Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754363AbcLTTEN (ORCPT ); Tue, 20 Dec 2016 14:04:13 -0500 Received: from mailhost.informatik.uni-hamburg.de ([134.100.9.70]:40280 "EHLO mailhost.informatik.uni-hamburg.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S934184AbcLTTCs (ORCPT ); Tue, 20 Dec 2016 14:02:48 -0500 From: Sven Schmidt <4sschmid@informatik.uni-hamburg.de> To: akpm@linux-foundation.org Cc: bongkyu.kim@lge.com, sergey.senozhatsky@gmail.com, gregkh@linuxfoundation.org, linux-kernel@vger.kernel.org, Sven Schmidt <4sschmid@informatik.uni-hamburg.de> Subject: [PATCH 3/3] lib: Update LZ4 compressor module based on LZ4 v1.7.2. Date: Tue, 20 Dec 2016 19:53:12 +0100 Message-Id: <1482259992-16680-4-git-send-email-4sschmid@informatik.uni-hamburg.de> X-Mailer: git-send-email 2.1.4 In-Reply-To: <1482259992-16680-1-git-send-email-4sschmid@informatik.uni-hamburg.de> References: <1482259992-16680-1-git-send-email-4sschmid@informatik.uni-hamburg.de> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 125401 Lines: 3603 This patch updates LZ4 kernel module to LZ4 v1.7.2 by Yann Collet. The kernel module is inspired by the previous work by Chanho Min. The updated LZ4 module will not break existing code since there were alias methods added to ensure backwards compatibility. API changes: New method LZ4_compress_fast which differs from the variant available in kernel by the new acceleration parameter, allowing to trade compression ratio for more speedup. LZ4_decompress_fast is the respective decompression method, allowing to decompress data compressed with any LZ4 compression method including LZ4HC. Also the useful functions LZ4_decompress_safe_partial LZ4_compress_destsize were added. The latter reverses the logic by trying to compress as much data as possible from source to dest while the former aims to decompress partial blocks of data. The methods lz4_compress and lz4_decompress_unknownoutputsize are now known as LZ4_compress_default respectivley LZ4_decompress_safe. The old methods are still available for offering backwards compatibility. Signed-off-by: Sven Schmidt <4sschmid@informatik.uni-hamburg.de> --- include/linux/lz4.h | 267 +++++++++--- lib/decompress_unlz4.c | 11 +- lib/lz4/lz4_compress.c | 1024 +++++++++++++++++++++++++------------------ lib/lz4/lz4_decompress.c | 627 +++++++++++++-------------- lib/lz4/lz4defs.h | 359 +++++++++------ lib/lz4/lz4hc_compress.c | 1083 +++++++++++++++++++++++++--------------------- 6 files changed, 1941 insertions(+), 1430 deletions(-) diff --git a/include/linux/lz4.h b/include/linux/lz4.h index 6b784c5..4b8fce7 100644 --- a/include/linux/lz4.h +++ b/include/linux/lz4.h @@ -1,87 +1,218 @@ #ifndef __LZ4_H__ #define __LZ4_H__ + /* * LZ4 Kernel Interface * - * Copyright (C) 2013, LG Electronics, Kyungsik Lee + * Copyright (C) 2016, Sven Schmidt <4sschmid@informatik.uni-hamburg.de> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + +#include + +/*-************************************************************************ +* Version +**************************************************************************/ +#define LZ4_VERSION_MAJOR 1 /* for breaking interface changes */ +#define LZ4_VERSION_MINOR 7 /* for new (non-breaking) interface capabilities */ +#define LZ4_VERSION_RELEASE 2 /* for tweaks, bug-fixes, or development */ + +#define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE) + +/*-************************************************************************ +* Constants +**************************************************************************/ #define LZ4_MEM_COMPRESS (16384) #define LZ4HC_MEM_COMPRESS (262144 + (2 * sizeof(unsigned char *))) -/* - * lz4_compressbound() - * Provides the maximum size that LZ4 may output in a "worst case" scenario - * (input data not compressible) - */ -static inline size_t lz4_compressbound(size_t isize) -{ - return isize + (isize / 255) + 16; +#define LZ4_MAX_INPUT_SIZE 0x7E000000 /* 2 113 929 216 bytes */ +#define LZ4_COMPRESSBOUND(isize) ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16) + +#define LZ4HC_MIN_CLEVEL 3 +#define LZ4HC_DEFAULT_CLEVEL 9 +#define LZ4HC_MAX_CLEVEL 16 + +/*-************************************************************************ +* Compression Functions +**************************************************************************/ + +/*!LZ4_compressbound() : + Provides the maximum size that LZ4 may output in a "worst case" scenario + (input data not compressible) +*/ +static inline size_t LZ4_compressBound(size_t isize) { + return LZ4_COMPRESSBOUND(isize); } -/* - * lz4_compress() - * src : source address of the original data - * src_len : size of the original data - * dst : output buffer address of the compressed data - * This requires 'dst' of size LZ4_COMPRESSBOUND. - * dst_len : is the output size, which is returned after compress done - * workmem : address of the working memory. - * This requires 'workmem' of size LZ4_MEM_COMPRESS. - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer and workmem must be already allocated with - * the defined size. - */ -int lz4_compress(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len, void *wrkmem); - - /* - * lz4hc_compress() - * src : source address of the original data - * src_len : size of the original data - * dst : output buffer address of the compressed data - * This requires 'dst' of size LZ4_COMPRESSBOUND. - * dst_len : is the output size, which is returned after compress done - * workmem : address of the working memory. - * This requires 'workmem' of size LZ4HC_MEM_COMPRESS. - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer and workmem must be already allocated with - * the defined size. - */ -int lz4hc_compress(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len, void *wrkmem); +/*! lz4_compressbound() : + For backward compabitiliby +*/ +static inline size_t lz4_compressbound(size_t isize) { + return lz4_compressbound(isize); +} -/* - * lz4_decompress() - * src : source address of the compressed data - * src_len : is the input size, whcih is returned after decompress done - * dest : output buffer address of the decompressed data - * actual_dest_len: is the size of uncompressed data, supposing it's known - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer must be already allocated. - * slightly faster than lz4_decompress_unknownoutputsize() - */ -int lz4_decompress(const unsigned char *src, size_t *src_len, - unsigned char *dest, size_t actual_dest_len); +/*! LZ4_compress_default() : + Compresses 'sourceSize' bytes from buffer 'source' + into already allocated 'dest' buffer of size 'maxDestSize'. + Compression is guaranteed to succeed if 'maxDestSize' >= LZ4_compressBound(sourceSize). + It also runs faster, so it's a recommended setting. + If the function cannot compress 'source' into a more limited 'dest' budget, + compression stops *immediately*, and the function result is zero. + As a consequence, 'dest' content is not valid. + This function never writes outside 'dest' buffer, nor read outside 'source' buffer. + sourceSize : Max supported value is LZ4_MAX_INPUT_VALUE + maxDestSize : full or partial size of buffer 'dest' (which must be already allocated) + workmem : address of the working memory. This requires 'workmem' of size LZ4_MEM_COMPRESS. + return : the number of bytes written into buffer 'dest' (necessarily <= maxOutputSize) + or 0 if compression fails */ +int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize, void* wrkmem); -/* - * lz4_decompress_unknownoutputsize() - * src : source address of the compressed data - * src_len : is the input size, therefore the compressed size - * dest : output buffer address of the decompressed data - * dest_len: is the max size of the destination buffer, which is - * returned with actual size of decompressed data after - * decompress done - * return : Success if return 0 - * Error if return (< 0) - * note : Destination buffer must be already allocated. +/*! +LZ4_compress_fast() : + 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 ACCELERATION_DEFAULT, which is 1. +*/ +int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, void* wrkmem, int acceleration); + +/*! +LZ4_compress_destSize() : + Reverse the logic, by compressing as much data as possible from 'source' buffer + into already allocated buffer 'dest' of size 'targetDestSize'. + This function either compresses the entire 'source' content into 'dest' if it's large enough, + or fill 'dest' buffer completely with as much data as possible from 'source'. + *sourceSizePtr : will be modified to indicate how many bytes where read from 'source' to fill 'dest'. + New value is necessarily <= old value. + workmem : address of the working memory. This requires 'workmem' of size LZ4_MEM_COMPRESS. + return : Nb bytes written into 'dest' (necessarily <= targetDestSize) + or 0 if compression fails +*/ +int LZ4_compress_destSize (const char* source, char* dest, int* sourceSizePtr, int targetDestSize, void* wrkmem); + +/*! + * lz4_compress() : + For backwards compabitiliby + src : source address of the original data + src_len : size of the original data + dst : output buffer address of the compressed data + This requires 'dst' of size LZ4_COMPRESSBOUND. + dst_len : is the output size, which is returned after compress done + workmem : address of the working memory. + This requires 'workmem' of size LZ4_MEM_COMPRESS. + return : Success if return 0 + Error if return (< 0) + note : Destination buffer and workmem must be already allocated with + the defined size. */ -int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len, - unsigned char *dest, size_t *dest_len); +int lz4_compress(const unsigned char *src, int src_len, unsigned char *dst, int dst_len, void *wrkmem); + +/*-************************************************************************ +* Decompression Functions +**************************************************************************/ + +/*! +LZ4_decompress_fast() : + originalSize : is the original and therefore uncompressed size + return : the number of bytes read from the source buffer (in other words, the compressed size) + If the source stream is detected malformed, the function will stop decoding and return a negative result. + Destination buffer must be already allocated. Its size must be a minimum of 'originalSize' bytes. + note : This function fully respect memory boundaries for properly formed compressed data. + It is a bit faster than LZ4_decompress_safe(). + However, it does not provide any protection against intentionally modified data stream (malicious input). + Use this function in trusted environment only (data to decode comes from a trusted source). +*/ +int LZ4_decompress_fast(const char* source, char* dest, int originalSize); + +/*! +LZ4_decompress_safe() : + compressedSize : is the precise full size of the compressed block. + maxDecompressedSize : is the size of destination buffer, which must be already allocated. + return : the number of bytes decompressed into destination buffer (necessarily <= maxDecompressedSize) + If destination buffer is not large enough, decoding will stop and output an error code (<0). + If the source stream is detected malformed, the function will stop decoding