MD4: replace implementation

/*-

/*

   Copyright (C) 1990-2, RSA Data Security, Inc. All rights reserved.

 * This is an OpenSSL-compatible implementation of the RSA Data Security, Inc.

 * MD4 Message-Digest Algorithm (RFC 1320).

   License to copy and use this software is granted provided that it

 *

   is identified as the "RSA Data Security, Inc. MD4 Message-Digest

 * Homepage:

   Algorithm" in all material mentioning or referencing this software

 * http://openwall.info/wiki/people/solar/software/public-domain-source-code/md4

   or this function.

 *

 * Author:

   License is also granted to make and use derivative works provided

 * Alexander Peslyak, better known as Solar Designer <solar at openwall.com>

   that such works are identified as "derived from the RSA Data

 *

   Security, Inc. MD4 Message-Digest Algorithm" in all material

 * This software was written by Alexander Peslyak in 2001.  No copyright is

   mentioning or referencing the derived work.

 * claimed, and the software is hereby placed in the public domain.

 * In case this attempt to disclaim copyright and place the software in the

   RSA Data Security, Inc. makes no representations concerning either

 * public domain is deemed null and void, then the software is

   the merchantability of this software or the suitability of this

 * Copyright (c) 2001 Alexander Peslyak and it is hereby released to the

   software for any particular purpose. It is provided "as is"

 * general public under the following terms:

   without express or implied warranty of any kind.

 *

 * Redistribution and use in source and binary forms, with or without

   These notices must be retained in any copies of any part of this

 * modification, are permitted.

   documentation and/or software.

 *

 * There's ABSOLUTELY NO WARRANTY, express or implied.

 *

 * (This is a heavily cut-down "BSD license".)

 *

 * This differs from Colin Plumb's older public domain implementation in that

 * no exactly 32-bit integer data type is required (any 32-bit or wider

 * unsigned integer data type will do), there's no compile-time endianness

 * configuration, and the function prototypes match OpenSSL's.  No code from

 * Colin Plumb's implementation has been reused; this comment merely compares

 * the properties of the two independent implementations.

 *

 * The primary goals of this implementation are portability and ease of use.

 * It is meant to be fast, but not as fast as possible.  Some known

 * optimizations are not included to reduce source code size and avoid

 * compile-time configuration.

 */

 */

#include "curl_setup.h"

#include "curl_setup.h"

#include "curl_md4.h"

#include "curl_md4.h"

#include "warnless.h"

#include "warnless.h"

typedef unsigned int UINT4;

#ifndef HAVE_OPENSSL

typedef struct MD4Context {

#include <string.h>

  UINT4 state[4];               /* state (ABCD) */

  UINT4 count[2];               /* number of bits, modulo 2^64 (lsb first) */

  unsigned char buffer[64];     /* input buffer */

} MD4_CTX;

/* Constants for MD4Transform routine.

/* Any 32-bit or wider unsigned integer data type will do */

 */

typedef unsigned int MD4_u32plus;

#define S11 3

#define S12 7

#define S13 11

#define S14 19

#define S21 3

#define S22 5

#define S23 9

#define S24 13

#define S31 3

#define S32 9

#define S33 11

#define S34 15

static void MD4Transform(UINT4 [4], const unsigned char [64]);

static void Encode(unsigned char *, UINT4 *, unsigned int);

static void Decode(UINT4 *, const unsigned char *, unsigned int);

static unsigned char PADDING[64] = {

  0x80, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,

  0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0

};

/* F, G and H are basic MD4 functions.

 */

#define F(x, y, z) (((x) & (y)) | ((~x) & (z)))

#define G(x, y, z) (((x) & (y)) | ((x) & (z)) | ((y) & (z)))

#define H(x, y, z) ((x) ^ (y) ^ (z))

/* ROTATE_LEFT rotates x left n bits.

typedef struct {

 */

  MD4_u32plus lo, hi;

#define ROTATE_LEFT(x, n) (((x) << (n)) | ((x) >> (32-(n))))

  MD4_u32plus a, b, c, d;

  unsigned char buffer[64];

  MD4_u32plus block[16];

} MD4_CTX;

/* FF, GG and HH are transformations for rounds 1, 2 and 3 */

extern void MD4_Init(MD4_CTX *ctx);

/* Rotation is separate from addition to prevent recomputation */

extern void MD4_Update(MD4_CTX *ctx, const void *data, unsigned long size);

