diff options
Diffstat (limited to '3rdparty/lzma/C/Aes.c')
-rw-r--r-- | 3rdparty/lzma/C/Aes.c | 274 |
1 files changed, 186 insertions, 88 deletions
diff --git a/3rdparty/lzma/C/Aes.c b/3rdparty/lzma/C/Aes.c index b10b9e58a55..bcaafab1188 100644 --- a/3rdparty/lzma/C/Aes.c +++ b/3rdparty/lzma/C/Aes.c @@ -1,10 +1,17 @@ /* Aes.c -- AES encryption / decryption -2016-05-21 : Igor Pavlov : Public domain */ +2023-04-02 : Igor Pavlov : Public domain */ #include "Precomp.h" -#include "Aes.h" #include "CpuArch.h" +#include "Aes.h" + +AES_CODE_FUNC g_AesCbc_Decode; +#ifndef Z7_SFX +AES_CODE_FUNC g_AesCbc_Encode; +AES_CODE_FUNC g_AesCtr_Code; +UInt32 g_Aes_SupportedFunctions_Flags; +#endif static UInt32 T[256 * 4]; static const Byte Sbox[256] = { @@ -25,23 +32,10 @@ static const Byte Sbox[256] = { 0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94, 0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf, 0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68, 0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16}; -void MY_FAST_CALL AesCbc_Encode(UInt32 *ivAes, Byte *data, size_t numBlocks); -void MY_FAST_CALL AesCbc_Decode(UInt32 *ivAes, Byte *data, size_t numBlocks); -void MY_FAST_CALL AesCtr_Code(UInt32 *ivAes, Byte *data, size_t numBlocks); - -void MY_FAST_CALL AesCbc_Encode_Intel(UInt32 *ivAes, Byte *data, size_t numBlocks); -void MY_FAST_CALL AesCbc_Decode_Intel(UInt32 *ivAes, Byte *data, size_t numBlocks); -void MY_FAST_CALL AesCtr_Code_Intel(UInt32 *ivAes, Byte *data, size_t numBlocks); - -AES_CODE_FUNC g_AesCbc_Encode; -AES_CODE_FUNC g_AesCbc_Decode; -AES_CODE_FUNC g_AesCtr_Code; static UInt32 D[256 * 4]; static Byte InvS[256]; -static const Byte Rcon[11] = { 0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36 }; - #define xtime(x) ((((x) << 1) ^ (((x) & 0x80) != 0 ? 0x1B : 0)) & 0xFF) #define Ui32(a0, a1, a2, a3) ((UInt32)(a0) | ((UInt32)(a1) << 8) | ((UInt32)(a2) << 16) | ((UInt32)(a3) << 24)) @@ -49,7 +43,43 @@ static const Byte Rcon[11] = { 0x00, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0 #define gb0(x) ( (x) & 0xFF) #define gb1(x) (((x) >> ( 8)) & 0xFF) #define gb2(x) (((x) >> (16)) & 0xFF) -#define gb3(x) (((x) >> (24)) & 0xFF) +#define gb3(x) (((x) >> (24))) + +#define gb(n, x) gb ## n(x) + +#define TT(x) (T + (x << 8)) +#define DD(x) (D + (x << 8)) + + +// #define Z7_SHOW_AES_STATUS + +#ifdef MY_CPU_X86_OR_AMD64 + #define USE_HW_AES +#elif defined(MY_CPU_ARM_OR_ARM64) && defined(MY_CPU_LE) + #if defined(__clang__) + #if (__clang_major__ >= 8) // fix that check + #define USE_HW_AES + #endif + #elif defined(__GNUC__) + #if (__GNUC__ >= 6) // fix that check + #define USE_HW_AES + #endif + #elif defined(_MSC_VER) + #if _MSC_VER >= 1910 + #define USE_HW_AES + #endif + #endif +#endif + +#ifdef USE_HW_AES +#ifdef Z7_SHOW_AES_STATUS +#include <stdio.h> +#define PRF(x) x +#else +#define PRF(x) +#endif +#endif + void AesGenTables(void) { @@ -60,46 +90,76 @@ void AesGenTables(void) for (i = 0; i < 256; i++) { { - UInt32 a1 = Sbox[i]; - UInt32 a2 = xtime(a1); - UInt32 a3 = a2 ^ a1; - T[ i] = Ui32(a2, a1, a1, a3); - T[0x100 + i] = Ui32(a3, a2, a1, a1); - T[0x200 + i] = Ui32(a1, a3, a2, a1); - T[0x300 + i] = Ui32(a1, a1, a3, a2); + const UInt32 a1 = Sbox[i]; + const UInt32 a2 = xtime(a1); + const UInt32 a3 = a2 ^ a1; + TT(0)[i] = Ui32(a2, a1, a1, a3); + TT(1)[i] = Ui32(a3, a2, a1, a1); + TT(2)[i] = Ui32(a1, a3, a2, a1); + TT(3)[i] = Ui32(a1, a1, a3, a2); } { - UInt32 a1 = InvS[i]; - UInt32 a2 = xtime(a1); - UInt32 a4 = xtime(a2); - UInt32 a8 = xtime(a4); - UInt32 a9 = a8 ^ a1; - UInt32 aB = a8 ^ a2 ^ a1; - UInt32 aD = a8 ^ a4 ^ a1; - UInt32 aE = a8 ^ a4 ^ a2; - D[ i] = Ui32(aE, a9, aD, aB); - D[0x100 + i] = Ui32(aB, aE, a9, aD); - D[0x200 + i] = Ui32(aD, aB, aE, a9); - D[0x300 + i] = Ui32(a9, aD, aB, aE); + const UInt32 a1 = InvS[i]; + const UInt32 a2 = xtime(a1); + const UInt32 a4 = xtime(a2); + const UInt32 a8 = xtime(a4); + const UInt32 a9 = a8 ^ a1; + const UInt32 aB = a8 ^ a2 ^ a1; + const UInt32 aD = a8 ^ a4 ^ a1; + const UInt32 aE = a8 ^ a4 ^ a2; + DD(0)[i] = Ui32(aE, a9, aD, aB); + DD(1)[i] = Ui32(aB, aE, a9, aD); + DD(2)[i] = Ui32(aD, aB, aE, a9); + DD(3)[i] = Ui32(a9, aD, aB, aE); } } - g_AesCbc_Encode = AesCbc_Encode; - g_AesCbc_Decode = AesCbc_Decode; - g_AesCtr_Code = AesCtr_Code; + { + AES_CODE_FUNC d = AesCbc_Decode; + #ifndef Z7_SFX + AES_CODE_FUNC e = AesCbc_Encode; + AES_CODE_FUNC c = AesCtr_Code; + UInt32 flags = 0; + #endif - #ifdef MY_CPU_X86_OR_AMD64 - if (CPU_Is_Aes_Supported()) + #ifdef USE_HW_AES + if (CPU_IsSupported_AES()) { - g_AesCbc_Encode = AesCbc_Encode_Intel; - g_AesCbc_Decode = AesCbc_Decode_Intel; - g_AesCtr_Code = AesCtr_Code_Intel; + // #pragma message ("AES HW") + PRF(printf("\n===AES HW\n")); + d = AesCbc_Decode_HW; + + #ifndef Z7_SFX + e = AesCbc_Encode_HW; + c = AesCtr_Code_HW; + flags = k_Aes_SupportedFunctions_HW; + #endif + + #ifdef MY_CPU_X86_OR_AMD64 + if (CPU_IsSupported_VAES_AVX2()) + { + PRF(printf("\n===vaes avx2\n")); + d = AesCbc_Decode_HW_256; + #ifndef Z7_SFX + c = AesCtr_Code_HW_256; + flags |= k_Aes_SupportedFunctions_HW_256; + #endif + } + #endif } #endif + + g_AesCbc_Decode = d; + #ifndef Z7_SFX + g_AesCbc_Encode = e; + g_AesCtr_Code = c; + g_Aes_SupportedFunctions_Flags = flags; + #endif + } } -#define HT(i, x, s) (T + (x << 8))[gb ## x(s[(i + x) & 3])] +#define HT(i, x, s) TT(x)[gb(x, s[(i + x) & 3])] #define HT4(m, i, s, p) m[i] = \ HT(i, 0, s) ^ \ @@ -113,11 +173,11 @@ void AesGenTables(void) HT4(m, 2, s, p); \ HT4(m, 3, s, p); \ -#define FT(i, x) Sbox[gb ## x(m[(i + x) & 3])] +#define FT(i, x) Sbox[gb(x, m[(i + x) & 3])] #define FT4(i) dest[i] = Ui32(FT(i, 0), FT(i, 1), FT(i, 2), FT(i, 3)) ^ w[i]; -#define HD(i, x, s) (D + (x << 8))[gb ## x(s[(i - x) & 3])] +#define HD(i, x, s) DD(x)[gb(x, s[(i - x) & 3])] #define HD4(m, i, s, p) m[i] = \ HD(i, 0, s) ^ \ @@ -131,13 +191,16 @@ void AesGenTables(void) HD4(m, 2, s, p); \ HD4(m, 3, s, p); \ -#define FD(i, x) InvS[gb ## x(m[(i - x) & 3])] +#define FD(i, x) InvS[gb(x, m[(i - x) & 3])] #define FD4(i) dest[i] = Ui32(FD(i, 0), FD(i, 1), FD(i, 2), FD(i, 3)) ^ w[i]; -void MY_FAST_CALL Aes_SetKey_Enc(UInt32 *w, const Byte *key, unsigned keySize) +void Z7_FASTCALL Aes_SetKey_Enc(UInt32 *w, const Byte *key, unsigned keySize) { - unsigned i, wSize; - wSize = keySize + 28; + unsigned i, m; + const UInt32 *wLim; + UInt32 t; + UInt32 rcon = 1; + keySize /= 4; w[0] = ((UInt32)keySize / 2) + 3; w += 4; @@ -145,19 +208,29 @@ void MY_FAST_CALL Aes_SetKey_Enc(UInt32 *w, const Byte *key, unsigned keySize) for (i = 0; i < keySize; i++, key += 4) w[i] = GetUi32(key); - for (; i < wSize; i++) + t = w[(size_t)keySize - 1]; + wLim = w + (size_t)keySize * 3 + 28; + m = 0; + do { - UInt32 t = w[i - 1]; - unsigned rem = i % keySize; - if (rem == 0) - t = Ui32(Sbox[gb1(t)] ^ Rcon[i / keySize], Sbox[gb2(t)], Sbox[gb3(t)], Sbox[gb0(t)]); - else if (keySize > 6 && rem == 4) + if (m == 0) + { + t = Ui32(Sbox[gb1(t)] ^ rcon, Sbox[gb2(t)], Sbox[gb3(t)], Sbox[gb0(t)]); + rcon <<= 1; + if (rcon & 0x100) + rcon = 0x1b; + m = keySize; + } + else if (m == 4 && keySize > 6) t = Ui32(Sbox[gb0(t)], Sbox[gb1(t)], Sbox[gb2(t)], Sbox[gb3(t)]); - w[i] = w[i - keySize] ^ t; + m--; + t ^= w[0]; + w[keySize] = t; } + while (++w != wLim); } -void MY_FAST_CALL Aes_SetKey_Dec(UInt32 *w, const Byte *key, unsigned keySize) +void Z7_FASTCALL Aes_SetKey_Dec(UInt32 *w, const Byte *key, unsigned keySize) { unsigned i, num; Aes_SetKey_Enc(w, key, keySize); @@ -167,10 +240,10 @@ void MY_FAST_CALL Aes_SetKey_Dec(UInt32 *w, const Byte *key, unsigned keySize) { UInt32 r = w[i]; w[i] = - D[ (unsigned)Sbox[gb0(r)]] ^ - D[0x100 + (unsigned)Sbox[gb1(r)]] ^ - D[0x200 + (unsigned)Sbox[gb2(r)]] ^ - D[0x300 + (unsigned)Sbox[gb3(r)]]; + DD(0)[Sbox[gb0(r)]] ^ + DD(1)[Sbox[gb1(r)]] ^ + DD(2)[Sbox[gb2(r)]] ^ + DD(3)[Sbox[gb3(r)]]; } } @@ -178,6 +251,7 @@ void MY_FAST_CALL Aes_SetKey_Dec(UInt32 *w, const Byte *key, unsigned keySize) src and dest are pointers to 4 UInt32 words. src and dest can point to same block */ +// Z7_FORCE_INLINE static void Aes_Encode(const UInt32 *w, UInt32 *dest, const UInt32 *src) { UInt32 s[4]; @@ -191,16 +265,20 @@ static void Aes_Encode(const UInt32 *w, UInt32 *dest, const UInt32 *src) w += 4; for (;;) { - HT16(m, s, 0); + HT16(m, s, 0) if (--numRounds2 == 0) break; - HT16(s, m, 4); + HT16(s, m, 4) w += 8; } w += 