Welcome to mirror list, hosted at ThFree Co, Russian Federation.

github.com/wolfpld/tracy.git - Unnamed repository; edit this file 'description' to name the repository.
summaryrefslogtreecommitdiff
path: root/public
diff options
context:
space:
mode:
authorBartosz Taudul <wolf@nereid.pl>2022-08-16 15:43:50 +0300
committerBartosz Taudul <wolf@nereid.pl>2022-08-16 15:43:50 +0300
commit06b986ad908a79d4d68cf10557078b4049360e69 (patch)
treea5667efa52519c7b1498d5e2c8f4d49c6f785152 /public
parent3d9d242153bb09ec692fb94f9f527b5e402e8287 (diff)
Bump LZ4 to 1.9.4.
Diffstat (limited to 'public')
-rw-r--r--public/common/tracy_lz4.cpp616
-rw-r--r--public/common/tracy_lz4.hpp162
-rw-r--r--public/common/tracy_lz4hc.cpp238
-rw-r--r--public/common/tracy_lz4hc.hpp28
4 files changed, 679 insertions, 365 deletions
diff --git a/public/common/tracy_lz4.cpp b/public/common/tracy_lz4.cpp
index 5a31aa75..6c26639c 100644
--- a/public/common/tracy_lz4.cpp
+++ b/public/common/tracy_lz4.cpp
@@ -1,6 +1,6 @@
/*
LZ4 - Fast LZ compression algorithm
- Copyright (C) 2011-present, Yann Collet.
+ Copyright (C) 2011-2020, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
@@ -124,6 +124,7 @@
#if defined(_MSC_VER) && (_MSC_VER >= 1400) /* Visual Studio 2005+ */
# include <intrin.h> /* only present in VS2005+ */
# pragma warning(disable : 4127) /* disable: C4127: conditional expression is constant */
+# pragma warning(disable : 6237) /* disable: C6237: conditional expression is always 0 */
#endif /* _MSC_VER */
#ifndef LZ4_FORCE_INLINE
@@ -187,7 +188,27 @@
/*-************************************
* Memory routines
**************************************/
-#ifdef LZ4_USER_MEMORY_FUNCTIONS
+
+/*! LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION :
+ * Disable relatively high-level LZ4/HC functions that use dynamic memory
+ * allocation functions (malloc(), calloc(), free()).
+ *
+ * Note that this is a compile-time switch. And since it disables
+ * public/stable LZ4 v1 API functions, we don't recommend using this
+ * symbol to generate a library for distribution.
+ *
+ * The following public functions are removed when this symbol is defined.
+ * - lz4 : LZ4_createStream, LZ4_freeStream,
+ * LZ4_createStreamDecode, LZ4_freeStreamDecode, LZ4_create (deprecated)
+ * - lz4hc : LZ4_createStreamHC, LZ4_freeStreamHC,
+ * LZ4_createHC (deprecated), LZ4_freeHC (deprecated)
+ * - lz4frame, lz4file : All LZ4F_* functions
+ */
+#if defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
+# define ALLOC(s) lz4_error_memory_allocation_is_disabled
+# define ALLOC_AND_ZERO(s) lz4_error_memory_allocation_is_disabled
+# define FREEMEM(p) lz4_error_memory_allocation_is_disabled
+#elif defined(LZ4_USER_MEMORY_FUNCTIONS)
/* memory management functions can be customized by user project.
* Below functions must exist somewhere in the Project
* and be available at link time */
@@ -204,8 +225,13 @@ void LZ4_free(void* p);
# define FREEMEM(p) free(p)
#endif
-#include <string.h> /* memset, memcpy */
-#define MEM_INIT(p,v,s) memset((p),(v),(s))
+#if ! LZ4_FREESTANDING
+# include <string.h> /* memset, memcpy */
+#endif
+#if !defined(LZ4_memset)
+# define LZ4_memset(p,v,s) memset((p),(v),(s))
+#endif
+#define MEM_INIT(p,v,s) LZ4_memset((p),(v),(s))
/*-************************************
@@ -318,10 +344,20 @@ namespace tracy
* memcpy() as if it were standard compliant, so it can inline it in freestanding
* environments. This is needed when decompressing the Linux Kernel, for example.
*/
-#if defined(__GNUC__) && (__GNUC__ >= 4)
-#define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
-#else
-#define LZ4_memcpy(dst, src, size) memcpy(dst, src, size)
+#if !defined(LZ4_memcpy)
+# if defined(__GNUC__) && (__GNUC__ >= 4)
+# define LZ4_memcpy(dst, src, size) __builtin_memcpy(dst, src, size)
+# else
+# define LZ4_memcpy(dst, src, size) memcpy(dst, src, size)
+# endif
+#endif
+
+#if !defined(LZ4_memmove)
+# if defined(__GNUC__) && (__GNUC__ >= 4)
+# define LZ4_memmove __builtin_memmove
+# else
+# define LZ4_memmove memmove
+# endif
#endif
static unsigned LZ4_isLittleEndian(void)
@@ -345,14 +381,14 @@ static void LZ4_write32(void* memPtr, U32 value) { *(U32*)memPtr = value; }
/* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
/* currently only defined for gcc and icc */
-typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) unalign;
+typedef union { U16 u16; U32 u32; reg_t uArch; } __attribute__((packed)) LZ4_unalign;
-static U16 LZ4_read16(const void* ptr) { return ((const unalign*)ptr)->u16; }
-static U32 LZ4_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
-static reg_t LZ4_read_ARCH(const void* ptr) { return ((const unalign*)ptr)->uArch; }
+static U16 LZ4_read16(const void* ptr) { return ((const LZ4_unalign*)ptr)->u16; }
+static U32 LZ4_read32(const void* ptr) { return ((const LZ4_unalign*)ptr)->u32; }
+static reg_t LZ4_read_ARCH(const void* ptr) { return ((const LZ4_unalign*)ptr)->uArch; }
-static void LZ4_write16(void* memPtr, U16 value) { ((unalign*)memPtr)->u16 = value; }
-static void LZ4_write32(void* memPtr, U32 value) { ((unalign*)memPtr)->u32 = value; }
+static void LZ4_write16(void* memPtr, U16 value) { ((LZ4_unalign*)memPtr)->u16 = value; }
+static void LZ4_write32(void* memPtr, U32 value) { ((LZ4_unalign*)memPtr)->u32 = value; }
#else /* safe and portable access using memcpy() */
@@ -423,10 +459,12 @@ static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3};
#ifndef LZ4_FAST_DEC_LOOP
# if defined __i386__ || defined _M_IX86 || defined __x86_64__ || defined _M_X64
# define LZ4_FAST_DEC_LOOP 1
+# elif defined(__aarch64__) && defined(__APPLE__)
+# define LZ4_FAST_DEC_LOOP 1
# elif defined(__aarch64__) && !defined(__clang__)
- /* On aarch64, we disable this optimization for clang because on certain
- * mobile chipsets, performance is reduced with clang. For information
- * refer to https://github.com/lz4/lz4/pull/707 */
+ /* On non-Apple aarch64, we disable this optimization for clang because
+ * on certain mobile chipsets, performance is reduced with clang. 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
@@ -488,7 +526,14 @@ LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const si
case 2:
LZ4_memcpy(v, srcPtr, 2);
LZ4_memcpy(&v[2], srcPtr, 2);
+#if defined(_MSC_VER) && (_MSC_VER <= 1933) /* MSVC 2022 ver 17.3 or earlier */
+# pragma warning(push)
+# pragma warning(disable : 6385) /* warning C6385: Reading invalid data from 'v'. */
+#endif
LZ4_memcpy(&v[4], v, 4);
+#if defined(_MSC_VER) && (_MSC_VER <= 1933) /* MSVC 2022 ver 17.3 or earlier */
+# pragma warning(pop)
+#endif
break;
case 4:
LZ4_memcpy(v, srcPtr, 4);
@@ -517,9 +562,20 @@ LZ4_FORCE_INLINE unsigned LZ4_NbCommonBytes (reg_t val)
assert(val != 0);
if (LZ4_isLittleEndian()) {
if (sizeof(val) == 8) {
-# if defined(_MSC_VER) && (_MSC_VER >= 1800) && defined(_M_AMD64) && !defined(LZ4_FORCE_SW_BITCOUNT)
+# if defined(_MSC_VER) && (_MSC_VER >= 1800) && (defined(_M_AMD64) && !defined(_M_ARM64EC)) && !defined(LZ4_FORCE_SW_BITCOUNT)
+/*-*************************************************************************************************
+* ARM64EC is a Microsoft-designed ARM64 ABI compatible with AMD64 applications on ARM64 Windows 11.
+* The ARM64EC ABI does not support AVX/AVX2/AVX512 instructions, nor their relevant intrinsics
+* including _tzcnt_u64. Therefore, we need to neuter the _tzcnt_u64 code path for ARM64EC.
+****************************************************************************************************/
+# if defined(__clang__) && (__clang_major__ < 10)
+ /* Avoid undefined clang-cl intrinsics issue.
+ * See https://github.com/lz4/lz4/pull/1017 for details. */
+ return (unsigned)__builtin_ia32_tzcnt_u64(val) >> 3;
+# else
/* x64 CPUS without BMI support interpret `TZCNT` as `REP BSF` */
return (unsigned)_tzcnt_u64(val) >> 3;
+# endif
# elif defined(_MSC_VER) && defined(_WIN64) && !defined(LZ4_FORCE_SW_BITCOUNT)
unsigned long r = 0;
_BitScanForward64(&r, (U64)val);
@@ -654,10 +710,10 @@ typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;
* - usingExtDict : Like withPrefix64k, but the preceding content is somewhere
* else in memory, starting at ctx->dictionary with length
* ctx->dictSize.
- * - usingDictCtx : Like usingExtDict, but everything concerning the preceding
- * content is in a separate context, pointed to by
- * ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table
- * entries in the current context that refer to positions
+ * - usingDictCtx : Everything concerning the preceding content is
+ * in a separate context, pointed to by ctx->dictCtx.
+ * ctx->dictionary, ctx->dictSize, and table entries
+ * in the current context that refer to positions
* preceding the beginning of the current compression are
* ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
* ->dictSize describe the location and size of the preceding
@@ -674,18 +730,21 @@ typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
int LZ4_versionNumber (void) { return LZ4_VERSION_NUMBER; }
const char* LZ4_versionString(void) { return LZ4_VERSION_STRING; }
int LZ4_compressBound(int isize) { return LZ4_COMPRESSBOUND(isize); }
-int LZ4_sizeofState(void) { return LZ4_STREAMSIZE; }
+int LZ4_sizeofState(void) { return sizeof(LZ4_stream_t); }
-/*-************************************
-* Internal Definitions used in Tests
-**************************************/
+/*-****************************************
+* Internal Definitions, used only in Tests
+*******************************************/
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);
+int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
+ int compressedSize, int targetOutputSize, int dstCapacity,
+ const void* dictStart, size_t dictSize);
/*-******************************
* Compression functions
@@ -822,9 +881,10 @@ LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
}
}
- /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back, is faster
- * than compressing without a gap. However, compressing with
- * currentOffset == 0 is faster still, so we preserve that case.
+ /* Adding a gap, so all previous entries are > LZ4_DISTANCE_MAX back,
+ * is faster than compressing without a gap.
+ * However, compressing with currentOffset == 0 is faster still,
+ * so we preserve that case.
