diff --git a/common/tracy_lz4.cpp b/common/tracy_lz4.cpp index 0cecdc1d..9f5e9bfa 100644 --- a/common/tracy_lz4.cpp +++ b/common/tracy_lz4.cpp @@ -45,10 +45,16 @@ #endif /* - * ACCELERATION_DEFAULT : + * LZ4_ACCELERATION_DEFAULT : * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 */ -#define ACCELERATION_DEFAULT 1 +#define LZ4_ACCELERATION_DEFAULT 1 +/* + * LZ4_ACCELERATION_MAX : + * Any "acceleration" value higher than this threshold + * get treated as LZ4_ACCELERATION_MAX instead (fix #876) + */ +#define LZ4_ACCELERATION_MAX 65537 /*-************************************ @@ -82,6 +88,7 @@ * Define this parameter if your target system or compiler does not support hardware bit count */ #if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */ +# undef LZ4_FORCE_SW_BITCOUNT /* avoid double def */ # define LZ4_FORCE_SW_BITCOUNT #endif @@ -106,17 +113,17 @@ #define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */ #endif -#include "tracy_lz4.hpp" +#define LZ4_STATIC_LINKING_ONLY /* LZ4_DISTANCE_MAX */ +#include "lz4.h" /* see also "memory routines" below */ /*-************************************ * Compiler Options **************************************/ -#ifdef _MSC_VER /* Visual Studio */ -# include -# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ -# pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ +#if defined(_MSC_VER) && (_MSC_VER >= 1400) /* Visual Studio 2005+ */ +# include /* only present in VS2005+ */ +# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ #endif /* _MSC_VER */ #ifndef LZ4_FORCE_INLINE @@ -135,7 +142,7 @@ # endif /* _MSC_VER */ #endif /* LZ4_FORCE_INLINE */ -/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE +/* LZ4_FORCE_O2 and LZ4_FORCE_INLINE * gcc on ppc64le generates an unrolled SIMDized loop for LZ4_wildCopy8, * together with a simple 8-byte copy loop as a fall-back path. * However, this optimization hurts the decompression speed by >30%, @@ -150,11 +157,11 @@ * of LZ4_wildCopy8 does not affect the compression speed. */ #if defined(__PPC64__) && defined(__LITTLE_ENDIAN__) && defined(__GNUC__) && !defined(__clang__) -# define LZ4_FORCE_O2_GCC_PPC64LE __attribute__((optimize("O2"))) -# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE __attribute__((optimize("O2"))) LZ4_FORCE_INLINE +# define LZ4_FORCE_O2 __attribute__((optimize("O2"))) +# undef LZ4_FORCE_INLINE +# define LZ4_FORCE_INLINE static __inline __attribute__((optimize("O2"),always_inline)) #else -# define LZ4_FORCE_O2_GCC_PPC64LE -# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static +# define LZ4_FORCE_O2 #endif #if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) @@ -170,249 +177,37 @@ #define unlikely(expr) expect((expr) != 0, 0) #endif +/* Should the alignment test prove unreliable, for some reason, + * it can be disabled by setting LZ4_ALIGN_TEST to 0 */ +#ifndef LZ4_ALIGN_TEST /* can be externally provided */ +# define LZ4_ALIGN_TEST 1 +#endif + /*-************************************ * Memory routines **************************************/ -#include /* malloc, calloc, free */ -#define ALLOC(s) malloc(s) -#define ALLOC_AND_ZERO(s) calloc(1,s) -#define FREEMEM(p) free(p) +#ifdef LZ4_USER_MEMORY_FUNCTIONS +/* memory management functions can be customized by user project. + * Below functions must exist somewhere in the Project + * and be available at link time */ +void* LZ4_malloc(size_t s); +void* LZ4_calloc(size_t n, size_t s); +void LZ4_free(void* p); +# define ALLOC(s) LZ4_malloc(s) +# define ALLOC_AND_ZERO(s) LZ4_calloc(1,s) +# define FREEMEM(p) LZ4_free(p) +#else +# include /* malloc, calloc, free */ +# define ALLOC(s) malloc(s) +# define ALLOC_AND_ZERO(s) calloc(1,s) +# define FREEMEM(p) free(p) +#endif + #include /* memset, memcpy */ #define MEM_INIT(p,v,s) memset((p),(v),(s)) -/*-************************************ -* Types -**************************************/ -#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -# include - typedef uint8_t BYTE; - typedef uint16_t U16; - typedef uint32_t U32; - typedef int32_t S32; - typedef uint64_t U64; - typedef uintptr_t uptrval; -#else - typedef unsigned char BYTE; - typedef unsigned short U16; - typedef unsigned int U32; - typedef signed int S32; - typedef unsigned long long U64; - typedef size_t uptrval; /* generally true, except OpenVMS-64 */ -#endif - -#if defined(__x86_64__) - typedef U64 reg_t; /* 64-bits in x32 mode */ -#else - typedef size_t reg_t; /* 32-bits in x32 mode */ -#endif - -namespace tracy -{ - -typedef enum { - notLimited = 0, - limitedOutput = 1, - fillOutput = 2 -} limitedOutput_directive; - - -/*-************************************ -* Reading and writing into memory -**************************************/ -static unsigned LZ4_isLittleEndian(void) -{ - const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ - return one.c[0]; -} - - -#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2) -/* lie to the compiler about data alignment; use with caution */ - -LZ4_FORCE_INLINE U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; } -LZ4_FORCE_INLINE U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; } -LZ4_FORCE_INLINE reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; } - -LZ4_FORCE_INLINE void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } -LZ4_FORCE_INLINE void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } - -#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1) - -/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ -/* currently only defined for gcc and icc */ -typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign; - -LZ4_FORCE_INLINE U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; } -LZ4_FORCE_INLINE U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; } -LZ4_FORCE_INLINE reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; } - -LZ4_FORCE_INLINE void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; } -LZ4_FORCE_INLINE void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; } - -#else /* safe and portable access using memcpy() */ - -LZ4_FORCE_INLINE U16 LZ4_read16(const void* memPtr) -{ - U16 val; memcpy(&val, memPtr, sizeof(val)); return val; -} - -LZ4_FORCE_INLINE U32 LZ4_read32(const void* memPtr) -{ - U32 val; memcpy(&val, memPtr, sizeof(val)); return val; -} - -LZ4_FORCE_INLINE reg_t LZ4_read_ARCH(const void* memPtr) -{ - reg_t val; memcpy(&val, memPtr, sizeof(val)); return val; -} - -LZ4_FORCE_INLINE void LZ4_write16(void* memPtr, U16 value) -{ - memcpy(memPtr, &value, sizeof(value)); -} - -LZ4_FORCE_INLINE void LZ4_write32(void* memPtr, U32 value) -{ - memcpy(memPtr, &value, sizeof(value)); -} - -#endif /* LZ4_FORCE_MEMORY_ACCESS */ - - -LZ4_FORCE_INLINE U16 LZ4_readLE16(const void* memPtr) -{ - if (LZ4_isLittleEndian()) { - return LZ4_read16(memPtr); - } else { - const BYTE* p = (const BYTE*)memPtr; - return (U16)((U16)p[0] + (p[1]<<8)); - } -} - -LZ4_FORCE_INLINE void LZ4_writeLE16(void* memPtr, U16 value) -{ - if (LZ4_isLittleEndian()) { - LZ4_write16(memPtr, value); - } else { - BYTE* p = (BYTE*)memPtr; - p[0] = (BYTE) value; - p[1] = (BYTE)(value>>8); - } -} - -/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ -LZ4_FORCE_O2_INLINE_GCC_PPC64LE -void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd) -{ - BYTE* d = (BYTE*)dstPtr; - const BYTE* s = (const BYTE*)srcPtr; - BYTE* const e = (BYTE*)dstEnd; - - do { memcpy(d,s,8); d+=8; s+=8; } while (d= 16. */ -LZ4_FORCE_O2_INLINE_GCC_PPC64LE void -LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd) -{ - BYTE* d = (BYTE*)dstPtr; - const BYTE* s = (const BYTE*)srcPtr; - BYTE* const e = (BYTE*)dstEnd; - - do { memcpy(d,s,16); memcpy(d+16,s+16,16); d+=32; s+=32; } while (d 65535) /* max supported by LZ4 format */ +#define LZ4_DISTANCE_ABSOLUTE_MAX 65535 +#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX) /* max supported by LZ4 format */ # error "LZ4_DISTANCE_MAX is too big : must be <= 65535" #endif @@ -458,89 +250,354 @@ static const int LZ4_minLength = (MFLIMIT+1); #if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2) # include -static int g_debuglog_enable = 1; -# define DEBUGLOG(l, ...) { \ - if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \ - fprintf(stderr, __FILE__ ": "); \ - fprintf(stderr, __VA_ARGS__); \ - fprintf(stderr, " \n"); \ - } } + static int g_debuglog_enable = 1; +# define DEBUGLOG(l, ...) { \ + if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) { \ + fprintf(stderr, __FILE__ ": "); \ + fprintf(stderr, __VA_ARGS__); \ + fprintf(stderr, " \n"); \ + } } #else -# define DEBUGLOG(l, ...) {} /* disabled */ +# define DEBUGLOG(l, ...) {} /* disabled */ +#endif + +static int LZ4_isAligned(const void* ptr, size_t alignment) +{ + return ((size_t)ptr & (alignment -1)) == 0; +} + + +/*-************************************ +* Types +**************************************/ +#include +#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) +# include + typedef uint8_t BYTE; + typedef uint16_t U16; + typedef uint32_t U32; + typedef int32_t S32; + typedef uint64_t U64; + typedef uintptr_t uptrval; +#else +# if UINT_MAX != 4294967295UL +# error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4" +# endif + typedef unsigned char BYTE; + typedef unsigned short U16; + typedef unsigned int U32; + typedef signed int S32; + typedef unsigned long long U64; + typedef size_t uptrval; /* generally true, except OpenVMS-64 */ +#endif + +#if defined(__x86_64__) + typedef U64 reg_t; /* 64-bits in x32 mode */ +#else + typedef size_t reg_t; /* 32-bits in x32 mode */ +#endif + +typedef enum { + notLimited = 0, + limitedOutput = 1, + fillOutput = 2 +} limitedOutput_directive; + + +/*-************************************ +* Reading and writing into memory +**************************************/ + +/** + * LZ4 relies on memcpy with a constant size being inlined. In freestanding + * environments, the compiler can't assume the implementation of memcpy() is + * standard compliant, so it can't apply its specialized memcpy() inlining + * logic. When possible, use __builtin_memcpy() to tell the compiler to analyze + * memcpy() as if it were standard compliant, so it can inline it in freestanding + * environments. This is needed when decompressing the Linux Kernel, for example. + */ +#if defined(__GNUC__) && (__GNUC__ >= 4) +#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size) +#else +#define LZ4_memcpy(dst, src, size) memcpy(dst, src, size) +#endif + +static unsigned LZ4_isLittleEndian(void) +{ + const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ + return one.c[0]; +} + + +#if defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==2) +/* lie to the compiler about data alignment; use with caution */ + +static U16 LZ4_read16(const void* memPtr) { return *(const U16*) memPtr; } +static U32 LZ4_read32(const void* memPtr) { return *(const U32*) memPtr; } +static reg_t LZ4_read_ARCH(const void* memPtr) { return *(const reg_t*) memPtr; } + +static void LZ4_write16(void* memPtr, U16 value) { *(U16*)memPtr = value; } +static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } + +#elif defined(LZ4_FORCE_MEMORY_ACCESS) && (LZ4_FORCE_MEMORY_ACCESS==1) + +/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */ +/* currently only defined for gcc and icc */ +typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign; + +static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; } +static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; } +static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; } + +static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; } +static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; } + +#else /* safe and portable access using memcpy() */ + +static U16 LZ4_read16(const void* memPtr) +{ + U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; +} + +static U32 LZ4_read32(const void* memPtr) +{ + U32 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; +} + +static reg_t LZ4_read_ARCH(const void* memPtr) +{ + reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; +} + +static void LZ4_write16(void* memPtr, U16 value) +{ + LZ4_memcpy(memPtr, &value, sizeof(value)); +} + +static void LZ4_write32(void* memPtr, U32 value) +{ + LZ4_memcpy(memPtr, &value, sizeof(value)); +} + +#endif /* LZ4_FORCE_MEMORY_ACCESS */ + + +static U16 LZ4_readLE16(const void* memPtr) +{ + if (LZ4_isLittleEndian()) { + return LZ4_read16(memPtr); + } else { + const BYTE* p = (const BYTE*)memPtr; + return (U16)((U16)p[0] + (p[1]<<8)); + } +} + +static void LZ4_writeLE16(void* memPtr, U16 value) +{ + if (LZ4_isLittleEndian()) { + LZ4_write16(memPtr, value); + } else { + BYTE* p = (BYTE*)memPtr; + p[0] = (BYTE) value; + p[1] = (BYTE)(value>>8); + } +} + +/* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ +LZ4_FORCE_INLINE +void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; + + do { LZ4_memcpy(d,s,8); d+=8; s+=8; } while (d= 16. */ +LZ4_FORCE_INLINE void +LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; + + do { LZ4_memcpy(d,s,16); LZ4_memcpy(d+16,s+16,16); d+=32; s+=32; } while (d= dstPtr + MINMATCH + * - there is at least 8 bytes available to write after dstEnd */ +LZ4_FORCE_INLINE void +LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset) +{ + BYTE v[8]; + + assert(dstEnd >= dstPtr + MINMATCH); + + switch(offset) { + case 1: + MEM_INIT(v, *srcPtr, 8); + break; + case 2: + LZ4_memcpy(v, srcPtr, 2); + LZ4_memcpy(&v[2], srcPtr, 2); + LZ4_memcpy(&v[4], v, 4); + break; + case 4: + LZ4_memcpy(v, srcPtr, 4); + LZ4_memcpy(&v[4], srcPtr, 4); + break; + default: + LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset); + return; + } + + LZ4_memcpy(dstPtr, v, 8); + dstPtr += 8; + while (dstPtr < dstEnd) { + LZ4_memcpy(dstPtr, v, 8); + dstPtr += 8; + } +} #endif /*-************************************ * Common functions **************************************/ -LZ4_FORCE_INLINE -unsigned LZ4_NbCommonBytes (reg_t val) +static unsigned LZ4_NbCommonBytes (reg_t val) { + assert(val != 0); if (LZ4_isLittleEndian()) { - if (sizeof(val)==8) { -# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (unsigned)_tzcnt_u64((U64)val)>>3; -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctzll((U64)val) >> 3); + if (sizeof(val) == 8) { +# if defined(_MSC_VER) && (_MSC_VER >= 1800) && defined(_M_AMD64) && !defined(LZ4_FORCE_SW_BITCOUNT) + /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */ + return (unsigned)_tzcnt_u64(val) >> 3; +# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r = 0; + _BitScanForward64(&r, (U64)val); + return (unsigned)r >> 3; +# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_ctzll((U64)val) >> 3; # else - static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, - 0, 3, 1, 3, 1, 4, 2, 7, - 0, 2, 3, 6, 1, 5, 3, 5, - 1, 3, 4, 4, 2, 5, 6, 7, - 7, 0, 1, 2, 3, 3, 4, 6, - 2, 6, 5, 5, 3, 4, 5, 6, - 7, 1, 2, 4, 6, 4, 4, 5, - 7, 2, 6, 5, 7, 6, 7, 7 }; - return DeBruijnBytePos[((U64)((val & -(long long)val) * 0x0218A392CDABBD3FULL)) >> 58]; + const U64 m = 0x0101010101010101ULL; + val ^= val - 1; + return (unsigned)(((U64)((val & (m - 1)) * m)) >> 56); # endif } else /* 32 bits */ { -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (unsigned)_tzcnt_u32((U32)val)>>3; -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctz((U32)val) >> 3); +# if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT) + unsigned long r; + _BitScanForward(&r, (U32)val); + return (unsigned)r >> 3; +# elif (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_ctz((U32)val) >> 3; # else - static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, - 3, 2, 2, 1, 3, 2, 0, 1, - 3, 3, 1, 2, 2, 2, 2, 0, - 3, 1, 2, 0, 1, 0, 1, 1 }; - return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; + const U32 m = 0x01010101; + return (unsigned)((((val - 1) ^ val) & (m - 1)) * m) >> 24; # endif } } else /* Big Endian CPU */ { - if (sizeof(val)==8) { /* 64-bits */ -# if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse64( &r, val ); - return (unsigned)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clzll((U64)val) >> 3); + if (sizeof(val)==8) { +# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(__TINYC__) && !