diff options
Diffstat (limited to 'src')
| -rw-r--r-- | src/compat/compat-lz4.c | 2187 | ||||
| -rw-r--r-- | src/compat/compat-lz4.h | 737 | ||||
| -rw-r--r-- | src/openvpn/init.c | 3 | ||||
| -rw-r--r-- | src/openvpn/manage.c | 30 | ||||
| -rw-r--r-- | src/openvpn/networking_iproute2.c | 2 | ||||
| -rw-r--r-- | src/openvpn/options.c | 80 | ||||
| -rw-r--r-- | src/openvpn/route.c | 16 | ||||
| -rw-r--r-- | src/openvpn/socket.c | 58 | ||||
| -rw-r--r-- | src/openvpn/ssl.c | 8 | ||||
| -rw-r--r-- | src/openvpn/ssl_ncp.c | 18 | ||||
| -rw-r--r-- | src/openvpn/ssl_verify.c | 177 | ||||
| -rw-r--r-- | src/openvpn/tun.c | 2 |
12 files changed, 2311 insertions, 1007 deletions
diff --git a/src/compat/compat-lz4.c b/src/compat/compat-lz4.c index 723157d..26a3980 100644 --- a/src/compat/compat-lz4.c +++ b/src/compat/compat-lz4.c @@ -1,5 +1,5 @@ /* This file has been backported by dev-tools/lz4-rebaser.sh - * from upstream lz4 commit 7bb64ff2b69a9f8367de (v1.7.5) + * from upstream lz4 commit fdf2ef5809ca875c4545 (v1.9.2) */ #ifdef HAVE_CONFIG_H #include "config.h" @@ -10,7 +10,7 @@ #ifdef NEED_COMPAT_LZ4 /* LZ4 - Fast LZ compression algorithm - Copyright (C) 2011-2016, Yann Collet. + Copyright (C) 2011-present, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -42,17 +42,16 @@ - LZ4 source repository : https://github.com/lz4/lz4 */ - /*-************************************ * Tuning parameters **************************************/ /* - * HEAPMODE : + * LZ4_HEAPMODE : * Select how default compression functions will allocate memory for their hash table, * in memory stack (0:default, fastest), or in memory heap (1:requires malloc()). */ -#ifndef HEAPMODE -# define HEAPMODE 0 +#ifndef LZ4_HEAPMODE +# define LZ4_HEAPMODE 0 #endif /* @@ -73,16 +72,17 @@ * Method 1 : `__packed` statement. It depends on compiler extension (ie, not portable). * This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`. * Method 2 : direct access. This method is portable but violate C standard. - * It can generate buggy code on targets which generate assembly depending on alignment. + * It can generate buggy code on targets which assembly generation depends on alignment. * But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6) * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details. * Prefer these methods in priority order (0 > 1 > 2) */ -#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally, on command line for example */ -# if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) +#ifndef LZ4_FORCE_MEMORY_ACCESS /* can be defined externally */ +# if defined(__GNUC__) && \ + ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) \ + || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) ) # define LZ4_FORCE_MEMORY_ACCESS 2 -# elif defined(__INTEL_COMPILER) || \ - (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) )) +# elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__) # define LZ4_FORCE_MEMORY_ACCESS 1 # endif #endif @@ -91,14 +91,32 @@ * LZ4_FORCE_SW_BITCOUNT * 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 Windows CE does not support Hardware bit count */ +#if defined(_MSC_VER) && defined(_WIN32_WCE) /* Visual Studio for WinCE doesn't support Hardware bit count */ # define LZ4_FORCE_SW_BITCOUNT #endif + /*-************************************ * Dependency **************************************/ +/* + * LZ4_SRC_INCLUDED: + * Amalgamation flag, whether lz4.c is included + */ +#ifndef LZ4_SRC_INCLUDED +# define LZ4_SRC_INCLUDED 1 +#endif + +#ifndef LZ4_STATIC_LINKING_ONLY +#define LZ4_STATIC_LINKING_ONLY +#endif + +#ifndef LZ4_DISABLE_DEPRECATE_WARNINGS +#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */ +#endif + +#define LZ4_STATIC_LINKING_ONLY /* LZ4_DISTANCE_MAX */ #include "compat-lz4.h" /* see also "memory routines" below */ @@ -107,42 +125,130 @@ * Compiler Options **************************************/ #ifdef _MSC_VER /* Visual Studio */ -# define FORCE_INLINE static __forceinline # include <intrin.h> # pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */ # pragma warning(disable : 4293) /* disable: C4293: too large shift (32-bits) */ -#else -# if defined(__GNUC__) || defined(__clang__) -# define FORCE_INLINE static inline __attribute__((always_inline)) -# elif defined(__cplusplus) || (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) -# define FORCE_INLINE static inline -# else -# define FORCE_INLINE static -# endif #endif /* _MSC_VER */ +#ifndef LZ4_FORCE_INLINE +# ifdef _MSC_VER /* Visual Studio */ +# define LZ4_FORCE_INLINE static __forceinline +# else +# if defined (__cplusplus) || defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L /* C99 */ +# ifdef __GNUC__ +# define LZ4_FORCE_INLINE static inline __attribute__((always_inline)) +# else +# define LZ4_FORCE_INLINE static inline +# endif +# else +# define LZ4_FORCE_INLINE static +# endif /* __STDC_VERSION__ */ +# endif /* _MSC_VER */ +#endif /* LZ4_FORCE_INLINE */ + +/* LZ4_FORCE_O2_GCC_PPC64LE and LZ4_FORCE_O2_INLINE_GCC_PPC64LE + * 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%, + * because the execution does not go to the optimized loop + * for typical compressible data, and all of the preamble checks + * before going to the fall-back path become useless overhead. + * This optimization happens only with the -O3 flag, and -O2 generates + * a simple 8-byte copy loop. + * With gcc on ppc64le, all of the LZ4_decompress_* and LZ4_wildCopy8 + * functions are annotated with __attribute__((optimize("O2"))), + * and also LZ4_wildCopy8 is forcibly inlined, so that the O2 attribute + * 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 +#else +# define LZ4_FORCE_O2_GCC_PPC64LE +# define LZ4_FORCE_O2_INLINE_GCC_PPC64LE static +#endif + #if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) #endif +#ifndef likely #define likely(expr) expect((expr) != 0, 1) +#endif +#ifndef unlikely #define unlikely(expr) expect((expr) != 0, 0) +#endif /*-************************************ * Memory routines **************************************/ #include <stdlib.h> /* malloc, calloc, free */ -#define ALLOCATOR(n,s) calloc(n,s) -#define FREEMEM free +#define ALLOC(s) malloc(s) +#define ALLOC_AND_ZERO(s) calloc(1,s) +#define FREEMEM(p) free(p) #include <string.h> /* memset, memcpy */ -#define MEM_INIT memset +#define MEM_INIT(p,v,s) memset((p),(v),(s)) /*-************************************ -* Basic Types +* Common Constants +**************************************/ +#define MINMATCH 4 + +#define WILDCOPYLENGTH 8 +#define LASTLITERALS 5 /* see ../doc/lz4_Block_format.md#parsing-restrictions */ +#define MFLIMIT 12 /* see ../doc/lz4_Block_format.md#parsing-restrictions */ +#define MATCH_SAFEGUARD_DISTANCE ((2*WILDCOPYLENGTH) - MINMATCH) /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */ +#define FASTLOOP_SAFE_DISTANCE 64 +static const int LZ4_minLength = (MFLIMIT+1); + +#define KB *(1 <<10) +#define MB *(1 <<20) +#define GB *(1U<<30) + +#define LZ4_DISTANCE_ABSOLUTE_MAX 65535 +#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX) /* max supported by LZ4 format */ +# error "LZ4_DISTANCE_MAX is too big : must be <= 65535" +#endif + +#define ML_BITS 4 +#define ML_MASK ((1U<<ML_BITS)-1) +#define RUN_BITS (8-ML_BITS) +#define RUN_MASK ((1U<<RUN_BITS)-1) + + +/*-************************************ +* Error detection +**************************************/ +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1) +# include <assert.h> +#else +# ifndef assert +# define assert(condition) ((void)0) +# endif +#endif + +#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use after variable declarations */ + +#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2) +# include <stdio.h> +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 */ +#endif + + +/*-************************************ +* Types **************************************/ #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) # include <stdint.h> @@ -167,6 +273,13 @@ typedef size_t reg_t; /* 32-bits in x32 mode */ #endif +typedef enum { + notLimited = 0, + limitedOutput = 1, + fillOutput = 2 +} limitedOutput_directive; + + /*-************************************ * Reading and writing into memory **************************************/ @@ -200,7 +313,7 @@ static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArc static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; } static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; } -#else /* safe and portable access through memcpy() */ +#else /* safe and portable access using memcpy() */ static U16 LZ4_read16(const void* memPtr) { @@ -251,55 +364,113 @@ static void LZ4_writeLE16(void* memPtr, U16 value) } } -static void LZ4_copy8(void* dst, const void* src) -{ - memcpy(dst,src,8); -} - /* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */ -static void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) +LZ4_FORCE_O2_INLINE_GCC_PPC64LE +void LZ4_wildCopy8(void* dstPtr, const void* srcPtr, void* dstEnd) { BYTE* d = (BYTE*)dstPtr; const BYTE* s = (const BYTE*)srcPtr; BYTE* const e = (BYTE*)dstEnd; - do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e); + do { memcpy(d,s,8); d+=8; s+=8; } while (d<e); } +static const unsigned inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4}; +static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3}; -/*-************************************ -* Common Constants -**************************************/ -#define MINMATCH 4 -#define WILDCOPYLENGTH 8 -#define LASTLITERALS 5 -#define MFLIMIT (WILDCOPYLENGTH+MINMATCH) -static const int LZ4_minLength = (MFLIMIT+1); +#ifndef LZ4_FAST_DEC_LOOP +# if defined(__i386__) || defined(__x86_64__) +# define LZ4_FAST_DEC_LOOP 1 +# elif defined(__aarch64__) && !defined(__clang__) + /* On aarch64, we disable this optimization for clang because on certain + * mobile chipsets and clang, it reduces performance. For more information + * refer to https://github.com/lz4/lz4/pull/707. */ +# define LZ4_FAST_DEC_LOOP 1 +# else +# define LZ4_FAST_DEC_LOOP 0 +# endif +#endif -#define KB *(1 <<10) -#define MB *(1 <<20) -#define GB *(1U<<30) +#if LZ4_FAST_DEC_LOOP + +LZ4_FORCE_O2_INLINE_GCC_PPC64LE void +LZ4_memcpy_using_offset_base(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset) +{ + if (offset < 8) { + dstPtr[0] = srcPtr[0]; + dstPtr[1] = srcPtr[1]; + dstPtr[2] = srcPtr[2]; + dstPtr[3] = srcPtr[3]; + srcPtr += inc32table[offset]; + memcpy(dstPtr+4, srcPtr, 4); + srcPtr -= dec64table[offset]; + dstPtr += 8; + } else { + memcpy(dstPtr, srcPtr, 8); + dstPtr += 8; + srcPtr += 8; + } -#define MAXD_LOG 16 -#define MAX_DISTANCE ((1 << MAXD_LOG) - 1) + LZ4_wildCopy8(dstPtr, srcPtr, dstEnd); +} -#define ML_BITS 4 -#define ML_MASK ((1U<<ML_BITS)-1) -#define RUN_BITS (8-ML_BITS) -#define RUN_MASK ((1U<<RUN_BITS)-1) +/* customized variant of memcpy, which can overwrite up to 32 bytes beyond dstEnd + * this version copies two times 16 bytes (instead of one time 32 bytes) + * because it must be compatible with offsets >= 16. */ +LZ4_FORCE_O2_INLINE_GCC_PPC64LE void +LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; + + do { memcpy(d,s,16); memcpy(d+16,s+16,16); d+=32; s+=32; } while (d<e); +} +/* LZ4_memcpy_using_offset() presumes : + * - dstEnd >= dstPtr + MINMATCH + * - there is at least 8 bytes available to write after dstEnd */ +LZ4_FORCE_O2_INLINE_GCC_PPC64LE void +LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset) +{ + BYTE v[8]; -/*-************************************ -* Common Utils -**************************************/ -#define LZ4_STATIC_ASSERT(c) { enum { LZ4_static_assert = 1/(int)(!!(c)) }; } /* use only *after* variable declarations */ + assert(dstEnd >= dstPtr + MINMATCH); + LZ4_write32(dstPtr, 0); /* silence an msan warning when offset==0 */ + + switch(offset) { + case 1: + memset(v, *srcPtr, 8); + break; + case 2: + memcpy(v, srcPtr, 2); + memcpy(&v[2], srcPtr, 2); + memcpy(&v[4], &v[0], 4); + break; + case 4: + memcpy(v, srcPtr, 4); + memcpy(&v[4], srcPtr, 4); + break; + default: + LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset); + return; + } + + memcpy(dstPtr, v, 8); + dstPtr += 8; + while (dstPtr < dstEnd) { + memcpy(dstPtr, v, 8); + dstPtr += 8; + } +} +#endif /*-************************************ * Common functions **************************************/ -static unsigned LZ4_NbCommonBytes (register reg_t val) +static unsigned LZ4_NbCommonBytes (reg_t val) { if (LZ4_isLittleEndian()) { if (sizeof(val)==8) { @@ -308,9 +479,16 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) _BitScanForward64( &r, (U64)val ); return (int)(r>>3); # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctzll((U64)val) >> 3); + 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 }; + 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]; # endif } else /* 32 bits */ { @@ -319,23 +497,29 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) _BitScanForward( &r, (U32)val ); return (int)(r>>3); # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_ctz((U32)val) >> 3); + 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 }; + 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]; # endif } } else /* Big Endian CPU */ { - if (sizeof(val)==8) { + if (sizeof(val)==8) { /* 64-bits */ # if defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; _BitScanReverse64( &r, val ); return (unsigned)(r>>3); # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clzll((U64)val) >> 3); + return (unsigned)__builtin_clzll((U64)val) >> 3; # else + 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. */ unsigned r; - if (!(val>>32)) { r=4; } else { r=0; val>>=32; } + if (!(val>>by32)) { r=4; } else { r=0; val>>=by32; } if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } r += (!val); return r; @@ -346,7 +530,7 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) _BitScanReverse( &r, (unsigned long)val ); return (unsigned)(r>>3); # elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT) - return (__builtin_clz((U32)val) >> 3); + return (unsigned)__builtin_clz((U32)val) >> 3; # else unsigned r; if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } @@ -358,11 +542,20 @@ static unsigned LZ4_NbCommonBytes (register reg_t val) } #define STEPSIZE sizeof(reg_t) -static unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) +LZ4_FORCE_INLINE +unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) { const BYTE* const pStart = pIn; - while (likely(pIn<pInLimit-(STEPSIZE-1))) { + if (likely(pIn < pInLimit-(STEPSIZE-1))) { + reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); + if (!diff) { + pIn+=STEPSIZE; pMatch+=STEPSIZE; + } else { + return LZ4_NbCommonBytes(diff); + } } + + while (likely(pIn < pInLimit-(STEPSIZE-1))) { reg_t const diff = LZ4_read_ARCH(pMatch) ^ LZ4_read_ARCH(pIn); if (!diff) { pIn+=STEPSIZE; pMatch+=STEPSIZE; continue; } pIn += LZ4_NbCommonBytes(diff); @@ -387,15 +580,34 @@ static const U32 LZ4_skipTrigger = 6; /* Increase this value ==> compression ru /*-************************************ * Local Structures and types **************************************/ -typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive; -typedef enum { byPtr, byU32, byU16 } tableType_t; - -typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive; +typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t; + +/** + * This enum distinguishes several different modes of accessing previous + * content in the stream. + * + * - noDict : There is no preceding content. + * - withPrefix64k : Table entries up to ctx->dictSize before the current blob + * blob being compressed are valid and refer to the preceding + * content (of length ctx->dictSize), which is available + * contiguously preceding in memory the content currently + * being compressed. + * - 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 + * 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 + * content, and matches are found by looking in the ctx + * ->dictCtx->hashTable. + */ +typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive; typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; -typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive; -typedef enum { full = 0, partial = 1 } earlyEnd_directive; - /*-************************************ * Local Utils @@ -406,6 +618,23 @@ int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); } int LZ4_sizeofState() { return LZ4_STREAMSIZE; } +/*-************************************ +* Internal Definitions used in Tests +**************************************/ +#if defined (__cplusplus) +extern "C" { +#endif + +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize); + +int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, + int compressedSize, int maxOutputSize, + const void* dictStart, size_t dictSize); + +#if defined (__cplusplus) +} +#endif + /*-****************************** * Compression functions ********************************/ @@ -419,102 +648,225 @@ static U32 LZ4_hash4(U32 sequence, tableType_t const tableType) static U32 LZ4_hash5(U64 sequence, tableType_t const tableType) { - static const U64 prime5bytes = 889523592379ULL; - static const U64 prime8bytes = 11400714785074694791ULL; const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; - if (LZ4_isLittleEndian()) + if (LZ4_isLittleEndian()) { + const U64 prime5bytes = 889523592379ULL; return (U32)(((sequence << 24) * prime5bytes) >> (64 - hashLog)); - else + } else { + const U64 prime8bytes = 11400714785074694791ULL; return (U32)(((sequence >> 24) * prime8bytes) >> (64 - hashLog)); + } } -FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) +LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType) { if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType); return LZ4_hash4(LZ4_read32(p), tableType); } -static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase) +static void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType) { switch (tableType) { + default: /* fallthrough */ + case clearedTable: { /* illegal! */ assert(0); return; } + case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; } + } +} + +static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType) +{ + switch (tableType) + { + default: /* fallthrough */ + case clearedTable: /* fallthrough */ + case byPtr: { /* illegal! */ assert(0); return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; } + case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; } + } +} + +static void LZ4_putPositionOnHash(const BYTE* p, U32 