and return a negative result. + This function is protected against buffer overflow exploits, including malicious data packets. + It never writes outside output buffer, nor reads outside input buffer. +*/ +int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize); + +/*! +LZ4_decompress_safe_partial() : + This function decompress a compressed block of size 'compressedSize' at position 'source' + into destination buffer 'dest' of size 'maxDecompressedSize'. + The function tries to stop decompressing operation as soon as 'targetOutputSize' has been reached, + reducing decompression time. + return : the number of bytes decoded in the destination buffer (necessarily <= maxDecompressedSize) + Note : this number can be < 'targetOutputSize' should the compressed block to decode be smaller. + Always control how many bytes were decoded. + If the source stream is detected malformed, the function will stop decoding and return a negative result. + This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets +*/ +int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize); + + +/*! +lz4_decompress_unknownoutputsize() : + For backwards compabitiliby + src : source address of the compressed data + src_len : is the input size, therefore the compressed size + dest : output buffer address of the decompressed data + dest_len: is the max size of the destination buffer, which is + returned with actual size of decompressed data after + decompress done + return : Success if return 0 + Error if return (< 0) + note : Destination buffer must be already allocated. +*/ +int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len, unsigned char *dest, size_t *dest_len); + +/*! +lz4_decompress() : + For backwards compabitiliby + src : source address of the compressed data + src_len : is the input size, whcih is returned after decompress done + dest : output buffer address of the decompressed data + actual_dest_len: is the size of uncompressed data, supposing it's known + return : Success if return 0 + Error if return (< 0) + note : Destination buffer must be already allocated. + slightly faster than lz4_decompress_unknownoutputsize() +*/ +int lz4_decompress(const unsigned char *src, size_t *src_len, unsigned char *dest, size_t actual_dest_len); + +/*-************************************************************************ + * LZ4 HC Compression + **************************************************************************/ + +/*! LZ4_compress_HC() : + Compress data from `src` into `dst`, using the more powerful but slower "HC" algorithm. dst` must be already allocated. + wrkmem : address of the working memory. This requires 'wrkmem' of size LZ4HC_MEM_COMPRESS. + Compression is guaranteed to succeed if `dstCapacity >= LZ4_compressBound(srcSize)` + Max supported `srcSize` value is LZ4_MAX_INPUT_SIZE + 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. + @return : the number of bytes written into 'dst' or 0 if compression fails. +*/ +int LZ4_compress_HC(const char* src, char* dst, int srcSize, int dstCapacity, int compressionLevel, void* wrkmem); + +/*! lz4hc_compress() + For backwards compabitiliby + src : source address of the original data + src_len : size of the original data + dst : output buffer address of the compressed data + This requires 'dst' of size LZ4_COMPRESSBOUND. + dst_len : is the output size, which is returned after compress done + workmem : address of the working memory. + This requires 'workmem' of size LZ4HC_MEM_COMPRESS. + return : Success if return 0 + Error if return (< 0) + note : Destination buffer and workmem must be already allocated with + the defined size. +*/ +int lz4hc_compress(const unsigned char *src, size_t src_len, unsigned char *dst, size_t *dst_len, void *wrkmem); + #endif diff --git a/lib/decompress_unlz4.c b/lib/decompress_unlz4.c index 036fc88..ee00eb2 100644 --- a/lib/decompress_unlz4.c +++ b/lib/decompress_unlz4.c @@ -72,7 +72,7 @@ STATIC inline int INIT unlz4(u8 *input, long in_len, error("NULL input pointer and missing fill function"); goto exit_1; } else { - inp = large_malloc(lz4_compressbound(uncomp_chunksize)); + inp = large_malloc(LZ4_compressBound(uncomp_chunksize)); if (!inp) { error("Could not allocate input buffer"); goto exit_1; @@ -136,7 +136,7 @@ STATIC inline int INIT unlz4(u8 *input, long in_len, inp += 4; size -= 4; } else { - if (chunksize > lz4_compressbound(uncomp_chunksize)) { + if (chunksize > LZ4_compressBound(uncomp_chunksize)) { error("chunk length is longer than allocated"); goto exit_2; } @@ -152,11 +152,12 @@ STATIC inline int INIT unlz4(u8 *input, long in_len, out_len -= dest_len; } else dest_len = out_len; - ret = lz4_decompress(inp, &chunksize, outp, dest_len); + + ret = LZ4_decompress_fast(inp, outp, chunksize); #else dest_len = uncomp_chunksize; - ret = lz4_decompress_unknownoutputsize(inp, chunksize, outp, - &dest_len); + + ret = LZ4_decompress_safe(inp, outp, chunksize, dest_len); #endif if (ret < 0) { error("Decoding failed"); diff --git a/lib/lz4/lz4_compress.c b/lib/lz4/lz4_compress.c index 28321d8..551f586 100644 --- a/lib/lz4/lz4_compress.c +++ b/lib/lz4/lz4_compress.c @@ -1,443 +1,639 @@ /* - * LZ4 - Fast LZ compression algorithm - * Copyright (C) 2011-2012, 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 - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You can contact the author at : - * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html - * - LZ4 source repository : http://code.google.com/p/lz4/ - * - * Changed for kernel use by: - * Chanho Min - */ - + LZ4 - Fast LZ compression algorithm + Copyright (C) 2011-2016, 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 + modification, are permitted provided that the following conditions are + met: + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following disclaimer + in the documentation and/or other materials provided with the + distribution. + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + You can contact the author at : + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 + + + Changed for kernel use by: + Sven Schmidt <4sschmid@informatik.uni-hamburg.de> +*/ + +/*-************************************ +* Includes +**************************************/ +#include "lz4defs.h" +#include +#include #include #include -#include #include -#include "lz4defs.h" /* - * LZ4_compressCtx : - * ----------------- - * Compress 'isize' bytes from 'source' into an output buffer 'dest' of - * maximum size 'maxOutputSize'. * If it cannot achieve it, compression - * will stop, and result of the function will be zero. - * return : the number of bytes written in buffer 'dest', or 0 if the - * compression fails + * ACCELERATION_DEFAULT : + * Select "acceleration" for LZ4_compress_fast() when parameter value <= 0 */ -static inline int lz4_compressctx(void *ctx, - const char *source, - char *dest, - int isize, - int maxoutputsize) +#define ACCELERATION_DEFAULT 1 + +/*-****************************** +* Compression functions +********************************/ +static U32 LZ4_hashSequence(U32 sequence, tableType_t const tableType) +{ + if (tableType == byU16) + return (((sequence) * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1))); + else + return (((sequence) * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG)); +} + +static const U64 prime5bytes = 889523592379ULL; +static U32 LZ4_hashSequence64(size_t sequence, tableType_t const tableType) +{ + const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG; + const U32 hashMask = (1<> (40 - hashLog)) & hashMask; +} + +static U32 LZ4_hashSequenceT(size_t sequence, tableType_t const tableType) +{ + if (LZ4_64bits()) + return LZ4_hashSequence64(sequence, tableType); + return LZ4_hashSequence((U32)sequence, tableType); +} + +static U32 LZ4_hashPosition(const void* p, tableType_t tableType) { return LZ4_hashSequenceT(LZ4_read_ARCH(p), tableType); } + +static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase) +{ + switch (tableType) + { + case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; } + case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; } + case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; } + } +} + +static void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + U32 const h = LZ4_hashPosition(p, tableType); + LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase); +} + +static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; } + if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; } + { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; } /* default, to ensure a return */ +} + +static const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase) +{ + U32 const h = LZ4_hashPosition(p, tableType); + return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase); +} + + +/** LZ4_compress_generic() : + inlined, to ensure branches are decided at compilation time */ +FORCE_INLINE int LZ4_compress_generic( + void* const ctx, + const char* const source, + char* const dest, + const int inputSize, + const int maxOutputSize, + const limitedOutput_directive outputLimited, + const tableType_t tableType, + const dict_directive dict, + const dictIssue_directive dictIssue, + const U32 acceleration) { - HTYPE *hashtable = (HTYPE *)ctx; - const u8 *ip = (u8 *)source; -#if LZ4_ARCH64 - const BYTE * const base = ip; -#else - const int base = 0; -#endif - const u8 *anchor = ip; - const u8 *const iend = ip + isize; - const u8 *const mflimit = iend - MFLIMIT; - #define MATCHLIMIT (iend - LASTLITERALS) - - u8 *op = (u8 *) dest; - u8 *const oend = op + maxoutputsize; - int length; - const int skipstrength = SKIPSTRENGTH; - u32 forwardh; - int lastrun; - - /* Init */ - if (isize < MINLENGTH) - goto _last_literals; - - memset((void *)hashtable, 0, LZ4_MEM_COMPRESS); - - /* First Byte */ - hashtable[LZ4_HASH_VALUE(ip)] = ip - base; - ip++; - forwardh = LZ4_HASH_VALUE(ip); - - /* Main Loop */ - for (;;) { - int findmatchattempts = (1U << skipstrength) + 3; - const u8 *forwardip = ip; - const u8 *ref; - u8 *token; - - /* Find a match */ - do { - u32 h = forwardh; - int step = findmatchattempts++ >> skipstrength; - ip = forwardip; - forwardip = ip + step; - - if (unlikely(forwardip > mflimit)) - goto _last_literals; - - forwardh = LZ4_HASH_VALUE(forwardip); - ref = base + hashtable[h]; - hashtable[h] = ip - base; - } while ((ref < ip - MAX_DISTANCE) || (A32(ref) != A32(ip))); - - /* Catch up */ - while ((ip > anchor) && (ref > (u8 *)source) && - unlikely(ip[-1] == ref[-1])) { - ip--; - ref--; - } - - /* Encode Literal length */ - length = (int)(ip - anchor); - token = op++; - /* check output limit */ - if (unlikely(op + length + (2 + 1 + LASTLITERALS) + - (length >> 8) > oend)) - return 0; - - if (length >= (int)RUN_MASK) { - int len; - *token = (RUN_MASK << ML_BITS); - len = length - RUN_MASK; - for (; len > 254 ; len -= 255) - *op++ = 255; - *op++ = (u8)len; - } else - *token = (length << ML_BITS); - - /* Copy Literals */ - LZ4_BLINDCOPY(anchor, op, length); + LZ4_stream_t_internal* const dictPtr = (LZ4_stream_t_internal*)ctx; + + const BYTE* ip = (const BYTE*) source; + 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; + const BYTE* const matchlimit = iend - LASTLITERALS; + + BYTE* op = (BYTE*) dest; + BYTE* const