0
\$\begingroup\$

I'm hoping to benchmark SHA-1 on a 8051 micro controller, so I'm looking for an efficient implementation of (HMAC) SHA-1 for the 8051. C or assembly works for me. Given the age of both SHA-1 and 8051, it's quite surprising that Google searches have come up with nothing related at all.

I'd have guessed Atmel, Microchip, and other vendors would offer an implementation of it (under a certain license), but I can't seem to find anything.

Any guidance will be appreciated.

EDIT Here's an implementation, which I think is speed optimised but not designed for the 8051. Theoretically, should it do okay on the 8051?

#include <string.h>

#include "sha1.h"

#define GET_UINT32(n,b,i)                       \
{                                               \
    (n) = ( (uint32) (b)[(i)    ] << 24 )       \
        | ( (uint32) (b)[(i) + 1] << 16 )       \
        | ( (uint32) (b)[(i) + 2] <<  8 )       \
        | ( (uint32) (b)[(i) + 3]       );      \
}

#define PUT_UINT32(n,b,i)                       \
{                                               \
    (b)[(i)    ] = (uint8) ( (n) >> 24 );       \
    (b)[(i) + 1] = (uint8) ( (n) >> 16 );       \
    (b)[(i) + 2] = (uint8) ( (n) >>  8 );       \
    (b)[(i) + 3] = (uint8) ( (n)       );       \
}

void sha1_starts( sha1_context *ctx )
{
    ctx->total[0] = 0;
    ctx->total[1] = 0;

    ctx->state[0] = 0x67452301;
    ctx->state[1] = 0xEFCDAB89;
    ctx->state[2] = 0x98BADCFE;
    ctx->state[3] = 0x10325476;
    ctx->state[4] = 0xC3D2E1F0;
}

void sha1_process( sha1_context *ctx, uint8 data[64] )
{
    uint32 temp, W[16], A, B, C, D, E;

    GET_UINT32( W[0],  data,  0 );
    GET_UINT32( W[1],  data,  4 );
    GET_UINT32( W[2],  data,  8 );
    GET_UINT32( W[3],  data, 12 );
    GET_UINT32( W[4],  data, 16 );
    GET_UINT32( W[5],  data, 20 );
    GET_UINT32( W[6],  data, 24 );
    GET_UINT32( W[7],  data, 28 );
    GET_UINT32( W[8],  data, 32 );
    GET_UINT32( W[9],  data, 36 );
    GET_UINT32( W[10], data, 40 );
    GET_UINT32( W[11], data, 44 );
    GET_UINT32( W[12], data, 48 );
    GET_UINT32( W[13], data, 52 );
    GET_UINT32( W[14], data, 56 );
    GET_UINT32( W[15], data, 60 );

#define S(x,n) ((x << n) | ((x & 0xFFFFFFFF) >> (32 - n)))

#define R(t)                                            \
(                                                       \
    temp = W[(t -  3) & 0x0F] ^ W[(t - 8) & 0x0F] ^     \
           W[(t - 14) & 0x0F] ^ W[ t      & 0x0F],      \
    ( W[t & 0x0F] = S(temp,1) )                         \
)

#define P(a,b,c,d,e,x)                                  \
{                                                       \
    e += S(a,5) + F(b,c,d) + K + x; b = S(b,30);        \
}

    A = ctx->state[0];
    B = ctx->state[1];
    C = ctx->state[2];
    D = ctx->state[3];
    E = ctx->state[4];

#define F(x,y,z) (z ^ (x & (y ^ z)))
#define K 0x5A827999

    P( A, B, C, D, E, W[0]  );
    P( E, A, B, C, D, W[1]  );
    P( D, E, A, B, C, W[2]  );
    P( C, D, E, A, B, W[3]  );
    P( B, C, D, E, A, W[4]  );
    P( A, B, C, D, E, W[5]  );
    P( E, A, B, C, D, W[6]  );
    P( D, E, A, B, C, W[7]  );
    P( C, D, E, A, B, W[8]  );
    P( B, C, D, E, A, W[9]  );
    P( A, B, C, D, E, W[10] );
    P( E, A, B, C, D, W[11] );
    P( D, E, A, B, C, W[12] );
    P( C, D, E, A, B, W[13] );
    P( B, C, D, E, A, W[14] );
    P( A, B, C, D, E, W[15] );
    P( E, A, B, C, D, R(16) );
    P( D, E, A, B, C, R(17) );
    P( C, D, E, A, B, R(18) );
    P( B, C, D, E, A, R(19) );