h, + void* tableBase, tableType_t const tableType, + const BYTE* srcBase) +{ + switch (tableType) + { + case clearedTable: { /* illegal! */ assert(0); return; } case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; } case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; } case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; } } } -FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) { U32 const h = LZ4_hashPosition(p, tableType); LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); } -static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +/* LZ4_getIndexOnHash() : + * Index of match position registered in hash table. + * hash position must be calculated by using base+index, or dictBase+index. + * 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_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2); + if (tableType == byU32) { + const U32* const hashTable = (const U32*) tableBase; + assert(h < (1U << (LZ4_MEMORY_USAGE-2))); + return hashTable[h]; + } + if (tableType == byU16) { + const U16* const hashTable = (const U16*) tableBase; + assert(h < (1U << (LZ4_MEMORY_USAGE-1))); + return hashTable[h]; + } + assert(0); return 0; /* forbidden case */ +} + +static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase) { - if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } - if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } - { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ + if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; } + if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; } + { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ } -FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +LZ4_FORCE_INLINE const BYTE* +LZ4_getPosition(const BYTE* p, + const void* tableBase, tableType_t tableType, + const BYTE* srcBase) { U32 const h = LZ4_hashPosition(p, tableType); return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); } +LZ4_FORCE_INLINE void +LZ4_prepareTable(LZ4_stream_t_internal* const cctx, + const int inputSize, + const tableType_t tableType) { + /* If compression failed during the previous step, then the context + * is marked as dirty, therefore, it has to be fully reset. + */ + if (cctx->dirty) { + DEBUGLOG(5, "LZ4_prepareTable: Full reset for %p", cctx); + MEM_INIT(cctx, 0, sizeof(LZ4_stream_t_internal)); + return; + } + + /* 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) { + assert(inputSize >= 0); + if (cctx->tableType != tableType + || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU) + || ((tableType == byU32) && cctx->currentOffset > 1 GB) + || tableType == byPtr + || inputSize >= 4 KB) + { + DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx); + MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE); + cctx->currentOffset = 0; + cctx->tableType = clearedTable; + } 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. + */ + if (cctx->currentOffset != 0 && tableType == byU32) { + DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset"); + cctx->currentOffset += 64 KB; + } + + /* Finally, clear history */ + cctx->dictCtx = NULL; + cctx->dictionary = NULL; + cctx->dictSize = 0; +} /** LZ4_compress_generic() : inlined, to ensure branches are decided at compilation time */ -FORCE_INLINE int LZ4_compress_generic( +LZ4_FORCE_INLINE int LZ4_compress_generic( LZ4_stream_t_internal* const cctx, const char* const source, char* const dest, const int inputSize, + int *inputConsumed, /* only written when outputDirective == fillOutput */ const int maxOutputSize, - const limitedOutput_directive outputLimited, + const limitedOutput_directive outputDirective, const tableType_t tableType, - const dict_directive dict, + const dict_directive dictDirective, const dictIssue_directive dictIssue, - const U32 acceleration) + const int acceleration) { + int result; const BYTE* ip = (const BYTE*) source; - const BYTE* base; + + U32 const startIndex = cctx->currentOffset; + const BYTE* base = (const BYTE*) source - startIndex; const BYTE* lowLimit; - const BYTE* const lowRefLimit = ip - cctx->dictSize; - const BYTE* const dictionary = cctx->dictionary; - const BYTE* const dictEnd = dictionary + cctx->dictSize; - const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source; + + const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx; + const BYTE* const dictionary = + dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary; + const U32 dictSize = + dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize; + const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0; /* make indexes in dictCtx comparable with index in current context */ + + 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* anchor = (const BYTE*) source; const BYTE* const iend = ip + inputSize; - const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1; const BYTE* const matchlimit = iend - LASTLITERALS; + /* 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) ? + dictionary + dictSize - dictCtx->currentOffset : + dictionary + dictSize - startIndex; + BYTE* op = (BYTE*) dest; BYTE* const olimit = op + maxOutputSize; + U32 offset = 0; U32 forwardH; - /* Init conditions */ - if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported inputSize, too large (or negative) */ - switch(dict) - { - case noDict: - default: - base = (const BYTE*)source; - lowLimit = (const BYTE*)source; - break; - case withPrefix64k: - base = (const BYTE*)source - cctx->currentOffset; - lowLimit = (const BYTE*)source - cctx->dictSize; - break; - case usingExtDict: - base = (const BYTE*)source - cctx->currentOffset; - lowLimit = (const BYTE*)source; - break; + DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType); + /* 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); + + lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0); + + /* Update context state */ + if (dictDirective == usingDictCtx) { + /* Subsequent linked blocks can't use the dictionary. */ + /* Instead, they use the block we just compressed. */ + cctx->dictCtx = NULL; + cctx->dictSize = (U32)inputSize; + } else { + cctx->dictSize += (U32)inputSize; } - if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ - if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ + cctx->currentOffset += (U32)inputSize; + cctx->tableType = (U16)tableType; + + if (inputSize<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ /* First Byte */ LZ4_putPosition(ip, cctx->hashTable, tableType, base); @@ -522,50 +874,112 @@ FORCE_INLINE int LZ4_compress_generic( /* Main Loop */ for ( ; ; ) { - ptrdiff_t refDelta = 0; const BYTE* match; BYTE* token; + const BYTE* filledIp; /* Find a match */ - { const BYTE* forwardIp = ip; - unsigned step = 1; - unsigned searchMatchNb = acceleration << LZ4_skipTrigger; + if (tableType == byPtr) { + const BYTE* forwardIp = ip; + int step = 1; + int searchMatchNb = acceleration << LZ4_skipTrigger; do { U32 const h = forwardH; ip = forwardIp; forwardIp += step; step = (searchMatchNb++ >> LZ4_skipTrigger); - if (unlikely(forwardIp > mflimit)) goto _last_literals; + if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; + assert(ip < mflimitPlusOne); match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base); - if (dict==usingExtDict) { - if (match < (const BYTE*)source) { - refDelta = dictDelta; + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base); + + } while ( (match+LZ4_DISTANCE_MAX < ip) + || (LZ4_read32(match) != LZ4_read32(ip)) ); + + } else { /* byU32, byU16 */ + + const BYTE* forwardIp = ip; + int step = 1; + int searchMatchNb = acceleration << LZ4_skipTrigger; + do { + U32 const h = forwardH; + U32 const current = (U32)(forwardIp - base); + U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); + assert(matchIndex <= current); + assert(forwardIp - base < (ptrdiff_t)(2 GB - 1)); + ip = forwardIp; + forwardIp += step; + step = (searchMatchNb++ >> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals; + assert(ip < mflimitPlusOne); + + if (dictDirective == usingDictCtx) { + if (matchIndex < startIndex) { + /* there was no match, try the dictionary */ + assert(tableType == byU32); + matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); + match = dictBase + matchIndex; + matchIndex += dictDelta; /* make dictCtx index comparable with current context */ lowLimit = dictionary; } else { - refDelta = 0; + match = base + matchIndex; lowLimit = (const BYTE*)source; - } } + } + } else if (dictDirective==usingExtDict) { + if (matchIndex < startIndex) { + DEBUGLOG(7, "extDict candidate: matchIndex=%5u < startIndex=%5u", matchIndex, startIndex); + assert(startIndex - matchIndex >= MINMATCH); + match = dictBase + matchIndex; + lowLimit = dictionary; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; + } + } else { /* single continuous memory segment */ + match = base + matchIndex; + } forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base); + LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); + + DEBUGLOG(7, "candidate at pos=%u (offset=%u \n", matchIndex, current - matchIndex); + if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; } /* match outside of valid area */ + assert(matchIndex < current); + if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX)) + && (matchIndex+LZ4_DISTANCE_MAX < current)) { + continue; + } /* too far */ + assert((current - matchIndex) <= LZ4_DISTANCE_MAX); /* match now expected within distance */ + + if (LZ4_read32(match) == LZ4_read32(ip)) { + if (maybe_extMem) offset = current - matchIndex; + break; /* match found */ + } - } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0) - || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) - || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) ); + } while(1); } /* Catch up */ - while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } + filledIp = ip; + while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } /* Encode Literals */ { unsigned const litLength = (unsigned)(ip - anchor); token = op++; - if ((outputLimited) && /* Check output buffer overflow */ - (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) - return 0; + if ((outputDirective == limitedOutput) && /* Check output buffer overflow */ + (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) { + return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ + } + if ((outputDirective == fillOutput) && + (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) { + op--; + goto _last_literals; + } if (litLength >= RUN_MASK) { - int len = (int)litLength-RUN_MASK; + int len = (int)(litLength - RUN_MASK); *token = (RUN_MASK<<ML_BITS); for(; len >= 255 ; len-=255) *op++ = 255; *op++ = (BYTE)len; @@ -573,82 +987,183 @@ FORCE_INLINE int LZ4_compress_generic( else *token = (BYTE)(litLength<<ML_BITS); /* Copy Literals */ - LZ4_wildCopy(op, anchor, op+litLength); + LZ4_wildCopy8(op, anchor, op+litLength); op+=litLength; + DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", + (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source)); } _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 + * - 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 + */ + + if ((outputDirective == fillOutput) && + (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) { + /* the match was too close to the end, rewind and go to last literals */ + op = token; + goto _last_literals; + } + /* Encode Offset */ - LZ4_writeLE16(op, (U16)(ip-match)); op+=2; + if (maybe_extMem) { /* static test */ + DEBUGLOG(6, " with offset=%u (ext if > %i)", offset, (int)(ip - (const BYTE*)source)); + assert(offset <= LZ4_DISTANCE_MAX && offset > 0); + LZ4_writeLE16(op, (U16)offset); op+=2; + } else { + DEBUGLOG(6, " with offset=%u (same segment)", (U32)(ip - match)); + assert(ip-match <= LZ4_DISTANCE_MAX); + LZ4_writeLE16(op, (U16)(ip - match)); op+=2; + } /* Encode MatchLength */ { unsigned matchCode; - if ((dict==usingExtDict) && (lowLimit==dictionary)) { - const BYTE* limit; - match += refDelta; - limit = ip + (dictEnd-match); + if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx) + && (lowLimit==dictionary) /* match within extDict */ ) { + const BYTE* limit = ip + (dictEnd-match); + assert(dictEnd > match); if (limit > matchlimit) limit = matchlimit; matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); - ip += MINMATCH + matchCode; + ip += (size_t)matchCode + MINMATCH; if (ip==limit) { - unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit); + unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit); matchCode += more; ip += more; } + DEBUGLOG(6, " with matchLength=%u starting in extDict", matchCode+MINMATCH); } else { matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - ip += MINMATCH + matchCode; + ip += (size_t)matchCode + MINMATCH; + DEBUGLOG(6, " with matchLength=%u", matchCode+MINMATCH); } - if ( outputLimited && /* Check output buffer overflow */ - (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) - return 0; + if ((outputDirective) && /* Check output buffer overflow */ + (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) { + if (outputDirective == fillOutput) { + /* Match description too long : reduce it */ + U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255; + ip -= matchCode - newMatchCode; + assert(newMatchCode < matchCode); + matchCode = newMatchCode; + if (unlikely(ip <= filledIp)) { + /* We have already filled up to filledIp so if ip ends up less than filledIp + * we have positions in the hash table beyond the current position. This is + * a problem if we reuse the hash table. So we have to remove these positions + * from the hash table. + */ + const BYTE* ptr; + DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip)); + for (ptr = ip; ptr <= filledIp; ++ptr) { + U32 const h = LZ4_hashPosition(ptr, tableType); + LZ4_clearHash(h, cctx->hashTable, tableType); + } + } + } else { + assert(outputDirective == limitedOutput); + return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ + } + } if (matchCode >= ML_MASK) { *token += ML_MASK; matchCode -= ML_MASK; LZ4_write32(op, 0xFFFFFFFF); - while (matchCode >= 4*255) op+=4, LZ4_write32(op, 0xFFFFFFFF), matchCode -= 4*255; + while (matchCode >= 4*255) { + op+=4; + LZ4_write32(op, 0xFFFFFFFF); + matchCode -= 4*255; + } op += matchCode / 255; *op++ = (BYTE)(matchCode % 255); } else *token += (BYTE)(matchCode); } + /* Ensure we have enough space for the last literals. */ + assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit)); anchor = ip; /* Test end of chunk */ - if (ip > mflimit) break; + if (ip >= mflimitPlusOne) break; /* Fill table */ LZ4_putPosition(ip-2, cctx->hashTable, tableType, base); /* Test next position */ - match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); - if (dict==usingExtDict) { - if (match < (const BYTE*)source) { - refDelta = dictDelta; - lowLimit = dictionary; - } else { - refDelta = 0; - lowLimit = (const BYTE*)source; - } } - LZ4_putPosition(ip, cctx->hashTable, tableType, base); - if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1) - && (match+MAX_DISTANCE>=ip) - && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) ) - { token=op++; *token=0; goto _next_match; } + if (tableType == byPtr) { + + match = LZ4_getPosition(ip, cctx->hashTable, tableType, base); + LZ4_putPosition(ip, cctx->hashTable, tableType, base); + if ( (match+LZ4_DISTANCE_MAX >= ip) + && (LZ4_read32(match) == LZ4_read32(ip)) ) + { token=op++; *token=0; goto _next_match; } + + } else { /* byU32, byU16 */ + + U32 const h = LZ4_hashPosition(ip, tableType); + U32 const current = (U32)(ip-base); + U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType); + assert(matchIndex < current); + if (dictDirective == usingDictCtx) { + if (matchIndex < startIndex) { + /* there was no match, try the dictionary */ + matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32); + match = dictBase + matchIndex; + lowLimit = dictionary; /* required for match length counter */ + matchIndex += dictDelta; + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; /* required for match length counter */ + } + } else if (dictDirective==usingExtDict) { + if (matchIndex < startIndex) { + match = dictBase + matchIndex; + lowLimit = dictionary; /* required for match length counter */ + } else { + match = base + matchIndex; + lowLimit = (const BYTE*)source; /* required for match length counter */ + } + } else { /* single memory segment */ + match = base + matchIndex; + } + LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType); + assert(matchIndex < current); + if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1) + && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current)) + && (LZ4_read32(match) == LZ4_read32(ip)) ) { + token=op++; + *token=0; + if (maybe_extMem) offset = current - matchIndex; + DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i", + (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source)); + goto _next_match; + } + } /* Prepare next loop */ forwardH = LZ4_hashPosition(++ip, tableType); + } _last_literals: /* Encode Last Literals */ - { size_t const lastRun = (size_t)(iend - anchor); - if ( (outputLimited) && /* Check output buffer overflow */ - ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) ) - return 0; + { size_t lastRun = (size_t)(iend - anchor); + if ( (outputDirective) && /* Check output buffer overflow */ + (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) { + if (outputDirective == fillOutput) { + /* adapt lastRun to fill 'dst' */ + assert(olimit >= op); + lastRun = (size_t)(olimit-op) - 1; + lastRun -= (lastRun+240)/255; + } else { + assert(outputDirective == limitedOutput); + return 0; /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */ + } + } if (lastRun >= RUN_MASK) { size_t accumulator = lastRun - RUN_MASK; *op++ = RUN_MASK << ML_BITS; @@ -658,251 +1173,154 @@ _last_literals: *op++ = (BYTE)(lastRun<<ML_BITS); } memcpy(op, anchor, lastRun); + ip = anchor + lastRun; op += lastRun; } - /* End */ - return (int) (((char*)op)-dest); + if (outputDirective == fillOutput) { + *inputConsumed = (int) (((const char*)ip)-source); + } + DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, (int)(((char*)op) - dest)); + result = (int)(((char*)op) - dest); + assert(result > 0); + return result; } 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 (maxOutputSize >= LZ4_compressBound(inputSize)) { + if (inputSize < LZ4_64Klimit) { + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + if (inputSize < LZ4_64Klimit) { + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } +} + +/** + * LZ4_compress_fast_extState_fastReset() : + * A