From a3998d066381a45cd1e18e76cab6e5b1e27ee169 Mon Sep 17 00:00:00 2001 From: Thomas Waldmann Date: Mon, 29 Jan 2024 21:54:49 +0100 Subject: [PATCH] upgrade bundled lz4 to 1.9.4 --- src/borg/algorithms/lz4/lib/lz4.c | 1092 +++++++++++++++++++---------- src/borg/algorithms/lz4/lib/lz4.h | 294 +++++--- 2 files changed, 894 insertions(+), 492 deletions(-) diff --git a/src/borg/algorithms/lz4/lib/lz4.c b/src/borg/algorithms/lz4/lib/lz4.c index 9808d70ae..654bfdf32 100644 --- a/src/borg/algorithms/lz4/lib/lz4.c +++ b/src/borg/algorithms/lz4/lib/lz4.c @@ -1,6 +1,6 @@ /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-present, Yann Collet. + Copyright (C) 2011-2020, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -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 @@ -114,10 +121,10 @@ /*-************************************ * 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 */ +# pragma warning(disable : 6237) /* disable: C6237: conditional expression is always 0 */ #endif /* _MSC_VER */ #ifndef LZ4_FORCE_INLINE @@ -136,7 +143,7 @@ # 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%, @@ -151,11 +158,11 @@ * 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__) @@ -171,16 +178,60 @@ #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) -#include /* memset, memcpy */ -#define MEM_INIT(p,v,s) memset((p),(v),(s)) + +/*! LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION : + * Disable relatively high-level LZ4/HC functions that use dynamic memory + * allocation functions (malloc(), calloc(), free()). + * + * Note that this is a compile-time switch. And since it disables + * public/stable LZ4 v1 API functions, we don't recommend using this + * symbol to generate a library for distribution. + * + * The following public functions are removed when this symbol is defined. + * - lz4 : LZ4_createStream, LZ4_freeStream, + * LZ4_createStreamDecode, LZ4_freeStreamDecode, LZ4_create (deprecated) + * - lz4hc : LZ4_createStreamHC, LZ4_freeStreamHC, + * LZ4_createHC (deprecated), LZ4_freeHC (deprecated) + * - lz4frame, lz4file : All LZ4F_* functions + */ +#if defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) +# define ALLOC(s) lz4_error_memory_allocation_is_disabled +# define ALLOC_AND_ZERO(s) lz4_error_memory_allocation_is_disabled +# define FREEMEM(p) lz4_error_memory_allocation_is_disabled +#elif defined(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 + +#if ! LZ4_FREESTANDING +# include /* memset, memcpy */ +#endif +#if !defined(LZ4_memset) +# define LZ4_memset(p,v,s) memset((p),(v),(s)) +#endif +#define MEM_INIT(p,v,s) LZ4_memset((p),(v),(s)) /*-************************************ @@ -225,21 +276,27 @@ 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; @@ -249,6 +306,9 @@ static int g_debuglog_enable = 1; 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; @@ -273,6 +333,31 @@ typedef enum { /*-************************************ * 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(LZ4_memcpy) +# 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 +#endif + +#if !defined(LZ4_memmove) +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4_memmove __builtin_memmove +# else +# define LZ4_memmove memmove +# endif +#endif + static unsigned LZ4_isLittleEndian(void) { const union { U32 u; BYTE c[4]; } one = { 1 }; /* don't use static : performance detrimental */ @@ -294,40 +379,40 @@ static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; } /* __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; +typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) LZ4_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 U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign*)ptr)->u16; } +static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign*)ptr)->u32; } +static reg_t LZ4_read_ARCH(const void* ptr) { return ((const LZ4_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; } +static void LZ4_write16(void* memPtr, U16 value) { ((LZ4_unalign*)memPtr)->u16 = value; } +static void LZ4_write32(void* memPtr, U32 value) { ((LZ4_unalign*)memPtr)->u32 = value; } #else /* safe and portable access using memcpy() */ static U16 LZ4_read16(const void* memPtr) { - U16 val; memcpy(&val, memPtr, sizeof(val)); return val; + U16 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; } static U32 LZ4_read32(const void* memPtr) { - U32 val; memcpy(&val, memPtr, sizeof(val)); return val; + U32 val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; } static reg_t LZ4_read_ARCH(const void* memPtr) { - reg_t val; memcpy(&val, memPtr, sizeof(val)); return val; + reg_t val; LZ4_memcpy(&val, memPtr, sizeof(val)); return val; } static void LZ4_write16(void* memPtr, U16 value) { - memcpy(memPtr, &value, sizeof(value)); + LZ4_memcpy(memPtr, &value, sizeof(value)); } static void LZ4_write32(void* memPtr, U32 value) { - memcpy(memPtr, &value, sizeof(value)); + LZ4_memcpy(memPtr, &value, sizeof(value)); } #endif /* LZ4_FORCE_MEMORY_ACCESS */ @@ -355,14 +440,14 @@ static void LZ4_writeLE16(void* memPtr, U16 value) } /* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ -LZ4_FORCE_O2_INLINE_GCC_PPC64LE +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 { memcpy(d,s,8); d+=8; s+=8; } while (d= 16. */ -LZ4_FORCE_O2_INLINE_GCC_PPC64LE void +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 { memcpy(d,s,16); 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_O2_INLINE_GCC_PPC64LE void +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); - LZ4_write32(dstPtr, 0); /* silence an msan warning when offset==0 */ switch(offset) { case 1: - memset(v, *srcPtr, 8); + MEM_INIT(v, *srcPtr, 8); break; case 2: - memcpy(v, srcPtr, 2); - memcpy(&v[2], srcPtr, 2); - memcpy(&v[4], &v[0], 4); + LZ4_memcpy(v, srcPtr, 2); + LZ4_memcpy(&v[2], srcPtr, 2); +#if defined(_MSC_VER) && (_MSC_VER <= 1933) /* MSVC 2022 ver 17.3 or earlier */ +# pragma warning(push) +# pragma warning(disable : 6385) /* warning C6385: Reading invalid data from 'v'. */ +#endif + LZ4_memcpy(&v[4], v, 4); +#if defined(_MSC_VER) && (_MSC_VER <= 1933) /* MSVC 2022 ver 17.3 or earlier */ +# pragma warning(pop) +#endif break; case 4: - memcpy(v, srcPtr, 4); - memcpy(&v[4], srcPtr, 4); + LZ4_memcpy(v, srcPtr, 4); + LZ4_memcpy(&v[4], srcPtr, 4); break; default: LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset); return; } - memcpy(dstPtr, v, 8); + LZ4_memcpy(dstPtr, v, 8); dstPtr += 8; while (dstPtr < dstEnd) { - memcpy(dstPtr, v, 8); + LZ4_memcpy(dstPtr, v, 8); dstPtr += 8; } } @@ -462,75 +557,103 @@ LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const si **************************************/ 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) + if (sizeof(val) == 