llama.cpp/examples/gguf-hash/deps/sha1/sha1.c
Brian f7cab35ef9
gguf-hash: model wide and per tensor hashing using xxhash and sha1 (#8048)
CLI to hash GGUF files to detect difference on a per model and per tensor level

The hash type we support is:

- `--xxh64`: use xhash 64bit hash mode (default)
- `--sha1`: use sha1
- `--uuid`: use uuid
- `--sha256`: use sha256

While most POSIX systems already have hash checking programs like sha256sum, it
is designed to check entire files. This is not ideal for our purpose if we want
to check for consistency of the tensor data even if the metadata content of the
gguf KV store has been updated.

This program is designed to hash a gguf tensor payload on a 'per tensor layer'
in addition to a 'entire tensor model' hash. The intent is that the entire
tensor layer can be checked first but if there is any detected inconsistencies,
then the per tensor hash can be used to narrow down the specific tensor layer
that has inconsistencies.

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
2024-07-07 22:58:43 +10:00

296 lines
7.4 KiB
C

/*
SHA-1 in C
By Steve Reid <steve@edmweb.com>
100% Public Domain
Test Vectors (from FIPS PUB 180-1)
"abc"
A9993E36 4706816A BA3E2571 7850C26C 9CD0D89D
"abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq"
84983E44 1C3BD26E BAAE4AA1 F95129E5 E54670F1
A million repetitions of "a"
34AA973C D4C4DAA4 F61EEB2B DBAD2731 6534016F
*/
/* #define LITTLE_ENDIAN * This should be #define'd already, if true. */
/* #define SHA1HANDSOFF * Copies data before messing with it. */
#define SHA1HANDSOFF
#include <stdio.h>
#include <string.h>
/* for uint32_t */
#include <stdint.h>
#include "sha1.h"
#define rol(value, bits) (((value) << (bits)) | ((value) >> (32 - (bits))))
/* blk0() and blk() perform the initial expand. */
/* I got the idea of expanding during the round function from SSLeay */
#if BYTE_ORDER == LITTLE_ENDIAN
#define blk0(i) (block->l[i] = (rol(block->l[i],24)&0xFF00FF00) \
|(rol(block->l[i],8)&0x00FF00FF))
#elif BYTE_ORDER == BIG_ENDIAN
#define blk0(i) block->l[i]
#else
#error "Endianness not defined!"
#endif
#define blk(i) (block->l[i&15] = rol(block->l[(i+13)&15]^block->l[(i+8)&15] \
^block->l[(i+2)&15]^block->l[i&15],1))
/* (R0+R1), R2, R3, R4 are the different operations used in SHA1 */
#define R0(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk0(i)+0x5A827999+rol(v,5);w=rol(w,30);
#define R1(v,w,x,y,z,i) z+=((w&(x^y))^y)+blk(i)+0x5A827999+rol(v,5);w=rol(w,30);
#define R2(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0x6ED9EBA1+rol(v,5);w=rol(w,30);
#define R3(v,w,x,y,z,i) z+=(((w|x)&y)|(w&x))+blk(i)+0x8F1BBCDC+rol(v,5);w=rol(w,30);
#define R4(v,w,x,y,z,i) z+=(w^x^y)+blk(i)+0xCA62C1D6+rol(v,5);w=rol(w,30);
/* Hash a single 512-bit block. This is the core of the algorithm. */
void SHA1Transform(
uint32_t state[5],
const unsigned char buffer[64]
)
{
uint32_t a, b, c, d, e;
typedef union
{
unsigned char c[64];
uint32_t l[16];
} CHAR64LONG16;
#ifdef SHA1HANDSOFF
CHAR64LONG16 block[1]; /* use array to appear as a pointer */
memcpy(block, buffer, 64);
#else
/* The following had better never be used because it causes the
* pointer-to-const buffer to be cast into a pointer to non-const.
* And the result is written through. I threw a "const" in, hoping
* this will cause a diagnostic.
*/
CHAR64LONG16 *block = (const CHAR64LONG16 *) buffer;
#endif
/* Copy context->state[] to working vars */
a = state[0];
b = state[1];
c = state[2];
d = state[3];
e = state[4];
/* 4 rounds of 20 operations each. Loop unrolled. */
R0(a, b, c, d, e, 0);
R0(e, a, b, c, d, 1);
R0(d, e, a, b, c, 2);
R0(c, d, e, a, b, 3);
R0(b, c, d, e, a, 4);
R0(a, b, c, d, e, 5);
R0(e, a, b, c, d, 6);
R0(d, e, a, b, c, 7);
R0(c, d, e, a, b, 8);
R0(b, c, d, e, a, 9);
R0(a, b, c, d, e, 10);
R0(e, a, b, c, d, 11);
R0(d, e, a, b, c, 12);
R0(c, d, e, a, b, 13);
R0(b, c, d, e, a, 14);
R0(a, b, c, d, e, 15);