*/
if (cctx->currentOffset != 0 && tableType == byU32) {
DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
@@ -848,7 +908,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
const char* const source,
char* const dest,
const int inputSize,
- int *inputConsumed, /* only written when outputDirective == fillOutput */
+ int* inputConsumed, /* only written when outputDirective == fillOutput */
const int maxOutputSize,
const limitedOutput_directive outputDirective,
const tableType_t tableType,
@@ -880,7 +940,8 @@ LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
/* the dictCtx currentOffset is indexed on the start of the dictionary,
* while a dictionary in the current context precedes the currentOffset */
- const BYTE* dictBase = !dictionary ? NULL : (dictDirective == usingDictCtx) ?
+ const BYTE* dictBase = (dictionary == NULL) ? NULL :
+ (dictDirective == usingDictCtx) ?
dictionary + dictSize - dictCtx->currentOffset :
dictionary + dictSize - startIndex;
@@ -976,10 +1037,11 @@ LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
match = base + matchIndex;
lowLimit = (const BYTE*)source;
}
- } else if (dictDirective==usingExtDict) {
+ } else if (dictDirective == usingExtDict) {
if (matchIndex < startIndex) {
DEBUGLOG(7, "extDict candidate: matchIndex=%5u < startIndex=%5u", matchIndex, startIndex);
assert(startIndex - matchIndex >= MINMATCH);
+ assert(dictBase);
match = dictBase + matchIndex;
lowLimit = dictionary;
} else {
@@ -1043,7 +1105,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic_validated(
_next_match:
/* at this stage, the following variables must be correctly set :
* - ip : at start of LZ operation
- * - match : at start of previous pattern occurence; can be within current prefix, or within extDict
+ * - match : at start of previous pattern occurrence; can be within current prefix, or within extDict
* - offset : if maybe_ext_memSegment==1 (constant)
* - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
* - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
@@ -1168,6 +1230,7 @@ _next_match:
}
} else if (dictDirective==usingExtDict) {
if (matchIndex < startIndex) {
+ assert(dictBase);
match = dictBase + matchIndex;
lowLimit = dictionary; /* required for match length counter */
} else {
@@ -1350,7 +1413,7 @@ int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutp
{
int result;
#if (LZ4_HEAPMODE)
- LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
+ LZ4_stream_t* ctxPtr = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t)); /* malloc-calloc always properly aligned */
if (ctxPtr == NULL) return 0;
#else
LZ4_stream_t ctx;
@@ -1415,15 +1478,17 @@ int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targe
* Streaming functions
********************************/
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4_stream_t* LZ4_createStream(void)
{
LZ4_stream_t* const lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
- LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal)); /* A compilation error here means LZ4_STREAMSIZE is not large enough */
+ LZ4_STATIC_ASSERT(sizeof(LZ4_stream_t) >= sizeof(LZ4_stream_t_internal));
DEBUGLOG(4, "LZ4_createStream %p", lz4s);
if (lz4s == NULL) return NULL;
LZ4_initStream(lz4s, sizeof(*lz4s));
return lz4s;
}
+#endif
static size_t LZ4_stream_t_alignment(void)
{
@@ -1457,6 +1522,7 @@ void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
}
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
{
if (!LZ4_stream) return 0; /* support free on NULL */
@@ -1464,6 +1530,7 @@ int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
FREEMEM(LZ4_stream);
return (0);
}
+#endif
#define HASH_UNIT sizeof(reg_t)
@@ -1509,8 +1576,9 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
return (int)dict->dictSize;
}
-void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream) {
- const LZ4_stream_t_internal* dictCtx = dictionaryStream == NULL ? NULL :
+void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream)
+{
+ const LZ4_stream_t_internal* dictCtx = (dictionaryStream == NULL) ? NULL :
&(dictionaryStream->internal_donotuse);
DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)",
@@ -1563,36 +1631,40 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream,
int acceleration)
{
const tableType_t tableType = byU32;
- LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
- const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+ LZ4_stream_t_internal* const streamPtr = &LZ4_stream->internal_donotuse;
+ const char* dictEnd = streamPtr->dictSize ? (const char*)streamPtr->dictionary + streamPtr->dictSize : NULL;
- DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize);
+ DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i, dictSize=%u)", inputSize, streamPtr->dictSize);
- LZ4_renormDictT(streamPtr, inputSize); /* avoid index overflow */
+ LZ4_renormDictT(streamPtr, inputSize); /* fix index overflow */
if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT;
if (acceleration > LZ4_ACCELERATION_MAX) acceleration = LZ4_ACCELERATION_MAX;
/* invalidate tiny dictionaries */
- if ( (streamPtr->dictSize-1 < 4-1) /* intentional underflow */
- && (dictEnd != (const BYTE*)source) ) {
+ if ( (streamPtr->dictSize < 4) /* tiny dictionary : not enough for a hash */
+ && (dictEnd != source) /* prefix mode */
+ && (inputSize > 0) /* tolerance : don't lose history, in case next invocation would use prefix mode */
+ && (streamPtr->dictCtx == NULL) /* usingDictCtx */
+ ) {
DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary);
+ /* remove dictionary existence from history, to employ faster prefix mode */
streamPtr->dictSize = 0;
streamPtr->dictionary = (const BYTE*)source;
- dictEnd = (const BYTE*)source;
+ dictEnd = source;
}
/* Check overlapping input/dictionary space */
- { const BYTE* sourceEnd = (const BYTE*) source + inputSize;
- if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) {
+ { const char* const sourceEnd = source + inputSize;
+ if ((sourceEnd > (const char*)streamPtr->dictionary) && (sourceEnd < dictEnd)) {
streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
- streamPtr->dictionary = dictEnd - streamPtr->dictSize;
+ streamPtr->dictionary = (const BYTE*)dictEnd - streamPtr->dictSize;
}
}
/* prefix mode : source data follows dictionary */
- if (dictEnd == (const BYTE*)source) {
+ if (dictEnd == source) {
if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
else
@@ -1618,7 +1690,7 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream,
} else {
result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
}
- } else {
+ } else { /* small data <= 4 KB */
if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
} else {
@@ -1656,21 +1728,25 @@ int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char*
/*! LZ4_saveDict() :
* If previously compressed data block is not guaranteed to remain available at its memory location,
* save it into a safer place (char* safeBuffer).
- * Note : you don't need to call LZ4_loadDict() afterwards,
- * dictionary is immediately usable, you can therefore call LZ4_compress_fast_continue().
- * Return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
+ * Note : no need to call LZ4_loadDict() afterwards, dictionary is immediately usable,
+ * one can therefore call LZ4_compress_fast_continue() right after.
+ * @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
*/
int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
{
LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
- const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
+
+ DEBUGLOG(5, "LZ4_saveDict : dictSize=%i, safeBuffer=%p", dictSize, safeBuffer);
if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */
if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; }
if (safeBuffer == NULL) assert(dictSize == 0);
- if (dictSize > 0)
- memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
+ if (dictSize > 0) {
+ const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
+ assert(dict->dictionary);
+ LZ4_memmove(safeBuffer, previousDictEnd - dictSize, (size_t)dictSize);
+ }
dict->dictionary = (const BYTE*)safeBuffer;
dict->dictSize = (U32)dictSize;
@@ -1684,39 +1760,163 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
* Decompression functions
********************************/
-typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
typedef enum { decode_full_block = 0, partial_decode = 1 } earlyEnd_directive;
#undef MIN
#define MIN(a,b) ( (a) < (b) ? (a) : (b) )
+
+/* variant for decompress_unsafe()
+ * does not know end of input
+ * presumes input is well formed
+ * note : will consume at least one byte */
+size_t read_long_length_no_check(const BYTE** pp)
+{
+ size_t b, l = 0;
+ do { b = **pp; (*pp)++; l += b; } while (b==255);
+ DEBUGLOG(6, "read_long_length_no_check: +length=%zu using %zu input bytes", l, l/255 + 1)
+ return l;
+}
+
+/* core decoder variant for LZ4_decompress_fast*()
+ * for legacy support only : these entry points are deprecated.
+ * - Presumes input is correctly formed (no defense vs malformed inputs)
+ * - Does not know input size (presume input buffer is "large enough")
+ * - Decompress a full block (only)
+ * @return : nb of bytes read from input.
+ * Note : this variant is not optimized for speed, just for maintenance.
+ * the goal is to remove support of decompress_fast*() variants by v2.0
+**/
+LZ4_FORCE_INLINE int
+LZ4_decompress_unsafe_generic(
+ const BYTE* const istart,
+ BYTE* const ostart,
+ int decompressedSize,
+
+ size_t prefixSize,
+ const BYTE* const dictStart, /* only if dict==usingExtDict */
+ const size_t dictSize /* note: =0 if dictStart==NULL */
+ )
+{
+ const BYTE* ip = istart;
+ BYTE* op = (BYTE*)ostart;
+ BYTE* const oend = ostart + decompressedSize;
+ const BYTE* const prefixStart = ostart - prefixSize;
+
+ DEBUGLOG(5, "LZ4_decompress_unsafe_generic");
+ if (dictStart == NULL) assert(dictSize == 0);
+
+ while (1) {
+ /* start new sequence */
+ unsigned token = *ip++;
+
+ /* literals */
+ { size_t ll = token >> ML_BITS;
+ if (ll==15) {
+ /* long literal length */
+ ll += read_long_length_no_check(&ip);
+ }
+ if ((size_t)(oend-op) < ll) return -1; /* output buffer overflow */
+ LZ4_memmove(op, ip, ll); /* support in-place decompression */
+ op += ll;
+ ip += ll;
+ if ((size_t)(oend-op) < MFLIMIT) {
+ if (op==oend) break; /* end of block */
+ DEBUGLOG(5, "invalid: literals end at distance %zi from end of block", oend-op);
+ /* incorrect end of block :
+ * last match must start at least MFLIMIT==12 bytes before end of output block */
+ return -1;
+ } }
+
+ /* match */
+ { size_t ml = token & 15;
+ size_t const offset = LZ4_readLE16(ip);
+ ip+=2;
+
+ if (ml==15) {
+ /* long literal length */
+ ml += read_long_length_no_check(&ip);
+ }
+ ml += MINMATCH;
+
+ if ((size_t)(oend-op) < ml) return -1; /* output buffer overflow */
+
+ { const BYTE* match = op - offset;
+
+ /* out of range */
+ if (offset > (size_t)(op - prefixStart) + dictSize) {
+ DEBUGLOG(6, "offset out of range");
+ return -1;
+ }
+
+ /* check special case : extDict */
+ if (offset > (size_t)(op - prefixStart)) {
+ /* extDict scenario */
+ const BYTE* const dictEnd = dictStart + dictSize;
+ const BYTE* extMatch = dictEnd - (offset - (size_t)(op-prefixStart));
+ size_t const extml = (size_t)(dictEnd - extMatch);
+ if (extml > ml) {
+ /* match entirely within extDict */
+ LZ4_memmove(op, extMatch, ml);
+ op += ml;
+ ml = 0;
+ } else {
+ /* match split between extDict & prefix */
+ LZ4_memmove(op, extMatch, extml);
+ op += extml;
+ ml -= extml;
+ }
+ match = prefixStart;
+ }
+
+ /* match copy - slow variant, supporting overlap copy */
+ { size_t u;
+ for (u=0; u<ml; u++) {
+ op[u] = match[u];
+ } } }
+ op += ml;
+ if ((size_t)(oend-op) < LASTLITERALS) {
+ DEBUGLOG(5, "invalid: match ends at distance %zi from end of block", oend-op);
+ /* incorrect end of block :
+ * last match must stop at least LASTLITERALS==5 bytes before end of output block */
+ return -1;
+ }
+ } /* match */
+ } /* main loop */
+ return (int)(ip - istart);
+}
+
+
/* 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)
-{
- U32 length = 0;
- U32 s;
- if (initial_check && unlikely((*ip) >= lencheck)) { /* overflow detection */
- *error = initial_error;
- return length;
+ * @ip : input pointer
+ * @ilimit : position after which if length is not decoded, the input is necessarily corrupted.
