AmendHub

--- md5asm.c Wed Jan 6 01:44:37 1904 +++ md5asm.c Wed Jan 6 01:53:39 1904 @@ -0,0 +1,448 @@ + +/* MD5ASM.C - MD5 with inline assembly speed-ups + * derived from the RSA Data Security, Inc. + * MD5 Message-Digest Algorithm + * + * The speed ups are as follows: + * + * 1. ROTATE_LEFT has been replaced with a series of macros that + * interpolate ROL.L instructions that each do a maximum rotation + * of 8 bits; + * + * 2. MD5Transform replaces the only function calls, Decode and + * MD5_memset, with inline assembly implementations; + * + * 3. MD5_memcpy and MD5_memset copy THINK C 5.0's assembly + * implementations. + * + * Validate with mddriver.c + */ + +/* Copyright (C) 1991-2, RSA Data Security, Inc. Created 1991. All + rights reserved. + + License to copy and use this software is granted provided that it + is identified as the "RSA Data Security, Inc. MD5 Message-Digest + Algorithm" in all material mentioning or referencing this software + or this function. + + License is also granted to make and use derivative works provided + that such works are identified as "derived from the RSA Data + Security, Inc. MD5 Message-Digest Algorithm" in all material + mentioning or referencing the derived work. + + RSA Data Security, Inc. makes no representations concerning either + the merchantability of this software or the suitability of this + software for any particular purpose. It is provided "as is" + without express or implied warranty of any kind. + + These notices must be retained in any copies of any part of this + documentation and/or software. + + Assembly speed-ups ©2024 mrw <plus@m0001a.org> +*/ + +#include "global.h" +#include "md5.h" + +/* Constants for MD5Transform routine. + */ +#define S11 7 +#define S12 12 +#define S13 17 +#define S14 22 +#define S21 5 +#define S22 9 +#define S23 14 +#define S24 20 +#define S31 4 +#define S32 11 +#define S33 16 +#define S34 23 +#define S41 6 +#define S42 10 +#define S43 15 +#define S44 21 + +static void MD5Transform PROTO_LIST ((UINT4 [4], unsigned char [64])); +static void Encode PROTO_LIST +((unsigned char *, UINT4 *, unsigned int)); +static void MD5_memcpy PROTO_LIST ((POINTER, POINTER, unsigned long)); +static void MD5_memset PROTO_LIST ((POINTER, int, unsigned long)); + +#ifdef _MD5_EXPLICIT_INIT +static unsigned char *PADDING; +#else +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 +}; +#endif + +/* F, G, H and I are basic MD5 functions. + */ +#define F(x, y, z) (((x) & (y)) | ((~x) & (z))) +#define G(x, y, z) (((x) & (z)) | ((y) & (~z))) +#define H(x, y, z) ((x) ^ (y) ^ (z)) +#define I(x, y, z) ((y) ^ ((x) | (~z))) + +/* ROTATE_LEFT rotates x left n bits. + * Displacement is a literal to reduce register pressure; + * that requires it be <= 8, thus the 3 variants. + */ +#define LITERAL # +#define ROTATE_LEFT_A0(x, n) asm { rol.l LITERAL n,x } +#define ROTATE_LEFT_A8(x, n) asm { rol.l #8,x } \ + asm { rol.l LITERAL n-8,x } +#define ROTATE_LEFT_AA(x, n) asm { rol.l #8,x } \ + asm { rol.l #8,x} \ + asm { rol.l LITERAL n-16,x } + +/* FF, GG, HH, and II transformations for rounds 1, 2, 3, and 4. + Rotation is separate from addition to prevent recomputation. + A0,A8,AA variants correspond to rotates above. +*/ +#define FFA0(a, b, c, d, x, s, ac) { \ + (a) += F ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A0 (a, s); \ + (a) += (b); \ + } +#define FFA8(a, b, c, d, x, s, ac) { \ + (a) += F ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A8 (a, s); \ + (a) += (b); \ + } +#define FFAA(a, b, c, d, x, s, ac) { \ + (a) += F ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_AA (a, s); \ + (a) += (b); \ + } + +#define GGA0(a, b, c, d, x, s, ac) { \ + (a) += G ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A0 (a, s); \ + (a) += (b); \ + } +#define GGA8(a, b, c, d, x, s, ac) { \ + (a) += G ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A8 (a, s); \ + (a) += (b); \ + } +#define GGAA(a, b, c, d, x, s, ac) { \ + (a) += G ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_AA (a, s); \ + (a) += (b); \ + } + +#define HHA0(a, b, c, d, x, s, ac) { \ + (a) += H ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A0 (a, s); \ + (a) += (b); \ + } +#define HHA8(a, b, c, d, x, s, ac) { \ + (a) += H ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A8 (a, s); \ + (a) += (b); \ + } +#define HHAA(a, b, c, d, x, s, ac) { \ + (a) += H ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_AA (a, s); \ + (a) += (b); \ + } + +#define IIA0(a, b, c, d, x, s, ac) { \ + (a) += I ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A0 (a, s); \ + (a) += (b); \ + } +#define IIA8(a, b, c, d, x, s, ac) { \ + (a) += I ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_A8 (a, s); \ + (a) += (b); \ + } +#define IIAA(a, b, c, d, x, s, ac) { \ + (a) += I ((b), (c), (d)) + (x) + (UINT4)(ac); \ + ROTATE_LEFT_AA (a, s); \ + (a) += (b); \ + } + +/* MD5 initialization. Begins an MD5 operation, writing a new context. + */ +void MD5Init (context) +MD5_CTX *context; /* context */ +{ + context->count[0] = context->count[1] = 0; + /* Load magic initialization constants. + */ + context->state[0] = 0x67452301; + context->state[1] = 0xefcdab89; + context->state[2] = 0x98badcfe; + context->state[3] = 0x10325476; +} + +/* MD5 block update operation. Continues an MD5 message-digest + operation, processing another message block, and updating the + context. +*/ +void MD5Update (context, input, inputLen) + MD5_CTX *context; /* context */ + unsigned char *input; /* input block */ + unsigned int inputLen; /* length of input block */ +{ + unsigned int i, index, partLen; + + /* Compute number of bytes mod 64 */ + index = (unsigned int)((context->count[0] >> 3) & 0x3F); + + /* Update number of bits */ + if ((context->count[0] += ((UINT4)inputLen << 3)) + < ((UINT4)inputLen << 3)) + context->count[1]++; + context->count[1] += ((UINT4)inputLen >> 29); + + partLen = 64 - index; + + /* Transform as many times as possible. + */ + if (inputLen >= partLen) { + MD5_memcpy + ((POINTER)&context->buffer[index], (POINTER)input, partLen); + MD5Transform (context->state, context->buffer); + + for (i = partLen; i + 63 < inputLen; i += 64) + MD5Transform (context->state, &input[i]); + + index = 0; + } + else + i = 0; + + /* Buffer remaining input */ + MD5_memcpy + ((POINTER)&context->buffer[index], (POINTER)&input[i], + inputLen-i); +} + +/* MD5 finalization. Ends an MD5 message-digest operation, writing the + the message digest and zeroizing the context. +*/ +void MD5Final (digest, context) + unsigned char digest[16]; /* message digest */ + MD5_CTX *context; /* context */ +{ + unsigned char