diff options
author | 2023-05-04 02:41:16 +1000 | |
---|---|---|
committer | 2023-05-04 02:41:16 +1000 | |
commit | a504bde3a7462b54fafd5cfc2f52e58d0f3218e1 (patch) | |
tree | 8b3108d572b1a0873a6cdbb4e8af1f17179545c3 /3rdparty/lzma/C/Sha256.c | |
parent | befb9bf4a8cfdb2b693a32e32535b5eac522c5d8 (diff) |
3rdparty/lzma: Updated to LZMA SDK version 22.01
Diffstat (limited to '3rdparty/lzma/C/Sha256.c')
-rw-r--r-- | 3rdparty/lzma/C/Sha256.c | 452 |
1 files changed, 345 insertions, 107 deletions
diff --git a/3rdparty/lzma/C/Sha256.c b/3rdparty/lzma/C/Sha256.c index b5bc19b9602..8b3983ea732 100644 --- a/3rdparty/lzma/C/Sha256.c +++ b/3rdparty/lzma/C/Sha256.c @@ -1,5 +1,5 @@ -/* Crypto/Sha256.c -- SHA-256 Hash -2015-11-14 : Igor Pavlov : Public domain +/* Sha256.c -- SHA-256 Hash +2021-04-01 : Igor Pavlov : Public domain This code is based on public domain code from Wei Dai's Crypto++ library. */ #include "Precomp.h" @@ -10,16 +10,107 @@ This code is based on public domain code from Wei Dai's Crypto++ library. */ #include "RotateDefs.h" #include "Sha256.h" +#if defined(_MSC_VER) && (_MSC_VER < 1900) +// #define USE_MY_MM +#endif + +#ifdef MY_CPU_X86_OR_AMD64 + #ifdef _MSC_VER + #if _MSC_VER >= 1200 + #define _SHA_SUPPORTED + #endif + #elif defined(__clang__) + #if (__clang_major__ >= 8) // fix that check + #define _SHA_SUPPORTED + #endif + #elif defined(__GNUC__) + #if (__GNUC__ >= 8) // fix that check + #define _SHA_SUPPORTED + #endif + #elif defined(__INTEL_COMPILER) + #if (__INTEL_COMPILER >= 1800) // fix that check + #define _SHA_SUPPORTED + #endif + #endif +#elif defined(MY_CPU_ARM_OR_ARM64) + #ifdef _MSC_VER + #if _MSC_VER >= 1910 + #define _SHA_SUPPORTED + #endif + #elif defined(__clang__) + #if (__clang_major__ >= 8) // fix that check + #define _SHA_SUPPORTED + #endif + #elif defined(__GNUC__) + #if (__GNUC__ >= 6) // fix that check + #define _SHA_SUPPORTED + #endif + #endif +#endif + +void MY_FAST_CALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks); + +#ifdef _SHA_SUPPORTED + void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks); + + static SHA256_FUNC_UPDATE_BLOCKS g_FUNC_UPDATE_BLOCKS = Sha256_UpdateBlocks; + static SHA256_FUNC_UPDATE_BLOCKS g_FUNC_UPDATE_BLOCKS_HW; + + #define UPDATE_BLOCKS(p) p->func_UpdateBlocks +#else + #define UPDATE_BLOCKS(p) Sha256_UpdateBlocks +#endif + + +BoolInt Sha256_SetFunction(CSha256 *p, unsigned algo) +{ + SHA256_FUNC_UPDATE_BLOCKS func = Sha256_UpdateBlocks; + + #ifdef _SHA_SUPPORTED + if (algo != SHA256_ALGO_SW) + { + if (algo == SHA256_ALGO_DEFAULT) + func = g_FUNC_UPDATE_BLOCKS; + else + { + if (algo != SHA256_ALGO_HW) + return False; + func = g_FUNC_UPDATE_BLOCKS_HW; + if (!func) + return False; + } + } + #else + if (algo > 1) + return False; + #endif + + p->func_UpdateBlocks = func; + return True; +} + + /* define it for speed optimization */ -#ifndef _SFX -#define _SHA256_UNROLL -#define _SHA256_UNROLL2 + +#ifdef _SFX + #define STEP_PRE 1 + #define STEP_MAIN 1 +#else + #define STEP_PRE 2 + #define STEP_MAIN 4 + // #define _SHA256_UNROLL #endif -/* #define _SHA256_UNROLL2 */ +#if STEP_MAIN != 16 + #define _SHA256_BIG_W +#endif -void Sha256_Init(CSha256 *p) + + + +void Sha256_InitState(CSha256 *p) { + p->count = 0; p->state[0] = 0x6a09e667; p->state[1] = 0xbb67ae85; p->state[2] = 0x3c6ef372; @@ -28,7 +119,17 @@ void Sha256_Init(CSha256 *p) p->state[5] = 0x9b05688c; p->state[6] = 0x1f83d9ab; p->state[7] = 0x5be0cd19; - p->count = 0; +} + +void Sha256_Init(CSha256 *p) +{ + p->func_UpdateBlocks = + #ifdef _SHA_SUPPORTED + g_FUNC_UPDATE_BLOCKS; + #else + NULL; + #endif + Sha256_InitState(p); } #define S0(x) (rotrFixed(x, 2) ^ rotrFixed(x,13) ^ rotrFixed(x, 22)) @@ -36,61 +137,100 @@ void Sha256_Init(CSha256 *p) #define s0(x) (rotrFixed(x, 7) ^ rotrFixed(x,18) ^ (x >> 3)) #define s1(x) (rotrFixed(x,17) ^ rotrFixed(x,19) ^ (x >> 10)) -#define blk0(i) (W[i]) -#define blk2(i) (W[i] += s1(W[((i)-2)&15]) + W[((i)-7)&15] + s0(W[((i)-15)&15])) - #define Ch(x,y,z) (z^(x&(y^z))) #define Maj(x,y,z) ((x&y)|(z&(x|y))) -#ifdef _SHA256_UNROLL2 - -#define R(a,b,c,d,e,f,g,h, i) \ - h += S1(e) + Ch(e,f,g) + K[(i)+(j)] + (j ? blk2(i) : blk0(i)); \ - d += h; \ - h += S0(a) + Maj(a, b, c) -#define RX_8(i) \ - R(a,b,c,d,e,f,g,h, i); \ - R(h,a,b,c,d,e,f,g, i+1); \ - R(g,h,a,b,c,d,e,f, i+2); \ - R(f,g,h,a,b,c,d,e, i+3); \ - R(e,f,g,h,a,b,c,d, i+4); \ - R(d,e,f,g,h,a,b,c, i+5); \ - R(c,d,e,f,g,h,a,b, i+6); \ - R(b,c,d,e,f,g,h,a, i+7) +#define W_PRE(i) (W[(i) + (size_t)(j)] = GetBe32(data + ((size_t)(j) + i) * 4)) -#define RX_16 RX_8(0); RX_8(8); +#define blk2_main(j, i) s1(w(j, (i)-2)) + w(j, (i)-7) + s0(w(j, (i)-15)) +#ifdef _SHA256_BIG_W + // we use +i instead of +(i) to change the order to solve CLANG compiler warning for signed/unsigned. + #define w(j, i) W[(size_t)(j) + i] + #define blk2(j, i) (w(j, i) = w(j, (i)-16) + blk2_main(j, i)) #else + #if STEP_MAIN == 16 + #define w(j, i) W[(i) & 15] + #else + #define w(j, i) W[((size_t)(j) + (i)) & 15] + #endif + #define blk2(j, i) (w(j, i) += blk2_main(j, i)) +#endif -#define a(i) T[(0-(i))&7] -#define b(i) T[(1-(i))&7] -#define c(i) T[(2-(i))&7] -#define d(i) T[(3-(i))&7] -#define e(i) T[(4-(i))&7] -#define f(i) T[(5-(i))&7] -#define g(i) T[(6-(i))&7] -#define h(i) T[(7-(i))&7] - -#define R(i) \ - h(i) += S1(e(i)) + Ch(e(i),f(i),g(i)) + K[(i)+(j)] + (j ? blk2(i) : blk0(i)); \ - d(i) += h(i); \ - h(i) += S0(a(i)) + Maj(a(i), b(i), c(i)) \ +#define W_MAIN(i) blk2(j, i) -#ifdef _SHA256_UNROLL -#define RX_8(i) R(i+0); R(i+1); R(i+2); R(i+3); R(i+4); R(i+5); R(i+6); R(i+7); -#define RX_16 RX_8(0); RX_8(8); +#define T1(wx, i) \ + tmp = h + S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + wx(i); \ + h = g; \ + g = f; \ + f = e; \ + e = d + tmp; \ + tmp += S0(a) + Maj(a, b, c); \ + d = c; \ + c = b; \ + b = a; \ + a = tmp; \ -#else +#define R1_PRE(i) T1( W_PRE, i) +#define R1_MAIN(i) T1( W_MAIN, i) -#define RX_16 unsigned i; for (i = 0; i < 16; i++) { R(i); } +#if (!defined(_SHA256_UNROLL) || STEP_MAIN < 8) && (STEP_MAIN >= 4) +#define R2_MAIN(i) \ + R1_MAIN(i) \ + R1_MAIN(i + 1) \ #endif + + +#if defined(_SHA256_UNROLL) && STEP_MAIN >= 8 + +#define T4( a,b,c,d,e,f,g,h, wx, i) \ + h += S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + wx(i); \ + tmp = h; \ + h += d; \ + d = tmp + S0(a) + Maj(a, b, c); \ + +#define R4( wx, i) \ + T4 ( a,b,c,d,e,f,g,h, wx, (i )); \ + T4 ( d,a,b,c,h,e,f,g, wx, (i+1)); \ + T4 ( c,d,a,b,g,h,e,f, wx, (i+2)); \ + T4 ( b,c,d,a,f,g,h,e, wx, (i+3)); \ + +#define R4_PRE(i) R4( W_PRE, i) +#define R4_MAIN(i) R4( W_MAIN, i) + + +#define T8( a,b,c,d,e,f,g,h, wx, i) \ + h += S1(e) + Ch(e,f,g) + K[(i)+(size_t)(j)] + wx(i); \ + d += h; \ + h += S0(a) + Maj(a, b, c); \ + +#define R8( wx, i) \ + T8 ( a,b,c,d,e,f,g,h, wx, i ); \ + T8 ( h,a,b,c,d,e,f,g, wx, i+1); \ + T8 ( g,h,a,b,c,d,e,f, wx, i+2); \ + T8 ( f,g,h,a,b,c,d,e, wx, i+3); \ + T8 ( e,f,g,h,a,b,c,d, wx, i+4); \ + T8 ( d,e,f,g,h,a,b,c, wx, i+5); \ + T8 ( c,d,e,f,g,h,a,b, wx, i+6); \ + T8 ( b,c,d,e,f,g,h,a, wx, i+7); \ + +#define R8_PRE(i) R8( W_PRE, i) +#define R8_MAIN(i) R8( W_MAIN, i) + #endif -static const UInt32 K[64] = { +void MY_FAST_CALL Sha256_UpdateBlocks_HW(UInt32 state[8], const Byte *data, size_t numBlocks); + +// static +extern MY_ALIGN(64) +const UInt32 SHA256_K_ARRAY[64]; + +MY_ALIGN(64) +const UInt32 SHA256_K_ARRAY[64] = { 0x428a2f98, 0x71374491, 0xb5c0fbcf, 0xe9b5dba5, 0x3956c25b, 0x59f111f1, 0x923f82a4, 0xab1c5ed5, 0xd807aa98, 0x12835b01, 0x243185be, 0x550c7dc3, @@ -109,30 +249,27 @@ static const UInt32 K[64] = { 0x90befffa, 0xa4506ceb, 0xbef9a3f7, 0xc67178f2 }; -static void Sha256_WriteByteBlock(CSha256 *p) -{ - UInt32 W[16]; - unsigned j; - UInt32 *state; +#define K SHA256_K_ARRAY - #ifdef _SHA256_UNROLL2 - UInt32 a,b,c,d,e,f,g,h; + +MY_NO_INLINE +void MY_FAST_CALL Sha256_UpdateBlocks(UInt32 state[8], const Byte *data, size_t numBlocks) +{ + UInt32 W + #ifdef _SHA256_BIG_W + [64]; #else - UInt32 T[8]; + [16]; #endif - for (j = 0; j < 16; j += 4) - { - const Byte *ccc = p->buffer + j * 4; - W[j ] = GetBe32(ccc); - W[j + 1] = GetBe32(ccc + 4); - W[j + 2] = GetBe32(ccc + 8); - W[j + 3] = GetBe32(ccc + 12); - } + unsigned j; - state = p->state; + UInt32 a,b,c,d,e,f,g,h; - #ifdef _SHA256_UNROLL2 + #if !defined(_SHA256_UNROLL) || (STEP_MAIN <= 4) || (STEP_PRE <= 4) + UInt32 tmp; + #endif + a = state[0]; b = state[1]; c = state[2]; @@ -141,39 +278,96 @@ static void Sha256_WriteByteBlock(CSha256 *p) f = state[5]; g = state[6]; h = state[7]; - #else - for (j = 0; j < 8; j++) - T[j] = state[j]; - #endif - for (j = 0; j < 64; j += 16) + while (numBlocks) { - RX_16 + + for (j = 0; j < 16; j += STEP_PRE) + { + #if STEP_PRE > 4 + + #if STEP_PRE < 8 + R4_PRE(0); + #else + R8_PRE(0); + #if STEP_PRE == 16 + R8_PRE(8); + #endif + #endif + + #else + + R1_PRE(0); + #if STEP_PRE >= 2 + R1_PRE(1); + #if STEP_PRE >= 4 + R1_PRE(2); + R1_PRE(3); + #endif + #endif + + #endif + } + + for (j = 16; j < 64; j += STEP_MAIN) + { + #if defined(_SHA256_UNROLL) && STEP_MAIN >= 8 + + #if STEP_MAIN < 8 + R4_MAIN(0); + #else + R8_MAIN(0); + #if STEP_MAIN == 16 + R8_MAIN(8); + #endif + #endif + + #else + + R1_MAIN(0); + #if STEP_MAIN >= 2 + R1_MAIN(1); + #if STEP_MAIN >= 4 + R2_MAIN(2); + #if STEP_MAIN >= 8 + R2_MAIN(4); + R2_MAIN(6); + #if STEP_MAIN >= 16 + R2_MAIN(8); + R2_MAIN(10); + R2_MAIN(12); + R2_MAIN(14); + #endif + #endif + #endif + #endif + #endif + } + + a += state[0]; state[0] = a; + b += state[1]; state[1] = b; + c += state[2]; state[2] = c; + d += state[3]; state[3] = d; + e += state[4]; state[4] = e; + f += state[5]; state[5] = f; + g += state[6]; state[6] = g; + h += state[7]; state[7] = h; + + data += 64; + numBlocks--; } - #ifdef _SHA256_UNROLL2 - state[0] += a; - state[1] += b; - state[2] += c; - state[3] += d; - state[4] += e; - state[5] += f; - state[6] += g; - state[7] += h; - #else - for (j = 0; j < 8; j++) - state[j] += T[j]; - #endif - /* Wipe variables */ /* memset(W, 0, sizeof(W)); */ - /* memset(T, 0, sizeof(T)); */ } #undef S0 #undef S1 #undef s0 #undef s1 +#undef K + +#define Sha256_UpdateBlock(p) UPDATE_BLOCKS(p)(p->state, p->buffer, 1) void Sha256_Update(CSha256 *p, const Byte *data, size_t size) { @@ -193,25 +387,26 @@ void Sha256_Update(CSha256 *p, const Byte *data, size_t size) return; } - size -= num; - memcpy(p->buffer + pos, data, num); - data += num; + if (pos != 0) + { + size -= num; + memcpy(p->buffer + pos, data, num); + data += num; + Sha256_UpdateBlock(p); + } } - - for (;;) { - Sha256_WriteByteBlock(p); - if (size < 64) - break; - size -= 64; - memcpy(p->buffer, data, 64); - data += 64; - } - - if (size != 0) + size_t numBlocks = size >> 6; + UPDATE_BLOCKS(p)(p->state, data, numBlocks); + size &= 0x3F; + if (size == 0) + return; + data += (numBlocks << 6); memcpy(p->buffer, data, size); + } } + void Sha256_Final(CSha256 *p, Byte *digest) { unsigned pos = (unsigned)p->count & 0x3F; @@ -219,13 +414,30 @@ void Sha256_Final(CSha256 *p, Byte *digest) p->buffer[pos++] = 0x80; - while (pos != (64 - 8)) + if (pos > (64 - 8)) + { + while (pos != 64) { p->buffer[pos++] = 0; } + // memset(&p->buf.buffer[pos], 0, 64 - pos); + Sha256_UpdateBlock(p); + pos = 0; + } + + /* + if (pos & 3) { - pos &= 0x3F; - if (pos == 0) - Sha256_WriteByteBlock(p); - p->buffer[pos++] = 0; + p->buffer[pos] = 0; + p->buffer[pos + 1] = 0; + p->buffer[pos + 2] = 0; + pos += 3; + pos &= ~3; } + { + for (; pos < 64 - 8; pos += 4) + *(UInt32 *)(&p->buffer[pos]) = 0; + } + */ + + memset(&p->buffer[pos], 0, (64 - 8) - pos); { UInt64 numBits = (p->count << 3); @@ -233,16 +445,42 @@ void Sha256_Final(CSha256 *p, Byte *digest) SetBe32(p->buffer + 64 - 4, (UInt32)(numBits)); } - Sha256_WriteByteBlock(p); + Sha256_UpdateBlock(p); for (i = 0; i < 8; i += 2) { UInt32 v0 = p->state[i]; - UInt32 v1 = p->state[i + 1]; + UInt32 v1 = p->state[(size_t)i + 1]; SetBe32(digest , v0); SetBe32(digest + 4, v1); digest += 8; } - Sha256_Init(p); + Sha256_InitState(p); +} + + +void Sha256Prepare() +{ + #ifdef _SHA_SUPPORTED + SHA256_FUNC_UPDATE_BLOCKS f, f_hw; + f = Sha256_UpdateBlocks; + f_hw = NULL; + #ifdef MY_CPU_X86_OR_AMD64 + #ifndef USE_MY_MM + if (CPU_IsSupported_SHA() + && CPU_IsSupported_SSSE3() + // && CPU_IsSupported_SSE41() + ) + #endif + #else + if (CPU_IsSupported_SHA2()) + #endif + { + // printf("\n========== HW SHA256 ======== \n"); + f = f_hw = Sha256_UpdateBlocks_HW; + } + g_FUNC_UPDATE_BLOCKS = f; + g_FUNC_UPDATE_BLOCKS_HW = f_hw; + #endif } |