sha_locl.h 9.6 KB
Newer Older
1
/* crypto/sha/sha_locl.h */
2
/* Copyright (C) 1995-1998 Eric Young (eay@cryptsoft.com)
3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61
 * All rights reserved.
 *
 * This package is an SSL implementation written
 * by Eric Young (eay@cryptsoft.com).
 * The implementation was written so as to conform with Netscapes SSL.
 * 
 * This library is free for commercial and non-commercial use as long as
 * the following conditions are aheared to.  The following conditions
 * apply to all code found in this distribution, be it the RC4, RSA,
 * lhash, DES, etc., code; not just the SSL code.  The SSL documentation
 * included with this distribution is covered by the same copyright terms
 * except that the holder is Tim Hudson (tjh@cryptsoft.com).
 * 
 * Copyright remains Eric Young's, and as such any Copyright notices in
 * the code are not to be removed.
 * If this package is used in a product, Eric Young should be given attribution
 * as the author of the parts of the library used.
 * This can be in the form of a textual message at program startup or
 * in documentation (online or textual) provided with the package.
 * 
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *    "This product includes cryptographic software written by
 *     Eric Young (eay@cryptsoft.com)"
 *    The word 'cryptographic' can be left out if the rouines from the library
 *    being used are not cryptographic related :-).
 * 4. If you include any Windows specific code (or a derivative thereof) from 
 *    the apps directory (application code) you must include an acknowledgement:
 *    "This product includes software written by Tim Hudson (tjh@cryptsoft.com)"
 * 
 * THIS SOFTWARE IS PROVIDED BY ERIC YOUNG ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 * 
 * The licence and distribution terms for any publically available version or
 * derivative of this code cannot be changed.  i.e. this code cannot simply be
 * copied and put under another distribution licence
 * [including the GNU Public Licence.]
 */

#include <stdlib.h>
#include <string.h>

62 63
#include <openssl/opensslconf.h>

64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
#ifdef undef
/* one or the other needs to be defined */
#ifndef SHA_1 /* FIPE 180-1 */
#define SHA_0 /* FIPS 180   */
#endif
#endif

#undef c2nl
#define c2nl(c,l)	(l =(((unsigned long)(*((c)++)))<<24), \
			 l|=(((unsigned long)(*((c)++)))<<16), \
			 l|=(((unsigned long)(*((c)++)))<< 8), \
			 l|=(((unsigned long)(*((c)++)))    ))

#undef p_c2nl
#define p_c2nl(c,l,n)	{ \
			switch (n) { \
			case 0: l =((unsigned long)(*((c)++)))<<24; \
			case 1: l|=((unsigned long)(*((c)++)))<<16; \
			case 2: l|=((unsigned long)(*((c)++)))<< 8; \
			case 3: l|=((unsigned long)(*((c)++))); \
				} \
			}

#undef c2nl_p
/* NOTE the pointer is not incremented at the end of this */
#define c2nl_p(c,l,n)	{ \
			l=0; \
			(c)+=n; \
			switch (n) { \
			case 3: l =((unsigned long)(*(--(c))))<< 8; \
			case 2: l|=((unsigned long)(*(--(c))))<<16; \
			case 1: l|=((unsigned long)(*(--(c))))<<24; \
				} \
			}

#undef p_c2nl_p
#define p_c2nl_p(c,l,sc,len) { \
			switch (sc) \
				{ \
			case 0: l =((unsigned long)(*((c)++)))<<24; \
				if (--len == 0) break; \
			case 1: l|=((unsigned long)(*((c)++)))<<16; \
				if (--len == 0) break; \
			case 2: l|=((unsigned long)(*((c)++)))<< 8; \
				} \
			}

#undef nl2c
#define nl2c(l,c)	(*((c)++)=(unsigned char)(((l)>>24)&0xff), \
			 *((c)++)=(unsigned char)(((l)>>16)&0xff), \
			 *((c)++)=(unsigned char)(((l)>> 8)&0xff), \
			 *((c)++)=(unsigned char)(((l)    )&0xff))

117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161
#undef c2l
#define c2l(c,l)	(l =(((unsigned long)(*((c)++)))    ), \
			 l|=(((unsigned long)(*((c)++)))<< 8), \
			 l|=(((unsigned long)(*((c)++)))<<16), \
			 l|=(((unsigned long)(*((c)++)))<<24))