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_clzll((U64)val) >> 3; # else +#if 1 + /* this method is probably faster, + * but adds a 128 bytes lookup table */ + static const unsigned char ctz7_tab[128] = { + 7, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 6, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 5, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + 4, 0, 1, 0, 2, 0, 1, 0, 3, 0, 1, 0, 2, 0, 1, 0, + }; + U64 const mask = 0x0101010101010101ULL; + U64 const t = (((val >> 8) - mask) | val) & mask; + return ctz7_tab[(t * 0x0080402010080402ULL) >> 57]; +#else + /* this method doesn't consume memory space like the previous one, + * but it contains several branches, + * that may end up slowing execution */ static const U32 by32 = sizeof(val)*4; /* 32 on 64 bits (goal), 16 on 32 bits. - Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. - Note that this code path is never triggered in 32-bits mode. */ + Just to avoid some static analyzer complaining about shift by 32 on 32-bits target. + Note that this code path is never triggered in 32-bits mode. */ unsigned r; if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } r += (!val); return r; +#endif # endif } else /* 32 bits */ { -# if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) - unsigned long r = 0; - _BitScanReverse( &r, (unsigned long)val ); - return (unsigned)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clz((U32)val) >> 3); +# if (defined(__clang__) || (defined(__GNUC__) && ((__GNUC__ > 3) || \ + ((__GNUC__ == 3) && (__GNUC_MINOR__ >= 4))))) && \ + !defined(LZ4_FORCE_SW_BITCOUNT) + return (unsigned)__builtin_clz((U32)val) >> 3; # else - unsigned r; - if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } - r += (!val); - return r; + val >>= 8; + val = ((((val + 0x00FFFF00) | 0x00FFFFFF) + val) | + (val + 0x00FF0000)) >> 24; + return (unsigned)val ^ 3; # endif } } } + #define STEPSIZE sizeof(reg_t) LZ4_FORCE_INLINE unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) @@ -615,16 +672,25 @@ typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; } const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; } int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } -int LZ4_sizeofState() { return LZ4_STREAMSIZE; } +int LZ4_sizeofState(void) { return LZ4_STREAMSIZE; } /*-************************************ * Internal Definitions used in Tests **************************************/ +#if defined (__cplusplus) +extern "C" { +#endif -int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize); +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize); -int LZ4_decompress_safe_forceExtDict(const char* in, char* out, int inSize, int outSize, const void* dict, size_t dictSize); +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, + int compressedSize, int maxOutputSize, + const void* dictStart, size_t dictSize); + +#if defined (__cplusplus) +} +#endif /*-****************************** * Compression functions @@ -655,6 +721,18 @@ LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tab return LZ4_hash4(LZ4_read32(p), tableType); } +LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType) +{ + switch (tableType) + { + default: /* fallthrough */ + case clearedTable: { /* illegal! */ assert(0); return; } + case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; } + } +} + LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) { switch (tableType) @@ -708,49 +786,42 @@ LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_ assert(0); return 0; /* forbidden case */ } -LZ4_FORCE_INLINE const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase) +static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase) { if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; } if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; } { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ } -LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, - const void* tableBase, tableType_t tableType, - const BYTE* srcBase) +LZ4_FORCE_INLINE const BYTE* +LZ4_getPosition(const BYTE* p, + const void* tableBase, tableType_t tableType, + const BYTE* srcBase) { U32 const h = LZ4_hashPosition(p, tableType); return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } -LZ4_FORCE_INLINE void LZ4_prepareTable( - LZ4_stream_t_internal* const cctx, - const int inputSize, - const tableType_t tableType) { - /* If compression failed during the previous step, then the context - * is marked as dirty, therefore, it has to be fully reset. - */ - if (cctx->dirty) { - DEBUGLOG(5, "LZ4_prepareTable: Full reset for %p", cctx); - MEM_INIT(cctx, 0, sizeof(LZ4_stream_t_internal)); - return; - } - +LZ4_FORCE_INLINE void +LZ4_prepareTable(LZ4_stream_t_internal* const cctx, + const int inputSize, + const tableType_t tableType) { /* If the table hasn't been used, it's guaranteed to be zeroed out, and is * therefore safe to use no matter what mode we're in. Otherwise, we figure * out if it's safe to leave as is or whether it needs to be reset. */ - if (cctx->tableType != clearedTable) { - if (cctx->tableType != tableType - || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU) - || (tableType == byU32 && cctx->currentOffset > 1 GB) + if ((tableType_t)cctx->tableType != clearedTable) { + assert(inputSize >= 0); + if ((tableType_t)cctx->tableType != tableType + || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU) + || ((tableType == byU32) && cctx->currentOffset > 1 GB) || tableType == byPtr || inputSize >= 4 KB) { DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx); MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE); cctx->currentOffset = 0; - cctx->tableType = clearedTable; + cctx->tableType = (U32)clearedTable; } else { DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)"); } @@ -772,8 +843,12 @@ LZ4_FORCE_INLINE void LZ4_prepareTable( } /** LZ4_compress_generic() : - inlined, to ensure branches are decided at compilation time */ -LZ4_FORCE_INLINE int LZ4_compress_generic( + * inlined, to ensure branches are decided at compilation time. + * Presumed already validated at this stage: + * - source != NULL + * - inputSize > 0 + */ +LZ4_FORCE_INLINE int LZ4_compress_generic_validated( LZ4_stream_t_internal* const cctx, const char* const source, char* const dest, @@ -802,7 +877,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx); U32 const prefixIdxLimit = startIndex - dictSize; /* used when dictDirective == dictSmall */ - const BYTE* const dictEnd = dictionary + dictSize; + const BYTE* const dictEnd = dictionary ? dictionary + dictSize : dictionary; const BYTE* anchor = (const BYTE*) source; const BYTE* const iend = ip + inputSize; const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1; @@ -810,7 +885,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( /* the dictCtx currentOffset is indexed on the start of the dictionary, * while a dictionary in the current context precedes the currentOffset */ - const BYTE* dictBase = (dictDirective == usingDictCtx) ? + const BYTE* dictBase = !dictionary ? NULL : (dictDirective == usingDictCtx) ? dictionary + dictSize - dictCtx->currentOffset : dictionary + dictSize - startIndex; @@ -820,12 +895,12 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( U32 offset = 0; U32 forwardH; - DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType); + DEBUGLOG(5, "LZ4_compress_generic_validated: srcSize=%i, tableType=%u", inputSize, tableType); + assert(ip != NULL); /* If init conditions are not met, we don't have to mark stream * as having dirty context, since no action was taken yet */ - if (outputDirective == fillOutput && maxOutputSize < 1) return 0; /* Impossible to store anything */ - if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported inputSize, too large (or negative) */ - if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */ + if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) { return 0; } /* Size too large (not within 64K limit) */ if (tableType==byPtr) assert(dictDirective==noDict); /* only supported use case with byPtr */ assert(acceleration >= 1); @@ -841,7 +916,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( cctx->dictSize += (U32)inputSize; } cctx->currentOffset += (U32)inputSize; - cctx->tableType = (U16)tableType; + cctx->tableType = (U32)tableType; if (inputSizehashTable, tableType); - if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue; /* match outside of valid area */ + DEBUGLOG(7, "candidate at pos=%u (offset=%u \n", matchIndex, current - matchIndex); + if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; } /* match outside of valid area */ assert(matchIndex < current); - if ((tableType != byU16) && (matchIndex+LZ4_DISTANCE_MAX < current)) continue; /* too far */ - if (tableType == byU16) assert((current - matchIndex) <= LZ4_DISTANCE_MAX); /* too_far presumed impossible with byU16 */ + if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX)) + && (matchIndex+LZ4_DISTANCE_MAX < current)) { + continue; + } /* too far */ + assert((current - matchIndex) <= LZ4_DISTANCE_MAX); /* match now expected within distance */ if (LZ4_read32(match) == LZ4_read32(ip)) { if (maybe_extMem) offset = current - matchIndex; @@ -935,15 +1015,16 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( } /* Catch up */ + filledIp = ip; while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } /* Encode Literals */ { unsigned const litLength = (unsigned)(ip - anchor); token = op++; if ((outputDirective == limitedOutput) && /* Check output buffer overflow */ - (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) + (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) { return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ - + } if ((outputDirective == fillOutput) && (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) { op--; @@ -1014,12 +1095,26 @@ _next_match: } if ((outputDirective) && /* Check output buffer overflow */ - (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) { + (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) { if (outputDirective == fillOutput) { /* Match description too long : reduce it */ - U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 2 - 1 - LASTLITERALS) * 255; + U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255; ip -= matchCode - newMatchCode; + assert(newMatchCode < matchCode); matchCode = newMatchCode; + if (unlikely(ip <= filledIp)) { + /* We have already filled up to filledIp so if ip ends up less than filledIp + * we have positions in the hash table beyond the current position. This is + * a problem if we reuse the hash table. So we have to remove these positions + * from the hash table. + */ + const BYTE* ptr; + DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip)); + for (ptr = ip; ptr <= filledIp; ++ptr) { + U32 const h = LZ4_hashPosition(ptr, tableType); + LZ4_clearHash(h, cctx->hashTable, tableType); + } + } } else { assert(outputDirective == limitedOutput); return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ @@ -1039,6 +1134,8 @@ _next_match: } else *token += (BYTE)(matchCode); } + /* Ensure we have enough space for the last literals. */ + assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit)); anchor = ip; @@ -1088,7 +1185,7 @@ _next_match: LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); assert(matchIndex < current); if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1) - && ((tableType==byU16) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current)) + && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current)) && (LZ4_read32(match) == LZ4_read32(ip)) ) { token=op++; *token=0; @@ -1112,13 +1209,14 @@ _last_literals: if (outputDirective == fillOutput) { /* adapt lastRun to fill 'dst' */ assert(olimit >= op); - lastRun = (size_t)(olimit-op) - 1; - lastRun -= (lastRun+240)/255; + lastRun = (size_t)(olimit-op) - 1/*token*/; + lastRun -= (lastRun + 256 - RUN_MASK) / 256; /*additional length tokens*/ } else { assert(outputDirective == limitedOutput); return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ } } + DEBUGLOG(6, "Final literal run : %i literals", (int)lastRun); if (lastRun >= RUN_MASK) { size_t accumulator = lastRun - RUN_MASK; *op++ = RUN_MASK << ML_BITS; @@ -1127,7 +1225,7 @@ _last_literals: } else { *op++ = (BYTE)(lastRun< 0); + DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, result); return result; } +/** LZ4_compress_generic() : + * inlined, to ensure branches are decided at compilation time; + * takes care of src == (NULL, 0) + * and forward the rest to LZ4_compress_generic_validated */ +LZ4_FORCE_INLINE int LZ4_compress_generic( + LZ4_stream_t_internal* const cctx, + const char* const src, + char* const dst, + const int srcSize, + int *inputConsumed, /* only written when outputDirective == fillOutput */ + const int dstCapacity, + const limitedOutput_directive outputDirective, + const tableType_t tableType, + const