+ * @initial_check - check ip >= ipmax before start of loop. Returns initial_error if so.
+ * @error (output) - error code. Must be set to 0 before call.
+**/
+typedef size_t Rvl_t;
+static const Rvl_t rvl_error = (Rvl_t)(-1);
+LZ4_FORCE_INLINE Rvl_t
+read_variable_length(const BYTE** ip, const BYTE* ilimit,
+ int initial_check)
+{
+ Rvl_t s, length = 0;
+ assert(ip != NULL);
+ assert(*ip != NULL);
+ assert(ilimit != NULL);
+ if (initial_check && unlikely((*ip) >= ilimit)) { /* read limit reached */
+ return rvl_error;
}
do {
s = **ip;
(*ip)++;
length += s;
- if (loop_check && unlikely((*ip) >= lencheck)) { /* overflow detection */
- *error = loop_error;
- return length;
+ if (unlikely((*ip) > ilimit)) { /* read limit reached */
+ return rvl_error;
+ }
+ /* accumulator overflow detection (32-bit mode only) */
+ if ((sizeof(length)<8) && unlikely(length > ((Rvl_t)(-1)/2)) ) {
+ return rvl_error;
}
} while (s==255);
@@ -1736,7 +1936,6 @@ LZ4_decompress_generic(
int srcSize,
int outputSize, /* If endOnInput==endOnInputSize, this value is `dstCapacity` */
- endCondition_directive endOnInput, /* endOnOutputSize, endOnInputSize */
earlyEnd_directive partialDecoding, /* full, partial */
dict_directive dict, /* noDict, withPrefix64k, usingExtDict */
const BYTE* const lowPrefix, /* always <= dst, == dst when no prefix */
@@ -1744,7 +1943,7 @@ LZ4_decompress_generic(
const size_t dictSize /* note : = 0 if noDict */
)
{
- if (src == NULL) { return -1; }
+ if ((src == NULL) || (outputSize < 0)) { return -1; }
{ const BYTE* ip = (const BYTE*) src;
const BYTE* const iend = ip + srcSize;
@@ -1755,13 +1954,12 @@ LZ4_decompress_generic(
const BYTE* const dictEnd = (dictStart == NULL) ? NULL : dictStart + dictSize;
- const int safeDecode = (endOnInput==endOnInputSize);
- const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
+ const int checkOffset = (dictSize < (int)(64 KB));
/* Set up the "end" pointers for the shortcut. */
- const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/;
- const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/;
+ const BYTE* const shortiend = iend - 14 /*maxLL*/ - 2 /*offset*/;
+ const BYTE* const shortoend = oend - 14 /*maxLL*/ - 18 /*maxML*/;
const BYTE* match;
size_t offset;
@@ -1773,83 +1971,70 @@ LZ4_decompress_generic(
/* Special cases */
assert(lowPrefix <= op);
- if ((endOnInput) && (unlikely(outputSize==0))) {
+ if (unlikely(outputSize==0)) {
/* Empty output buffer */
if (partialDecoding) return 0;
return ((srcSize==1) && (*ip==0)) ? 0 : -1;
}
- if ((!endOnInput) && (unlikely(outputSize==0))) { return (*ip==0 ? 1 : -1); }
- if ((endOnInput) && unlikely(srcSize==0)) { return -1; }
+ if (unlikely(srcSize==0)) { return -1; }
- /* Currently the fast loop shows a regression on qualcomm arm chips. */
+ /* LZ4_FAST_DEC_LOOP:
+ * designed for modern OoO performance cpus,
+ * where copying reliably 32-bytes is preferable to an unpredictable branch.
+ * note : fast loop may show a regression for some client arm chips. */
#if LZ4_FAST_DEC_LOOP
if ((oend - op) < FASTLOOP_SAFE_DISTANCE) {
DEBUGLOG(6, "skip fast decode loop");
goto safe_decode;
}
- /* Fast loop : decode sequences as long as output < iend-FASTLOOP_SAFE_DISTANCE */
+ /* Fast loop : decode sequences as long as output < oend-FASTLOOP_SAFE_DISTANCE */
while (1) {
/* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
- if (endOnInput) { assert(ip < iend); }
+ assert(ip < iend);
token = *ip++;
length = token >> ML_BITS; /* literal length */
- assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
-
/* decode literal length */
if (length == RUN_MASK) {
- variable_length_error error = ok;
- length += read_variable_length(&ip, iend-RUN_MASK, (int)endOnInput, (int)endOnInput, &error);
- if (error == initial_error) { goto _output_error; }
- if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
- if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+ size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1);
+ if (addl == rvl_error) { goto _output_error; }
+ length += addl;
+ if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+ if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
/* copy literals */
cpy = op+length;
LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
- if (endOnInput) { /* LZ4_decompress_safe() */
- if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
- LZ4_wildCopy32(op, ip, cpy);
- } else { /* LZ4_decompress_fast() */
- if (cpy>oend-8) { goto safe_literal_copy; }
- LZ4_wildCopy8(op, ip, cpy); /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
- * it doesn't know input length, and only relies on end-of-block properties */
- }
+ if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
+ LZ4_wildCopy32(op, ip, cpy);
ip += length; op = cpy;
} else {
cpy = op+length;
- if (endOnInput) { /* LZ4_decompress_safe() */
- DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
- /* We don't need to check oend, since we check it once for each loop below */
- if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
- /* Literals can only be 14, but hope compilers optimize if we copy by a register size */
- LZ4_memcpy(op, ip, 16);
- } else { /* LZ4_decompress_fast() */
- /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
- * it doesn't know input length, and relies on end-of-block properties */
- LZ4_memcpy(op, ip, 8);
- if (length > 8) { LZ4_memcpy(op+8, ip+8, 8); }
- }
+ DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
+ /* We don't need to check oend, since we check it once for each loop below */
+ if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
+ /* Literals can only be <= 14, but hope compilers optimize better when copy by a register size */
+ LZ4_memcpy(op, ip, 16);
ip += length; op = cpy;
}
/* get offset */
offset = LZ4_readLE16(ip); ip+=2;
match = op - offset;
- assert(match <= op);
+ assert(match <= op); /* overflow check */
/* get matchlength */
length = token & ML_MASK;
if (length == ML_MASK) {
- variable_length_error error = ok;
- if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
- length += read_variable_length(&ip, iend - LASTLITERALS + 1, (int)endOnInput, 0, &error);
- if (error != ok) { goto _output_error; }
- if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
+ size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
+ if (addl == rvl_error) { goto _output_error; }
+ length += addl;
length += MINMATCH;
+ if (unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
+ if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
goto safe_match_copy;
}
@@ -1859,7 +2044,7 @@ LZ4_decompress_generic(
goto safe_match_copy;
}
- /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */
+ /* Fastpath check: skip LZ4_wildCopy32 when true */
if ((dict == withPrefix64k) || (match >= lowPrefix)) {
if (offset >= 8) {
assert(match >= lowPrefix);
@@ -1876,6 +2061,7 @@ LZ4_decompress_generic(
if (checkOffset && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
/* match starting within external dictionary */
if ((dict==usingExtDict) && (match < lowPrefix)) {
+ assert(dictEnd != NULL);
if (unlikely(op+length > oend-LASTLITERALS)) {
if (partialDecoding) {
DEBUGLOG(7, "partialDecoding: dictionary match, close to dstEnd");
@@ -1886,7 +2072,7 @@ LZ4_decompress_generic(
if (length <= (size_t)(lowPrefix-match)) {
/* match fits entirely within external dictionary : just copy */
- memmove(op, dictEnd - (lowPrefix-match), length);
+ LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
op += length;
} else {
/* match stretches into both external dictionary and current block */
@@ -1922,11 +2108,10 @@ LZ4_decompress_generic(
/* Main Loop : decode remaining sequences where output < FASTLOOP_SAFE_DISTANCE */
while (1) {
+ assert(ip < iend);
token = *ip++;
length = token >> ML_BITS; /* literal length */
- assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
-
/* A two-stage shortcut for the most common case:
* 1) If the literal length is 0..14, and there is enough space,
* enter the shortcut and copy 16 bytes on behalf of the literals
@@ -1936,11 +2121,11 @@ LZ4_decompress_generic(
* those 18 bytes earlier, upon entering the shortcut (in other words,
* there is a combined check for both stages).
*/
- if ( (endOnInput ? length != RUN_MASK : length <= 8)
+ if ( (length != RUN_MASK)
/* strictly "less than" on input, to re-enter the loop with at least one byte */
- && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) {
+ && likely((ip < shortiend) & (op <= shortoend)) ) {
/* Copy the literals */
- LZ4_memcpy(op, ip, endOnInput ? 16 : 8);
+ LZ4_memcpy(op, ip, 16);
op += length; ip += length;
/* The second stage: prepare for match copying, decode full info.
@@ -1970,11 +2155,11 @@ LZ4_decompress_generic(
/* decode literal length */
if (length == RUN_MASK) {
- variable_length_error error = ok;
- length += read_variable_length(&ip, iend-RUN_MASK, (int)endOnInput, (int)endOnInput, &error);
- if (error == initial_error) { goto _output_error; }
- if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
- if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
+ size_t const addl = read_variable_length(&ip, iend-RUN_MASK, 1);
+ if (addl == rvl_error) { goto _output_error; }
+ length += addl;
+ if (unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+ if (unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
}
/* copy literals */
@@ -1983,9 +2168,7 @@ LZ4_decompress_generic(
safe_literal_copy:
#endif
LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
- if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) )
- || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
- {
+ if ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) {
/* We've either hit the input parsing restriction or the output parsing restriction.
* In the normal scenario, decoding a full block, it must be the last sequence,
* otherwise it's an error (invalid input or dimensions).
@@ -1995,7 +2178,6 @@ LZ4_decompress_generic(
/* Since we are partial decoding we may be in this block because of the output parsing
* restriction, which is not valid since the output buffer is allowed to be undersized.
*/
- assert(endOnInput);
DEBUGLOG(7, "partialDecoding: copying literals, close to input or output end")
DEBUGLOG(7, "partialDecoding: literal length = %u", (unsigned)length);
DEBUGLOG(7, "partialDecoding: remaining space in dstBuffer : %i", (int)(oend - op));
@@ -2016,21 +2198,17 @@ LZ4_decompress_generic(
length = (size_t)(oend-op);
}
} 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))) {
+ if ((ip+length != iend) || (cpy > oend)) {
DEBUGLOG(6, "should have been last run of literals")
DEBUGLOG(6, "ip(%p) + length(%i) = %p != iend (%p)", ip, (int)length, ip+length, iend);
DEBUGLOG(6, "or cpy(%p) > oend(%p)", cpy, oend);
goto _output_error;
}
}
- memmove(op, ip, length); /* supports overlapping memory regions; only matters for in-place decompression scenarios */
+ LZ4_memmove(op, ip, length); /* supports overlapping memory regions, for in-place decompression scenarios */
ip += length;
op += length;
/* Necessarily EOF when !partialDecoding.
