diff --git a/sha.h b/sha.h index 81e1571e41ec9beb888bab8701ee13f49ef3c6a2..6dcb292cd31e053fc1ad2e80cf99f4aec436a4c3 100644 --- a/sha.h +++ b/sha.h @@ -65,6 +65,11 @@ sha1_digest(struct sha1_ctx *ctx, unsigned length, uint8_t *digest); +/* Internal compression function. STATE points to 5 uint32_t words, + and DATA points to 16 uint32_t words which are destroyed. */ +void +_nettle_sha1_compress(uint32_t *state, uint32_t *data); + /* SHA256 */ #define SHA256_DIGEST_SIZE 32 diff --git a/sha1-compress.c b/sha1-compress.c new file mode 100644 index 0000000000000000000000000000000000000000..83ba7aadc7af1b5973ae659d23acd41f0ddf9e4c --- /dev/null +++ b/sha1-compress.c @@ -0,0 +1,220 @@ +/* sha1-compress.c + * + * The compression function of the sha1 hash function. + */ + +/* nettle, low-level cryptographics library + * + * Copyright (C) 2001, 2004 Peter Gutmann, Andrew Kuchling, Niels Möller + * + * The nettle library is free software; you can redistribute it and/or modify + * it under the terms of the GNU Lesser General Public License as published by + * the Free Software Foundation; either version 2.1 of the License, or (at your + * option) any later version. + * + * The nettle library is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY + * or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Lesser General Public + * License for more details. + * + * You should have received a copy of the GNU Lesser General Public License + * along with the nettle library; see the file COPYING.LIB. If not, write to + * the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, + * MA 02111-1307, USA. + */ + +/* Here's the first paragraph of Peter Gutmann's posting, + * <30ajo5$oe8@ccu2.auckland.ac.nz>: + * + * The following is my SHA (FIPS 180) code updated to allow use of the "fixed" + * SHA, thanks to Jim Gillogly and an anonymous contributor for the information on + * what's changed in the new version. The fix is a simple change which involves + * adding a single rotate in the initial expansion function. It is unknown + * whether this is an optimal solution to the problem which was discovered in the + * SHA or whether it's simply a bandaid which fixes the problem with a minimum of + * effort (for example the reengineering of a great many Capstone chips). + */ + +#if HAVE_CONFIG_H +# include "config.h" +#endif + +#include <assert.h> +#include <stdlib.h> +#include <string.h> + +#include "sha.h" + +#include "macros.h" + +/* A block, treated as a sequence of 32-bit words. */ +#define SHA1_DATA_LENGTH 16 + +/* The SHA f()-functions. The f1 and f3 functions can be optimized to + save one boolean operation each - thanks to Rich Schroeppel, + rcs@cs.arizona.edu for discovering this */ + +/* #define f1(x,y,z) ( ( x & y ) | ( ~x & z ) ) Rounds 0-19 */ +#define f1(x,y,z) ( z ^ ( x & ( y ^ z ) ) ) /* Rounds 0-19 */ +#define f2(x,y,z) ( x ^ y ^ z ) /* Rounds 20-39 */ +/* #define f3(x,y,z) ( ( x & y ) | ( x & z ) | ( y & z ) ) Rounds 40-59 */ +#define f3(x,y,z) ( ( x & y ) | ( z & ( x | y ) ) ) /* Rounds 40-59 */ +#define f4(x,y,z) ( x ^ y ^ z ) /* Rounds 60-79 */ + +/* The SHA Mysterious