olimit = op + maxOutputSize; + + U32 forwardH; + size_t refDelta=0; + + /* Init conditions */ + if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported inputSize, too large (or negative) */ + switch(dict) + { + case noDict: + default: + base = (const BYTE*)source; + lowLimit = (const BYTE*)source; + break; + case withPrefix64k: + base = (const BYTE*)source - 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) && (inputSize>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (inputSize> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimit)) goto _last_literals; + + match = LZ4_getPositionOnHash(h, ctx, 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); + LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + + } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0) + || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) + || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) ); + } + + /* Catch up */ + while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; } + + /* Encode Literals */ + { unsigned const litLength = (unsigned)(ip - anchor); + token = op++; + if ((outputLimited) && /* Check output buffer overflow */ + (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit))) + return 0; + if (litLength >= RUN_MASK) { + int len = (int)litLength-RUN_MASK; + *token = (RUN_MASK<= 255 ; len-=255) *op++ = 255; + *op++ = (BYTE)len; + } + else *token = (BYTE)(litLength<> 8) > oend)) - return 0; - if (length >= (int)ML_MASK) { - *token += ML_MASK; - length -= ML_MASK; - for (; length > 509 ; length -= 510) { - *op++ = 255; - *op++ = 255; - } - if (length > 254) { - length -= 255; - *op++ = 255; - } - *op++ = (u8)length; - } else - *token += length; - - /* Test end of chunk */ - if (ip > mflimit) { - anchor = ip; - break; - } - - /* Fill table */ - hashtable[LZ4_HASH_VALUE(ip-2)] = ip - 2 - base; - - /* Test next position */ - ref = base + hashtable[LZ4_HASH_VALUE(ip)]; - hashtable[LZ4_HASH_VALUE(ip)] = ip - base; - if ((ref > ip - (MAX_DISTANCE + 1)) && (A32(ref) == A32(ip))) { - token = op++; - *token = 0; - goto _next_match; - } - - /* Prepare next loop */ - anchor = ip++; - forwardh = LZ4_HASH_VALUE(ip); - } + /* Encode Offset */ + LZ4_writeLE16(op, (U16)(ip-match)); op+=2; + + /* Encode MatchLength */ + { unsigned matchCode; + + if ((dict==usingExtDict) && (lowLimit==dictionary)) { + const BYTE* limit; + match += refDelta; + limit = ip + (dictEnd-match); + if (limit > matchlimit) limit = matchlimit; + matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit); + ip += MINMATCH + matchCode; + if (ip==limit) { + unsigned const 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 */ + (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) + return 0; + if (matchCode >= ML_MASK) { + *token += ML_MASK; + matchCode -= ML_MASK; + LZ4_write32(op, 0xFFFFFFFF); + while (matchCode >= 4*255) op+=4, LZ4_write32(op, 0xFFFFFFFF), matchCode -= 4*255; + op += matchCode / 255; + *op++ = (BYTE)(matchCode % 255); + } else + *token += (BYTE)(matchCode); + } + + anchor = ip; + + /* Test end of chunk */ + if (ip > mflimit) break; + + /* Fill table */ + LZ4_putPosition(ip-2, ctx, tableType, base); + + /* Test next position */ + match = LZ4_getPosition(ip, ctx, tableType, base); + if (dict==usingExtDict) { + if (match < (const BYTE*)source) { + refDelta = dictDelta; + lowLimit = dictionary; + } else { + refDelta = 0; + lowLimit = (const BYTE*)source; + } } + LZ4_putPosition(ip, ctx, tableType, base); + if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1) + && (match+MAX_DISTANCE>=ip) + && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) ) + { token=op++; *token=0; goto _next_match; } + + /* Prepare next loop */ + forwardH = LZ4_hashPosition(++ip, tableType); + } _last_literals: - /* Encode Last Literals */ - lastrun = (int)(iend - anchor); - if (((char *)op - dest) + lastrun + 1 - + ((lastrun + 255 - RUN_MASK) / 255) > (u32)maxoutputsize) - return 0; - - if (lastrun >= (int)RUN_MASK) { - *op++ = (RUN_MASK << ML_BITS); - lastrun -= RUN_MASK; - for (; lastrun > 254 ; lastrun -= 255) - *op++ = 255; - *op++ = (u8)lastrun; - } else - *op++ = (lastrun << ML_BITS); - memcpy(op, anchor, iend - anchor); - op += iend - anchor; - - /* End */ - return (int)(((char *)op) - dest); + /* Encode Last Literals */ + { const size_t lastRun = (size_t)(iend - anchor); + if ( (outputLimited) && /* Check output buffer overflow */ + ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) ) + return 0; + if (lastRun >= RUN_MASK) { + size_t accumulator = lastRun - RUN_MASK; + *op++ = RUN_MASK << ML_BITS; + for(; accumulator >= 255 ; accumulator-=255) *op++ = 255; + *op++ = (BYTE) accumulator; + } else { + *op++ = (BYTE)(lastRun<= LZ4_compressBound(inputSize)) { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(state, source, dest, inputSize, 0, notLimited, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } else { + if (inputSize < LZ4_64Klimit) + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration); + else + return LZ4_compress_generic(state, source, dest, inputSize, maxOutputSize, limitedOutput, LZ4_64bits() ? byU32 : byPtr, noDict, noDictIssue, acceleration); + } +} + + +int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, void* wrkmem, int acceleration) { - u16 *hashtable = (u16 *)ctx; - const u8 *ip = (u8 *) source; - const u8 *anchor = ip; - const u8 *const base = ip; - const u8 *const iend = ip + isize; - const u8 *const mflimit = iend - MFLIMIT; - #define MATCHLIMIT (iend - LASTLITERALS) - - u8 *op = (u8 *) dest; - u8 *const oend = op + maxoutputsize; - int len, length; - const int skipstrength = SKIPSTRENGTH; - u32 forwardh; - int lastrun; - - /* Init */ - if (isize < MINLENGTH) - goto _last_literals; - - memset((void *)hashtable, 0, LZ4_MEM_COMPRESS); - - /* First Byte */ - ip++; - forwardh = LZ4_HASH64K_VALUE(ip); - - /* Main Loop */ - for (;;) { - int findmatchattempts = (1U << skipstrength) + 3; - const u8 *forwardip = ip; - const u8 *ref; - u8 *token; - - /* Find a match */ - do { - u32 h = forwardh; - int step = findmatchattempts++ >> skipstrength; - ip = forwardip; - forwardip = ip + step; - - if (forwardip > mflimit) - goto _last_literals; - - forwardh = LZ4_HASH64K_VALUE(forwardip); - ref = base + hashtable[h]; - hashtable[h] = (u16)(ip - base); - } while (A32(ref) != A32(ip)); - - /* Catch up */ - while ((ip > anchor) && (ref > (u8 *)source) - && (ip[-1] == ref[-1])) { - ip--; - ref--; - } - - /* Encode Literal length */ - length = (int)(ip - anchor); - token = op++; - /* Check output limit */ - if (unlikely(op + length + (2 + 1 + LASTLITERALS) - + (length >> 8) > oend)) - return 0; - if (length >= (int)RUN_MASK) { - *token = (RUN_MASK << ML_BITS); - len = length - RUN_MASK; - for (; len > 254 ; len -= 255) - *op++ = 255; - *op++ = (u8)len; - } else - *token = (length << ML_BITS); - - /* Copy Literals */ - LZ4_BLINDCOPY(anchor, op, length); + int result = LZ4_compress_fast_extState(wrkmem, source, dest, inputSize, maxOutputSize, acceleration); + + return result; +} + + +int LZ4_compress_default(const char* source, char* dest, int inputSize, int maxOutputSize, void* wrkmem) +{ + return LZ4_compress_fast(source, dest, inputSize, maxOutputSize, wrkmem, 1); +} + +/*-****************************** +* *_destSize() variant +********************************/ + +static int LZ4_compress_destSize_generic( + void* const ctx, + const char* const src, + char* const dst, + int* const srcSizePtr, + const int targetDstSize, + const tableType_t tableType) +{ + const BYTE* ip = (const BYTE*) src; + const BYTE* base = (const BYTE*) src; + const BYTE* lowLimit = (const BYTE*) src; + const BYTE* anchor = ip; + const BYTE* const iend = ip + *srcSizePtr; + const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const matchlimit = iend - LASTLITERALS; + + BYTE* op = (BYTE*) dst; + BYTE* const oend = op + targetDstSize; + BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */; + BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */); + BYTE* const oMaxSeq = oMaxLit - 1 /* token */; + + U32 forwardH; + + + /* Init conditions */ + if (targetDstSize < 1) return 0; /* Impossible to store anything */ + if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0; /* Unsupported input size, too large (or negative) */ + if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0; /* Size too large (not within 64K limit) */ + if (*srcSizePtr> LZ4_skipTrigger); + + if (unlikely(forwardIp > mflimit)) goto _last_literals; + + match = LZ4_getPositionOnHash(h, ctx, tableType, base); + forwardH = LZ4_hashPosition(forwardIp, tableType); + LZ4_putPositionOnHash(ip, h, ctx, tableType, base); + + } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip)) + || (LZ4_read32(match) != LZ4_read32(ip)) ); + } + + /* Catch up */ + while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; } + + /* Encode Literal length */ + { unsigned litLength = (unsigned)(ip - anchor); + token = op++; + if (op + ((litLength+240)/255) + litLength > oMaxLit) { + /* Not enough space for a last match */ + op--; + goto _last_literals; + } + if (litLength>=RUN_MASK) { + unsigned len = litLength - RUN_MASK; + *token=(RUN_MASK<= 255 ; len-=255) *op++ = 255; + *op++ = (BYTE)len; + } + else *token = (BYTE)(litLength<> 8) > oend)) - return 0; - if (len >= (int)ML_MASK) { - *token += ML_MASK; - len -= ML_MASK; - for (; len > 509 ; len -= 510) { - *op++ = 255; - *op++ = 255; - } - if (len > 254) { - len -= 255; - *op++ = 255; - } - *op++ = (u8)len; - } else - *token += len; - - /* Test end of chunk */ - if (ip > mflimit) { - anchor = ip; - break; - } - - /* Fill table */ - hashtable[LZ4_HASH64K_VALUE(ip-2)] = (u16)(ip - 2 - base); - - /* Test next position */ - ref = base + hashtable[LZ4_HASH64K_VALUE(ip)]; - hashtable[LZ4_HASH64K_VALUE(ip)] = (u16)(ip - base); - if (A32(ref) == A32(ip)) { - token = op++; - *token = 0; - goto _next_match; - } - - /* Prepare next loop */ - anchor = ip++; - forwardh = LZ4_HASH64K_VALUE(ip); - } + /* 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, tableType, base); + + /* Test next position */ + match = LZ4_getPosition(ip, ctx, tableType, base); + LZ4_putPosition(ip, ctx, 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 */ - lastrun = (int)(iend - anchor); - if (op + lastrun + 1 + (lastrun - RUN_MASK + 255) / 255 > oend) - return 0; - if (lastrun >= (int)RUN_MASK) { - *op++ = (RUN_MASK << ML_BITS); - lastrun -= RUN_MASK; - for (; lastrun > 254 ; lastrun -= 255) - *op++ = 255; - *op++ = (u8)lastrun; - } else - *op++ = (lastrun << ML_BITS); - memcpy(op, anchor, iend - anchor); - op += iend - anchor; - /* End */ - return (int)(((char *)op) - dest); + /* 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, src, dst, srcSizePtr, targetDstSize, byU16); + else + return LZ4_compress_destSize_generic(state, src, dst, srcSizePtr, targetDstSize, LZ4_64bits() ? byU32 : byPtr); + } +} - if (src_len < LZ4_64KLIMIT) - out_len = lz4_compress64kctx(wrkmem, src, dst, src_len, - lz4_compressbound(src_len)); - else - out_len = lz4_compressctx(wrkmem, src, dst, src_len, - lz4_compressbound(src_len)); - if (out_len < 0) - goto exit; +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); +} - *dst_len = out_len; +static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src) +{ + if ((LZ4_dict->currentOffset > 0x80000000) || + ((size_t)LZ4_dict->currentOffset > (size_t)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; ihashTable[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; + } +} - return 0; -exit: - return ret; +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_t_internal*)LZ4_stream; + const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + + const BYTE* smallest = (const BYTE*) source; + if (streamPtr->initCheck) return 0; /* Uninitialized structure detected */ + if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd; + LZ4_renormDictT(streamPtr, smallest); + if (acceleration < 1) acceleration = 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(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration); + else + result = LZ4_compress_generic(LZ4_stream, 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(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration); + else + result = LZ4_compress_generic(LZ4_stream, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration); + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + return result; + } +} + +/*~ + * for backwards compatibility +*/ +int lz4_compress(const unsigned char *src, int src_len, unsigned char *dst, int dst_len, void *wrkmem) { + return LZ4_compress_default(src, dst, src_len, dst_len, wrkmem); +} + +/* Hidden debug function, to force external dictionary mode */ +int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize) +{ + LZ4_stream_t_internal* streamPtr = (LZ4_stream_t_internal*)LZ4_dict; + int result; + const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize; + + const BYTE* smallest = dictEnd; + if (smallest > (const BYTE*) source) smallest = (const BYTE*) source; + LZ4_renormDictT((LZ4_stream_t_internal*)LZ4_dict, smallest); + + result = LZ4_compress_generic(LZ4_dict, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1); + + streamPtr->dictionary = (const BYTE*)source; + streamPtr->dictSize = (U32)inputSize; + streamPtr->currentOffset += (U32)inputSize; + + return result; +} + + +int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize) +{ + LZ4_stream_t_internal* dict = (LZ4_stream_t_internal*) LZ4_dict; + const BYTE* previousDictEnd = dict->dictionary + dict->dictSize; + + if ((U32)dictSize > 64 KB) dictSize = 64 KB; /* useless to define a dictionary > 64 KB */ + if ((U32)dictSize > dict->dictSize) dictSize = dict->dictSize; + + memmove(safeBuffer, previousDictEnd - dictSize, dictSize); + + dict->dictionary = (const BYTE*)safeBuffer; + dict->dictSize = (U32)dictSize; + + return dictSize; } -EXPORT_SYMBOL(lz4_compress); MODULE_LICENSE("Dual BSD/GPL"); MODULE_DESCRIPTION("LZ4 compressor"); + +/* Kernel exports */ +EXPORT_SYMBOL(LZ4_compress_default); +EXPORT_SYMBOL(LZ4_compress_fast); +EXPORT_SYMBOL(LZ4_compress_destSize); +EXPORT_SYMBOL(lz4_compress); diff --git a/lib/lz4/lz4_decompress.c b/lib/lz4/lz4_decompress.c index 6d940c7..bcadc31 100644 --- a/lib/lz4/lz4_decompress.c +++ b/lib/lz4/lz4_decompress.c @@ -1,343 +1,326 @@ /* - * LZ4 Decompressor for Linux kernel - * - * Copyright (C) 2013, LG Electronics, Kyungsik Lee - * - * Based on LZ4 implementation by Yann Collet. - * - * LZ4 - Fast LZ compression algorithm - * Copyright (C) 2011-2012, 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 - * modification, are permitted provided that the following conditions are - * met: - * - * * Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * * Redistributions in binary form must reproduce the above - * copyright notice, this list of conditions and the following disclaimer - * in the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS - * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT - * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR - * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT - * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, - * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT - * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, - * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY - * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - * - * You can contact the author at : - * - LZ4 homepage : http://fastcompression.blogspot.com/p/lz4.html - * - LZ4 source repository : http://code.google.com/p/lz4/ - */ - -#ifndef STATIC + LZ4 - Fast LZ compression algorithm + Copyright (C) 2011-2016, 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 + modification, are permitted provided that the following conditions are + met: + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following disclaimer + in the documentation and/or other materials provided with the + distribution. + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + You can contact the author at : + - LZ4 homepage : http://www.lz4.org + - LZ4 source repository : https://github.com/lz4/lz4 + + Changed for kernel use by: + Sven Schmidt <4sschmid@informatik.uni-hamburg.de> +*/ + +/*-************************************ +* Includes +**************************************/ +#include "lz4defs.h" +#include +#include #include #include -#endif -#include - #include -#include "lz4defs.h" - -static const int dec32table[] = {0, 3, 2, 3, 0, 0, 0, 0}; -#if LZ4_ARCH64 -static const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; -#endif - -static int lz4_uncompress(const char *source, char *dest, int osize) +/*-***************************** +* Decompression functions +*******************************/ +/*! LZ4_decompress_generic() : + * This generic decompression function cover all use cases. + * It shall be instantiated several times, using different sets of directives + * Note that it is important this generic function is really inlined, + * in order to remove useless branches during compilation optimization. + */ +FORCE_INLINE int LZ4_decompress_generic( + const char* const source, + char* const dest, + int inputSize, + int outputSize, /* If endOnInput==endOnInputSize, this value is the max size of Output Buffer. */ + + int endOnInput, /* endOnOutputSize, endOnInputSize */ + int partialDecoding, /* full, partial */ + int targetOutputSize, /* only used if partialDecoding==partial */ + int dict, /* noDict, withPrefix64k, usingExtDict */ + const BYTE* const lowPrefix, /* == dest when no prefix */ + const BYTE* const dictStart, /* only if dict==usingExtDict */ + const size_t dictSize /* note : = 0 if noDict */ + ) { - const BYTE *ip = (const BYTE *) source; - const BYTE *ref; - BYTE *op = (BYTE *) dest; - BYTE * const oend = op + osize; - BYTE *cpy; - unsigned token; - size_t length; - - while (1) { - - /* get runlength */ - token = *ip++; - length = (token >> ML_BITS); - if (length == RUN_MASK) { - size_t len; - - len = *ip++; - for (; len == 255; length += 255) - len = *ip++; - if (unlikely(length > (size_t)(length + len))) - goto _output_error; - length += len; - } - - /* copy literals */ - cpy = op + length; - if (unlikely(cpy > oend - COPYLENGTH)) { - /* - * Error: not enough place for another match - * (min 4) + 5 literals - */ - if (cpy != oend) - goto _output_error; - - memcpy(op, ip, length); - ip += length; - break; /* EOF */ - } - LZ4_WILDCOPY(ip, op, cpy); - ip -= (op - cpy); - op = cpy; - - /* get offset */ - LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip); - ip += 2; - - /* Error: offset create reference outside destination buffer */ - if (unlikely(ref < (BYTE *const) dest)) - goto _output_error; - - /* get matchlength */ - length = token & ML_MASK; - if (length == ML_MASK) { - for (; *ip == 255; length += 255) - ip++; - if (unlikely(length > (size_t)(length + *ip))) - goto _output_error; - length += *ip++; - } - - /* copy repeated sequence */ - if (unlikely((op - ref) < STEPSIZE)) { -#if LZ4_ARCH64 - int dec64 = dec64table[op - ref]; -#else - const int dec64 = 0; -#endif - op[0] = ref[0]; - op[1] = ref[1]; - op[2] = ref[2]; - op[3] = ref[3]; - op += 4; - ref += 4; - ref -= dec32table[op-ref]; - PUT4(ref, op); - op += STEPSIZE - 4; - ref -= dec64; - } else { - LZ4_COPYSTEP(ref, op); - } - cpy = op + length - (STEPSIZE - 4); - if (cpy > (oend - COPYLENGTH)) { - - /* Error: request to write beyond destination buffer */ - if (cpy > oend) - goto _output_error; -#if LZ4_ARCH64 - if ((ref + COPYLENGTH) > oend) -#else - if ((ref + COPYLENGTH) > oend || - (op + COPYLENGTH) > oend) -#endif - goto _output_error; - LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); - while (op < cpy) - *op++ = *ref++; - op = cpy; - /* - * Check EOF (should never happen, since last 5 bytes - * are supposed to be literals) - */ - if (op == oend) - goto _output_error; - continue; - } - LZ4_SECURECOPY(ref, op, cpy); - op = cpy; /* correction */ - } - /* end of decoding */ - return (int) (((char *)ip) - source); - - /* write overflow error detected */ + /* Local Variables */ + const BYTE* ip = (const BYTE*) source; + const BYTE* const iend = ip + inputSize; + + BYTE* op = (BYTE*) dest; + BYTE* const oend = op + outputSize; + BYTE* cpy; + BYTE* oexit = op + targetOutputSize; + const BYTE* const lowLimit = lowPrefix - dictSize; + + const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize; + const unsigned dec32table[] = {4, 1, 2, 1, 4, 4, 4, 4}; + const int dec64table[] = {0, 0, 0, -1, 0, 1, 2, 3}; + + const int safeDecode = (endOnInput==endOnInputSize); + const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB))); + + + /* Special cases */ + if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT; /* targetOutputSize too high => decode everything */ + if ((endOnInput) && (unlikely(outputSize==0))) return ((inputSize==1) && (*ip==0)) ? 