@@ -2042,7 +2220,7 @@ LZ4_decompress_generic(
break;
}
} else {
- LZ4_wildCopy8(op, ip, cpy); /* may overwrite up to WILDCOPYLENGTH beyond cpy */
+ LZ4_wildCopy8(op, ip, cpy); /* can overwrite up to 8 bytes beyond cpy */
ip += length; op = cpy;
}
@@ -2055,10 +2233,10 @@ LZ4_decompress_generic(
_copy_match:
if (length == ML_MASK) {
- variable_length_error error = ok;
- length += read_variable_length(&ip, iend - LASTLITERALS + 1, (int)endOnInput, 0, &error);
- if (error != ok) goto _output_error;
- if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */
+ size_t const addl = read_variable_length(&ip, iend - LASTLITERALS + 1, 0);
+ if (addl == rvl_error) { goto _output_error; }
+ length += addl;
+ if (unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error; /* overflow detection */
}
length += MINMATCH;
@@ -2068,6 +2246,7 @@ LZ4_decompress_generic(
if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error; /* Error : offset outside buffers */
/* match starting within external dictionary */
if ((dict==usingExtDict) && (match < lowPrefix)) {
+ assert(dictEnd != NULL);
if (unlikely(op+length > oend-LASTLITERALS)) {
if (partialDecoding) length = MIN(length, (size_t)(oend-op));
else goto _output_error; /* doesn't respect parsing restriction */
@@ -2075,7 +2254,7 @@ LZ4_decompress_generic(
if (length <= (size_t)(lowPrefix-match)) {
/* match fits entirely within external dictionary : just copy */
- memmove(op, dictEnd - (lowPrefix-match), length);
+ LZ4_memmove(op, dictEnd - (lowPrefix-match), length);
op += length;
} else {
/* match stretches into both external dictionary and current block */
@@ -2146,12 +2325,8 @@ LZ4_decompress_generic(
}
/* end of decoding */
- if (endOnInput) {
- DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst));
- return (int) (((char*)op)-dst); /* Nb of output bytes decoded */
- } else {
- return (int) (((const char*)ip)-src); /* Nb of input bytes read */
- }
+ DEBUGLOG(5, "decoded %i bytes", (int) (((char*)op)-dst));
+ return (int) (((char*)op)-dst); /* Nb of output bytes decoded */
/* Overflow error detected */
_output_error:
@@ -2166,7 +2341,7 @@ LZ4_FORCE_O2
int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
- endOnInputSize, decode_full_block, noDict,
+ decode_full_block, noDict,
(BYTE*)dest, NULL, 0);
}
@@ -2175,16 +2350,17 @@ int LZ4_decompress_safe_partial(const char* src, char* dst, int compressedSize,
{
dstCapacity = MIN(targetOutputSize, dstCapacity);
return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity,
- endOnInputSize, partial_decode,
+ partial_decode,
noDict, (BYTE*)dst, NULL, 0);
}
LZ4_FORCE_O2
int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
{
- return LZ4_decompress_generic(source, dest, 0, originalSize,
- endOnOutputSize, decode_full_block, withPrefix64k,
- (BYTE*)dest - 64 KB, NULL, 0);
+ DEBUGLOG(5, "LZ4_decompress_fast");
+ return LZ4_decompress_unsafe_generic(
+ (const BYTE*)source, (BYTE*)dest, originalSize,
+ 0, NULL, 0);
}
/*===== Instantiate a few more decoding cases, used more than once. =====*/
@@ -2193,16 +2369,25 @@ LZ4_FORCE_O2 /* Exported, an obsolete API function. */
int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
- endOnInputSize, decode_full_block, withPrefix64k,
+ decode_full_block, withPrefix64k,
+ (BYTE*)dest - 64 KB, NULL, 0);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_safe_partial_withPrefix64k(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity)
+{
+ dstCapacity = MIN(targetOutputSize, dstCapacity);
+ return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
+ partial_decode, withPrefix64k,
(BYTE*)dest - 64 KB, NULL, 0);
}
/* Another obsolete API function, paired with the previous one. */
int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
{
- /* LZ4_decompress_fast doesn't validate match offsets,
- * and thus serves well with any prefixed dictionary. */
- return LZ4_decompress_fast(source, dest, originalSize);
+ return LZ4_decompress_unsafe_generic(
+ (const BYTE*)source, (BYTE*)dest, originalSize,
+ 64 KB, NULL, 0);
}
LZ4_FORCE_O2
@@ -2210,7 +2395,17 @@ static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, i
size_t prefixSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
- endOnInputSize, decode_full_block, noDict,
+ decode_full_block, noDict,
+ (BYTE*)dest-prefixSize, NULL, 0);
+}
+
+LZ4_FORCE_O2
+static int LZ4_decompress_safe_partial_withSmallPrefix(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity,
+ size_t prefixSize)
+{
+ dstCapacity = MIN(targetOutputSize, dstCapacity);
+ return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
+ partial_decode, noDict,
(BYTE*)dest-prefixSize, NULL, 0);
}
@@ -2220,7 +2415,18 @@ int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
const void* dictStart, size_t dictSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
- endOnInputSize, decode_full_block, usingExtDict,
+ decode_full_block, usingExtDict,
+ (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+LZ4_FORCE_O2
+int LZ4_decompress_safe_partial_forceExtDict(const char* source, char* dest,
+ int compressedSize, int targetOutputSize, int dstCapacity,
+ const void* dictStart, size_t dictSize)
+{
+ dstCapacity = MIN(targetOutputSize, dstCapacity);
+ return LZ4_decompress_generic(source, dest, compressedSize, dstCapacity,
+ partial_decode, usingExtDict,
(BYTE*)dest, (const BYTE*)dictStart, dictSize);
}
@@ -2228,9 +2434,9 @@ LZ4_FORCE_O2
static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize,
const void* dictStart, size_t dictSize)
{
- return LZ4_decompress_generic(source, dest, 0, originalSize,
- endOnOutputSize, decode_full_block, usingExtDict,
- (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+ return LZ4_decompress_unsafe_generic(
+ (const BYTE*)source, (BYTE*)dest, originalSize,
+ 0, (const BYTE*)dictStart, dictSize);
}
/* The "double dictionary" mode, for use with e.g. ring buffers: the first part
@@ -2242,26 +2448,17 @@ int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compresse
size_t prefixSize, const void* dictStart, size_t dictSize)
{
return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
- endOnInputSize, decode_full_block, usingExtDict,
- (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
-}
-
-LZ4_FORCE_INLINE
-int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalSize,
- size_t prefixSize, const void* dictStart, size_t dictSize)
-{
- return LZ4_decompress_generic(source, dest, 0, originalSize,
- endOnOutputSize, decode_full_block, usingExtDict,
+ decode_full_block, usingExtDict,
(BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
}
/*===== streaming decompression functions =====*/
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4_streamDecode_t* LZ4_createStreamDecode(void)
{
- LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
- LZ4_STATIC_ASSERT(LZ4_STREAMDECODESIZE >= sizeof(LZ4_streamDecode_t_internal)); /* A compilation error here means LZ4_STREAMDECODESIZE is not large enough */
- return lz4s;
+ LZ4_STATIC_ASSERT(sizeof(LZ4_streamDecode_t) >= sizeof(LZ4_streamDecode_t_internal));
+ return (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
}
int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
@@ -2270,6 +2467,7 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
FREEMEM(LZ4_stream);
return 0;
}
+#endif
/*! LZ4_setStreamDecode() :
* Use this function to instruct where to find the dictionary.
@@ -2280,8 +2478,13 @@ int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
{
LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
- lz4sd->prefixSize = (size_t) dictSize;
- lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+ lz4sd->prefixSize = (size_t)dictSize;
+ if (dictSize) {
+ assert(dictionary != NULL);
+ lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
+ } else {
+ lz4sd->prefixEnd = (const BYTE*) dictionary;
+ }
lz4sd->externalDict = NULL;
lz4sd->extDictSize = 0;
return 1;
@@ -2353,29 +2556,35 @@ int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const ch
return result;
}
-LZ4_FORCE_O2
-int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
+LZ4_FORCE_O2 int
+LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode,
+ const char* source, char* dest, int originalSize)
{
- LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
+ LZ4_streamDecode_t_internal* const lz4sd =
+ (assert(LZ4_streamDecode!=NULL), &LZ4_streamDecode->internal_donotuse);
int result;
+
+ DEBUGLOG(5, "LZ4_decompress_fast_continue (toDecodeSize=%i)", originalSize);
assert(originalSize >= 0);
if (lz4sd->prefixSize == 0) {
+ DEBUGLOG(5, "first invocation : no prefix nor extDict");
assert(lz4sd->extDictSize == 0);
result = LZ4_decompress_fast(source, dest, originalSize);
if (result <= 0) return result;
lz4sd->prefixSize = (size_t)originalSize;
lz4sd->prefixEnd = (BYTE*)dest + originalSize;
} else if (lz4sd->prefixEnd == (BYTE*)dest) {
- if (lz4sd->prefixSize >= 64 KB - 1 || lz4sd->extDictSize == 0)
- result = LZ4_decompress_fast(source, dest, originalSize);
- else
- result = LZ4_decompress_fast_doubleDict(source, dest, originalSize,
- lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+ DEBUGLOG(5, "continue using existing prefix");
+ result = LZ4_decompress_unsafe_generic(
+ (const BYTE*)source, (BYTE*)dest, originalSize,
+ lz4sd->prefixSize,
+ lz4sd->externalDict, lz4sd->extDictSize);
if (result <= 0) return result;
lz4sd->prefixSize += (size_t)originalSize;
lz4sd->prefixEnd += originalSize;
} else {
+ DEBUGLOG(5, "prefix becomes extDict");
lz4sd->extDictSize = lz4sd->prefixSize;
lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
result = LZ4_decompress_fast_extDict(source, dest, originalSize,
@@ -2411,10 +2620,27 @@ int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressed
return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize);
}
+int LZ4_decompress_safe_partial_usingDict(const char* source, char* dest, int compressedSize, int targetOutputSize, int dstCapacity, const char* dictStart, int dictSize)
+{
+ if (dictSize==0)
+ return LZ4_decompress_safe_partial(source, dest, compressedSize, targetOutputSize, dstCapacity);
+ if (dictStart+dictSize == dest) {
+ if (dictSize >= 64 KB - 1) {
+ return LZ4_decompress_safe_partial_withPrefix64k(source, dest, compressedSize, targetOutputSize, dstCapacity);
+ }
+ assert(dictSize >= 0);
+ return LZ4_decompress_safe_partial_withSmallPrefix(source, dest, compressedSize, targetOutputSize, dstCapacity, (size_t)dictSize);
+ }
+ assert(dictSize >= 0);
+ return LZ4_decompress_safe_partial_forceExtDict(source, dest, compressedSize, targetOutputSize, dstCapacity, dictStart, (size_t)dictSize);
+}
+
int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
{
if (dictSize==0 || dictStart+dictSize == dest)
- return LZ4_decompress_fast(source, dest, originalSize);
+ return LZ4_decompress_unsafe_generic(
+ (const BYTE*)source, (BYTE*)dest, originalSize,
+ (size_t)dictSize, NULL, 0);
assert(dictSize >= 0);
return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize);
}
@@ -2466,7 +2692,7 @@ int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize,
/* Obsolete Streaming functions */
-int LZ4_sizeofStreamState(void) { return LZ4_STREAMSIZE; }
+int LZ4_sizeofStreamState(void) { return sizeof(LZ4_stream_t); }
int LZ4_resetStreamState(void* state, char* inputBuffer)
{
@@ -2475,11 +2701,13 @@ int LZ4_resetStreamState(void* state, char* inputBuffer)
return 0;
}
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
void* LZ4_create (char* inputBuffer)
{
(void)inputBuffer;
return LZ4_createStream();
}
+#endif
char* LZ4_slideInputBuffer (void* state)
{
diff --git a/public/common/tracy_lz4.hpp b/public/common/tracy_lz4.hpp
index 1ccdcff1..672c2feb 100644
--- a/public/common/tracy_lz4.hpp
+++ b/public/common/tracy_lz4.hpp
@@ -1,7 +1,7 @@
/*
* LZ4 - Fast LZ compression algorithm
* Header File
- * Copyright (C) 2011-present, Yann Collet.