#undef p_c2l
#define p_c2l(c,l,n)	{ \
			switch (n) { \
			case 0: l =((unsigned long)(*((c)++))); \
			case 1: l|=((unsigned long)(*((c)++)))<< 8; \
			case 2: l|=((unsigned long)(*((c)++)))<<16; \
			case 3: l|=((unsigned long)(*((c)++)))<<24; \
				} \
			}

#undef c2l_p
/* NOTE the pointer is not incremented at the end of this */
#define c2l_p(c,l,n)	{ \
			l=0; \
			(c)+=n; \
			switch (n) { \
			case 3: l =((unsigned long)(*(--(c))))<<16; \
			case 2: l|=((unsigned long)(*(--(c))))<< 8; \
			case 1: l|=((unsigned long)(*(--(c)))); \
				} \
			}

#undef p_c2l_p
#define p_c2l_p(c,l,sc,len) { \
			switch (sc) \
				{ \
			case 0: l =((unsigned long)(*((c)++))); \
				if (--len == 0) break; \
			case 1: l|=((unsigned long)(*((c)++)))<< 8; \
				if (--len == 0) break; \
			case 2: l|=((unsigned long)(*((c)++)))<<16; \
				} \
			}

#undef l2c
#define l2c(l,c)	(*((c)++)=(unsigned char)(((l)    )&0xff), \
			 *((c)++)=(unsigned char)(((l)>> 8)&0xff), \
			 *((c)++)=(unsigned char)(((l)>>16)&0xff), \
			 *((c)++)=(unsigned char)(((l)>>24)&0xff))
162

163 164 165 166
#ifndef SHA_LONG_LOG2
#define SHA_LONG_LOG2	2	/* default to 32 bits */
#endif

167
#undef ROTATE
168
#undef Endian_Reverse32
169 170
#if defined(WIN32)
#define ROTATE(a,n)     _lrotl(a,n)
171
#elif defined(__GNUC__) && !defined(PEDANTIC)
172
/* some inline assembler templates by <appro@fy.chalmers.se> */
173
#if defined(__i386) && !defined(NO_ASM)
174 175 176 177 178 179 180 181 182
#define ROTATE(a,n)	({ register unsigned int ret;	\
				asm ("roll %1,%0"	\
				: "=r"(ret)		\
				: "I"(n), "0"(a)	\
				: "cc");		\
			   ret;				\
			})
#ifndef I386_ONLY
#define Endian_Reverse32(a) \
183
			{ register unsigned int ltmp=(a);	\
184
				asm ("bswapl %0"	\
185 186
				: "=r"(ltmp) : "0"(ltmp));	\
			  (a)=ltmp;			\
187 188 189 190 191 192 193 194 195 196 197
			}
#endif
#elif defined(__powerpc)
#define ROTATE(a,n)	({ register unsigned int ret;		\
				asm ("rlwinm %0,%1,%2,0,31"	\
				: "=r"(ret)			\
				: "r"(a), "I"(n));		\
			   ret;					\
			})
/* Endian_Reverse32 is not needed for PowerPC */
#endif
198 199 200
#endif

/* A nice byte order reversal from Wei Dai <weidai@eskimo.com> */
201 202
#ifdef ROTATE
#ifndef Endian_Reverse32
203 204 205
/* 5 instructions with rotate instruction, else 9 */
#define Endian_Reverse32(a) \
	{ \
206 207
	unsigned long t=(a); \
	(a)=((ROTATE(t,8)&0x00FF00FF)|(ROTATE((t&0x00FF00FF),24))); \
208
	}
209
#endif
210
#else
211 212
#define ROTATE(a,n)     (((a)<<(n))|(((a)&0xffffffff)>>(32-(n))))
#ifndef Endian_Reverse32
213 214 215
/* 6 instructions with rotate instruction, else 8 */
#define Endian_Reverse32(a) \
	{ \
216 217 218
	unsigned long t=(a); \
	t=(((t>>8)&0x00FF00FF)|((t&0x00FF00FF)<<8)); \
	(a)=ROTATE(t,16); \
219 220
	}
#endif
221 222 223 224 225 226 227 228 229 230 231 232 233 234 235
/*
 * Originally the middle line started with l=(((l&0xFF00FF00)>>8)|...
 * It's rewritten as above for two reasons:
 *	- RISCs aren't good at long constants and have to explicitely
 *	  compose 'em with several (well, usually 2) instructions in a
 *	  register before performing the actual operation and (as you
 *	  already realized:-) having same constant should inspire the
 *	  compiler to permanently allocate the only register for it;
 *	- most modern CPUs have two ALUs, but usually only one has
 *	  circuitry for shifts:-( this minor tweak inspires compiler
 *	  to schedule shift instructions in a better way...
 *
 *				<appro@fy.chalmers.se>
 */
#endif
236 237 238 239 240 241 242 243 244 245 246 247 248 249