0 : -1; /* Empty output buffer */ + if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0?1:-1); + + /* Main Loop : decode sequences */ + while (1) { + unsigned token; + size_t length; + const BYTE* match; + size_t offset; + + /* get literal length */ + token = *ip++; + if ((length=(token>>ML_BITS)) == RUN_MASK) { + unsigned s; + do { + s = *ip++; + length += s; + } while ( likely(endOnInput ? ip(partialDecoding?oexit:oend-MFLIMIT)) || (ip+length>iend-(2+1+LASTLITERALS))) ) + || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) ) + { + if (partialDecoding) { + if (cpy > oend) goto _output_error; /* Error : write attempt beyond end of output buffer */ + if ((endOnInput) && (ip+length > iend)) goto _output_error; /* Error : read attempt beyond end of input buffer */ + } else { + if ((!endOnInput) && (cpy != oend)) goto _output_error; /* Error : block decoding must stop exactly there */ + if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error; /* Error : input must be consumed */ + } + memcpy(op, ip, length); + ip += length; + op += length; + break; /* Necessarily EOF, due to parsing restrictions */ + } + LZ4_wildCopy(op, ip, cpy); + ip += length; op = cpy; + + /* get offset */ + offset = LZ4_readLE16(ip); ip+=2; + match = op - offset; + if ((checkOffset) && (unlikely(match < lowLimit))) goto _output_error; /* Error : offset outside buffers */ + + /* get matchlength */ + length = token & ML_MASK; + if (length == ML_MASK) { + unsigned s; + do { + s = *ip++; + if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error; + length += s; + } while (s==255); + if ((safeDecode) && unlikely((size_t)(op+length)<(size_t)op)) goto _output_error; /* overflow detection */ + } + length += MINMATCH; + + /* check external dictionary */ + if ((dict==usingExtDict) && (match < lowPrefix)) { + if (unlikely(op+length > oend-LASTLITERALS)) goto _output_error; /* doesn't respect parsing restriction */ + + if (length <= (size_t)(lowPrefix-match)) { + /* match can be copied as a single segment from external dictionary */ + memmove(op, dictEnd - (lowPrefix-match), length); + op += length; + } else { + /* match encompass external dictionary and current block */ + size_t const copySize = (size_t)(lowPrefix-match); + size_t const restSize = length - copySize; + memcpy(op, dictEnd - copySize, copySize); + op += copySize; + if (restSize > (size_t)(op-lowPrefix)) { /* overlap copy */ + BYTE* const endOfMatch = op + restSize; + const BYTE* copyFrom = lowPrefix; + while (op < endOfMatch) *op++ = *copyFrom++; + } else { + memcpy(op, lowPrefix, restSize); + op += restSize; + } } + continue; + } + + /* copy match within block */ + cpy = op + length; + if (unlikely(offset<8)) { + const int dec64 = dec64table[offset]; + op[0] = match[0]; + op[1] = match[1]; + op[2] = match[2]; + op[3] = match[3]; + match += dec32table[offset]; + memcpy(op+4, match, 4); + match -= dec64; + } else { LZ4_copy8(op, match); match+=8; } + op += 8; + + if (unlikely(cpy>oend-12)) { + BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1); + if (cpy > oend-LASTLITERALS) goto _output_error; /* Error : last LASTLITERALS bytes must be literals (uncompressed) */ + if (op < oCopyLimit) { + LZ4_wildCopy(op, match, oCopyLimit); + match += oCopyLimit - op; + op = oCopyLimit; + } + while (op16) LZ4_wildCopy(op+8, match+8, cpy); + } + op=cpy; /* correction */ + } + + /* end of decoding */ + if (endOnInput) + return (int) (((char*)op)-dest); /* Nb of output bytes decoded */ + else + return (int) (((const char*)ip)-source); /* Nb of input bytes read */ + + /* Overflow error detected */ _output_error: - return -1; + return (int) (-(((const char*)ip)-source))-1; } -static int lz4_uncompress_unknownoutputsize(const char *source, char *dest, - int isize, size_t maxoutputsize) +int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize) { - const BYTE *ip = (const BYTE *) source; - const BYTE *const iend = ip + isize; - const BYTE *ref; - - - BYTE *op = (BYTE *) dest; - BYTE * const oend = op + maxoutputsize; - BYTE *cpy; - - /* Main Loop */ - while (ip < iend) { - - unsigned token; - size_t length; - - /* get runlength */ - token = *ip++; - length = (token >> ML_BITS); - if (length == RUN_MASK) { - int s = 255; - while ((ip < iend) && (s == 255)) { - s = *ip++; - if (unlikely(length > (size_t)(length + s))) - goto _output_error; - length += s; - } - } - /* copy literals */ - cpy = op + length; - if ((cpy > oend - COPYLENGTH) || - (ip + length > iend - COPYLENGTH)) { - - if (cpy > oend) - goto _output_error;/* writes beyond buffer */ - - if (ip + length != iend) - goto _output_error;/* - * Error: LZ4 format requires - * to consume all input - * at this stage - */ - memcpy(op, ip, length); - op += length; - break;/* Necessarily EOF, due to parsing restrictions */ - } - LZ4_WILDCOPY(ip, op, cpy); - ip -= (op - cpy); - op = cpy; - - /* get offset */ - LZ4_READ_LITTLEENDIAN_16(ref, cpy, ip); - ip += 2; - if (ref < (BYTE * const) dest) - goto _output_error; - /* - * Error : offset creates reference - * outside of destination buffer - */ - - /* get matchlength */ - length = (token & ML_MASK); - if (length == ML_MASK) { - while (ip < iend) { - int s = *ip++; - if (unlikely(length > (size_t)(length + s))) - goto _output_error; - length += s; - if (s == 255) - continue; - break; - } - } - - /* copy repeated sequence */ - if (unlikely((op - ref) < STEPSIZE)) { -#if LZ4_ARCH64 - int dec64 = dec64table[op - ref]; -#else - const int dec64 = 0; -#endif - op[0] = ref[0]; - op[1] = ref[1]; - op[2] = ref[2]; - op[3] = ref[3]; - op += 4; - ref += 4; - ref -= dec32table[op - ref]; - PUT4(ref, op); - op += STEPSIZE - 4; - ref -= dec64; - } else { - LZ4_COPYSTEP(ref, op); - } - cpy = op + length - (STEPSIZE-4); - if (cpy > oend - COPYLENGTH) { - if (cpy > oend) - goto _output_error; /* write outside of buf */ -#if LZ4_ARCH64 - if ((ref + COPYLENGTH) > oend) -#else - if ((ref + COPYLENGTH) > oend || - (op + COPYLENGTH) > oend) -#endif - goto _output_error; - LZ4_SECURECOPY(ref, op, (oend - COPYLENGTH)); - while (op < cpy) - *op++ = *ref++; - op = cpy; - /* - * Check EOF (should never happen, since last 5 bytes - * are supposed to be literals) - */ - if (op == oend) - goto _output_error; - continue; - } - LZ4_SECURECOPY(ref, op, cpy); - op = cpy; /* correction */ - } - /* end of decoding */ - return (int) (((char *) op) - dest); - - /* write overflow error detected */ -_output_error: - return -1; + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0); } -int lz4_decompress(const unsigned char *src, size_t *src_len, - unsigned char *dest, size_t actual_dest_len) +int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize) { - int ret = -1; - int input_len = 0; + return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0); +} - input_len = lz4_uncompress(src, dest, actual_dest_len); - if (input_len < 0) - goto exit_0; - *src_len = input_len; +int LZ4_decompress_fast(const char* source, char* dest, int originalSize) +{ + return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB); +} - return 0; -exit_0: - return ret; +/*! + * LZ4_setStreamDecode() : + * Use this function to instruct where to find the dictionary. + * This function is not necessary if previous data is still available where it was decoded. + * Loading a size of 0 is allowed (same effect as no dictionary). + * Return : 1 if OK, 0 if error + */ +int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize) +{ + LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; + lz4sd->prefixSize = (size_t) dictSize; + lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize; + lz4sd->externalDict = NULL; + lz4sd->extDictSize = 0; + return 1; } -#ifndef STATIC -EXPORT_SYMBOL(lz4_decompress); -#endif -int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len, - unsigned char *dest, size_t *dest_len) +/* +*_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() +*/ +int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize) { - int ret = -1; - int out_len = 0; - - out_len = lz4_uncompress_unknownoutputsize(src, dest, src_len, - *dest_len); - if (out_len < 0) - goto exit_0; - *dest_len = out_len; - - return 0; -exit_0: - return ret; + LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; + int result; + + if (lz4sd->prefixEnd == (BYTE*)dest) { + result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, full, 0, + usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += result; + lz4sd->prefixEnd += result; + } else { + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize; + result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, + endOnInputSize, full, 0, + usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = result; + lz4sd->prefixEnd = (BYTE*)dest + result; + } + + return result; +} + +int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize) +{ + LZ4_streamDecode_t_internal* lz4sd = (LZ4_streamDecode_t_internal*) LZ4_streamDecode; + int result; + + if (lz4sd->prefixEnd == (BYTE*)dest) { + result = LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, full, 0, + usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize += originalSize; + lz4sd->prefixEnd += originalSize; + } else { + lz4sd->extDictSize = lz4sd->prefixSize; + lz4sd->externalDict = (BYTE*)dest - lz4sd->extDictSize; + result = LZ4_decompress_generic(source, dest, 0, originalSize, + endOnOutputSize, full, 0, + usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize); + if (result <= 0) return result; + lz4sd->prefixSize = originalSize; + lz4sd->prefixEnd = (BYTE*)dest + originalSize; + } + + return result; +} + +/* + * for backwards compatibility + */ +int lz4_decompress_unknownoutputsize(const unsigned char *src, size_t src_len, unsigned char *dest, size_t *dest_len) { + return LZ4_decompress_safe(src, dest, (int)src_len, (int)*dest_len); +} + +/* + * for backwards compatibility + */ +int lz4_decompress(const unsigned char *src, size_t *src_len, unsigned char *dest, size_t actual_dest_len) { + return LZ4_decompress_fast(src, dest, (int)actual_dest_len); } -#ifndef STATIC -EXPORT_SYMBOL(lz4_decompress_unknownoutputsize); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_DESCRIPTION("LZ4 Decompressor"); -#endif +MODULE_DESCRIPTION("LZ4 decompressor"); + +/* Kernel exports */ +EXPORT_SYMBOL(LZ4_decompress_fast); +EXPORT_SYMBOL(LZ4_decompress_safe); +EXPORT_SYMBOL(LZ4_decompress_safe_partial); +EXPORT_SYMBOL(lz4_decompress); +EXPORT_SYMBOL(lz4_decompress_unknownoutputsize); diff --git a/lib/lz4/lz4defs.h b/lib/lz4/lz4defs.h index c79d7ea..a024344 100644 --- a/lib/lz4/lz4defs.h +++ b/lib/lz4/lz4defs.h @@ -1,157 +1,272 @@ +#ifndef __LZ4DEFS_H__ +#define __LZ4DEFS_H__ + /* - * lz4defs.h -- architecture specific defines + * lz4defs.h -- common and architecture specific defines * - * Copyright (C) 2013, LG Electronics, Kyungsik Lee + * Copyright (C) 2016, Sven Schmidt <4sschmid@informatik.uni-hamburg.de> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ + #include + +#define FORCE_INLINE static inline + /* * Detects 64 bits mode - */ +*/ #if defined(CONFIG_64BIT) #define LZ4_ARCH64 1 #else #define LZ4_ARCH64 0 #endif +static inline unsigned LZ4_64bits(void) { return LZ4_ARCH64; } + /* - * Architecture-specific macros + * Little/big endian */ -#define BYTE u8 -typedef struct _U16_S { u16 v; } U16_S; -typedef struct _U32_S { u32 v; } U32_S; -typedef struct _U64_S { u64 v; } U64_S; -#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) - -#define A16(x) (((U16_S *)(x))->v) -#define A32(x) (((U32_S *)(x))->v) -#define A64(x) (((U64_S *)(x))->v) - -#define PUT4(s, d) (A32(d) = A32(s)) -#define PUT8(s, d) (A64(d) = A64(s)) - -#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \ - (d = s - A16(p)) - -#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \ - do { \ - A16(p) = v; \ - p += 2; \ - } while (0) -#else /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */ - -#define A64(x) get_unaligned((u64 *)&(((U16_S *)(x))->v)) -#define A32(x) get_unaligned((u32 *)&(((U16_S *)(x))->v)) -#define A16(x) get_unaligned((u16 *)&(((U16_S *)(x))->v)) - -#define PUT4(s, d) \ - put_unaligned(get_unaligned((const u32 *) s), (u32 *) d) -#define PUT8(s, d) \ - put_unaligned(get_unaligned((const u64 *) s), (u64 *) d) - -#define LZ4_READ_LITTLEENDIAN_16(d, s, p) \ - (d = s - get_unaligned_le16(p)) - -#define LZ4_WRITE_LITTLEENDIAN_16(p, v) \ - do { \ - put_unaligned_le16(v, (u16 *)(p)); \ - p += 2; \ - } while (0) +#ifdef __LITTLE_ENDIAN +#define LZ4_isLittleEndian(void) (true) +#else +#define LZ4_isLittleEndian(void) (false) #endif -#define COPYLENGTH 8 -#define ML_BITS 4 -#define ML_MASK ((1U << ML_BITS) - 1) -#define RUN_BITS (8 - ML_BITS) -#define RUN_MASK ((1U << RUN_BITS) - 1) -#define MEMORY_USAGE 14 -#define MINMATCH 4 -#define SKIPSTRENGTH 6 -#define LASTLITERALS 5 -#define MFLIMIT (COPYLENGTH + MINMATCH) -#define MINLENGTH (MFLIMIT + 1) -#define