dict_directive dictDirective, + const dictIssue_directive dictIssue, + const int acceleration) +{ + DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, dstCapacity=%i", + srcSize, dstCapacity); + + if ((U32)srcSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; } /* Unsupported srcSize, too large (or negative) */ + if (srcSize == 0) { /* src == NULL supported if srcSize == 0 */ + if (outputDirective != notLimited && dstCapacity <= 0) return 0; /* no output, can't write anything */ + DEBUGLOG(5, "Generating an empty block"); + assert(outputDirective == notLimited || dstCapacity >= 1); + assert(dst != NULL); + dst[0] = 0; + if (outputDirective == fillOutput) { + assert (inputConsumed != NULL); + *inputConsumed = 0; + } + return 1; + } + assert(src != NULL); + + return LZ4_compress_generic_validated(cctx, src, dst, srcSize, + inputConsumed, /* only written into if outputDirective == fillOutput */ + dstCapacity, outputDirective, + tableType, dictDirective, dictIssue, acceleration); +} + int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { LZ4_stream_t_internal* const ctx = & LZ4_initStream(state, sizeof(LZ4_stream_t)) -> internal_donotuse; assert(ctx != NULL); - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; + if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX; if (maxOutputSize >= LZ4_compressBound(inputSize)) { if (inputSize < LZ4_64Klimit) { return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration); @@ -1155,7 +1295,7 @@ int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); } } else { - if (inputSize < LZ4_64Klimit) {; + if (inputSize < LZ4_64Klimit) { return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); } else { const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32; @@ -1176,7 +1316,8 @@ int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) { LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse; - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; + if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX; if (dstCapacity >= LZ4_compressBound(srcSize)) { if (srcSize < LZ4_64Klimit) { @@ -1235,22 +1376,6 @@ int LZ4_compress_default(const char* src, char* dst, int srcSize, int maxOutputS } -/* hidden debug function */ -/* strangely enough, gcc generates faster code when this function is uncommented, even if unused */ -int LZ4_compress_fast_force(const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) -{ - LZ4_stream_t ctx; - LZ4_initStream(&ctx, sizeof(ctx)); - - if (srcSize < LZ4_64Klimit) { - return LZ4_compress_generic(&ctx.internal_donotuse, src, dst, srcSize, NULL, dstCapacity, limitedOutput, byU16, noDict, noDictIssue, acceleration); - } else { - tableType_t const addrMode = (sizeof(void*) > 4) ? byU32 : byPtr; - return LZ4_compress_generic(&ctx.internal_donotuse, src, dst, srcSize, NULL, dstCapacity, limitedOutput, addrMode, noDict, noDictIssue, acceleration); - } -} - - /* Note!: This function leaves the stream in an unclean/broken state! * It is not safe to subsequently use the same state with a _fastReset() or * _continue() call without resetting it. */ @@ -1305,27 +1430,23 @@ LZ4_stream_t* LZ4_createStream(void) return lz4s; } -#ifndef _MSC_VER /* for some reason, Visual fails the aligment test on 32-bit x86 : - it reports an aligment of 8-bytes, - while actually aligning LZ4_stream_t on 4 bytes. */ static size_t LZ4_stream_t_alignment(void) { - struct { char c; LZ4_stream_t t; } t_a; - return sizeof(t_a) - sizeof(t_a.t); -} +#if LZ4_ALIGN_TEST + typedef struct { char c; LZ4_stream_t t; } t_a; + return sizeof(t_a) - sizeof(LZ4_stream_t); +#else + return 1; /* effectively disabled */ #endif +} LZ4_stream_t* LZ4_initStream (void* buffer, size_t size) { DEBUGLOG(5, "LZ4_initStream"); - if (buffer == NULL) return NULL; - if (size < sizeof(LZ4_stream_t)) return NULL; -#ifndef _MSC_VER /* for some reason, Visual fails the aligment test on 32-bit x86 : - it reports an aligment of 8-bytes, - while actually aligning LZ4_stream_t on 4 bytes. */ - if (((size_t)buffer) & (LZ4_stream_t_alignment() - 1)) return NULL; /* alignment check */ -#endif - MEM_INIT(buffer, 0, sizeof(LZ4_stream_t)); + if (buffer == NULL) { return NULL; } + if (size < sizeof(LZ4_stream_t)) { return NULL; } + if (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL; + MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal)); return (LZ4_stream_t*)buffer; } @@ -1334,7 +1455,7 @@ LZ4_stream_t* LZ4_initStream (void* buffer, size_t size) void LZ4_resetStream (LZ4_stream_t* LZ4_stream) { DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream); - MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t)); + MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t_internal)); } void LZ4_resetStream_fast(LZ4_stream_t* ctx) { @@ -1373,18 +1494,18 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) * there are only valid offsets in the window, which allows an optimization * in LZ4_compress_fast_continue() where it uses noDictIssue even when the * dictionary isn't a full 64k. */ - - if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; - base = dictEnd - 64 KB - dict->currentOffset; - dict->dictionary = p; - dict->dictSize = (U32)(dictEnd - p); dict->currentOffset += 64 KB; - dict->tableType = tableType; if (dictSize < (int)HASH_UNIT) { return 0; } + if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; + base = dictEnd - dict->currentOffset; + dict->dictionary = p; + dict->dictSize = (U32)(dictEnd - p); + dict->tableType = (U32)tableType; + while (p <= dictEnd-HASH_UNIT) { LZ4_putPosition(p, dict->hashTable, tableType, base); p+=3; @@ -1393,26 +1514,31 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) return (int)dict->dictSize; } -void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) { - /* Calling LZ4_resetStream_fast() here makes sure that changes will not be - * erased by subsequent calls to LZ4_resetStream_fast() in case stream was - * marked as having dirty context, e.g. requiring full reset. - */ - LZ4_resetStream_fast(working_stream); +void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream) { + const LZ4_stream_t_internal* dictCtx = dictionaryStream == NULL ? NULL : + &(dictionaryStream->internal_donotuse); - if (dictionary_stream != NULL) { + DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)", + workingStream, dictionaryStream, + dictCtx != NULL ? dictCtx->dictSize : 0); + + if (dictCtx != NULL) { /* If the current offset is zero, we will never look in the * external dictionary context, since there is no value a table * entry can take that indicate a miss. In that case, we need * to bump the offset to something non-zero. */ - if (working_stream->internal_donotuse.currentOffset == 0) { - working_stream->internal_donotuse.currentOffset = 64 KB; + if (workingStream->internal_donotuse.currentOffset == 0) { + workingStream->internal_donotuse.currentOffset = 64 KB; + } + + /* Don't actually attach an empty dictionary. + */ + if (dictCtx->dictSize == 0) { + dictCtx = NULL; } - working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse); - } else { - working_stream->internal_donotuse.dictCtx = NULL; } + workingStream->internal_donotuse.dictCtx = dictCtx; } @@ -1447,9 +1573,9 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize); - if (streamPtr->dirty) return 0; /* Uninitialized structure detected */ LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */ - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; + if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX; /* invalidate tiny dictionaries */ if ( (streamPtr->dictSize-1 < 4-1) /* intentional underflow */ @@ -1492,7 +1618,7 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, * cost to copy the dictionary's tables into the active context, * so that the compression loop is only looking into one table. */ - memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t)); + LZ4_memcpy(streamPtr, streamPtr->dictCtx, sizeof(*streamPtr)); result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); } else { result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration); @@ -1544,10 +1670,12 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse; const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize; - if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ - if ((U32)dictSize > dict->dictSize) dictSize = (int)dict->dictSize; + if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */ + if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; } - memmove(safeBuffer, previousDictEnd - dictSize, dictSize); + if (safeBuffer == NULL) assert(dictSize == 0); + if (dictSize > 0) + memmove(safeBuffer, previousDictEnd - dictSize, dictSize); dict->dictionary = (const BYTE*)safeBuffer; dict->dictSize = (U32)dictSize; @@ -1577,25 +1705,27 @@ typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive; */ typedef enum { loop_error = -2, initial_error = -1, ok = 0 } variable_length_error; LZ4_FORCE_INLINE unsigned -read_variable_length(const BYTE**ip, const BYTE* lencheck, int loop_check, int initial_check, variable_length_error* error) +read_variable_length(const BYTE**ip, const BYTE* lencheck, + int loop_check, int initial_check, + variable_length_error* error) { - unsigned length = 0; - unsigned s; - if (initial_check && unlikely((*ip) >= lencheck)) { /* overflow detection */ - *error = initial_error; - return length; - } - do { - s = **ip; - (*ip)++; - length += s; - if (loop_check && unlikely((*ip) >= lencheck)) { /* overflow detection */ - *error = loop_error; - return length; + U32 length = 0; + U32 s; + if (initial_check && unlikely((*ip) >= lencheck)) { /* overflow detection */ + *error = initial_error; + return length; } - } while (s==255); + do { + s = **ip; + (*ip)++; + length += s; + if (loop_check && unlikely((*ip) >= lencheck)) { /* overflow detection */ + *error = loop_error; + return length; + } + } while (s==255); - return length; + return length; } /*! LZ4_decompress_generic() : @@ -1619,7 +1749,7 @@ LZ4_decompress_generic( const size_t dictSize /* note : = 0 if noDict */ ) { - if (src == NULL) return -1; + if (src == NULL) { return -1; } { const BYTE* ip = (const BYTE*) src; const BYTE* const iend = ip + srcSize; @@ -1648,9 +1778,13 @@ LZ4_decompress_generic( /* Special cases */ assert(lowPrefix <= op); - if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ - if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0 ? 1 : -1); - if ((endOnInput) && unlikely(srcSize==0)) return -1; + if ((endOnInput) && (unlikely(outputSize==0))) { + /* Empty output buffer */ + if (partialDecoding) return 0; + return ((srcSize==1) && (*ip==0)) ? 0 : -1; + } + if ((!endOnInput) && (unlikely(outputSize==0))) { return (*ip==0 ? 1 : -1); } + if ((endOnInput) && unlikely(srcSize==0)) { return -1; } /* Currently the fast loop shows a regression on qualcomm arm chips. */ #if LZ4_FAST_DEC_LOOP @@ -1663,7 +1797,7 @@ LZ4_decompress_generic( while (1) { /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */ assert(oend - op >= FASTLOOP_SAFE_DISTANCE); - if (endOnInput) assert(ip < iend); + if (endOnInput) { assert(ip < iend); } token = *ip++; length = token >> ML_BITS; /* literal length */ @@ -1672,19 +1806,19 @@ LZ4_decompress_generic( /* decode literal length */ if (length == RUN_MASK) { variable_length_error error = ok; - length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error); - if (error == initial_error) goto _output_error; - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error; /* overflow detection */ - if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error; /* overflow detection */ + length += read_variable_length(&ip, iend-RUN_MASK, (int)endOnInput, (int)endOnInput, &error); + if (error == initial_error) { goto _output_error; } + if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */ + if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */ /* copy literals */ cpy = op+length; LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); if (endOnInput) { /* LZ4_decompress_safe() */ - if ((cpy>oend-32) || (ip+length>iend-32)) goto safe_literal_copy; + if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; } LZ4_wildCopy32(op, ip, cpy); } else { /* LZ4_decompress_fast() */ - if (cpy>oend-8) goto safe_literal_copy; + if (cpy>oend-8) { goto safe_literal_copy; } LZ4_wildCopy8(op, ip, cpy); /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time : * it doesn't know input length, and only relies on end-of-block properties */ } @@ -1694,14 +1828,14 @@ LZ4_decompress_generic( if (endOnInput) { /* LZ4_decompress_safe() */ DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length); /* We don't need to check oend, since we check it once for each loop below */ - if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) goto safe_literal_copy; + if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; } /* Literals can only be 14, but hope compilers optimize if we copy by a register size */ - memcpy(op, ip, 16); + LZ4_memcpy(op, ip, 16); } else { /* LZ4_decompress_fast() */ /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time : * it doesn't know input length, and relies on end-of-block properties */ - memcpy(op, ip, 8); - if (length > 8) memcpy(op+8, ip+8, 8); + LZ4_memcpy(op, ip, 8); + if (length > 8) { LZ4_memcpy(op+8, ip+8, 8); } } ip += length; op = cpy; } @@ -1709,17 +1843,17 @@ LZ4_decompress_generic( /* get offset */ offset = LZ4_readLE16(ip); ip+=2; match = op - offset; + assert(match <= op); /* get matchlength */ length = token & ML_MASK; - if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ - if (length == ML_MASK) { - variable_length_error error = ok; - length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error); - if (error != ok) goto _output_error; - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ + variable_length_error error = ok; + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */ + length += read_variable_length(&ip, iend - LASTLITERALS + 1, (int)endOnInput, 0, &error); + if (error != ok) { goto _output_error; } + if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */ length += MINMATCH; if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { goto safe_match_copy; @@ -1731,21 +1865,29 @@ LZ4_decompress_generic( } /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */ - if (!