Date: Thu, 8 Aug 2019 15:37:56 +0000 (UTC) From: Conrad Meyer <cem@FreeBSD.org> To: src-committers@freebsd.org, svn-src-all@freebsd.org, svn-src-vendor@freebsd.org Subject: svn commit: r350754 - in vendor/zstd/dist: . contrib/largeNbDicts contrib/seekable_format contrib/seekable_format/examples doc lib lib/compress lib/decompress lib/legacy programs tests Message-ID: <201908081537.x78FbuwU008673@repo.freebsd.org>
next in thread | raw e-mail | index | archive | help
Author: cem Date: Thu Aug 8 15:37:56 2019 New Revision: 350754 URL: https://svnweb.freebsd.org/changeset/base/350754 Log: import zstd 1.4.2 Added: vendor/zstd/dist/contrib/seekable_format/examples/seekable_decompression_mem.c (contents, props changed) vendor/zstd/dist/lib/compress/zstd_compress_literals.c (contents, props changed) vendor/zstd/dist/lib/compress/zstd_compress_literals.h (contents, props changed) vendor/zstd/dist/lib/compress/zstd_compress_sequences.c (contents, props changed) vendor/zstd/dist/lib/compress/zstd_compress_sequences.h (contents, props changed) Modified: vendor/zstd/dist/CHANGELOG vendor/zstd/dist/contrib/largeNbDicts/largeNbDicts.c vendor/zstd/dist/contrib/seekable_format/examples/.gitignore vendor/zstd/dist/contrib/seekable_format/examples/Makefile vendor/zstd/dist/contrib/seekable_format/zstdseek_decompress.c vendor/zstd/dist/doc/zstd_manual.html vendor/zstd/dist/lib/compress/zstd_compress.c vendor/zstd/dist/lib/compress/zstd_compress_internal.h vendor/zstd/dist/lib/decompress/zstd_decompress.c vendor/zstd/dist/lib/legacy/zstd_v05.c vendor/zstd/dist/lib/zstd.h vendor/zstd/dist/programs/README.md vendor/zstd/dist/programs/util.c vendor/zstd/dist/programs/zstd.1 vendor/zstd/dist/programs/zstd.1.md vendor/zstd/dist/programs/zstdcli.c vendor/zstd/dist/programs/zstdgrep.1 vendor/zstd/dist/programs/zstdless.1 vendor/zstd/dist/tests/decodecorpus.c Modified: vendor/zstd/dist/CHANGELOG ============================================================================== --- vendor/zstd/dist/CHANGELOG Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/CHANGELOG Thu Aug 8 15:37:56 2019 (r350754) @@ -1,3 +1,9 @@ +v1.4.2 +bug: Fix bug in zstd-0.5 decoder by @terrelln (#1696) +bug: Fix seekable decompression in-memory API by @iburinoc (#1695) +misc: Validate blocks are smaller than size limit by @vivekmg (#1685) +misc: Restructure source files by @ephiepark (#1679) + v1.4.1 bug: Fix data corruption in niche use cases by @terrelln (#1659) bug: Fuzz legacy modes, fix uncovered bugs by @terrelln (#1593, #1594, #1595) Modified: vendor/zstd/dist/contrib/largeNbDicts/largeNbDicts.c ============================================================================== --- vendor/zstd/dist/contrib/largeNbDicts/largeNbDicts.c Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/contrib/largeNbDicts/largeNbDicts.c Thu Aug 8 15:37:56 2019 (r350754) @@ -559,7 +559,7 @@ static int benchMem(slice_collection_t dstBlocks, CONTROL(BMK_isSuccessful_runOutcome(outcome)); BMK_runTime_t const result = BMK_extract_runTime(outcome); - U64 const dTime_ns = result.nanoSecPerRun; + double const dTime_ns = result.nanoSecPerRun; double const dTime_sec = (double)dTime_ns / 1000000000; size_t const srcSize = result.sumOfReturn; double const dSpeed_MBps = (double)srcSize / dTime_sec / (1 MB); Modified: vendor/zstd/dist/contrib/seekable_format/examples/.gitignore ============================================================================== --- vendor/zstd/dist/contrib/seekable_format/examples/.gitignore Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/contrib/seekable_format/examples/.gitignore Thu Aug 8 15:37:56 2019 (r350754) @@ -1,4 +1,5 @@ seekable_compression seekable_decompression +seekable_decompression_mem parallel_processing parallel_compression Modified: vendor/zstd/dist/contrib/seekable_format/examples/Makefile ============================================================================== --- vendor/zstd/dist/contrib/seekable_format/examples/Makefile Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/contrib/seekable_format/examples/Makefile Thu Aug 8 15:37:56 2019 (r350754) @@ -24,7 +24,8 @@ SEEKABLE_OBJS = ../zstdseek_compress.c ../zstdseek_dec default: all -all: seekable_compression seekable_decompression parallel_processing +all: seekable_compression seekable_decompression seekable_decompression_mem \ + parallel_processing $(ZSTDLIB): make -C $(ZSTDLIB_PATH) $(ZSTDLIB_NAME) @@ -35,6 +36,9 @@ seekable_compression : seekable_compression.c $(SEEKAB seekable_decompression : seekable_decompression.c $(SEEKABLE_OBJS) $(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@ +seekable_decompression_mem : seekable_decompression_mem.c $(SEEKABLE_OBJS) + $(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@ + parallel_processing : parallel_processing.c $(SEEKABLE_OBJS) $(CC) $(CPPFLAGS) $(CFLAGS) $^ $(LDFLAGS) -o $@ -pthread @@ -44,5 +48,6 @@ parallel_compression : parallel_compression.c $(SEEKAB clean: @rm -f core *.o tmp* result* *.zst \ seekable_compression seekable_decompression \ + seekable_decompression_mem \ parallel_processing parallel_compression @echo Cleaning completed Added: vendor/zstd/dist/contrib/seekable_format/examples/seekable_decompression_mem.c ============================================================================== --- /dev/null 00:00:00 1970 (empty, because file is newly added) +++ vendor/zstd/dist/contrib/seekable_format/examples/seekable_decompression_mem.c Thu Aug 8 15:37:56 2019 (r350754) @@ -0,0 +1,144 @@ +/* + * Copyright (c) 2017-present, 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). + */ + + +#include <stdlib.h> // malloc, exit +#include <stdio.h> // fprintf, perror, feof +#include <string.h> // strerror +#include <errno.h> // errno +#define ZSTD_STATIC_LINKING_ONLY +#include <zstd.h> // presumes zstd library is installed +#include <zstd_errors.h> + +#include "zstd_seekable.h" + +#define MIN(a, b) ((a) < (b) ? (a) : (b)) + +#define MAX_FILE_SIZE (8 * 1024 * 1024) + +static void* malloc_orDie(size_t size) +{ + void* const buff = malloc(size); + if (buff) return buff; + /* error */ + perror("malloc"); + exit(1); +} + +static void* realloc_orDie(void* ptr, size_t size) +{ + ptr = realloc(ptr, size); + if (ptr) return ptr; + /* error */ + perror("realloc"); + exit(1); +} + +static FILE* fopen_orDie(const char *filename, const char *instruction) +{ + FILE* const inFile = fopen(filename, instruction); + if (inFile) return inFile; + /* error */ + perror(filename); + exit(3); +} + +static size_t fread_orDie(void* buffer, size_t sizeToRead, FILE* file) +{ + size_t const readSize = fread(buffer, 1, sizeToRead, file); + if (readSize == sizeToRead) return readSize; /* good */ + if (feof(file)) return readSize; /* good, reached end of file */ + /* error */ + perror("fread"); + exit(4); +} + +static size_t fwrite_orDie(const void* buffer, size_t sizeToWrite, FILE* file) +{ + size_t const writtenSize = fwrite(buffer, 1, sizeToWrite, file); + if (writtenSize == sizeToWrite) return sizeToWrite; /* good */ + /* error */ + perror("fwrite"); + exit(5); +} + +static size_t fclose_orDie(FILE* file) +{ + if (!fclose(file)) return 0; + /* error */ + perror("fclose"); + exit(6); +} + +static void fseek_orDie(FILE* file, long int offset, int origin) { + if (!fseek(file, offset, origin)) { + if (!fflush(file)) return; + } + /* error */ + perror("fseek"); + exit(7); +} + + +static void decompressFile_orDie(const char* fname, off_t startOffset, off_t endOffset) +{ + FILE* const fin = fopen_orDie(fname, "rb"); + FILE* const fout = stdout; + // Just for demo purposes, assume file is <= MAX_FILE_SIZE + void* const buffIn = malloc_orDie(MAX_FILE_SIZE); + size_t const inSize = fread_orDie(buffIn, MAX_FILE_SIZE, fin); + size_t const buffOutSize = ZSTD_DStreamOutSize(); /* Guarantee to successfully flush at least one complete compressed block in all circumstances. */ + void* const buffOut = malloc_orDie(buffOutSize); + + ZSTD_seekable* const seekable = ZSTD_seekable_create(); + if (seekable==NULL) { fprintf(stderr, "ZSTD_seekable_create() error \n"); exit(10); } + + size_t const initResult = ZSTD_seekable_initBuff(seekable, buffIn, inSize); + if (ZSTD_isError(initResult)) { fprintf(stderr, "ZSTD_seekable_init() error : %s \n", ZSTD_getErrorName(initResult)); exit(11); } + + while (startOffset < endOffset) { + size_t const result = ZSTD_seekable_decompress(seekable, buffOut, MIN(endOffset - startOffset, buffOutSize), startOffset); + + if (ZSTD_isError(result)) { + fprintf(stderr, "ZSTD_seekable_decompress() error : %s \n", + ZSTD_getErrorName(result)); + exit(12); + } + fwrite_orDie(buffOut, result, fout); + startOffset += result; + } + + ZSTD_seekable_free(seekable); + fclose_orDie(fin); + fclose_orDie(fout); + free(buffIn); + free(buffOut); +} + + +int main(int argc, const char** argv) +{ + const char* const exeName = argv[0]; + + if (argc!