#undef K
#undef F

#define F(x,y,z) (x ^ y ^ z)
#define K 0x6ED9EBA1

    P( A, B, C, D, E, R(20) );
    P( E, A, B, C, D, R(21) );
    P( D, E, A, B, C, R(22) );
    P( C, D, E, A, B, R(23) );
    P( B, C, D, E, A, R(24) );
    P( A, B, C, D, E, R(25) );
    P( E, A, B, C, D, R(26) );
    P( D, E, A, B, C, R(27) );
    P( C, D, E, A, B, R(28) );
    P( B, C, D, E, A, R(29) );
    P( A, B, C, D, E, R(30) );
    P( E, A, B, C, D, R(31) );
    P( D, E, A, B, C, R(32) );
    P( C, D, E, A, B, R(33) );
    P( B, C, D, E, A, R(34) );
    P( A, B, C, D, E, R(35) );
    P( E, A, B, C, D, R(36) );
    P( D, E, A, B, C, R(37) );
    P( C, D, E, A, B, R(38) );
    P( B, C, D, E, A, R(39) );

#undef K
#undef F

#define F(x,y,z) ((x & y) | (z & (x | y)))
#define K 0x8F1BBCDC

    P( A, B, C, D, E, R(40) );
    P( E, A, B, C, D, R(41) );
    P( D, E, A, B, C, R(42) );
    P( C, D, E, A, B, R(43) );
    P( B, C, D, E, A, R(44) );
    P( A, B, C, D, E, R(45) );
    P( E, A, B, C, D, R(46) );
    P( D, E, A, B, C, R(47) );
    P( C, D, E, A, B, R(48) );
    P( B, C, D, E, A, R(49) );
    P( A, B, C, D, E, R(50) );
    P( E, A, B, C, D, R(51) );
    P( D, E, A, B, C, R(52) );
    P( C, D, E, A, B, R(53) );
    P( B, C, D, E, A, R(54) );
    P( A, B, C, D, E, R(55) );
    P( E, A, B, C, D, R(56) );
    P( D, E, A, B, C, R(57) );
    P( C, D, E, A, B, R(58) );
    P( B, C, D, E, A, R(59) );

#undef K
#undef F

#define F(x,y,z) (x ^ y ^ z)
#define K 0xCA62C1D6

    P( A, B, C, D, E, R(60) );
    P( E, A, B, C, D, R(61) );
    P( D, E, A, B, C, R(62) );
    P( C, D, E, A, B, R(63) );
    P( B, C, D, E, A, R(64) );
    P( A, B, C, D, E, R(65) );
    P( E, A, B, C, D, R(66) );
    P( D, E, A, B, C, R(67) );
    P( C, D, E, A, B, R(68) );
    P( B, C, D, E, A, R(69) );
    P( A, B, C, D, E, R(70) );
    P( E, A, B, C, D, R(71) );
    P( D, E, A, B, C, R(72) );
    P( C, D, E, A, B, R(73) );
    P( B, C, D, E, A, R(74) );
    P( A, B, C, D, E, R(75) );
    P( E, A, B, C, D, R(76) );
    P( D, E, A, B, C, R(77) );
    P( C, D, E, A, B, R(78) );
    P( B, C, D, E, A, R(79) );

#undef K
#undef F

    ctx->state[0] += A;
    ctx->state[1] += B;
    ctx->state[2] += C;
    ctx->state[3] += D;
    ctx->state[4] += E;
}

void sha1_update( sha1_context *ctx, uint8 *input, uint32 length )
{
    uint32 left, fill;

    if( ! length ) return;

    left = ctx->total[0] & 0x3F;
    fill = 64 - left;

    ctx->total[0] += length;
    ctx->total[0] &= 0xFFFFFFFF;

    if( ctx->total[0] < length )
        ctx->total[1]++;

    if( left && length >= fill )
    {
        memcpy( (void *) (ctx->buffer + left),
                (void *) input, fill );
        sha1_process( ctx, ctx->buffer );
        length -= fill;
        input  += fill;
        left = 0;
    }

    while( length >= 64 )
    {
        sha1_process( ctx, input );
        length -= 64;
        input  += 64;
    }

    if( length )
    {
        memcpy( (void *) (ctx->buffer + left),
                (void *) input, length );
    }
}

static uint8 sha1_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
};

void sha1_finish( sha1_context *ctx, uint8 digest[20] )
{
    uint32 last, padn;
    uint32 high, low;
    uint8 msglen[8];

    high = ( ctx->total[0] >> 29 )
         | ( ctx->total[1] <<  3 );
    low  = ( ctx->total[0] <<  3 );

    PUT_UINT32( high, msglen, 0 );
    PUT_UINT32( low,  msglen, 4 );

    last = ctx->total[0] & 0x3F;
    padn = ( last < 56 ) ? ( 56 - last ) : ( 120 - last );

    sha1_update( ctx, sha1_padding, padn );
    sha1_update( ctx, msglen, 8 );

    PUT_UINT32( ctx->state[0], digest,  0 );
    PUT_UINT32( ctx->state[1], digest,  4 );
    PUT_UINT32( ctx->state[2], digest,  8 );
    PUT_UINT32( ctx->state[3], digest, 12 );
    PUT_UINT32( ctx->state[4], digest, 16 );
}