#define FF(a, b, c, d, x, s) { \

extern void MD4_Final(unsigned char *result, MD4_CTX *ctx);

    (a) += F ((b), (c), (d)) + (x); \

    (a) = ROTATE_LEFT ((a), (s)); \

  }

#define GG(a, b, c, d, x, s) { \

    (a) += G ((b), (c), (d)) + (x) + (UINT4)0x5a827999; \

    (a) = ROTATE_LEFT ((a), (s)); \

  }

#define HH(a, b, c, d, x, s) { \

    (a) += H ((b), (c), (d)) + (x) + (UINT4)0x6ed9eba1; \

    (a) = ROTATE_LEFT ((a), (s)); \

  }

/* MD4 initialization. Begins an MD4 operation, writing a new context.

/*

 * The basic MD4 functions.

 *

 * F and G are optimized compared to their RFC 1320 definitions, with the

 * optimization for F borrowed from Colin Plumb's MD5 implementation.

 */

 */

static void MD4Init(MD4_CTX *context)

#define F(x, y, z)			((z) ^ ((x) & ((y) ^ (z))))

{

#define G(x, y, z)			(((x) & ((y) | (z))) | ((y) & (z)))

  context->count[0] = context->count[1] = 0;

#define H(x, y, z)			((x) ^ (y) ^ (z))

  /* Load magic initialization constants.

/*

 * The MD4 transformation for all three rounds.

 */

 */

  context->state[0] = 0x67452301;

#define STEP(f, a, b, c, d, x, s) \

  context->state[1] = 0xefcdab89;

	(a) += f((b), (c), (d)) + (x); \

  context->state[2] = 0x98badcfe;

	(a) = (((a) << (s)) | (((a) & 0xffffffff) >> (32 - (s))));

  context->state[3] = 0x10325476;

}

/*

 * SET reads 4 input bytes in little-endian byte order and stores them

/* MD4 block update operation. Continues an MD4 message-digest

 * in a properly aligned word in host byte order.

     operation, processing another message block, and updating the

 *

     context.

 * The check for little-endian architectures that tolerate unaligned

 * memory accesses is just an optimization.  Nothing will break if it

 * doesn't work.

 */

 */

static void MD4Update(MD4_CTX *context, const unsigned char *input,

#if defined(__i386__) || defined(__x86_64__) || defined(__vax__)

                      unsigned int inputLen)

#define SET(n) \

{

	(*(MD4_u32plus *)&ptr[(n) * 4])

  unsigned int i, bufindex, partLen;

#define GET(n) \

	SET(n)

  /* Compute number of bytes mod 64 */

#else

  bufindex = (unsigned int)((context->count[0] >> 3) & 0x3F);

#define SET(n) \

  /* Update number of bits */

	(ctx->block[(n)] = \

  if((context->count[0] += ((UINT4)inputLen << 3))

	(MD4_u32plus)ptr[(n) * 4] | \

     < ((UINT4)inputLen << 3))

	((MD4_u32plus)ptr[(n) * 4 + 1] << 8) | \

    context->count[1]++;

	((MD4_u32plus)ptr[(n) * 4 + 2] << 16) | \

  context->count[1] += ((UINT4)inputLen >> 29);

	((MD4_u32plus)ptr[(n) * 4 + 3] << 24))

#define GET(n) \

  partLen = 64 - bufindex;

	(ctx->block[(n)])

  /* Transform as many times as possible.

#endif

/*

 * This processes one or more 64-byte data blocks, but does NOT update

 * the bit counters.  There are no alignment requirements.

 */

 */

  if(inputLen >= partLen) {

static const void *body(MD4_CTX *ctx, const void *data, unsigned long size)

    memcpy(&context->buffer[bufindex], input, partLen);

{

    MD4Transform (context->state, context->buffer);

  const unsigned char *ptr;

  MD4_u32plus a, b, c, d;

    for(i = partLen; i + 63 < inputLen; i += 64)

  MD4_u32plus saved_a, saved_b, saved_c, saved_d;

      MD4Transform (context->state, &input[i]);

    bufindex = 0;

  ptr = (const unsigned char *)data;

  }

  else

    i = 0;

  /* Buffer remaining input */

  a = ctx->a;

  memcpy(&context->buffer[bufindex], &input[i], inputLen-i);

  b = ctx->b;

}

  c = ctx->c;

  d = ctx->d;

