/* * Copyright (c) 2020 Red Hat, Inc. * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License * as published by the Free Software Foundation; either version 2 * of the License, or (at your option) any later version. * * This program is distributed in the hope that it will be useful, * but WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA * 02110-1301, USA. * * $Id: //eng/vdo-releases/aluminum/src/c++/vdo/base/lz4.c#2 $ */ // Get the memcpy fixup from common.h. #include "common.h" /* 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/ */ /* * With authors permission dual licensed as BSD/GPL for linux kernel * * Origin: http://lz4.googlecode.com/svn/trunk * Revision: 88 */ //************************************** // Tuning parameters //************************************** // 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 MEMORY_USAGE 14 // NOTCOMPRESSIBLE_DETECTIONLEVEL : // Decreasing this value will make the algorithm skip faster data segments considered "incompressible" // This may decrease compression ratio dramatically, but will be faster on incompressible data // Increasing this value will make the algorithm search more before declaring a segment "incompressible" // This could improve compression a bit, but will be slower on incompressible data // The default value (6) is recommended #define NOTCOMPRESSIBLE_DETECTIONLEVEL 6 // BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE : // This will provide a small boost to performance for big endian cpu, but the resulting compressed stream will be incompatible with little-endian CPU. // You can set this option to 1 in situations where data will remain within closed environment // This option is useless on Little_Endian CPU (such as x86) //#define BIG_ENDIAN_NATIVE_BUT_INCOMPATIBLE 1 //************************************** // CPU Feature Detection //************************************** // 32 or 64 bits ? #if (defined(__x86_64__) || defined(__x86_64) || defined(__amd64__) || defined(__amd64) || defined(__ppc64__) || defined(_WIN64) || defined(__LP64__) || defined(_LP64) ) // Detects 64 bits mode # define LZ4_ARCH64 1 #else # define LZ4_ARCH64 0 #endif // Little Endian or Big Endian ? // GCC normally defines these three macros (and PDP-endian which we ignore). #if !defined(__ORDER_LITTLE_ENDIAN__) || !defined(__ORDER_BIG_ENDIAN__) \ || !defined(__BYTE_ORDER__) #error "GCC byte order macros not defined?" #endif #if __BYTE_ORDER__ == __ORDER_BIG_ENDIAN__ # define LZ4_BIG_ENDIAN 1 #elif __BYTE_ORDER__ != __ORDER_LITTLE_ENDIAN__ # error "fix byte order check" #endif // Unaligned memory access is automatically enabled for "common" CPU, such as x86. // For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected // If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance #if defined(__ARM_FEATURE_UNALIGNED) # define LZ4_FORCE_UNALIGNED_ACCESS 1 #endif // Define this parameter if your target system or compiler does not support hardware bit count #if defined(_MSC_VER) && defined(_WIN32_WCE) // Visual Studio for Windows CE does not support Hardware bit count # define LZ4_FORCE_SW_BITCOUNT #endif //************************************** // Compiler Options //************************************** #if __STDC_VERSION__ >= 199901L // C99 /* "restrict" is a known keyword */ #else # define restrict // Disable restrict #endif #define _GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__) #ifdef _MSC_VER // Visual Studio # include // For Visual 2005 # if LZ4_ARCH64 // 64-bit # pragma intrinsic(_BitScanForward64) // For Visual 2005 # pragma intrinsic(_BitScanReverse64) // For Visual 2005 # else # pragma intrinsic(_BitScanForward) // For Visual 2005 # pragma intrinsic(_BitScanReverse) // For Visual 2005 # endif #endif #ifdef _MSC_VER # define lz4_bswap16(x) _byteswap_ushort(x) #else # define lz4_bswap16(x) ((unsigned short int) ((((x) >> 8) & 0xffu) | (((x) & 0xffu) << 8))) #endif #if (_GCC_VERSION >= 302) || (__INTEL_COMPILER >= 800) || defined(__clang__) # define expect(expr,value) (__builtin_expect ((expr),(value)) ) #else # define expect(expr,value) (expr) #endif //************************************** // Includes //************************************** #ifdef __KERNEL__ # include // for memset #else /* __KERNEL__ */ # include // for malloc # include // for memset #endif /* __KERNEL__ */ #include "lz4.h" //************************************** // Basic Types //************************************** #if defined(_MSC_VER) // Visual Studio does not support 'stdint' natively # define BYTE unsigned __int8 # define U16 unsigned __int16 # define U32 unsigned __int32 # define S32 __int32 # define U64 unsigned __int64 #else # ifdef __KERNEL__ # include # else /* __KERNEL__ */ # include # endif /* __KERNEL__ */ # define BYTE uint8_t # define U16 uint16_t # define U32 uint32_t # define S32 int32_t # define U64 uint64_t #endif #ifndef LZ4_FORCE_UNALIGNED_ACCESS # pragma pack(push, 1) #endif typedef struct _U16_S { U16 v; } U16_S; typedef struct _U32_S { U32 v; } U32_S; typedef struct _U64_S { U64 v; } U64_S; #ifndef LZ4_FORCE_UNALIGNED_ACCESS # pragma pack(pop) #endif #define A64(x) (((U64_S *)(x))->v) #define A32(x) (((U32_S *)(x))->v) #define A16(x) (((U16_S *)(x))->v) //************************************** // Constants //************************************** #define MINMATCH 4 #define HASH_LOG (MEMORY_USAGE-2) #define HASHTABLESIZE (1 << HASH_LOG) #define HASH_MASK (HASHTABLESIZE - 1) #define SKIPSTRENGTH (NOTCOMPRESSIBLE_DETECTIONLEVEL>2?NOTCOMPRESSIBLE_DETECTIONLEVEL:2) #define STACKLIMIT 13 #define HEAPMODE (HASH_LOG>STACKLIMIT) // Defines if memory is allocated into the stack (local variable), or into the heap (malloc()). #define COPYLENGTH 8 #define LASTLITERALS 5 #define MFLIMIT (COPYLENGTH+MINMATCH) #define MINLENGTH (MFLIMIT+1) #define MAXD_LOG 16 #define MAX_DISTANCE ((1 << MAXD_LOG) - 1) #define ML_BITS 4 #define ML_MASK ((1U<> ((MINMATCH*8)-HASH_LOG)) #define LZ4_HASH_VALUE(p) LZ4_HASH_FUNCTION(A32(p)) #define LZ4_WILDCOPY(s,d,e) do { LZ4_COPYPACKET(s,d) } while (d>3); #elif defined(__GNUC__) && (_GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_clzll(val) >> 3); #else int r; if (!(val>>32)) { r=4; } else { r=0; val>>=32; } if (!(val>>16)) { r+=2; val>>=8; } else { val>>=24; } r += (!val); return r; #endif #else #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; _BitScanForward64( &r, val ); return (int)(r>>3); #elif defined(__GNUC__) && (_GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_ctzll(val) >> 3); #else static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2, 0, 3, 1, 3, 1, 4, 2, 7, 0, 2, 3, 6, 1, 5, 3, 5, 1, 3, 4, 4, 2, 5, 6, 7, 7, 0, 1, 2, 3, 3, 4, 6, 2, 6, 5, 5, 3, 4, 5, 6, 7, 1, 2, 4, 6, 4, 4, 5, 7, 2, 6, 5, 7, 6, 7, 7 }; return DeBruijnBytePos[((U64)((val & -val) * 0x0218A392CDABBD3F)) >> 58]; #endif #endif } #else static inline int LZ4_NbCommonBytes (register U32 val) { #if defined(LZ4_BIG_ENDIAN) #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; _BitScanReverse( &r, val ); return (int)(r>>3); #elif defined(__GNUC__) && (_GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_clz(val) >> 3); #else int r; if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; } r += (!val); return r; #endif #else #if defined(_MSC_VER) && !defined(LZ4_FORCE_SW_BITCOUNT) unsigned long r = 0; _BitScanForward( &r, val ); return (int)(r>>3); #elif defined(__GNUC__) && (_GCC_VERSION >= 304) && !defined(LZ4_FORCE_SW_BITCOUNT) return (__builtin_ctz(val) >> 3); #else static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0, 3, 2, 2, 1, 3, 2, 0, 1, 3, 3, 1, 2, 2, 2, 2, 0, 3, 1, 2, 0, 1, 0, 1, 1 }; return DeBruijnBytePos[((U32)((val & -(S32)val) * 0x077CB531U)) >> 27]; #endif #endif } #endif //****************************** // Compression functions //****************************** // 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 static inline int LZ4_compressCtx(void** ctx, const char* source, char* dest, int isize, int maxOutputSize) { #if HEAPMODE struct refTables *srt = (struct refTables *) (*ctx); HTYPE* HashTable; #else HTYPE HashTable[HASHTABLESIZE] = {0}; #endif const BYTE* ip = (BYTE*) source; INITBASE(base); const BYTE* anchor = ip; const BYTE* const iend = ip + isize; const BYTE* const mflimit = iend - MFLIMIT; #define matchlimit (iend - LASTLITERALS) BYTE* op = (BYTE*) dest; BYTE* const oend = op + maxOutputSize; int len, length; const int skipStrength = SKIPSTRENGTH; U32 forwardH; // Init if (isizehashTable); memset((void*)HashTable, 0, sizeof(srt->hashTable)); #else (void) ctx; #endif // First Byte HashTable[LZ4_HASH_VALUE(ip)] = ip - base; ip++; forwardH = LZ4_HASH_VALUE(ip); // Main Loop for ( ; ; ) { int findMatchAttempts = (1U << skipStrength) + 3; const