=4) { + fprintf(stderr, "wrong arguments\n"); + fprintf(stderr, "usage:\n"); + fprintf(stderr, "%s FILE START END\n", exeName); + return 1; + } + + { + const char* const inFilename = argv[1]; + off_t const startOffset = atoll(argv[2]); + off_t const endOffset = atoll(argv[3]); + decompressFile_orDie(inFilename, startOffset, endOffset); + } + + return 0; +} Modified: vendor/zstd/dist/contrib/seekable_format/zstdseek_decompress.c ============================================================================== --- vendor/zstd/dist/contrib/seekable_format/zstdseek_decompress.c Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/contrib/seekable_format/zstdseek_decompress.c Thu Aug 8 15:37:56 2019 (r350754) @@ -106,7 +106,7 @@ typedef struct { static int ZSTD_seekable_read_buff(void* opaque, void* buffer, size_t n) { buffWrapper_t* buff = (buffWrapper_t*) opaque; - if (buff->size + n > buff->pos) return -1; + if (buff->pos + n > buff->size) return -1; memcpy(buffer, (const BYTE*)buff->ptr + buff->pos, n); buff->pos += n; return 0; @@ -124,7 +124,7 @@ static int ZSTD_seekable_seek_buff(void* opaque, long newOffset = (unsigned long long)buff->pos + offset; break; case SEEK_END: - newOffset = (unsigned long long)buff->size - offset; + newOffset = (unsigned long long)buff->size + offset; break; default: assert(0); /* not possible */ Modified: vendor/zstd/dist/doc/zstd_manual.html ============================================================================== --- vendor/zstd/dist/doc/zstd_manual.html Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/doc/zstd_manual.html Thu Aug 8 15:37:56 2019 (r350754) @@ -1,10 +1,10 @@ <html> <head> <meta http-equiv="Content-Type" content="text/html; charset=ISO-8859-1"> -<title>zstd 1.4.1 Manual</title> +<title>zstd 1.4.2 Manual</title> </head> <body> -<h1>zstd 1.4.1 Manual</h1> +<h1>zstd 1.4.2 Manual</h1> <hr> <a name="Contents"></a><h2>Contents</h2> <ol> Modified: vendor/zstd/dist/lib/compress/zstd_compress.c ============================================================================== --- vendor/zstd/dist/lib/compress/zstd_compress.c Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/lib/compress/zstd_compress.c Thu Aug 8 15:37:56 2019 (r350754) @@ -21,6 +21,8 @@ #define HUF_STATIC_LINKING_ONLY #include "huf.h" #include "zstd_compress_internal.h" +#include "zstd_compress_sequences.h" +#include "zstd_compress_literals.h" #include "zstd_fast.h" #include "zstd_double_fast.h" #include "zstd_lazy.h" @@ -397,18 +399,6 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter para } } -/* ZSTD_cParam_withinBounds: - * @return 1 if value is within cParam bounds, - * 0 otherwise */ -static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value) -{ - ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); - if (ZSTD_isError(bounds.error)) return 0; - if (value < bounds.lowerBound) return 0; - if (value > bounds.upperBound) return 0; - return 1; -} - /* ZSTD_cParam_clampBounds: * Clamps the value into the bounded range. */ @@ -1903,155 +1893,6 @@ static size_t ZSTD_noCompressBlock (void* dst, size_t return ZSTD_blockHeaderSize + srcSize; } -static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize) -{ - BYTE* const ostart = (BYTE* const)dst; - U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); - - RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall); - - switch(flSize) - { - case 1: /* 2 - 1 - 5 */ - ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3)); - break; - case 2: /* 2 - 2 - 12 */ - MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4))); - break; - case 3: /* 2 - 2 - 20 */ - MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4))); - break; - default: /* not necessary : flSize is {1,2,3} */ - assert(0); - } - - memcpy(ostart + flSize, src, srcSize); - return srcSize + flSize; -} - -static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize) -{ - BYTE* const ostart = (BYTE* const)dst; - U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); - - (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */ - - switch(flSize) - { - case 1: /* 2 - 1 - 5 */ - ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3)); - break; - case 2: /* 2 - 2 - 12 */ - MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4))); - break; - case 3: /* 2 - 2 - 20 */ - MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4))); - break; - default: /* not necessary : flSize is {1,2,3} */ - assert(0); - } - - ostart[flSize] = *(const BYTE*)src; - return flSize+1; -} - - -/* ZSTD_minGain() : - * minimum compression required - * to generate a compress block or a compressed literals section. - * note : use same formula for both situations */ -static size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat) -{ - U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6; - ZSTD_STATIC_ASSERT(ZSTD_btultra == 8); - assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat)); - return (srcSize >> minlog) + 