4; - FT4(0); FT4(1); FT4(2); FT4(3); + FT4(0) + FT4(1) + FT4(2) + FT4(3) } +Z7_FORCE_INLINE static void Aes_Decode(const UInt32 *w, UInt32 *dest, const UInt32 *src) { UInt32 s[4]; @@ -214,12 +292,15 @@ static void Aes_Decode(const UInt32 *w, UInt32 *dest, const UInt32 *src) for (;;) { w -= 8; - HD16(m, s, 4); + HD16(m, s, 4) if (--numRounds2 == 0) break; - HD16(s, m, 0); + HD16(s, m, 0) } - FD4(0); FD4(1); FD4(2); FD4(3); + FD4(0) + FD4(1) + FD4(2) + FD4(3) } void AesCbc_Init(UInt32 *p, const Byte *iv) @@ -229,7 +310,7 @@ void AesCbc_Init(UInt32 *p, const Byte *iv) p[i] = GetUi32(iv + i * 4); } -void MY_FAST_CALL AesCbc_Encode(UInt32 *p, Byte *data, size_t numBlocks) +void Z7_FASTCALL AesCbc_Encode(UInt32 *p, Byte *data, size_t numBlocks) { for (; numBlocks != 0; numBlocks--, data += AES_BLOCK_SIZE) { @@ -240,14 +321,14 @@ void MY_FAST_CALL AesCbc_Encode(UInt32 *p, Byte *data, size_t numBlocks) Aes_Encode(p + 4, p, p); - SetUi32(data, p[0]); - SetUi32(data + 4, p[1]); - SetUi32(data + 8, p[2]); - SetUi32(data + 12, p[3]); + SetUi32(data, p[0]) + SetUi32(data + 4, p[1]) + SetUi32(data + 8, p[2]) + SetUi32(data + 12, p[3]) } } -void MY_FAST_CALL AesCbc_Decode(UInt32 *p, Byte *data, size_t numBlocks) +void Z7_FASTCALL AesCbc_Decode(UInt32 *p, Byte *data, size_t numBlocks) { UInt32 in[4], out[4]; for (; numBlocks != 0; numBlocks--, data += AES_BLOCK_SIZE) @@ -259,10 +340,10 @@ void MY_FAST_CALL AesCbc_Decode(UInt32 *p, Byte *data, size_t numBlocks) Aes_Decode(p + 4, out, in); - SetUi32(data, p[0] ^ out[0]); - SetUi32(data + 4, p[1] ^ out[1]); - SetUi32(data + 8, p[2] ^ out[2]); - SetUi32(data + 12, p[3] ^ out[3]); + SetUi32(data, p[0] ^ out[0]) + SetUi32(data + 4, p[1] ^ out[1]) + SetUi32(data + 8, p[2] ^ out[2]) + SetUi32(data + 12, p[3] ^ out[3]) p[0] = in[0]; p[1] = in[1]; @@ -271,25 +352,42 @@ void MY_FAST_CALL AesCbc_Decode(UInt32 *p, Byte *data, size_t numBlocks) } } -void MY_FAST_CALL AesCtr_Code(UInt32 *p, Byte *data, size_t numBlocks) +void Z7_FASTCALL AesCtr_Code(UInt32 *p, Byte *data, size_t numBlocks) { for (; numBlocks != 0; numBlocks--) { UInt32 temp[4]; - Byte buf[16]; - int i; + unsigned i; if (++p[0] == 0) p[1]++; Aes_Encode(p + 4, temp, p); - SetUi32(buf, temp[0]); - SetUi32(buf + 4, temp[1]); - SetUi32(buf + 8, temp[2]); - SetUi32(buf + 12, temp[3]); - - for (i = 0; i < 16; i++) - *data++ ^= buf[i]; + for (i = 0; i < 4; i++, data += 4) + { + const UInt32 t = temp[i]; + + #ifdef MY_CPU_LE_UNALIGN + *((UInt32 *)(void *)data) ^= t; + #else + data[0] = (Byte)(data[0] ^ (t & 0xFF)); + data[1] = (Byte)(data[1] ^ ((t >> 8) & 0xFF)); + data[2] = (Byte)(data[2] ^ ((t >> 16) & 0xFF)); + data[3] = (Byte)(data[3] ^ ((t >> 24))); + #endif + } } } + +#undef xtime +#undef Ui32 +#undef gb0 +#undef gb1 +#undef gb2 +#undef gb3 +#undef gb +#undef TT +#undef DD +#undef USE_HW_AES +#undef PRF |