BYTE* forwardIp = ip; const BYTE* ref; BYTE* 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>(BYTE*)source) && unlikely(ip[-1]==ref[-1])) { ip--; ref--; } // Encode Literal length length = (int)(ip - anchor); token = op++; if (unlikely(op + length + (2 + 1 + LASTLITERALS) + (length>>8) > oend)) return 0; // Check output limit #ifdef _MSC_VER if (length>=(int)RUN_MASK) { int len = length-RUN_MASK; *token=(RUN_MASK<254) { do { *op++ = 255; len -= 255; } while (len>254); *op++ = (BYTE)len; memcpy(op, anchor, length); op += length; goto _next_match; } else *op++ = (BYTE)len; } else *token = (length<=(int)RUN_MASK) { *token=(RUN_MASK< 254 ; len-=255) *op++ = 255; *op++ = (BYTE)len; } else *token = (length<>8) > oend)) return 0; // Check output limit 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++ = (BYTE)len; } else *token += len; // 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); } _last_literals: // Encode Last Literals { int 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< 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } else *op++ = (lastRun<> ((MINMATCH*8)-HASHLOG64K)) #define LZ4_HASH64K_VALUE(p) LZ4_HASH64K_FUNCTION(A32(p)) static inline int LZ4_compress64kCtx(void** ctx, const char* source, char* dest, int isize, int maxOutputSize) { #if HEAPMODE struct refTables *srt = (struct refTables *) (*ctx); U16* HashTable; #else U16 HashTable[HASH64KTABLESIZE] = {0}; #endif const BYTE* ip = (BYTE*) source; const BYTE* anchor = ip; const BYTE* const base = ip; const BYTE* const iend = ip + isize; const BYTE* const mflimit = iend - MFLIMIT; #define matchlimit (iend - LASTLITERALS) BYTE* op = (BYTE*) dest; BYTE* const oend = op + maxOutputSize; int len, length; const int skipStrength = SKIPSTRENGTH; U32 forwardH; // Init if (isizehashTable); memset((void*)HashTable, 0, sizeof(srt->hashTable)); #else (void) ctx; #endif // First Byte ip++; forwardH = LZ4_HASH64K_VALUE(ip); // Main Loop for ( ; ; ) { int findMatchAttempts = (1U << skipStrength) + 3; const BYTE* forwardIp = ip; const BYTE* ref; BYTE* 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>(BYTE*)source) && (ip[-1]==ref[-1])) { ip--; ref--; } // Encode Literal length length = (int)(ip - anchor); token = op++; if (unlikely(op + length + (2 + 1 + LASTLITERALS) + (length>>8) > oend)) return 0; // Check output limit #ifdef _MSC_VER if (length>=(int)RUN_MASK) { int len = length-RUN_MASK; *token=(RUN_MASK<254) { do { *op++ = 255; len -= 255; } while (len>254); *op++ = (BYTE)len; memcpy(op, anchor, length); op += length; goto _next_match; } else *op++ = (BYTE)len; } else *token = (length<=(int)RUN_MASK) { *token=(RUN_MASK< 254 ; len-=255) *op++ = 255; *op++ = (BYTE)len; } else *token = (length<>8) > oend)) return 0; // Check output limit 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++ = (BYTE)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); } _last_literals: // Encode Last Literals { int lastRun = (int)(iend - anchor); if (op + lastRun + 1 + (lastRun-RUN_MASK+255)/255 > oend) return 0; if (lastRun>=(int)RUN_MASK) { *op++=(RUN_MASK< 254 ; lastRun-=255) *op++ = 255; *op++ = (BYTE) lastRun; } else *op++ = (lastRun<>ML_BITS)) == RUN_MASK) { size_t len; for (;(len=*ip++)==255;length+=255){} length += len; } // copy literals cpy = op+length; if (unlikely(cpy>oend-COPYLENGTH)) { if (cpy != oend) goto _output_error; // Error : not enough place for another match (min 4) + 5 literals 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; if (unlikely(ref < (BYTE* const)dest)) goto _output_error; // Error : offset create reference outside destination buffer // get matchlength if ((length=(token&ML_MASK)) == ML_MASK) { for (;*ip==255;length+=255) {ip++;} length += *ip++; } // copy repeated sequence if (unlikely((op-ref)oend-COPYLENGTH) { if (cpy > oend) goto _output_error; // Error : request to write beyond destination buffer LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH)); while(op>ML_BITS)) == RUN_MASK) { int s=255; while ((ipoend-COPYLENGTH) || (ip+length>iend-COPYLENGTH)) { if (cpy > oend) goto _output_error; // Error : writes beyond output 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 if ((length=(token&ML_MASK)) == ML_MASK) { while (ipoend-COPYLENGTH) { if (cpy > oend) goto _output_error; // Error : request to write outside of destination buffer LZ4_SECURECOPY(ref, op, (oend-COPYLENGTH)); while(op