8) { +# if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT) +/*-************************************************************************************************* +* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11. +* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics +* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC. +****************************************************************************************************/ +# if defined(__clang__) && (__clang_major__ < 10) + /* Avoid undefined clang-cl intrinsics issue. + * See https://github.com/lz4/lz4/pull/1017 for details. */ + return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3; +# else + /* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */ + return (unsigned)_tzcnt_u64(val) >> 3; +# endif +# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; - _BitScanForward64( &r, (U64)val ); - return (int)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) + _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) +# if defined(_MSC_VER) && (_MSC_VER >= 1400) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r; - _BitScanForward( &r, (U32)val ); - return (int)(r>>3); -# elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) + _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) + 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) +# 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) @@ -585,10 +708,10 @@ typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t; * - usingExtDict : Like withPrefix64k, but the preceding content is somewhere * else in memory, starting at ctx->dictionary with length * ctx->dictSize. - * - usingDictCtx : Like usingExtDict, but everything concerning the preceding - * content is in a separate context, pointed to by - * ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table - * entries in the current context that refer to positions + * - usingDictCtx : Everything concerning the preceding content is + * in a separate context, pointed to by ctx->dictCtx. + * ctx->dictionary, ctx->dictSize, and table entries + * in the current context that refer to positions * preceding the beginning of the current compression are * ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx * ->dictSize describe the location and size of the preceding @@ -605,12 +728,12 @@ 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 sizeof(LZ4_stream_t); } -/*-************************************ -* Internal Definitions used in Tests -**************************************/ +/*-**************************************** +* Internal Definitions, used only in Tests +*******************************************/ #if defined (__cplusplus) extern "C" { #endif @@ -620,7 +743,9 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const void* dictStart, size_t dictSize); - +int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest, + int compressedSize, int targetOutputSize, int dstCapacity, + const void* dictStart, size_t dictSize); #if defined (__cplusplus) } #endif @@ -628,7 +753,7 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, /*-****************************** * Compression functions ********************************/ -static U32 LZ4_hash4(U32 sequence, tableType_t const tableType) +LZ4_FORCE_INLINE U32 LZ4_hash4(U32 sequence, tableType_t const tableType) { if (tableType == byU16) return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); @@ -636,7 +761,7 @@ static U32 LZ4_hash4(U32 sequence, tableType_t const tableType) return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); } -static U32 LZ4_hash5(U64 sequence, tableType_t const tableType) +LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType) { const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; if (LZ4_isLittleEndian()) { @@ -654,7 +779,7 @@ LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tab return LZ4_hash4(LZ4_read32(p), tableType); } -static void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType) +LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType) { switch (tableType) { @@ -666,7 +791,7 @@ static void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType) } } -static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) +LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) { switch (tableType) { @@ -678,7 +803,7 @@ static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t cons } } -static void LZ4_putPositionOnHash(const BYTE* p, U32 h, +LZ4_FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase) { @@ -703,7 +828,7 @@ LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_ * Assumption 1 : only valid if tableType == byU32 or byU16. * Assumption 2 : h is presumed valid (within limits of hash table) */ -static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType) +LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType) { LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2); if (tableType == byU32) { @@ -739,22 +864,13 @@ 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; - } - /* 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 ((tableType_t)cctx->tableType != clearedTable) { assert(inputSize >= 0); - if (cctx->tableType != tableType + if ((tableType_t)cctx->tableType != tableType || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU) || ((tableType == byU32) && cctx->currentOffset > 1 GB) || tableType == byPtr @@ -763,15 +879,16 @@ LZ4_prepareTable(LZ4_stream_t_internal* const cctx, 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)"); } } - /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back, is faster - * than compressing without a gap. However, compressing with - * currentOffset == 0 is faster still, so we preserve that case. + /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back, + * is faster than compressing without a gap. + * However, compressing with currentOffset == 0 is faster still, + * so we preserve that case. */ if (cctx->currentOffset != 0 && tableType == byU32) { DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset"); @@ -785,13 +902,17 @@ LZ4_prepareTable(LZ4_stream_t_internal* const cctx, } /** 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, const int inputSize, - int *inputConsumed, /* only written when outputDirective == fillOutput */ + int* inputConsumed, /* only written when outputDirective == fillOutput */ const int maxOutputSize, const limitedOutput_directive outputDirective, const tableType_t tableType, @@ -815,7 +936,7 @@ 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; @@ -823,7 +944,8 @@ 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) ? NULL : + (dictDirective == usingDictCtx) ? dictionary + dictSize - dictCtx->currentOffset : dictionary + dictSize - startIndex; @@ -833,11 +955,11 @@ 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 (tableType==byPtr) assert(dictDirective==noDict); /* only supported use case with byPtr */ assert(acceleration >= 1); @@ -854,7 +976,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( cctx->dictSize += (U32)inputSize; } cctx->currentOffset += (U32)inputSize; - cctx->tableType = (U16)tableType; + cctx->tableType = (U32)tableType; if (inputSize= MINMATCH); + assert(dictBase); match = dictBase + matchIndex; lowLimit = dictionary; } else { @@ -986,7 +1109,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic( _next_match: /* at this stage, the following variables must be correctly set : * - ip : at start of LZ operation - * - match : at start of previous pattern occurence; can be within current prefix, or within extDict + * - match : at start of previous pattern occurrence; can be within current prefix, or within extDict * - offset : if maybe_ext_memSegment==1 (constant) * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written @@ -1111,6 +1234,7 @@ _next_match: } } else if (dictDirective==usingExtDict) { if (matchIndex < startIndex) { + assert(dictBase); match = dictBase + matchIndex; lowLimit = dictionary; /* required for match length counter */ } else { @@ -1147,13 +1271,14 @@ _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; @@ -1162,7 +1287,7 @@ _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); @@ -1211,7 +1378,8 @@ 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) { @@ -1249,7 +1417,7 @@ int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutp { int result; #if (LZ4_HEAPMODE) - LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + LZ4_stream_t* ctxPtr = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ if (ctxPtr == NULL) return 0; #else LZ4_stream_t ctx; @@ -1270,22 +1438,6 @@ 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. */ @@ -1330,37 +1482,35 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe * Streaming functions ********************************/ +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) LZ4_stream_t* LZ4_createStream(void) { LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); - LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */ + LZ4_STATIC_ASSERT(sizeof(LZ4_stream_t) >= sizeof(LZ4_stream_t_internal)); DEBUGLOG(4, "LZ4_createStream %p", lz4s); if (lz4s == NULL) return NULL; LZ4_initStream(lz4s, sizeof(*lz4s)); return lz4s; } +#endif -#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 (!LZ4_isAligned(buffer, LZ4_stream_t_alignment())) return NULL; + MEM_INIT(buffer, 0, sizeof(LZ4_stream_t_internal)); return (LZ4_stream_t*)buffer; } @@ -1369,13 +1519,14 @@ 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) { LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32); } +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { if (!LZ4_stream) return 0; /* support free on NULL */ @@ -1383,6 +1534,7 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream) FREEMEM(LZ4_stream); return (0); } +#endif #define HASH_UNIT sizeof(reg_t) @@ -1418,7 +1570,7 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) base = dictEnd - dict->currentOffset; dict->dictionary = p; dict->dictSize = (U32)(dictEnd - p); - dict->tableType = tableType; + dict->tableType = (U32)tableType; while (p <= dictEnd-HASH_UNIT) { LZ4_putPosition(p, dict->hashTable, tableType, base); @@ -1428,20 +1580,15 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) return (int)dict->dictSize; } -void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream) { - const LZ4_stream_t_internal* dictCtx = dictionaryStream == NULL ? NULL : +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); DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)", workingStream, dictionaryStream, dictCtx != NULL ? dictCtx->dictSize : 0); - /* 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(workingStream); - 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 @@ -1488,36 +1635,40 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, int acceleration) { const tableType_t tableType = byU32; - LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse; - const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize; + LZ4_stream_t_internal* const streamPtr = &LZ4_stream->internal_donotuse; + const char* dictEnd = streamPtr->dictSize ? (const char*)streamPtr->dictionary + streamPtr->dictSize : NULL; - DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize); + DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i, dictSize=%u)", inputSize, streamPtr->dictSize); - if (streamPtr->dirty) { return 0; } /* Uninitialized structure detected */ - LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */ - if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + LZ4_renormDictT(streamPtr, inputSize); /* fix index overflow */ + 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 */ - && (dictEnd != (const BYTE*)source) ) { + if ( (streamPtr->dictSize < 4) /* tiny dictionary : not enough for a hash */ + && (dictEnd != source) /* prefix mode */ + && (inputSize > 0) /* tolerance : don't lose history, in case next invocation would use prefix mode */ + && (streamPtr->dictCtx == NULL) /* usingDictCtx */ + ) { DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary); + /* remove dictionary existence from history, to employ faster prefix mode */ streamPtr->dictSize = 0; streamPtr->dictionary = (const BYTE*)source; - dictEnd = (const BYTE*)source; + dictEnd = source; } /* Check overlapping input/dictionary space */ - { const BYTE* sourceEnd = (const BYTE*) source + inputSize; - if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) { + { const char* const sourceEnd = source + inputSize; + if ((sourceEnd > (const char*)streamPtr->dictionary) && (sourceEnd < dictEnd)) { streamPtr->dictSize = (U32)(dictEnd - sourceEnd); if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB; if (streamPtr->dictSize < 4) streamPtr->dictSize = 0; - streamPtr->dictionary = dictEnd - streamPtr->dictSize; + streamPtr->dictionary = (const BYTE*)dictEnd - streamPtr->dictSize; } } /* prefix mode : source data follows dictionary */ - if (dictEnd == (const BYTE*)source) { + if (dictEnd == source) { if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration); else @@ -1538,12 +1689,12 @@ 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); } - } else { + } else { /* small data <= 4 KB */ if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration); } else { @@ -1581,19 +1732,25 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* /*! LZ4_saveDict() : * If previously compressed data block is not guaranteed to remain available at its memory location, * save it into a safer place (char* safeBuffer). - * Note : you don't need to call LZ4_loadDict() afterwards, - * dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue(). - * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. + * Note : no need to call LZ4_loadDict() afterwards, dictionary is immediately