From 607eff5412cd52603e6e19ceb98c8d6b9508bd0e Mon Sep 17 00:00:00 2001 From: John Galt Date: Tue, 3 May 2022 16:15:19 -0400 Subject: [PATCH] lz4: Revert "lz4: remove unused functions" - This reverts commit 9f4c0c41c6d2 as EROFS uses LZ4_decompress_safe_partial(). Signed-off-by: Cyber Knight Signed-off-by: azrim --- include/linux/lz4.h | 392 ++++++++++++++++++++++++++++++++ lib/lz4/lz4_compress.c | 477 ++++++++++++++++++++++++++++++++++++++- lib/lz4/lz4_decompress.c | 276 +++++++++++++++++++++- lib/lz4/lz4defs.h | 2 +- 4 files changed, 1141 insertions(+), 6 deletions(-) diff --git a/include/linux/lz4.h b/include/linux/lz4.h index 9fb02c477f8f..c00f47ecdd75 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -133,6 +133,23 @@ typedef union { LZ4HC_CCtx_internal internal_donotuse; } LZ4_streamHC_t; +/* + * LZ4_streamDecode_t - information structure to track an + * LZ4 stream during decompression. + * + * init this structure using LZ4_setStreamDecode (or memset()) before first use + */ +typedef struct { + const uint8_t *externalDict; + size_t extDictSize; + const uint8_t *prefixEnd; + size_t prefixSize; +} LZ4_streamDecode_t_internal; +typedef union { + unsigned long long table[LZ4_STREAMDECODESIZE_U64]; + LZ4_streamDecode_t_internal internal_donotuse; +} LZ4_streamDecode_t; + /*-************************************************************************ * SIZE OF STATE **************************************************************************/ @@ -180,6 +197,54 @@ static inline int LZ4_compressBound(size_t isize) int LZ4_compress_default(const char *source, char *dest, int inputSize, int maxOutputSize, void *wrkmem); +/** + * LZ4_compress_fast() - As LZ4_compress_default providing an acceleration param + * @source: source address of the original data + * @dest: output buffer address of the compressed data + * @inputSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxOutputSize: full or partial size of buffer 'dest' + * which must be already allocated + * @acceleration: acceleration factor + * @wrkmem: address of the working memory. + * This requires 'workmem' of LZ4_MEM_COMPRESS. + * + * Same as LZ4_compress_default(), but allows to select an "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 LZ4_ACCELERATION_DEFAULT, which is 1. + * + * Return: Number of bytes written into buffer 'dest' + * (necessarily <= maxOutputSize) or 0 if compression fails + */ +static int LZ4_compress_fast(const char *source, char *dest, int inputSize, + int maxOutputSize, int acceleration, void *wrkmem); + +/** + * LZ4_compress_destSize() - Compress as much data as possible + * from source to dest + * @source: source address of the original data + * @dest: output buffer address of the compressed data + * @sourceSizePtr: will be modified to indicate how many bytes where read + * from 'source' to fill 'dest'. New value is necessarily <= old value. + * @targetDestSize: Size of buffer 'dest' which must be already allocated + * @wrkmem: address of the working memory. + * This requires 'workmem' of LZ4_MEM_COMPRESS. + * + * 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'. + * + * Return: Number of bytes written into 'dest' (necessarily <= targetDestSize) + * or 0 if compression fails + */ +static int LZ4_compress_destSize(const char *source, char *dest, int *sourceSizePtr, + int targetDestSize, void *wrkmem); + /*-************************************************************************ * Decompression Functions **************************************************************************/ @@ -227,6 +292,34 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize); int LZ4_decompress_safe(const char *source, char *dest, int compressedSize, int maxDecompressedSize); +/** + * LZ4_decompress_safe_partial() - Decompress a block of size 'compressedSize' + * at position 'source' into buffer 'dest' + * @source: source address of the compressed data + * @dest: output buffer address of the decompressed data which must be + * already allocated + * @compressedSize: is the precise full size of the compressed block. + * @targetOutputSize: the decompression operation will try + * to stop as soon as 'targetOutputSize' has been reached + * @maxDecompressedSize: is the size of destination buffer + * + * This function decompresses 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. + * This function never writes outside of output buffer, + * and never reads outside of input buffer. + * It