/* * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc. * All rights reserved. * * This source code is licensed under both the BSD-style license (found in the * LICENSE file in the root directory of this source tree) and the GPLv2 (found * in the COPYING file in the root directory of this source tree). * You may select, at your option, one of the above-listed licenses. */ #ifndef ZSTD_CCOMMON_H_MODULE #define ZSTD_CCOMMON_H_MODULE /* this module contains definitions which must be identical * across compression, decompression and dictBuilder. * It also contains a few functions useful to at least 2 of them * and which benefit from being inlined */ /*-************************************* * Dependencies ***************************************/ #ifdef __aarch64__ #include #endif #include "compiler.h" #include "mem.h" #include "debug.h" /* assert, DEBUGLOG, RAWLOG, g_debuglevel */ #include "error_private.h" #define ZSTD_STATIC_LINKING_ONLY #include "../zstd.h" #define FSE_STATIC_LINKING_ONLY #include "fse.h" #define HUF_STATIC_LINKING_ONLY #include "huf.h" #ifndef XXH_STATIC_LINKING_ONLY # define XXH_STATIC_LINKING_ONLY /* XXH64_state_t */ #endif #include "xxhash.h" /* XXH_reset, update, digest */ #if defined (__cplusplus) extern "C" { #endif /* ---- static assert (debug) --- */ #define ZSTD_STATIC_ASSERT(c) DEBUG_STATIC_ASSERT(c) #define ZSTD_isError ERR_isError /* for inlining */ #define FSE_isError ERR_isError #define HUF_isError ERR_isError /*-************************************* * shared macros ***************************************/ #undef MIN #undef MAX #define MIN(a,b) ((a)<(b) ? (a) : (b)) #define MAX(a,b) ((a)>(b) ? (a) : (b)) /** * Ignore: this is an internal helper. * * This is a helper function to help force C99-correctness during compilation. * Under strict compilation modes, variadic macro arguments can't be empty. * However, variadic function arguments can be. Using a function therefore lets * us statically check that at least one (string) argument was passed, * independent of the compilation flags. */ static INLINE_KEYWORD UNUSED_ATTR void _force_has_format_string(const char *format, ...) { (void)format; } /** * Ignore: this is an internal helper. * * We want to force this function invocation to be syntactically correct, but * we don't want to force runtime evaluation of its arguments. */ #define _FORCE_HAS_FORMAT_STRING(...) \ if (0) { \ _force_has_format_string(__VA_ARGS__); \ } /** * Return the specified error if the condition evaluates to true. * * In debug modes, prints additional information. * In order to do that (particularly, printing the conditional that failed), * this can't just wrap RETURN_ERROR(). */ #define RETURN_ERROR_IF(cond, err, ...) \ if (cond) { \ RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", \ __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \ _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \ RAWLOG(3, ": " __VA_ARGS__); \ RAWLOG(3, "\n"); \ return ERROR(err); \ } /** * Unconditionally return the specified error. * * In debug modes, prints additional information. */ #define RETURN_ERROR(err, ...) \ do { \ RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", \ __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \ _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \ RAWLOG(3, ": " __VA_ARGS__); \ RAWLOG(3, "\n"); \ return ERROR(err); \ } while(0); /** * If the provided expression evaluates to an error code, returns that error code. * * In debug modes, prints additional information. */ #define FORWARD_IF_ERROR(err, ...) \ do { \ size_t const err_code = (err); \ if (ERR_isError(err_code)) { \ RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", \ __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \ _FORCE_HAS_FORMAT_STRING(__VA_ARGS__); \ RAWLOG(3, ": " __VA_ARGS__); \ RAWLOG(3, "\n"); \ return err_code; \ } \ } while(0); /*-************************************* * Common constants ***************************************/ #define ZSTD_OPT_NUM (1<<12) #define ZSTD_REP_NUM 3 /* number of repcodes */ #define ZSTD_REP_MOVE (ZSTD_REP_NUM-1) static const U32 repStartValue[ZSTD_REP_NUM] = { 1, 4, 8 }; #define KB *(1 <<10) #define MB *(1 <<20) #define GB *(1U<<30) #define BIT7 128 #define BIT6 64 #define BIT5 32 #define BIT4 16 #define BIT1 2 #define BIT0 1 #define ZSTD_WINDOWLOG_ABSOLUTEMIN 10 static const size_t ZSTD_fcs_fieldSize[4] = { 0, 2, 4, 8 }; static const size_t ZSTD_did_fieldSize[4] = { 0, 1, 2, 4 }; #define ZSTD_FRAMEIDSIZE 4 /* magic number size */ #define ZSTD_BLOCKHEADERSIZE 3 /* C standard doesn't allow `static const` variable to be init using another `static const` variable */ static const size_t ZSTD_blockHeaderSize = ZSTD_BLOCKHEADERSIZE; typedef enum { bt_raw, bt_rle, bt_compressed, bt_reserved } blockType_e; #define ZSTD_FRAMECHECKSUMSIZE 4 #define MIN_SEQUENCES_SIZE 1 /* nbSeq==0 */ #define MIN_CBLOCK_SIZE (1 /*litCSize*/ + 1 /* RLE or RAW */ + MIN_SEQUENCES_SIZE /* nbSeq==0 */) /* for a non-null block */ #define HufLog 12 typedef enum { set_basic, set_rle, set_compressed, set_repeat } symbolEncodingType_e; #define LONGNBSEQ 