variant of LZ4_compress_fast_extState(). + * + * Using this variant avoids an expensive initialization step. It is only safe + * to call if the state buffer is known to be correctly initialized already + * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of + * "correctly initialized"). + */ +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; - LZ4_resetStream((LZ4_stream_t*)state); if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; - if (maxOutputSize >= LZ4_compressBound(inputSize)) { - if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); - else - return LZ4_compress_generic(ctx, source, dest, inputSize, 0, notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + if (dstCapacity >= LZ4_compressBound(srcSize)) { + if (srcSize < LZ4_64Klimit) { + const tableType_t tableType = byU16; + LZ4_prepareTable(ctx, srcSize, tableType); + if (ctx->currentOffset) { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration); + } else { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + LZ4_prepareTable(ctx, srcSize, tableType); + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration); + } } else { - if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); - else - return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration); + if (srcSize < LZ4_64Klimit) { + const tableType_t tableType = byU16; + LZ4_prepareTable(ctx, srcSize, tableType); + if (ctx->currentOffset) { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration); + } else { + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } + } else { + const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + LZ4_prepareTable(ctx, srcSize, tableType); + return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration); + } } } int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) { -#if (HEAPMODE) - void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + int result; +#if (LZ4_HEAPMODE) + LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + if (ctxPtr == NULL) return 0; #else LZ4_stream_t ctx; - void* const ctxPtr = &ctx; + LZ4_stream_t* const ctxPtr = &ctx; #endif + result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); - int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration); - -#if (HEAPMODE) +#if (LZ4_HEAPMODE) FREEMEM(ctxPtr); #endif return result; } -int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize) +int LZ4_compress_default(const char* src, char* dst, int srcSize, int maxOutputSize) { - return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, 1); + return LZ4_compress_fast(src, dst, srcSize, maxOutputSize, 1); } /* hidden debug function */ /* strangely enough, gcc generates faster code when this function is uncommented, even if unused */ -int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +int LZ4_compress_fast_force(const char* src, char* dst, int srcSize, int dstCapacity, int acceleration) { LZ4_stream_t ctx; - LZ4_resetStream(&ctx); - - if (inputSize < LZ4_64Klimit) - return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); - else - return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration); -} - - -/*-****************************** -* *_destSize() variant -********************************/ + LZ4_initStream(&ctx, sizeof(ctx)); -static int LZ4_compress_destSize_generic( - LZ4_stream_t_internal* const ctx, - const char* const src, - char* const dst, - int* const srcSizePtr, - const int targetDstSize, - const tableType_t tableType) -{ - const BYTE* ip = (const BYTE*) src; - const BYTE* base = (const BYTE*) src; - const BYTE* lowLimit = (const BYTE*) src; - const BYTE* anchor = ip; - const BYTE* const iend = ip + *srcSizePtr; - const BYTE* const mflimit = iend - MFLIMIT; - const BYTE* const matchlimit = iend - LASTLITERALS; - - BYTE* op = (BYTE*) dst; - BYTE* const oend = op + targetDstSize; - BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */; - BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */); - BYTE* const oMaxSeq = oMaxLit - 1 /* token */; - - U32 forwardH; - - - /* Init conditions */ - if (targetDstSize < 1) return 0; /* Impossible to store anything */ - if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ - if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ - if (*srcSizePtr<LZ4_minLength) goto _last_literals; /* Input too small, no compression (all literals) */ - - /* First Byte */ - *srcSizePtr = 0; - LZ4_putPosition(ip, ctx->hashTable, tableType, base); - ip++; forwardH = LZ4_hashPosition(ip, tableType); - - /* Main Loop */ - for ( ; ; ) { - const BYTE* match; - BYTE* token; - - /* Find a match */ - { const BYTE* forwardIp = ip; - unsigned step = 1; - unsigned searchMatchNb = 1 << LZ4_skipTrigger; - - do { - U32 h = forwardH; - ip = forwardIp; - forwardIp += step; - step = (searchMatchNb++ >> LZ4_skipTrigger); - - if (unlikely(forwardIp > mflimit)) goto _last_literals; - - match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base); - forwardH = LZ4_hashPosition(forwardIp, tableType); - LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base); - - } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) - || (LZ4_read32(match) != LZ4_read32(ip)) ); - } - - /* Catch up */ - while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } - - /* Encode Literal length */ - { unsigned litLength = (unsigned)(ip - anchor); - token = op++; - if (op + ((litLength+240)/255) + litLength > oMaxLit) { - /* Not enough space for a last match */ - op--; - goto _last_literals; - } - if (litLength>=RUN_MASK) { - unsigned len = litLength - RUN_MASK; - *token=(RUN_MASK<<ML_BITS); - for(; len >= 255 ; len-=255) *op++ = 255; - *op++ = (BYTE)len; - } - else *token = (BYTE)(litLength<<ML_BITS); - - /* Copy Literals */ - LZ4_wildCopy(op, anchor, op+litLength); - op += litLength; - } - -_next_match: - /* Encode Offset */ - LZ4_writeLE16(op, (U16)(ip-match)); op+=2; - - /* Encode MatchLength */ - { size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit); - - if (op + ((matchLength+240)/255) > oMaxMatch) { - /* Match description too long : reduce it */ - matchLength = (15-1) + (oMaxMatch-op) * 255; - } - ip += MINMATCH + matchLength; - - if (matchLength>=ML_MASK) { - *token += ML_MASK; - matchLength -= ML_MASK; - while (matchLength >= 255) { matchLength-=255; *op++ = 255; } - *op++ = (BYTE)matchLength; - } - else *token += (BYTE)(matchLength); - } - - anchor = ip; - - /* Test end of block */ - if (ip > mflimit) break; - if (op > oMaxSeq) break; - - /* Fill table */ - LZ4_putPosition(ip-2, ctx->hashTable, tableType, base); - - /* Test next position */ - match = LZ4_getPosition(ip, ctx->hashTable, tableType, base); - LZ4_putPosition(ip, ctx->hashTable, tableType, base); - if ( (match+MAX_DISTANCE>=ip) - && (LZ4_read32(match)==LZ4_read32(ip)) ) - { token=op++; *token=0; goto _next_match; } - - /* Prepare next loop */ - forwardH = LZ4_hashPosition(++ip, tableType); - } - -_last_literals: - /* Encode Last Literals */ - { size_t lastRunSize = (size_t)(iend - anchor); - if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) { - /* adapt lastRunSize to fill 'dst' */ - lastRunSize = (oend-op) - 1; - lastRunSize -= (lastRunSize+240)/255; - } - ip = anchor + lastRunSize; - - if (lastRunSize >= RUN_MASK) { - size_t accumulator = lastRunSize - RUN_MASK; - *op++ = RUN_MASK << ML_BITS; - for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; - *op++ = (BYTE) accumulator; - } else { - *op++ = (BYTE)(lastRunSize<<ML_BITS); - } - memcpy(op, anchor, lastRunSize); - op += lastRunSize; + 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); } - - /* End */ - *srcSizePtr = (int) (((const char*)ip)-src); - return (int) (((char*)op)-dst); } +/* 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. */ static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize) { - LZ4_resetStream(state); + void* const s = LZ4_initStream(state, sizeof (*state)); + assert(s != NULL); (void)s; if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) { /* compression success is guaranteed */ return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1); } else { - if (*srcSizePtr < LZ4_64Klimit) - return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16); - else - return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr); - } + if (*srcSizePtr < LZ4_64Klimit) { + return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1); + } else { + tableType_t const addrMode = ((sizeof(void*)==4) && ((uptrval)src > LZ4_DISTANCE_MAX)) ? byPtr : byU32; + return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, addrMode, noDict, noDictIssue, 1); + } } } int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize) { -#if (HEAPMODE) - LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ +#if (LZ4_HEAPMODE) + LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */ + if (ctx == NULL) return 0; #else LZ4_stream_t ctxBody; LZ4_stream_t* ctx = &ctxBody; @@ -910,7 +1328,7 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize); -#if (HEAPMODE) +#if (LZ4_HEAPMODE) FREEMEM(ctx); #endif return result; @@ -924,19 +1342,54 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe LZ4_stream_t* LZ4_createStream(void) { - LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64); + 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_resetStream(lz4s); + DEBUGLOG(4, "LZ4_createStream %p", lz4s); + if (lz4s == NULL) return NULL; + LZ4_initStream(lz4s, sizeof(*lz4s)); return lz4s; } +#ifndef _MSC_VER /* for some reason, Visual fails the aligment test on 32-bit x86 : + it reports an aligment of 8-bytes, + while actually aligning LZ4_stream_t on 4 bytes. */ +static size_t LZ4_stream_t_alignment(void) +{ + struct { char c; LZ4_stream_t t; } t_a; + return sizeof(t_a) - sizeof(t_a.t); +} +#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)); + return (LZ4_stream_t*)buffer; +} + +/* resetStream is now deprecated, + * prefer initStream() which is more general */ 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)); } +void LZ4_resetStream_fast(LZ4_stream_t* ctx) { + LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32); +} + int LZ4_freeStream (LZ4_stream_t* LZ4_stream) { + if (!LZ4_stream) return 0; /* support free on NULL */ + DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream); FREEMEM(LZ4_stream); return (0); } @@ -946,43 +1399,88 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream) int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize) { LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse; + const tableType_t tableType = byU32; const BYTE* p = (const BYTE*)dictionary; const BYTE* const dictEnd = p + dictSize; const BYTE* base; - if ((dict->initCheck) || (dict->currentOffset > 1 GB)) /* Uninitialized structure, or reuse overflow */ - LZ4_resetStream(LZ4_dict); + DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict); + + /* It's necessary to reset the context, + * and not just continue it with prepareTable() + * to avoid any risk of generating overflowing matchIndex + * when compressing using this dictionary */ + LZ4_resetStream(LZ4_dict); + + /* We always increment the offset by 64 KB, since, if the dict is longer, + * we truncate it to the last 64k, and if it's shorter, we still want to + * advance by a whole window length so we can provide the guarantee that + * there are only valid offsets in the window, which allows an optimization + * in LZ4_compress_fast_continue() where it uses noDictIssue even when the + * dictionary isn't a full 64k. */ + dict->currentOffset += 64 KB; if (dictSize < (int)HASH_UNIT) { - dict->dictionary = NULL; - dict->dictSize = 0; return 0; } if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB; - dict->currentOffset += 64 KB; - base = p - dict->currentOffset; + base = dictEnd - dict->currentOffset; dict->dictionary = p; dict->dictSize = (U32)(dictEnd - p); - dict->currentOffset += dict->dictSize; + dict->tableType = tableType; while (p <= dictEnd-HASH_UNIT) { - LZ4_putPosition(p, dict->hashTable, byU32, base); + LZ4_putPosition(p, dict->hashTable, tableType, base); p+=3; } - return dict->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 : + &(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 + * entry can take that indicate a miss. In that case, we need + * to bump the offset to something non-zero. + */ + if (workingStream->internal_donotuse.currentOffset == 0) { + workingStream->internal_donotuse.currentOffset = 64 KB; + } -static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) + /* Don't actually attach an empty dictionary. + */ + if (dictCtx->dictSize == 0) { + dictCtx = NULL; + } + } + workingStream->internal_donotuse.dictCtx = dictCtx; +} + + +static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize) { - if ((LZ4_dict->currentOffset > 0x80000000) || - ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) { /* address space overflow */ + assert(nextSize >= 0); + if (LZ4_dict->currentOffset + (unsigned)nextSize > 0x80000000) { /* potential ptrdiff_t overflow (32-bits mode) */ /* rescale hash table */ U32 const delta = LZ4_dict->currentOffset - 64 KB; const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; int i; + DEBUGLOG(4, "LZ4_renormDictT"); for (i=0; i<LZ4_HASH_SIZE_U32; i++) { if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0; else LZ4_dict->hashTable[i] -= delta; @@ -994,17 +1492,30 @@ static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) } -int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration) +int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, + const char* source, char* dest, + int inputSize, int maxOutputSize, + int acceleration) { + const tableType_t tableType = byU32; LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse; - const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize; - const BYTE* smallest = (const BYTE*) source; - if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */ - if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd; - LZ4_renormDictT(streamPtr, smallest); + DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize); + + if (streamPtr->dirty) { return 0; } /* Uninitialized structure detected */ + LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */ if (acceleration < 1) acceleration = ACCELERATION_DEFAULT; + /* invalidate tiny dictionaries */ + if ( (streamPtr->dictSize-1 < 4-1) /* intentional underflow */ + && (dictEnd != (const BYTE*)source) ) { + DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary); + streamPtr->dictSize = 0; + streamPtr->dictionary = (const BYTE*)source; + dictEnd = (const BYTE*)source; + } + /* Check overlapping input/dictionary space */ { const BYTE* sourceEnd = (const BYTE*) source + inputSize; if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) { @@ -1017,46 +1528,61 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, ch /* prefix mode : source data follows dictionary */ if (dictEnd == (const BYTE*)source) { - int result; if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); + return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration); else - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration); - streamPtr->dictSize += (U32)inputSize; - streamPtr->currentOffset += (U32)inputSize; - return result; + return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration); } /* external dictionary mode */ { int result; - if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); - else - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); + if (streamPtr->dictCtx) { + /* We depend here on the fact that dictCtx'es (produced by + * LZ4_loadDict) guarantee that their tables contain no references + * to offsets between dictCtx->currentOffset - 64 KB and + * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe + * to use noDictIssue even when the dict isn't a full 64 KB. + */ + if (inputSize > 4 KB) { + /* For compressing large blobs, it is faster to pay the setup + * 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)); + 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 { + 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 { + result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration); + } + } streamPtr->dictionary = (const BYTE*)source; streamPtr->dictSize = (U32)inputSize; - streamPtr->currentOffset += (U32)inputSize; return result; } } -/* Hidden debug function, to force external dictionary mode */ -int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize) +/* Hidden debug function, to force-test external dictionary mode */ +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize) { LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse; int result; - const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; - const BYTE* smallest = dictEnd; - if (smallest > (const BYTE*) source) smallest = (const BYTE*) source; - LZ4_renormDictT(streamPtr, smallest); + LZ4_renormDictT(streamPtr, srcSize); - result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) { + result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1); + } else { + result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + } streamPtr->dictionary = (const BYTE*)source; - streamPtr->dictSize = (U32)inputSize; - streamPtr->currentOffset += (U32)inputSize; + streamPtr->dictSize = (U32)srcSize; return result; } @@ -1074,8 +1600,8 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse; const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize; - if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ - if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize; + if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */ + if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; } memmove(safeBuffer, previousDictEnd - dictSize, dictSize); @@ -1087,218 +1613,587 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) -/*-***************************** -* Decompression functions -*******************************/ +/*-******************************* + * 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) ) + +/* Read the variable-length literal or match length. + * + * ip - pointer to use as input. + * lencheck - end ip. Return an error if ip advances >= 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) +{ + 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; + } + } while (s==255); + + return length; +} + /*! LZ4_decompress_generic() : - * This generic decompression function cover all use cases. - * It shall be instantiated several times, using different sets of directives - * Note that it is important this