R1(e, a, b, c, d, 16);
R1(d, e, a, b, c, 17);
R1(c, d, e, a, b, 18);
R1(b, c, d, e, a, 19);
R2(a, b, c, d, e, 20);
R2(e, a, b, c, d, 21);
R2(d, e, a, b, c, 22);
R2(c, d, e, a, b, 23);
R2(b, c, d, e, a, 24);
R2(a, b, c, d, e, 25);
R2(e, a, b, c, d, 26);
R2(d, e, a, b, c, 27);
R2(c, d, e, a, b, 28);
R2(b, c, d, e, a, 29);
R2(a, b, c, d, e, 30);
R2(e, a, b, c, d, 31);
R2(d, e, a, b, c, 32);
R2(c, d, e, a, b, 33);
R2(b, c, d, e, a, 34);
R2(a, b, c, d, e, 35);
R2(e, a, b, c, d, 36);
R2(d, e, a, b, c, 37);
R2(c, d, e, a, b, 38);
R2(b, c, d, e, a, 39);
R3(a, b, c, d, e, 40);
R3(e, a, b, c, d, 41);
R3(d, e, a, b, c, 42);
R3(c, d, e, a, b, 43);
R3(b, c, d, e, a, 44);
R3(a, b, c, d, e, 45);
R3(e, a, b, c, d, 46);
R3(d, e, a, b, c, 47);
R3(c, d, e, a, b, 48);
R3(b, c, d, e, a, 49);
R3(a, b, c, d, e, 50);
R3(e, a, b, c, d, 51);
R3(d, e, a, b, c, 52);
R3(c, d, e, a, b, 53);
R3(b, c, d, e, a, 54);
R3(a, b, c, d, e, 55);
R3(e, a, b, c, d, 56);
R3(d, e, a, b, c, 57);
R3(c, d, e, a, b, 58);
R3(b, c, d, e, a, 59);
R4(a, b, c, d, e, 60);
R4(e, a, b, c, d, 61);
R4(d, e, a, b, c, 62);
R4(c, d, e, a, b, 63);
R4(b, c, d, e, a, 64);
R4(a, b, c, d, e, 65);
R4(e, a, b, c, d, 66);
R4(d, e, a, b, c, 67);
R4(c, d, e, a, b, 68);
R4(b, c, d, e, a, 69);
R4(a, b, c, d, e, 70);
R4(e, a, b, c, d, 71);
R4(d, e, a, b, c, 72);
R4(c, d, e, a, b, 73);
R4(b, c, d, e, a, 74);
R4(a, b, c, d, e, 75);
R4(e, a, b, c, d, 76);
R4(d, e, a, b, c, 77);
R4(c, d, e, a, b, 78);
R4(b, c, d, e, a, 79);
/* Add the working vars back into context.state[] */
state[0] += a;
state[1] += b;
state[2] += c;
state[3] += d;
state[4] += e;
/* Wipe variables */
a = b = c = d = e = 0;
#ifdef SHA1HANDSOFF
memset(block, '\0', sizeof(block));
#endif
}
/* SHA1Init - Initialize new context */
void SHA1Init(
SHA1_CTX * context
)
{
/* SHA1 initialization constants */
context->state[0] = 0x67452301;
context->state[1] = 0xEFCDAB89;
context->state[2] = 0x98BADCFE;
context->state[3] = 0x10325476;
context->state[4] = 0xC3D2E1F0;
context->count[0] = context->count[1] = 0;
}
/* Run your data through this. */
void SHA1Update(
SHA1_CTX * context,
const unsigned char *data,
uint32_t len
)
{
uint32_t i;
uint32_t j;
j = context->count[0];
if ((context->count[0] += len << 3) < j)
context->count[1]++;
context->count[1] += (len >> 29);
j = (j >> 3) & 63;
if ((j + len) > 63)
{
memcpy(&context->buffer[j], data, (i = 64 - j));
SHA1Transform(context->state, context->buffer);
for (; i + 63 < len; i += 64)
{
SHA1Transform(context->state, &data[i]);
}
j = 0;
}
else
i = 0;
memcpy(&context->buffer[j], &data[i], len - i);
}
/* Add padding and return the message digest. */
void SHA1Final(
unsigned char digest[20],
SHA1_CTX * context
)
{
unsigned i;
unsigned char finalcount[8];
unsigned char c;
#if 0 /* untested "improvement" by DHR */
/* Convert context->count to a sequence of bytes
* in finalcount. Second element first, but
* big-endian order within element.
* But we do it all backwards.
*/
unsigned char *fcp = &finalcount[8];
for (i = 0; i < 2; i++)
{
uint32_t t = context->count[i];
int j;
for (j = 0; j < 4; t >>= 8, j++)
*--fcp = (unsigned char) t}
#else
for (i = 0; i < 8; i++)
{
finalcount[i] = (unsigned char) ((context->count[(i >= 4 ? 0 : 1)] >> ((3 - (i & 3)) * 8)) & 255); /* Endian independent */
}
#endif
c = 0200;
SHA1Update(context, &c, 1);
while ((context->count[0] & 504) != 448)
{
c = 0000;
SHA1Update(context, &c, 1);
}
SHA1Update(context, finalcount, 8); /* Should cause a SHA1Transform() */
for (i = 0; i < 20; i++)
{
digest[i] = (unsigned char)
((context->state[i >> 2] >> ((3 - (i & 3)) * 8)) & 255);
}
/* Wipe variables */
memset(context, '\0', sizeof(*context));
memset(&finalcount, '\0', sizeof(finalcount));
}
void SHA1(
char *hash_out,
const char *str,
uint32_t len)
{
SHA1_CTX ctx;
unsigned int ii;
SHA1Init(&ctx);
for (ii=0; ii<len; ii+=1)
SHA1Update(&ctx, (const unsigned char*)str + ii, 1);
SHA1Final((unsigned char *)hash_out, &ctx);
}