crypto_auth/siphash24/sse41/siphash.c


#include <x86intrin.h>

#include "crypto_auth.h"
#include "crypto_uint64.h"
#include "crypto_uint32.h"
#include "crypto_uint8.h"
#include "crypto_verify_8.h"

typedef crypto_uint64 u64;
typedef crypto_uint32 u32;
typedef crypto_uint8 u8;


#define SIPHASH_ROUNDS 2
#define SIPHASH_FINALROUNDS 4

/*
typedef  uint8_t  u8;
typedef uint32_t u32;
typedef uint64_t u64;
*/

// Specialized for siphash, do not reuse
#define rotate16(x) _mm_shufflehi_epi16((x), _MM_SHUFFLE(2,1,0,3))

#define _mm_roti_epi64(x, c) (((c) == 16) ? rotate16((x)) : _mm_xor_si128(_mm_slli_epi64((x), (c)), _mm_srli_epi64((x), 64-(c))))
//#define _mm_roti_epi64(x, c)  _mm_xor_si128(_mm_slli_epi64((x), (c)), _mm_srli_epi64((x), 64-(c)))


static u64 siphash(const unsigned char key[16], const unsigned char *m, const u64 n)
{
	__m128i v0, v1, v02, v13;
	__m128i k0;
	__m128i mi, mask, len, h;
	const __m128i zero = _mm_setzero_si128();
	size_t i, k;
	union { u64 gpr; __m128i xmm; } hash;

	k0 = _mm_loadu_si128((__m128i*)(key + 0));

	v0 = _mm_xor_si128(k0, _mm_set_epi32(0x646f7261, 0x6e646f6d, 0x736f6d65, 0x70736575));
	v1 = _mm_xor_si128(k0, _mm_set_epi32(0x74656462, 0x79746573, 0x6c796765, 0x6e657261));

	v02 = _mm_unpacklo_epi64(v0, v1);
	v13 = _mm_unpackhi_epi64(v0, v1);

#define HALF_ROUND(a,b,s,t) \
do \
{ \
	__m128i b1,b2; \
	a = _mm_add_epi64(a, b);  \
	b1 = _mm_roti_epi64(b, s); b2 = _mm_roti_epi64(b, t); b = _mm_blend_epi16(b1, b2, 0xF0); \
	b = _mm_xor_si128(b, a);  \
} while(0)

#define COMPRESS(v02,v13) \
	do \
	{ \
		HALF_ROUND(v02,v13,13,16); \
		v02 = _mm_shuffle_epi32(v02, _MM_SHUFFLE(0,1,3,2)); \
		HALF_ROUND(v02,v13,17,21); \
		v02 = _mm_shuffle_epi32(v02, _MM_SHUFFLE(0,1,3,2)); \
	} while(0)

	for(i = 0; i < (n-n%8); i += 8)
	{
		mi = _mm_loadl_epi64((__m128i*)(m + i));
		v13 = _mm_xor_si128(v13, _mm_unpacklo_epi64(zero, mi));
		for(k = 0; k < SIPHASH_ROUNDS; ++k) COMPRESS(v02,v13);
		v02 = _mm_xor_si128(v02, mi);
	}

	mi = _mm_loadl_epi64((__m128i*)(m + i));
	len = _mm_set_epi32(0, 0, (n&0xff) << 24, 0);
	mask = _mm_srli_epi64(_mm_set_epi32(0, 0, 0xffffffff, 0xffffffff), 8*(8-n%8));
	mi = _mm_xor_si128(_mm_and_si128(mi, mask), len);

	v13 = _mm_xor_si128(v13, _mm_unpacklo_epi64(zero, mi));
	for(k = 0; k < SIPHASH_ROUNDS; ++k) COMPRESS(v02,v13);
	v02 = _mm_xor_si128(v02, mi);
	
	v02 = _mm_xor_si128(v02, _mm_set_epi32(0, 0xff, 0, 0));
	for(k = 0; k < SIPHASH_FINALROUNDS; ++k) COMPRESS(v02,v13);

	v0 = _mm_xor_si128(v02, v13);
	v0 = _mm_xor_si128(v0, _mm_castps_si128(_mm_movehl_ps(_mm_castsi128_ps(zero), _mm_castsi128_ps(v0))));
	hash.xmm = v0;