/* As  pointed out by Wei Dai <weidai@eskimo.com>, F() below can be
 * simplified to the code in F_00_19.  Wei attributes these optimisations
 * to Peter Gutmann's SHS code, and he attributes it to Rich Schroeppel.
 * #define F(x,y,z) (((x) & (y))  |  ((~(x)) & (z)))
 * I've just become aware of another tweak to be made, again from Wei Dai,
 * in F_40_59, (x&a)|(y&a) -> (x|y)&a
 */
#define	F_00_19(b,c,d)	((((c) ^ (d)) & (b)) ^ (d)) 
#define	F_20_39(b,c,d)	((b) ^ (c) ^ (d))
#define F_40_59(b,c,d)	(((b) & (c)) | (((b)|(c)) & (d))) 
#define	F_60_79(b,c,d)	F_20_39(b,c,d)

#undef Xupdate
250
#ifdef SHA_0
251 252
#define Xupdate(a,i,ia,ib,ic,id) X[(i)&0x0f]=(a)=\
	(ia[(i)&0x0f]^ib[((i)+2)&0x0f]^ic[((i)+8)&0x0f]^id[((i)+13)&0x0f]);
253 254
#endif
#ifdef SHA_1
255 256
#define Xupdate(a,i,ia,ib,ic,id) (a)=\
	(ia[(i)&0x0f]^ib[((i)+2)&0x0f]^ic[((i)+8)&0x0f]^id[((i)+13)&0x0f]);\
257 258 259
	X[(i)&0x0f]=(a)=ROTATE((a),1);
#endif

260 261
#define BODY_00_15(i,a,b,c,d,e,f,xa) \
	(f)=xa[i]+(e)+K_00_19+ROTATE((a),5)+F_00_19((b),(c),(d)); \
262 263
	(b)=ROTATE((b),30);

264 265
#define BODY_16_19(i,a,b,c,d,e,f,xa,xb,xc,xd) \
	Xupdate(f,i,xa,xb,xc,xd); \
266 267 268
	(f)+=(e)+K_00_19+ROTATE((a),5)+F_00_19((b),(c),(d)); \
	(b)=ROTATE((b),30);

269 270 271 272 273 274 275
#define BODY_20_31(i,a,b,c,d,e,f,xa,xb,xc,xd) \
	Xupdate(f,i,xa,xb,xc,xd); \
	(f)+=(e)+K_20_39+ROTATE((a),5)+F_20_39((b),(c),(d)); \
	(b)=ROTATE((b),30);

#define BODY_32_39(i,a,b,c,d,e,f,xa) \
	Xupdate(f,i,xa,xa,xa,xa); \
276 277 278
	(f)+=(e)+K_20_39+ROTATE((a),5)+F_20_39((b),(c),(d)); \
	(b)=ROTATE((b),30);

279 280
#define BODY_40_59(i,a,b,c,d,e,f,xa) \
	Xupdate(f,i,xa,xa,xa,xa); \
281 282 283
	(f)+=(e)+K_40_59+ROTATE((a),5)+F_40_59((b),(c),(d)); \
	(b)=ROTATE((b),30);

284 285
#define BODY_60_79(i,a,b,c,d,e,f,xa) \
	Xupdate(f,i,xa,xa,xa,xa); \
286 287 288
	(f)=X[(i)&0x0f]+(e)+K_60_79+ROTATE((a),5)+F_60_79((b),(c),(d)); \
	(b)=ROTATE((b),30);