#ifdef TEST

#include <stdlib.h>
#include <stdio.h>

/*
 * those are the standard FIPS-180-1 test vectors
 */

static char *msg[] = 
{
    "abc",
    "abcdbcdecdefdefgefghfghighijhijkijkljklmklmnlmnomnopnopq",
    NULL
};

static char *val[] =
{
    "a9993e364706816aba3e25717850c26c9cd0d89d",
    "84983e441c3bd26ebaae4aa1f95129e5e54670f1",
    "34aa973cd4c4daa4f61eeb2bdbad27316534016f"
};

int main( int argc, char *argv[] )
{
    FILE *f;
    int i, j;
    char output[41];
    sha1_context ctx;
    unsigned char buf[1000];
    unsigned char sha1sum[20];

    if( argc < 2 )
    {
        printf( "\n SHA-1 Validation Tests:\n\n" );

        for( i = 0; i < 3; i++ )
        {
            printf( " Test %d ", i + 1 );

            sha1_starts( &ctx );

            if( i < 2 )
            {
                sha1_update( &ctx, (uint8 *) msg[i],
                             strlen( msg[i] ) );
            }
            else
            {
                memset( buf, 'a', 1000 );

                for( j = 0; j < 1000; j++ )
                {
                    sha1_update( &ctx, (uint8 *) buf, 1000 );
                }
            }

            sha1_finish( &ctx, sha1sum );

            for( j = 0; j < 20; j++ )
            {
                sprintf( output + j * 2, "%02x", sha1sum[j] );
            }

            if( memcmp( output, val[i], 40 ) )
            {
                printf( "failed!\n" );
                return( 1 );
            }

            printf( "passed.\n" );
        }

        printf( "\n" );
    }
    else
    {
        if( ! ( f = fopen( argv[1], "rb" ) ) )
        {
            perror( "fopen" );
            return( 1 );
        }

        sha1_starts( &ctx );

        while( ( i = fread( buf, 1, sizeof( buf ), f ) ) > 0 )
        {
            sha1_update( &ctx, buf, i );
        }

        sha1_finish( &ctx, sha1sum );

        for( j = 0; j < 20; j++ )
        {
            printf( "%02x", sha1sum[j] );
        }

        printf( "  %s\n", argv[1] );
    }

    return( 0 );
}

#endif

Thanks

\$\endgroup\$
  • \$\begingroup\$ It looks like these guys have implemented it (see table 1 in their paper), so you could email them. There's not much in the way of specifics on that [SHA-1 implementation] in the paper. \$\endgroup\$ – Fizz Oct 25 '15 at 13:39
  • \$\begingroup\$ Yeah, I read that paper too. It was published in 2008, so I'm not confident that they'd still have the code. I emailed them last week, but no response. :( \$\endgroup\$ – John M. Oct 25 '15 at 13:43
  • 2
    \$\begingroup\$ If you want to buy something, you could try cryptovia.com/8051_Hash.html Or at least compile a bog standard C-based implementation and compare the perf you get with that to both of these published data. \$\endgroup\$ – Fizz Oct 25 '15 at 13:43
  • \$\begingroup\$ the 8051 is an 8 bit processor with a max address space of 64k with a very limited stack depth. The compilers I have used on that microprocessor know nothing about 32bit integers. I suspect implementation of the sha-1 algorithm on the 8051 will get 'bogged down' in the manipulation of 32 bit ints and the code will soak up the majority of the available ram \$\endgroup\$ – user3629249 Oct 25 '15 at 14:58
  • 1
    \$\begingroup\$ You may also want to look at this. They've implemented SHA-1 on a 4-bit MCU and they detail what they've did. Also has a couple of refs to other 8-bit SHA-1 implementations although not for 8051. Free slides: www1.uwindsor.ca/sac2012/system/files/1b_Jacob.pdf, but the paper seems like isn't free anywhere. \$\endgroup\$ – Fizz Oct 25 '15 at 15:12
1
\$\begingroup\$

Your best bet in terms of a free implementation appears to be http://www.das-labor.org/wiki/AVR-Crypto-Lib/en This was referenced in the paper by Albrecht et al. as the generic (i.e. C) 8-bit implementation. It's probably a better starting point for a 8051 implementation than 32-bit code.

Looking briefly at the code it does seem that they've implemented as macros [that use 8-bit operations] most of the [32-bit] primitives they need.

\$\endgroup\$
  • \$\begingroup\$ Nice find! Something interesting though: if my reading is correct, it says 1183.84 cycles per byte (of input?). So, using the first paper's figures, it'd need 73398 cycles for 62 bytes. Compared to theirs, 8.46ms works out to be 7796 cycles (921583 cycles per sec). I'm guessing 7796 cycles can't be right, since the proprietary ones seem to do around 30k cycles for a 50 byte input. \$\endgroup\$ – John M. Oct 25 '15 at 15:33
  • \$\begingroup\$ I honestly don't know. It can't be that much effort to get that code to run an try it out yourself. \$\endgroup\$ – Fizz Oct 25 '15 at 15:36
  • \$\begingroup\$ It looks like it needs C99, which I don't think 8051 compilers tend to like. But I voted it up since it's still a good find! \$\endgroup\$ – John M. Oct 27 '15 at 2:40

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.