usable, + * one can therefore call LZ4_compress_fast_continue() right after. + * @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error. */ 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; + + DEBUGLOG(5, "LZ4_saveDict : dictSize=%i, safeBuffer=%p", dictSize, safeBuffer); 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) { + const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize; + assert(dict->dictionary); + LZ4_memmove(safeBuffer, previousDictEnd - dictSize, (size_t)dictSize); + } dict->dictionary = (const BYTE*)safeBuffer; dict->dictSize = (U32)dictSize; @@ -1607,41 +1764,167 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) * Decompression functions ********************************/ -typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive; #undef MIN #define MIN(a,b) ( (a) < (b) ? (a) : (b) ) + +/* variant for decompress_unsafe() + * does not know end of input + * presumes input is well formed + * note : will consume at least one byte */ +size_t read_long_length_no_check(const BYTE** pp) +{ + size_t b, l = 0; + do { b = **pp; (*pp)++; l += b; } while (b==255); + DEBUGLOG(6, "read_long_length_no_check: +length=%zu using %zu input bytes", l, l/255 + 1) + return l; +} + +/* core decoder variant for LZ4_decompress_fast*() + * for legacy support only : these entry points are deprecated. + * - Presumes input is correctly formed (no defense vs malformed inputs) + * - Does not know input size (presume input buffer is "large enough") + * - Decompress a full block (only) + * @return : nb of bytes read from input. + * Note : this variant is not optimized for speed, just for maintenance. + * the goal is to remove support of decompress_fast*() variants by v2.0 +**/ +LZ4_FORCE_INLINE int +LZ4_decompress_unsafe_generic( + const BYTE* const istart, + BYTE* const ostart, + int decompressedSize, + + size_t prefixSize, + const BYTE* const dictStart, /* only if dict==usingExtDict */ + const size_t dictSize /* note: =0 if dictStart==NULL */ + ) +{ + const BYTE* ip = istart; + BYTE* op = (BYTE*)ostart; + BYTE* const oend = ostart + decompressedSize; + const BYTE* const prefixStart = ostart - prefixSize; + + DEBUGLOG(5, "LZ4_decompress_unsafe_generic"); + if (dictStart == NULL) assert(dictSize == 0); + + while (1) { + /* start new sequence */ + unsigned token = *ip++; + + /* literals */ + { size_t ll = token >> ML_BITS; + if (ll==15) { + /* long literal length */ + ll += read_long_length_no_check(&ip); + } + if ((size_t)(oend-op) < ll) return -1; /* output buffer overflow */ + LZ4_memmove(op, ip, ll); /* support in-place decompression */ + op += ll; + ip += ll; + if ((size_t)(oend-op) < MFLIMIT) { + if (op==oend) break; /* end of block */ + DEBUGLOG(5, "invalid: literals end at distance %zi from end of block", oend-op); + /* incorrect end of block : + * last match must start at least MFLIMIT==12 bytes before end of output block */ + return -1; + } } + + /* match */ + { size_t ml = token & 15; + size_t const offset = LZ4_readLE16(ip); + ip+=2; + + if (ml==15) { + /* long literal length */ + ml += read_long_length_no_check(&ip); + } + ml += MINMATCH; + + if ((size_t)(oend-op) < ml) return -1; /* output buffer overflow */ + + { const BYTE* match = op - offset; + + /* out of range */ + if (offset > (size_t)(op - prefixStart) + dictSize) { + DEBUGLOG(6, "offset out of range"); + return -1; + } + + /* check special case : extDict */ + if (offset > (size_t)(op - prefixStart)) { + /* extDict scenario */ + const BYTE* const dictEnd = dictStart + dictSize; + const BYTE* extMatch = dictEnd - (offset - (size_t)(op-prefixStart)); + size_t const extml = (size_t)(dictEnd - extMatch); + if (extml > ml) { + /* match entirely within extDict */ + LZ4_memmove(op, extMatch, ml); + op += ml; + ml = 0; + } else { + /* match split between extDict & prefix */ + LZ4_memmove(op, extMatch, extml); + op += extml; + ml -= extml; + } + match = prefixStart; + } + + /* match copy - slow variant, supporting overlap copy */ + { size_t u; + for (u=0; u= lencheck. - * loop_check - check ip >= lencheck in body of loop. Returns loop_error if so. - * initial_check - check ip >= lencheck before start of loop. Returns initial_error if so. - * error (output) - error code. Should be set to 0 before call. - */ -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) + * @ip : input pointer + * @ilimit : position after which if length is not decoded, the input is necessarily corrupted. + * @initial_check - check ip >= ipmax before start of loop. Returns initial_error if so. + * @error (output) - error code. Must be set to 0 before call. +**/ +typedef size_t Rvl_t; +static const Rvl_t rvl_error = (Rvl_t)(-1); +LZ4_FORCE_INLINE Rvl_t +read_variable_length(const BYTE** ip, const BYTE* ilimit, + int initial_check) { - 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; + Rvl_t s, length = 0; + assert(ip != NULL); + assert(*ip != NULL); + assert(ilimit != NULL); + if (initial_check && unlikely((*ip) >= ilimit)) { /* read limit reached */ + return rvl_error; } - } while (s==255); + do { + s = **ip; + (*ip)++; + length += s; + if (unlikely((*ip) > ilimit)) { /* read limit reached */ + return rvl_error; + } + /* accumulator overflow detection (32-bit mode only) */ + if ((sizeof(length)<8) && unlikely(length > ((Rvl_t)(-1)/2)) ) { + return rvl_error; + } + } while (s==255); - return length; + return length; } /*! LZ4_decompress_generic() : @@ -1657,7 +1940,6 @@ LZ4_decompress_generic( int srcSize, int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */ - endCondition_directive endOnInput, /* endOnOutputSize, endOnInputSize */ earlyEnd_directive partialDecoding, /* full, partial */ dict_directive dict, /* noDict, withPrefix64k, usingExtDict */ const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */ @@ -1665,7 +1947,7 @@ LZ4_decompress_generic( const size_t dictSize /* note : = 0 if noDict */ ) { - if (src == NULL) { return -1; } + if ((src == NULL) || (outputSize < 0)) { return -1; } { const BYTE* ip = (const BYTE*) src; const BYTE* const iend = ip + srcSize; @@ -1676,13 +1958,12 @@ LZ4_decompress_generic( const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize; - const int safeDecode = (endOnInput==endOnInputSize); - const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); + const int checkOffset = (dictSize < (int)(64 KB)); /* Set up the "end" pointers for the shortcut. */ - const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/; - const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/; + const BYTE* const shortiend = iend - 14 /*maxLL*/ - 2 /*offset*/; + const BYTE* const shortoend = oend - 14 /*maxLL*/ - 18 /*maxML*/; const BYTE* match; size_t offset; @@ -1694,83 +1975,70 @@ LZ4_decompress_generic( /* Special cases */ assert(lowPrefix <= op); - if ((endOnInput) && (unlikely(outputSize==0))) { + if (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; } + if (unlikely(srcSize==0)) { return -1; } - /* Currently the fast loop shows a regression on qualcomm arm chips. */ + /* LZ4_FAST_DEC_LOOP: + * designed for modern OoO performance cpus, + * where copying reliably 32-bytes is preferable to an unpredictable branch. + * note : fast loop may show a regression for some client arm chips. */ #if LZ4_FAST_DEC_LOOP if ((oend - op) < FASTLOOP_SAFE_DISTANCE) { DEBUGLOG(6, "skip fast decode loop"); goto safe_decode; } - /* Fast loop : decode sequences as long as output < iend-FASTLOOP_SAFE_DISTANCE */ + /* Fast loop : decode sequences as long as output < oend-FASTLOOP_SAFE_DISTANCE */ while (1) { /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */ assert(oend - op >= FASTLOOP_SAFE_DISTANCE); - if (endOnInput) { assert(ip < iend); } + assert(ip < iend); token = *ip++; length = token >> ML_BITS; /* literal length */ - assert(!endOnInput || ip <= iend); /* ip < iend before the increment */ - /* 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 */ + size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1); + if (addl == rvl_error) { goto _output_error; } + length += addl; + if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */ + if (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; } - LZ4_wildCopy32(op, ip, cpy); - } else { /* LZ4_decompress_fast() */ - 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 */ - } + if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; } + LZ4_wildCopy32(op, ip, cpy); ip += length; op = cpy; } else { cpy = op+length; - 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; } - /* Literals can only be 14, but hope compilers optimize if we copy by a register size */ - 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); } - } + 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; } + /* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */ + LZ4_memcpy(op, ip, 16); ip += length; op = cpy; } /* get offset */ offset = LZ4_readLE16(ip); ip+=2; match = op - offset; - assert(match <= op); + assert(match <= op); /* overflow check */ /* get matchlength */ length = token & ML_MASK; if (length == ML_MASK) { - 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, endOnInput, 0, &error); - if (error != ok) { goto _output_error; } - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */ + size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0); + if (addl == rvl_error) { goto _output_error; } + length += addl; length += MINMATCH; + if (unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */ + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */ if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { goto safe_match_copy; } @@ -1780,46 +2048,48 @@ LZ4_decompress_generic( goto safe_match_copy; } - /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */ + /* Fastpath check: skip LZ4_wildCopy32 when true */ if ((dict == withPrefix64k) || (match >= lowPrefix)) { if (offset >= 8) { assert(match >= lowPrefix); assert(match <= op); assert(op + 18 <= oend); - memcpy(op, match, 8); - memcpy(op+8, match+8, 8); - memcpy(op+16, match+16, 2); + 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 */ + if (checkOffset && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */ /* match starting within external dictionary */ if ((dict==usingExtDict) && (match < lowPrefix)) { + assert(dictEnd != NULL); if (unlikely(op+length > oend-LASTLITERALS)) { if (partialDecoding) { - length = MIN(length, (size_t)(oend-op)); /* reach end of buffer */ + 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 */ - memmove(op, dictEnd - (lowPrefix-match), length); + LZ4_memmove(op, dictEnd - (lowPrefix-match), length); op += length; } else { /* 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; @@ -1842,11 +2112,10 @@ LZ4_decompress_generic( /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */ while (1) { + assert(ip < iend); token = *ip++; length = token >> ML_BITS; /* literal length */ - assert(!endOnInput || ip <= iend); /* ip < iend before the increment */ - /* A two-stage shortcut for the most common case: * 1) If the literal length is 0..14, and there is enough space, * enter the shortcut and copy 16 bytes on behalf of the literals @@ -1856,11 +2125,11 @@ LZ4_decompress_generic( * those 18 bytes earlier, upon entering the shortcut (in other words, * there is a combined check for both stages). */ - if ( (endOnInput ? length != RUN_MASK : length <= 8) + if ( (length != RUN_MASK) /* strictly "less than" on input, to re-enter the loop with at least one byte */ - && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) { + && likely((ip < shortiend) & (op <= shortoend)) ) { /* Copy the literals */ - memcpy(op, ip, endOnInput ? 16 : 8); + LZ4_memcpy(op, ip, 16); op += length; ip += length; /* The second stage: prepare for match copying, decode full info. @@ -1875,9 +2144,9 @@ 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; @@ -1890,11 +2159,11 @@ 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 */ + size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1); + if (addl == rvl_error) { goto _output_error; } + length += addl; + if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */ + if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */ } /* copy literals */ @@ -1903,55 +2172,59 @@ LZ4_decompress_generic( safe_literal_copy: #endif LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); - if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) - { + if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) { /* We've either hit the input parsing restriction or the output parsing restriction. - * If we've hit the input parsing condition then this must be the last sequence. - * If we've hit the output parsing condition then we are either using partialDecoding - * or we've hit the output parsing condition. + * 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) { /* 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); - /* If we're in this block because of the input parsing condition, then we must be on the - * last sequence (or invalid), so we must check that we exactly consume the input. + 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-(2+1+LASTLITERALS)) && (ip+length != iend)) { goto _output_error; } - assert(ip+length <= iend); - /* We are finishing in the middle of a literals segment. - * Break after the copy. + 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); } - assert(ip+length <= iend); } else { - /* 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))) { goto _output_error; } + if ((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; + } } - memmove(op, ip, length); /* supports overlapping memory regions, which only matters for