+ * Copyright (C) 2011-2020, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
@@ -95,39 +95,80 @@
# define LZ4LIB_API LZ4LIB_VISIBILITY
#endif
+/*! LZ4_FREESTANDING :
+ * When this macro is set to 1, it enables "freestanding mode" that is
+ * suitable for typical freestanding environment which doesn't support
+ * standard C library.
+ *
+ * - LZ4_FREESTANDING is a compile-time switch.
+ * - It requires the following macros to be defined:
+ * LZ4_memcpy, LZ4_memmove, LZ4_memset.
+ * - It only enables LZ4/HC functions which don't use heap.
+ * All LZ4F_* functions are not supported.
+ * - See tests/freestanding.c to check its basic setup.
+ */
+#if defined(LZ4_FREESTANDING) && (LZ4_FREESTANDING == 1)
+# define LZ4_HEAPMODE 0
+# define LZ4HC_HEAPMODE 0
+# define LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION 1
+# if !defined(LZ4_memcpy)
+# error "LZ4_FREESTANDING requires macro 'LZ4_memcpy'."
+# endif
+# if !defined(LZ4_memset)
+# error "LZ4_FREESTANDING requires macro 'LZ4_memset'."
+# endif
+# if !defined(LZ4_memmove)
+# error "LZ4_FREESTANDING requires macro 'LZ4_memmove'."
+# endif
+#elif ! defined(LZ4_FREESTANDING)
+# define LZ4_FREESTANDING 0
+#endif
+
+
/*------ Version ------*/
#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */
#define LZ4_VERSION_MINOR 9 /* for new (non-breaking) interface capabilities */
-#define LZ4_VERSION_RELEASE 3 /* for tweaks, bug-fixes, or development */
+#define LZ4_VERSION_RELEASE 4 /* for tweaks, bug-fixes, or development */
#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
#define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE
#define LZ4_QUOTE(str) #str
#define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
-#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
+#define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION) /* requires v1.7.3+ */
namespace tracy
{
-LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version */
-LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version */
+LZ4LIB_API int LZ4_versionNumber (void); /**< library version number; useful to check dll version; requires v1.3.0+ */
+LZ4LIB_API const char* LZ4_versionString (void); /**< library version string; useful to check dll version; requires v1.7.5+ */
/*-************************************
* Tuning parameter
**************************************/
+#define LZ4_MEMORY_USAGE_MIN 10
+#define LZ4_MEMORY_USAGE_DEFAULT 14
+#define LZ4_MEMORY_USAGE_MAX 20
+
/*!
* LZ4_MEMORY_USAGE :
- * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
- * Increasing memory usage improves compression ratio.
- * Reduced memory usage may improve speed, thanks to better cache locality.
+ * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; )
+ * Increasing memory usage improves compression ratio, at the cost of speed.
+ * Reduced memory usage may improve speed at the cost of ratio, thanks to better cache locality.
* Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
*/
#ifndef LZ4_MEMORY_USAGE
-# define LZ4_MEMORY_USAGE 14
+# define LZ4_MEMORY_USAGE LZ4_MEMORY_USAGE_DEFAULT
+#endif
+
+#if (LZ4_MEMORY_USAGE < LZ4_MEMORY_USAGE_MIN)
+# error "LZ4_MEMORY_USAGE is too small !"
#endif
+#if (LZ4_MEMORY_USAGE > LZ4_MEMORY_USAGE_MAX)
+# error "LZ4_MEMORY_USAGE is too large !"
+#endif
/*-************************************
* Simple Functions
@@ -271,8 +312,25 @@ LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcS
***********************************************/
typedef union LZ4_stream_u LZ4_stream_t; /* incomplete type (defined later) */
+/**
+ Note about RC_INVOKED
+
+ - RC_INVOKED is predefined symbol of rc.exe (the resource compiler which is part of MSVC/Visual Studio).
+ https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros
+
+ - Since rc.exe is a legacy compiler, it truncates long symbol (> 30 chars)
+ and reports warning "RC4011: identifier truncated".
+
+ - To eliminate the warning, we surround long preprocessor symbol with
+ "#if !defined(RC_INVOKED) ... #endif" block that means
+ "skip this block when rc.exe is trying to read it".
+*/
+#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4LIB_API LZ4_stream_t* LZ4_createStream(void);
LZ4LIB_API int LZ4_freeStream (LZ4_stream_t* streamPtr);
+#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */
+#endif
/*! LZ4_resetStream_fast() : v1.9.0+
* Use this to prepare an LZ4_stream_t for a new chain of dependent blocks
@@ -356,8 +414,12 @@ typedef union LZ4_streamDecode_u LZ4_streamDecode_t; /* tracking context */
* creation / destruction of streaming decompression tracking context.
* A tracking context can be re-used multiple times.
*/
+#if !defined(RC_INVOKED) /* https://docs.microsoft.com/en-us/windows/win32/menurc/predefined-macros */
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
LZ4LIB_API int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
+#endif /* !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION) */
+#endif
/*! LZ4_setStreamDecode() :
* An LZ4_streamDecode_t context can be allocated once and re-used multiple times.
@@ -407,7 +469,10 @@ LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize);
* save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression,
* then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block.
*/
-LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity);
+LZ4LIB_API int
+LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode,
+ const char* src, char* dst,
+ int srcSize, int dstCapacity);
/*! LZ4_decompress_*_usingDict() :
@@ -418,7 +483,16 @@ LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecod
* Performance tip : Decompression speed can be substantially increased
* when dst == dictStart + dictSize.
*/
-LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
+LZ4LIB_API int
+LZ4_decompress_safe_usingDict(const char* src, char* dst,
+ int srcSize, int dstCapacity,
+ const char* dictStart, int dictSize);
+
+LZ4LIB_API int
+LZ4_decompress_safe_partial_usingDict(const char* src, char* dst,
+ int compressedSize,
+ int targetOutputSize, int maxOutputSize,
+ const char* dictStart, int dictSize);
}
@@ -501,13 +575,15 @@ LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const c
* stream (and source buffer) must remain in-place / accessible / unchanged
* through the completion of the first compression call on the stream.
*/
-LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream);
+LZ4LIB_STATIC_API void
+LZ4_attach_dictionary(LZ4_stream_t* workingStream,
+ const LZ4_stream_t* dictionaryStream);
/*! In-place compression and decompression
*
* It's possible to have input and output sharing the same buffer,
- * for highly contrained memory environments.
+ * for highly constrained memory environments.
* In both cases, it requires input to lay at the end of the buffer,
* and decompression to start at beginning of the buffer.
* Buffer size must feature some margin, hence be larger than final size.
@@ -570,6 +646,8 @@ LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const
#endif /* LZ4_STATIC_3504398509 */
#endif /* LZ4_STATIC_LINKING_ONLY */
+
+
#ifndef TRACY_LZ4_H_98237428734687
#define TRACY_LZ4_H_98237428734687
@@ -599,38 +677,26 @@ namespace tracy
typedef unsigned int LZ4_u32;
#endif
+/*! LZ4_stream_t :
+ * Never ever use below internal definitions directly !
+ * These definitions are not API/ABI safe, and may change in future versions.
+ * If you need static allocation, declare or allocate an LZ4_stream_t object.
+**/
+
typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
struct LZ4_stream_t_internal {
LZ4_u32 hashTable[LZ4_HASH_SIZE_U32];
- LZ4_u32 currentOffset;
- LZ4_u32 tableType;
const LZ4_byte* dictionary;
const LZ4_stream_t_internal* dictCtx;
+ LZ4_u32 currentOffset;
+ LZ4_u32 tableType;
LZ4_u32 dictSize;
+ /* Implicit padding to ensure structure is aligned */
};
-typedef struct {
- const LZ4_byte* externalDict;
- size_t extDictSize;
- const LZ4_byte* prefixEnd;
- size_t prefixSize;
-} LZ4_streamDecode_t_internal;
-
-
-/*! LZ4_stream_t :
- * Do not use below internal definitions directly !
- * Declare or allocate an LZ4_stream_t instead.
- * LZ4_stream_t can also be created using LZ4_createStream(), which is recommended.
- * The structure definition can be convenient for static allocation
- * (on stack, or as part of larger structure).
- * Init this structure with LZ4_initStream() before first use.
- * note : only use this definition in association with static linking !
- * this definition is not API/ABI safe, and may change in future versions.
- */
-#define LZ4_STREAMSIZE 16416 /* static size, for inter-version compatibility */
-#define LZ4_STREAMSIZE_VOIDP (LZ4_STREAMSIZE / sizeof(void*))
+#define LZ4_STREAM_MINSIZE ((1UL << LZ4_MEMORY_USAGE) + 32) /* static size, for inter-version compatibility */
union LZ4_stream_u {
- void* table[LZ4_STREAMSIZE_VOIDP];
+ char minStateSize[LZ4_STREAM_MINSIZE];
LZ4_stream_t_internal internal_donotuse;
}; /* previously typedef'd to LZ4_stream_t */
@@ -648,21 +714,25 @@ union LZ4_stream_u {
* In which case, the function will @return NULL.
* Note2: An LZ4_stream_t structure guarantees correct alignment and size.
* Note3: Before v1.9.0, use LZ4_resetStream() instead
- */
+**/
LZ4LIB_API LZ4_stream_t* LZ4_initStream (void* buffer, size_t size);
/*! LZ4_streamDecode_t :
- * information structure to track an LZ4 stream during decompression.
- * init this structure using LZ4_setStreamDecode() before first use.
- * note : only use in association with static linking !
- * this definition is not API/ABI safe,
- * and may change in a future version !
- */
-#define LZ4_STREAMDECODESIZE_U64 (4 + ((sizeof(void*)==16) ? 2 : 0) /*AS-400*/ )
-#define LZ4_STREAMDECODESIZE (LZ4_STREAMDECODESIZE_U64 * sizeof(unsigned long long))
+ * Never ever use below internal definitions directly !
+ * These definitions are not API/ABI safe, and may change in future versions.
+ * If you need static allocation, declare or allocate an LZ4_streamDecode_t object.
+**/
+typedef struct {
+ const LZ4_byte* externalDict;
+ const LZ4_byte* prefixEnd;
+ size_t extDictSize;
+ size_t prefixSize;
+} LZ4_streamDecode_t_internal;
+
+#define LZ4_STREAMDECODE_MINSIZE 32
union LZ4_streamDecode_u {
- unsigned long long table[LZ4_STREAMDECODESIZE_U64];
+ char minStateSize[LZ4_STREAMDECODE_MINSIZE];
LZ4_streamDecode_t_internal internal_donotuse;
} ; /* previously typedef'd to LZ4_streamDecode_t */
diff --git a/public/common/tracy_lz4hc.cpp b/public/common/tracy_lz4hc.cpp
index 9c899b82..eec7239e 100644
--- a/public/common/tracy_lz4hc.cpp
+++ b/public/common/tracy_lz4hc.cpp
@@ -1,6 +1,6 @@
/*
LZ4 HC - High Compression Mode of LZ4
- Copyright (C) 2011-2017, Yann Collet.
+ Copyright (C) 2011-2020, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
@@ -42,7 +42,7 @@
* Select how default compression function will allocate workplace memory,
* in stack (0:fastest), or in heap (1:requires malloc()).
* Since workplace is rather large, heap mode is recommended.
