0da635fd1b
On recent x86-64 system with march=native|<cpu>|<microarchitecture
level> gcc/clang will automatically define all the available vector
extensions macros. crypto/blake2-config.h then correctly set all the
HAVE_<EXTENSION> macros.
crypto/blake2-round.h then checks the HAVE_<EXTENSION> macros for
including further headers:
#if defined(HAVE_SSE41)
#include "blake2b-load-sse41.h"
#else
#include "blake2b-load-sse2.h"
#endif
which is wrong. On recent systems it always results in including
blake2b-load-sse41.h. crypto/blake2-round.h itself is included by
crypto/blake2b-sse2.c and now we have a SSE2/SSE4.1 code mixing
resulting in the incompatible type for argument build errors described
in #589.
The idea is to remove the lines above from crypto/blake2-round.h and put
the includes directly into crypto/blake2b-sse2.c and
crypto/blake2b-sse41.c respectively.
Note this slightly diverges from the upstream BLAKE2 sources.
Pull-request: #591
Author: Tino Mai <mai.tino@gmail.com>
Signed-off-by: David Sterba <dsterba@suse.com>
100 lines
2.9 KiB
C
100 lines
2.9 KiB
C
/*
|
|
BLAKE2 reference source code package - optimized C implementations
|
|
|
|
Copyright 2012, Samuel Neves <sneves@dei.uc.pt>. You may use this under the
|
|
terms of the CC0, the OpenSSL Licence, or the Apache Public License 2.0, at
|
|
your option. The terms of these licenses can be found at:
|
|
|
|
- CC0 1.0 Universal : http://creativecommons.org/publicdomain/zero/1.0
|
|
- OpenSSL license : https://www.openssl.org/source/license.html
|
|
- Apache 2.0 : http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
More information about the BLAKE2 hash function can be found at
|
|
https://blake2.net.
|
|
*/
|
|
|
|
#include <stdint.h>
|
|
#include <string.h>
|
|
#include <stdio.h>
|
|
|
|
#include "blake2.h"
|
|
#include "blake2-impl.h"
|
|
#include "blake2-config.h"
|
|
|
|
#ifdef HAVE_SSE41
|
|
|
|
#include <emmintrin.h>
|
|
#if defined(HAVE_SSSE3)
|
|
#include <tmmintrin.h>
|
|
#endif
|
|
#if defined(HAVE_SSE41)
|
|
#include <smmintrin.h>
|
|
#endif
|
|
#if defined(HAVE_XOP)
|
|
#include <x86intrin.h>
|
|
#endif
|
|
|
|
#include "blake2b-load-sse41.h"
|
|
#include "blake2b-round.h"
|
|
|
|
static const uint64_t blake2b_IV[8] =
|
|
{
|
|
0x6a09e667f3bcc908ULL, 0xbb67ae8584caa73bULL,
|
|
0x3c6ef372fe94f82bULL, 0xa54ff53a5f1d36f1ULL,
|
|
0x510e527fade682d1ULL, 0x9b05688c2b3e6c1fULL,
|
|
0x1f83d9abfb41bd6bULL, 0x5be0cd19137e2179ULL
|
|
};
|
|
|
|
void blake2b_compress_sse41( blake2b_state *S, const uint8_t block[BLAKE2B_BLOCKBYTES] )
|
|
{
|
|
__m128i row1l, row1h;
|
|
__m128i row2l, row2h;
|
|
__m128i row3l, row3h;
|
|
__m128i row4l, row4h;
|
|
__m128i b0, b1;
|
|
__m128i t0, t1;
|
|
#if defined(HAVE_SSSE3) && !defined(HAVE_XOP)
|
|
const __m128i r16 = _mm_setr_epi8( 2, 3, 4, 5, 6, 7, 0, 1, 10, 11, 12, 13, 14, 15, 8, 9 );
|
|
const __m128i r24 = _mm_setr_epi8( 3, 4, 5, 6, 7, 0, 1, 2, 11, 12, 13, 14, 15, 8, 9, 10 );
|
|
#endif
|
|
const __m128i m0 = LOADU( block + 00 );
|
|
const __m128i m1 = LOADU( block + 16 );
|
|
const __m128i m2 = LOADU( block + 32 );
|
|
const __m128i m3 = LOADU( block + 48 );
|
|
const __m128i m4 = LOADU( block + 64 );
|
|
const __m128i m5 = LOADU( block + 80 );
|
|
const __m128i m6 = LOADU( block + 96 );
|
|
const __m128i m7 = LOADU( block + 112 );
|
|
|
|
row1l = LOADU( &S->h[0] );
|
|
row1h = LOADU( &S->h[2] );
|
|
row2l = LOADU( &S->h[4] );
|
|
row2h = LOADU( &S->h[6] );
|
|
row3l = LOADU( &blake2b_IV[0] );
|
|
row3h = LOADU( &blake2b_IV[2] );
|
|
row4l = _mm_xor_si128( LOADU( &blake2b_IV[4] ), LOADU( &S->t[0] ) );
|
|
row4h = _mm_xor_si128( LOADU( &blake2b_IV[6] ), LOADU( &S->f[0] ) );
|
|
ROUND( 0 );
|
|
ROUND( 1 );
|
|
ROUND( 2 );
|
|
ROUND( 3 );
|
|
ROUND( 4 );
|
|
ROUND( 5 );
|
|
ROUND( 6 );
|
|
ROUND( 7 );
|
|
ROUND( 8 );
|
|
ROUND( 9 );
|
|
ROUND( 10 );
|
|
ROUND( 11 );
|
|
row1l = _mm_xor_si128( row3l, row1l );
|
|
row1h = _mm_xor_si128( row3h, row1h );
|
|
STOREU( &S->h[0], _mm_xor_si128( LOADU( &S->h[0] ), row1l ) );
|
|
STOREU( &S->h[2], _mm_xor_si128( LOADU( &S->h[2] ), row1h ) );
|
|
row2l = _mm_xor_si128( row4l, row2l );
|
|
row2h = _mm_xor_si128( row4h, row2h );
|
|
STOREU( &S->h[4], _mm_xor_si128( LOADU( &S->h[4] ), row2l ) );
|
|
STOREU( &S->h[6], _mm_xor_si128( LOADU( &S->h[6] ), row2h ) );
|
|
}
|
|
|
|
#endif
|