2; -} - -static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf, - ZSTD_hufCTables_t* nextHuf, - ZSTD_strategy strategy, int disableLiteralCompression, - void* dst, size_t dstCapacity, - const void* src, size_t srcSize, - void* workspace, size_t wkspSize, - const int bmi2) -{ - size_t const minGain = ZSTD_minGain(srcSize, strategy); - size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB); - BYTE* const ostart = (BYTE*)dst; - U32 singleStream = srcSize < 256; - symbolEncodingType_e hType = set_compressed; - size_t cLitSize; - - DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)", - disableLiteralCompression); - - /* Prepare nextEntropy assuming reusing the existing table */ - memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); - - if (disableLiteralCompression) - return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); - - /* small ? don't even attempt compression (speed opt) */ -# define COMPRESS_LITERALS_SIZE_MIN 63 - { size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN; - if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); - } - - RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression"); - { HUF_repeat repeat = prevHuf->repeatMode; - int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0; - if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1; - cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, - workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) - : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, - workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2); - if (repeat != HUF_repeat_none) { - /* reused the existing table */ - hType = set_repeat; - } - } - - if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) { - memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); - return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); - } - if (cLitSize==1) { - memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); - return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize); - } - - if (hType == set_compressed) { - /* using a newly constructed table */ - nextHuf->repeatMode = HUF_repeat_check; - } - - /* Build header */ - switch(lhSize) - { - case 3: /* 2 - 2 - 10 - 10 */ - { U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14); - MEM_writeLE24(ostart, lhc); - break; - } - case 4: /* 2 - 2 - 14 - 14 */ - { U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18); - MEM_writeLE32(ostart, lhc); - break; - } - case 5: /* 2 - 2 - 18 - 18 */ - { U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22); - MEM_writeLE32(ostart, lhc); - ostart[4] = (BYTE)(cLitSize >> 10); - break; - } - default: /* not possible : lhSize is {3,4,5} */ - assert(0); - } - return lhSize+cLitSize; -} - - void ZSTD_seqToCodes(const seqStore_t* seqStorePtr) { const seqDef* const sequences = seqStorePtr->sequencesStart; @@ -2074,418 +1915,6 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr) mlCodeTable[seqStorePtr->longLengthPos] = MaxML; } - -/** - * -log2(x / 256) lookup table for x in [0, 256). - * If x == 0: Return 0 - * Else: Return floor(-log2(x / 256) * 256) - */ -static unsigned const kInverseProbabilityLog256[256] = { - 0, 2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162, - 1130, 1100, 1073, 1047, 1024, 1001, 980, 960, 941, 923, 906, 889, - 874, 859, 844, 830, 817, 804, 791, 779, 768, 756, 745, 734, - 724, 714, 704, 694, 685, 676, 667, 658, 650, 642, 633, 626, - 618, 610, 603, 595, 588, 581, 574, 567, 561, 554, 548, 542, - 535, 529, 523, 517, 512, 506, 500, 495, 489, 484, 478, 473, - 468, 463, 458, 453, 448, 443, 438, 434, 429, 424, 420, 415, - 411, 407, 402, 398, 394, 390, 386, 382, 377, 373, 370, 366, - 362, 358, 354, 350, 347, 343, 339, 336, 332, 329, 325, 322, - 318, 315, 311, 308, 305, 302, 298, 295, 292, 289, 286, 282, - 279, 276, 273, 270, 267, 264, 261, 258, 256, 253, 250, 247, - 244, 241, 239, 236, 233, 230, 228, 225, 222, 220, 217, 215, - 212, 209, 207, 204, 202, 199, 197, 194, 192, 190, 187, 185, - 182, 180, 178, 175, 173, 171, 168, 166, 164, 162, 159, 157, - 155, 153, 151, 149, 146, 144, 142, 140, 138, 136, 134, 132, - 130, 128, 126, 123, 121, 119, 117, 115, 114, 112, 110, 108, - 106, 104, 102, 100, 98, 96, 94, 93, 91, 89, 87, 85, - 83, 82, 80, 78, 76, 74, 73, 71, 69, 67, 66, 64, - 62, 61, 59, 57, 55, 54, 52, 50, 49, 47, 46, 44, - 42, 41, 39, 37, 36, 34, 33, 31, 30, 28, 26, 25, - 23, 22, 20, 19, 17, 16, 14, 13, 11, 10, 8, 7, - 5, 4, 2, 1, -}; - - -/** - * Returns the cost in bits of encoding the distribution described by count - * using the entropy bound. - */ -static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total) -{ - unsigned cost = 0; - unsigned s; - for (s = 0; s <= max; ++s) { - unsigned norm = (unsigned)((256 * count[s]) / total); - if (count[s] != 0 && norm == 0) - norm = 1; - assert(count[s] < total); - cost += count[s] * kInverseProbabilityLog256[norm]; - } - return cost >> 8; -} - - -/** - * Returns the cost in bits of encoding the distribution in count using the - * table described by norm. The max symbol support by norm is assumed >= max. - * norm must be valid for every symbol with non-zero probability in count. - */ -static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog, - unsigned const* count, unsigned const max) -{ - unsigned const shift = 8 - accuracyLog; - size_t cost = 0; - unsigned s; - assert(accuracyLog <= 8); - for (s = 0; s <= max; ++s) { - unsigned const normAcc = norm[s] != -1 ? norm[s] : 1; - unsigned const norm256 = normAcc << shift; - assert(norm256 > 0); - assert(norm256 < 256); - cost += count[s] * kInverseProbabilityLog256[norm256]; - } - return cost >> 8; -} - - -static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) { - void const* ptr = ctable; - U16 const* u16ptr = (U16 const*)ptr; - U32 const maxSymbolValue = MEM_read16(u16ptr + 1); - return maxSymbolValue; -} - - -/** - * Returns the cost in bits of encoding the distribution in count using ctable. - * Returns an error if ctable cannot represent all the symbols in count. - */ -static size_t ZSTD_fseBitCost( - FSE_CTable const* ctable, - unsigned const* count, - unsigned const max) -{ - unsigned const kAccuracyLog = 8; - size_t cost = 0; - unsigned s; - FSE_CState_t cstate; - FSE_initCState(&cstate, ctable); - RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC, - "Repeat FSE_CTable has maxSymbolValue %u < %u", - ZSTD_getFSEMaxSymbolValue(ctable), max); - for (s = 0; s <= max; ++s) { - unsigned const tableLog = cstate.stateLog; - unsigned const badCost = (tableLog + 1) << kAccuracyLog; - unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog); - if (count[s] == 0) - continue; - RETURN_ERROR_IF(bitCost >= badCost, GENERIC, - "Repeat FSE_CTable has Prob[%u] == 0", s); - cost += count[s] * bitCost; - } - return cost >> kAccuracyLog; -} - -/** - * Returns the cost in bytes of encoding the normalized count header. - * Returns an error if any of the helper functions return an error. - */ -static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max, - size_t const nbSeq, unsigned const FSELog) -{ - BYTE wksp[FSE_NCOUNTBOUND]; - S16 norm[MaxSeq + 1]; - const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); - FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max)); - return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog); -} - - -typedef enum { - ZSTD_defaultDisallowed = 0, - ZSTD_defaultAllowed = 1 -} ZSTD_defaultPolicy_e; - -MEM_STATIC symbolEncodingType_e -ZSTD_selectEncodingType( - FSE_repeat* repeatMode, unsigned const* count, unsigned const max, - size_t const mostFrequent, size_t nbSeq, unsigned const FSELog, - FSE_CTable const* prevCTable, - short const* defaultNorm, U32 defaultNormLog, - ZSTD_defaultPolicy_e const isDefaultAllowed, - ZSTD_strategy const strategy) -{ - ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0); - if (mostFrequent == nbSeq) { - *repeatMode = FSE_repeat_none; - if (isDefaultAllowed && nbSeq <= 2) { - /* Prefer set_basic over set_rle when there are 2 or less symbols, - * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol. - * If basic encoding isn't possible, always choose RLE. - */ - DEBUGLOG(5, "Selected set_basic"); - return set_basic; - } - DEBUGLOG(5, "Selected set_rle"); - return set_rle; - } - if (strategy < ZSTD_lazy) { - if (isDefaultAllowed) { - size_t const staticFse_nbSeq_max = 1000; - size_t const mult = 10 - strategy; - size_t const baseLog = 3; - size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog; /* 28-36 for offset, 56-72 for lengths */ - assert(defaultNormLog >= 5 && defaultNormLog <= 6); /* xx_DEFAULTNORMLOG */ - assert(mult <= 9 && mult >= 7); - if ( (*repeatMode == FSE_repeat_valid) - && (nbSeq < staticFse_nbSeq_max) ) { - DEBUGLOG(5, "Selected set_repeat"); - return set_repeat; - } - if ( (nbSeq < dynamicFse_nbSeq_min) - || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) { - DEBUGLOG(5, "Selected set_basic"); - /* The format allows default tables to be repeated, but it isn't useful. - * When using simple heuristics to select encoding type, we don't want - * to confuse these tables with dictionaries. When running more careful - * analysis, we don't need to waste time checking both repeating tables - * and default tables. - */ - *repeatMode = FSE_repeat_none; - return set_basic; - } - } - } else { - size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC); - size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC); - size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog); - size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq); - - if (isDefaultAllowed) { - assert(!ZSTD_isError(basicCost)); - assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost))); - } - assert(!ZSTD_isError(NCountCost)); - assert(compressedCost < ERROR(maxCode)); - DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u", - (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost); - if (basicCost <= repeatCost && basicCost <= compressedCost) { - DEBUGLOG(5, "Selected set_basic"); - assert(isDefaultAllowed); - *repeatMode = FSE_repeat_none; - return set_basic; - } - if (repeatCost <= compressedCost) { - DEBUGLOG(5, "Selected set_repeat"); - assert(!ZSTD_isError(repeatCost)); - return set_repeat; - } - assert(compressedCost < basicCost && compressedCost < repeatCost); - } - DEBUGLOG(5, "Selected set_compressed"); - *repeatMode = FSE_repeat_check; - return set_compressed; -} - -MEM_STATIC size_t -ZSTD_buildCTable(void* dst, size_t dstCapacity, - FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type, - unsigned* count, U32 max, - const BYTE* codeTable, size_t nbSeq, - const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax, - const FSE_CTable* prevCTable, size_t prevCTableSize, - void* workspace, size_t workspaceSize) -{ - BYTE* op = (BYTE*)dst; - const BYTE* const oend = op + dstCapacity; - DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity); - - switch (type) { - case set_rle: - FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max)); - RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall); - *op = codeTable[0]; - return 1; - case set_repeat: - memcpy(nextCTable, prevCTable, prevCTableSize); - return 0; - case set_basic: - FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize)); /* note : could be pre-calculated */ - return 0; - case set_compressed: { - S16 norm[MaxSeq + 1]; - size_t nbSeq_1 = nbSeq; - const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max); - if (count[codeTable[nbSeq-1]] > 1) { - count[codeTable[nbSeq-1]]--; - nbSeq_1--; - } - assert(nbSeq_1 > 1); - FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max)); - { size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog); /* overflow protected */ - FORWARD_IF_ERROR(NCountSize); - FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize)); - return NCountSize; - } - } - default: assert(0); RETURN_ERROR(GENERIC); - } -} - -FORCE_INLINE_TEMPLATE size_t -ZSTD_encodeSequences_body( - void* dst, size_t dstCapacity, - FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, - FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, - FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, - seqDef const* sequences, size_t nbSeq, int longOffsets) -{ - BIT_CStream_t blockStream; - FSE_CState_t stateMatchLength; - FSE_CState_t stateOffsetBits; - FSE_CState_t stateLitLength; - - RETURN_ERROR_IF( - ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)), - dstSize_tooSmall, "not enough space remaining"); - DEBUGLOG(6, "available space for bitstream : %i (dstCapacity=%u)", - (int)(blockStream.endPtr - blockStream.startPtr), - (unsigned)dstCapacity); - - /* first symbols */ - FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]); - FSE_initCState2(&stateOffsetBits, CTable_OffsetBits, ofCodeTable[nbSeq-1]); - FSE_initCState2(&stateLitLength, CTable_LitLength, llCodeTable[nbSeq-1]); - BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]); - if (MEM_32bits()) BIT_flushBits(&blockStream); - BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]); - if (MEM_32bits()) BIT_flushBits(&blockStream); - if (longOffsets) { - U32 const ofBits = ofCodeTable[nbSeq-1]; - int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1); - if (extraBits) { - BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits); - BIT_flushBits(&blockStream); - } - BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits, - ofBits - extraBits); - } else { - BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]); - } - BIT_flushBits(&blockStream); - - { size_t n; - for (n=nbSeq-2 ; n<nbSeq ; n--) { /* intentional underflow */ - BYTE const llCode = llCodeTable[n]; - BYTE const ofCode = ofCodeTable[n]; - BYTE const mlCode = mlCodeTable[n]; - U32 const llBits = LL_bits[llCode]; - U32 const ofBits = ofCode; - U32 const mlBits = ML_bits[mlCode]; - DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u", - (unsigned)sequences[n].litLength, - (unsigned)sequences[n].matchLength + MINMATCH, - (unsigned)sequences[n].offset); - /* 32b*/ /* 64b*/ - /* (7)*/ /* (7)*/ - FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode); /* 15 */ /* 15 */ - FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode); /* 24 */ /* 24 */ - if (MEM_32bits()) BIT_flushBits(&blockStream); /* (7)*/ - FSE_encodeSymbol(&blockStream, &stateLitLength, llCode); /* 16 */ /* 33 */ - if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog))) - BIT_flushBits(&blockStream); /* (7)*/ - BIT_addBits(&blockStream, sequences[n].litLength, llBits); - if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream); - BIT_addBits(&blockStream, sequences[n].matchLength, mlBits); - if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream); - if (longOffsets) { - int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1); - if (extraBits) { - BIT_addBits(&blockStream, sequences[n].offset, extraBits); - BIT_flushBits(&blockStream); /* (7)*/ - } - BIT_addBits(&blockStream, sequences[n].offset >> extraBits, - ofBits - extraBits); /* 31 */ - } else { - BIT_addBits(&blockStream, sequences[n].offset, ofBits); /* 31 */ - } - BIT_flushBits(&blockStream); /* (7)*/ - DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr)); - } } - - DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog); - FSE_flushCState(&blockStream, &stateMatchLength); - DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog); - FSE_flushCState(&blockStream, &stateOffsetBits); - DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog); - FSE_flushCState(&blockStream, &stateLitLength); - - { size_t const streamSize = BIT_closeCStream(&blockStream); - RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space"); - return streamSize; - } -} - -static size_t -ZSTD_encodeSequences_default( - void* dst, size_t dstCapacity, - FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, - FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, - FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, - seqDef const* sequences, size_t nbSeq, int longOffsets) -{ - return ZSTD_encodeSequences_body(dst, dstCapacity, - CTable_MatchLength, mlCodeTable, - CTable_OffsetBits, ofCodeTable, - CTable_LitLength, llCodeTable, - sequences, nbSeq, longOffsets); -} - - -#if DYNAMIC_BMI2 - -static TARGET_ATTRIBUTE("bmi2") size_t -ZSTD_encodeSequences_bmi2( - void* dst, size_t dstCapacity, - FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, - FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, - FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, - seqDef const* sequences, size_t nbSeq, int longOffsets) -{ - return ZSTD_encodeSequences_body(dst, dstCapacity, - CTable_MatchLength, mlCodeTable, - CTable_OffsetBits, ofCodeTable, - CTable_LitLength, llCodeTable, - sequences, nbSeq, longOffsets); -} - -#endif - -static size_t ZSTD_encodeSequences( - void* dst, size_t dstCapacity, - FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable, - FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable, - FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable, - seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2) -{ - DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity); -#if DYNAMIC_BMI2 - if (bmi2) { - return ZSTD_encodeSequences_bmi2(dst, dstCapacity, - CTable_MatchLength, mlCodeTable, - CTable_OffsetBits, ofCodeTable, - CTable_LitLength, llCodeTable, - sequences, nbSeq, longOffsets); - } -#endif - (void)bmi2; - return ZSTD_encodeSequences_default(dst, dstCapacity, - CTable_MatchLength, mlCodeTable, - CTable_OffsetBits, ofCodeTable, - CTable_LitLength, llCodeTable, - sequences, nbSeq, longOffsets); -} - static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams) { switch (cctxParams->literalCompressionMode) { @@ -2530,8 +1959,8 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePt BYTE* seqHead; BYTE* lastNCount = NULL; + DEBUGLOG(5, "ZSTD_compressSequences_internal (nbSeq=%zu)", nbSeq); ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog))); - DEBUGLOG(5, "ZSTD_compressSequences_internal"); /* Compress literals */ { const BYTE* const literals = seqStorePtr->litStart; Modified: vendor/zstd/dist/lib/compress/zstd_compress_internal.h ============================================================================== --- vendor/zstd/dist/lib/compress/zstd_compress_internal.h Thu Aug 8 15:32:53 2019 (r350753) +++ vendor/zstd/dist/lib/compress/zstd_compress_internal.h Thu Aug 8 15:37:56 2019 (r350754) @@ -307,6 +307,30 @@ MEM_STATIC U32 ZSTD_MLcode(U32 mlBase) return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase]; } +/* ZSTD_cParam_withinBounds: + * @return 1 if value is within cParam bounds, + * 0 otherwise */ +MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value) +{ + ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam); + if (ZSTD_isError(bounds.error)) return 0; + if (value < bounds.lowerBound) return 0; + if (value > bounds.upperBound) return 0; + return 1; +} + +/* ZSTD_minGain() : + * minimum compression required + * to generate a compress block or a compressed literals section. + * note : use same formula for both situations */ +MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat) +{ + U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6; + ZSTD_STATIC_ASSERT(ZSTD_btultra == 8); + assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat)); + return (srcSize >> minlog) + 2; +} + /*! ZSTD_storeSeq() : * Store a sequence (literal length, literals, offset code and match length code) into seqStore_t. * `offsetCode` : distance to match + 3 (values 1-3 are repCodes). Added: vendor/zstd/dist/lib/compress/zstd_compress_literals.c ============================================================================== --- /dev/null 00:00:00 1970 (empty, because file is newly added) +++ vendor/zstd/dist/lib/compress/zstd_compress_literals.c Thu Aug 8 15:37:56 2019 (r350754) @@ -0,0 +1,149 @@ +/* + * Copyright (c) 2016-present, 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. + */ + + /*-************************************* + * Dependencies + ***************************************/ +#include "zstd_compress_literals.h" + +size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + BYTE* const ostart = (BYTE* const)dst; + U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); + + RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall); + + switch(flSize) + { + case 1: /* 2 - 1 - 5 */ + ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3)); + break; + case 2: /* 2 - 2 - 12 */ + MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4))); + break; + case 3: /* 2 - 2 - 20 */ + MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4))); + break; + default: /* not necessary : flSize is {1,2,3} */ + assert(0); + } + + memcpy(ostart + flSize, src, srcSize); + return srcSize + flSize; +} + +size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize) +{ + BYTE* const ostart = (BYTE* const)dst; + U32 const flSize = 1 + (srcSize>31) + (srcSize>4095); + + (void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */ + + switch(flSize) + { + case 1: /* 2 - 1 - 5 */ + ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3)); + break; + case 2: /* 2 - 2 - 12 */ + MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4))); + break; + case 3: /* 2 - 2 - 20 */ + MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4))); + break; + default: /* not necessary : flSize is {1,2,3} */ + assert(0); + } + + ostart[flSize] = *(const BYTE*)src; + return flSize+1; +} + +size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf, + ZSTD_hufCTables_t* nextHuf, + ZSTD_strategy strategy, int disableLiteralCompression, + void* dst, size_t dstCapacity, + const void* src, size_t srcSize, + void* workspace, size_t wkspSize, + const int bmi2) +{ + size_t const minGain = ZSTD_minGain(srcSize, strategy); + size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB); + BYTE* const ostart = (BYTE*)dst; + U32 singleStream = srcSize < 256; + symbolEncodingType_e hType = set_compressed; + size_t cLitSize; + + DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)", + disableLiteralCompression); + + /* Prepare nextEntropy assuming reusing the existing table */ + memcpy(nextHuf, prevHuf, sizeof(*prevHuf)); + + if (disableLiteralCompression) + return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); + + /* small ? don't even attempt compression (speed opt) */ +# define COMPRESS_LITERALS_SIZE_MIN 63 + { size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN; + if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize); + } + + RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression"); + { HUF_repeat repeat = prevHuf->repeatMode; + int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0; + if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1; + cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, + workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2) + : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11, + workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2); + if (repeat != HUF_repeat_none) { + /* reused the existing table */ *** DIFF OUTPUT TRUNCATED AT 1000 LINES ***
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?201908081537.x78FbuwU008673>