- */
+**/
#ifndef LZ4HC_HEAPMODE
# define LZ4HC_HEAPMODE 1
#endif
@@ -102,18 +102,20 @@ static void LZ4HC_clearTables (LZ4HC_CCtx_internal* hc4)
static void LZ4HC_init_internal (LZ4HC_CCtx_internal* hc4, const BYTE* start)
{
- uptrval startingOffset = (uptrval)(hc4->end - hc4->base);
- if (startingOffset > 1 GB) {
+ size_t const bufferSize = (size_t)(hc4->end - hc4->prefixStart);
+ size_t newStartingOffset = bufferSize + hc4->dictLimit;
+ assert(newStartingOffset >= bufferSize); /* check overflow */
+ if (newStartingOffset > 1 GB) {
LZ4HC_clearTables(hc4);
- startingOffset = 0;
+ newStartingOffset = 0;
}
- startingOffset += 64 KB;
- hc4->nextToUpdate = (U32) startingOffset;
- hc4->base = start - startingOffset;
+ newStartingOffset += 64 KB;
+ hc4->nextToUpdate = (U32)newStartingOffset;
+ hc4->prefixStart = start;
hc4->end = start;
- hc4->dictBase = start - startingOffset;
- hc4->dictLimit = (U32) startingOffset;
- hc4->lowLimit = (U32) startingOffset;
+ hc4->dictStart = start;
+ hc4->dictLimit = (U32)newStartingOffset;
+ hc4->lowLimit = (U32)newStartingOffset;
}
@@ -122,12 +124,15 @@ LZ4_FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip)
{
U16* const chainTable = hc4->chainTable;
U32* const hashTable = hc4->hashTable;
- const BYTE* const base = hc4->base;
- U32 const target = (U32)(ip - base);
+ const BYTE* const prefixPtr = hc4->prefixStart;
+ U32 const prefixIdx = hc4->dictLimit;
+ U32 const target = (U32)(ip - prefixPtr) + prefixIdx;
U32 idx = hc4->nextToUpdate;
+ assert(ip >= prefixPtr);
+ assert(target >= prefixIdx);
while (idx < target) {
- U32 const h = LZ4HC_hashPtr(base+idx);
+ U32 const h = LZ4HC_hashPtr(prefixPtr+idx-prefixIdx);
size_t delta = idx - hashTable[h];
if (delta>LZ4_DISTANCE_MAX) delta = LZ4_DISTANCE_MAX;
DELTANEXTU16(chainTable, idx) = (U16)delta;
@@ -196,15 +201,14 @@ LZ4HC_countPattern(const BYTE* ip, const BYTE* const iEnd, U32 const pattern32)
BYTE const byte = (BYTE)(pattern >> bitOffset);
if (*ip != byte) break;
ip ++; bitOffset -= 8;
- }
- }
+ } }
return (unsigned)(ip - iStart);
}
/* LZ4HC_reverseCountPattern() :
* pattern must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!)
- * read using natural platform endianess */
+ * read using natural platform endianness */
static unsigned
LZ4HC_reverseCountPattern(const BYTE* ip, const BYTE* const iLow, U32 pattern)
{
@@ -214,7 +218,7 @@ LZ4HC_reverseCountPattern(const BYTE* ip, const BYTE* const iLow, U32 pattern)
if (LZ4_read32(ip-4) != pattern) break;
ip -= 4;
}
- { const BYTE* bytePtr = (const BYTE*)(&pattern) + 3; /* works for any endianess */
+ { const BYTE* bytePtr = (const BYTE*)(&pattern) + 3; /* works for any endianness */
while (likely(ip>iLow)) {
if (ip[-1] != *bytePtr) break;
ip--; bytePtr--;
@@ -237,28 +241,28 @@ typedef enum { favorCompressionRatio=0, favorDecompressionSpeed } HCfavor_e;
LZ4_FORCE_INLINE int
LZ4HC_InsertAndGetWiderMatch (
- LZ4HC_CCtx_internal* hc4,
- const BYTE* const ip,
- const BYTE* const iLowLimit,
- const BYTE* const iHighLimit,
- int longest,
- const BYTE** matchpos,
- const BYTE** startpos,
- const int maxNbAttempts,
- const int patternAnalysis,
- const int chainSwap,
- const dictCtx_directive dict,
- const HCfavor_e favorDecSpeed)
+ LZ4HC_CCtx_internal* const hc4,
+ const BYTE* const ip,
+ const BYTE* const iLowLimit, const BYTE* const iHighLimit,
+ int longest,
+ const BYTE** matchpos,
+ const BYTE** startpos,
+ const int maxNbAttempts,
+ const int patternAnalysis, const int chainSwap,
+ const dictCtx_directive dict,
+ const HCfavor_e favorDecSpeed)
{
U16* const chainTable = hc4->chainTable;
U32* const HashTable = hc4->hashTable;
const LZ4HC_CCtx_internal * const dictCtx = hc4->dictCtx;
- const BYTE* const base = hc4->base;
- const U32 dictLimit = hc4->dictLimit;
- const BYTE* const lowPrefixPtr = base + dictLimit;
- const U32 ipIndex = (U32)(ip - base);
- const U32 lowestMatchIndex = (hc4->lowLimit + (LZ4_DISTANCE_MAX + 1) > ipIndex) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX;
- const BYTE* const dictBase = hc4->dictBase;
+ const BYTE* const prefixPtr = hc4->prefixStart;
+ const U32 prefixIdx = hc4->dictLimit;
+ const U32 ipIndex = (U32)(ip - prefixPtr) + prefixIdx;
+ const int withinStartDistance = (hc4->lowLimit + (LZ4_DISTANCE_MAX + 1) > ipIndex);
+ const U32 lowestMatchIndex = (withinStartDistance) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX;
+ const BYTE* const dictStart = hc4->dictStart;
+ const U32 dictIdx = hc4->lowLimit;
+ const BYTE* const dictEnd = dictStart + prefixIdx - dictIdx;
int const lookBackLength = (int)(ip-iLowLimit);
int nbAttempts = maxNbAttempts;
U32 matchChainPos = 0;
@@ -280,14 +284,13 @@ LZ4HC_InsertAndGetWiderMatch (
assert(matchIndex < ipIndex);
if (favorDecSpeed && (ipIndex - matchIndex < 8)) {
/* do nothing */
- } else if (matchIndex >= dictLimit) { /* within current Prefix */
- const BYTE* const matchPtr = base + matchIndex;
- assert(matchPtr >= lowPrefixPtr);
+ } else if (matchIndex >= prefixIdx) { /* within current Prefix */
+ const BYTE* const matchPtr = prefixPtr + matchIndex - prefixIdx;
assert(matchPtr < ip);
assert(longest >= 1);
if (LZ4_read16(iLowLimit + longest - 1) == LZ4_read16(matchPtr - lookBackLength + longest - 1)) {
if (LZ4_read32(matchPtr) == pattern) {
- int const back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, lowPrefixPtr) : 0;
+ int const back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, prefixPtr) : 0;
matchLength = MINMATCH + (int)LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit);
matchLength -= back;
if (matchLength > longest) {
@@ -296,24 +299,25 @@ LZ4HC_InsertAndGetWiderMatch (
*startpos = ip + back;
} } }
} else { /* lowestMatchIndex <= matchIndex < dictLimit */
- const BYTE* const matchPtr = dictBase + matchIndex;
- if (LZ4_read32(matchPtr) == pattern) {
- const BYTE* const dictStart = dictBase + hc4->lowLimit;
+ const BYTE* const matchPtr = dictStart + (matchIndex - dictIdx);
+ assert(matchIndex >= dictIdx);
+ if ( likely(matchIndex <= prefixIdx - 4)
+ && (LZ4_read32(matchPtr) == pattern) ) {
int back = 0;
- const BYTE* vLimit = ip + (dictLimit - matchIndex);
+ const BYTE* vLimit = ip + (prefixIdx - matchIndex);
if (vLimit > iHighLimit) vLimit = iHighLimit;
matchLength = (int)LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH;
if ((ip+matchLength == vLimit) && (vLimit < iHighLimit))
- matchLength += LZ4_count(ip+matchLength, lowPrefixPtr, iHighLimit);
+ matchLength += LZ4_count(ip+matchLength, prefixPtr, iHighLimit);
back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictStart) : 0;
matchLength -= back;
if (matchLength > longest) {
longest = matchLength;
- *matchpos = base + matchIndex + back; /* virtual pos, relative to ip, to retrieve offset */
+ *matchpos = prefixPtr - prefixIdx + matchIndex + back; /* virtual pos, relative to ip, to retrieve offset */
*startpos = ip + back;
} } }
- if (chainSwap && matchLength==longest) { /* better match => select a better chain */
+ if (chainSwap && matchLength==longest) { /* better match => select a better chain */
assert(lookBackLength==0); /* search forward only */
if (matchIndex + (U32)longest <= ipIndex) {
int const kTrigger = 4;
@@ -329,8 +333,7 @@ LZ4HC_InsertAndGetWiderMatch (
distanceToNextMatch = candidateDist;
matchChainPos = (U32)pos;
accel = 1 << kTrigger;
- }
- }
+ } }
if (distanceToNextMatch > 1) {
if (distanceToNextMatch > matchIndex) break; /* avoid overflow */
matchIndex -= distanceToNextMatch;
@@ -350,23 +353,24 @@ LZ4HC_InsertAndGetWiderMatch (
repeat = rep_not;
} }
if ( (repeat == rep_confirmed) && (matchCandidateIdx >= lowestMatchIndex)
- && LZ4HC_protectDictEnd(dictLimit, matchCandidateIdx) ) {
- const int extDict = matchCandidateIdx < dictLimit;
- const BYTE* const matchPtr = (extDict ? dictBase : base) + matchCandidateIdx;
+ && LZ4HC_protectDictEnd(prefixIdx, matchCandidateIdx) ) {
+ const int extDict = matchCandidateIdx < prefixIdx;
+ const BYTE* const matchPtr = (extDict ? dictStart - dictIdx : prefixPtr - prefixIdx) + matchCandidateIdx;
if (LZ4_read32(matchPtr) == pattern) { /* good candidate */
- const BYTE* const dictStart = dictBase + hc4->lowLimit;
- const BYTE* const iLimit = extDict ? dictBase + dictLimit : iHighLimit;
+ const BYTE* const iLimit = extDict ? dictEnd : iHighLimit;
size_t forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iLimit, pattern) + sizeof(pattern);
if (extDict && matchPtr + forwardPatternLength == iLimit) {
U32 const rotatedPattern = LZ4HC_rotatePattern(forwardPatternLength, pattern);
- forwardPatternLength += LZ4HC_countPattern(lowPrefixPtr, iHighLimit, rotatedPattern);
+ forwardPatternLength += LZ4HC_countPattern(prefixPtr, iHighLimit, rotatedPattern);
}
- { const BYTE* const lowestMatchPtr = extDict ? dictStart : lowPrefixPtr;
+ { const BYTE* const lowestMatchPtr = extDict ? dictStart : prefixPtr;
size_t backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern);
size_t currentSegmentLength;
- if (!extDict && matchPtr - backLength == lowPrefixPtr && hc4->lowLimit < dictLimit) {
+ if (!extDict
+ && matchPtr - backLength == prefixPtr
+ && dictIdx < prefixIdx) {
U32 const rotatedPattern = LZ4HC_rotatePattern((U32)(-(int)backLength), pattern);
- backLength += LZ4HC_reverseCountPattern(dictBase + dictLimit, dictStart, rotatedPattern);
+ backLength += LZ4HC_reverseCountPattern(dictEnd, dictStart, rotatedPattern);
}
/* Limit backLength not go further than lowestMatchIndex */