bits[8]; + unsigned int index, padLen; + + /* Save number of bits */ + Encode (bits, context->count, 8); + + /* Pad out to 56 mod 64. + */ + index = (unsigned int)((context->count[0] >> 3) & 0x3f); + padLen = (index < 56) ? (56 - index) : (120 - index); + MD5Update (context, PADDING, padLen); + + /* Append length (before padding) */ + MD5Update (context, bits, 8); + /* Store state in digest */ + Encode (digest, context->state, 16); + + /* Zeroize sensitive information. + */ + MD5_memset ((POINTER)context, 0, sizeof (*context)); +} + + +/* MD5 basic transformation. Transforms state based on block. + */ +static void MD5Transform (state, block) + UINT4 state[4]; + unsigned char block[64]; +{ + register unsigned long a, b, c, d; + unsigned long x[16]; + + // BUG - the assembler wants to copy x[0] instead of x into a0 + // alias to a pointer to force it to copy the address + unsigned long *xp = x; + + /* Inline Decode - translate block to 16 little endian integers */ + asm { + movea.l block,a0 ;input addr + movea.l xp,a1 ;output addr + move.w #3,d0 ;loop counter + ;dbeq stops branching on -1 + @dloop: + movem.l (a0),a/b/c/d ;input -> 4 reg + + ;reverse a + rol.w #8,a ;1234 -> 1243 + swap a ;1243 -> 4312 + rol.w #8,a ;4312 -> 4321 + + ;reverse b + rol.w #8,b ;1234 -> 1243 + swap b ;1243 -> 4312 + rol.w #8,b ;4312 -> 4321 + + ;reverse c + rol.w #8,c ;1234 -> 1243 + swap c ;1243 -> 4312 + rol.w #8,c ;4312 -> 4321 + + ;reverse d + rol.w #8,d ;1234 -> 1243 + swap d ;1243 -> 4312 + rol.w #8,d ;4312 -> 4321 + + movem.l a/b/c/d,(a1) ;4 reg -> output + addi.l #16,a0 ;next input addr + addi.l #16,a1 ;next output addr + dbra d0,@dloop ;loop if > -1 + } + + a = state[0], b = state[1], c = state[2], d = state[3]; + + /* Round 1 */ + FFA0 (a, b, c, d, x[ 0], S11, 0xd76aa478); /* 1 */ + FFA8 (d, a, b, c, x[ 1], S12, 0xe8c7b756); /* 2 */ + FFAA (c, d, a, b, x[ 2], S13, 0x242070db); /* 3 */ + FFAA (b, c, d, a, x[ 3], S14, 0xc1bdceee); /* 4 */ + FFA0 (a, b, c, d, x[ 4], S11, 0xf57c0faf); /* 5 */ + FFA8 (d, a, b, c, x[ 5], S12, 0x4787c62a); /* 6 */ + FFAA (c, d, a, b, x[ 6], S13, 0xa8304613); /* 7 */ + FFAA (b, c, d, a, x[ 7], S14, 0xfd469501); /* 8 */ + FFA0 (a, b, c, d, x[ 8], S11, 0x698098d8); /* 9 */ + FFA8 (d, a, b, c, x[ 9], S12, 0x8b44f7af); /* 10 */ + FFAA (c, d, a, b, x[10], S13, 0xffff5bb1); /* 11 */ + FFAA (b, c, d, a, x[11], S14, 0x895cd7be); /* 12 */ + FFA0 (a, b, c, d, x[12], S11, 0x6b901122); /* 13 */ + FFA8 (d, a, b, c, x[13], S12, 0xfd987193); /* 14 */ + FFAA (c, d, a, b, x[14], S13, 0xa679438e); /* 15 */ + FFAA (b, c, d, a, x[15], S14, 0x49b40821); /* 16 */ + + /* Round 2 */ + GGA0 (a, b, c, d, x[ 1], S21, 0xf61e2562); /* 17 */ + GGA8 (d, a, b, c, x[ 6], S22, 0xc040b340); /* 18 */ + GGA8 (c, d, a, b, x[11], S23, 0x265e5a51); /* 19 */ + GGAA (b, c, d, a, x[ 0], S24, 0xe9b6c7aa); /* 20 */ + GGA0 (a, b, c, d, x[ 5], S21, 0xd62f105d); /* 21 */ + GGA8 (d, a, b, c, x[10], S22, 0x2441453); /* 22 */ + GGA8 (c, d, a, b, x[15], S23, 0xd8a1e681); /* 23 */ + GGAA (b, c, d, a, x[ 4], S24, 0xe7d3fbc8); /* 24 */ + GGA0 (a, b, c, d, x[ 9], S21, 0x21e1cde6); /* 25 */ + GGA8 (d, a, b, c, x[14], S22, 0xc33707d6); /* 26 */ + GGA8 (c, d, a, b, x[ 3], S23, 0xf4d50d87); /* 27 */ + GGAA (b, c, d, a, x[ 8], S24, 0x455a14ed); /* 28 */ + GGA0 (a, b, c, d, x[13], S21, 0xa9e3e905); /* 