/* MD4 padding. */

  do {

static void MD4Pad(MD4_CTX *context)

    saved_a = a;

{

    saved_b = b;

  unsigned char bits[8];

    saved_c = c;

  unsigned int bufindex, padLen;

    saved_d = d;

  /* Save number of bits */

/* Round 1 */

  Encode (bits, context->count, 8);

    STEP(F, a, b, c, d, SET(0), 3)

      STEP(F, d, a, b, c, SET(1), 7)

      STEP(F, c, d, a, b, SET(2), 11)

      STEP(F, b, c, d, a, SET(3), 19)

      STEP(F, a, b, c, d, SET(4), 3)

      STEP(F, d, a, b, c, SET(5), 7)

      STEP(F, c, d, a, b, SET(6), 11)

      STEP(F, b, c, d, a, SET(7), 19)

      STEP(F, a, b, c, d, SET(8), 3)

      STEP(F, d, a, b, c, SET(9), 7)

      STEP(F, c, d, a, b, SET(10), 11)

      STEP(F, b, c, d, a, SET(11), 19)

      STEP(F, a, b, c, d, SET(12), 3)

      STEP(F, d, a, b, c, SET(13), 7)

      STEP(F, c, d, a, b, SET(14), 11)

      STEP(F, b, c, d, a, SET(15), 19)

  /* Pad out to 56 mod 64.

/* Round 2 */

   */

      STEP(G, a, b, c, d, GET(0) + 0x5a827999, 3)

  bufindex = (unsigned int)((context->count[0] >> 3) & 0x3f);

      STEP(G, d, a, b, c, GET(4) + 0x5a827999, 5)

  padLen = (bufindex < 56) ? (56 - bufindex) : (120 - bufindex);

      STEP(G, c, d, a, b, GET(8) + 0x5a827999, 9)

  MD4Update (context, PADDING, padLen);

      STEP(G, b, c, d, a, GET(12) + 0x5a827999, 13)

      STEP(G, a, b, c, d, GET(1) + 0x5a827999, 3)

      STEP(G, d, a, b, c, GET(5) + 0x5a827999, 5)

      STEP(G, c, d, a, b, GET(9) + 0x5a827999, 9)

      STEP(G, b, c, d, a, GET(13) + 0x5a827999, 13)

      STEP(G, a, b, c, d, GET(2) + 0x5a827999, 3)

      STEP(G, d, a, b, c, GET(6) + 0x5a827999, 5)

      STEP(G, c, d, a, b, GET(10) + 0x5a827999, 9)

      STEP(G, b, c, d, a, GET(14) + 0x5a827999, 13)

      STEP(G, a, b, c, d, GET(3) + 0x5a827999, 3)

      STEP(G, d, a, b, c, GET(7) + 0x5a827999, 5)

      STEP(G, c, d, a, b, GET(11) + 0x5a827999, 9)

      STEP(G, b, c, d, a, GET(15) + 0x5a827999, 13)

  /* Append length (before padding) */

/* Round 3 */

  MD4Update (context, bits, 8);

      STEP(H, a, b, c, d, GET(0) + 0x6ed9eba1, 3)

      STEP(H, d, a, b, c, GET(8) + 0x6ed9eba1, 9)

      STEP(H, c, d, a, b, GET(4) + 0x6ed9eba1, 11)

      STEP(H, b, c, d, a, GET(12) + 0x6ed9eba1, 15)

      STEP(H, a, b, c, d, GET(2) + 0x6ed9eba1, 3)

      STEP(H, d, a, b, c, GET(10) + 0x6ed9eba1, 9)

      STEP(H, c, d, a, b, GET(6) + 0x6ed9eba1, 11)

      STEP(H, b, c, d, a, GET(14) + 0x6ed9eba1, 15)

      STEP(H, a, b, c, d, GET(1) + 0x6ed9eba1, 3)

      STEP(H, d, a, b, c, GET(9) + 0x6ed9eba1, 9)

      STEP(H, c, d, a, b, GET(5) + 0x6ed9eba1, 11)

      STEP(H, b, c, d, a, GET(13) + 0x6ed9eba1, 15)

      STEP(H, a, b, c, d, GET(3) + 0x6ed9eba1, 3)

      STEP(H, d, a, b, c, GET(11) + 0x6ed9eba1, 9)

      STEP(H, c, d, a, b, GET(7) + 0x6ed9eba1, 11)

      STEP(H, b, c, d, a, GET(15) + 0x6ed9eba1, 15)

      a += saved_a;

    b += saved_b;

    c += saved_c;

    d += saved_d;

    ptr += 64;

  } while (size -= 64);

  ctx->a = a;

  ctx->b = b;

  ctx->c = c;

  ctx->d = d;

  return ptr;

}

}

/* MD4 finalization. Ends an MD4 message-digest operation, writing the

void MD4_Init(MD4_CTX *ctx)

     the message digest and zeroizing the context.