backLength = matchCandidateIdx - MAX(matchCandidateIdx - (U32)backLength, lowestMatchIndex);
@@ -376,28 +380,28 @@ LZ4HC_InsertAndGetWiderMatch (
if ( (currentSegmentLength >= srcPatternLength) /* current pattern segment large enough to contain full srcPatternLength */
&& (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */
U32 const newMatchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength; /* best position, full pattern, might be followed by more match */
- if (LZ4HC_protectDictEnd(dictLimit, newMatchIndex))
+ if (LZ4HC_protectDictEnd(prefixIdx, newMatchIndex))
matchIndex = newMatchIndex;
else {
/* Can only happen if started in the prefix */
- assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict);
- matchIndex = dictLimit;
+ assert(newMatchIndex >= prefixIdx - 3 && newMatchIndex < prefixIdx && !extDict);
+ matchIndex = prefixIdx;
}
} else {
U32 const newMatchIndex = matchCandidateIdx - (U32)backLength; /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */
- if (!LZ4HC_protectDictEnd(dictLimit, newMatchIndex)) {
- assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict);
- matchIndex = dictLimit;
+ if (!LZ4HC_protectDictEnd(prefixIdx, newMatchIndex)) {
+ assert(newMatchIndex >= prefixIdx - 3 && newMatchIndex < prefixIdx && !extDict);
+ matchIndex = prefixIdx;
} else {
matchIndex = newMatchIndex;
if (lookBackLength==0) { /* no back possible */
size_t const maxML = MIN(currentSegmentLength, srcPatternLength);
if ((size_t)longest < maxML) {
- assert(base + matchIndex != ip);
- if ((size_t)(ip - base) - matchIndex > LZ4_DISTANCE_MAX) break;
+ assert(prefixPtr - prefixIdx + matchIndex != ip);
+ if ((size_t)(ip - prefixPtr) + prefixIdx - matchIndex > LZ4_DISTANCE_MAX) break;
assert(maxML < 2 GB);
longest = (int)maxML;
- *matchpos = base + matchIndex; /* virtual pos, relative to ip, to retrieve offset */
+ *matchpos = prefixPtr - prefixIdx + matchIndex; /* virtual pos, relative to ip, to retrieve offset */
*startpos = ip;
}
{ U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex);
@@ -416,12 +420,12 @@ LZ4HC_InsertAndGetWiderMatch (
if ( dict == usingDictCtxHc
&& nbAttempts > 0
&& ipIndex - lowestMatchIndex < LZ4_DISTANCE_MAX) {
- size_t const dictEndOffset = (size_t)(dictCtx->end - dictCtx->base);
+ size_t const dictEndOffset = (size_t)(dictCtx->end - dictCtx->prefixStart) + dictCtx->dictLimit;
U32 dictMatchIndex = dictCtx->hashTable[LZ4HC_hashPtr(ip)];
assert(dictEndOffset <= 1 GB);
matchIndex = dictMatchIndex + lowestMatchIndex - (U32)dictEndOffset;
while (ipIndex - matchIndex <= LZ4_DISTANCE_MAX && nbAttempts--) {
- const BYTE* const matchPtr = dictCtx->base + dictMatchIndex;
+ const BYTE* const matchPtr = dictCtx->prefixStart - dictCtx->dictLimit + dictMatchIndex;
if (LZ4_read32(matchPtr) == pattern) {
int mlt;
@@ -429,11 +433,11 @@ LZ4HC_InsertAndGetWiderMatch (
const BYTE* vLimit = ip + (dictEndOffset - dictMatchIndex);
if (vLimit > iHighLimit) vLimit = iHighLimit;
mlt = (int)LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH;
- back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictCtx->base + dictCtx->dictLimit) : 0;
+ back = lookBackLength ? LZ4HC_countBack(ip, matchPtr, iLowLimit, dictCtx->prefixStart) : 0;
mlt -= back;
if (mlt > longest) {
longest = mlt;
- *matchpos = base + matchIndex + back;
+ *matchpos = prefixPtr - prefixIdx + matchIndex + back;
*startpos = ip + back;
} }
@@ -445,13 +449,13 @@ LZ4HC_InsertAndGetWiderMatch (
return longest;
}
-LZ4_FORCE_INLINE
-int LZ4HC_InsertAndFindBestMatch(LZ4HC_CCtx_internal* const hc4, /* Index table will be updated */
- const BYTE* const ip, const BYTE* const iLimit,
- const BYTE** matchpos,
- const int maxNbAttempts,
- const int patternAnalysis,
- const dictCtx_directive dict)
+LZ4_FORCE_INLINE int
+LZ4HC_InsertAndFindBestMatch(LZ4HC_CCtx_internal* const hc4, /* Index table will be updated */
+ const BYTE* const ip, const BYTE* const iLimit,
+ const BYTE** matchpos,
+ const int maxNbAttempts,
+ const int patternAnalysis,
+ const dictCtx_directive dict)
{
const BYTE* uselessPtr = ip;
/* note : LZ4HC_InsertAndGetWiderMatch() is able to modify the starting position of a match (*startpos),
@@ -754,7 +758,7 @@ _last_literals:
} else {
*op++ = (BYTE)(lastRunSize << ML_BITS);
}
- memcpy(op, anchor, lastRunSize);
+ LZ4_memcpy(op, anchor, lastRunSize);
op += lastRunSize;
}
@@ -887,13 +891,13 @@ LZ4HC_compress_generic_dictCtx (
limitedOutput_directive limit
)
{
- const size_t position = (size_t)(ctx->end - ctx->base) - ctx->lowLimit;
+ const size_t position = (size_t)(ctx->end - ctx->prefixStart) + (ctx->dictLimit - ctx->lowLimit);
assert(ctx->dictCtx != NULL);
if (position >= 64 KB) {
ctx->dictCtx = NULL;
return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit);
} else if (position == 0 && *srcSizePtr > 4 KB) {
- memcpy(ctx, ctx->dictCtx, sizeof(LZ4HC_CCtx_internal));
+ LZ4_memcpy(ctx, ctx->dictCtx, sizeof(LZ4HC_CCtx_internal));
LZ4HC_setExternalDict(ctx, (const BYTE *)src);
ctx->compressionLevel = (short)cLevel;
return LZ4HC_compress_generic_noDictCtx(ctx, src, dst, srcSizePtr, dstCapacity, cLevel, limit);
@@ -956,13 +960,15 @@ int LZ4_compress_HC_extStateHC (void* state, const char* src, char* dst, int src
int LZ4_compress_HC(const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel)
{
+ int cSize;
#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
LZ4_streamHC_t* const statePtr = (LZ4_streamHC_t*)ALLOC(sizeof(LZ4_streamHC_t));
+ if (statePtr==NULL) return 0;
#else
LZ4_streamHC_t state;
LZ4_streamHC_t* const statePtr = &state;
#endif
- int const cSize = LZ4_compress_HC_extStateHC(statePtr, src, dst, srcSize, dstCapacity, compressionLevel);
+ cSize = LZ4_compress_HC_extStateHC(statePtr, src, dst, srcSize, dstCapacity, compressionLevel);
#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
FREEMEM(statePtr);
#endif
@@ -985,6 +991,7 @@ int LZ4_compress_HC_destSize(void* state, const char* source, char* dest, int* s
* Streaming Functions
**************************************/
/* allocation */
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4_streamHC_t* LZ4_createStreamHC(void)
{
LZ4_streamHC_t* const state =
@@ -1001,13 +1008,12 @@ int LZ4_freeStreamHC (LZ4_streamHC_t* LZ4_streamHCPtr)
FREEMEM(LZ4_streamHCPtr);
return 0;
}
+#endif
LZ4_streamHC_t* LZ4_initStreamHC (void* buffer, size_t size)
{
LZ4_streamHC_t* const LZ4_streamHCPtr = (LZ4_streamHC_t*)buffer;
- /* if compilation fails here, LZ4_STREAMHCSIZE must be increased */
- LZ4_STATIC_ASSERT(sizeof(LZ4HC_CCtx_internal) <= LZ4_STREAMHCSIZE);
DEBUGLOG(4, "LZ4_initStreamHC(%p, %u)", buffer, (unsigned)size);
/* check conditions */
if (buffer == NULL) return NULL;
@@ -1033,9 +1039,13 @@ void LZ4_resetStreamHC_fast (LZ4_streamHC_t* LZ4_streamHCPtr, int compressionLev
if (LZ4_streamHCPtr->internal_donotuse.dirty) {
LZ4_initStreamHC(LZ4_streamHCPtr, sizeof(*LZ4_streamHCPtr));
} else {
- /* preserve end - base : can trigger clearTable's threshold */
- LZ4_streamHCPtr->internal_donotuse.end -= (uptrval)LZ4_streamHCPtr->internal_donotuse.base;
- LZ4_streamHCPtr->internal_donotuse.base = NULL;
+ /* preserve end - prefixStart : can trigger clearTable's threshold */
+ if (LZ4_streamHCPtr->internal_donotuse.end != NULL) {
+ LZ4_streamHCPtr->internal_donotuse.end -= (uptrval)LZ4_streamHCPtr->internal_donotuse.prefixStart;
+ } else {
+ assert(LZ4_streamHCPtr->internal_donotuse.prefixStart == NULL);
+ }
+ LZ4_streamHCPtr->internal_donotuse.prefixStart = NULL;
LZ4_streamHCPtr->internal_donotuse.dictCtx = NULL;
}
LZ4_setCompressionLevel(LZ4_streamHCPtr, compressionLevel);
@@ -1086,14 +1096,14 @@ void LZ4_attach_HC_dictionary(LZ4_streamHC_t *working_stream, const LZ4_streamHC
static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock)
{
DEBUGLOG(4, "LZ4HC_setExternalDict(%p, %p)", ctxPtr, newBlock);
- if (ctxPtr->end >= ctxPtr->base + ctxPtr->dictLimit + 4)
+ if (ctxPtr->end >= ctxPtr->prefixStart + 4)
LZ4HC_Insert (ctxPtr, ctxPtr->end-3); /* Referencing remaining dictionary content */
/* Only one memory segment for extDict, so any previous extDict is lost at this stage */
ctxPtr->lowLimit = ctxPtr->dictLimit;
- ctxPtr->dictLimit = (U32)(ctxPtr->end - ctxPtr->base);
- ctxPtr->dictBase = ctxPtr->base;
- ctxPtr->base = newBlock - ctxPtr->dictLimit;
+ ctxPtr->dictStart = ctxPtr->prefixStart;
+ ctxPtr->dictLimit += (U32)(ctxPtr->end - ctxPtr->prefixStart);
+ ctxPtr->prefixStart = newBlock;
ctxPtr->end = newBlock;
ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */
@@ -1112,11 +1122,11 @@ LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr,
LZ4_streamHCPtr, src, *srcSizePtr, limit);
assert(ctxPtr != NULL);
/* auto-init if forgotten */
- if (ctxPtr->base == NULL) LZ4HC_init_internal (ctxPtr, (const BYTE*) src);
+ if (ctxPtr->prefixStart == NULL) LZ4HC_init_internal (ctxPtr, (const BYTE*) src);
/* Check overflow */
- if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB) {
- size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base) - ctxPtr->dictLimit;
+ if ((size_t)(ctxPtr->end - ctxPtr->prefixStart) + ctxPtr->dictLimit > 2 GB) {
+ size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->prefixStart);
if (dictSize > 64 KB) dictSize = 64 KB;
LZ4_loadDictHC(LZ4_streamHCPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize);
}
@@ -1127,13 +1137,16 @@ LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr,
/* Check overlapping input/dictionary space */