#undef COMPRESS
#undef HALF_ROUND
	//return _mm_extract_epi32(v0, 0) | (((u64)_mm_extract_epi32(v0, 1)) << 32);
	return hash.gpr;
}

int crypto_auth(unsigned char *out,const unsigned char *in,unsigned long long inlen,const unsigned char *k)
{
  int i;
  union
  {
    u8  bytes[8];
    u64 gpr;
  } hash;
  hash.gpr = siphash(k, in, inlen);
  for(i=0; i < 8; ++i) out[i] = hash.bytes[i];
  return 0;
}

int crypto_auth_verify(const unsigned char *h,const unsigned char *in,unsigned long long inlen,const unsigned char *k)
{
  u8 correct[8];
  crypto_auth(correct,in,inlen,k);
  return crypto_verify_8(h,correct);
}

#if 0
/*
   SipHash-2-4 output with
   k = 00 01 02 ...
   and
   in = (empty string)
   in = 00 (1 byte)
   in = 00 01 (2 bytes)
   in = 00 01 02 (3 bytes)
   ...
   in = 00 01 02 ... 3e (63 bytes)
*/
u8 vectors[64][8] =
{
  { 0x31, 0x0e, 0x0e, 0xdd, 0x47, 0xdb, 0x6f, 0x72, },
  { 0xfd, 0x67, 0xdc, 0x93, 0xc5, 0x39, 0xf8, 0x74, },
  { 0x5a, 0x4f, 0xa9, 0xd9, 0x09, 0x80, 0x6c, 0x0d, },
  { 0x2d, 0x7e, 0xfb, 0xd7, 0x96, 0x66, 0x67, 0x85, },
  { 0xb7, 0x87, 0x71, 0x27, 0xe0, 0x94, 0x27, 0xcf, },
  { 0x8d, 0xa6, 0x99, 0xcd, 0x64, 0x55, 0x76, 0x18, },
  { 0xce, 0xe3, 0xfe, 0x58, 0x6e, 0x46, 0xc9, 0xcb, },
  { 0x37, 0xd1, 0x01, 0x8b, 0xf5, 0x00, 0x02, 0xab, },
  { 0x62, 0x24, 0x93, 0x9a, 0x79, 0xf5, 0xf5, 0x93, },
  { 0xb0, 0xe4, 0xa9, 0x0b, 0xdf, 0x82, 0x00, 0x9e, },
  { 0xf3, 0xb9, 0xdd, 0x94, 0xc5, 0xbb, 0x5d, 0x7a, },
  { 0xa7, 0xad, 0x6b, 0x22, 0x46, 0x2f, 0xb3, 0xf4, },
  { 0xfb, 0xe5, 0x0e, 0x86, 0xbc, 0x8f, 0x1e, 0x75, },
  { 0x90, 0x3d, 0x84, 0xc0, 0x27, 0x56, 0xea, 0x14, },
  { 0xee, 0xf2, 0x7a, 0x8e, 0x90, 0xca, 0x23, 0xf7, },
  { 0xe5, 0x45, 0xbe, 0x49, 0x61, 0xca, 0x29, 0xa1, },
  { 0xdb, 0x9b, 0xc2, 0x57, 0x7f, 0xcc, 0x2a, 0x3f, },
  { 0x94, 0x47, 0xbe, 0x2c, 0xf5, 0xe9, 0x9a, 0x69, },
  { 0x9c, 0xd3, 0x8d, 0x96, 0xf0, 0xb3, 0xc1, 0x4b, },
  { 0xbd, 0x61, 0x79, 0xa7, 0x1d, 0xc9, 0x6d, 0xbb, },
  { 0x98, 0xee, 0xa2, 0x1a, 0xf2, 0x5c, 0xd6, 0xbe, },
  { 0xc7, 0x67, 0x3b, 0x2e, 0xb0, 0xcb, 0xf2, 0xd0, },
  { 0x88, 0x3e, 0xa3, 0xe3, 0x95, 0x67, 0x53, 0x93, },
  { 0xc8, 0xce, 0x5c, 0xcd, 0x8c, 0x03, 0x0c, 0xa8, },
  { 0x94, 0xaf, 0x49, 0xf6, 0xc6, 0x50, 0xad, 0xb8, },
  { 0xea, 0xb8, 0x85, 0x8a, 0xde, 0x92, 0xe1, 0xbc, },
  { 0xf3, 0x15, 0xbb, 0x5b, 0xb8, 0x35, 0xd8, 0x17, },
  { 0xad, 0xcf, 0x6b, 0x07, 0x63, 0x61, 0x2e, 0x2f, },
  { 0xa5, 0xc9, 0x1d, 0xa7, 0xac, 0xaa, 0x4d, 0xde, },