Constants */ + +#define K1 0x5A827999L /* Rounds 0-19 */ +#define K2 0x6ED9EBA1L /* Rounds 20-39 */ +#define K3 0x8F1BBCDCL /* Rounds 40-59 */ +#define K4 0xCA62C1D6L /* Rounds 60-79 */ + +/* 32-bit rotate left - kludged with shifts */ + +#define ROTL(n,X) ( ( (X) << (n) ) | ( (X) >> ( 32 - (n) ) ) ) + +/* The initial expanding function. The hash function is defined over an + 80-word expanded input array W, where the first 16 are copies of the input + data, and the remaining 64 are defined by + + W[ i ] = W[ i - 16 ] ^ W[ i - 14 ] ^ W[ i - 8 ] ^ W[ i - 3 ] + + This implementation generates these values on the fly in a circular + buffer - thanks to Colin Plumb, colin@nyx10.cs.du.edu for this + optimization. + + The updated SHA changes the expanding function by adding a rotate of 1 + bit. Thanks to Jim Gillogly, jim@rand.org, and an anonymous contributor + for this information */ + +#define expand(W,i) ( W[ i & 15 ] = \ + ROTL( 1, ( W[ i & 15 ] ^ W[ (i - 14) & 15 ] ^ \ + W[ (i - 8) & 15 ] ^ W[ (i - 3) & 15 ] ) ) ) + + +/* The prototype SHA sub-round. The fundamental sub-round is: + + a' = e + ROTL( 5, a ) + f( b, c, d ) + k + data; + b' = a; + c' = ROTL( 30, b ); + d' = c; + e' = d; + + but this is implemented by unrolling the loop 5 times and renaming the + variables ( e, a, b, c, d ) = ( a', b', c', d', e' ) each iteration. + This code is then replicated 20 times for each of the 4 functions, using + the next 20 values from the W[] array each time */ + +#define subRound(a, b, c, d, e, f, k, data) \ + ( e += ROTL( 5, a ) + f( b, c, d ) + k + data, b = ROTL( 30, b ) ) + +/* Perform the SHA transformation. Note that this code, like MD5, seems to + break some optimizing compilers due to the complexity of the expressions + and the size of the basic block. It may be necessary to split it into + sections, e.g. based on the four subrounds + + Note that this function destroys the data area */ + +void +_nettle_sha1_compress(uint32_t *state, uint32_t *data) +{ + uint32_t A, B, C, D, E; /* Local vars */ + + /* Set up first buffer and local data buffer */ + A = state[0]; + B = state[1]; + C = state[2]; + D = state[3]; + E = state[4]; + + /* Heavy mangling, in 4 sub-rounds of 20 interations each. */ + subRound( A, B, C, D, E, f1, K1, data[ 0] ); + subRound( E, A, B, C, D, f1, K1, data[ 1] ); + subRound( D, E, A, B, C, f1, K1, data[ 2] ); + subRound( C, D, E, A, B, f1, K1, data[ 3] ); + subRound( B, C, D, E, A, f1, K1, data[ 4] ); + subRound( A, B, C, D, E, f1, K1, data[ 5] ); + subRound( E, A, B, C, D, f1, K1, data[ 6] ); + subRound( D, E, A, B, C, f1, K1, data[ 7] ); + subRound( C, D, E, A, B, f1, K1, data[ 8] ); + subRound( B, C, D, E, A, f1, K1, data[ 9] ); + subRound( A, B, C, D, E, f1, K1, data[10] ); + subRound( E, A, B, C, D, f1, K1, data[11] ); + subRound( D, E, A, B, C, f1, K1, data[12] ); + subRound( C, D, E, A, B, f1, K1, data[13] ); + subRound( B, C, D, E, A, f1, K1, data[14] ); + subRound( A, B, C, D, E, f1, K1, data[15] ); + subRound( E, A, B, C, D, f1, K1, expand( data, 16 ) ); + subRound( D, E, A, B, C, f1, K1, expand( data, 17 ) ); + subRound( C, D, E, A, B, f1, K1, expand( data, 