{ const BYTE* sourceEnd = (const BYTE*) src + *srcSizePtr;
- const BYTE* const dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit;
- const BYTE* const dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit;
+ const BYTE* const dictBegin = ctxPtr->dictStart;
+ const BYTE* const dictEnd = ctxPtr->dictStart + (ctxPtr->dictLimit - ctxPtr->lowLimit);
if ((sourceEnd > dictBegin) && ((const BYTE*)src < dictEnd)) {
if (sourceEnd > dictEnd) sourceEnd = dictEnd;
- ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase);
- if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit;
- } }
+ ctxPtr->lowLimit += (U32)(sourceEnd - ctxPtr->dictStart);
+ ctxPtr->dictStart += (U32)(sourceEnd - ctxPtr->dictStart);
+ if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) {
+ ctxPtr->lowLimit = ctxPtr->dictLimit;
+ ctxPtr->dictStart = ctxPtr->prefixStart;
+ } } }
return LZ4HC_compress_generic (ctxPtr, src, dst, srcSizePtr, dstCapacity, ctxPtr->compressionLevel, limit);
}
@@ -1161,7 +1174,7 @@ int LZ4_compress_HC_continue_destSize (LZ4_streamHC_t* LZ4_streamHCPtr, const ch
int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictSize)
{
LZ4HC_CCtx_internal* const streamPtr = &LZ4_streamHCPtr->internal_donotuse;
- int const prefixSize = (int)(streamPtr->end - (streamPtr->base + streamPtr->dictLimit));
+ int const prefixSize = (int)(streamPtr->end - streamPtr->prefixStart);
DEBUGLOG(5, "LZ4_saveDictHC(%p, %p, %d)", LZ4_streamHCPtr, safeBuffer, dictSize);
assert(prefixSize >= 0);
if (dictSize > 64 KB) dictSize = 64 KB;
@@ -1169,12 +1182,13 @@ int LZ4_saveDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, char* safeBuffer, int dictS
if (dictSize > prefixSize) dictSize = prefixSize;
if (safeBuffer == NULL) assert(dictSize == 0);
if (dictSize > 0)
- memmove(safeBuffer, streamPtr->end - dictSize, dictSize);
- { U32 const endIndex = (U32)(streamPtr->end - streamPtr->base);
+ LZ4_memmove(safeBuffer, streamPtr->end - dictSize, dictSize);
+ { U32 const endIndex = (U32)(streamPtr->end - streamPtr->prefixStart) + streamPtr->dictLimit;
streamPtr->end = (const BYTE*)safeBuffer + dictSize;
- streamPtr->base = streamPtr->end - endIndex;
+ streamPtr->prefixStart = streamPtr->end - dictSize;
streamPtr->dictLimit = endIndex - (U32)dictSize;
streamPtr->lowLimit = endIndex - (U32)dictSize;
+ streamPtr->dictStart = streamPtr->prefixStart;
if (streamPtr->nextToUpdate < streamPtr->dictLimit)
streamPtr->nextToUpdate = streamPtr->dictLimit;
}
@@ -1202,7 +1216,7 @@ int LZ4_compressHC_limitedOutput_continue (LZ4_streamHC_t* ctx, const char* src,
/* Deprecated streaming functions */
-int LZ4_sizeofStreamStateHC(void) { return LZ4_STREAMHCSIZE; }
+int LZ4_sizeofStreamStateHC(void) { return sizeof(LZ4_streamHC_t); }
/* state is presumed correctly sized, aka >= sizeof(LZ4_streamHC_t)
* @return : 0 on success, !=0 if error */
@@ -1214,6 +1228,7 @@ int LZ4_resetStreamStateHC(void* state, char* inputBuffer)
return 0;
}
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
void* LZ4_createHC (const char* inputBuffer)
{
LZ4_streamHC_t* const hc4 = LZ4_createStreamHC();
@@ -1228,6 +1243,7 @@ int LZ4_freeHC (void* LZ4HC_Data)
FREEMEM(LZ4HC_Data);
return 0;
}
+#endif
int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* src, char* dst, int srcSize, int cLevel)
{
@@ -1241,11 +1257,11 @@ int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* src, c
char* LZ4_slideInputBufferHC(void* LZ4HC_Data)
{
- LZ4_streamHC_t *ctx = (LZ4_streamHC_t*)LZ4HC_Data;
- const BYTE *bufferStart = ctx->internal_donotuse.base + ctx->internal_donotuse.lowLimit;
+ LZ4_streamHC_t* const ctx = (LZ4_streamHC_t*)LZ4HC_Data;
+ const BYTE* bufferStart = ctx->internal_donotuse.prefixStart - ctx->internal_donotuse.dictLimit + ctx->internal_donotuse.lowLimit;
LZ4_resetStreamHC_fast(ctx, ctx->internal_donotuse.compressionLevel);
/* avoid const char * -> char * conversion warning :( */
- return (char *)(uptrval)bufferStart;
+ return (char*)(uptrval)bufferStart;
}
@@ -1328,7 +1344,7 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx,
{
int retval = 0;
#define TRAILING_LITERALS 3
-#ifdef LZ4HC_HEAPMODE
+#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
LZ4HC_optimal_t* const opt = (LZ4HC_optimal_t*)ALLOC(sizeof(LZ4HC_optimal_t) * (LZ4_OPT_NUM + TRAILING_LITERALS));
#else
LZ4HC_optimal_t opt[LZ4_OPT_NUM + TRAILING_LITERALS]; /* ~64 KB, which is a bit large for stack... */
@@ -1346,7 +1362,7 @@ static int LZ4HC_compress_optimal ( LZ4HC_CCtx_internal* ctx,
const BYTE* ovref = NULL;
/* init */
-#ifdef LZ4HC_HEAPMODE
+#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
if (opt == NULL) goto _return_label;
#endif
DEBUGLOG(5, "LZ4HC_compress_optimal(dst=%p, dstCapa=%u)", dst, (unsigned)dstCapacity);
@@ -1578,7 +1594,7 @@ _last_literals:
} else {
*op++ = (BYTE)(lastRunSize << ML_BITS);
}
- memcpy(op, anchor, lastRunSize);
+ LZ4_memcpy(op, anchor, lastRunSize);
op += lastRunSize;
}
@@ -1611,7 +1627,7 @@ if (limit == fillOutput) {
goto _last_literals;
}
_return_label:
-#ifdef LZ4HC_HEAPMODE
+#if defined(LZ4HC_HEAPMODE) && LZ4HC_HEAPMODE==1
FREEMEM(opt);
#endif
return retval;
diff --git a/public/common/tracy_lz4hc.hpp b/public/common/tracy_lz4hc.hpp
index 18bf30d4..460cbae7 100644
--- a/public/common/tracy_lz4hc.hpp
+++ b/public/common/tracy_lz4hc.hpp
@@ -1,7 +1,7 @@
/*
LZ4 HC - High Compression Mode of LZ4
Header File
- Copyright (C) 2011-2017, Yann Collet.
+ Copyright (C) 2011-2020, Yann Collet.
BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
Redistribution and use in source and binary forms, with or without
@@ -196,14 +196,17 @@ LZ4LIB_API int LZ4_saveDictHC (LZ4_streamHC_t* streamHCPtr, char* safeBuffer, in
#define LZ4HC_HASH_MASK (LZ4HC_HASHTABLESIZE - 1)
+/* Never ever use these definitions directly !
+ * Declare or allocate an LZ4_streamHC_t instead.
+**/
typedef struct LZ4HC_CCtx_internal LZ4HC_CCtx_internal;
struct LZ4HC_CCtx_internal
{
LZ4_u32 hashTable[LZ4HC_HASHTABLESIZE];
LZ4_u16 chainTable[LZ4HC_MAXD];
const LZ4_byte* end; /* next block here to continue on current prefix */
- const LZ4_byte* base; /* All index relative to this position */
- const LZ4_byte* dictBase; /* alternate base for extDict */
+ const LZ4_byte* prefixStart; /* Indexes relative to this position */
+ const LZ4_byte* dictStart; /* alternate reference for extDict */
LZ4_u32 dictLimit; /* below that point, need extDict */
LZ4_u32 lowLimit; /* below that point, no more dict */
LZ4_u32 nextToUpdate; /* index from which to continue dictionary update */
@@ -214,20 +217,15 @@ struct LZ4HC_CCtx_internal
const LZ4HC_CCtx_internal* dictCtx;
};
-
-/* Do not use these definitions directly !
- * Declare or allocate an LZ4_streamHC_t instead.
- */
-#define LZ4_STREAMHCSIZE 262200 /* static size, for inter-version compatibility */
-#define LZ4_STREAMHCSIZE_VOIDP (LZ4_STREAMHCSIZE / sizeof(void*))
+#define LZ4_STREAMHC_MINSIZE 262200 /* static size, for inter-version compatibility */
union LZ4_streamHC_u {
- void* table[LZ4_STREAMHCSIZE_VOIDP];
+ char minStateSize[LZ4_STREAMHC_MINSIZE];
LZ4HC_CCtx_internal internal_donotuse;
}; /* previously typedef'd to LZ4_streamHC_t */
/* LZ4_streamHC_t :
* This structure allows static allocation of LZ4 HC streaming state.
- * This can be used to allocate statically, on state, or as part of a larger structure.
+ * This can be used to allocate statically on stack, or as part of a larger structure.
*
* Such state **must** be initialized using LZ4_initStreamHC() before first use.
*
@@ -242,7 +240,7 @@ union LZ4_streamHC_u {
* Required before first use of a statically allocated LZ4_streamHC_t.
* Before v1.9.0 : use LZ4_resetStreamHC() instead
*/
-LZ4LIB_API LZ4_streamHC_t* LZ4_initStreamHC (void* buffer, size_t size);
+LZ4LIB_API LZ4_streamHC_t* LZ4_initStreamHC(void* buffer, size_t size);
/*-************************************
@@ -270,9 +268,11 @@ LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_comp
* LZ4_slideInputBufferHC() will truncate the history of the stream, rather
* than preserve a window-sized chunk of history.
*/
+#if !defined(LZ4_STATIC_LINKING_ONLY_DISABLE_MEMORY_ALLOCATION)
LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API void* LZ4_createHC (const char* inputBuffer);
-LZ4_DEPRECATED("use LZ4_saveDictHC() instead") LZ4LIB_API char* LZ4_slideInputBufferHC (void* LZ4HC_Data);
LZ4_DEPRECATED("use LZ4_freeStreamHC() instead") LZ4LIB_API int LZ4_freeHC (void* LZ4HC_Data);
+#endif
+LZ4_DEPRECATED("use LZ4_saveDictHC() instead") LZ4LIB_API char* LZ4_slideInputBufferHC (void* LZ4HC_Data);
LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_compress_HC_continue() instead") LZ4LIB_API int LZ4_compressHC2_limitedOutput_continue (void* LZ4HC_Data, const char* source, char* dest, int inputSize, int maxOutputSize, int compressionLevel);
LZ4_DEPRECATED("use LZ4_createStreamHC() instead") LZ4LIB_API int LZ4_sizeofStreamStateHC(void);
@@ -300,7 +300,7 @@ LZ4LIB_API void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionL
* They should not be linked from DLL,
* as there is no guarantee of API stability yet.
* Prototypes will be promoted to "stable" status
- * after successfull usage in real-life scenarios.
+ * after successful usage in real-life scenarios.
***************************************************/
#ifdef LZ4_HC_STATIC_LINKING_ONLY /* protection macro */
#ifndef TRACY_LZ4_HC_SLO_098092834
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-17 22:21:04 +0300