MAXD_LOG 16 -#define MAXD (1 << MAXD_LOG) -#define MAXD_MASK (u32)(MAXD - 1) -#define MAX_DISTANCE (MAXD - 1) -#define HASH_LOG (MAXD_LOG - 1) -#define HASHTABLESIZE (1 << HASH_LOG) -#define MAX_NB_ATTEMPTS 256 -#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH) -#define LZ4_64KLIMIT ((1<<16) + (MFLIMIT - 1)) -#define HASHLOG64K ((MEMORY_USAGE - 2) + 1) -#define HASH64KTABLESIZE (1U << HASHLOG64K) -#define LZ4_HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \ - ((MINMATCH * 8) - (MEMORY_USAGE-2))) -#define LZ4_HASH64K_VALUE(p) (((A32(p)) * 2654435761U) >> \ - ((MINMATCH * 8) - HASHLOG64K)) -#define HASH_VALUE(p) (((A32(p)) * 2654435761U) >> \ - ((MINMATCH * 8) - HASH_LOG)) - -#if LZ4_ARCH64/* 64-bit */ -#define STEPSIZE 8 - -#define LZ4_COPYSTEP(s, d) \ - do { \ - PUT8(s, d); \ - d += 8; \ - s += 8; \ - } while (0) - -#define LZ4_COPYPACKET(s, d) LZ4_COPYSTEP(s, d) - -#define LZ4_SECURECOPY(s, d, e) \ - do { \ - if (d < e) { \ - LZ4_WILDCOPY(s, d, e); \ - } \ - } while (0) -#define HTYPE u32 +/*-************************************ +* Tuning parameter +**************************************/ +/*! * LZ4_MEMORY_USAGE : + * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.) + * Increasing memory usage improves compression ratio + * Reduced memory usage can improve speed, due to cache effect + * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache + */ +#define LZ4_MEMORY_USAGE 10 -#ifdef __BIG_ENDIAN -#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3) +/*-************************************ +* Memory routines +**************************************/ +#include +#include /* memset, memcpy */ +#define MEM_INIT memset + +/*-************************************ +* Basic Types +**************************************/ +#if defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */ +# include + typedef uint8_t BYTE; + typedef uint16_t U16; + typedef uint32_t U32; + typedef int32_t S32; + typedef uint64_t U64; #else -#define LZ4_NBCOMMONBYTES(val) (__builtin_ctzll(val) >> 3) + typedef unsigned char BYTE; + typedef unsigned short U16; + typedef unsigned int U32; + typedef signed int S32; + typedef unsigned long long U64; #endif -#else /* 32-bit */ -#define STEPSIZE 4 +/*-************************************ +* Common Constants +**************************************/ +#define MINMATCH 4 + +#define WILDCOPYLENGTH 8 +#define LASTLITERALS 5 +#define MFLIMIT (WILDCOPYLENGTH+MINMATCH) +static const int LZ4_minLength = (MFLIMIT+1); + +#define KB *(1 <<10) +#define MB *(1 <<20) +#define GB *(1U<<30) + +#define MAXD_LOG 16 +#define MAX_DISTANCE ((1 << MAXD_LOG) - 1) +#define STEPSIZE sizeof(size_t) + +#define ML_BITS 4 +#define ML_MASK ((1U< compression run slower on incompressible data */ + +/*-************************************ +* Reading and writing into memory +**************************************/ + +static inline U16 LZ4_read16(const void* memPtr) +{ + U16 val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static inline U32 LZ4_read32(const void* memPtr) +{ + U32 val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static inline size_t LZ4_read_ARCH(const void* memPtr) +{ + size_t val; memcpy(&val, memPtr, sizeof(val)); return val; +} + +static inline void LZ4_write16(void* memPtr, U16 value) +{ + memcpy(memPtr, &value, sizeof(value)); +} + +static inline void LZ4_write32(void* memPtr, U32 value) +{ + memcpy(memPtr, &value, sizeof(value)); +} + +static inline U16 LZ4_readLE16(const void* memPtr) +{ + if (LZ4_isLittleEndian()) { + return LZ4_read16(memPtr); + } else { + const BYTE* p = (const BYTE*)memPtr; + return (U16)((U16)p[0] + (p[1]<<8)); + } +} + +static inline void LZ4_writeLE16(void* memPtr, U16 value) +{ + if (LZ4_isLittleEndian()) { + LZ4_write16(memPtr, value); + } else { + BYTE* p = (BYTE*)memPtr; + p[0] = (BYTE) value; + p[1] = (BYTE)(value>>8); + } +} -#define LZ4_COPYSTEP(s, d) \ - do { \ - PUT4(s, d); \ - d += 4; \ - s += 4; \ - } while (0) +static inline void LZ4_copy8(void* dst, const void* src) +{ + memcpy(dst,src,8); +} -#define LZ4_COPYPACKET(s, d) \ - do { \ - LZ4_COPYSTEP(s, d); \ - LZ4_COPYSTEP(s, d); \ - } while (0) +/* customized variant of memcpy, which can overwrite up to 7 bytes beyond dstEnd */ +static inline void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd) +{ + BYTE* d = (BYTE*)dstPtr; + const BYTE* s = (const BYTE*)srcPtr; + BYTE* const e = (BYTE*)dstEnd; -#define LZ4_SECURECOPY LZ4_WILDCOPY -#define HTYPE const u8* +#if 0 + const size_t l2 = 8 - (((size_t)d) & (sizeof(void*)-1)); + LZ4_copy8(d,s); if (d>e-9) return; + d+=l2; s+=l2; +#endif /* join to align */ + do { LZ4_copy8(d,s); d+=8; s+=8; } while (d> 3) +#else +#define LZ4_NBCOMMONBYTES(val) (__builtin_clzll(val) >> 3) +#endif +#else #ifdef __BIG_ENDIAN #define LZ4_NBCOMMONBYTES(val) (__builtin_clz(val) >> 3) #else #define LZ4_NBCOMMONBYTES(val) (__builtin_ctz(val) >> 3) #endif - #endif -#define LZ4_WILDCOPY(s, d, e) \ - do { \ - LZ4_COPYPACKET(s, d); \ - } while (d < e) - -#define LZ4_BLINDCOPY(s, d, l) \ - do { \ - u8 *e = (d) + l; \ - LZ4_WILDCOPY(s, d, e); \ - d = e; \ - } while (0) +static inline unsigned LZ4_count(const BYTE* pIn, const BYTE* pMatch, const BYTE* pInLimit) +{ + const BYTE* const pStart = pIn; + + while (likely(pIn - */ - + LZ4 HC - High Compression Mode of LZ4 + Copyright (C) 2011-2015, 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 + modification, are permitted provided that the following conditions are + met: + + * Redistributions of source code must retain the above copyright + notice, this list of conditions and the following disclaimer. + * Redistributions in binary form must reproduce the above + copyright notice, this list of conditions and the following disclaimer + in the documentation and/or other materials provided with the + distribution. + + THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR + A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT + OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, + DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY + THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT + (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE + OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. + + You can contact the author at : + - LZ4 source repository : https://github.com/lz4/lz4 + - LZ4 public forum : https://groups.google.com/forum/#!forum/lz4c + + Changed for kernel use by: + Sven Schmidt <4sschmid@informatik.uni-hamburg.de> +*/ +/* note : lz4hc is not an independent module, it requires lz4.h/lz4.c for proper compilation */ + +/*-************************************ +* Includes +**************************************/ +#include "lz4defs.h" +#include #include #include -#include -#include -#include "lz4defs.h" -struct lz4hc_data { - const u8 *base; - HTYPE hashtable[HASHTABLESIZE]; - u16 chaintable[MAXD]; - const u8 *nexttoupdate; -} __attribute__((__packed__)); +/* ************************************* +* Tuning Parameter +***************************************/ + +#define LZ4HC_DICTIONARY_LOGSIZE 16 +#define LZ4HC_MAXD (1<= 199901L) /* C99 */) +#include -static inline int lz4hc_init(struct lz4hc_data *hc4, const u8 *base) +typedef struct { - memset((void *)hc4->hashtable, 0, sizeof(hc4->hashtable)); - memset(hc4->chaintable, 0xFF, sizeof(hc4->chaintable)); + uint32_t hashTable[LZ4HC_HASHTABLESIZE]; + uint16_t chainTable[LZ4HC_MAXD]; + const uint8_t* end; /* next block here to continue on current prefix */ + const uint8_t* base; /* All index relative to this position */ + const uint8_t* dictBase; /* alternate base for extDict */ + uint8_t* inputBuffer; /* deprecated */ + uint32_t dictLimit; /* below that point, need extDict */ + uint32_t lowLimit; /* below that point, no more dict */ + uint32_t nextToUpdate; /* index from which to continue dictionary update */ + uint32_t compressionLevel; +} LZ4HC_CCtx_internal; -#if LZ4_ARCH64 - hc4->nexttoupdate = base + 1; #else - hc4->nexttoupdate = base; + +typedef struct +{ + unsigned int hashTable[LZ4HC_HASHTABLESIZE]; + unsigned short chainTable[LZ4HC_MAXD]; + const unsigned char* end; /* next block here to continue on current prefix */ + const unsigned char* base; /* All index relative to this position */ + const unsigned char* dictBase; /* alternate base for extDict */ + unsigned char* inputBuffer; /* deprecated */ + unsigned int dictLimit; /* below that point, need extDict */ + unsigned int lowLimit; /* below that point, no more dict */ + unsigned int nextToUpdate; /* index from which to continue dictionary update */ + unsigned int compressionLevel; +} LZ4HC_CCtx_internal; + +#endif + +#define LZ4_STREAMHCSIZE 262192 +#define LZ4_STREAMHCSIZE_SIZET (LZ4_STREAMHCSIZE / sizeof(size_t)) +union LZ4_streamHC_u { + size_t table[LZ4_STREAMHCSIZE_SIZET]; + LZ4HC_CCtx_internal internal_donotuse; +}; /* previously typedef'd to LZ4_streamHC_t */ + +/* ************************************* +* Local Compiler Options +***************************************/ +#if defined(__GNUC__) +# pragma GCC diagnostic ignored "-Wunused-function" +#endif + +#if defined (__clang__) +# pragma clang diagnostic ignored "-Wunused-function" #endif - hc4->base = base; - return 1; + + +/* ************************************* +* Common LZ4 definition +***************************************/ +#define LZ4_COMMONDEFS_ONLY +//#include "lz4.c" + + +/* ************************************* +* Local Constants +***************************************/ +#define OPTIMAL_ML (int)((ML_MASK-1)+MINMATCH) + + +/************************************** +* Local Macros +**************************************/ +#define HASH_FUNCTION(i) (((i) * 2654435761U) >> ((MINMATCH*8)-LZ4HC_HASH_LOG)) +/* #define DELTANEXTU16(p) chainTable[(p) & LZ4HC_MAXD_MASK] */ /* flexible, LZ4HC_MAXD dependent */ +#define DELTANEXTU16(p) chainTable[(U16)(p)] /* faster */ + +static U32 LZ4HC_hashPtr(const void* ptr) { return HASH_FUNCTION(LZ4_read32(ptr)); } + + + +/************************************** +* HC Compression +**************************************/ +static void LZ4HC_init (LZ4HC_CCtx_internal* hc4, const BYTE* start) +{ + MEM_INIT((void*)hc4->hashTable, 0, sizeof(hc4->hashTable)); + MEM_INIT(hc4->chainTable, 0xFF, sizeof(hc4->chainTable)); + hc4->nextToUpdate = 64 KB; + hc4->base = start - 64 KB; + hc4->end = start; + hc4->dictBase = start - 64 KB; + hc4->dictLimit = 64 KB; + hc4->lowLimit = 64 KB; } + /* Update chains up to ip (excluded) */ -static inline void lz4hc_insert(struct lz4hc_data *hc4, const u8 *ip) +FORCE_INLINE void LZ4HC_Insert (LZ4HC_CCtx_internal* hc4, const BYTE* ip) { - u16 *chaintable = hc4->chaintable; - HTYPE *hashtable = hc4->hashtable; -#if LZ4_ARCH64 - const BYTE * const base = hc4->base; -#else - const int base = 0; -#endif - - while (hc4->nexttoupdate < ip) { - const u8 *p = hc4->nexttoupdate; - size_t delta = p - (hashtable[HASH_VALUE(p)] + base); - if (delta > MAX_DISTANCE) - delta = MAX_DISTANCE; - chaintable[(size_t)(p) & MAXD_MASK] = (u16)delta; - hashtable[HASH_VALUE(p)] = (p) - base; - hc4->nexttoupdate++; - } + U16* const chainTable = hc4->chainTable; + U32* const hashTable = hc4->hashTable; + const BYTE* const base = hc4->base; + U32 const target = (U32)(ip - base); + U32 idx = hc4->nextToUpdate; + + while (idx < target) { + U32 const h = LZ4HC_hashPtr(base+idx); + size_t delta = idx - hashTable[h]; + if (delta>MAX_DISTANCE) delta = MAX_DISTANCE; + DELTANEXTU16(idx) = (U16)delta; + hashTable[h] = idx; + idx++; + } + + hc4->nextToUpdate = target; } -static inline size_t lz4hc_commonlength(const u8 *p1, const u8 *p2, - const u8 *const matchlimit) + +FORCE_INLINE int LZ4HC_InsertAndFindBestMatch (LZ4HC_CCtx_internal* hc4, /* Index table will be updated */ + const BYTE* ip, const BYTE* const iLimit, + const BYTE** matchpos, + const int maxNbAttempts) { - const u8 *p1t = p1; + U16* const chainTable = hc4->chainTable; + U32* const HashTable = hc4->hashTable; + const BYTE* const base = hc4->base; + const BYTE* const dictBase = hc4->dictBase; + const U32 dictLimit = hc4->dictLimit; + const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); + U32 matchIndex; + int nbAttempts=maxNbAttempts; + size_t ml=0; + + /* HC4 match finder */ + LZ4HC_Insert(hc4, ip); + matchIndex = HashTable[LZ4HC_hashPtr(ip)]; + + while ((matchIndex>=lowLimit) && (nbAttempts)) { + nbAttempts--; + if (matchIndex >= dictLimit) { + const BYTE* const match = base + matchIndex; + if (*(match+ml) == *(ip+ml) + && (LZ4_read32(match) == LZ4_read32(ip))) + { + size_t const mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, iLimit) + MINMATCH; + if (mlt > ml) { ml = mlt; *matchpos = match; } + } + } else { + const BYTE* const match = dictBase + matchIndex; + if (LZ4_read32(match) == LZ4_read32(ip)) { + size_t mlt; + const BYTE* vLimit = ip + (dictLimit - matchIndex); + if (vLimit > iLimit) vLimit = iLimit; + mlt = LZ4_count(ip+MINMATCH, match+MINMATCH, vLimit) + MINMATCH; + if ((ip+mlt == vLimit) && (vLimit < iLimit)) + mlt += LZ4_count(ip+mlt, base+dictLimit, iLimit); + if (mlt > ml) { ml = mlt; *matchpos = base + matchIndex; } /* virtual matchpos */ + } + } + matchIndex -= DELTANEXTU16(matchIndex); + } + + return (int)ml; +} - while (p1t < matchlimit - (STEPSIZE - 1)) { -#if LZ4_ARCH64 - u64 diff = A64(p2) ^ A64(p1t); -#else - u32 diff = A32(p2) ^ A32(p1t); -#endif - if (!diff) { - p1t += STEPSIZE; - p2 += STEPSIZE; - continue; - } - p1t += LZ4_NBCOMMONBYTES(diff); - return p1t - p1; - } -#if LZ4_ARCH64 - if ((p1t < (matchlimit-3)) && (A32(p2) == A32(p1t))) { - p1t += 4; - p2 += 4; - } -#endif - if ((p1t < (matchlimit - 1)) && (A16(p2) == A16(p1t))) { - p1t += 2; - p2 += 2; - } - if ((p1t < matchlimit) && (*p2 == *p1t)) - p1t++; - return p1t - p1; +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) +{ + U16* const chainTable = hc4->chainTable; + U32* const HashTable = hc4->hashTable; + const BYTE* const base = hc4->base; + const U32 dictLimit = hc4->dictLimit; + const BYTE* const lowPrefixPtr = base + dictLimit; + const U32 lowLimit = (hc4->lowLimit + 64 KB > (U32)(ip-base)) ? hc4->lowLimit : (U32)(ip - base) - (64 KB - 1); + const BYTE* const dictBase = hc4->dictBase; + U32 matchIndex; + int nbAttempts = maxNbAttempts; + int delta = (int)(ip-iLowLimit); + + + /* First Match */ + LZ4HC_Insert(hc4, ip); + matchIndex = HashTable[LZ4HC_hashPtr(ip)]; + + while ((matchIndex>=lowLimit) && (nbAttempts)) { + nbAttempts--; + if (matchIndex >= dictLimit) { + const BYTE* matchPtr = base + matchIndex; + if (*(iLowLimit + longest) == *(matchPtr - delta + longest)) { + if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { + int mlt = MINMATCH + LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, iHighLimit); + int back = 0; + + while ((ip+back > iLowLimit) + && (matchPtr+back > lowPrefixPtr) + && (ip[back-1] == matchPtr[back-1])) + back--; + + mlt -= back; + + if (mlt > longest) { + longest = (int)mlt; + *matchpos = matchPtr+back; + *startpos = ip+back; + } + } + } + } else { + const BYTE* const matchPtr = dictBase + matchIndex; + if (LZ4_read32(matchPtr) == LZ4_read32(ip)) { + size_t mlt; + int back=0; + const BYTE* vLimit = ip + (dictLimit - matchIndex); + if (vLimit > iHighLimit) vLimit = iHighLimit; + mlt = LZ4_count(ip+MINMATCH, matchPtr+MINMATCH, vLimit) + MINMATCH; + if ((ip+mlt == vLimit) && (vLimit < iHighLimit)) + mlt += LZ4_count(ip+mlt, base+dictLimit, iHighLimit); + while ((ip+back > iLowLimit) && (matchIndex+back > lowLimit) && (ip[back-1] == matchPtr[back-1])) back--; + mlt -= back; + if ((int)mlt > longest) { longest = (int)mlt; *matchpos = base + matchIndex + back; *startpos = ip+back; } + } + } + matchIndex -= DELTANEXTU16(matchIndex); + } + + return longest; } -static inline int lz4hc_insertandfindbestmatch(struct lz4hc_data *hc4, - const u8 *ip, const u8 *const matchlimit, const u8 **matchpos) +FORCE_INLINE int LZ4HC_encodeSequence ( + const BYTE** ip, + BYTE** op, + const BYTE** anchor, + int matchLength, + const BYTE* const match, + limitedOutput_directive limitedOutputBuffer, + BYTE* oend) { - u16 *const chaintable = hc4->chaintable; - HTYPE *const hashtable = hc4->hashtable; - const u8 *ref; -#if LZ4_ARCH64 - const BYTE * const base = hc4->base; -#else - const int base = 0; -#endif - int nbattempts = MAX_NB_ATTEMPTS; - size_t repl = 0, ml = 0; - u16 delta; - - /* HC4 match finder */ - lz4hc_insert(hc4, ip); - ref = hashtable[HASH_VALUE(ip)] + base; - - /* potential repetition */ - if (ref >= ip-4) { - /* confirmed */ - if (A32(ref) == A32(ip)) { - delta = (u16)(ip-ref); - repl = ml = lz4hc_commonlength(ip + MINMATCH, - ref + MINMATCH, matchlimit) + MINMATCH; - *matchpos = ref; - } - ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK]; - } - - while ((ref >= ip - MAX_DISTANCE) && nbattempts) { - nbattempts--; - if (*(ref + ml) == *(ip + ml)) { - if (A32(ref) == A32(ip)) { - size_t mlt = - lz4hc_commonlength(ip + MINMATCH, - ref + MINMATCH, matchlimit) + MINMATCH; - if (mlt > ml) { - ml = mlt; - *matchpos = ref; - } - } - } - ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK]; - } - - /* Complete table */ - if (repl) { - const BYTE *ptr = ip; - const BYTE *end; - end = ip + repl - (MINMATCH-1); - /* Pre-Load */ - while (ptr < end - delta) { - chaintable[(size_t)(ptr) & MAXD_MASK] = delta; - ptr++; - } - do { - chaintable[(size_t)(ptr) & MAXD_MASK] = delta; - /* Head of chain */ - hashtable[HASH_VALUE(ptr)] = (ptr) - base; - ptr++; - } while (ptr < end); - hc4->nexttoupdate = end; - } - - return (int)ml; + int length; + BYTE* token; + + /* Encode Literal length */ + length = (int)(*ip - *anchor); + token = (*op)++; + if ((limitedOutputBuffer) && ((*op + (length>>8) + length + (2 + 1 + LASTLITERALS)) > oend)) return 1; /* Check output limit */ + if (length>=(int)RUN_MASK) { int len; *token=(RUN_MASK< 254 ; len-=255) *(*op)++ = 255; *(*op)++ = (BYTE)len; } + else *token = (BYTE)(length<>8) + (1 + LASTLITERALS) > oend)) return 1; /* Check output limit */ + if (length>=(int)ML_MASK) { + *token += ML_MASK; + length -= ML_MASK; + for(; length > 509 ; length-=510) { *(*op)++ = 255; *(*op)++ = 255; } + if (length > 254) { length-=255; *(*op)++ = 255; } + *(*op)++ = (BYTE)length; + } else { + *token += (BYTE)(length); + } + + /* Prepare next loop */ + *ip += matchLength; + *anchor = *ip; + + return 0; } -static inline int lz4hc_insertandgetwidermatch(struct lz4hc_data *hc4, - const u8 *ip, const u8 *startlimit, const u8 *matchlimit, int longest, - const u8 **matchpos, const u8 **startpos) + +static int LZ4HC_compress_generic ( + LZ4HC_CCtx_internal* const ctx, + const char* const source, + char* const dest, + int const inputSize, + int const maxOutputSize, + int compressionLevel, + limitedOutput_directive limit + ) { - u16 *const chaintable = hc4->chaintable; - HTYPE *const hashtable = hc4->hashtable; -#if LZ4_ARCH64 - const BYTE * const base = hc4->base; -#else - const int base = 0; -#endif - const u8 *ref; - int nbattempts = MAX_NB_ATTEMPTS; - int delta = (int)(ip - startlimit); - - /* First Match */ - lz4hc_insert(hc4, ip); - ref = hashtable[HASH_VALUE(ip)] + base; - - while ((ref >= ip - MAX_DISTANCE) && (ref >= hc4->base) - && (nbattempts)) { - nbattempts--; - if (*(startlimit + longest) == *(ref - delta + longest)) { - if (A32(ref) == A32(ip)) { - const u8 *reft = ref + MINMATCH; - const u8 *ipt = ip + MINMATCH; - const u8 *startt = ip; - - while (ipt < matchlimit-(STEPSIZE - 1)) { - #if LZ4_ARCH64 - u64 diff = A64(reft) ^ A64(ipt); - #else - u32 diff = A32(reft) ^ A32(ipt); - #endif - - if (!diff) { - ipt += STEPSIZE; - reft += STEPSIZE; - continue; - } - ipt += LZ4_NBCOMMONBYTES(diff); - goto _endcount; - } - #if LZ4_ARCH64 - if ((ipt < (matchlimit - 3)) - && (A32(reft) == A32(ipt))) { - ipt += 4; - reft += 4; - } - ipt += 2; - #endif - if ((ipt < (matchlimit - 1)) - && (A16(reft) == A16(ipt))) { - reft += 2; - } - if ((ipt < matchlimit) && (*reft == *ipt)) - ipt++; -_endcount: - reft = ref; - - while ((startt > startlimit) - && (reft > hc4->base) - && (startt[-1] == reft[-1])) { - startt--; - reft--; - } - - if ((ipt - startt) > longest) { - longest = (int)(ipt - startt); - *matchpos = reft; - *startpos = startt; - } - } - } - ref -= (size_t)chaintable[(size_t)(ref) & MAXD_MASK]; - } - return longest; + const BYTE* ip = (const BYTE*) source; + const BYTE* anchor = ip; + const BYTE* const iend = ip + inputSize; + const BYTE* const mflimit = iend - MFLIMIT; + const BYTE* const matchlimit = (iend - LASTLITERALS); + + BYTE* op = (BYTE*) dest; + BYTE* const oend = op + maxOutputSize; + + unsigned maxNbAttempts; + int ml, ml2, ml3, ml0; + const BYTE* ref = NULL; + const BYTE* start2 = NULL; + const BYTE* ref2 = NULL; + const BYTE* start3 = NULL; + const BYTE* ref3 = NULL; + const BYTE* start0; + const BYTE* ref0; + + /* init */ + if (compressionLevel > LZ4HC_MAX_CLEVEL) compressionLevel = LZ4HC_MAX_CLEVEL; + if (compressionLevel < 1) compressionLevel = LZ4HC_DEFAULT_CLEVEL; + maxNbAttempts = 1 << (compressionLevel-1); + ctx->end += inputSize; + + ip++; + + /* Main Loop */ + while (ip < mflimit) { + ml = LZ4HC_InsertAndFindBestMatch (ctx, ip, matchlimit, (&ref), maxNbAttempts); + if (!ml) { ip++; continue; } + + /* saved, in case we would skip too much */ + start0 = ip; + ref0 = ref; + ml0 = ml; + +_Search2: + if (ip+ml < mflimit) + ml2 = LZ4HC_InsertAndGetWiderMatch(ctx, ip + ml - 2, ip + 0, matchlimit, ml, &ref2, &start2, maxNbAttempts); + else ml2 = ml; + + if (ml2 == ml) { /* No better match */ + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + continue; + } + + if (start0 < ip) { + if (start2 < ip + ml0) { /* empirical */ + ip = start0; + ref = ref0; + ml = ml0; + } + } + + /* Here, start0==ip */ + if ((start2 - ip) < 3) { /* First Match too small : removed */ + ml = ml2; + ip = start2; + ref =ref2; + goto _Search2; + } + +_Search3: + /* + * Currently we have : + * ml2 > ml1, and + * ip1+3 <= ip2 (usually < ip1+ml1) + */ + if ((start2 - ip) < OPTIMAL_ML) { + int correction; + int new_ml = ml; + if (new_ml > OPTIMAL_ML) new_ml = OPTIMAL_ML; + if (ip+new_ml > start2 + ml2 - MINMATCH) new_ml = (int)(start2 - ip) + ml2 - MINMATCH; + correction = new_ml - (int)(start2 - ip); + if (correction > 0) { + start2 += correction; + ref2 += correction; + ml2 -= correction; + } + } + /* Now, we have start2 = ip+new_ml, with new_ml = min(ml, OPTIMAL_ML=18) */ + + if (start2 + ml2 < mflimit) + ml3 = LZ4HC_InsertAndGetWiderMatch(ctx, start2 + ml2 - 3, start2, matchlimit, ml2, &ref3, &start3, maxNbAttempts); + else ml3 = ml2; + + if (ml3 == ml2) { /* No better match : 2 sequences to encode */ + /* ip & ref are known; Now for ml */ + if (start2 < ip+ml) ml = (int)(start2 - ip); + /* Now, encode 2 sequences */ + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + ip = start2; + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml2, ref2, limit, oend)) return 0; + continue; + } + + if (start3 < ip+ml+3) { /* Not enough space for match 2 : remove it */ + if (start3 >= (ip+ml)) { /* can write Seq1 immediately ==> Seq2 is removed, so Seq3 becomes Seq1 */ + if (start2 < ip+ml) { + int correction = (int)(ip+ml - start2); + start2 += correction; + ref2 += correction; + ml2 -= correction; + if (ml2 < MINMATCH) { + start2 = start3; + ref2 = ref3; + ml2 = ml3; + } + } + + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + ip = start3; + ref = ref3; + ml = ml3; + + start0 = start2; + ref0 = ref2; + ml0 = ml2; + goto _Search2; + } + + start2 = start3; + ref2 = ref3; + ml2 = ml3; + goto _Search3; + } + + /* + * OK, now we have 3 ascending matches; let's write at least the first one + * ip & ref are known; Now for ml + */ + if (start2 < ip+ml) { + if ((start2 - ip) < (int)ML_MASK) { + int correction; + if (ml > OPTIMAL_ML) ml = OPTIMAL_ML; + if (ip + ml > start2 + ml2 - MINMATCH) ml = (int)(start2 - ip) + ml2 - MINMATCH; + correction = ml - (int)(start2 - ip); + if (correction > 0) { + start2 += correction; + ref2 += correction; + ml2 -= correction; + } + } else { + ml = (int)(start2 - ip); + } + } + if (LZ4HC_encodeSequence(&ip, &op, &anchor, ml, ref, limit, oend)) return 0; + + ip = start2; + ref = ref2; + ml = ml2; + + start2 = start3; + ref2 = ref3; + ml2 = ml3; + + goto _Search3; + } + + /* Encode Last Literals */ + { int lastRun = (int)(iend - anchor); + if ((limit) && (((char*)op - dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize)) return 0; /* Check output limit */ + if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK< 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } + else *op++ = (BYTE)(lastRun<internal_donotuse; + if (((size_t)(state)&(sizeof(void*)-1)) != 0) return 0; /* Error : state is not aligned for pointers (32 or 64 bits) */ + LZ4HC_init (ctx, (const BYTE*)src); + if (maxDstSize < LZ4_compressBound(srcSize)) + return LZ4HC_compress_generic (ctx, src, dst, srcSize, maxDstSize, compressionLevel, limitedOutput); + else + return LZ4HC_compress_generic (ctx, src, dst, srcSize, maxDstSize, compressionLevel, notLimited); } -static inline int lz4_encodesequence(const u8 **ip, u8 **op, const u8 **anchor, - int ml, const u8 *ref) +int LZ4_compress_HC(const char* src, char* dst, int srcSize, int maxDstSize, int compressionLevel, void* wrkmem) { - int length, len; - u8 *token; - - /* Encode Literal length */ - length = (int)(*ip - *anchor); - token = (*op)++; - if (length >= (int)RUN_MASK) { - *token = (RUN_MASK << ML_BITS); - len = length - RUN_MASK; - for (; len > 254 ; len -= 255) - *(*op)++ = 255; - *(*op)++ = (u8)len; - } else - *token = (length << ML_BITS); - - /* Copy Literals */ - LZ4_BLINDCOPY(*anchor, *op, length); - - /* Encode Offset */ - LZ4_WRITE_LITTLEENDIAN_16(*op, (u16)(*ip - ref)); - - /* Encode MatchLength */ - len = (int)(ml - MINMATCH); - if (len >= (int)ML_MASK) { - *token += ML_MASK; - len -= ML_MASK; - for (; len > 509 ; len -= 510) { - *(*op)++ = 255; - *(*op)++ = 255; - } - if (len > 254) { - len -= 255; - *(*op)++ = 255; - } - *(*op)++ = (u8)len; - } else - *token += len; - - /* Prepare next loop */ - *ip += ml; - *anchor = *ip; - - return 0; + return LZ4_compress_HC_extStateHC(wrkmem, src, dst, srcSize, maxDstSize, compressionLevel); } -static int lz4_compresshcctx(struct lz4hc_data *ctx, - const char *source, - char *dest, - int isize) +int lz4hc_compress(const unsigned char *src, size_t src_len, unsigned char *dst, size_t *dst_len, void *wrkmem) { - const u8 *ip = (const u8 *)source; - const u8 *anchor = ip; - const u8 *const iend = ip + isize; - const u8 *const mflimit = iend - MFLIMIT; - const u8 *const matchlimit = (iend - LASTLITERALS); - - u8 *op = (u8 *)dest; - - int ml, ml2, ml3, ml0; - const u8 *ref = NULL; - const u8 *start2 = NULL; - const u8 *ref2 = NULL; - const u8 *start3 = NULL; - const u8 *ref3 = NULL; - const u8 *start0; - const u8 *ref0; - int lastrun; - - ip++; - - /* Main Loop */ - while (ip < mflimit) { - ml = lz4hc_insertandfindbestmatch(ctx, ip, matchlimit, (&ref)); - if (!ml) { - ip++; - continue; - } - - /* saved, in case we would skip too much */ - start0 = ip; - ref0 = ref; - ml0 = ml; -_search2: - if (ip+ml < mflimit) - ml2 = lz4hc_insertandgetwidermatch(ctx, ip + ml - 2, - ip + 1, matchlimit, ml, &ref2, &start2); - else - ml2 = ml; - /* No better match */ - if (ml2 == ml) { - lz4_encodesequence(&ip, &op, &anchor, ml, ref); - continue; - } - - if (start0 < ip) { - /* empirical */ - if (start2 < ip + ml0) { - ip = start0; - ref = ref0; - ml = ml0; - } - } - /* - * Here, start0==ip - * First Match too small : removed - */ - if ((start2 - ip) < 3) { - ml = ml2; - ip = start2; - ref = ref2; - goto _search2; - } - -_search3: - /* - * Currently we have : - * ml2 > ml1, and - * ip1+3 <= ip2 (usually < ip1+ml1) - */ - if ((start2 - ip) < OPTIMAL_ML) { - int correction; - int new_ml = ml; - if (new_ml > OPTIMAL_ML) - new_ml = OPTIMAL_ML; - if (ip + new_ml > start2 + ml2 - MINMATCH) - new_ml = (int)(start2 - ip) + ml2 - MINMATCH; - correction = new_ml - (int)(start2 - ip); - if (correction > 0) { - start2 += correction; - ref2 += correction; - ml2 -= correction; - } - } - /* - * Now, we have start2 = ip+new_ml, - * with new_ml=min(ml, OPTIMAL_ML=18) - */ - if (start2 + ml2 < mflimit) - ml3 = lz4hc_insertandgetwidermatch(ctx, - start2 + ml2 - 3, start2, matchlimit, - ml2, &ref3, &start3); - else - ml3 = ml2; - - /* No better match : 2 sequences to encode */ - if (ml3 == ml2) { - /* ip & ref are known; Now for ml */ - if (start2 < ip+ml) - ml = (int)(start2 - ip); - - /* Now, encode 2 sequences */ - lz4_encodesequence(&ip, &op, &anchor, ml, ref); - ip = start2; - lz4_encodesequence(&ip, &op, &anchor, ml2, ref2); - continue; - } - - /* Not enough space for match 2 : remove it */ - if (start3 < ip + ml + 3) { - /* - * can write Seq1 immediately ==> Seq2 is removed, - * so Seq3 becomes Seq1 - */ - if (start3 >= (ip + ml)) { - if (start2 < ip + ml) { - int correction = - (int)(ip + ml - start2); - start2 += correction; - ref2 += correction; - ml2 -= correction; - if (ml2 < MINMATCH) { - start2 = start3; - ref2 = ref3; - ml2 = ml3; - } - } - - lz4_encodesequence(&ip, &op, &anchor, ml, ref); - ip = start3; - ref = ref3; - ml = ml3; - - start0 = start2; - ref0 = ref2; - ml0 = ml2; - goto _search2; - } - - start2 = start3; - ref2 = ref3; - ml2 = ml3; - goto _search3; - } - - /* - * OK, now we have 3 ascending matches; let's write at least - * the first one ip & ref are known; Now for ml - */ - if (start2 < ip + ml) { - if ((start2 - ip) < (int)ML_MASK) { - int correction; - if (ml > OPTIMAL_ML) - ml = OPTIMAL_ML; - if (ip + ml > start2 + ml2 - MINMATCH) - ml = (int)(start2 - ip) + ml2 - - MINMATCH; - correction = ml - (int)(start2 - ip); - if (correction > 0) { - start2 += correction; - ref2 += correction; - ml2 -= correction; - } - } else - ml = (int)(start2 - ip); - } - lz4_encodesequence(&ip, &op, &anchor, ml, ref); - - ip = start2; - ref = ref2; - ml = ml2; - - start2 = start3; - ref2 = ref3; - ml2 = ml3; - - goto _search3; - } - - /* Encode Last Literals */ - lastrun = (int)(iend - anchor); - if (lastrun >= (int)RUN_MASK) { - *op++ = (RUN_MASK << ML_BITS); - lastrun -= RUN_MASK; - for (; lastrun > 254 ; lastrun -= 255) - *op++ = 255; - *op++ = (u8) lastrun; - } else - *op++ = (lastrun << ML_BITS); - memcpy(op, anchor, iend - anchor); - op += iend - anchor; - /* End */ - return (int) (((char *)op) - dest); + return LZ4_compress_HC(src, dst, (int)src_len, (int)((size_t)dst_len), LZ4HC_DEFAULT_CLEVEL, wrkmem); } -int lz4hc_compress(const unsigned char *src, size_t src_len, - unsigned char *dst, size_t *dst_len, void *wrkmem) +/************************************** +* Streaming Functions +**************************************/ + +int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr, const char* dictionary, int dictSize) { - int ret = -1; - int out_len = 0; + LZ4HC_CCtx_internal* ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + if (dictSize > 64 KB) { + dictionary += dictSize - 64 KB; + dictSize = 64 KB; + } + LZ4HC_init (ctxPtr, (const BYTE*)dictionary); + if (dictSize >= 4) LZ4HC_Insert (ctxPtr, (const BYTE*)dictionary +(dictSize-3)); + ctxPtr->end = (const BYTE*)dictionary + dictSize; + return dictSize; +} + - struct lz4hc_data *hc4 = (struct lz4hc_data *)wrkmem; - lz4hc_init(hc4, (const u8 *)src); - out_len = lz4_compresshcctx((struct lz4hc_data *)hc4, (const u8 *)src, - (char *)dst, (int)src_len); +/* compression */ - if (out_len < 0) - goto exit; +static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBlock) +{ + if (ctxPtr->end >= ctxPtr->base + 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->end = newBlock; + ctxPtr->nextToUpdate = ctxPtr->dictLimit; /* match referencing will resume from there */ +} - *dst_len = out_len; - return 0; +static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr, + const char* source, char* dest, + int inputSize, int maxOutputSize, limitedOutput_directive limit) +{ + LZ4HC_CCtx_internal* ctxPtr = &LZ4_streamHCPtr->internal_donotuse; + /* auto-init if forgotten */ + if (ctxPtr->base == NULL) LZ4HC_init (ctxPtr, (const BYTE*) source); + + /* Check overflow */ + if ((size_t)(ctxPtr->end - ctxPtr->base) > 2 GB) { + size_t dictSize = (size_t)(ctxPtr->end - ctxPtr->base) - ctxPtr->dictLimit; + if (dictSize > 64 KB) dictSize = 64 KB; + LZ4_loadDictHC(LZ4_streamHCPtr, (const char*)(ctxPtr->end) - dictSize, (int)dictSize); + } + + /* Check if blocks follow each other */ + if ((const BYTE*)source != ctxPtr->end) LZ4HC_setExternalDict(ctxPtr, (const BYTE*)source); + + /* Check overlapping input/dictionary space */ + { const BYTE* sourceEnd = (const BYTE*) source + inputSize; + const BYTE* const dictBegin = ctxPtr->dictBase + ctxPtr->lowLimit; + const BYTE* const dictEnd = ctxPtr->dictBase + ctxPtr->dictLimit; + if ((sourceEnd > dictBegin) && ((const BYTE*)source < dictEnd)) { + if (sourceEnd > dictEnd) sourceEnd = dictEnd; + ctxPtr->lowLimit = (U32)(sourceEnd - ctxPtr->dictBase); + if (ctxPtr->dictLimit - ctxPtr->lowLimit < 4) ctxPtr->lowLimit = ctxPtr->dictLimit; + } + } + + return LZ4HC_compress_generic (ctxPtr, source, dest, inputSize, maxOutputSize, ctxPtr->compressionLevel, limit); +} -exit: - return ret; +int LZ4_compress_HC_continue (LZ4_streamHC_t* LZ4_streamHCPtr, const char* source, char* dest, int inputSize, int maxOutputSize) +{ + if (maxOutputSize < LZ4_compressBound(inputSize)) + return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, limitedOutput); + else + return LZ4_compressHC_continue_generic (LZ4_streamHCPtr, source, dest, inputSize, maxOutputSize, notLimited); } -EXPORT_SYMBOL(lz4hc_compress); MODULE_LICENSE("Dual BSD/GPL"); -MODULE_DESCRIPTION("LZ4HC compressor"); +MODULE_DESCRIPTION("LZ4 HC compressor"); + +/* Kernel exports */ +EXPORT_SYMBOL(LZ4_compress_HC); +EXPORT_SYMBOL(lz4hc_compress); -- 2.1.4