generic function is really inlined, + * This generic decompression function covers all use cases. + * It shall be instantiated several times, using different sets of directives. + * Note that it is important for performance that this function really get inlined, * in order to remove useless branches during compilation optimization. */ -FORCE_INLINE int LZ4_decompress_generic( - const char* const source, - char* const dest, - int inputSize, - int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */ - - int endOnInput, /* endOnOutputSize, endOnInputSize */ - int partialDecoding, /* full, partial */ - int targetOutputSize, /* only used if partialDecoding==partial */ - int dict, /* noDict, withPrefix64k, usingExtDict */ - const BYTE* const lowPrefix, /* == dest when no prefix */ +LZ4_FORCE_INLINE int +LZ4_decompress_generic( + const char* const src, + char* const dst, + 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 */ const BYTE* const dictStart, /* only if dict==usingExtDict */ const size_t dictSize /* note : = 0 if noDict */ ) { - /* Local Variables */ - const BYTE* ip = (const BYTE*) source; - const BYTE* const iend = ip + inputSize; + if (src == NULL) { return -1; } - BYTE* op = (BYTE*) dest; - BYTE* const oend = op + outputSize; - BYTE* cpy; - BYTE* oexit = op + targetOutputSize; - const BYTE* const lowLimit = lowPrefix - dictSize; + { const BYTE* ip = (const BYTE*) src; + const BYTE* const iend = ip + srcSize; - const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; - const unsigned dec32table[] = {0, 1, 2, 1, 4, 4, 4, 4}; - const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; + BYTE* op = (BYTE*) dst; + BYTE* const oend = op + outputSize; + BYTE* cpy; - const int safeDecode = (endOnInput==endOnInputSize); - const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); + const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize; + const int safeDecode = (endOnInput==endOnInputSize); + const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); - /* Special cases */ - if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ - if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ - if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); - /* Main Loop : decode sequences */ - while (1) { - size_t length; + /* 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* match; size_t offset; + unsigned token; + size_t length; - /* get literal length */ - unsigned const token = *ip++; - if ((length=(token>>ML_BITS)) == RUN_MASK) { - unsigned s; - do { - s = *ip++; - length += s; - } while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) ); - 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 */ + + DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i, dstSize:%i)", srcSize, outputSize); + + /* Special cases */ + assert(lowPrefix <= op); + if ((endOnInput) && (unlikely(outputSize==0))) { + /* Empty output buffer */ + if (partialDecoding) return 0; + return ((srcSize==1) && (*ip==0)) ? 0 : -1; + } + if ((!endOnInput) && (unlikely(outputSize==0))) { return (*ip==0 ? 1 : -1); } + if ((endOnInput) && unlikely(srcSize==0)) { return -1; } + + /* Currently the fast loop shows a regression on qualcomm arm chips. */ +#if LZ4_FAST_DEC_LOOP + if ((oend - op) < FASTLOOP_SAFE_DISTANCE) { + DEBUGLOG(6, "skip fast decode loop"); + goto safe_decode; } - /* copy literals */ - cpy = op+length; - if ( ((endOnInput) && ((cpy>(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) - || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) - { - if (partialDecoding) { - if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */ - if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ + /* Fast loop : decode sequences as long as output < iend-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); } + 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 */ + + /* 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 */ + } + ip += length; op = cpy; } else { - if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ - if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */ + 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); } + } + ip += length; op = cpy; } - memcpy(op, ip, length); - ip += length; - op += length; - break; /* Necessarily EOF, due to parsing restrictions */ - } - LZ4_wildCopy(op, ip, cpy); - ip += length; op = cpy; - - /* get offset */ - offset = LZ4_readLE16(ip); ip+=2; - match = op - offset; - if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside buffers */ - LZ4_write32(op, (U32)offset); /* costs ~1%; silence an msan warning when offset==0 */ - - /* get matchlength */ - length = token & ML_MASK; - if (length == ML_MASK) { - unsigned s; - do { - s = *ip++; - if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error; - length += s; - } while (s==255); - if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */ + + /* get offset */ + offset = LZ4_readLE16(ip); ip+=2; + match = op - offset; + assert(match <= op); + + /* 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 */ + length += MINMATCH; + if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { + goto safe_match_copy; + } + } else { + length += MINMATCH; + if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) { + goto safe_match_copy; + } + + /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if 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); + op += length; + continue; + } } } + + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */ + /* match starting within external dictionary */ + if ((dict==usingExtDict) && (match < lowPrefix)) { + if (unlikely(op+length > oend-LASTLITERALS)) { + if (partialDecoding) { + length = MIN(length, (size_t)(oend-op)); /* reach end of buffer */ + } 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); + 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); + 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); + op += restSize; + } } + continue; + } + + /* copy match within block */ + cpy = op + length; + + assert((op <= oend) && (oend-op >= 32)); + if (unlikely(offset<16)) { + LZ4_memcpy_using_offset(op, match, cpy, offset); + } else { + LZ4_wildCopy32(op, match, cpy); + } + + op = cpy; /* wildcopy correction */ } - length += MINMATCH; + safe_decode: +#endif + + /* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */ + while (1) { + 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 + * (in the fast mode, only 8 bytes can be safely copied this way). + * 2) Further if the match length is 4..18, copy 18 bytes in a similar + * manner; but we ensure that there's enough space in the output for + * 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) + /* strictly "less than" on input, to re-enter the loop with at least one byte */ + && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) { + /* Copy the literals */ + memcpy(op, ip, endOnInput ? 16 : 8); + op += length; ip += length; + + /* The second stage: prepare for match copying, decode full info. + * If it doesn't work out, the info won't be wasted. */ + length = token & ML_MASK; /* match length */ + offset = LZ4_readLE16(ip); ip += 2; + match = op - offset; + assert(match <= op); /* check overflow */ + + /* Do not deal with overlapping matches. */ + if ( (length != ML_MASK) + && (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); + op += length + MINMATCH; + /* Both stages worked, load the next token. */ + continue; + } + + /* The second stage didn't work out, but the info is ready. + * Propel it right to the point of match copying. */ + goto _copy_match; + } - /* check external dictionary */ - if ((dict==usingExtDict) && (match < lowPrefix)) { - if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ + /* 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 */ + } - if (length <= (size_t)(lowPrefix-match)) { - /* match can be copied as a single segment from external dictionary */ - memmove(op, dictEnd - (lowPrefix-match), length); + /* copy literals */ + cpy = op+length; +#if LZ4_FAST_DEC_LOOP + safe_literal_copy: +#endif + LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH); + if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) + { + /* We've either hit the input parsing restriction or the output parsing restriction. + * 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. + */ + 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. + */ + 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 (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; } + } + memmove(op, ip, length); /* supports overlapping memory regions, which only matters 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. + */ + if (!partialDecoding || (cpy == oend) || (ip == iend)) { + break; + } } else { - /* match encompass external dictionary and current block */ - size_t const copySize = (size_t)(lowPrefix-match); - size_t const restSize = length - copySize; - 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++; + LZ4_wildCopy8(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */ + ip += length; op = cpy; + } + + /* get offset */ + offset = LZ4_readLE16(ip); ip+=2; + match = op - offset; + + /* get matchlength */ + length = token & ML_MASK; + + _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 */ + } + length += MINMATCH; + +#if LZ4_FAST_DEC_LOOP + safe_match_copy: +#endif + if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */ + /* match starting within external dictionary */ + if ((dict==usingExtDict) && (match < lowPrefix)) { + if (unlikely(op+length > oend-LASTLITERALS)) { + if (partialDecoding) length = MIN(length, (size_t)(oend-op)); + else goto _output_error; /* doesn't respect parsing restriction */ + } + + if (length <= (size_t)(lowPrefix-match)) { + /* match fits entirely within external dictionary : just copy */ + memmove(op, dictEnd - (lowPrefix-match), length); + op += length; } else { - memcpy(op, lowPrefix, restSize); - op += restSize; - } } - continue; - } + /* 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); + 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); + op += restSize; + } } + continue; + } + assert(match >= lowPrefix); + + /* copy match within block */ + cpy = op + length; + + /* partialDecoding : may end anywhere within the block */ + assert(op<=oend); + if (partialDecoding && (cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + size_t const mlen = MIN(length, (size_t)(oend-op)); + const BYTE* const matchEnd = match + mlen; + BYTE* const copyEnd = op + mlen; + if (matchEnd > op) { /* overlap copy */ + while (op < copyEnd) { *op++ = *match++; } + } else { + memcpy(op, match, mlen); + } + op = copyEnd; + if (op == oend) { break; } + continue; + } - /* copy match within block */ - cpy = op + length; - if (unlikely(offset<8)) { - const int dec64 = dec64table[offset]; - op[0] = match[0]; - op[1] = match[1]; - op[2] = match[2]; - op[3] = match[3]; - match += dec32table[offset]; - memcpy(op+4, match, 4); - match -= dec64; - } else { LZ4_copy8(op, match); match+=8; } - op += 8; - - if (unlikely(cpy>oend-12)) { - BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1); - if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ - if (op < oCopyLimit) { - LZ4_wildCopy(op, match, oCopyLimit); - match += oCopyLimit - op; - op = oCopyLimit; + if (unlikely(offset<8)) { + LZ4_write32(op, 0); /* silence msan warning when offset==0 */ + op[0] = match[0]; + op[1] = match[1]; + op[2] = match[2]; + op[3] = match[3]; + match += inc32table[offset]; + memcpy(op+4, match, 4); + match -= dec64table[offset]; + } else { + memcpy(op, match, 8); + match += 8; } - while (op<cpy) *op++ = *match++; - } else { - LZ4_copy8(op, match); - if (length>16) LZ4_wildCopy(op+8, match+8, cpy); + op += 8; + + if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) { + BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1); + if (cpy > oend-LASTLITERALS) { goto _output_error; } /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ + if (op < oCopyLimit) { + LZ4_wildCopy8(op, match, oCopyLimit); + match += oCopyLimit - op; + op = oCopyLimit; + } + while (op < cpy) { *op++ = *match++; } + } else { + memcpy(op, match, 8); + if (length > 16) { LZ4_wildCopy8(op+8, match+8, cpy); } + } + op = cpy; /* wildcopy correction */ } - op=cpy; /* correction */ - } - /* end of decoding */ - if (endOnInput) - return (int) (((char*)op)-dest); /* Nb of output bytes decoded */ - else - return (int) (((const char*)ip)-source); /* Nb of input bytes read */ + /* 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 */ + } - /* Overflow error detected */ -_output_error: - return (int) (-(((const char*)ip)-source))-1; + /* Overflow error detected */ + _output_error: + return (int) (-(((const char*)ip)-src))-1; + } } +/*===== Instantiate the API decoding functions. =====*/ + +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0); + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, + endOnInputSize, decode_full_block, noDict, + (BYTE*)dest, NULL, 0); } -int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize) +LZ4_FORCE_O2_GCC_PPC64LE +int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize, int targetOutputSize, int dstCapacity) { - return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0); + dstCapacity = MIN(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, + endOnInputSize, partial_decode, + noDict, (BYTE*)dst, NULL, 0); } +LZ4_FORCE_O2_GCC_PPC64LE int LZ4_decompress_fast(const char* source, char* dest, int originalSize) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB); + return LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, decode_full_block, withPrefix64k, + (BYTE*)dest - 64 KB, NULL, 0); } +/*===== Instantiate a few more decoding cases, used more than once. =====*/ -/*===== streaming decompression functions =====*/ +LZ4_FORCE_O2_GCC_PPC64LE /* 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, + (BYTE*)dest - 64 KB, NULL, 0); +} -/* - * If you prefer dynamic allocation methods, - * LZ4_createStreamDecode() - * provides a pointer (void*) towards an initialized LZ4_streamDecode_t structure. +/* 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); +} + +LZ4_FORCE_O2_GCC_PPC64LE +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, + (BYTE*)dest-prefixSize, NULL, 0); +} + +LZ4_FORCE_O2_GCC_PPC64LE +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, + (BYTE*)dest, (const BYTE*)dictStart, dictSize); +} + +LZ4_FORCE_O2_GCC_PPC64LE +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); +} + +/* The "double dictionary" mode, for use with e.g. ring buffers: the first part + * of the dictionary is passed as prefix, and the second via dictStart + dictSize. + * These routines are used only once, in LZ4_decompress_*_continue(). */ +LZ4_FORCE_INLINE +int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize, + 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, + (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize); +} + +/*===== streaming decompression functions =====*/ + LZ4_streamDecode_t* LZ4_createStreamDecode(void) { - LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t)); + 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; } int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream) { + if (LZ4_stream == NULL) { return 0; } /* support free on NULL */ FREEMEM(LZ4_stream); return 0; } -/*! - * LZ4_setStreamDecode() : - * Use this function to instruct where to find the dictionary. - * This function is not necessary if previous data is still available where it was decoded. - * Loading a size of 0 is allowed (same effect as no dictionary). - * Return : 1 if OK, 0 if error +/*! LZ4_setStreamDecode() : + * Use this function to instruct where to find the dictionary. + * This function is not necessary if previous data is still available where it was decoded. + * Loading a size of 0 is allowed (same effect as no dictionary). + * @return : 1 if OK, 0 if error */ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) { @@ -1310,6 +2205,25 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti return 1; } +/*! LZ4_decoderRingBufferSize() : + * when setting a ring buffer for streaming decompression (optional scenario), + * provides the minimum size of this ring buffer + * to be compatible with any source respecting maxBlockSize condition. + * Note : in a ring buffer scenario, + * blocks are presumed decompressed next to each other. + * When not enough space remains for next block (remainingSize < maxBlockSize), + * decoding resumes from beginning of ring buffer. + * @return : minimum ring buffer size, + * or 0 if there is an error (invalid maxBlockSize). + */ +int LZ4_decoderRingBufferSize(int maxBlockSize) +{ + if (maxBlockSize < 0) return 0; + if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0; + if (maxBlockSize < 16) maxBlockSize = 16; + return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize); +} + /* *_continue() : These decoding functions allow decompression of multiple blocks in "streaming" mode. @@ -1317,52 +2231,75 @@ int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dicti 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 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; int result; - if (lz4sd->prefixEnd == (BYTE*)dest) { - result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, - usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (lz4sd->prefixSize == 0) { + /* The first call, no dictionary yet. */ + assert(lz4sd->extDictSize == 0); + result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); + if (result <= 0) return result; + lz4sd->prefixSize = (size_t)result; + lz4sd->prefixEnd = (BYTE*)dest + result; + } else if (lz4sd->prefixEnd == (BYTE*)dest) { + /* They're rolling the current segment. */ + if (lz4sd->prefixSize >= 64 KB - 1) + result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); + else if (lz4sd->extDictSize == 0) + result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, + lz4sd->prefixSize); + else + result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize, + lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; - lz4sd->prefixSize += result; + lz4sd->prefixSize += (size_t)result; lz4sd->prefixEnd += result; } else { + /* The buffer wraps around, or they're switching to another buffer. */ lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; - result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, - endOnInputSize, full, 0, - usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + result = LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, + lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; - lz4sd->prefixSize = result; + lz4sd->prefixSize = (size_t)result; lz4sd->prefixEnd = (BYTE*)dest + result; } 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_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse; int result; + assert(originalSize >= 0); - if (lz4sd->prefixEnd == (BYTE*)dest) { - result = LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, full, 0, - usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (lz4sd->prefixSize == 0) { + 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); if (result <= 0) return result; - lz4sd->prefixSize += originalSize; + lz4sd->prefixSize += (size_t)originalSize; lz4sd->prefixEnd += originalSize; } else { lz4sd->extDictSize = lz4sd->prefixSize; lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; - result = LZ4_decompress_generic(source, dest, 0, originalSize, - endOnOutputSize, full, 0, - usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + result = LZ4_decompress_fast_extDict(source, dest, originalSize, + lz4sd->externalDict, lz4sd->extDictSize); if (result <= 0) return result; - lz4sd->prefixSize = originalSize; + lz4sd->prefixSize = (size_t)originalSize; lz4sd->prefixEnd = (BYTE*)dest + originalSize; } @@ -1377,32 +2314,27 @@ Advanced decoding functions : the dictionary must be explicitly provided within parameters */ -FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize) +int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) { if (dictSize==0) - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0); + return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize); if (dictStart+dictSize == dest) { - if (dictSize >= (int)(64 KB - 1)) - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0); - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0); + if (dictSize >= 64 KB - 1) { + return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize); + } + assert(dictSize >= 0); + return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize); } - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); -} - -int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) -{ - return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize); + assert(dictSize >= 0); + return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize); } int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize) { - return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize); -} - -/* debug function */ -int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize); + if (dictSize==0 || dictStart+dictSize == dest) + return LZ4_decompress_fast(source, dest, originalSize); + assert(dictSize >= 0); + return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize); } @@ -1410,64 +2342,67 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compres * Obsolete Functions ***************************************************/ /* obsolete compression functions */ -int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); } -int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); } -int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); } -int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); } -int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); } -int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); } +int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) +{ + return LZ4_compress_default(source, dest, inputSize, maxOutputSize); +} +int LZ4_compress(const char* src, char* dest, int srcSize) +{ + return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize)); +} +int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) +{ + return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); +} +int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) +{ + return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); +} +int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int dstCapacity) +{ + return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1); +} +int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) +{ + return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); +} /* -These function names are deprecated and should no longer be used. +These decompression functions are deprecated and should no longer be used. They are only provided here for compatibility with older user programs. - LZ4_uncompress is totally equivalent to LZ4_decompress_fast - LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe */ -int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); } -int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); } - +int LZ4_uncompress (const char* source, char* dest, int outputSize) +{ + return LZ4_decompress_fast(source, dest, outputSize); +} +int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) +{ + return LZ4_decompress_safe(source, dest, isize, maxOutputSize); +} /* Obsolete Streaming functions */ int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; } -static void LZ4_init(LZ4_stream_t* lz4ds, BYTE* base) -{ - MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t)); - lz4ds->internal_donotuse.bufferStart = base; -} - int LZ4_resetStreamState(void* state, char* inputBuffer) { - if ((((uptrval)state) & 3) != 0) return 1; /* Error : pointer is not aligned on 4-bytes boundary */ - LZ4_init((LZ4_stream_t*)state, (BYTE*)inputBuffer); + (void)inputBuffer; + LZ4_resetStream((LZ4_stream_t*)state); return 0; } void* LZ4_create (char* inputBuffer) { - LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t)); - LZ4_init (lz4ds, (BYTE*)inputBuffer); - return lz4ds; + (void)inputBuffer; + return LZ4_createStream(); } -char* LZ4_slideInputBuffer (void* LZ4_Data) -{ - LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse; - int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB); - return (char*)(ctx->bufferStart + dictSize); -} - -/* Obsolete streaming decompression functions */ - -int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize) -{ - return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB); -} - -int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize) +char* LZ4_slideInputBuffer (void* state) { - return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB); + /* avoid const char * -> char * conversion warning */ + return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary; } #endif /* LZ4_COMMONDEFS_ONLY */ diff --git a/src/compat/compat-lz4.h b/src/compat/compat-lz4.h index 0aae19c..32108e2 100644 --- a/src/compat/compat-lz4.h +++ b/src/compat/compat-lz4.h @@ -1,7 +1,7 @@ /* * LZ4 - Fast LZ compression algorithm * Header File - * Copyright (C) 2011-2016, Yann Collet. + * Copyright (C) 2011-present, Yann Collet. BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php) @@ -32,13 +32,13 @@ - LZ4 homepage : http://www.lz4.org - LZ4 source repository : https://github.com/lz4/lz4 */ -#ifndef LZ4_H_2983827168210 -#define LZ4_H_2983827168210 - #if defined (__cplusplus) extern "C" { #endif +#ifndef LZ4_H_2983827168210 +#define LZ4_H_2983827168210 + /* --- Dependency --- */ #include <stddef.h> /* size_t */ @@ -46,24 +46,31 @@ extern "C" { /** Introduction - LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core, + LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core, scalable with multi-cores CPU. It features an extremely fast decoder, with speed in multiple GB/s per core, typically reaching RAM speed limits on multi-core systems. The LZ4 compression library provides in-memory compression and decompression functions. + It gives full buffer control to user. Compression can be done in: - a single step (described as Simple Functions) - a single step, reusing a context (described in Advanced Functions) - unbounded multiple steps (described as Streaming compression) - lz4.h provides block compression functions. It gives full buffer control to user. - Decompressing an lz4-compressed block also requires metadata (such as compressed size). - Each application is free to encode such metadata in whichever way it wants. + lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md). + Decompressing such a compressed block requires additional metadata. + Exact metadata depends on exact decompression function. + For the typical case of LZ4_decompress_safe(), + metadata includes block's compressed size, and maximum bound of decompressed size. + Each application is free to encode and pass such metadata in whichever way it wants. + + lz4.h only handle blocks, it can not generate Frames. - An additional format, called LZ4 frame specification (doc/lz4_Frame_format.md), - take care of encoding standard metadata alongside LZ4-compressed blocks. - If your application requires interoperability, it's recommended to use it. - A library is provided to take care of it, see lz4frame.h. + Blocks are different from Frames (doc/lz4_Frame_format.md). + Frames bundle both blocks and metadata in a specified manner. + Embedding metadata is required for compressed data to be self-contained and portable. + Frame format is delivered through a companion API, declared in lz4frame.h. + The `lz4` CLI can only manage frames. */ /*^*************************************************************** @@ -72,20 +79,28 @@ extern "C" { /* * LZ4_DLL_EXPORT : * Enable exporting of functions when building a Windows DLL +* LZ4LIB_VISIBILITY : +* Control library symbols visibility. */ +#ifndef LZ4LIB_VISIBILITY +# if defined(__GNUC__) && (__GNUC__ >= 4) +# define LZ4LIB_VISIBILITY __attribute__ ((visibility ("default"))) +# else +# define LZ4LIB_VISIBILITY +# endif +#endif #if defined(LZ4_DLL_EXPORT) && (LZ4_DLL_EXPORT==1) -# define LZ4LIB_API __declspec(dllexport) +# define LZ4LIB_API __declspec(dllexport) LZ4LIB_VISIBILITY #elif defined(LZ4_DLL_IMPORT) && (LZ4_DLL_IMPORT==1) -# define LZ4LIB_API __declspec(dllimport) /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ +# define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/ #else -# define LZ4LIB_API +# define LZ4LIB_API LZ4LIB_VISIBILITY #endif - -/*========== Version =========== */ +/*------ Version ------*/ #define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ -#define LZ4_VERSION_MINOR 7 /* for new (non-breaking) interface capabilities */ -#define LZ4_VERSION_RELEASE 5 /* for tweaks, bug-fixes, or development */ +#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_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) @@ -94,8 +109,8 @@ extern "C" { #define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str) #define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) -LZ4LIB_API int LZ4_versionNumber (void); -LZ4LIB_API const char* LZ4_versionString (void); +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 */ /*-************************************ @@ -104,41 +119,49 @@ LZ4LIB_API const char* LZ4_versionString (void); /*! * 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 can improve speed, due to cache effect + * Increasing memory usage improves compression ratio. + * Reduced memory usage may improve speed, thanks to better cache locality. * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache */ -#define LZ4_MEMORY_USAGE 14 +#ifndef LZ4_MEMORY_USAGE +# define LZ4_MEMORY_USAGE 14 +#endif /*-************************************ * Simple Functions **************************************/ /*! LZ4_compress_default() : - Compresses 'sourceSize' bytes from buffer 'source' - into already allocated 'dest' buffer of size 'maxDestSize'. - Compression is guaranteed to succeed if 'maxDestSize' >= LZ4_compressBound(sourceSize). - It also runs faster, so it's a recommended setting. - If the function cannot compress 'source' into a more limited 'dest' budget, - compression stops *immediately*, and the function result is zero. - As a consequence, 'dest' content is not valid. - This function never writes outside 'dest' buffer, nor read outside 'source' buffer. - sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE - maxDestSize : full or partial size of buffer 'dest' (which must be already allocated) - return : the number of bytes written into buffer 'dest' (necessarily <= maxOutputSize) - or 0 if compression fails */ -LZ4LIB_API int LZ4_compress_default(const char* source, char* dest, int sourceSize, int maxDestSize); + * Compresses 'srcSize' bytes from buffer 'src' + * into already allocated 'dst' buffer of size 'dstCapacity'. + * Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize). + * It also runs faster, so it's a recommended setting. + * If the function cannot compress 'src' into a more limited 'dst' budget, + * compression stops *immediately*, and the function result is zero. + * In which case, 'dst' content is undefined (invalid). + * srcSize : max supported value is LZ4_MAX_INPUT_SIZE. + * dstCapacity : size of buffer 'dst' (which must be already allocated) + * @return : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity) + * or 0 if compression fails + * Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer). + */ +LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity); /*! LZ4_decompress_safe() : - compressedSize : is the precise full size of the compressed block. - maxDecompressedSize : is the size of destination buffer, which must be already allocated. - return : the number of bytes decompressed into destination buffer (necessarily <= maxDecompressedSize) - If destination buffer is not large enough, decoding will stop and output an error code (<0). - If the source stream is detected malformed, the function will stop decoding and return a negative result. - This function is protected against buffer overflow exploits, including malicious data packets. - It never writes outside output buffer, nor reads outside input buffer. -*/ -LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compressedSize, int maxDecompressedSize); + * compressedSize : is the exact complete size of the compressed block. + * dstCapacity : is the size of destination buffer (which must be already allocated), presumed an upper bound of decompressed size. + * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity) + * If destination buffer is not large enough, decoding will stop and output an error code (negative value). + * If the source stream is detected malformed, the function will stop decoding and return a negative result. + * Note 1 : This function is protected against malicious data packets : + * it will never writes outside 'dst' buffer, nor read outside 'source' buffer, + * even if the compressed block is maliciously modified to order the decoder to do these actions. + * In such case, the decoder stops immediately, and considers the compressed block malformed. + * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them. + * The implementation is free to send / store / derive this information in whichever way is most beneficial. + * If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead. + */ +LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity); /*-************************************ @@ -147,184 +170,389 @@ LZ4LIB_API int LZ4_decompress_safe (const char* source, char* dest, int compress #define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ #define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) -/*! -LZ4_compressBound() : +/*! LZ4_compressBound() : Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible) This function is primarily useful for memory allocation purposes (destination buffer size). Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example). - Note that LZ4_compress_default() compress faster when dest buffer size is >= LZ4_compressBound(srcSize) + Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize) inputSize : max supported value is LZ4_MAX_INPUT_SIZE return : maximum output size in a "worst case" scenario - or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE) + or 0, if input size is incorrect (too large or negative) */ LZ4LIB_API int LZ4_compressBound(int inputSize); -/*! -LZ4_compress_fast() : - Same as LZ4_compress_default(), but allows to select an "acceleration" factor. +/*! LZ4_compress_fast() : + Same as LZ4_compress_default(), but allows selection of "acceleration" factor. 