is therefore protected against malicious data packets. + * + * Return: the number of bytes decoded in the destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + * + */ +static int LZ4_decompress_safe_partial(const char *source, char *dest, + int compressedSize, int targetOutputSize, int maxDecompressedSize); + /*-************************************************************************ * LZ4 HC Compression **************************************************************************/ @@ -253,4 +346,303 @@ int LZ4_decompress_safe(const char *source, char *dest, int compressedSize, int LZ4_compress_HC(const char *src, char *dst, int srcSize, int dstCapacity, int compressionLevel, void *wrkmem); +/** + * LZ4_resetStreamHC() - Init an allocated 'LZ4_streamHC_t' structure + * @streamHCPtr: pointer to the 'LZ4_streamHC_t' structure + * @compressionLevel: Recommended values are between 4 and 9, although any + * value between 1 and LZ4HC_MAX_CLEVEL will work. + * Values >LZ4HC_MAX_CLEVEL behave the same as 16. + * + * An LZ4_streamHC_t structure can be allocated once + * and re-used multiple times. + * Use this function to init an allocated `LZ4_streamHC_t` structure + * and start a new compression. + */ +static void LZ4_resetStreamHC(LZ4_streamHC_t *streamHCPtr, int compressionLevel); + +/** + * LZ4_loadDictHC() - Load a static dictionary into LZ4_streamHC + * @streamHCPtr: pointer to the LZ4HC_stream_t + * @dictionary: dictionary to load + * @dictSize: size of dictionary + * + * Use this function to load a static dictionary into LZ4HC_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) + */ +static int LZ4_loadDictHC(LZ4_streamHC_t *streamHCPtr, const char *dictionary, + int dictSize); + +/** + * LZ4_compress_HC_continue() - Compress 'src' using data from previously + * compressed blocks as a dictionary using the HC algorithm + * @streamHCPtr: Pointer to the previous 'LZ4_streamHC_t' structure + * @src: source address of the original data + * @dst: output buffer address of the compressed data, + * which must be already allocated + * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxDstSize: full or partial size of buffer 'dest' + * which must be already allocated + * + * These functions compress data in successive blocks of any size, using + * previous blocks as dictionary. One key assumption is that previous + * blocks (up to 64 KB) remain read-accessible while + * compressing next blocks. There is an exception for ring buffers, + * which can be smaller than 64 KB. + * Ring buffers scenario is automatically detected and handled by + * LZ4_compress_HC_continue(). + * Before starting compression, state must be properly initialized, + * using LZ4_resetStreamHC(). + * A first "fictional block" can then be designated as + * initial dictionary, using LZ4_loadDictHC() (Optional). + * Then, use LZ4_compress_HC_continue() + * to compress each successive block. Previous memory blocks + * (including initial dictionary when present) must remain accessible + * and unmodified during compression. + * 'dst' buffer should be sized to handle worst case scenarios, using + * LZ4_compressBound(), to ensure operation success. + * If, for any reason, previous data blocks can't be preserved unmodified + * in memory during next compression block, + * you must save it to a safer memory space, using LZ4_saveDictHC(). + * Return value of LZ4_saveDictHC() is the size of dictionary + * effectively saved into 'safeBuffer'. + * + * Return: Number of bytes written into buffer 'dst' or 0 if compression fails + */ +static int LZ4_compress_HC_continue(LZ4_streamHC_t *streamHCPtr, const char *src, + char *dst, int srcSize, int maxDstSize); + +/** + * LZ4_saveDictHC() - Save static dictionary from LZ4HC_stream + * @streamHCPtr: pointer to the 'LZ4HC_stream_t' structure + * @safeBuffer: buffer to save dictionary to, must be already allocated + * @maxDictSize: size of 'safeBuffer' + * + * 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_loadDictHC() afterwards, + * dictionary is immediately usable, you can therefore call + * LZ4_compress_HC_continue(). + * + * Return : saved dictionary size in bytes (necessarily <= maxDictSize), + * or 0 if error. + */ +static int LZ4_saveDictHC(LZ4_streamHC_t *streamHCPtr, char *safeBuffer, + int maxDictSize); + +/*-********************************************* + * Streaming Compression Functions + ***********************************************/ + +/** + * LZ4_resetStream() - Init an allocated 'LZ4_stream_t' structure + * @LZ4_stream: pointer to the 'LZ4_stream_t' structure + * + * 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. + */ +static __always_inline void LZ4_resetStream(LZ4_stream_t *LZ4_stream); + +/** + * LZ4_loadDict() - Load a static dictionary into LZ4_stream + * @streamPtr: pointer to the LZ4_stream_t + * @dictionary: dictionary to load + * @dictSize: size of dictionary + * + * 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) + */ +int LZ4_loadDict(LZ4_stream_t *streamPtr, const char *dictionary, + int dictSize); + +/** + * LZ4_saveDict() - Save static dictionary from LZ4_stream + * @streamPtr: pointer to the 'LZ4_stream_t' structure + * @safeBuffer: buffer to save dictionary to, must be already allocated + * @dictSize: size of 'safeBuffer' + * + * 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. + */ +int LZ4_saveDict(LZ4_stream_t *streamPtr, char *safeBuffer, int dictSize); + +/** + * LZ4_compress_fast_continue() - Compress 'src' using data from previously + * compressed blocks as a dictionary + * @streamPtr: Pointer to the previous 'LZ4_stream_t' structure + * @src: source address of the original data + * @dst: output buffer address of the compressed data, + * which must be already allocated + * @srcSize: size of the input data. Max supported value is LZ4_MAX_INPUT_SIZE + * @maxDstSize: full or partial size of buffer 'dest' + * which must be already allocated + * @acceleration: acceleration factor + * + * 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 ! + * If maxDstSize >= LZ4_compressBound(srcSize), + * compression is guaranteed to succeed, and runs faster. + * + * Return: Number of bytes written into buffer 'dst' or 0 if compression fails + */ +static int LZ4_compress_fast_continue(LZ4_stream_t *streamPtr, const char *src, + char *dst, int srcSize, int maxDstSize, int acceleration); + +/** + * LZ4_setStreamDecode() - Instruct where to find dictionary + * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure + * @dictionary: dictionary to use + * @dictSize: size of dictionary + * + * 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 + */ +static int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode, + const char *dictionary, int dictSize); + +/** + * LZ4_decompress_safe_continue() - Decompress blocks in streaming mode + * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated + * @compressedSize: is the precise full size of the compressed block + * @maxDecompressedSize: is the size of 'dest' buffer + * + * This decoding function allows 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. W + * 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() + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +static int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode, + const char *source, char *dest, int compressedSize, + int maxDecompressedSize); + +/** + * LZ4_decompress_fast_continue() - Decompress blocks in streaming mode + * @LZ4_streamDecode: the 'LZ4_streamDecode_t' structure + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated with 'originalSize' bytes + * @originalSize: is the original and therefore uncompressed size + * + * This decoding function allows 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. W + * 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() + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +static int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode, + const char *source, char *dest, int originalSize); + +/** + * LZ4_decompress_safe_usingDict() - Same as LZ4_setStreamDecode() + * followed by LZ4_decompress_safe_continue() + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated + * @compressedSize: is the precise full size of the compressed block + * @maxDecompressedSize: is the size of 'dest' buffer + * @dictStart: pointer to the start of the dictionary in memory + * @dictSize: size of dictionary + * + * This decoding function works the same as + * a combination of LZ4_setStreamDecode() followed by + * LZ4_decompress_safe_continue() + * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure. + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +static int LZ4_decompress_safe_usingDict(const char *source, char *dest, + int compressedSize, int maxDecompressedSize, const char *dictStart, + int dictSize); + +/** + * LZ4_decompress_fast_usingDict() - Same as