 */

static void MD4Final (unsigned char digest[16], MD4_CTX *context)

{

{

  /* Do padding */

  ctx->a = 0x67452301;

  MD4Pad (context);

  ctx->b = 0xefcdab89;

  ctx->c = 0x98badcfe;

  ctx->d = 0x10325476;

  /* Store state in digest */

  ctx->lo = 0;

  Encode (digest, context->state, 16);

  ctx->hi = 0;

  /* Zeroize sensitive information.

   */

  memset(context, 0, sizeof(*context));

}

}

/* MD4 basic transformation. Transforms state based on block.

void MD4_Update(MD4_CTX *ctx, const void *data, unsigned long size)

 */

static void MD4Transform (UINT4 state[4], const unsigned char block[64])

{

{

  UINT4 a = state[0], b = state[1], c = state[2], d = state[3], x[16];

  MD4_u32plus saved_lo;

  unsigned long used, available;

  Decode (x, block, 64);

  saved_lo = ctx->lo;

  if ((ctx->lo = (saved_lo + size) & 0x1fffffff) < saved_lo)

    ctx->hi++;

  ctx->hi += size >> 29;

  /* Round 1 */

  used = saved_lo & 0x3f;

  FF (a, b, c, d, x[ 0], S11); /* 1 */

  FF (d, a, b, c, x[ 1], S12); /* 2 */

  FF (c, d, a, b, x[ 2], S13); /* 3 */

  FF (b, c, d, a, x[ 3], S14); /* 4 */

  FF (a, b, c, d, x[ 4], S11); /* 5 */

  FF (d, a, b, c, x[ 5], S12); /* 6 */

  FF (c, d, a, b, x[ 6], S13); /* 7 */

  FF (b, c, d, a, x[ 7], S14); /* 8 */

  FF (a, b, c, d, x[ 8], S11); /* 9 */

  FF (d, a, b, c, x[ 9], S12); /* 10 */

  FF (c, d, a, b, x[10], S13); /* 11 */

  FF (b, c, d, a, x[11], S14); /* 12 */

  FF (a, b, c, d, x[12], S11); /* 13 */

  FF (d, a, b, c, x[13], S12); /* 14 */

  FF (c, d, a, b, x[14], S13); /* 15 */

  FF (b, c, d, a, x[15], S14); /* 16 */

  /* Round 2 */

  if (used) {

  GG (a, b, c, d, x[ 0], S21); /* 17 */

    available = 64 - used;

  GG (d, a, b, c, x[ 4], S22); /* 18 */

  GG (c, d, a, b, x[ 8], S23); /* 19 */

  GG (b, c, d, a, x[12], S24); /* 20 */

  GG (a, b, c, d, x[ 1], S21); /* 21 */

  GG (d, a, b, c, x[ 5], S22); /* 22 */

  GG (c, d, a, b, x[ 9], S23); /* 23 */

  GG (b, c, d, a, x[13], S24); /* 24 */

  GG (a, b, c, d, x[ 2], S21); /* 25 */

  GG (d, a, b, c, x[ 6], S22); /* 26 */

  GG (c, d, a, b, x[10], S23); /* 27 */

  GG (b, c, d, a, x[14], S24); /* 28 */

  GG (a, b, c, d, x[ 3], S21); /* 29 */

  GG (d, a, b, c, x[ 7], S22); /* 30 */

  GG (c, d, a, b, x[11], S23); /* 31 */

  GG (b, c, d, a, x[15], S24); /* 32 */

  /* Round 3 */

    if (size < available) {

  HH (a, b, c, d, x[ 0], S31); /* 33 */

      memcpy(&ctx->buffer[used], data, size);

  HH (d, a, b, c, x[ 8], S32); /* 34 */

      return;