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 (see lz4.c), which is 1. + Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c). */ -LZ4LIB_API int LZ4_compress_fast (const char* source, char* dest, int sourceSize, int maxDestSize, int acceleration); +LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); -/*! -LZ4_compress_fast_extState() : - Same compression function, just using an externally allocated memory space to store compression state. - Use LZ4_sizeofState() to know how much memory must be allocated, - and allocate it on 8-bytes boundaries (using malloc() typically). - Then, provide it as 'void* state' to compression function. -*/ +/*! LZ4_compress_fast_extState() : + * Same as LZ4_compress_fast(), using an externally allocated memory space for its state. + * Use LZ4_sizeofState() to know how much memory must be allocated, + * and allocate it on 8-bytes boundaries (using `malloc()` typically). + * Then, provide this buffer as `void* state` to compression function. + */ LZ4LIB_API int LZ4_sizeofState(void); -LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* source, char* dest, int inputSize, int maxDestSize, int acceleration); - - -/*! -LZ4_compress_destSize() : - Reverse the logic, by compressing as much data as possible from 'source' buffer - into already allocated buffer 'dest' of size 'targetDestSize'. - This function either compresses the entire 'source' content into 'dest' if it's large enough, - or fill 'dest' buffer completely with as much data as possible from 'source'. - *sourceSizePtr : will be modified to indicate how many bytes where read from 'source' to fill 'dest'. - New value is necessarily <= old value. - return : Nb bytes written into 'dest' (necessarily <= targetDestSize) - or 0 if compression fails -*/ -LZ4LIB_API int LZ4_compress_destSize (const char* source, char* dest, int* sourceSizePtr, int targetDestSize); - - -/*! -LZ4_decompress_fast() : - originalSize : is the original and therefore uncompressed size - return : the number of bytes read from the source buffer (in other words, the compressed size) - If the source stream is detected malformed, the function will stop decoding and return a negative result. - Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes. - note : This function fully respect memory boundaries for properly formed compressed data. - It is a bit faster than LZ4_decompress_safe(). - However, it does not provide any protection against intentionally modified data stream (malicious input). - Use this function in trusted environment only (data to decode comes from a trusted source). -*/ -LZ4LIB_API int LZ4_decompress_fast (const char* source, char* dest, int originalSize); - -/*! -LZ4_decompress_safe_partial() : - This function decompress a compressed block of size 'compressedSize' at position 'source' - into destination buffer 'dest' of size 'maxDecompressedSize'. - The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached, - reducing decompression time. - return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize) - Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller. - Always control how many bytes were decoded. - If the source stream is detected malformed, the function will stop decoding and return a negative result. - This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets +LZ4LIB_API int LZ4_compress_fast_extState (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + + +/*! LZ4_compress_destSize() : + * Reverse the logic : compresses as much data as possible from 'src' buffer + * into already allocated buffer 'dst', of size >= 'targetDestSize'. + * This function either compresses the entire 'src' content into 'dst' if it's large enough, + * or fill 'dst' buffer completely with as much data as possible from 'src'. + * note: acceleration parameter is fixed to "default". + * + * *srcSizePtr : will be modified to indicate how many bytes where read from 'src' to fill 'dst'. + * New value is necessarily <= input value. + * @return : Nb bytes written into 'dst' (necessarily <= targetDestSize) + * or 0 if compression fails. */ -LZ4LIB_API int LZ4_decompress_safe_partial (const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); +LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize); + + +/*! LZ4_decompress_safe_partial() : + * 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. + * + * @return : the number of bytes decoded in `dst` (necessarily <= dstCapacity) + * If source stream is detected malformed, function returns a negative result. + * + * Note : @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, + * 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, + * 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. + */ +LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity); /*-********************************************* * Streaming Compression Functions ***********************************************/ -typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ +typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */ -/*! LZ4_createStream() and LZ4_freeStream() : - * LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure. - * LZ4_freeStream() releases its memory. - */ LZ4LIB_API LZ4_stream_t* LZ4_createStream(void); LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr); -/*! LZ4_resetStream() : - * An LZ4_stream_t structure can be allocated once and re-used multiple times. - * Use this function to init an allocated `LZ4_stream_t` structure and start a new compression. +/*! LZ4_resetStream_fast() : v1.9.0+ + * Use this to prepare an LZ4_stream_t for a new chain of dependent blocks + * (e.g., LZ4_compress_fast_continue()). + * + * An LZ4_stream_t must be initialized once before usage. + * This is automatically done when created by LZ4_createStream(). + * However, should the LZ4_stream_t be simply declared on stack (for example), + * it's necessary to initialize it first, using LZ4_initStream(). + * + * After init, start any new stream with LZ4_resetStream_fast(). + * A same LZ4_stream_t can be re-used multiple times consecutively + * and compress multiple streams, + * provided that it starts each new stream with LZ4_resetStream_fast(). + * + * LZ4_resetStream_fast() is much faster than LZ4_initStream(), + * but is not compatible with memory regions containing garbage data. + * + * Note: it's only useful to call LZ4_resetStream_fast() + * in the context of streaming compression. + * The *extState* functions perform their own resets. + * Invoking LZ4_resetStream_fast() before is redundant, and even counterproductive. */ -LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); +LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr); /*! LZ4_loadDict() : - * Use this function to load a static dictionary into LZ4_stream. - * Any previous data will be forgotten, only 'dictionary' will remain in memory. - * Loading a size of 0 is allowed. - * Return : dictionary size, in bytes (necessarily <= 64 KB) + * Use this function to reference a static dictionary into LZ4_stream_t. + * The dictionary must remain available during compression. + * LZ4_loadDict() triggers a reset, so any previous data will be forgotten. + * The same dictionary will have to be loaded on decompression side for successful decoding. + * Dictionary are useful for better compression of small data (KB range). + * While LZ4 accept any input as dictionary, + * results are generally better when using Zstandard's Dictionary Builder. + * Loading a size of 0 is allowed, and is the same as reset. + * @return : loaded dictionary size, in bytes (necessarily <= 64 KB) */ LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize); /*! LZ4_compress_fast_continue() : - * Compress buffer content 'src', using data from previously compressed blocks as dictionary to improve compression ratio. - * Important : Previous data blocks are assumed to still be present and unmodified ! - * 'dst' buffer must be already allocated. - * If maxDstSize >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. - * If not, and if compressed data cannot fit into 'dst' buffer size, compression stops, and function returns a zero. + * Compress 'src' content using data from previously compressed blocks, for better compression ratio. + * 'dst' buffer must be already allocated. + * If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster. + * + * @return : size of compressed block + * or 0 if there is an error (typically, cannot fit into 'dst'). + * + * Note 1 : Each invocation to LZ4_compress_fast_continue() generates a new block. + * Each block has precise boundaries. + * Each block must be decompressed separately, calling LZ4_decompress_*() with relevant metadata. + * It's not possible to append blocks together and expect a single invocation of LZ4_decompress_*() to decompress them together. + * + * Note 2 : The previous 64KB of source data is __assumed__ to remain present, unmodified, at same address in memory ! + * + * Note 3 : When input is structured as a double-buffer, each buffer can have any size, including < 64 KB. + * Make sure that buffers are separated, by at least one byte. + * This construction ensures that each block only depends on previous block. + * + * Note 4 : If input buffer is a ring-buffer, it can have any size, including < 64 KB. + * + * Note 5 : After an error, the stream status is undefined (invalid), it can only be reset or freed. */ -LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int maxDstSize, int acceleration); +LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); /*! LZ4_saveDict() : - * If previously compressed data block is not guaranteed to remain available at its memory location, + * If last 64KB data cannot be guaranteed to remain available at its current 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. + * This is schematically equivalent to a memcpy() followed by LZ4_loadDict(), + * but is much faster, because LZ4_saveDict() doesn't need to rebuild tables. + * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error. */ -LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize); +LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize); /*-********************************************** * Streaming Decompression Functions * Bufferless synchronous API ************************************************/ -typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* incomplete type (defined later) */ +typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */ -/* creation / destruction of streaming decompression tracking structure */ +/*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() : + * creation / destruction of streaming decompression tracking context. + * A tracking context can be re-used multiple times. + */ LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void); LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream); /*! LZ4_setStreamDecode() : - * Use this function to instruct where to find the dictionary. - * Setting a size of 0 is allowed (same effect as reset). - * @return : 1 if OK, 0 if error + * An LZ4_streamDecode_t context can be allocated once and re-used multiple times. + * Use this function to start decompression of a new stream of blocks. + * A dictionary can optionally be set. Use NULL or size 0 for a reset order. + * Dictionary is presumed stable : it must remain accessible and unmodified during next decompression. + * @return : 1 if OK, 0 if error */ LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize); -/*! -LZ4_decompress_*_continue() : - These decoding functions allow decompression of multiple blocks in "streaming" mode. - Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB) - In the case of a ring buffers, decoding buffer must be either : - - Exactly same size as encoding buffer, with same update rule (block boundaries at same positions) - In which case, the decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB). - - Larger than encoding buffer, by a minimum of maxBlockSize more bytes. - maxBlockSize is implementation dependent. It's the maximum size you intend to compress into a single block. - In which case, encoding and decoding buffers do not need to be synchronized, - and encoding ring buffer can have any size, including small ones ( < 64 KB). - - _At least_ 64 KB + 8 bytes + maxBlockSize. - In which case, encoding and decoding buffers do not need to be synchronized, - and encoding ring buffer can have any size, including larger than decoding buffer. - Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer, - and indicate where it is saved using LZ4_setStreamDecode() +/*! LZ4_decoderRingBufferSize() : v1.8.2+ + * Note : in a ring buffer scenario (optional), + * blocks are presumed decompressed next to each other + * up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize), + * at which stage it resumes from beginning of ring buffer. + * When setting such a ring buffer for streaming decompression, + * provides the minimum size of this ring buffer + * to be compatible with any source respecting maxBlockSize condition. + * @return : minimum ring buffer size, + * or 0 if there is an error (invalid maxBlockSize). + */ +LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize); +#define LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize) (65536 + 14 + (maxBlockSize)) /* for static allocation; maxBlockSize presumed valid */ + +/*! LZ4_decompress_*_continue() : + * These decoding functions allow decompression of consecutive blocks in "streaming" mode. + * A block is an unsplittable entity, it must be presented entirely to a decompression function. + * Decompression functions only accepts one block at a time. + * The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded. + * If less than 64KB of data has been decoded, all the data must be present. + * + * Special : if decompression side sets a ring buffer, it must respect one of the following conditions : + * - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize). + * maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes. + * In which case, encoding and decoding buffers do not need to be synchronized. + * Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize. + * - Synchronized mode : + * Decompression buffer size is _exactly_ the same as compression buffer size, + * and follows exactly same update rule (block boundaries at same positions), + * and decoding function is provided with exact decompressed size of each block (exception for last block of the stream), + * _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB). + * - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes. + * In which case, encoding and decoding buffers do not need to be synchronized, + * and encoding ring buffer can have any size, including small ones ( < 64 KB). + * + * Whenever these conditions are not possible, + * 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* source, char* dest, int compressedSize, int maxDecompressedSize); -LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize); +LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity); /*! LZ4_decompress_*_usingDict() : * These decoding functions work the same as * a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue() * They are stand-alone, and don't need an LZ4_streamDecode_t structure. + * Dictionary is presumed stable : it must remain accessible and unmodified during decompression. + * Performance tip : Decompression speed can be substantially increased + * when dst == dictStart + dictSize. */ -LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* source, char* dest, int compressedSize, int maxDecompressedSize, const char* dictStart, int dictSize); -LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, int originalSize, const char* dictStart, int dictSize); +LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize); +#endif /* LZ4_H_2983827168210 */ -/*^********************************************** + +/*^************************************* * !!!!!! STATIC LINKING ONLY !!!!!! - ***********************************************/ -/*-************************************ - * Private definitions - ************************************** - * Do not use these definitions. - * They are exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`. - * Using these definitions will expose code to API and/or ABI break in future versions of the library. - **************************************/ + ***************************************/ + +/*-**************************************************************************** + * Experimental section + * + * Symbols declared in this section must be considered unstable. Their + * signatures or semantics may change, or they may be removed altogether in the + * future. They are therefore only safe to depend on when the caller is + * statically linked against the library. + * + * To protect against unsafe usage, not only are the declarations guarded, + * the definitions are hidden by default + * when building LZ4 as a shared/dynamic library. + * + * In order to access these declarations, + * define LZ4_STATIC_LINKING_ONLY in your application + * before including LZ4's headers. + * + * In order to make their implementations accessible dynamically, you must + * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library. + ******************************************************************************/ + +#ifdef LZ4_STATIC_LINKING_ONLY + +#ifndef LZ4_STATIC_3504398509 +#define LZ4_STATIC_3504398509 + +#ifdef LZ4_PUBLISH_STATIC_FUNCTIONS +#define LZ4LIB_STATIC_API LZ4LIB_API +#else +#define LZ4LIB_STATIC_API +#endif + + +/*! LZ4_compress_fast_extState_fastReset() : + * A variant of LZ4_compress_fast_extState(). + * + * Using this variant avoids an expensive initialization step. + * It is only safe to call if the state buffer is known to be correctly initialized already + * (see above comment on LZ4_resetStream_fast() for a definition of "correctly initialized"). + * From a high level, the difference is that + * this function initializes the provided state with a call to something like LZ4_resetStream_fast() + * while LZ4_compress_fast_extState() starts with a call to LZ4_resetStream(). + */ +LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration); + +/*! LZ4_attach_dictionary() : + * This is an experimental API that allows + * efficient use of a static dictionary many times. + * + * Rather than re-loading the dictionary buffer into a working context before + * each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a + * working LZ4_stream_t, this function introduces a no-copy setup mechanism, + * in which the working stream references the dictionary stream in-place. + * + * Several assumptions are made about the state of the dictionary stream. + * Currently, only streams which have been prepared by LZ4_loadDict() should + * be expected to work. + * + * Alternatively, the provided dictionaryStream may be NULL, + * in which case any existing dictionary stream is unset. + * + * If a dictionary is provided, it replaces any pre-existing stream history. + * The dictionary contents are the only history that can be referenced and + * logically immediately precede the data compressed in the first subsequent + * compression call. + * + * The dictionary will only remain attached to the working stream through the + * first compression call, at the end of which it is cleared. The dictionary + * 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); + + +/*! In-place compression and decompression + * + * It's possible to have input and output sharing the same buffer, + * for highly contrained memory environments. + * In both cases, it requires input to lay at the end of the buffer, + * and decompression to start at beginning of the buffer. + * Buffer size must feature some margin, hence be larger than final size. + * + * |<------------------------buffer--------------------------------->| + * |<-----------compressed data--------->| + * |<-----------decompressed size------------------>| + * |<----margin---->| + * + * This technique is more useful for decompression, + * since decompressed size is typically larger, + * and margin is short. + * + * In-place decompression will work inside any buffer + * which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize). + * This presumes that decompressedSize > compressedSize. + * Otherwise, it means compression actually expanded data, + * and it would be more efficient to store such data with a flag indicating it's not compressed. + * This can happen when data is not compressible (already compressed, or encrypted). + * + * For in-place compression, margin is larger, as it must be able to cope with both + * history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX, + * and data expansion, which can happen when input is not compressible. + * As a consequence, buffer size requirements are much higher, + * and memory savings