LZ4_setStreamDecode() + * followed by LZ4_decompress_fast_continue() + * @source: source address of the compressed data + * @dest: output buffer address of the uncompressed data + * which must be already allocated with 'originalSize' bytes + * @originalSize: is the original and therefore uncompressed size + * @dictStart: pointer to the start of the dictionary in memory + * @dictSize: size of dictionary + * + * This decoding function works the same as + * a combination of LZ4_setStreamDecode() followed by + * LZ4_decompress_fast_continue() + * It is stand-alone, and doesn't need an LZ4_streamDecode_t structure. + * + * Return: number of bytes decompressed into destination buffer + * (necessarily <= maxDecompressedSize) + * or a negative result in case of error + */ +static int LZ4_decompress_fast_usingDict(const char *source, char *dest, + int originalSize, const char *dictStart, int dictSize); + #endif diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c index aa09d3cae270..ee20d9d2bbdf 100644 --- a/lib/lz4/lz4_compress.c +++ b/lib/lz4/lz4_compress.c @@ -189,6 +189,9 @@ static FORCE_INLINE int LZ4_compress_generic( const BYTE *base; const BYTE *lowLimit; const BYTE * const lowRefLimit = ip - dictPtr->dictSize; + const BYTE * const dictionary = dictPtr->dictionary; + const BYTE * const dictEnd = dictionary + dictPtr->dictSize; + const size_t dictDelta = dictEnd - (const BYTE *)source; const BYTE *anchor = (const BYTE *) source; const BYTE * const iend = ip + inputSize; const BYTE * const mflimit = iend - MFLIMIT; @@ -216,6 +219,10 @@ static FORCE_INLINE int LZ4_compress_generic( base = (const BYTE *)source - dictPtr->currentOffset; lowLimit = (const BYTE *)source - dictPtr->dictSize; break; + case usingExtDict: + base = (const BYTE *)source - dictPtr->currentOffset; + lowLimit = (const BYTE *)source; + break; } if ((tableType == byU16) @@ -259,6 +266,15 @@ static FORCE_INLINE int LZ4_compress_generic( dictPtr->hashTable, tableType, base); + if (dict == usingExtDict) { + if (match < (const BYTE *)source) { + refDelta = dictDelta; + lowLimit = dictionary; + } else { + refDelta = 0; + lowLimit = (const BYTE *)source; + } } + forwardH = LZ4_hashPosition(forwardIp, tableType); @@ -319,9 +335,34 @@ _next_match: { unsigned int matchCode; - matchCode = LZ4_count(ip + MINMATCH, - match + MINMATCH, matchlimit); - ip += MINMATCH + matchCode; + if ((dict == usingExtDict) + && (lowLimit == dictionary)) { + const BYTE *limit; + + match += refDelta; + limit = ip + (dictEnd - match); + + if (limit > matchlimit) + limit = matchlimit; + + matchCode = LZ4_count(ip + MINMATCH, + match + MINMATCH, limit); + + ip += MINMATCH + matchCode; + + if (ip == limit) { + unsigned const int more = LZ4_count(ip, + (const BYTE *)source, + matchlimit); + + matchCode += more; + ip += more; + } + } else { + matchCode = LZ4_count(ip + MINMATCH, + match + MINMATCH, matchlimit); + ip += MINMATCH + matchCode; + } if (outputLimited && /* Check output buffer overflow */ @@ -360,6 +401,16 @@ _next_match: match = LZ4_getPosition(ip, dictPtr->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, dictPtr->hashTable, tableType, base); if (((dictIssue == dictSmall) ? (match >= lowRefLimit) : 1) @@ -419,7 +470,7 @@ static int LZ4_compress_fast_extState( const tableType_t tableType = byPtr; #endif - memset(state, 0, sizeof(LZ4_stream_t)); + LZ4_resetStream((LZ4_stream_t *)state); if (acceleration < 1) acceleration = LZ4_ACCELERATION_DEFAULT; @@ -464,5 +515,423 @@ int LZ4_compress_default(const char *source, char *dest, int inputSize, } EXPORT_SYMBOL(LZ4_compress_default); +/*-****************************** + * *_destSize() variant + ********************************/ +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 */ + /* Impossible to store anything */ + if (targetDstSize < 1) + return 0; + /* Unsupported input size, too large (or negative) */ + if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) + return 0; + /* Size too large (not within 64K limit) */ + if ((tableType == byU16) && (*srcSizePtr >= LZ4_64Klimit)) + return 0; + /* Input too small, no compression (all literals) */ + if (*srcSizePtr < LZ4_minLength) + goto _last_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 int step = 1; + unsigned int 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 int litLength = (unsigned int)(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 int len = litLength - RUN_MASK; + *token = (RUN_MASK<= 