(dict == usingExtDict) || (match >= lowPrefix)) { + if ((dict == withPrefix64k) || (match >= lowPrefix)) { if (offset >= 8) { - memcpy(op, match, 8); - memcpy(op+8, match+8, 8); - memcpy(op+16, match+16, 2); + assert(match >= lowPrefix); + assert(match <= op); + assert(op + 18 <= oend); + + LZ4_memcpy(op, match, 8); + LZ4_memcpy(op+8, match+8, 8); + LZ4_memcpy(op+16, match+16, 2); op += length; continue; } } } + if (checkOffset && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */ /* match starting within external dictionary */ if ((dict==usingExtDict) && (match < lowPrefix)) { if (unlikely(op+length > oend-LASTLITERALS)) { - if (partialDecoding) length = MIN(length, (size_t)(oend-op)); - else goto _output_error; /* doesn't respect parsing restriction */ - } + if (partialDecoding) { + DEBUGLOG(7, "partialDecoding: dictionary match, close to dstEnd"); + length = MIN(length, (size_t)(oend-op)); + } else { + goto _output_error; /* end-of-block condition violated */ + } } if (length <= (size_t)(lowPrefix-match)) { /* match fits entirely within external dictionary : just copy */ @@ -1755,14 +1897,14 @@ LZ4_decompress_generic( /* match stretches into both external dictionary and current block */ size_t const copySize = (size_t)(lowPrefix - match); size_t const restSize = length - copySize; - memcpy(op, dictEnd - copySize, copySize); + LZ4_memcpy(op, dictEnd - copySize, copySize); op += copySize; if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ BYTE* const endOfMatch = op + restSize; const BYTE* copyFrom = lowPrefix; - while (op < endOfMatch) *op++ = *copyFrom++; + while (op < endOfMatch) { *op++ = *copyFrom++; } } else { - memcpy(op, lowPrefix, restSize); + LZ4_memcpy(op, lowPrefix, restSize); op += restSize; } } continue; @@ -1803,7 +1945,7 @@ LZ4_decompress_generic( /* strictly "less than" on input, to re-enter the loop with at least one byte */ && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) { /* Copy the literals */ - memcpy(op, ip, endOnInput ? 16 : 8); + LZ4_memcpy(op, ip, endOnInput ? 16 : 8); op += length; ip += length; /* The second stage: prepare for match copying, decode full info. @@ -1818,9 +1960,9 @@ LZ4_decompress_generic( && (offset >= 8) && (dict==withPrefix64k || match >= lowPrefix) ) { /* Copy the match. */ - memcpy(op + 0, match + 0, 8); - memcpy(op + 8, match + 8, 8); - memcpy(op +16, match +16, 2); + LZ4_memcpy(op + 0, match + 0, 8); + LZ4_memcpy(op + 8, match + 8, 8); + LZ4_memcpy(op +16, match +16, 2); op += length + MINMATCH; /* Both stages worked, load the next token. */ continue; @@ -1833,11 +1975,11 @@ LZ4_decompress_generic( /* decode literal length */ if (length == RUN_MASK) { - variable_length_error error = ok; - length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error); - if (error == initial_error) goto _output_error; - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error; /* overflow detection */ - if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error; /* overflow detection */ + variable_length_error error = ok; + length += read_variable_length(&ip, iend-RUN_MASK, (int)endOnInput, (int)endOnInput, &error); + if (error == initial_error) { goto _output_error; } + if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */ + if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */ } /* copy literals */ @@ -1849,21 +1991,61 @@ LZ4_decompress_generic( if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) ) || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) { + /* We've either hit the input parsing restriction or the output parsing restriction. + * In the normal scenario, decoding a full block, it must be the last sequence, + * otherwise it's an error (invalid input or dimensions). + * In partialDecoding scenario, it's necessary to ensure there is no buffer overflow. + */ if (partialDecoding) { - if (cpy > oend) { cpy = oend; assert(op<=oend); length = (size_t)(oend-op); } /* Partial decoding : stop in the middle of literal segment */ - if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ + /* Since we are partial decoding we may be in this block because of the output parsing + * restriction, which is not valid since the output buffer is allowed to be undersized. + */ + assert(endOnInput); + DEBUGLOG(7, "partialDecoding: copying literals, close to input or output end") + DEBUGLOG(7, "partialDecoding: literal length = %u", (unsigned)length); + DEBUGLOG(7, "partialDecoding: remaining space in dstBuffer : %i", (int)(oend - op)); + DEBUGLOG(7, "partialDecoding: remaining space in srcBuffer : %i", (int)(iend - ip)); + /* Finishing in the middle of a literals segment, + * due to lack of input. + */ + if (ip+length > iend) { + length = (size_t)(iend-ip); + cpy = op + length; + } + /* Finishing in the middle of a literals segment, + * due to lack of output space. + */ + if (cpy > oend) { + cpy = oend; + assert(op<=oend); + length = (size_t)(oend-op); + } } else { - if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ - if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */ + /* We must be on the last sequence because of the parsing limitations so check + * that we exactly regenerate the original size (must be exact when !endOnInput). + */ + if ((!endOnInput) && (cpy != oend)) { goto _output_error; } + /* We must be on the last sequence (or invalid) because of the parsing limitations + * so check that we exactly consume the input and don't overrun the output buffer. + */ + if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) { + DEBUGLOG(6, "should have been last run of literals") + DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend); + DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend); + goto _output_error; + } } - memcpy(op, ip, length); + memmove(op, ip, length); /* supports overlapping memory regions; only matters for in-place decompression scenarios */ ip += length; op += length; - if (!partialDecoding || (cpy == oend)) { - /* Necessarily EOF, due to parsing restrictions */ + /* Necessarily EOF when !partialDecoding. + * When partialDecoding, it is EOF if we've either + * filled the output buffer or + * can't proceed with reading an offset for following match. + */ + if (!partialDecoding || (cpy == oend) || (ip >= (iend-2))) { break; } - } else { LZ4_wildCopy8(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */ ip += length; op = cpy; @@ -1877,16 +2059,9 @@ LZ4_decompress_generic( length = token & ML_MASK; _copy_match: - if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ - if (!partialDecoding) { - assert(oend > op); - assert(oend - op >= 4); - LZ4_write32(op, 0); /* silence an msan warning when offset==0; costs <1%; */ - } /* note : when partialDecoding, there is no guarantee that at least 4 bytes remain available in output buffer */ - if (length == ML_MASK) { variable_length_error error = ok; - length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error); + length += read_variable_length(&ip, iend - LASTLITERALS + 1, (int)endOnInput, 0, &error); if (error != ok) goto _output_error; if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ } @@ -1895,6 +2070,7 @@ LZ4_decompress_generic( #if LZ4_FAST_DEC_LOOP safe_match_copy: #endif + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ /* match starting within external dictionary */ if ((dict==usingExtDict) && (match < lowPrefix)) { if (unlikely(op+length > oend-LASTLITERALS)) { @@ -1910,18 +2086,19 @@ LZ4_decompress_generic( /* match stretches into both external dictionary and current block */ size_t const copySize = (size_t)(lowPrefix - match); size_t const restSize = length - copySize; - memcpy(op, dictEnd - copySize, copySize); + LZ4_memcpy(op, dictEnd - copySize, copySize); op += copySize; if (restSize > (size_t)(op - lowPrefix)) { /* overlap copy */ BYTE* const endOfMatch = op + restSize; const BYTE* copyFrom = lowPrefix; while (op < endOfMatch) *op++ = *copyFrom++; } else { - memcpy(op, lowPrefix, restSize); + LZ4_memcpy(op, lowPrefix, restSize); op += restSize; } } continue; } + assert(match >= lowPrefix); /* copy match within block */ cpy = op + length; @@ -1933,50 +2110,53 @@ LZ4_decompress_generic( const BYTE* const matchEnd = match + mlen; BYTE* const copyEnd = op + mlen; if (matchEnd > op) { /* overlap copy */ - while (op < copyEnd) *op++ = *match++; + while (op < copyEnd) { *op++ = *match++; } } else { - memcpy(op, match, mlen); + LZ4_memcpy(op, match, mlen); } op = copyEnd; - if (op==oend) break; + if (op == oend) { break; } continue; } if (unlikely(offset<8)) { + LZ4_write32(op, 0); /* silence msan warning when offset==0 */ op[0] = match[0]; op[1] = match[1]; op[2] = match[2]; op[3] = match[3]; match += inc32table[offset]; - memcpy(op+4, match, 4); + LZ4_memcpy(op+4, match, 4); match -= dec64table[offset]; } else { - memcpy(op, match, 8); + LZ4_memcpy(op, match, 8); match += 8; } op += 8; if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1); - if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ + if (cpy > oend-LASTLITERALS) { goto _output_error; } /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ if (op < oCopyLimit) { LZ4_wildCopy8(op, match, oCopyLimit); match += oCopyLimit - op; op = oCopyLimit; } - while (op < cpy) *op++ = *match++; + while (op < cpy) { *op++ = *match++; } } else { - memcpy(op, match, 8); - if (length > 16) LZ4_wildCopy8(op+8, match+8, cpy); + LZ4_memcpy(op, match, 8); + if (length > 16) { LZ4_wildCopy8(op+8, match+8, cpy); } } op = cpy; /* wildcopy correction */ } /* end of decoding */ - if (endOnInput) + if (endOnInput) { + DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst)); return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ - else + } else { return (int) (((const char*)ip)-src); /* Nb of input bytes read */ + } /* Overflow error detected */ _output_error: @@ -1987,7 +2167,7 @@ LZ4_decompress_generic( /*===== Instantiate the API decoding functions. =====*/ -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, @@ -1995,7 +2175,7 @@ int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int (BYTE*)dest, NULL, 0); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity) { dstCapacity = MIN(targetOutputSize, dstCapacity); @@ -2004,7 +2184,7 @@ int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, noDict, (BYTE*)dst, NULL, 0); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 int LZ4_decompress_fast(const char* source, char* dest, int originalSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, @@ -2014,7 +2194,7 @@ int LZ4_decompress_fast(const char* source, char* dest, int originalSize) /*===== Instantiate a few more decoding cases, used more than once. =====*/ -LZ4_FORCE_O2_GCC_PPC64LE /* Exported, an obsolete API function. */ +LZ4_FORCE_O2 /* Exported, an obsolete API function. */ int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, @@ -2030,7 +2210,7 @@ int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int origin return LZ4_decompress_fast(source, dest, originalSize); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize, size_t prefixSize) { @@ -2039,7 +2219,7 @@ static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, i (BYTE*)dest-prefixSize, NULL, 0); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const void* dictStart, size_t dictSize) @@ -2049,7 +2229,7 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, (BYTE*)dest, (const BYTE*)dictStart, dictSize); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize, const void* dictStart, size_t dictSize) { @@ -2091,7 +2271,7 @@ LZ4_streamDecode_t* LZ4_createStreamDecode(void) int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) { - if (LZ4_stream == NULL) return 0; /* support free on NULL */ + if (LZ4_stream == NULL) { return 0; } /* support free on NULL */ FREEMEM(LZ4_stream); return 0; } @@ -2138,7 +2318,7 @@ int LZ4_decoderRingBufferSize(int maxBlockSize) If it's not possible, save the relevant part of decoded data into a safe buffer, and indicate where it stands using LZ4_setStreamDecode() */ -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) { LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; @@ -2178,7 +2358,7 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch return result; } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) { LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; @@ -2226,18 +2406,22 @@ int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressed if (dictSize==0) return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); if (dictStart+dictSize == dest) { - if (dictSize >= 64 KB - 1) + if (dictSize >= 64 KB - 1) { return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); - return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize); } - return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize); + assert(dictSize >= 0); + return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize); } int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) { if (dictSize==0 || dictStart+dictSize == dest) return LZ4_decompress_fast(source, dest, originalSize); - return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, dictSize); + assert(dictSize >= 0); + return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize); } @@ -2249,9 +2433,9 @@ int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, in { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); } -int LZ4_compress(const char* source, char* dest, int inputSize) +int LZ4_compress(const char* src, char* dest, int srcSize) { - return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); + return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize)); } int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { @@ -2287,7 +2471,7 @@ int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, /* Obsolete Streaming functions */ -int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; } +int LZ4_sizeofStreamState(void) { return LZ4_STREAMSIZE; } int LZ4_resetStreamState(void* state, char* inputBuffer) { @@ -2309,5 +2493,3 @@ char* LZ4_slideInputBuffer (void* state) } #endif /* LZ4_COMMONDEFS_ONLY */ - -} diff --git a/common/tracy_lz4.hpp b/common/tracy_lz4.hpp index c6428be2..7ab1e483 100644 --- a/common/tracy_lz4.hpp +++ b/common/tracy_lz4.hpp @@ -32,22 +32,21 @@ - LZ4 homepage : http://www.lz4.org - LZ4 source repository : https://github.com/lz4/lz4 */ +#if defined (__cplusplus) +extern "C" { +#endif - -#ifndef TRACY_LZ4_H_2983827168210 -#define TRACY_LZ4_H_2983827168210 +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 /* --- Dependency --- */ #include /* size_t */ -#include -namespace tracy -{ /** Introduction - LZ4 is lossless compression algorithm, providing compression speed at 500 MB/s per core, + LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core, scalable with multi-cores CPU. It features an