18 ) ); + subRound( B, C, D, E, A, f1, K1, expand( data, 19 ) ); + + subRound( A, B, C, D, E, f2, K2, expand( data, 20 ) ); + subRound( E, A, B, C, D, f2, K2, expand( data, 21 ) ); + subRound( D, E, A, B, C, f2, K2, expand( data, 22 ) ); + subRound( C, D, E, A, B, f2, K2, expand( data, 23 ) ); + subRound( B, C, D, E, A, f2, K2, expand( data, 24 ) ); + subRound( A, B, C, D, E, f2, K2, expand( data, 25 ) ); + subRound( E, A, B, C, D, f2, K2, expand( data, 26 ) ); + subRound( D, E, A, B, C, f2, K2, expand( data, 27 ) ); + subRound( C, D, E, A, B, f2, K2, expand( data, 28 ) ); + subRound( B, C, D, E, A, f2, K2, expand( data, 29 ) ); + subRound( A, B, C, D, E, f2, K2, expand( data, 30 ) ); + subRound( E, A, B, C, D, f2, K2, expand( data, 31 ) ); + subRound( D, E, A, B, C, f2, K2, expand( data, 32 ) ); + subRound( C, D, E, A, B, f2, K2, expand( data, 33 ) ); + subRound( B, C, D, E, A, f2, K2, expand( data, 34 ) ); + subRound( A, B, C, D, E, f2, K2, expand( data, 35 ) ); + subRound( E, A, B, C, D, f2, K2, expand( data, 36 ) ); + subRound( D, E, A, B, C, f2, K2, expand( data, 37 ) ); + subRound( C, D, E, A, B, f2, K2, expand( data, 38 ) ); + subRound( B, C, D, E, A, f2, K2, expand( data, 39 ) ); + + subRound( A, B, C, D, E, f3, K3, expand( data, 40 ) ); + subRound( E, A, B, C, D, f3, K3, expand( data, 41 ) ); + subRound( D, E, A, B, C, f3, K3, expand( data, 42 ) ); + subRound( C, D, E, A, B, f3, K3, expand( data, 43 ) ); + subRound( B, C, D, E, A, f3, K3, expand( data, 44 ) ); + subRound( A, B, C, D, E, f3, K3, expand( data, 45 ) ); + subRound( E, A, B, C, D, f3, K3, expand( data, 46 ) ); + subRound( D, E, A, B, C, f3, K3, expand( data, 47 ) ); + subRound( C, D, E, A, B, f3, K3, expand( data, 48 ) ); + subRound( B, C, D, E, A, f3, K3, expand( data, 49 ) ); + subRound( A, B, C, D, E, f3, K3, expand( data, 50 ) ); + subRound( E, A, B, C, D, f3, K3, expand( data, 51 ) ); + subRound( D, E, A, B, C, f3, K3, expand( data, 52 ) ); + subRound( C, D, E, A, B, f3, K3, expand( data, 53 ) ); + subRound( B, C, D, E, A, f3, K3, expand( data, 54 ) ); + subRound( A, B, C, D, E, f3, K3, expand( data, 55 ) ); + subRound( E, A, B, C, D, f3, K3, expand( data, 56 ) ); + subRound( D, E, A, B, C, f3, K3, expand( data, 57 ) ); + subRound( C, D, E, A, B, f3, K3, expand( data, 58 ) ); + subRound( B, C, D, E, A, f3, K3, expand( data, 59 ) ); + + subRound( A, B, C, D, E, f4, K4, expand( data, 60 ) ); + subRound( E, A, B, C, D, f4, K4, expand( data, 61 ) ); + subRound( D, E, A, B, C, f4, K4, expand( data, 62 ) ); + subRound( C, D, E, A, B, f4, K4, expand( data, 63 ) ); + subRound( B, C, D, E, A, f4, K4, expand( data, 64 ) ); + subRound( A, B, C, D, E, f4, K4, expand( data, 65 ) ); + subRound( E, A, B, C, D, f4, K4, expand( data, 66 ) ); + subRound( D, E, A, B, C, f4, K4, expand( data, 67 ) ); + subRound( C, D, E, A, B, f4, K4, expand( data, 68 ) ); + subRound( B, C, D, E, A, f4, K4, expand( data, 69 ) ); + subRound( A, B, C, D, E, f4, K4, expand( data, 70 ) ); + subRound( E, A, B, C, D, f4, K4, expand( data, 71 ) ); + subRound( D, E, A, B, C, f4, K4, expand( data, 72 ) ); + subRound( C, D, E, A, B, f4, K4, expand( data, 73 ) ); + subRound( B, C, D, E, A, f4, K4, expand( data, 74 ) ); + subRound( A, B, C, D, E, f4, K4, expand( data, 75 ) ); + subRound( E, A, B, C, D, f4, K4, expand( data, 76 ) ); + subRound( D, E, A, B, C, f4, K4, expand( data, 77 ) ); + subRound( C, D, E, A, B, f4, K4, expand( data, 78 ) ); + subRound( B, C, D, E, A, f4, K4, expand( data, 79 ) ); + + /* Build message digest */ + state[0] += A; + state[1] += B; + state[2] += C; + state[3] += D; + state[4] += E; +} diff --git a/sha1.c b/sha1.c index 391f5479bf350798ca8d81628e1400f5c8d1f7c2..d03b597518e4ef1973f9b81431b46a518a873f9a 100644 --- a/sha1.c +++ b/sha1.c @@ -50,24 +50,6 @@ /* A block, treated as a sequence of 32-bit words. */ #define SHA1_DATA_LENGTH 16 -/* The SHA f()-functions. The f1 and f3 functions can be optimized to - save one boolean operation each - thanks to Rich Schroeppel, - rcs@cs.arizona.edu for discovering this */ - -/* #define f1(x,y,z) ( ( x & y ) | ( ~x & z ) ) Rounds 0-19 */ -#define f1(x,y,z) ( z ^ ( x & ( y ^ z ) ) ) /* Rounds 0-19 */ -#define f2(x,y,z) ( x ^ y ^ z ) /* Rounds 20-39 */ -/* #define f3(x,y,z) ( ( x & y ) | ( x & z ) | ( y & z ) ) Rounds 40-59 */ -#define f3(x,y,z) ( ( x & y ) | ( z & ( x | y ) ) ) /* Rounds 40-59 */ -#define f4(x,y,z) ( x ^ y ^ z ) /* Rounds 60-79 */ - -/* The SHA Mysterious Constants */ - -#define K1 0x5A827999L /* Rounds 0-19 */ -#define K2 0x6ED9EBA1L /* Rounds 20-39 */ -#define K3 0x8F1BBCDCL /* Rounds 40-59 */ -#define K4 0xCA62C1D6L /* Rounds 60-79 */ - /* SHA initial values */ #define h0init 0x67452301L @@ -76,45 +58,6 @@ #define h3init 0x10325476L #define h4init 0xC3D2E1F0L -/* 32-bit rotate left - kludged with shifts */ - -#define ROTL(n,X) ( ( (X) << (n) ) | ( (X) >> ( 32 - (n) ) ) ) - -/* The initial expanding function. The hash function is defined over an - 80-word expanded input array W, where the first 16 are copies of the input - data, and the remaining 64 are defined by - - W[ i ] = W[ i - 16 ] ^ W[ i - 14 ] ^ W[ i - 8 ] ^ W[ i - 3 ] - - This implementation generates these values on the fly in a circular - buffer - thanks to Colin Plumb, colin@nyx10.cs.du.edu for this - optimization. - - The updated SHA changes the expanding function by adding a rotate of 1 - bit. Thanks to Jim Gillogly, jim@rand.org, and an anonymous contributor - for this information */ - -#define expand(W,i) ( W[ i & 15 ] = \ - ROTL( 1, ( W[ i & 15 ] ^ W[ (i - 14) & 15 ] ^ \ - W[ (i - 8) & 15 ] ^ W[ (i - 3) & 15 ] ) ) ) - - -/* The prototype SHA sub-round. The fundamental sub-round is: - - a' = e + ROTL( 5, a ) + f( b, c, d ) + k + data; - b' = a; - c' = ROTL( 30, b ); - d' = c; - e' = d; - - but this is implemented by unrolling the loop 5 times and renaming the - variables ( e, a, b, c, d ) = ( a', b', c', d', e' ) each iteration. - This code is then replicated 20 times for each of the 4 functions, using - the next 20 values from the W[] array each time */ - -#define subRound(a, b, c, d, e, f, k, data) \ - ( e += ROTL( 5, a ) + f( b, c, d ) + k + data, b = ROTL( 30, b ) ) - /* Initialize the SHA values */ void @@ -134,117 +77,9 @@ sha1_init(struct sha1_ctx *ctx) ctx->index = 0; } -/* Perform the SHA transformation. Note that this code, like MD5, seems to - break some optimizing compilers due to the complexity of the expressions - and the size of the basic block. It may be necessary to split it into - sections, e.g. based on the four subrounds - - Note that this function destroys the data area */ - -static void -sha1_transform(uint32_t *state, uint32_t *data) -{ - uint32_t A, B, C, D, E; /* Local vars */ - - /* Set up first buffer and local data buffer */ - A = state[0]; - B = state[1]; - C = state[2]; - D = state[3]; - E = state[4]; - - /* Heavy mangling, in 4 sub-rounds of 20 interations each. */ - subRound( A, B, C, D, E, f1, K1, data[ 0] ); - subRound( E, A, B, C, D, f1, K1, data[ 1] ); - subRound( D, E, A, B, C, f1, K1, data[ 2] ); - subRound( C, D, E, A, B, f1, K1, data[ 3] ); - subRound( B, C, D, E, A, f1, K1, data[ 4] ); - subRound( A, B, C, D, E, f1, K1, data[ 5] ); - subRound( E, A, B, C, D, f1, K1, data[ 6] ); - subRound( D, E, A, B, C, f1, K1, data[ 7] ); - subRound( C, D, E, A, B, f1, K1, data[ 8] ); - subRound( B, C, D, E, A, f1, K1, data[ 9] ); - subRound( A, B, C, D, E, f1, K1, data[10] ); - subRound( E, A, B, C, D, f1, K1, data[11] ); - subRound( D, E, A, B, C, f1, K1, data[12] ); - subRound( C, D, E, A, B, f1, K1, data[13] ); - subRound( B, C, D, E, A, f1, K1, data[14] ); - subRound( A, B, C, D, E, f1, K1, data[15] ); - subRound( E, A, B, C, D, f1, K1, expand( data, 16 ) ); - subRound( D, E, A, B, C, f1, K1, expand( data, 17 ) ); - subRound( C, D, E, A, B, f1, K1, expand( data, 18 ) ); - subRound( B, C, D, E, A, f1, K1, expand( data, 19 ) ); - - subRound( A, B, C, D, E, f2, K2, expand( data, 20 ) ); - subRound( E, A, B, C, D, f2, K2, expand( data, 21 ) ); - subRound( D, E, A, B, C, f2, K2, expand( data, 22 ) ); - subRound( C, D, E, A, B, f2, K2, expand( data, 23 ) ); - subRound( B, C, D, E, A, f2, K2, expand( data, 24 ) ); - subRound( A, B, C, D, E, f2, K2, expand( data, 25 ) ); - subRound( E, A, B, C, D, f2, K2, expand( data, 26 ) ); - subRound( D, E, A, B, C, f2, K2, expand( data, 27 ) ); - subRound( C, D, E, A, B, f2, K2, expand( data, 28 ) ); - subRound( B, C, D, E, A, f2, K2, expand( data, 29 ) ); - subRound( A, B, C, D, E, f2, K2, expand( data, 30 ) ); - subRound( E, A, B, C, D, f2, K2, expand( data, 31 ) ); - subRound( D, E, A, B, C, f2, K2, expand( data, 32 ) ); - subRound( C, D, E, A, B, f2, K2, expand( data, 33 ) ); - subRound( B, C, D, E, A, f2, K2, expand( data, 34 ) ); - subRound( A, B, C, D, E, f2, K2, expand( data, 35 ) ); - subRound( E, A, B, C, D, f2, K2, expand( data, 36 ) ); - subRound( D, E, A, B, C, f2, K2, expand( data, 37 ) ); - subRound( C, D, E, A, B, f2, K2, expand( data, 38 ) ); - subRound( B, C, D, E, A, f2, K2, expand( data, 39 ) ); - - subRound( A, B, C, D, E, f3, K3, expand( data, 40 ) ); - subRound( E, A, B, C, D, f3, K3, expand( data, 41 ) ); - subRound( D, E, A, B, C, f3, K3, expand( data, 42 ) ); - subRound( C, D, E, A, B, f3, K3, expand( data, 43 ) ); - subRound( B, C, D, E, A, f3, K3, expand( data, 44 ) ); - subRound( A, B, C, D, E, f3, K3, expand( data, 