in-place decompression scenarios */ + LZ4_memmove(op, ip, length); /* supports overlapping memory regions, for in-place decompression scenarios */ ip += length; op += length; - /* Necessarily EOF when !partialDecoding. When partialDecoding - * it is EOF if we've either filled the output buffer or hit - * the input parsing restriction. + /* 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)) { + if (!partialDecoding || (cpy == oend) || (ip >= (iend-2))) { break; } } else { - LZ4_wildCopy8(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */ + LZ4_wildCopy8(op, ip, cpy); /* can overwrite up to 8 bytes beyond cpy */ ip += length; op = cpy; } @@ -1964,10 +2237,10 @@ LZ4_decompress_generic( _copy_match: 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 */ + size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0); + if (addl == rvl_error) { goto _output_error; } + length += addl; + if (unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ } length += MINMATCH; @@ -1977,6 +2250,7 @@ LZ4_decompress_generic( if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ /* match starting within external dictionary */ if ((dict==usingExtDict) && (match < lowPrefix)) { + assert(dictEnd != NULL); if (unlikely(op+length > oend-LASTLITERALS)) { if (partialDecoding) length = MIN(length, (size_t)(oend-op)); else goto _output_error; /* doesn't respect parsing restriction */ @@ -1984,20 +2258,20 @@ LZ4_decompress_generic( if (length <= (size_t)(lowPrefix-match)) { /* match fits entirely within external dictionary : just copy */ - memmove(op, dictEnd - (lowPrefix-match), length); + LZ4_memmove(op, dictEnd - (lowPrefix-match), length); op += length; } else { /* 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; @@ -2016,7 +2290,7 @@ LZ4_decompress_generic( if (matchEnd > op) { /* overlap copy */ while (op < copyEnd) { *op++ = *match++; } } else { - memcpy(op, match, mlen); + LZ4_memcpy(op, match, mlen); } op = copyEnd; if (op == oend) { break; } @@ -2030,10 +2304,10 @@ LZ4_decompress_generic( 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; @@ -2048,18 +2322,15 @@ LZ4_decompress_generic( } while (op < cpy) { *op++ = *match++; } } else { - memcpy(op, match, 8); + LZ4_memcpy(op, match, 8); if (length > 16) { LZ4_wildCopy8(op+8, match+8, cpy); } } op = cpy; /* wildcopy correction */ } /* end of decoding */ - if (endOnInput) { - return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ - } else { - return (int) (((const char*)ip)-src); /* Nb of input bytes read */ - } + DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst)); + return (int) (((char*)op)-dst); /* Nb of output bytes decoded */ /* Overflow error detected */ _output_error: @@ -2070,75 +2341,106 @@ 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, - endOnInputSize, decode_full_block, noDict, + decode_full_block, noDict, (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); return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, - endOnInputSize, partial_decode, + partial_decode, 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, - endOnOutputSize, decode_full_block, withPrefix64k, - (BYTE*)dest - 64 KB, NULL, 0); + DEBUGLOG(5, "LZ4_decompress_fast"); + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + 0, NULL, 0); } /*===== 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, - endOnInputSize, decode_full_block, withPrefix64k, + decode_full_block, withPrefix64k, + (BYTE*)dest - 64 KB, NULL, 0); +} + +LZ4_FORCE_O2 +static int LZ4_decompress_safe_partial_withPrefix64k(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity, + partial_decode, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 0); } /* Another obsolete API function, paired with the previous one. */ int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) { - /* LZ4_decompress_fast doesn't validate match offsets, - * and thus serves well with any prefixed dictionary. */ - return LZ4_decompress_fast(source, dest, originalSize); + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + 64 KB, NULL, 0); } -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) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, noDict, + decode_full_block, noDict, (BYTE*)dest-prefixSize, NULL, 0); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 +static int LZ4_decompress_safe_partial_withSmallPrefix(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, + size_t prefixSize) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity, + partial_decode, noDict, + (BYTE*)dest-prefixSize, NULL, 0); +} + +LZ4_FORCE_O2 int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const void* dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, usingExtDict, + decode_full_block, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); } -LZ4_FORCE_O2_GCC_PPC64LE +LZ4_FORCE_O2 +int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest, + int compressedSize, int targetOutputSize, int dstCapacity, + const void* dictStart, size_t dictSize) +{ + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity, + partial_decode, usingExtDict, + (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +LZ4_FORCE_O2 static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize, const void* dictStart, size_t dictSize) { - return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, decode_full_block, usingExtDict, - (BYTE*)dest, (const BYTE*)dictStart, dictSize); + return LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + 0, (const BYTE*)dictStart, dictSize); } /* The "double dictionary" mode, for use with e.g. ring buffers: the first part @@ -2150,26 +2452,17 @@ int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compresse size_t prefixSize, const void* dictStart, size_t dictSize) { return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, decode_full_block, usingExtDict, - (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); -} - -LZ4_FORCE_INLINE -int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalSize, - size_t prefixSize, const void* dictStart, size_t dictSize) -{ - return LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, decode_full_block, usingExtDict, + decode_full_block, usingExtDict, (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); } /*===== streaming decompression functions =====*/ +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) LZ4_streamDecode_t* LZ4_createStreamDecode(void) { - LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t)); - LZ4_STATIC_ASSERT(LZ4_STREAMDECODESIZE >= sizeof(LZ4_streamDecode_t_internal)); /* A compilation error here means LZ4_STREAMDECODESIZE is not large enough */ - return lz4s; + LZ4_STATIC_ASSERT(sizeof(LZ4_streamDecode_t) >= sizeof(LZ4_streamDecode_t_internal)); + return (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t)); } int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) @@ -2178,6 +2471,7 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) FREEMEM(LZ4_stream); return 0; } +#endif /*! LZ4_setStreamDecode() : * Use this function to instruct where to find the dictionary. @@ -2188,8 +2482,13 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) { LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; - lz4sd->prefixSize = (size_t) dictSize; - lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + lz4sd->prefixSize = (size_t)dictSize; + if (dictSize) { + assert(dictionary != NULL); + lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + } else { + lz4sd->prefixEnd = (const BYTE*) dictionary; + } lz4sd->externalDict = NULL; lz4sd->extDictSize = 0; return 1; @@ -2221,7 +2520,7 @@ 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; @@ -2261,29 +2560,35 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch return result; } -LZ4_FORCE_O2_GCC_PPC64LE -int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) +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; + LZ4_streamDecode_t_internal* const lz4sd = + (assert(LZ4_streamDecode!=NULL), &LZ4_streamDecode->internal_donotuse); int result; + + DEBUGLOG(5, "LZ4_decompress_fast_continue (toDecodeSize=%i)", originalSize); assert(originalSize >= 0); if (lz4sd->prefixSize == 0) { + DEBUGLOG(5, "first invocation : no prefix nor extDict"); assert(lz4sd->extDictSize == 0); result = LZ4_decompress_fast(source, dest, originalSize); if (result <= 0) return result; lz4sd->prefixSize = (size_t)originalSize; lz4sd->prefixEnd = (BYTE*)dest + originalSize; } else if (lz4sd->prefixEnd == (BYTE*)dest) { - if (lz4sd->prefixSize >= 64 KB - 1 || lz4sd->extDictSize == 0) - result = LZ4_decompress_fast(source, dest, originalSize); - else - result = LZ4_decompress_fast_doubleDict(source, dest, originalSize, - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + DEBUGLOG(5, "continue using existing prefix"); + result = LZ4_decompress_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + lz4sd->prefixSize, + lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; lz4sd->prefixSize += (size_t)originalSize; lz4sd->prefixEnd += originalSize; } else { + DEBUGLOG(5, "prefix becomes extDict"); lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; result = LZ4_decompress_fast_extDict(source, dest, originalSize, @@ -2319,10 +2624,27 @@ int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressed return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize); } +int LZ4_decompress_safe_partial_usingDict(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, const char* dictStart, int dictSize) +{ + if (dictSize==0) + return LZ4_decompress_safe_partial(source, dest, compressedSize, targetOutputSize, dstCapacity); + if (dictStart+dictSize == dest) { + if (dictSize >= 64 KB - 1) { + return LZ4_decompress_safe_partial_withPrefix64k(source, dest, compressedSize, targetOutputSize, dstCapacity); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_partial_withSmallPrefix(source, dest, compressedSize, targetOutputSize, dstCapacity, (size_t)dictSize); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_partial_forceExtDict(source, dest, compressedSize, targetOutputSize, dstCapacity, 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_unsafe_generic( + (const BYTE*)source, (BYTE*)dest, originalSize, + (size_t)dictSize, NULL, 0); assert(dictSize >= 0); return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize); } @@ -2374,7 +2696,7 @@ 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 sizeof(LZ4_stream_t); } int LZ4_resetStreamState(void* state, char* inputBuffer) { @@ -2383,11 +2705,13 @@ int LZ4_resetStreamState(void* state, char* inputBuffer) return 0; } +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) void* LZ4_create (char* inputBuffer) { (void)inputBuffer; return LZ4_createStream(); } +#endif char* LZ4_slideInputBuffer (void* state) { diff --git a/src/borg/algorithms/lz4/lib/lz4.h b/src/borg/algorithms/lz4/lib/lz4.h index 32108e232..491c6087c 100644 --- a/src/borg/algorithms/lz4/lib/lz4.h +++ b/src/borg/algorithms/lz4/lib/lz4.h @@ -1,7 +1,7 @@ /* * LZ4 - Fast LZ compression algorithm * Header File - * Copyright (C) 2011-present, Yann Collet. + * Copyright (C) 2011-2020, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -97,36 +97,77 @@ extern "C" { # define LZ4LIB_API LZ4LIB_VISIBILITY #endif +/*! LZ4_FREESTANDING : + * When this macro is set to 1, it enables "freestanding mode" that is + * suitable for typical freestanding environment which doesn't support + * standard C library. + * + * - LZ4_FREESTANDING is a compile-time switch. + * - It requires the following macros to be defined: + * LZ4_memcpy, LZ4_memmove, LZ4_memset. + * - It only enables LZ4/HC functions which don't use heap. + * All LZ4F_* functions are not supported. + * - See tests/freestanding.c to check its basic setup. + */ +#if defined(LZ4_FREESTANDING) && (LZ4_FREESTANDING == 1) +# define LZ4_HEAPMODE 0 +# define LZ4HC_HEAPMODE 0 +# define LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION 1 +# if !defined(LZ4_memcpy) +# error "LZ4_FREESTANDING requires macro 'LZ4_memcpy'." +# endif +# if !defined(LZ4_memset) +# error "LZ4_FREESTANDING requires macro 'LZ4_memset'." +# endif +# if !defined(LZ4_memmove) +# error "LZ4_FREESTANDING requires macro 'LZ4_memmove'." +# endif +#elif ! defined(LZ4_FREESTANDING) +# define LZ4_FREESTANDING 0 +#endif + + /*------ 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 2 /* for tweaks, bug-fixes, or development */ +#define LZ4_VERSION_RELEASE 4 /* for tweaks, bug-fixes, or development */ #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) #define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE #define LZ4_QUOTE(str) #str #define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) -#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) +#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) /* requires v1.7.3+ */ -LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version */ -LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version */ +LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version; requires v1.3.0+ */ +LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version; requires v1.7.5+ */ /*-************************************ * Tuning parameter **************************************/ +#define LZ4_MEMORY_USAGE_MIN 10 +#define LZ4_MEMORY_USAGE_DEFAULT 14 +#define LZ4_MEMORY_USAGE_MAX 20 + /*! * LZ4_MEMORY_USAGE : - * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) - * Increasing memory usage improves compression ratio. - * Reduced memory usage may improve speed, thanks to better cache locality. + * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; ) + * Increasing memory usage improves compression