extremely fast decoder, with speed in multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. @@ -59,16 +58,19 @@ namespace tracy - unbounded multiple steps (described as Streaming compression) lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md). - Decompressing a block requires additional metadata, such as its compressed size. + Decompressing such a compressed block requires additional metadata. + Exact metadata depends on exact decompression function. + For the typical case of LZ4_decompress_safe(), + metadata includes block's compressed size, and maximum bound of decompressed size. Each application is free to encode and pass such metadata in whichever way it wants. lz4.h only handle blocks, it can not generate Frames. Blocks are different from Frames (doc/lz4_Frame_format.md). Frames bundle both blocks and metadata in a specified manner. - This are required for compressed data to be self-contained and portable. + Embedding metadata is required for compressed data to be self-contained and portable. Frame format is delivered through a companion API, declared in lz4frame.h. - Note that the `lz4` CLI can only manage frames. + The `lz4` CLI can only manage frames. */ /*^*************************************************************** @@ -98,7 +100,7 @@ namespace tracy /*------ Version ------*/ #define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ #define LZ4_VERSION_MINOR 9 /* for new (non-breaking) interface capabilities */ -#define LZ4_VERSION_RELEASE 1 /* for tweaks, bug-fixes, or development */ +#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */ #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) @@ -130,29 +132,35 @@ LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; * Simple Functions **************************************/ /*! LZ4_compress_default() : - Compresses 'srcSize' bytes from buffer 'src' - into already allocated 'dst' buffer of size 'dstCapacity'. - Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize). - It also runs faster, so it's a recommended setting. - If the function cannot compress 'src' into a more limited 'dst' budget, - compression stops *immediately*, and the function result is zero. - In which case, 'dst' content is undefined (invalid). - srcSize : max supported value is LZ4_MAX_INPUT_SIZE. - dstCapacity : size of buffer 'dst' (which must be already allocated) - @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity) - or 0 if compression fails - Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer). -*/ + * Compresses 'srcSize' bytes from buffer 'src' + * into already allocated 'dst' buffer of size 'dstCapacity'. + * Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize). + * It also runs faster, so it's a recommended setting. + * If the function cannot compress 'src' into a more limited 'dst' budget, + * compression stops *immediately*, and the function result is zero. + * In which case, 'dst' content is undefined (invalid). + * srcSize : max supported value is LZ4_MAX_INPUT_SIZE. + * dstCapacity : size of buffer 'dst' (which must be already allocated) + * @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity) + * or 0 if compression fails + * Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer). + */ LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity); /*! LZ4_decompress_safe() : - compressedSize : is the exact complete size of the compressed block. - dstCapacity : is the size of destination buffer, which must be already allocated. - @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity) - If destination buffer is not large enough, decoding will stop and output an error code (negative value). - If the source stream is detected malformed, the function will stop decoding and return a negative result. - Note : This function is protected against malicious data packets (never writes outside 'dst' buffer, nor read outside 'source' buffer). -*/ + * compressedSize : is the exact complete size of the compressed block. + * dstCapacity : is the size of destination buffer (which must be already allocated), presumed an upper bound of decompressed size. + * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity) + * If destination buffer is not large enough, decoding will stop and output an error code (negative value). + * If the source stream is detected malformed, the function will stop decoding and return a negative result. + * Note 1 : This function is protected against malicious data packets : + * it will never writes outside 'dst' buffer, nor read outside 'source' buffer, + * even if the compressed block is maliciously modified to order the decoder to do these actions. + * In such case, the decoder stops immediately, and considers the compressed block malformed. + * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them. + * The implementation is free to send / store / derive this information in whichever way is most beneficial. + * If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead. + */ LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity); @@ -178,7 +186,8 @@ LZ4LIB_API int LZ4_compressBound(int inputSize); The larger the acceleration value, the faster the algorithm, but also the lesser the compression. It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed. An acceleration value of "1" is the same as regular LZ4_compress_default() - Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c). + Values <= 0 will be replaced by LZ4_ACCELERATION_DEFAULT (currently == 1, see lz4.c). + Values > LZ4_ACCELERATION_MAX will be replaced by LZ4_ACCELERATION_MAX (currently == 65537, see lz4.c). */ LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); @@ -204,7 +213,18 @@ LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* d * New value is necessarily <= input value. * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize) * or 0 if compression fails. -*/ + * + * Note : from v1.8.2 to v1.9.1, this function had a bug (fixed un v1.9.2+): + * the produced compressed content could, in specific circumstances, + * require to be decompressed into a destination buffer larger + * by at least 1 byte than the content to decompress. + * If an application uses `LZ4_compress_destSize()`, + * it's highly recommended to update liblz4 to v1.9.2 or better. + * If this can't be done or ensured, + * the receiving decompression function should provide + * a dstCapacity which is > decompressedSize, by at least 1 byte. + * See https://github.com/lz4/lz4/issues/859 for details + */ LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize); @@ -212,25 +232,35 @@ LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePt * Decompress an LZ4 compressed block, of size 'srcSize' at position 'src', * into destination buffer 'dst' of size 'dstCapacity'. * Up to 'targetOutputSize' bytes will be decoded. - * The function stops decoding on reaching this objective, - * which can boost performance when only the beginning of a block is required. + * The function stops decoding on reaching this objective. + * This can be useful to boost performance + * whenever only the beginning of a block is required. * - * @return : the number of bytes decoded in `dst` (necessarily <= dstCapacity) + * @return : the number of bytes decoded in `dst` (necessarily <= targetOutputSize) * If source stream is detected malformed, function returns a negative result. * - * Note : @return can be < targetOutputSize, if compressed block contains less data. + * Note 1 : @return can be < targetOutputSize, if compressed block contains less data. * - * Note 2 : this function features 2 parameters, targetOutputSize and dstCapacity, - * and expects targetOutputSize <= dstCapacity. - * It effectively stops decoding on reaching targetOutputSize, + * Note 2 : targetOutputSize must be <= dstCapacity + * + * Note 3 : this function effectively stops decoding on reaching targetOutputSize, * so dstCapacity is kind of redundant. - * This is because in a previous version of this function, - * decoding operation would not "break" a sequence in the middle. - * As a consequence, there was no guarantee that decoding would stop at exactly targetOutputSize, + * This is because in older versions of this function, + * decoding operation would still write complete sequences. + * Therefore, there was no guarantee that it would stop writing at exactly targetOutputSize, * it could write more bytes, though only up to dstCapacity. * Some "margin" used to be required for this operation to work properly. - * This is no longer necessary. - * The function nonetheless keeps its signature, in an effort to not break API. + * Thankfully, this is no longer necessary. + * The function nonetheless keeps the same signature, in an effort to preserve API compatibility. + * + * Note 4 : If srcSize is the exact size of the block, + * then targetOutputSize can be any value, + * including larger than the block's decompressed size. + * The function will, at most, generate block's decompressed size. + * + * Note 5 : If srcSize is _larger_ than block's compressed size, + * then targetOutputSize **MUST** be <= block's decompressed size. + * Otherwise, *silent corruption will occur*. */ LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity); @@ -389,6 +419,8 @@ LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecod */ LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize); +#endif /* LZ4_H_2983827168210 */ + /*^************************************* * !!!!!! STATIC LINKING ONLY !!!!!! @@ -414,14 +446,17 @@ LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int sr * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library. ******************************************************************************/ +#ifdef LZ4_STATIC_LINKING_ONLY + +#ifndef LZ4_STATIC_3504398509 +#define LZ4_STATIC_3504398509 + #ifdef LZ4_PUBLISH_STATIC_FUNCTIONS #define LZ4LIB_STATIC_API LZ4LIB_API #else #define LZ4LIB_STATIC_API #endif -#ifdef LZ4_STATIC_LINKING_ONLY - /*! LZ4_compress_fast_extState_fastReset() : * A variant of LZ4_compress_fast_extState(). @@ -463,78 +498,135 @@ LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const c */ LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream); + +/*! In-place compression and decompression + * + * It's possible to have input and output sharing the same buffer, + * for highly contrained memory environments. + * In both cases, it requires input to lay at the end of the buffer, + * and decompression to start at beginning of the buffer. + * Buffer size must feature some margin, hence be larger than final size. + * + * |<------------------------buffer--------------------------------->| + * |<-----------compressed data--------->| + * |<-----------decompressed size------------------>| + * |<----margin---->| + * + * This technique is more useful for decompression, + * since decompressed size is typically larger, + * and margin is short. + * + * In-place decompression will work inside any buffer + * which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize). + * This presumes that decompressedSize > compressedSize. + * Otherwise, it means compression actually expanded data, + * and it would be more efficient to store such data with a flag indicating it's not compressed. + * This can happen when data is not compressible (already compressed, or encrypted). + * + * For in-place compression, margin is larger, as it must be able to cope with both + * history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX, + * and data expansion, which can happen when input is not compressible. + * As a consequence, buffer size requirements are much higher, + * and memory savings offered by in-place compression are more limited. + * + * There are ways to limit this cost for compression : + * - Reduce history size, by modifying LZ4_DISTANCE_MAX. + * Note that it is a compile-time constant, so all compressions will apply this limit. + * Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX, + * so it's a reasonable trick when inputs are known to be small. + * - Require the compressor to deliver a "maximum compressed size". + * This is the `dstCapacity` parameter in `LZ4_compress*()`. + * When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail, + * in which case, the return code will be 0 (zero). + * The caller must be ready for these cases to happen, + * and typically design a backup scheme to send data uncompressed. + * The combination of both techniques can significantly reduce + * the amount of margin required for in-place compression. + * + * In-place compression can work in any buffer + * which size is >= (maxCompressedSize) + * with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success. + * LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX, + * so it's possible to reduce memory requirements by playing with them. + */ + +#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32) +#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize) ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize)) /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */ + +#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */ +# define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */ #endif +#define LZ4_COMPRESS_INPLACE_MARGIN (LZ4_DISTANCE_MAX + 32) /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */ +#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize) ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN) /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */ + +#endif /* LZ4_STATIC_3504398509 */ +#endif /* LZ4_STATIC_LINKING_ONLY */ + + + +#ifndef LZ4_H_98237428734687 +#define LZ4_H_98237428734687 /*-************************************************************ - * PRIVATE DEFINITIONS + * Private Definitions ************************************************************** * Do not use these definitions directly. * They are only exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`. - * Accessing members will expose code to API and/or ABI break in future versions of the library. + * Accessing members will expose user code to API and/or ABI break in future versions of the library. **************************************************************/ #define LZ4_HASHLOG (LZ4_MEMORY_USAGE-2) #define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE) #define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG) /* required as macro for static allocation */ #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -#include - -typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; -struct