  { 0x71, 0x65, 0x95, 0x87, 0x66, 0x50, 0xa2, 0xa6, },
  { 0x28, 0xef, 0x49, 0x5c, 0x53, 0xa3, 0x87, 0xad, },
  { 0x42, 0xc3, 0x41, 0xd8, 0xfa, 0x92, 0xd8, 0x32, },
  { 0xce, 0x7c, 0xf2, 0x72, 0x2f, 0x51, 0x27, 0x71, },
  { 0xe3, 0x78, 0x59, 0xf9, 0x46, 0x23, 0xf3, 0xa7, },
  { 0x38, 0x12, 0x05, 0xbb, 0x1a, 0xb0, 0xe0, 0x12, },
  { 0xae, 0x97, 0xa1, 0x0f, 0xd4, 0x34, 0xe0, 0x15, },
  { 0xb4, 0xa3, 0x15, 0x08, 0xbe, 0xff, 0x4d, 0x31, },
  { 0x81, 0x39, 0x62, 0x29, 0xf0, 0x90, 0x79, 0x02, },
  { 0x4d, 0x0c, 0xf4, 0x9e, 0xe5, 0xd4, 0xdc, 0xca, },
  { 0x5c, 0x73, 0x33, 0x6a, 0x76, 0xd8, 0xbf, 0x9a, },
  { 0xd0, 0xa7, 0x04, 0x53, 0x6b, 0xa9, 0x3e, 0x0e, },
  { 0x92, 0x59, 0x58, 0xfc, 0xd6, 0x42, 0x0c, 0xad, },
  { 0xa9, 0x15, 0xc2, 0x9b, 0xc8, 0x06, 0x73, 0x18, },
  { 0x95, 0x2b, 0x79, 0xf3, 0xbc, 0x0a, 0xa6, 0xd4, },
  { 0xf2, 0x1d, 0xf2, 0xe4, 0x1d, 0x45, 0x35, 0xf9, },
  { 0x87, 0x57, 0x75, 0x19, 0x04, 0x8f, 0x53, 0xa9, },
  { 0x10, 0xa5, 0x6c, 0xf5, 0xdf, 0xcd, 0x9a, 0xdb, },
  { 0xeb, 0x75, 0x09, 0x5c, 0xcd, 0x98, 0x6c, 0xd0, },
  { 0x51, 0xa9, 0xcb, 0x9e, 0xcb, 0xa3, 0x12, 0xe6, },
  { 0x96, 0xaf, 0xad, 0xfc, 0x2c, 0xe6, 0x66, 0xc7, },
  { 0x72, 0xfe, 0x52, 0x97, 0x5a, 0x43, 0x64, 0xee, },
  { 0x5a, 0x16, 0x45, 0xb2, 0x76, 0xd5, 0x92, 0xa1, },
  { 0xb2, 0x74, 0xcb, 0x8e, 0xbf, 0x87, 0x87, 0x0a, },
  { 0x6f, 0x9b, 0xb4, 0x20, 0x3d, 0xe7, 0xb3, 0x81, },
  { 0xea, 0xec, 0xb2, 0xa3, 0x0b, 0x22, 0xa8, 0x7f, },
  { 0x99, 0x24, 0xa4, 0x3c, 0xc1, 0x31, 0x57, 0x24, },
  { 0xbd, 0x83, 0x8d, 0x3a, 0xaf, 0xbf, 0x8d, 0xb7, },
  { 0x0b, 0x1a, 0x2a, 0x32, 0x65, 0xd5, 0x1a, 0xea, },
  { 0x13, 0x50, 0x79, 0xa3, 0x23, 0x1c, 0xe6, 0x60, },
  { 0x93, 0x2b, 0x28, 0x46, 0xe4, 0xd7, 0x06, 0x66, },
  { 0xe1, 0x91, 0x5f, 0x5c, 0xb1, 0xec, 0xa4, 0x6c, },
  { 0xf3, 0x25, 0x96, 0x5c, 0xa1, 0x6d, 0x62, 0x9f, },
  { 0x57, 0x5f, 0xf2, 0x8e, 0x60, 0x38, 0x1b, 0xe5, },
  { 0x72, 0x45, 0x06, 0xeb, 0x4c, 0x32, 0x8a, 0x95, }
};


int test_vectors()
{
#define MAXLEN 64
  u8 in[MAXLEN], out[8], k[16];
  int i;
  int ok = 1;

  for( i = 0; i < 16; ++i ) k[i] = i;

  for( i = 0; i < MAXLEN; ++i )
  {
    in[i] = i;
    crypto_auth( out, in, i, k );

    if ( memcmp( out, vectors[i], 8 ) )
    {
      printf( "test vector failed for %d bytes\n", i );
      ok = 0;
    }
  }

  return ok;
}

int main()
{
  if ( test_vectors() ) printf( "test vectors ok\n" );

  return 0;
}

#endif