45 ) ); - subRound( E, A, B, C, D, f3, K3, expand( data, 46 ) ); - subRound( D, E, A, B, C, f3, K3, expand( data, 47 ) ); - subRound( C, D, E, A, B, f3, K3, expand( data, 48 ) ); - subRound( B, C, D, E, A, f3, K3, expand( data, 49 ) ); - subRound( A, B, C, D, E, f3, K3, expand( data, 50 ) ); - subRound( E, A, B, C, D, f3, K3, expand( data, 51 ) ); - subRound( D, E, A, B, C, f3, K3, expand( data, 52 ) ); - subRound( C, D, E, A, B, f3, K3, expand( data, 53 ) ); - subRound( B, C, D, E, A, f3, K3, expand( data, 54 ) ); - subRound( A, B, C, D, E, f3, K3, expand( data, 55 ) ); - subRound( E, A, B, C, D, f3, K3, expand( data, 56 ) ); - subRound( D, E, A, B, C, f3, K3, expand( data, 57 ) ); - subRound( C, D, E, A, B, f3, K3, expand( data, 58 ) ); - subRound( B, C, D, E, A, f3, K3, expand( data, 59 ) ); - - subRound( A, B, C, D, E, f4, K4, expand( data, 60 ) ); - subRound( E, A, B, C, D, f4, K4, expand( data, 61 ) ); - subRound( D, E, A, B, C, f4, K4, expand( data, 62 ) ); - subRound( C, D, E, A, B, f4, K4, expand( data, 63 ) ); - subRound( B, C, D, E, A, f4, K4, expand( data, 64 ) ); - subRound( A, B, C, D, E, f4, K4, expand( data, 65 ) ); - subRound( E, A, B, C, D, f4, K4, expand( data, 66 ) ); - subRound( D, E, A, B, C, f4, K4, expand( data, 67 ) ); - subRound( C, D, E, A, B, f4, K4, expand( data, 68 ) ); - subRound( B, C, D, E, A, f4, K4, expand( data, 69 ) ); - subRound( A, B, C, D, E, f4, K4, expand( data, 70 ) ); - subRound( E, A, B, C, D, f4, K4, expand( data, 71 ) ); - subRound( D, E, A, B, C, f4, K4, expand( data, 72 ) ); - subRound( C, D, E, A, B, f4, K4, expand( data, 73 ) ); - subRound( B, C, D, E, A, f4, K4, expand( data, 74 ) ); - subRound( A, B, C, D, E, f4, K4, expand( data, 75 ) ); - subRound( E, A, B, C, D, f4, K4, expand( data, 76 ) ); - subRound( D, E, A, B, C, f4, K4, expand( data, 77 ) ); - subRound( C, D, E, A, B, f4, K4, expand( data, 78 ) ); - subRound( B, C, D, E, A, f4, K4, expand( data, 79 ) ); - - /* Build message digest */ - state[0] += A; - state[1] += B; - state[2] += C; - state[3] += D; - state[4] += E; -} +/* Compression function, written in assembler on some systems. + Note that it destroys the data array. */ +#define sha1_compress _nettle_sha1_compress static void sha1_block(struct sha1_ctx *ctx, const uint8_t *block) @@ -260,7 +95,7 @@ sha1_block(struct sha1_ctx *ctx, const uint8_t *block) for (i = 0; i<SHA1_DATA_LENGTH; i++, block += 4) data[i] = READ_UINT32(block); - sha1_transform(ctx->digest, data); + sha1_compress(ctx->digest, data); } void @@ -327,7 +162,7 @@ sha1_final(struct sha1_ctx *ctx) * pad with another one */ for (i = words ; i < SHA1_DATA_LENGTH; i++) data[i] = 0; - sha1_transform(ctx->digest, data); + sha1_compress(ctx->digest, data); for (i = 0; i < (SHA1_DATA_LENGTH-2); i++) data[i] = 0; } @@ -338,7 +173,7 @@ sha1_final(struct sha1_ctx *ctx) /* There are 512 = 2^9 bits in one block */ data[SHA1_DATA_LENGTH-2] = (ctx->count_high << 9) | (ctx->count_low >> 23); data[SHA1_DATA_LENGTH-1] = (ctx->count_low << 9) | (ctx->index << 3); - sha1_transform(ctx->digest, data); + sha1_compress(ctx->digest, data); } void