offered by in-place compression are more limited. + * + * There are ways to limit this cost for compression : + * - Reduce history size, by modifying LZ4_DISTANCE_MAX. + * Note that it is a compile-time constant, so all compressions will apply this limit. + * Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX, + * so it's a reasonable trick when inputs are known to be small. + * - Require the compressor to deliver a "maximum compressed size". + * This is the `dstCapacity` parameter in `LZ4_compress*()`. + * When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail, + * in which case, the return code will be 0 (zero). + * The caller must be ready for these cases to happen, + * and typically design a backup scheme to send data uncompressed. + * The combination of both techniques can significantly reduce + * the amount of margin required for in-place compression. + * + * In-place compression can work in any buffer + * which size is >= (maxCompressedSize) + * with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success. + * LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX, + * so it's possible to reduce memory requirements by playing with them. + */ + +#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize) (((compressedSize) >> 8) + 32) +#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize) ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize)) /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */ + +#ifndef LZ4_DISTANCE_MAX /* history window size; can be user-defined at compile time */ +# define LZ4_DISTANCE_MAX 65535 /* set to maximum value by default */ +#endif + +#define LZ4_COMPRESS_INPLACE_MARGIN (LZ4_DISTANCE_MAX + 32) /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */ +#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize) ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN) /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */ + +#endif /* LZ4_STATIC_3504398509 */ +#endif /* LZ4_STATIC_LINKING_ONLY */ + + + +#ifndef LZ4_H_98237428734687 +#define LZ4_H_98237428734687 + +/*-************************************************************ + * PRIVATE DEFINITIONS + ************************************************************** + * 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. + **************************************************************/ #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 */ @@ -332,14 +560,16 @@ LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* source, char* dest, in #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */) #include <stdint.h> -typedef struct { +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; - uint32_t initCheck; + uint16_t dirty; + uint16_t tableType; const uint8_t* dictionary; - uint8_t* bufferStart; /* obsolete, used for slideInputBuffer */ + const LZ4_stream_t_internal* dictCtx; uint32_t dictSize; -} LZ4_stream_t_internal; +}; typedef struct { const uint8_t* externalDict; @@ -350,49 +580,67 @@ typedef struct { #else -typedef struct { +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 int initCheck; + unsigned short dirty; + unsigned short tableType; const unsigned char* dictionary; - unsigned char* bufferStart; /* obsolete, used for slideInputBuffer */ + const LZ4_stream_t_internal* dictCtx; unsigned int dictSize; -} LZ4_stream_t_internal; +}; typedef struct { const unsigned char* externalDict; - size_t extDictSize; const unsigned char* prefixEnd; + size_t extDictSize; size_t prefixSize; } LZ4_streamDecode_t_internal; #endif -/*! - * LZ4_stream_t : - * information structure to track an LZ4 stream. - * init this structure 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 ! +/*! 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) +#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)) union LZ4_stream_u { unsigned long long table[LZ4_STREAMSIZE_U64]; LZ4_stream_t_internal internal_donotuse; } ; /* previously typedef'd to LZ4_stream_t */ +/*! LZ4_initStream() : v1.9.0+ + * An LZ4_stream_t structure must be initialized at least once. + * This is automatically done when invoking LZ4_createStream(), + * but it's not when the structure is simply declared on stack (for example). + * + * Use LZ4_initStream() to properly initialize a newly declared LZ4_stream_t. + * It can also initialize any arbitrary buffer of sufficient size, + * and will @return a pointer of proper type upon initialization. + * + * Note : initialization fails if size and alignment conditions are not respected. + * 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 (or memset()) 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 ! + +/*! 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 +#define LZ4_STREAMDECODESIZE_U64 (4 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ ) #define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long)) union LZ4_streamDecode_u { unsigned long long table[LZ4_STREAMDECODESIZE_U64]; @@ -400,15 +648,22 @@ union LZ4_streamDecode_u { } ; /* previously typedef'd to LZ4_streamDecode_t */ -/*=************************************ + +/*-************************************ * Obsolete Functions **************************************/ -/* Deprecation warnings */ -/* Should these warnings be a problem, - it is generally possible to disable them, - typically with -Wno-deprecated-declarations for gcc - or _CRT_SECURE_NO_WARNINGS in Visual. - Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */ + +/*! Deprecation warnings + * + * Deprecated functions make the compiler generate a warning when invoked. + * This is meant to invite users to update their source code. + * Should deprecation warnings be a problem, it is generally possible to disable them, + * typically with -Wno-deprecated-declarations for gcc + * or _CRT_SECURE_NO_WARNINGS in Visual. + * + * Another method is to define LZ4_DISABLE_DEPRECATE_WARNINGS + * before including the header file. + */ #ifdef LZ4_DISABLE_DEPRECATE_WARNINGS # define LZ4_DEPRECATED(message) /* disable deprecation warnings */ #else @@ -428,36 +683,82 @@ union LZ4_streamDecode_u { #endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */ /* Obsolete compression functions */ -LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress (const char* source, char* dest, int sourceSize); -LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); -LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress (const char* src, char* dest, int srcSize); +LZ4_DEPRECATED("use LZ4_compress_default() instead") LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState (void* state, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize); +LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize); /* Obsolete decompression functions */ -/* These function names are completely deprecated and must no longer be used. - They are only provided in lz4.c for compatibility with older programs. - - LZ4_uncompress is the same as LZ4_decompress_fast - - LZ4_uncompress_unknownOutputSize is the same as LZ4_decompress_safe - These function prototypes are now disabled; uncomment them only if you really need them. - It is highly recommended to stop using these prototypes and migrate to maintained ones */ -/* int LZ4_uncompress (const char* source, char* dest, int outputSize); */ -/* int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize); */ - -/* Obsolete streaming functions; use new streaming interface whenever possible */ -LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer); -LZ4_DEPRECATED("use LZ4_createStream() instead") int LZ4_sizeofStreamState(void); -LZ4_DEPRECATED("use LZ4_resetStream() instead") int LZ4_resetStreamState(void* state, char* inputBuffer); -LZ4_DEPRECATED("use LZ4_saveDict() instead") char* LZ4_slideInputBuffer (void* state); +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! + * + * 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 + * possible: using them will still produce a correct output. However, they don't + * actually retain any history between compression calls. The compression ratio + * achieved will therefore be no better than compressing each chunk + * independently. + */ +LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer); +LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int LZ4_sizeofStreamState(void); +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 */ -LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize); -LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize); +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!** + * These functions used to be faster than LZ4_decompress_safe(), + * but it has changed, and they are now slower than LZ4_decompress_safe(). + * 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. + * 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. + * + * Parameters: + * originalSize : is the uncompressed size to regenerate. + * `dst` must be already allocated, its size must be >= 'originalSize' bytes. + * @return : number of bytes read from source buffer (== compressed size). + * The function expects to finish at block's end exactly. + * If the source stream is detected malformed, the function stops decoding and returns a negative result. + * note : LZ4_decompress_fast*() requires originalSize. Thanks to this information, it never writes past the output buffer. + * However, since it doesn't know its 'src' size, it may read an unknown amount of input, past input buffer bounds. + * Also, since match offsets are not validated, match reads from 'src' may underflow too. + * These issues never happen if input (compressed) data is correct. + * 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") +LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize); +LZ4_DEPRECATED("This function is deprecated and unsafe. Consider using LZ4_decompress_safe_usingDict() instead") +LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize); + +/*! LZ4_resetStream() : + * An LZ4_stream_t structure must be initialized at least once. + * This is done with LZ4_initStream(), or LZ4_resetStream(). + * Consider switching to LZ4_initStream(), + * invoking LZ4_resetStream() will trigger deprecation warnings in the future. + */ +LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr); + + +#endif /* LZ4_H_98237428734687 */ #if defined (__cplusplus) } #endif - -#endif /* LZ4_H_2983827168210 */ diff --git a/src/openvpn/init.c b/src/openvpn/init.c index d1ad5c8..31ecadc 100644 --- a/src/openvpn/init.c +++ b/src/openvpn/init.c @@ -3646,7 +3646,8 @@ do_close_link_socket(struct context *c) && ( (c->options.persist_remote_ip) || ( c->sig->source != SIG_SOURCE_HARD - && ((c->c1.link_socket_addr.current_remote && c->c1.link_socket_addr.current_remote->ai_next) + && ((c->c1.link_socket_addr.current_remote + && c->c1.link_socket_addr.current_remote->ai_next) || c->options.no_advance)) ))) { diff --git a/src/openvpn/manage.c b/src/openvpn/manage.c index 898cb3b..ac14217 100644 --- a/src/openvpn/manage.c +++ b/src/openvpn/manage.c @@ -3310,12 +3310,17 @@ man_block(struct management *man, volatile int *signal_received, const time_t ex if (man_standalone_ok(man)) { + /* expire time can be already overdue, for this case init zero + * timeout to avoid waiting first time and exit loop early with + * either obtained event or timeout. + */ + tv.tv_usec = 0; + tv.tv_sec = 0; + while (true) { event_reset(man->connection.es); management_socket_set(man, man->connection.es, NULL, NULL); - tv.tv_usec = 0; - tv.tv_sec = 1; if (man_check_for_signals(signal_received)) { status = -1; @@ -3343,6 +3348,10 @@ man_block(struct management *man, volatile int *signal_received, const time_t ex } break; } + + /* wait one second more */ + tv.tv_sec = 1; + tv.tv_usec = 0; } } return status; @@ -3444,7 +3453,7 @@ management_event_loop_n_seconds(struct management *man, int sec) /* set expire time */ update_time(); - if (sec) + if (sec >= 0) { expire = now + sec; } @@ -3474,7 +3483,7 @@ management_event_loop_n_seconds(struct management *man, int sec) /* revert state */ man->persist.standalone_disabled = standalone_disabled_save; } - else + else if (sec > 0) { sleep(sec); } @@ -4117,11 +4126,15 @@ log_history_ref(const struct log_history *h, const int index) void management_sleep(const int n) { - if (management) + if (n < 0) + { + return; + } + else if (management) { management_event_loop_n_seconds(management, n); } - else + else if (n > 0) { sleep(n); } @@ -4132,7 +4145,10 @@ management_sleep(const int n) void management_sleep(const int n) { - sleep(n); + if (n > 0) + { + sleep(n); + } } #endif /* ENABLE_MANAGEMENT */ diff --git a/src/openvpn/networking_iproute2.c b/src/openvpn/networking_iproute2.c index f3b9c61..3b46052 100644 --- a/src/openvpn/networking_iproute2.c +++ b/src/openvpn/networking_iproute2.c @@ -88,6 +88,8 @@ net_iface_mtu_set(openvpn_net_ctx_t *ctx, const char *iface, uint32_t mtu) argv_msg(M_INFO, &argv); openvpn_execve_check(&argv, ctx->es, S_FATAL, "Linux ip link set failed"); + argv_free(&argv); + return 0; } diff --git a/src/openvpn/options.c b/src/openvpn/options.c index 3df803d..658ca53 100644 --- a/src/openvpn/options.c +++ b/src/openvpn/options.c @@ -1983,7 +1983,8 @@ connection_entry_load_re(struct connection_entry *ce, const struct remote_entry } static void -options_postprocess_verify_ce(const struct options *options, const struct connection_entry *ce) +options_postprocess_verify_ce(const struct options *options, + const struct connection_entry *ce) { struct options defaults; int dev = DEV_TYPE_UNDEF; @@ -2011,7 +2012,9 @@ options_postprocess_verify_ce(const struct options *options, const struct connec */ if (ce->proto == PROTO_TCP) { - msg(M_USAGE, "--proto tcp is ambiguous in this context. Please specify --proto tcp-server or --proto tcp-client"); + msg(M_USAGE, + "--proto tcp is ambiguous in this context. Please specify " + "--proto tcp-server or --proto tcp-client"); } /* @@ -2051,8 +2054,9 @@ options_postprocess_verify_ce(const struct options *options, const struct connec if (options->inetd) { - msg(M_WARN, "DEPRECATED OPTION: --inetd mode is deprecated " - "and will be removed in OpenVPN 2.6"); + msg(M_WARN, + "DEPRECATED OPTION: --inetd mode is deprecated and will be removed " + "in OpenVPN 2.6"); } if (options->lladdr && dev != DEV_TYPE_TAP) @@ -2065,7 +2069,9 @@ options_postprocess_verify_ce(const struct options *options, const struct connec */ if (options->ce.tun_mtu_defined && options->ce.link_mtu_defined) { - msg(M_USAGE, "only one of --tun-mtu or --link-mtu may be defined (note that --ifconfig implies --link-mtu %d)", LINK_MTU_DEFAULT); + msg(M_USAGE, + "only one of --tun-mtu or --link-mtu may be defined (note that " + "--ifconfig implies --link-mtu %d)", LINK_MTU_DEFAULT); } if (!proto_is_udp(ce->proto) && options->mtu_test) @@ -2092,18 +2098,23 @@ options_postprocess_verify_ce(const struct options *options, const struct connec if (string_defined_equal(ce->remote, options->ifconfig_local) || string_defined_equal(ce->remote, options->ifconfig_remote_netmask)) { - msg(M_USAGE, "--local and --remote addresses must be distinct from --ifconfig addresses"); + msg(M_USAGE, + "--local and --remote addresses must be distinct from --ifconfig " + "addresses"); } if (string_defined_equal(ce->local, options->ifconfig_local) || string_defined_equal(ce->local, options->ifconfig_remote_netmask)) { - msg(M_USAGE, "--local addresses must be distinct from --ifconfig addresses"); + msg(M_USAGE, + "--local addresses must be distinct from --ifconfig addresses"); } - if (string_defined_equal(options->ifconfig_local, options->ifconfig_remote_netmask)) + if (string_defined_equal(options->ifconfig_local, + options->ifconfig_remote_netmask)) { - msg(M_USAGE, "local and remote/netmask --ifconfig addresses must be different"); + msg(M_USAGE, + "local and remote/netmask --ifconfig addresses must be different"); } if (ce->bind_defined && !ce->bind_local) @@ -2113,12 +2124,14 @@ options_postprocess_verify_ce(const struct options *options, const struct connec if (ce->local && !ce->bind_local) { - msg(M_USAGE, "--local and --nobind don't make sense when used together"); + msg(M_USAGE, + "--local and --nobind don't make sense when used together"); } if (ce->local_port_defined && !ce->bind_local) { - msg(M_USAGE, "--lport and --nobind don't make sense when used together"); + msg(M_USAGE, + "--lport and --nobind don't make sense when used together"); } if (!ce->remote && !ce->bind_local) @@ -2207,7 +2220,8 @@ options_postprocess_verify_ce(const struct options *options, const struct connec if (!proto_is_udp(ce->proto) && ce->explicit_exit_notification) { - msg(M_USAGE, "--explicit-exit-notify can only be used with --proto udp"); + msg(M_USAGE, + "--explicit-exit-notify can only be used with --proto udp"); } if (!ce->remote && ce->proto == PROTO_TCP_CLIENT) @@ -2217,16 +2231,21 @@ options_postprocess_verify_ce(const struct options *options, const struct connec if ((ce->http_proxy_options) && ce->proto != PROTO_TCP_CLIENT) { - msg(M_USAGE, "--http-proxy MUST be used in TCP Client mode (i.e. --proto tcp-client)"); + msg(M_USAGE, + "--http-proxy MUST be used in TCP Client mode (i.e. --proto " + "tcp-client)"); } + if ((ce->http_proxy_options) && !ce->http_proxy_options->server) { - msg(M_USAGE, "--http-proxy not specified but other http proxy options present"); + msg(M_USAGE, + "--http-proxy not specified but other http proxy options present"); } if (ce->http_proxy_options && ce->socks_proxy_server) { - msg(M_USAGE, "--http-proxy can not be used together with --socks-proxy"); + msg(M_USAGE, + "--http-proxy can not be used together with --socks-proxy"); } if (ce->socks_proxy_server && ce->proto == PROTO_TCP_SERVER) @@ -2292,8 +2311,9 @@ options_postprocess_verify_ce(const struct options *options, const struct connec { msg(M_USAGE, "--socks-proxy cannot be used with --mode server"); } - /* <connection> blocks force to have a remote embedded, so we check for the - * --remote and bail out if it is present */ + /* <connection> blocks force to have a remote embedded, so we check + * for the --remote and bail out if it is present + */ if (options->connection_list->len >1 || options->connection_list->array[0]->remote) { @@ -2310,12 +2330,15 @@ options_postprocess_verify_ce(const struct options *options, const struct connec } if (options->ipchange) { - msg(M_USAGE, "--ipchange cannot be used with --mode server (use --client-connect instead)"); + msg(M_USAGE, + "--ipchange cannot be used with --mode server (use " + "--client-connect instead)"); } if (!