ratio, at the cost of speed. + * Reduced memory usage may improve speed at the cost of ratio, thanks to better cache locality. * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ #ifndef LZ4_MEMORY_USAGE -# define LZ4_MEMORY_USAGE 14 +# define LZ4_MEMORY_USAGE LZ4_MEMORY_USAGE_DEFAULT #endif +#if (LZ4_MEMORY_USAGE < LZ4_MEMORY_USAGE_MIN) +# error "LZ4_MEMORY_USAGE is too small !" +#endif + +#if (LZ4_MEMORY_USAGE > LZ4_MEMORY_USAGE_MAX) +# error "LZ4_MEMORY_USAGE is too large !" +#endif /*-************************************ * Simple Functions @@ -186,7 +227,8 @@ 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); @@ -212,7 +254,18 @@ 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); @@ -220,25 +273,35 @@ 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); @@ -248,8 +311,25 @@ LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcS ***********************************************/ typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ +/** + Note about RC_INVOKED + + - RC_INVOKED is predefined symbol of rc.exe (the resource compiler which is part of MSVC/Visual Studio). + https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros + + - Since rc.exe is a legacy compiler, it truncates long symbol (> 30 chars) + and reports warning "RC4011: identifier truncated". + + - To eliminate the warning, we surround long preprocessor symbol with + "#if !defined(RC_INVOKED) ... #endif" block that means + "skip this block when rc.exe is trying to read it". +*/ +#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */ +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); +#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */ +#endif /*! LZ4_resetStream_fast() : v1.9.0+ * Use this to prepare an LZ4_stream_t for a new chain of dependent blocks @@ -333,8 +413,12 @@ typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */ * creation / destruction of streaming decompression tracking context. * A tracking context can be re-used multiple times. */ +#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */ +#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); +#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */ +#endif /*! LZ4_setStreamDecode() : * An LZ4_streamDecode_t context can be allocated once and re-used multiple times. @@ -384,7 +468,10 @@ LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize); * save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression, * then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block. */ -LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity); +LZ4LIB_API int +LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, + const char* src, char* dst, + int srcSize, int dstCapacity); /*! LZ4_decompress_*_usingDict() : @@ -395,7 +482,16 @@ LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecod * Performance tip : Decompression speed can be substantially increased * when dst == dictStart + dictSize. */ -LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize); +LZ4LIB_API int +LZ4_decompress_safe_usingDict(const char* src, char* dst, + int srcSize, int dstCapacity, + const char* dictStart, int dictSize); + +LZ4LIB_API int +LZ4_decompress_safe_partial_usingDict(const char* src, char* dst, + int compressedSize, + int targetOutputSize, int maxOutputSize, + const char* dictStart, int dictSize); #endif /* LZ4_H_2983827168210 */ @@ -474,13 +570,15 @@ LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const c * stream (and source buffer) must remain in-place / accessible / unchanged * through the completion of the first compression call on the stream. */ -LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream); +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. + * for highly constrained 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. @@ -547,74 +645,52 @@ LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const #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 /*! LZ4_stream_t : - * information structure to track an LZ4 stream. - * 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. - */ -#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)) + * Never ever use below internal definitions directly ! + * These definitions are not API/ABI safe, and may change in future versions. + * If you need static allocation, declare or allocate an LZ4_stream_t object. +**/ + +typedef struct LZ4_stream_t_internal LZ4_stream_t_internal; +struct LZ4_stream_t_internal { + LZ4_u32 hashTable[LZ4_HASH_SIZE_U32]; + const LZ4_byte* dictionary; + const LZ4_stream_t_internal* dictCtx; + LZ4_u32 currentOffset; + LZ4_u32 tableType; + LZ4_u32 dictSize; + /* Implicit padding to ensure structure is aligned */ +}; + +#define LZ4_STREAM_MINSIZE ((1UL << LZ4_MEMORY_USAGE) + 32) /* static size, for inter-version compatibility */ union LZ4_stream_u { - unsigned long long table[LZ4_STREAMSIZE_U64]; + char minStateSize[LZ4_STREAM_MINSIZE]; 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. @@ -629,21 +705,25 @@ union LZ4_stream_u { * In which case, the function will @return NULL. * Note2: An LZ4_stream_t structure guarantees correct alignment and size. * Note3: Before v1.9.0, use LZ4_resetStream() instead - */ +**/ LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size); /*! LZ4_streamDecode_t : - * information structure to track an LZ4 stream during decompression. - * init this structure using LZ4_setStreamDecode() before first use. - * note : only use in association with static linking ! - * this definition is not API/ABI safe, - * and may change in a future version ! - */ -#define LZ4_STREAMDECODESIZE_U64 (4 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ ) -#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long)) + * Never ever use below internal definitions directly ! + * These definitions are not API/ABI safe, and may change in future versions. + * If you need static allocation, declare or allocate an LZ4_streamDecode_t object. +**/ +typedef struct { + const LZ4_byte* externalDict; + const LZ4_byte* prefixEnd; + size_t extDictSize; + size_t prefixSize; +} LZ4_streamDecode_t_internal; + +#define LZ4_STREAMDECODE_MINSIZE 32 union LZ4_streamDecode_u { - unsigned long long table[LZ4_STREAMDECODESIZE_U64]; + char minStateSize[LZ4_STREAMDECODE_MINSIZE]; LZ4_streamDecode_t_internal internal_donotuse; } ; /* previously typedef'd to LZ4_streamDecode_t */ @@ -667,22 +747,21 @@ 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 */ +/*! 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); @@ -690,11 +769,12 @@ LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_co 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 @@ -708,23 +788,22 @@ 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. @@ -739,7 +818,6 @@ 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")