0x7F00 #define MINMATCH 3 #define Litbits 8 #define MaxLit ((1<= 8 || (ovtype == ZSTD_no_overlap && diff <= -WILDCOPY_VECLEN)); if (ovtype == ZSTD_overlap_src_before_dst && diff < WILDCOPY_VECLEN) { /* Handle short offset copies. */ do { COPY8(op, ip) } while (op < oend); } else { assert(diff >= WILDCOPY_VECLEN || diff <= -WILDCOPY_VECLEN); /* Separate out the first COPY16() call because the copy length is * almost certain to be short, so the branches have different * probabilities. Since it is almost certain to be short, only do * one COPY16() in the first call. Then, do two calls per loop since * at that point it is more likely to have a high trip count. */ #ifndef __aarch64__ do { COPY16(op, ip); } while (op < oend); #else COPY16(op, ip); if (op >= oend) return; do { COPY16(op, ip); COPY16(op, ip); } while (op < oend); #endif } } MEM_STATIC size_t ZSTD_limitCopy(void* dst, size_t dstCapacity, const void* src, size_t srcSize) { size_t const length = MIN(dstCapacity, srcSize); if (length > 0) { memcpy(dst, src, length); } return length; } /* define "workspace is too large" as this number of times larger than needed */ #define ZSTD_WORKSPACETOOLARGE_FACTOR 3 /* when workspace is continuously too large * during at least this number of times, * context's memory usage is considered wasteful, * because it's sized to handle a worst case scenario which rarely happens. * In which case, resize it down to free some memory */ #define ZSTD_WORKSPACETOOLARGE_MAXDURATION 128 /*-******************************************* * Private declarations *********************************************/ typedef struct seqDef_s { U32 offset; U16 litLength; U16 matchLength; } seqDef; typedef struct { seqDef* sequencesStart; seqDef* sequences; BYTE* litStart; BYTE* lit; BYTE* llCode; BYTE* mlCode; BYTE* ofCode; size_t maxNbSeq; size_t maxNbLit; U32 longLengthID; /* 0 == no longLength; 1 == Lit.longLength; 2 == Match.longLength; */ U32 longLengthPos; } seqStore_t; typedef struct { U32 litLength; U32 matchLength; } ZSTD_sequenceLength; /** * Returns the ZSTD_sequenceLength for the given sequences. It handles the decoding of long sequences * indicated by longLengthPos and longLengthID, and adds MINMATCH back to matchLength. */ MEM_STATIC ZSTD_sequenceLength ZSTD_getSequenceLength(seqStore_t const* seqStore, seqDef const* seq) { ZSTD_sequenceLength seqLen; seqLen.litLength = seq->litLength; seqLen.matchLength = seq->matchLength + MINMATCH; if (seqStore->longLengthPos == (U32)(seq - seqStore->sequencesStart)) { if (seqStore->longLengthID == 1) { seqLen.litLength += 0xFFFF; } if (seqStore->longLengthID == 2) { seqLen.matchLength += 0xFFFF; } } return seqLen; } /** * Contains the compressed frame size and an upper-bound for the decompressed frame size. * Note: before using `compressedSize`, check for errors using ZSTD_isError(). * similarly, before using `decompressedBound`, check for errors using: * `decompressedBound != ZSTD_CONTENTSIZE_ERROR` */ typedef struct { size_t compressedSize; unsigned long long decompressedBound; } ZSTD_frameSizeInfo; /* decompress & legacy */ const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx); /* compress & dictBuilder */ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr); /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */ /* custom memory allocation functions */ void* ZSTD_malloc(size_t size, ZSTD_customMem customMem); void* ZSTD_calloc(size_t size, ZSTD_customMem customMem); void ZSTD_free(void* ptr, ZSTD_customMem customMem); MEM_STATIC U32 ZSTD_highbit32(U32 val) /* compress, dictBuilder, decodeCorpus */ { assert(val != 0); { # if defined(_MSC_VER) /* Visual */ unsigned long r=0; return _BitScanReverse(&r, val) ? (unsigned)r : 0; # elif defined(__GNUC__) && (__GNUC__ >= 3) /* GCC Intrinsic */ return __builtin_clz (val) ^ 31; # elif defined(__ICCARM__) /* IAR Intrinsic */ return 31 - __CLZ(val); # else /* Software version */ static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 }; U32 v = val; v |= v >> 1; v |= v >> 2; v |= v >> 4; v |= v >> 8; v |= v >> 16; return DeBruijnClz[(v * 0x07C4ACDDU) >> 27]; # endif } } /* ZSTD_invalidateRepCodes() : * ensures next compression will not use repcodes from previous block. * Note : only works with regular variant; * do not use with extDict variant ! */ void ZSTD_invalidateRepCodes(ZSTD_CCtx* cctx); /* zstdmt, adaptive_compression (shouldn't get this definition from here) */ typedef struct { blockType_e blockType; U32 lastBlock; U32 origSize; } blockProperties_t; /* declared here for decompress and fullbench */ /*! ZSTD_getcBlockSize() : * Provides the size of compressed block from block header `src` */ /* Used by: decompress, fullbench (does not get its definition from here) */ size_t ZSTD_getcBlockSize(const void* src, size_t srcSize, blockProperties_t* bpPtr); /*! ZSTD_decodeSeqHeaders() : * decode sequence header from src */ /* Used by: decompress, fullbench (does not get its definition from here) */ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr, const void* src, size_t srcSize); #if defined (__cplusplus) } #endif #endif /* ZSTD_CCOMMON_H_MODULE */