_int *a, const mp_int *b, mp_int *c, int digs);
int fast_s_mp_sqr(const mp_int *a, mp_int *b);
int s_mp_sqr(const mp_int *a, mp_int *b);
int mp_karatsuba_mul(const mp_int *a, const mp_int *b, mp_int *c);
int mp_toom_mul(const mp_int *a, const mp_int *b, mp_int *c);
int mp_karatsuba_sqr(const mp_int *a, mp_int *b);
int mp_toom_sqr(const mp_int *a, mp_int *b);
int fast_mp_invmod(const mp_int *a, const mp_int *b, mp_int *c);
int mp_invmod_slow(const mp_int *a, const mp_int *b, mp_int *c);
int fast_mp_montgomery_reduce(mp_int *x, const mp_int *n, mp_digit rho);
int mp_exptmod_fast(const mp_int *G, const mp_int *X, const mp_int *P, mp_int *Y, int redmode);
int s_mp_exptmod(const mp_int *G, const mp_int *X, const mp_int *P, mp_int *Y, int redmode);
void bn_reverse(unsigned char *s, int len);

extern const char *const mp_s_rmap;
extern const uint8_t mp_s_rmap_reverse[];
extern const size_t mp_s_rmap_reverse_sz;

/* Fancy macro to set an MPI from another type.
 * There are several things assumed:
 *  x is the counter and unsigned
 *  a is the pointer to the MPI
 *  b is the original value that should be set in the MPI.
 */
#define MP_SET_XLONG(func_name, type)                    \
int func_name (mp_int * a, type b)                       \
{                                                        \
  unsigned int  x;                                       \
  int           res;                                     \
                                                         \
  mp_zero (a);                                           \
                                                         \
  /* set four bits at a time */                          \
  for (x = 0; x < (sizeof(type) * 2u); x++) {            \
    /* shift the number up four bits */                  \
    if ((res = mp_mul_2d (a, 4, a)) != MP_OKAY) {        \
      return res;                                        \
    }                                                    \
                                                         \
    /* OR in the top four bits of the source */          \
    a->dp[0] |= (mp_digit)(b >> ((sizeof(type) * 8u) - 4u)) & 15uL;\
                                                         \
    /* shift the source up to the next four bits */      \
    b <<= 4;                                             \
                                                         \
    /* ensure that digits are not clamped off */         \
    a->used += 1;                                        \
  }                                                      \
  mp_clamp (a);                                          \
  return MP_OKAY;                                        \
}

#ifdef __cplusplus
}
#endif

#endif


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