  HH (c, d, a, b, x[ 4], S33); /* 35 */

  HH (b, c, d, a, x[12], S34); /* 36 */

  HH (a, b, c, d, x[ 2], S31); /* 37 */

  HH (d, a, b, c, x[10], S32); /* 38 */

  HH (c, d, a, b, x[ 6], S33); /* 39 */

  HH (b, c, d, a, x[14], S34); /* 40 */

  HH (a, b, c, d, x[ 1], S31); /* 41 */

  HH (d, a, b, c, x[ 9], S32); /* 42 */

  HH (c, d, a, b, x[ 5], S33); /* 43 */

  HH (b, c, d, a, x[13], S34); /* 44 */

  HH (a, b, c, d, x[ 3], S31); /* 45 */

  HH (d, a, b, c, x[11], S32); /* 46 */

  HH (c, d, a, b, x[ 7], S33); /* 47 */

  HH (b, c, d, a, x[15], S34); /* 48 */

  state[0] += a;

  state[1] += b;

  state[2] += c;

  state[3] += d;

  /* Zeroize sensitive information.

   */

  memset(x, 0, sizeof(x));

    }

    }

/* Encodes input (UINT4) into output (unsigned char). Assumes len is

    memcpy(&ctx->buffer[used], data, available);

     a multiple of 4.

    data = (const unsigned char *)data + available;

 */

    size -= available;

static void Encode(unsigned char *output, UINT4 *input, unsigned int len)

    body(ctx, ctx->buffer, 64);

{

  }

  unsigned int i, j;

  for(i = 0, j = 0; j < len; i++, j += 4) {

  if (size >= 64) {

    output[j] = (unsigned char)(input[i] & 0xff);

    data = body(ctx, data, size & ~(unsigned long)0x3f);

    output[j+1] = (unsigned char)((input[i] >> 8) & 0xff);

    size &= 0x3f;

    output[j+2] = (unsigned char)((input[i] >> 16) & 0xff);

    output[j+3] = (unsigned char)((input[i] >> 24) & 0xff);

  }

  }

  memcpy(ctx->buffer, data, size);

}

}

/* Decodes input (unsigned char) into output (UINT4). Assumes len is

void MD4_Final(unsigned char *result, MD4_CTX *ctx)

     a multiple of 4.

 */

static void Decode (UINT4 *output, const unsigned char *input,

                    unsigned int len)

{

{

  unsigned int i, j;

  unsigned long used, available;

  used = ctx->lo & 0x3f;

  for(i = 0, j = 0; j < len; i++, j += 4)

  ctx->buffer[used++] = 0x80;

    output[i] = ((UINT4)input[j]) | (((UINT4)input[j+1]) << 8) |

      (((UINT4)input[j+2]) << 16) | (((UINT4)input[j+3]) << 24);

  available = 64 - used;

  if (available < 8) {

    memset(&ctx->buffer[used], 0, available);

    body(ctx, ctx->buffer, 64);

    used = 0;

    available = 64;

  }

  }

  memset(&ctx->buffer[used], 0, available - 8);

  ctx->lo <<= 3;

  ctx->buffer[56] = ctx->lo;

  ctx->buffer[57] = ctx->lo >> 8;

  ctx->buffer[58] = ctx->lo >> 16;

  ctx->buffer[59] = ctx->lo >> 24;

  ctx->buffer[60] = ctx->hi;

  ctx->buffer[61] = ctx->hi >> 8;

  ctx->buffer[62] = ctx->hi >> 16;

  ctx->buffer[63] = ctx->hi >> 24;

  body(ctx, ctx->buffer, 64);

  result[0] = ctx->a;

  result[1] = ctx->a >> 8;

  result[2] = ctx->a >> 16;

  result[3] = ctx->a >> 24;

  result[4] = ctx->b;

  result[5] = ctx->b >> 8;

  result[6] = ctx->b >> 16;

  result[7] = ctx->b >> 24;

  result[8] = ctx->c;

  result[9] = ctx->c >> 8;

  result[10] = ctx->c >> 16;

  result[11] = ctx->c >> 24;

  result[12] = ctx->d;

  result[13] = ctx->d >> 8;

  result[14] = ctx->d >> 16;

  result[15] = ctx->d >> 24;

  memset(ctx, 0, sizeof(*ctx));

}

#endif

void Curl_md4it(unsigned char *output, const unsigned char *input, size_t len)

void Curl_md4it(unsigned char *output, const unsigned char *input, size_t len)

{

{

  MD4_CTX ctx;

  MD4_CTX ctx;