29 */ + GGA8 (d, a, b, c, x[ 2], S22, 0xfcefa3f8); /* 30 */ + GGA8 (c, d, a, b, x[ 7], S23, 0x676f02d9); /* 31 */ + GGAA (b, c, d, a, x[12], S24, 0x8d2a4c8a); /* 32 */ + + /* Round 3 */ + HHA0 (a, b, c, d, x[ 5], S31, 0xfffa3942); /* 33 */ + HHA8 (d, a, b, c, x[ 8], S32, 0x8771f681); /* 34 */ + HHA8 (c, d, a, b, x[11], S33, 0x6d9d6122); /* 35 */ + HHAA (b, c, d, a, x[14], S34, 0xfde5380c); /* 36 */ + HHA0 (a, b, c, d, x[ 1], S31, 0xa4beea44); /* 37 */ + HHA8 (d, a, b, c, x[ 4], S32, 0x4bdecfa9); /* 38 */ + HHA8 (c, d, a, b, x[ 7], S33, 0xf6bb4b60); /* 39 */ + HHAA (b, c, d, a, x[10], S34, 0xbebfbc70); /* 40 */ + HHA0 (a, b, c, d, x[13], S31, 0x289b7ec6); /* 41 */ + HHA8 (d, a, b, c, x[ 0], S32, 0xeaa127fa); /* 42 */ + HHA8 (c, d, a, b, x[ 3], S33, 0xd4ef3085); /* 43 */ + HHAA (b, c, d, a, x[ 6], S34, 0x4881d05); /* 44 */ + HHA0 (a, b, c, d, x[ 9], S31, 0xd9d4d039); /* 45 */ + HHA8 (d, a, b, c, x[12], S32, 0xe6db99e5); /* 46 */ + HHA8 (c, d, a, b, x[15], S33, 0x1fa27cf8); /* 47 */ + HHAA (b, c, d, a, x[ 2], S34, 0xc4ac5665); /* 48 */ + + /* Round 4 */ + IIA0 (a, b, c, d, x[ 0], S41, 0xf4292244); /* 49 */ + IIA8 (d, a, b, c, x[ 7], S42, 0x432aff97); /* 50 */ + IIA8 (c, d, a, b, x[14], S43, 0xab9423a7); /* 51 */ + IIAA (b, c, d, a, x[ 5], S44, 0xfc93a039); /* 52 */ + IIA0 (a, b, c, d, x[12], S41, 0x655b59c3); /* 53 */ + IIA8 (d, a, b, c, x[ 3], S42, 0x8f0ccc92); /* 54 */ + IIA8 (c, d, a, b, x[10], S43, 0xffeff47d); /* 55 */ + IIAA (b, c, d, a, x[ 1], S44, 0x85845dd1); /* 56 */ + IIA0 (a, b, c, d, x[ 8], S41, 0x6fa87e4f); /* 57 */ + IIA8 (d, a, b, c, x[15], S42, 0xfe2ce6e0); /* 58 */ + IIA8 (c, d, a, b, x[ 6], S43, 0xa3014314); /* 59 */ + IIAA (b, c, d, a, x[13], S44, 0x4e0811a1); /* 60 */ + IIA0 (a, b, c, d, x[ 4], S41, 0xf7537e82); /* 61 */ + IIA8 (d, a, b, c, x[11], S42, 0xbd3af235); /* 62 */ + IIA8 (c, d, a, b, x[ 2], S43, 0x2ad7d2bb); /* 63 */ + IIAA (b, c, d, a, x[ 9], S44, 0xeb86d391); /* 64 */ + + state[0] += a; + state[1] += b; + state[2] += c; + state[3] += d; + + /* Zeroize sensitive information. + * Inline for speed. + */ + asm { + movea.l xp,a0 ; A0 = output + move.l #15,a ; D2.L = n + @mloop move.b 0,(a0)+ + dbra a,@mloop + } +} + +/* Encodes input (UINT4) into output (unsigned char). Assumes len is + a multiple of 4. +*/ +static void Encode (output, input, len) + unsigned char *output; + UINT4 *input; + unsigned int len; +{ + unsigned int i, j; + + for (i = 0, j = 0; j < len; i++, j += 4) { + output[j] = (unsigned char)(input[i] & 0xff); + output[j+1] = (unsigned char)((input[i] >> 8) & 0xff); + output[j+2] = (unsigned char)((input[i] >> 16) & 0xff); + output[j+3] = (unsigned char)((input[i] >> 24) & 0xff); + } +} + +/* Adapted from THINK C 5.0 mem.c + */ +static void MD5_memcpy (output, input, len) + POINTER output; + POINTER input; + unsigned long len; +{ + asm { + movea.l output,a0 ; A0 = output + movea.l input,a1 ; A1 = input + move.l len,d1 ; D1.L = n + bra.s @2 +@1 move.b (a1)+,(a0)+ + subq.l #1,d1 +@2 bne.s @1 + } +} + +/* Adapted from THINK C 5.0 mem.c + */ +static void MD5_memset (output, value, len) + POINTER output; + int value; + unsigned long len; +{ + asm { + movea.l output,a0 ; A0 = output + move.b value,d1 ; D1.B = (unsigned char) c + move.l len,d2 ; D2.L = n + bra.s @2 +@1 move.b d1,(a0)+ + subq.l #1,d2 +@2 bne.s @1 + } +} +