(proto_is_dgram(ce->proto) || ce->proto == PROTO_TCP_SERVER)) { - msg(M_USAGE, "--mode server currently only supports " - "--proto udp or --proto tcp-server or --proto tcp6-server"); + msg(M_USAGE, + "--mode server currently only supports --proto udp or --proto " + "tcp-server or --proto tcp6-server"); } if (!proto_is_udp(ce->proto) && (options->cf_max || options->cf_per)) { @@ -2817,12 +2840,14 @@ options_postprocess_mutate_ce(struct options *o, struct connection_entry *ce) } #endif - if (ce->proto == PROTO_TCP_CLIENT && !ce->local && !ce->local_port_defined && !ce->bind_defined) + if (ce->proto == PROTO_TCP_CLIENT && !ce->local + && !ce->local_port_defined && !ce->bind_defined) { ce->bind_local = false; } - if (ce->proto == PROTO_UDP && ce->socks_proxy_server && !ce->local && !ce->local_port_defined && !ce->bind_defined) + if (ce->proto == PROTO_UDP && ce->socks_proxy_server && !ce->local + && !ce->local_port_defined && !ce->bind_defined) { ce->bind_local = false; } @@ -2832,7 +2857,9 @@ options_postprocess_mutate_ce(struct options *o, struct connection_entry *ce) ce->local_port = NULL; } - /* if protocol forcing is enabled, disable all protocols except for the forced one */ + /* if protocol forcing is enabled, disable all protocols + * except for the forced one + */ if (o->proto_force >= 0 && o->proto_force != ce->proto) { ce->flags |= CE_DISABLED; @@ -5690,7 +5717,9 @@ add_option(struct options *options, const sa_family_t af = ascii2af(p[3]); if (proto < 0) { - msg(msglevel, "remote: bad protocol associated with host %s: '%s'", p[1], p[3]); + msg(msglevel, + "remote: bad protocol associated with host %s: '%s'", + p[1], p[3]); goto err; } re.proto = proto; @@ -6210,7 +6239,8 @@ add_option(struct options *options, af = ascii2af(p[1]); if (proto < 0) { - msg(msglevel, "Bad protocol: '%s'. Allowed protocols with --proto option: %s", + msg(msglevel, + "Bad protocol: '%s'. Allowed protocols with --proto option: %s", p[1], proto2ascii_all(&gc)); goto err; diff --git a/src/openvpn/route.c b/src/openvpn/route.c index d75aa5f..5e1dca6 100644 --- a/src/openvpn/route.c +++ b/src/openvpn/route.c @@ -1011,14 +1011,10 @@ redirect_default_route_to_vpn(struct route_list *rl, const struct tuntap *tt, * - we are connecting to a non-IPv4 remote host (i.e. we use IPv6) */ else if (!(rl->rgi.flags & RGI_ADDR_DEFINED) && !local - && (rl->spec.remote_host != IPV4_INVALID_ADDR)) + && (rl->spec.flags & RTSA_REMOTE_HOST)) { msg(M_WARN, "%s Cannot read current default gateway from system", err); } - else if (!(rl->spec.flags & RTSA_REMOTE_HOST)) - { - msg(M_WARN, "%s Cannot obtain current remote host address", err); - } else { #ifndef TARGET_ANDROID @@ -1041,7 +1037,8 @@ redirect_default_route_to_vpn(struct route_list *rl, const struct tuntap *tt, /* route remote host to original default gateway */ /* if remote_host is not ipv4 (ie: ipv6), just skip * adding this special /32 route */ - if (rl->spec.remote_host != IPV4_INVALID_ADDR) + if ((rl->spec.flags & RTSA_REMOTE_HOST) + && rl->spec.remote_host != IPV4_INVALID_ADDR) { add_route3(rl->spec.remote_host, IPV4_NETMASK_HOST, @@ -1479,6 +1476,13 @@ setenv_route_ipv6(struct env_set *es, const struct route_ipv6 *r6, int i) buf_printf( &name2, "route_ipv6_gateway_%d", i ); setenv_str( es, BSTR(&name2), print_in6_addr( r6->gateway, 0, &gc )); + + if (r6->flags & RT_METRIC_DEFINED) + { + struct buffer name3 = alloc_buf_gc( 256, &gc ); + buf_printf( &name3, "route_ipv6_metric_%d", i) ; + setenv_int( es, BSTR(&name3), r6->metric); + } } gc_free(&gc); } diff --git a/src/openvpn/socket.c b/src/openvpn/socket.c index 76bdbfc..9775068 100644 --- a/src/openvpn/socket.c +++ b/src/openvpn/socket.c @@ -378,7 +378,8 @@ do_preresolve(struct context *c) /* HTTP remote hostname does not need to be resolved */ if (!ce->http_proxy_options) { - status = do_preresolve_host(c, remote, ce->remote_port, ce->af, flags); + status = do_preresolve_host(c, remote, ce->remote_port, + ce->af, flags); if (status != 0) { goto err; @@ -417,7 +418,8 @@ do_preresolve(struct context *c) { flags |= GETADDR_PASSIVE; flags &= ~GETADDR_RANDOMIZE; - status = do_preresolve_host(c, ce->local, ce->local_port, ce->af, flags); + status = do_preresolve_host(c, ce->local, ce->local_port, + ce->af, flags); if (status != 0) { goto err; @@ -526,7 +528,9 @@ openvpn_getaddrinfo(unsigned int flags, if ((flags & GETADDR_MENTION_RESOLVE_RETRY) && !resolve_retry_seconds) { - fmt = "RESOLVE: Cannot resolve host address: %s:%s (%s) (I would have retried this name query if you had specified the --resolv-retry option.)"; + fmt = "RESOLVE: Cannot resolve host address: %s:%s (%s) " + "(I would have retried this name query if you had " + "specified the --resolv-retry option.)"; } if (!(flags & GETADDR_RESOLVE) || status == EAI_FAIL) @@ -558,11 +562,13 @@ openvpn_getaddrinfo(unsigned int flags, while (true) { #ifndef _WIN32 + /* force resolv.conf reload */ res_init(); #endif /* try hostname lookup */ hints.ai_flags &= ~AI_NUMERICHOST; - dmsg(D_SOCKET_DEBUG, "GETADDRINFO flags=0x%04x ai_family=%d ai_socktype=%d", + dmsg(D_SOCKET_DEBUG, + "GETADDRINFO flags=0x%04x ai_family=%d ai_socktype=%d", flags, hints.ai_family, hints.ai_socktype); status = getaddrinfo(hostname, servname, &hints, res); @@ -573,7 +579,9 @@ openvpn_getaddrinfo(unsigned int flags, { if (*signal_received == SIGUSR1) /* ignore SIGUSR1 */ { - msg(level, "RESOLVE: Ignored SIGUSR1 signal received during DNS resolution attempt"); + msg(level, + "RESOLVE: Ignored SIGUSR1 signal received during " + "DNS resolution attempt"); *signal_received = 0; } else @@ -634,7 +642,9 @@ openvpn_getaddrinfo(unsigned int flags, /* IP address parse succeeded */ if (flags & GETADDR_RANDOMIZE) { - msg(M_WARN, "WARNING: ignoring --remote-random-hostname because the hostname is an IP address"); + msg(M_WARN, + "WARNING: ignoring --remote-random-hostname because the " + "hostname is an IP address"); } } @@ -1470,14 +1480,14 @@ openvpn_connect(socket_descriptor_t sd, struct pollfd fds[1]; fds[0].fd = sd; fds[0].events = POLLOUT; - status = poll(fds, 1, 0); + status = poll(fds, 1, (connect_timeout > 0) ? 1000 : 0); #else fd_set writes; struct timeval tv; FD_ZERO(&writes); openvpn_fd_set(sd, &writes); - tv.tv_sec = 0; + tv.tv_sec = (connect_timeout > 0) ? 1 : 0; tv.tv_usec = 0; status = select(sd + 1, NULL, &writes, NULL, &tv); @@ -1507,7 +1517,7 @@ openvpn_connect(socket_descriptor_t sd, #endif break; } - management_sleep(1); + management_sleep(0); continue; } @@ -1802,7 +1812,8 @@ resolve_remote(struct link_socket *sock, sock->info.lsa->remote_list = ai; sock->info.lsa->current_remote = ai; - dmsg(D_SOCKET_DEBUG, "RESOLVE_REMOTE flags=0x%04x phase=%d rrs=%d sig=%d status=%d", + dmsg(D_SOCKET_DEBUG, + "RESOLVE_REMOTE flags=0x%04x phase=%d rrs=%d sig=%d status=%d", flags, phase, retry, @@ -3155,22 +3166,22 @@ struct proto_names { /* Indexed by PROTO_x */ static const struct proto_names proto_names[] = { - {"proto-uninitialized", "proto-NONE", AF_UNSPEC, PROTO_NONE}, + {"proto-uninitialized", "proto-NONE", AF_UNSPEC, PROTO_NONE}, /* try IPv4 and IPv6 (client), bind dual-stack (server) */ - {"udp", "UDP", AF_UNSPEC, PROTO_UDP}, - {"tcp-server", "TCP_SERVER", AF_UNSPEC, PROTO_TCP_SERVER}, - {"tcp-client", "TCP_CLIENT", AF_UNSPEC, PROTO_TCP_CLIENT}, - {"tcp", "TCP", AF_UNSPEC, PROTO_TCP}, + {"udp", "UDP", AF_UNSPEC, PROTO_UDP}, + {"tcp-server", "TCP_SERVER", AF_UNSPEC, PROTO_TCP_SERVER}, + {"tcp-client", "TCP_CLIENT", AF_UNSPEC, PROTO_TCP_CLIENT}, + {"tcp", "TCP", AF_UNSPEC, PROTO_TCP}, /* force IPv4 */ - {"udp4", "UDPv4", AF_INET, PROTO_UDP}, - {"tcp4-server","TCPv4_SERVER", AF_INET, PROTO_TCP_SERVER}, - {"tcp4-client","TCPv4_CLIENT", AF_INET, PROTO_TCP_CLIENT}, - {"tcp4", "TCPv4", AF_INET, PROTO_TCP}, + {"udp4", "UDPv4", AF_INET, PROTO_UDP}, + {"tcp4-server", "TCPv4_SERVER", AF_INET, PROTO_TCP_SERVER}, + {"tcp4-client", "TCPv4_CLIENT", AF_INET, PROTO_TCP_CLIENT}, + {"tcp4", "TCPv4", AF_INET, PROTO_TCP}, /* force IPv6 */ - {"udp6","UDPv6", AF_INET6, PROTO_UDP}, - {"tcp6-server","TCPv6_SERVER", AF_INET6, PROTO_TCP_SERVER}, - {"tcp6-client","TCPv6_CLIENT", AF_INET6, PROTO_TCP_CLIENT}, - {"tcp6","TCPv6", AF_INET6, PROTO_TCP}, + {"udp6", "UDPv6", AF_INET6, PROTO_UDP}, + {"tcp6-server", "TCPv6_SERVER", AF_INET6, PROTO_TCP_SERVER}, + {"tcp6-client", "TCPv6_CLIENT", AF_INET6, PROTO_TCP_CLIENT}, + {"tcp6", "TCPv6", AF_INET6, PROTO_TCP}, }; bool @@ -3182,6 +3193,7 @@ proto_is_net(int proto) } return proto != PROTO_NONE; } + bool proto_is_dgram(int proto) { diff --git a/src/openvpn/ssl.c b/src/openvpn/ssl.c index f16114c..c6ba812 100644 --- a/src/openvpn/ssl.c +++ b/src/openvpn/ssl.c @@ -2484,6 +2484,14 @@ key_method_2_read(struct buffer *buf, struct tls_multi *multi, struct tls_sessio multi->remote_ciphername = options_string_extract_option(options, "cipher", NULL); + /* In OCC we send '[null-cipher]' instead 'none' */ + if (multi->remote_ciphername + && strcmp(multi->remote_ciphername, "[null-cipher]") == 0) + { + free(multi->remote_ciphername); + multi->remote_ciphername = string_alloc("none", NULL); + } + if (tls_session_user_pass_enabled(session)) { /* Perform username/password authentication */ diff --git a/src/openvpn/ssl_ncp.c b/src/openvpn/ssl_ncp.c index 5549639..45bddbe 100644 --- a/src/openvpn/ssl_ncp.c +++ b/src/openvpn/ssl_ncp.c @@ -110,7 +110,15 @@ mutate_ncp_cipher_list(const char *list, struct gc_arena *gc) * e.g. replacing AeS-128-gCm with AES-128-GCM */ const cipher_kt_t *ktc = cipher_kt_get(token); - if (!ktc) + if (strcmp(token, "none") == 0) + { + msg(M_WARN, "WARNING: cipher 'none' specified for --data-ciphers. " + "This allows negotiation of NO encryption and " + "tunnelled data WILL then be transmitted in clear text " + "over the network! " + "PLEASE DO RECONSIDER THIS SETTING!"); + } + if (!ktc && strcmp(token, "none") != 0) { msg(M_WARN, "Unsupported cipher in --data-ciphers: %s", token); error_found = true; @@ -118,6 +126,12 @@ mutate_ncp_cipher_list(const char *list, struct gc_arena *gc) else { const char *ovpn_cipher_name = cipher_kt_name(ktc); + if (ktc == NULL) + { + /* NULL resolves to [null-cipher] but we need none for + * data-ciphers */ + ovpn_cipher_name = "none"; + } if (buf_len(&new_list)> 0) { @@ -325,4 +339,4 @@ check_pull_client_ncp(struct context *c, const int found) "to this server."); return false; } -}
\ No newline at end of file +} diff --git a/src/openvpn/ssl_verify.c b/src/openvpn/ssl_verify.c index 97ccb93..33115eb 100644 --- a/src/openvpn/ssl_verify.c +++ b/src/openvpn/ssl_verify.c @@ -1068,69 +1068,51 @@ verify_user_pass_script(struct tls_session *session, struct tls_multi *multi, const char *tmp_file = ""; bool ret = false; - /* Is username defined? */ - if ((session->opt->ssl_flags & SSLF_AUTH_USER_PASS_OPTIONAL) || strlen(up->username)) + /* Set environmental variables prior to calling script */ + setenv_str(session->opt->es, "script_type", "user-pass-verify"); + + /* format command line */ + argv_parse_cmd(&argv, session->opt->auth_user_pass_verify_script); + + if (session->opt->auth_user_pass_verify_script_via_file) { - /* Set environmental variables prior to calling script */ - setenv_str(session->opt->es, "script_type", "user-pass-verify"); + struct status_output *so; - if (session->opt->auth_user_pass_verify_script_via_file) + tmp_file = platform_create_temp_file(session->opt->tmp_dir, "up", + &gc); + if (tmp_file) { - struct status_output *so; - - tmp_file = platform_create_temp_file(session->opt->tmp_dir, "up", - &gc); - if (tmp_file) - { - so = status_open(tmp_file, 0, -1, NULL, STATUS_OUTPUT_WRITE); - status_printf(so, "%s", up->username); - status_printf(so, "%s", up->password); - if (!status_close(so)) - { - msg(D_TLS_ERRORS, "TLS Auth Error: could not write username/password to file: %s", - tmp_file); - goto done; - } - } - else + so = status_open(tmp_file, 0, -1, NULL, STATUS_OUTPUT_WRITE); + status_printf(so, "%s", up->username); + status_printf(so, "%s", up->password); + if (!status_close(so)) { - msg(D_TLS_ERRORS, "TLS Auth Error: could not create write " - "username/password to temp file"); + msg(D_TLS_ERRORS, "TLS Auth Error: could not write username/password to file: %s", + tmp_file); + goto done; } + /* pass temp file name to script */ + argv_printf_cat(&argv, "%s", tmp_file); } else { - setenv_str(session->opt->es, "username", up->username); - setenv_str(session->opt->es, "password", up->password); - } - - /* setenv incoming cert common name for script */ - setenv_str(session->opt->es, "common_name", session->common_name); - - /* setenv client real IP address */ - setenv_untrusted(session); - - /* add auth-token environment */ - add_session_token_env(session, multi, up); - - /* format command line */ - argv_parse_cmd(&argv, session->opt->auth_user_pass_verify_script); - argv_printf_cat(&argv, "%s", tmp_file); - - /* call command */ - ret = openvpn_run_script(&argv, session->opt->es, 0, - "--auth-user-pass-verify"); - - if (!session->opt->auth_user_pass_verify_script_via_file) - { - setenv_del(session->opt->es, "password"); + msg(D_TLS_ERRORS, "TLS Auth Error: could not create write " + "username/password to temp file"); } } else { - msg(D_TLS_ERRORS, "TLS Auth Error: peer provided a blank username"); + setenv_str(session->opt->es, "password", up->password); } + /* call command */ + ret = openvpn_run_script(&argv, session->opt->es, 0, + "--auth-user-pass-verify"); + + if (!session->opt->auth_user_pass_verify_script_via_file) + { + setenv_del(session->opt->es, "password"); + } done: if (tmp_file && strlen(tmp_file) > 0) { @@ -1154,48 +1136,31 @@ verify_user_pass_plugin(struct tls_session *session, struct tls_multi *multi, struct key_state *ks = &session->key[KS_PRIMARY]; /* primary key */ #endif - /* Is username defined? */ - if ((session->opt->ssl_flags & SSLF_AUTH_USER_PASS_OPTIONAL) || strlen(up->username)) - { - /* set username/password in private env space */ - setenv_str(session->opt->es, "username", up->username); - setenv_str(session->opt->es, "password", up->password); - - /* setenv incoming cert common name for script */ - setenv_str(session->opt->es, "common_name", session->common_name); + /* set password in private env space */ + setenv_str(session->opt->es, "password", up->password); - /* setenv client real IP address */ - setenv_untrusted(session); - - /* add auth-token environment */ - add_session_token_env(session, multi, up); #ifdef PLUGIN_DEF_AUTH - /* generate filename for deferred auth control file */ - if (!key_state_gen_auth_control_file(ks, session->opt)) - { - msg(D_TLS_ERRORS, "TLS Auth Error (%s): " - "could not create deferred auth control file", __func__); - return retval; - } + /* generate filename for deferred auth control file */ + if (!key_state_gen_auth_control_file(ks, session->opt)) + { + msg(D_TLS_ERRORS, "TLS Auth Error (%s): " + "could not create deferred auth control file", __func__); + return retval; + } #endif - /* call command */ - retval = plugin_call(session->opt->plugins, OPENVPN_PLUGIN_AUTH_USER_PASS_VERIFY, NULL, NULL, session->opt->es); + /* call command */ + retval = plugin_call(session->opt->plugins, OPENVPN_PLUGIN_AUTH_USER_PASS_VERIFY, NULL, NULL, session->opt->es); #ifdef PLUGIN_DEF_AUTH - /* purge auth control filename (and file itself) for non-deferred returns */ - if (retval != OPENVPN_PLUGIN_FUNC_DEFERRED) - { - key_state_rm_auth_control_file(ks); - } -#endif - - setenv_del(session->opt->es, "password"); - } - else + /* purge auth control filename (and file itself) for non-deferred returns */ + if (retval != OPENVPN_PLUGIN_FUNC_DEFERRED) { - msg(D_TLS_ERRORS, "TLS Auth Error (verify_user_pass_plugin): peer provided a blank username"); + key_state_rm_auth_control_file(ks); } +#endif + + setenv_del(session->opt->es, "password"); return retval; } @@ -1218,12 +1183,30 @@ verify_user_pass_management(struct tls_session *session, int retval = KMDA_ERROR; struct key_state *ks = &session->key[KS_PRIMARY]; /* primary key */ + /* set username/password in private env space */ + setenv_str(session->opt->es, "password", up->password); + + if (management) + { + management_notify_client_needing_auth(management, ks->mda_key_id, session->opt->mda_context, session->opt->es); + } + + setenv_del(session->opt->es, "password"); + + retval = KMDA_SUCCESS; + + return retval; +} +#endif /* ifdef MANAGEMENT_DEF_AUTH */ + +static bool +set_verify_user_pass_env(struct user_pass *up, struct tls_multi *multi, + struct tls_session *session) +{ /* Is username defined? */ if ((session->opt->ssl_flags & SSLF_AUTH_USER_PASS_OPTIONAL) || strlen(up->username)) { - /* set username/password in private env space */ setenv_str(session->opt->es, "username", up->username); - setenv_str(session->opt->es, "password", up->password); /* setenv incoming cert common name for script */ setenv_str(session->opt->es, "common_name", session->common_name); @@ -1236,24 +1219,14 @@ verify_user_pass_management(struct tls_session *session, * allow the management to figure out if it is a new session or a continued one */ add_session_token_env(session, multi, up); - if (management) - { - management_notify_client_needing_auth(management, ks->mda_key_id, session->opt->mda_context, session->opt->es); - } - - setenv_del(session->opt->es, "password"); - - retval = KMDA_SUCCESS; + return true; } else { - msg(D_TLS_ERRORS, "TLS Auth Error (verify_user_pass_management): peer provided a blank username"); + msg(D_TLS_ERRORS, "TLS Auth Error: peer provided a blank username"); + return false; } - - return retval; } -#endif /* ifdef MANAGEMENT_DEF_AUTH */ - /* * Main username/password verification entry point @@ -1325,6 +1298,14 @@ verify_user_pass(struct user_pass *up, struct tls_multi *multi, return; } } + + /* Set the environment variables used by all auth variants */ + if (!set_verify_user_pass_env(up, multi, session)) + { + skip_auth = true; + s1 = OPENVPN_PLUGIN_FUNC_ERROR; + } + /* call plugin(s) and/or script */ if (!skip_auth) { diff --git a/src/openvpn/tun.c b/src/openvpn/tun.c index 9eeaed0..8315a42 100644 --- a/src/openvpn/tun.c +++ b/src/openvpn/tun.c @@ -6571,7 +6571,7 @@ tun_open_device(struct tuntap *tt, const char *dev_node, const char **device_gui if (!*device_guid) { - msg(M_FATAL, "All %s adapters on this system are currently in use.", print_windows_driver(tt->windows_driver)); + msg(M_FATAL, "All %s adapters on this system are currently in use or disabled.", print_windows_driver(tt->windows_driver)); } if (tt->windows_driver != windows_driver) |