LZ4_stream_t_internal { - uint32_t hashTable[LZ4_HASH_SIZE_U32]; - uint32_t currentOffset; - uint16_t dirty; - uint16_t tableType; - const uint8_t* dictionary; - const LZ4_stream_t_internal* dictCtx; - uint32_t dictSize; -}; - -typedef struct { - const uint8_t* externalDict; - size_t extDictSize; - const uint8_t* prefixEnd; - size_t prefixSize; -} LZ4_streamDecode_t_internal; - +# include + typedef int8_t LZ4_i8; + typedef uint8_t LZ4_byte; + typedef uint16_t LZ4_u16; + typedef uint32_t LZ4_u32; #else - -typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; -struct LZ4_stream_t_internal { - unsigned int hashTable[LZ4_HASH_SIZE_U32]; - unsigned int currentOffset; - unsigned short dirty; - unsigned short tableType; - const unsigned char* dictionary; - const LZ4_stream_t_internal* dictCtx; - unsigned int dictSize; -}; - -typedef struct { - const unsigned char* externalDict; - const unsigned char* prefixEnd; - size_t extDictSize; - size_t prefixSize; -} LZ4_streamDecode_t_internal; - + typedef signed char LZ4_i8; + typedef unsigned char LZ4_byte; + typedef unsigned short LZ4_u16; + typedef unsigned int LZ4_u32; #endif +typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; +struct LZ4_stream_t_internal { + LZ4_u32 hashTable[LZ4_HASH_SIZE_U32]; + LZ4_u32 currentOffset; + LZ4_u32 tableType; + const LZ4_byte* dictionary; + const LZ4_stream_t_internal* dictCtx; + LZ4_u32 dictSize; +}; + +typedef struct { + const LZ4_byte* externalDict; + size_t extDictSize; + const LZ4_byte* prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + + /*! LZ4_stream_t : - * information structure to track an LZ4 stream. + * Do not use below internal definitions directly ! + * Declare or allocate an LZ4_stream_t instead. * LZ4_stream_t can also be created using LZ4_createStream(), which is recommended. * The structure definition can be convenient for static allocation * (on stack, or as part of larger structure). * Init this structure with LZ4_initStream() before first use. * note : only use this definition in association with static linking ! - * this definition is not API/ABI safe, and may change in a future version. + * this definition is not API/ABI safe, and may change in future versions. */ -#define LZ4_STREAMSIZE_U64 ((1 << (LZ4_MEMORY_USAGE-3)) + 4 + ((sizeof(void*)==16) ? 4 : 0) /*AS-400*/ ) -#define LZ4_STREAMSIZE (LZ4_STREAMSIZE_U64 * sizeof(unsigned long long)) +#define LZ4_STREAMSIZE 16416 /* static size, for inter-version compatibility */ +#define LZ4_STREAMSIZE_VOIDP (LZ4_STREAMSIZE / sizeof(void*)) union LZ4_stream_u { - unsigned long long table[LZ4_STREAMSIZE_U64]; + void* table[LZ4_STREAMSIZE_VOIDP]; LZ4_stream_t_internal internal_donotuse; -} ; /* previously typedef'd to LZ4_stream_t */ +}; /* previously typedef'd to LZ4_stream_t */ + /*! LZ4_initStream() : v1.9.0+ * An LZ4_stream_t structure must be initialized at least once. @@ -568,6 +660,7 @@ union LZ4_streamDecode_u { } ; /* previously typedef'd to LZ4_streamDecode_t */ + /*-************************************ * Obsolete Functions **************************************/ @@ -586,34 +679,34 @@ union LZ4_streamDecode_u { #ifdef LZ4_DISABLE_DEPRECATE_WARNINGS # define LZ4_DEPRECATED(message) /* disable deprecation warnings */ #else -# define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) # if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */ # define LZ4_DEPRECATED(message) [[deprecated(message)]] -# elif (LZ4_GCC_VERSION >= 405) || defined(__clang__) -# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) -# elif (LZ4_GCC_VERSION >= 301) -# define LZ4_DEPRECATED(message) __attribute__((deprecated)) # elif defined(_MSC_VER) # define LZ4_DEPRECATED(message) __declspec(deprecated(message)) +# elif defined(__clang__) || (defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 45)) +# define LZ4_DEPRECATED(message) __attribute__((deprecated(message))) +# elif defined(__GNUC__) && (__GNUC__ * 10 + __GNUC_MINOR__ >= 31) +# define LZ4_DEPRECATED(message) __attribute__((deprecated)) # else -# pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler") -# define LZ4_DEPRECATED(message) +# pragma message("WARNING: LZ4_DEPRECATED needs custom implementation for this compiler") +# define LZ4_DEPRECATED(message) /* disabled */ # endif #endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */ -/* Obsolete compression functions */ -LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* source, char* dest, int sourceSize); -LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); +/*! Obsolete compression functions (since v1.7.3) */ +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize); LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); -/* Obsolete decompression functions */ +/*! Obsolete decompression functions (since v1.8.0) */ LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize); LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); -/* Obsolete streaming functions; degraded functionality; do not use! +/* Obsolete streaming functions (since v1.7.0) + * degraded functionality; do not use! * * In order to perform streaming compression, these functions depended on data * that is no longer tracked in the state. They have been preserved as well as @@ -627,23 +720,22 @@ LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStre LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API int LZ4_resetStreamState(void* state, char* inputBuffer); LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API char* LZ4_slideInputBuffer (void* state); -/* Obsolete streaming decoding functions */ +/*! Obsolete streaming decoding functions (since v1.7.0) */ LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); -/*! LZ4_decompress_fast() : **unsafe!** +/*! Obsolete LZ4_decompress_fast variants (since v1.9.0) : * These functions used to be faster than LZ4_decompress_safe(), - * but it has changed, and they are now slower than LZ4_decompress_safe(). + * but this is no longer the case. They are now slower. * This is because LZ4_decompress_fast() doesn't know the input size, - * and therefore must progress more cautiously in the input buffer to not read beyond the end of block. + * and therefore must progress more cautiously into the input buffer to not read beyond the end of block. * On top of that `LZ4_decompress_fast()` is not protected vs malformed or malicious inputs, making it a security liability. * As a consequence, LZ4_decompress_fast() is strongly discouraged, and deprecated. * * The last remaining LZ4_decompress_fast() specificity is that * it can decompress a block without knowing its compressed size. - * Such functionality could be achieved in a more secure manner, - * by also providing the maximum size of input buffer, - * but it would require new prototypes, and adaptation of the implementation to this new use case. + * Such functionality can be achieved in a more secure manner + * by employing LZ4_decompress_safe_partial(). * * Parameters: * originalSize : is the uncompressed size to regenerate. @@ -658,7 +750,6 @@ LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4 * But they may happen if input data is invalid (error or intentional tampering). * As a consequence, use these functions in trusted environments with trusted data **only**. */ - LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize); LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_continue() instead") @@ -674,6 +765,10 @@ LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int or */ LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); -} -#endif /* LZ4_H_2983827168210 */ +#endif /* LZ4_H_98237428734687 */ + + +#if defined (__cplusplus) +} +#endif diff --git a/common/tracy_lz4hc.cpp b/common/tracy_lz4hc.cpp index a7a2d11a..77c9f430 100644 --- a/common/tracy_lz4hc.cpp +++ b/common/tracy_lz4hc.cpp @@ -50,10 +50,10 @@ /*=== Dependency ===*/ #define LZ4_HC_STATIC_LINKING_ONLY -#include "tracy_lz4hc.hpp" +#include "lz4hc.h" -/*=== Common LZ4 definitions ===*/ +/*=== Common definitions ===*/ #if defined(__GNUC__) # pragma GCC diagnostic ignored "-Wunused-function" #endif @@ -61,21 +61,15 @@ # pragma clang diagnostic ignored "-Wunused-function" #endif -namespace tracy -{ +#define LZ4_COMMONDEFS_ONLY +#ifndef LZ4_SRC_INCLUDED +#include "lz4.c" /* LZ4_count, constants, mem */ +#endif + /*=== Enums ===*/ typedef enum { noDictCtx, usingDictCtxHc } dictCtx_directive; -} - -#define LZ4_COMMONDEFS_ONLY -#ifndef LZ4_SRC_INCLUDED -#include "tracy_lz4.cpp" /* LZ4_count, constants, mem */ -#endif - -namespace tracy -{ /*=== Constants ===*/ #define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH) @@ -99,7 +93,7 @@ static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr) **************************************/ static void LZ4HC_clearTables (LZ4HC_CCtx_internal* hc4) { - MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable)); + MEM_INIT(hc4->hashTable, 0, sizeof(hc4->hashTable)); MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable)); } @@ -158,13 +152,28 @@ int LZ4HC_countBack(const BYTE* const ip, const BYTE* const match, return back; } +#if defined(_MSC_VER) +# define LZ4HC_rotl32(x,r) _rotl(x,r) +#else +# define LZ4HC_rotl32(x,r) ((x << r) | (x >> (32 - r))) +#endif + + +static U32 LZ4HC_rotatePattern(size_t const rotate, U32 const pattern) +{ + size_t const bitsToRotate = (rotate & (sizeof(pattern) - 1)) << 3; + if (bitsToRotate == 0) return pattern; + return LZ4HC_rotl32(pattern, (int)bitsToRotate); +} + /* LZ4HC_countPattern() : * pattern32 must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!) */ static unsigned LZ4HC_countPattern(const BYTE* ip, const BYTE* const iEnd, U32 const pattern32) { const BYTE* const iStart = ip; - reg_t const pattern = (sizeof(pattern)==8) ? (reg_t)pattern32 + (((reg_t)pattern32) << 32) : pattern32; + reg_t const pattern = (sizeof(pattern)==8) ? + (reg_t)pattern32 + (((reg_t)pattern32) << (sizeof(pattern)*4)) : pattern32; while (likely(ip < iEnd-(sizeof(pattern)-1))) { reg_t const diff = LZ4_read_ARCH(ip) ^ pattern; @@ -210,6 +219,16 @@ LZ4HC_reverseCountPattern(const BYTE* ip, const BYTE* const iLow, U32 pattern) return (unsigned)(iStart - ip); } +/* LZ4HC_protectDictEnd() : + * Checks if the match is in the last 3 bytes of the dictionary, so reading the + * 4 byte MINMATCH would overflow. + * @returns true if the match index is okay. + */ +static int LZ4HC_protectDictEnd(U32 const dictLimit, U32 const matchIndex) +{ + return ((U32)((dictLimit - 1) - matchIndex) >= 3); +} + typedef enum { rep_untested, rep_not, rep_confirmed } repeat_state_e; typedef enum { favorCompressionRatio=0, favorDecompressionSpeed } HCfavor_e; @@ -235,7 +254,7 @@ LZ4HC_InsertAndGetWiderMatch ( const U32 dictLimit = hc4->dictLimit; const BYTE* const lowPrefixPtr = base + dictLimit; const U32 ipIndex = (U32)(ip - base); - const U32 lowestMatchIndex = (hc4->lowLimit + 64 KB > ipIndex) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX; + const U32 lowestMatchIndex = (hc4->lowLimit + (LZ4_DISTANCE_MAX + 1) > ipIndex) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX; const BYTE* const dictBase = hc4->dictBase; int const lookBackLength = (int)(ip-iLowLimit); int nbAttempts = maxNbAttempts; @@ -252,7 +271,7 @@ LZ4HC_InsertAndGetWiderMatch ( DEBUGLOG(7, "First match at index %u / %u (lowestMatchIndex)", matchIndex, lowestMatchIndex); - while ((matchIndex>=lowestMatchIndex) && (nbAttempts)) { + while ((matchIndex>=lowestMatchIndex) && (nbAttempts>0)) { int matchLength=0; nbAttempts--; assert(matchIndex < ipIndex); @@ -294,14 +313,21 @@ LZ4HC_InsertAndGetWiderMatch ( if (chainSwap && matchLength==longest) { /* better match => select a better chain */ assert(lookBackLength==0); /* search forward only */ if (matchIndex + (U32)longest <= ipIndex) { + int const kTrigger = 4; U32 distanceToNextMatch = 1; + int const end = longest - MINMATCH + 1; + int step = 1; + int accel = 1 << kTrigger; int pos; - for (pos = 0; pos <= longest - MINMATCH; pos++) { + for (pos = 0; pos < end; pos += step) { U32 const candidateDist = DELTANEXTU16(chainTable, matchIndex + (U32)pos); + step = (accel++ >> kTrigger); if (candidateDist > distanceToNextMatch) { distanceToNextMatch = candidateDist; matchChainPos = (U32)pos; - } } + accel = 1 << kTrigger; + } + } if (distanceToNextMatch > 1) { if (distanceToNextMatch > matchIndex) break; /* avoid overflow */ matchIndex -= distanceToNextMatch; @@ -320,34 +346,61 @@ LZ4HC_InsertAndGetWiderMatch ( } else { repeat = rep_not; } } - if ( (repeat == rep_confirmed) - && (matchCandidateIdx >= dictLimit) ) { /* same segment only */ - const BYTE* const matchPtr = base + matchCandidateIdx; + if ( (repeat == rep_confirmed) && (matchCandidateIdx >= lowestMatchIndex) + && LZ4HC_protectDictEnd(dictLimit, matchCandidateIdx) ) { + const int extDict = matchCandidateIdx < dictLimit; + const BYTE* const matchPtr = (extDict ? dictBase : base) + matchCandidateIdx; if (LZ4_read32(matchPtr) == pattern) { /* good candidate */ - size_t const forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iHighLimit, pattern) + sizeof(pattern); - const BYTE* const lowestMatchPtr = (lowPrefixPtr + LZ4_DISTANCE_MAX >= ip) ? lowPrefixPtr : ip - LZ4_DISTANCE_MAX; - size_t const backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern); - size_t const currentSegmentLength = backLength + forwardPatternLength; - - if ( (currentSegmentLength >= srcPatternLength) /* current pattern segment large enough to contain full srcPatternLength */ - && (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */ - matchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength; /* best position, full pattern, might be followed by more match */ - } else { - matchIndex = matchCandidateIdx - (U32)backLength; /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */ - if (lookBackLength==0) { /* no back possible */ - size_t const maxML = MIN(currentSegmentLength, srcPatternLength); - if ((size_t)longest < maxML) { - assert(base + matchIndex < ip); - if (ip - (base+matchIndex) > LZ4_DISTANCE_MAX) break; - assert(maxML < 2 GB); - longest = (int)maxML; - *matchpos = base + matchIndex; /* virtual pos, relative to ip, to retrieve offset */ - *startpos = ip; + const BYTE* const dictStart = dictBase + hc4->lowLimit; + const BYTE* const iLimit = extDict ? dictBase + dictLimit : iHighLimit; + size_t forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iLimit, pattern) + sizeof(pattern); + if (extDict && matchPtr + forwardPatternLength == iLimit) { + U32 const rotatedPattern = LZ4HC_rotatePattern(forwardPatternLength, pattern); + forwardPatternLength += LZ4HC_countPattern(lowPrefixPtr, iHighLimit, rotatedPattern); + } + { const BYTE* const lowestMatchPtr = extDict ? dictStart : lowPrefixPtr; + size_t backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern); + size_t currentSegmentLength; + if (!extDict && matchPtr - backLength == lowPrefixPtr && hc4->lowLimit < dictLimit) { + U32 const rotatedPattern = LZ4HC_rotatePattern((U32)(-(int)backLength), pattern); + backLength += LZ4HC_reverseCountPattern(dictBase + dictLimit, dictStart, rotatedPattern); + } + /* Limit backLength not go further than lowestMatchIndex */ + backLength = matchCandidateIdx - MAX(matchCandidateIdx - (U32)backLength, lowestMatchIndex); + assert(matchCandidateIdx - backLength >= lowestMatchIndex); + currentSegmentLength = backLength + forwardPatternLength; + /* Adjust to end of pattern if the source pattern fits, otherwise the beginning of the pattern */ + if ( (currentSegmentLength >= srcPatternLength) /* current pattern segment large enough to contain full srcPatternLength */ + && (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */ + U32 const newMatchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength; /* best position, full pattern, might be followed by more match */ + if (LZ4HC_protectDictEnd(dictLimit, newMatchIndex)) + matchIndex = newMatchIndex; + else { + /* Can only happen if started in the prefix */ + assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict); + matchIndex = dictLimit; } - { U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex); - if (distToNextPattern > matchIndex) break; /* avoid overflow */ - matchIndex -= distToNextPattern; - } } } + } else { + U32 const newMatchIndex = matchCandidateIdx - (U32)backLength; /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */ + if (!LZ4HC_protectDictEnd(dictLimit, newMatchIndex)) { + assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict); + matchIndex = dictLimit; + } else { + matchIndex = newMatchIndex; + if (lookBackLength==0) { /* no back possible */ + size_t const maxML = MIN(currentSegmentLength, srcPatternLength); + if ((size_t)longest < maxML) { + assert(base + matchIndex != ip); + if ((size_t)(ip - base) - matchIndex > LZ4_DISTANCE_MAX) break; + assert(maxML < 2 GB); + longest = (int)maxML; + *matchpos = base + matchIndex; /* virtual pos, relative to ip, to retrieve offset */ + *startpos = ip; + } + { U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex); + if (distToNextPattern > matchIndex) break; /* avoid overflow */ + matchIndex -= distToNextPattern; + } } } } } continue; } } } } /* PA optimization */ @@ -358,7 +411,7 @@ LZ4HC_InsertAndGetWiderMatch ( } /* while ((matchIndex>=lowestMatchIndex) && (nbAttempts)) */ if ( dict == usingDictCtxHc - && nbAttempts + && nbAttempts > 0 && ipIndex - lowestMatchIndex < LZ4_DISTANCE_MAX) { size_t const dictEndOffset = (size_t)(dictCtx->end - dictCtx->base); U32 dictMatchIndex = dictCtx->hashTable[LZ4HC_hashPtr(ip)]; @@ -408,74 +461,90 @@ int LZ4HC_InsertAndFindBestMatch(LZ4HC_CCtx_internal* const hc4, /* Index tabl * @return : 0 if ok, * 1 if buffer issue detected */ LZ4_FORCE_INLINE int LZ4HC_encodeSequence ( - const BYTE** ip, - BYTE** op, - const BYTE** anchor, + const BYTE** _ip, + BYTE** _op, + const BYTE** _anchor, int matchLength, const BYTE* const match, limitedOutput_directive limit, BYTE* oend) { +#define ip (*_ip) +#define op (*_op) +#define anchor (*_anchor) + size_t length; - BYTE* const token = (*op)++; + BYTE* const token = op++; #if defined(LZ4_DEBUG) && (LZ4_DEBUG >= 6) static const BYTE* start = NULL; static U32 totalCost = 0; - U32 const pos = (start==NULL) ? 0 : (U32)(*anchor - start); - U32 const ll = (U32)(*ip - *anchor); + U32 const pos = (start==NULL) ? 0 : (U32)(anchor - start); + U32 const ll = (U32)(ip - anchor); U32 const llAdd = (ll>=15) ? ((ll-15) / 255) + 1 : 0; U32 const mlAdd = (matchLength>=19) ? ((matchLength-19) / 255) + 1 : 0; U32 const cost = 1 + llAdd + ll + 2 + mlAdd; - if (start==NULL) start = *anchor; /* only works for single segment */ + if (start==NULL) start = anchor; /* only works for single segment */ /* g_debuglog_enable = (pos >= 2228) & (pos <= 2262); */ - DEBUGLOG(6, "pos:%7u -- literals:%3u, match:%4i, offset:%5u, cost:%3u + %u", + DEBUGLOG(6, "pos:%7u -- literals:%4u, match:%4i, offset:%5u, cost:%4u + %5u", pos, - (U32)(*ip - *anchor), matchLength, (U32)(*ip-match), + (U32)(ip - anchor), matchLength, (U32)(ip-match), cost, totalCost); totalCost += cost; #endif /* Encode Literal length */ - length = (size_t)(*ip - *anchor); - if ((limit) && ((*op + (length / 255) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */ + length = (size_t)(ip - anchor); + LZ4_STATIC_ASSERT(notLimited == 0); + /* Check output limit */ + if (limit && ((op + (length / 255) + length + (2 + 1 + LASTLITERALS)) > oend)) { + DEBUGLOG(6, "Not enough room to write %i literals (%i bytes remaining)", + (int)length, (int)(oend - op)); + return 1; + } if (length >= RUN_MASK) { size_t len = length - RUN_MASK; *token = (RUN_MASK << ML_BITS); - for(; len >= 255 ; len -= 255) *(*op)++ = 255; - *(*op)++ = (BYTE)len; + for(; len >= 255 ; len -= 255) *op++ = 255; + *op++ = (BYTE)len; } else { *token = (BYTE)(length << ML_BITS); } /* Copy Literals */ - LZ4_wildCopy8(*op, *anchor, (*op) + length); - *op += length; + LZ4_wildCopy8(op, anchor, op + length); + op += length; /* Encode Offset */ - assert( (*ip - match) <= LZ4_DISTANCE_MAX ); /* note : consider providing offset as a value, rather than as a pointer difference */ - LZ4_writeLE16(*op, (U16)(*ip-match)); *op += 2; + assert( (ip - match) <= LZ4_DISTANCE_MAX ); /* note : consider providing offset as a value, rather than as a pointer difference */ + LZ4_writeLE16(op, (U16)(ip - match)); op += 2; /* Encode MatchLength */ assert(matchLength >= MINMATCH); length = (size_t)matchLength - MINMATCH; - if ((limit) && (*op + (length / 255) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */ + if (limit && (op + (length / 255) + (1 + LASTLITERALS) > oend)) { + DEBUGLOG(6, "Not enough room to write match length"); + return 1; /* Check output limit */ + } if (length >= ML_MASK) { *token += ML_MASK; length -= ML_MASK; - for(; length >= 510 ; length -= 510) { *(*op)++ = 255; *(*op)++ = 255; } - if (length >= 255) { length -= 255; *(*op)++ = 255; } - *(*op)++ = (BYTE)length; + for(; length >= 510 ; length -= 510) { *op++ = 255; *op++ = 255; } + if (length >= 255) { length -= 255; *op++ = 255; } + *op++ = (BYTE)length; } else { *token += (BYTE)(length); } /* Prepare next loop */ - *ip += matchLength; - *anchor = *ip; + ip += matchLength; + anchor = ip; return 0; } +#undef ip +#undef op +#undef anchor LZ4_FORCE_INLINE int LZ4HC_compress_hashChain ( LZ4HC_CCtx_internal* const ctx, @@ -483,7 +552,7 @@ LZ4_FORCE_INLINE int LZ4HC_compress_hashChain ( char* const dest, int* srcSizePtr, int const maxOutputSize, - unsigned maxNbAttempts, + int maxNbAttempts, const limitedOutput_directive limit, const dictCtx_directive dict ) @@ -513,7 +582,7 @@ LZ4_FORCE_INLINE int LZ4HC_compress_hashChain ( /* init */ *srcSizePtr = 0; if (limit == fillOutput) oend -= LASTLITERALS; /* Hack for support LZ4 format restriction */ - if (inputSize < LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ + if (inputSize < LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ /* Main Loop */ while (ip <= mflimit) { @@ -585,7 +654,11 @@ _Search3: if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ref, limit, oend)) goto _dest_overflow; ip = start2; optr = op; - if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml2, ref2, limit, oend)) goto _dest_overflow; + if (LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml2, ref2, limit, oend)) { + ml = ml2; + ref = ref2; + goto _dest_overflow; + } continue; } @@ -657,17 +730,18 @@ _Search3: _last_literals: /* Encode Last Literals */ { size_t lastRunSize = (size_t)(iend - anchor); /* literals */ - size_t litLength = (lastRunSize + 255 - RUN_MASK) / 255; - size_t const totalSize = 1 + litLength + lastRunSize; + size_t llAdd = (lastRunSize + 255 - RUN_MASK) / 255; + size_t const totalSize = 1 + llAdd + lastRunSize; if (limit == fillOutput) oend += LASTLITERALS; /* restore correct value */ if (limit && (op + totalSize > oend)) { - if (limit == limitedOutput) return 0; /* Check output limit */ + if (limit == limitedOutput) return 0; /* adapt lastRunSize to fill 'dest' */ - lastRunSize = (size_t)(oend - op) - 1; - litLength = (lastRunSize + 255 - RUN_MASK) / 255; - lastRunSize -= litLength; + lastRunSize = (size_t)(oend - op) - 1 /*token*/; + llAdd = (lastRunSize + 256 - RUN_MASK) / 256; + lastRunSize -= llAdd; } - ip = anchor + lastRunSize; + DEBUGLOG(6, "Final literal run : %i literals", (int)lastRunSize); + ip = anchor + lastRunSize; /* can be != iend if limit==fillOutput */ if (lastRunSize >= RUN_MASK) { size_t accumulator = lastRunSize - RUN_MASK; @@ -687,9 +761,25 @@ _last_literals: _dest_overflow: if (limit == fillOutput) { + /* Assumption : ip, anchor, ml and ref must be set correctly */ + size_t const ll = (size_t)(ip - anchor); + size_t const ll_addbytes = (ll + 240) / 255; + size_t const ll_totalCost = 1 + ll_addbytes + ll; + BYTE* const maxLitPos = oend - 3; /* 2 for offset, 1 for token */ + DEBUGLOG(6, "Last sequence overflowing"); op = optr; /* restore correct out pointer */ + if (op + ll_totalCost <= maxLitPos) { + /* ll validated; now adjust match length */ + size_t const bytesLeftForMl = (size_t)(maxLitPos - (op+ll_totalCost)); + size_t const maxMlSize = MINMATCH + (ML_MASK-1) + (bytesLeftForMl * 255); + assert(maxMlSize < INT_MAX); assert(ml >= 0); + if ((size_t)ml > maxMlSize) ml = (int)maxMlSize; + if ((oend + LASTLITERALS) - (op + ll_totalCost + 2) - 1 + ml >= MFLIMIT) { + LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ref, notLimited, oend); + } } goto _last_literals; } + /* compression failed */ return 0; } @@ -700,7 +790,7 @@ static int LZ4HC_compress_optimal( LZ4HC_CCtx_internal* ctx, int const nbSearches, size_t sufficient_len, const limitedOutput_directive limit, int const fullUpdate, const dictCtx_directive dict, - HCfavor_e favorDecSpeed); + const HCfavor_e favorDecSpeed); LZ4_FORCE_INLINE int LZ4HC_compress_generic_internal ( @@ -717,7 +807,7 @@ LZ4_FORCE_INLINE int LZ4HC_compress_generic_internal ( typedef enum { lz4hc, lz4opt } lz4hc_strat_e; typedef struct { lz4hc_strat_e strat; - U32 nbSearches; + int nbSearches; U32 targetLength; } cParams_t; static const cParams_t clTable[LZ4HC_CLEVEL_MAX+1] = { @@ -736,7 +826,8 @@ LZ4_FORCE_INLINE int LZ4HC_compress_generic_internal ( { lz4opt,16384,LZ4_OPT_NUM }, /* 12==LZ4HC_CLEVEL_MAX */ }; - DEBUGLOG(4, "LZ4HC_compress_generic(ctx=%p, src=%p, srcSize=%d)", ctx, src, *srcSizePtr); + DEBUGLOG(4, "LZ4HC_compress_generic(ctx=%p, src=%p, srcSize=%d, limit=%d)", + ctx, src, *srcSizePtr, limit); if (limit == fillOutput && dstCapacity < 1) return 0; /* Impossible to store anything */ if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size (too large or negative) */ @@ -756,7 +847,7 @@ LZ4_FORCE_INLINE int LZ4HC_compress_generic_internal ( assert(cParam.strat == lz4opt); result = LZ4HC_compress_optimal(ctx, src, dst, srcSizePtr, dstCapacity, - (int)cParam.nbSearches, cParam.targetLength, limit, + cParam.nbSearches, cParam.targetLength, limit, cLevel == LZ4HC_CLEVEL_MAX, /* ultra mode */ dict, favor); } @@ -829,27 +920,22 @@ LZ4HC_compress_generic ( int LZ4_sizeofStateHC(void) { return (int)sizeof(LZ4_streamHC_t); } -#ifndef _MSC_VER /* for some reason, Visual fails the aligment test on 32-bit x86 : - * it reports an aligment of 8-bytes, - * while actually aligning LZ4_streamHC_t on 4 bytes. */ static size_t LZ4_streamHC_t_alignment(void) { - struct { char c; LZ4_streamHC_t t; } t_a; - return sizeof(t_a) - sizeof(t_a.t); -} +#if LZ4_ALIGN_TEST + typedef struct { char c; LZ4_streamHC_t t; } t_a; + return sizeof(t_a) - sizeof(LZ4_streamHC_t); +#else + return 1; /* effectively disabled */ #endif +} /* state is presumed correctly initialized, * in which case its size and alignment have already been validate */ int LZ4_compress_HC_extStateHC_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel) { LZ4HC_CCtx_internal* const ctx = &((LZ4_streamHC_t*)state)->internal_donotuse; -#ifndef _MSC_VER /* for some reason, Visual fails the aligment test on 32-bit x86 : - * it reports an aligment of 8-bytes, - * while actually aligning LZ4_streamHC_t on 4 bytes. */ - assert(((size_t)state & (LZ4_streamHC_t_alignment() - 1)) == 0); /* check alignment */ -#endif - if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ + if (!LZ4_isAligned(state, LZ4_streamHC_t_alignment())) return 0; LZ4_resetStreamHC_fast((LZ4_streamHC_t*)state, compressionLevel); LZ4HC_init_internal (ctx, (const BYTE*)src); if (dstCapacity < LZ4_compressBound(srcSize)) @@ -898,10 +984,11 @@ int LZ4_compress_HC_destSize(void* state, const char* source, char* dest, int* s /* allocation */ LZ4_streamHC_t* LZ4_createStreamHC(void) { - LZ4_streamHC_t* const LZ4_streamHCPtr = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t)); - if (LZ4_streamHCPtr==NULL) return NULL; - LZ4_initStreamHC(LZ4_streamHCPtr, sizeof(*LZ4_streamHCPtr)); /* full initialization, malloc'ed buffer can be full of garbage */ - return LZ4_streamHCPtr; + LZ4_streamHC_t* const state = + (LZ4_streamHC_t*)ALLOC_AND_ZERO(sizeof(LZ4_streamHC_t)); + if (state == NULL) return NULL; + LZ4_setCompressionLevel(state, LZ4HC_CLEVEL_DEFAULT); + return state; } int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) @@ -916,22 +1003,16 @@ int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr) LZ4_streamHC_t* LZ4_initStreamHC (void* buffer, size_t size) { LZ4_streamHC_t* const LZ4_streamHCPtr = (LZ4_streamHC_t*)buffer; - if (buffer == NULL) return NULL; - if (size < sizeof(LZ4_streamHC_t)) return NULL; -#ifndef _MSC_VER /* for some reason, Visual fails the aligment test on 32-bit x86 : - * it reports an aligment of 8-bytes, - * while actually aligning LZ4_streamHC_t on 4 bytes. */ - if (((size_t)buffer) & (LZ4_streamHC_t_alignment() - 1)) return NULL; /* alignment check */ -#endif /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */ LZ4_STATIC_ASSERT(sizeof(LZ4HC_CCtx_internal) <= LZ4_STREAMHCSIZE); - DEBUGLOG(4, "LZ4_initStreamHC(%p, %u)", LZ4_streamHCPtr, (unsigned)size); - /* end-base will trigger a clearTable on starting compression */ - LZ4_streamHCPtr->internal_donotuse.end = (const BYTE *)(ptrdiff_t)-1; - LZ4_streamHCPtr->internal_donotuse.base = NULL; - LZ4_streamHCPtr->internal_donotuse.dictCtx = NULL; - LZ4_streamHCPtr->internal_donotuse.favorDecSpeed = 0; - LZ4_streamHCPtr->internal_donotuse.dirty = 0; + DEBUGLOG(4, "LZ4_initStreamHC(%p, %u)", buffer, (unsigned)size); + /* check conditions */ + if (buffer == NULL) return NULL; + if (size < sizeof(LZ4_streamHC_t)) return NULL; + if (!LZ4_isAligned(buffer, LZ4_streamHC_t_alignment())) return NULL; + /* init */ + { LZ4HC_CCtx_internal* const hcstate = &(LZ4_streamHCPtr->internal_donotuse); + MEM_INIT(hcstate, 0, sizeof(*hcstate)); } LZ4_setCompressionLevel(LZ4_streamHCPtr, LZ4HC_CLEVEL_DEFAULT); return LZ4_streamHCPtr; } @@ -976,7 +1057,7 @@ int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize) { LZ4HC_CCtx_internal* const ctxPtr = &LZ4_streamHCPtr->internal_donotuse; - DEBUGLOG(4, "LZ4_loadDictHC(%p, %p, %d)", LZ4_streamHCPtr, dictionary, dictSize); + DEBUGLOG(4, "LZ4_loadDictHC(ctx:%p, dict:%p, dictSize:%d)", LZ4_streamHCPtr, dictionary, dictSize); assert(LZ4_streamHCPtr != NULL); if (dictSize > 64 KB) { dictionary += (size_t)dictSize - 64 KB; @@ -1012,16 +1093,20 @@ static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBl ctxPtr->base = newBlock - ctxPtr->dictLimit; ctxPtr->end = newBlock; ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */ + + /* cannot reference an extDict and a dictCtx at the same time */ + ctxPtr->dictCtx = NULL; } -static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, - const char* src, char* dst, - int* srcSizePtr, int dstCapacity, - limitedOutput_directive limit) +static int +LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, + const char* src, char* dst, + int* srcSizePtr, int dstCapacity, + limitedOutput_directive limit) { LZ4HC_CCtx_internal* const ctxPtr = &LZ4_streamHCPtr->internal_donotuse; - DEBUGLOG(4, "LZ4_compressHC_continue_generic(ctx=%p, src=%p, srcSize=%d)", - LZ4_streamHCPtr, src, *srcSizePtr); + DEBUGLOG(5, "LZ4_compressHC_continue_generic(ctx=%p, src=%p, srcSize=%d, limit=%d)", + LZ4_streamHCPtr, src, *srcSizePtr, limit); assert(ctxPtr != NULL); /* auto-init if forgotten */ if (ctxPtr->base == NULL) LZ4HC_init_internal (ctxPtr, (const BYTE*) src); @@ -1045,8 +1130,7 @@ static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, if (sourceEnd > dictEnd) sourceEnd = dictEnd; ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase); if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit; - } - } + } } return LZ4HC_compress_generic (ctxPtr, src, dst, srcSizePtr, dstCapacity, ctxPtr->compressionLevel, limit); } @@ -1066,23 +1150,30 @@ int LZ4_compress_HC_continue_destSize (LZ4_streamHC_t* LZ4_streamHCPtr, const ch -/* dictionary saving */ - +/* LZ4_saveDictHC : + * save history content + * into a user-provided buffer + * which is then used to continue compression + */ int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize) { LZ4HC_CCtx_internal* const streamPtr = &LZ4_streamHCPtr->internal_donotuse; int const prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit)); - DEBUGLOG(4, "LZ4_saveDictHC(%p, %p, %d)", LZ4_streamHCPtr, safeBuffer, dictSize); + DEBUGLOG(5, "LZ4_saveDictHC(%p, %p, %d)", LZ4_streamHCPtr, safeBuffer, dictSize); + assert(prefixSize >= 0); if (dictSize > 64 KB) dictSize = 64 KB; if (dictSize < 4) dictSize = 0; if (dictSize > prefixSize) dictSize = prefixSize; - memmove(safeBuffer, streamPtr->end - dictSize, dictSize); + if (safeBuffer == NULL) assert(dictSize == 0); + if (dictSize > 0) + memmove(safeBuffer, streamPtr->end - dictSize, dictSize); { U32 const endIndex = (U32)(streamPtr->end - streamPtr->base); streamPtr->end = (const BYTE*)safeBuffer + dictSize; streamPtr->base = streamPtr->end - endIndex; streamPtr->dictLimit = endIndex - (U32)dictSize; streamPtr->lowLimit = endIndex - (U32)dictSize; - if (streamPtr->nextToUpdate < streamPtr->dictLimit) streamPtr->nextToUpdate = streamPtr->dictLimit; + if (streamPtr->nextToUpdate < streamPtr->dictLimit) + streamPtr->nextToUpdate = streamPtr->dictLimit; } return dictSize; } @@ -1232,8 +1323,13 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, const dictCtx_directive dict, const HCfavor_e favorDecSpeed) { + int retval = 0; #define TRAILING_LITERALS 3 +#ifdef LZ4HC_HEAPMODE + LZ4HC_optimal_t* const opt = (LZ4HC_optimal_t*)ALLOC(sizeof(LZ4HC_optimal_t) * (LZ4_OPT_NUM + TRAILING_LITERALS)); +#else LZ4HC_optimal_t opt[LZ4_OPT_NUM + TRAILING_LITERALS]; /* ~64 KB, which is a bit large for stack... */ +#endif const BYTE* ip = (const BYTE*) source; const BYTE* anchor = ip; @@ -1243,15 +1339,19 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, BYTE* op = (BYTE*) dst; BYTE* opSaved = (BYTE*) dst; BYTE* oend = op + dstCapacity; + int ovml = MINMATCH; /* overflow - last sequence */ + const BYTE* ovref = NULL; /* init */ +#ifdef LZ4HC_HEAPMODE + if (opt == NULL) goto _return_label; +#endif DEBUGLOG(5, "LZ4HC_compress_optimal(dst=%p, dstCapa=%u)", dst, (unsigned)dstCapacity); *srcSizePtr = 0; if (limit == fillOutput) oend -= LASTLITERALS; /* Hack for support LZ4 format restriction */ if (sufficient_len >= LZ4_OPT_NUM) sufficient_len = LZ4_OPT_NUM-1; /* Main Loop */ - assert(ip - anchor < LZ4_MAX_INPUT_SIZE); while (ip <= mflimit) { int const llen = (int)(ip - anchor); int best_mlen, best_off; @@ -1265,8 +1365,11 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, int const firstML = firstMatch.len; const BYTE* const matchPos = ip - firstMatch.off; opSaved = op; - if ( LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), firstML, matchPos, limit, oend) ) /* updates ip, op and anchor */ + if ( LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), firstML, matchPos, limit, oend) ) { /* updates ip, op and anchor */ + ovml = firstML; + ovref = matchPos; goto _dest_overflow; + } continue; } @@ -1408,7 +1511,7 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, best_off = opt[last_match_pos].off; cur = last_match_pos - best_mlen; - encode: /* cur, last_match_pos, best_mlen, best_off must be set */ +encode: /* cur, last_match_pos, best_mlen, best_off must be set */ assert(cur < LZ4_OPT_NUM); assert(last_match_pos >= 1); /* == 1 when only one candidate */ DEBUGLOG(6, "reverse traversal, looking for shortest path (last_match_pos=%i)", last_match_pos); @@ -1438,25 +1541,31 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, assert(ml >= MINMATCH); assert((offset >= 1) && (offset <= LZ4_DISTANCE_MAX)); opSaved = op; - if ( LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ip - offset, limit, oend) ) /* updates ip, op and anchor */ + if ( LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ml, ip - offset, limit, oend) ) { /* updates ip, op and anchor */ + ovml = ml; + ovref = ip - offset; goto _dest_overflow; - } } + } } } } /* while (ip <= mflimit) */ - _last_literals: +_last_literals: /* Encode Last Literals */ { size_t lastRunSize = (size_t)(iend - anchor); /* literals */ - size_t litLength = (lastRunSize + 255 - RUN_MASK) / 255; - size_t const totalSize = 1 + litLength + lastRunSize; + size_t llAdd = (lastRunSize + 255 - RUN_MASK) / 255; + size_t const totalSize = 1 + llAdd + lastRunSize; if (limit == fillOutput) oend += LASTLITERALS; /* restore correct value */ if (limit && (op + totalSize > oend)) { - if (limit == limitedOutput) return 0; /* Check output limit */ + if (limit == limitedOutput) { /* Check output limit */ + retval = 0; + goto _return_label; + } /* adapt lastRunSize to fill 'dst' */ - lastRunSize = (size_t)(oend - op) - 1; - litLength = (lastRunSize + 255 - RUN_MASK) / 255; - lastRunSize -= litLength; + lastRunSize = (size_t)(oend - op) - 1 /*token*/; + llAdd = (lastRunSize + 256 - RUN_MASK) / 256; + lastRunSize -= llAdd; } - ip = anchor + lastRunSize; + DEBUGLOG(6, "Final literal run : %i literals", (int)lastRunSize); + ip = anchor + lastRunSize; /* can be != iend if limit==fillOutput */ if (lastRunSize >= RUN_MASK) { size_t accumulator = lastRunSize - RUN_MASK; @@ -1472,14 +1581,35 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx, /* End */ *srcSizePtr = (int) (((const char*)ip) - source); - return (int) ((char*)op-dst); + retval = (int) ((char*)op-dst); + goto _return_label; - _dest_overflow: - if (limit == fillOutput) { - op = opSaved; /* restore correct out pointer */ - goto _last_literals; - } - return 0; - } - - } +_dest_overflow: +if (limit == fillOutput) { + /* Assumption : ip, anchor, ovml and ovref must be set correctly */ + size_t const ll = (size_t)(ip - anchor); + size_t const ll_addbytes = (ll + 240) / 255; + size_t const ll_totalCost = 1 + ll_addbytes + ll; + BYTE* const maxLitPos = oend - 3; /* 2 for offset, 1 for token */ + DEBUGLOG(6, "Last sequence overflowing (only %i bytes remaining)", (int)(oend-1-opSaved)); + op = opSaved; /* restore correct out pointer */ + if (op + ll_totalCost <= maxLitPos) { + /* ll validated; now adjust match length */ + size_t const bytesLeftForMl = (size_t)(maxLitPos - (op+ll_totalCost)); + size_t const maxMlSize = MINMATCH + (ML_MASK-1) + (bytesLeftForMl * 255); + assert(maxMlSize < INT_MAX); assert(ovml >= 0); + if ((size_t)ovml > maxMlSize) ovml = (int)maxMlSize; + if ((oend + LASTLITERALS) - (op + ll_totalCost + 2) - 1 + ovml >= MFLIMIT) { + DEBUGLOG(6, "Space to end : %i + ml (%i)", (int)((oend + LASTLITERALS) - (op + ll_totalCost + 2) - 1), ovml); + DEBUGLOG(6, "Before : ip = %p, anchor = %p", ip, anchor); + LZ4HC_encodeSequence(UPDATABLE(ip, op, anchor), ovml, ovref, notLimited, oend); + DEBUGLOG(6, "After : ip = %p, anchor = %p", ip, anchor); + } } + goto _last_literals; +} +_return_label: +#ifdef LZ4HC_HEAPMODE + FREEMEM(opt); +#endif + return retval; +} diff --git a/common/tracy_lz4hc.hpp b/common/tracy_lz4hc.hpp index ac276aff..3d441fb6 100644 --- a/common/tracy_lz4hc.hpp +++ b/common/tracy_lz4hc.hpp @@ -31,15 +31,17 @@ - LZ4 source repository : https://github.com/lz4/lz4 - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c */ -#ifndef TRACY_LZ4_HC_H_19834876238432 -#define TRACY_LZ4_HC_H_19834876238432 +#ifndef LZ4_HC_H_19834876238432 +#define LZ4_HC_H_19834876238432 + +#if defined (__cplusplus) +extern "C" { +#endif /* --- Dependency --- */ /* note : lz4hc requires lz4.h/lz4.c for compilation */ -#include "tracy_lz4.hpp" /* stddef, LZ4LIB_API, LZ4_DEPRECATED */ +#include "lz4.h" /* stddef, LZ4LIB_API, LZ4_DEPRECATED */ -namespace tracy -{ /* --- Useful constants --- */ #define LZ4HC_CLEVEL_MIN 3 @@ -196,57 +198,32 @@ LZ4LIB_API int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, in #define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1) -#if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -#include - typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal; struct LZ4HC_CCtx_internal { - uint32_t hashTable[LZ4HC_HASHTABLESIZE]; - uint16_t chainTable[LZ4HC_MAXD]; - const uint8_t* end; /* next block here to continue on current prefix */ - const uint8_t* base; /* All index relative to this position */ - const uint8_t* dictBase; /* alternate base for extDict */ - uint32_t dictLimit; /* below that point, need extDict */ - uint32_t lowLimit; /* below that point, no more dict */ - uint32_t nextToUpdate; /* index from which to continue dictionary update */ - short compressionLevel; - int8_t favorDecSpeed; /* favor decompression speed if this flag set, - otherwise, favor compression ratio */ - int8_t dirty; /* stream has to be fully reset if this flag is set */ + LZ4_u32 hashTable[LZ4HC_HASHTABLESIZE]; + LZ4_u16 chainTable[LZ4HC_MAXD]; + const LZ4_byte* end; /* next block here to continue on current prefix */ + const LZ4_byte* base; /* All index relative to this position */ + const LZ4_byte* dictBase; /* alternate base for extDict */ + LZ4_u32 dictLimit; /* below that point, need extDict */ + LZ4_u32 lowLimit; /* below that point, no more dict */ + LZ4_u32 nextToUpdate; /* index from which to continue dictionary update */ + short compressionLevel; + LZ4_i8 favorDecSpeed; /* favor decompression speed if this flag set, + otherwise, favor compression ratio */ + LZ4_i8 dirty; /* stream has to be fully reset if this flag is set */ const LZ4HC_CCtx_internal* dictCtx; }; -#else - -typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal; -struct LZ4HC_CCtx_internal -{ - unsigned int hashTable[LZ4HC_HASHTABLESIZE]; - unsigned short chainTable[LZ4HC_MAXD]; - const unsigned char* end; /* next block here to continue on current prefix */ - const unsigned char* base; /* All index relative to this position */ - const unsigned char* dictBase; /* alternate base for extDict */ - unsigned int dictLimit; /* below that point, need extDict */ - unsigned int lowLimit; /* below that point, no more dict */ - unsigned int nextToUpdate; /* index from which to continue dictionary update */ - short compressionLevel; - char favorDecSpeed; /* favor decompression speed if this flag set, - otherwise, favor compression ratio */ - char dirty; /* stream has to be fully reset if this flag is set */ - const LZ4HC_CCtx_internal* dictCtx; -}; - -#endif - /* Do not use these definitions directly ! * Declare or allocate an LZ4_streamHC_t instead. */ -#define LZ4_STREAMHCSIZE (4*LZ4HC_HASHTABLESIZE + 2*LZ4HC_MAXD + 56 + ((sizeof(void*)==16) ? 56 : 0) /* AS400*/ ) /* 262200 or 262256*/ -#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t)) +#define LZ4_STREAMHCSIZE 262200 /* static size, for inter-version compatibility */ +#define LZ4_STREAMHCSIZE_VOIDP (LZ4_STREAMHCSIZE / sizeof(void*)) union LZ4_streamHC_u { - size_t table[LZ4_STREAMHCSIZE_SIZET]; + void* table[LZ4_STREAMHCSIZE_VOIDP]; LZ4HC_CCtx_internal internal_donotuse; }; /* previously typedef'd to LZ4_streamHC_t */ @@ -315,7 +292,9 @@ LZ4_DEPRECATED("use LZ4_initStreamHC() instead") LZ4LIB_API int LZ4_resetStre LZ4LIB_API void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionLevel); +#if defined (__cplusplus) } +#endif #endif /* LZ4_HC_H_19834876238432 */ @@ -332,8 +311,12 @@ LZ4LIB_API void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionL #ifndef LZ4_HC_SLO_098092834 #define LZ4_HC_SLO_098092834 -namespace tracy -{ +#define LZ4_STATIC_LINKING_ONLY /* LZ4LIB_STATIC_API */ +#include "lz4.h" + +#if defined (__cplusplus) +extern "C" { +#endif /*! LZ4_setCompressionLevel() : v1.8.0+ (experimental) * It's possible to change compression level @@ -422,7 +405,9 @@ LZ4LIB_STATIC_API void LZ4_attach_HC_dictionary( LZ4_streamHC_t *working_stream, const LZ4_streamHC_t *dictionary_stream); +#if defined (__cplusplus) } +#endif #endif /* LZ4_HC_SLO_098092834 */ #endif /* LZ4_HC_STATIC_LINKING_ONLY */