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<= 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, tableType); + } +} + + +static int LZ4_compress_destSize( + const char *src, + char *dst, + int *srcSizePtr, + int targetDstSize, + void *wrkmem) +{ + return LZ4_compress_destSize_extState(wrkmem, src, dst, srcSizePtr, + targetDstSize); +} + +/*-****************************** + * Streaming functions + ********************************/ +static FORCE_INLINE void LZ4_resetStream(LZ4_stream_t *LZ4_stream) +{ + memset(LZ4_stream, 0, sizeof(LZ4_stream_t)); +} + +int LZ4_loadDict(LZ4_stream_t *LZ4_dict, + const char *dictionary, int dictSize) +{ + LZ4_stream_t_internal *dict = &LZ4_dict->internal_donotuse; + 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); + } + + 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; + dict->dictionary = p; + dict->dictSize = (U32)(dictEnd - p); + dict->currentOffset += dict->dictSize; + + while (p <= dictEnd - HASH_UNIT) { + LZ4_putPosition(p, dict->hashTable, byU32, base); + p += 3; + } + + return dict->dictSize; +} +EXPORT_SYMBOL(LZ4_loadDict); + +static void LZ4_renormDictT(LZ4_stream_t_internal *LZ4_dict, + const BYTE *src) +{ + if ((LZ4_dict->currentOffset > 0x80000000) || + ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) { + /* address space overflow */ + /* rescale hash table */ + U32 const delta = LZ4_dict->currentOffset - 64 * KB; + const BYTE *dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize; + int i; + + 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; + } + LZ4_dict->currentOffset = 64 * KB; + if (LZ4_dict->dictSize > 64 * KB) + LZ4_dict->dictSize = 64 * KB; + LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize; + } +} + +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) { + /* useless to define a dictionary > 64 * KB */ + dictSize = 64 * KB; + } + if ((U32)dictSize > dict->dictSize) + dictSize = dict->dictSize; + + memmove(safeBuffer, previousDictEnd - dictSize, dictSize); + + dict->dictionary = (const BYTE *)safeBuffer; + dict->dictSize = (U32)dictSize; + + return dictSize; +} +EXPORT_SYMBOL(LZ4_saveDict); + +static int LZ4_compress_fast_continue(LZ4_stream_t *LZ4_stream, const char *source, + char *dest, int inputSize, int maxOutputSize, int acceleration) +{ + LZ4_stream_t_internal *streamPtr = &LZ4_stream->internal_donotuse; + const BYTE * const dictEnd = streamPtr->dictionary + + streamPtr->dictSize; + + const BYTE *smallest = (const BYTE *) source; + + if (streamPtr->initCheck) { + /* Uninitialized structure detected */ + return 0; + } + + if ((streamPtr->dictSize > 0) && (smallest > dictEnd)) + smallest = dictEnd; + + LZ4_renormDictT(streamPtr, smallest); + + if (acceleration < 1) + acceleration = LZ4_ACCELERATION_DEFAULT; + + /* Check overlapping input/dictionary space */ + { + const BYTE *sourceEnd = (const BYTE *) source + inputSize; + + if ((sourceEnd > 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; + } + } + + /* 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); + } 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; + } + + /* 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); + } + streamPtr->dictionary = (const BYTE *)source; + streamPtr->dictSize = (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; + } +} + MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4 compressor"); diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index a69a756033c9..95c1b6e4c178 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -70,7 +70,7 @@ static FORCE_INLINE int LZ4_decompress_generic( endCondition_directive endOnInput, /* full, partial */ earlyEnd_directive partialDecoding, - /* noDict, withPrefix64k */ + /* noDict, withPrefix64k, usingExtDict */ dict_directive dict, /* always <= dst, == dst when no prefix */ const BYTE * const lowPrefix, @@ -87,6 +87,7 @@ static FORCE_INLINE int LZ4_decompress_generic( BYTE * const oend = op + outputSize; BYTE *cpy; + const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize; static const unsigned int inc32table[8] = {0, 1, 2, 1, 0, 4, 4, 4}; static const int dec64table[8] = {0, 0, 0, -1, -4, 1, 2, 3}; @@ -328,6 +329,48 @@ _copy_match: length += MINMATCH; + /* match starting within external dictionary */ + if ((dict == usingExtDict) && (match < lowPrefix)) { + if (unlikely(op + length > oend - LASTLITERALS)) { + /* doesn't respect parsing restriction */ + if (!partialDecoding) + goto _output_error; + length = min(length, (size_t)(oend - op)); + } + + 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; @@ -419,6 +462,15 @@ int LZ4_decompress_safe(const char *source, char *dest, noDict, (BYTE *)dest, NULL, 0); } +static int LZ4_decompress_safe_partial(const char *src, char *dst, + int compressedSize, int targetOutputSize, int dstCapacity) +{ + dstCapacity = min(targetOutputSize, dstCapacity); + return LZ4_decompress_generic(src, dst, compressedSize, dstCapacity, + endOnInputSize, partial_decode, + noDict, (BYTE *)dst, NULL, 0); +} + int LZ4_decompress_fast(const char *source, char *dest, int originalSize) { return LZ4_decompress_generic(source, dest, 0, originalSize, @@ -427,6 +479,228 @@ int LZ4_decompress_fast(const char *source, char *dest, int originalSize) (BYTE *)dest - 64 * KB, NULL, 0); } +/* ===== Instantiate a few more decoding cases, used more than once. ===== */ + +static 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); +} + +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); +} + +static 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); +} + +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(). + */ +static 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); +} + +static 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 ===== */ + +static 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->externalDict = NULL; + lz4sd->extDictSize = 0; + return 1; +} + +/* + * *_continue() : + * These decoding functions allow decompression of multiple blocks + * in "streaming" mode. + * Previously decoded blocks must still be available at the memory + * position where they were decoded. + * If it's not possible, save the relevant part of + * decoded data into a safe buffer, + * and indicate where it stands using LZ4_setStreamDecode() + */ +static 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->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 = 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->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_safe_forceExtDict(source, dest, + compressedSize, maxOutputSize, + lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) + return result; + lz4sd->prefixSize = result; + lz4sd->prefixEnd = (BYTE *)dest + result; + } + + return result; +} + +static 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; + + if (lz4sd->prefixSize == 0) { + assert(lz4sd->extDictSize == 0); + result = LZ4_decompress_fast(source, dest, originalSize); + if (result <= 0) + return result; + lz4sd->prefixSize = 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->prefixEnd += originalSize; + } else { + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; + result = LZ4_decompress_fast_extDict(source, dest, + originalSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) + return result; + lz4sd->prefixSize = originalSize; + lz4sd->prefixEnd = (BYTE *)dest + originalSize; + } + return result; +} + +static 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_safe(source, dest, + compressedSize, maxOutputSize); + if (dictStart+dictSize == dest) { + if (dictSize >= 64 * KB - 1) + return LZ4_decompress_safe_withPrefix64k(source, dest, + compressedSize, maxOutputSize); + return LZ4_decompress_safe_withSmallPrefix(source, dest, + compressedSize, maxOutputSize, dictSize); + } + return LZ4_decompress_safe_forceExtDict(source, dest, + compressedSize, maxOutputSize, dictStart, dictSize); +} + +static int LZ4_decompress_fast_usingDict(const char *source, char *dest, + int originalSize, + const char *dictStart, int dictSize) +{ + if (dictSize == 0 || dictStart + dictSize == dest) + return LZ4_decompress_fast(source, dest, originalSize); + + return LZ4_decompress_fast_extDict(source, dest, originalSize, + dictStart, dictSize); +} + #ifndef STATIC MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4 decompressor"); diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index 22ccb32c1f1d..673bd206aa98 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -234,7 +234,7 @@ static FORCE_INLINE unsigned int LZ4_count( typedef enum { noLimit = 0, limitedOutput = 1 } limitedOutput_directive; typedef enum { byPtr, byU32, byU16 } tableType_t; -typedef enum { noDict = 0, withPrefix64k } dict_directive; +typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive; typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive; typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;