mirrors/zstd
0
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2024-11-30 16:56:44 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #3419 from facebook/fix3416

Browse Source 
fix root cause of #3416
This commit is contained in:
Yann Collet 2023-01-13 00:21:08 -08:00 committed by GitHub
commit d5509080bc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 42 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
lib/common/huf.h
View File

@ -221,7 +221,7 @@ size_t HUF_compress4X_repeat(void* dst, size_t dstSize,
unsigned maxSymbolValue, unsigned tableLog,
void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2,
unsigned suspectUncompressible, HUF_depth_mode depthMode);
int suspectUncompressible, HUF_depth_mode depthMode);
/** HUF_buildCTable_wksp() :
* Same as HUF_buildCTable(), but using externally allocated scratch buffer.
@ -328,7 +328,7 @@ size_t HUF_compress1X_repeat(void* dst, size_t dstSize,
unsigned maxSymbolValue, unsigned tableLog,
void* workSpace, size_t wkspSize, /**< `workSpace` must be aligned on 4-bytes boundaries, `wkspSize` must be >= HUF_WORKSPACE_SIZE */
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2,
unsigned suspectUncompressible, HUF_depth_mode depthMode);
int suspectUncompressible, HUF_depth_mode depthMode);
size_t HUF_decompress1X1 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /* single-symbol decoder */
#ifndef HUF_FORCE_DECOMPRESS_X1

6
lib/compress/huf_compress.c
View File

@ -1318,7 +1318,7 @@ HUF_compress_internal (void* dst, size_t dstSize,
HUF_nbStreams_e nbStreams,
void* workSpace, size_t wkspSize,
HUF_CElt* oldHufTable, HUF_repeat* repeat, int preferRepeat,
const int bmi2, unsigned suspectUncompressible, HUF_depth_mode depthMode)
const int bmi2, int suspectUncompressible, HUF_depth_mode depthMode)
{
HUF_compress_tables_t* const table = (HUF_compress_tables_t*)HUF_alignUpWorkspace(workSpace, &wkspSize, ZSTD_ALIGNOF(size_t));
BYTE* const ostart = (BYTE*)dst;
@ -1439,7 +1439,7 @@ size_t HUF_compress1X_repeat (void* dst, size_t dstSize,
unsigned maxSymbolValue, unsigned huffLog,
void* workSpace, size_t wkspSize,
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat,
int bmi2, unsigned suspectUncompressible, HUF_depth_mode depthMode)
int bmi2, int suspectUncompressible, HUF_depth_mode depthMode)
{
DEBUGLOG(5, "HUF_compress1X_repeat (srcSize = %zu)", srcSize);
return HUF_compress_internal(dst, dstSize, src, srcSize,
@ -1472,7 +1472,7 @@ size_t HUF_compress4X_repeat (void* dst, size_t dstSize,
unsigned maxSymbolValue, unsigned huffLog,
void* workSpace, size_t wkspSize,
HUF_CElt* hufTable, HUF_repeat* repeat, int preferRepeat, int bmi2,
unsigned suspectUncompressible, HUF_depth_mode depthMode)
int suspectUncompressible, HUF_depth_mode depthMode)
{
DEBUGLOG(5, "HUF_compress4X_repeat (srcSize = %zu)", srcSize);
return HUF_compress_internal(dst, dstSize, src, srcSize,

43
lib/compress/zstd_compress_literals.c
View File

@ -24,9 +24,9 @@ static size_t showHexa(const void* src, size_t srcSize)
const BYTE* const ip = (const BYTE*)src;
size_t u;
for (u=0; u<srcSize; u++) {
RAWLOG(6, " %02X", ip[u]); (void)ip;
RAWLOG(5, " %02X", ip[u]); (void)ip;
}
RAWLOG(6, " \n");
RAWLOG(5, " \n");
return srcSize;
}
@ -65,12 +65,26 @@ size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src,
return srcSize + flSize;
}
static int allBytesIdentical(const void* src, size_t srcSize)
{
assert(srcSize >= 1);
assert(src != NULL);
{ const BYTE b = ((const BYTE*)src)[0];
size_t p;
for (p=1; p<srcSize; p++) {
if (((const BYTE*)src)[p] != b) return 0;
}
return 1;
}
}
size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
{
BYTE* const ostart = (BYTE*)dst;
U32 const flSize = 1 + (srcSize>31) + (srcSize>4095);
(void)dstCapacity; /* dstCapacity already guaranteed to be >=4, hence large enough */
assert(dstCapacity >= 4); (void)dstCapacity;
assert(allBytesIdentical(src, srcSize));
switch(flSize)
{
@ -88,7 +102,7 @@ size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void*
}
ostart[flSize] = *(const BYTE*)src;
DEBUGLOG(5, "RLE literals: %u -> %u", (U32)srcSize, (U32)flSize + 1);
DEBUGLOG(5, "RLE : Repeated Literal (%02X: %u times) -> %u bytes encoded", ((const BYTE*)src)[0], (U32)srcSize, (U32)flSize + 1);
return flSize+1;
}
@ -105,8 +119,8 @@ ZSTD_minLiteralsToCompress(ZSTD_strategy strategy, HUF_repeat huf_repeat)
/* btultra2 : min 8 bytes;
* then 2x larger for each successive compression strategy
* max threshold 64 bytes */
{ int const shift = MIN(9-strategy, 3);
size_t const mintc = (huf_repeat == HUF_repeat_valid) ? 6 : 8 << shift;
{ int const shift = MIN(9-(int)strategy, 3);
size_t const mintc = (huf_repeat == HUF_repeat_valid) ? 6 : (size_t)8 << shift;
DEBUGLOG(7, "minLiteralsToCompress = %zu", mintc);
return mintc;
}
@ -148,7 +162,7 @@ size_t ZSTD_compressLiterals (
{ HUF_repeat repeat = prevHuf->repeatMode;
int const preferRepeat = (strategy < ZSTD_lazy) ? srcSize <= 1024 : 0;
HUF_depth_mode const depthMode = (strategy >= HUF_OPTIMAL_DEPTH_THRESHOLD) ? HUF_depth_optimal : HUF_depth_fast;
typedef size_t (*huf_compress_f)(void*, size_t, const void*, size_t, unsigned, unsigned, void*, size_t, HUF_CElt*, HUF_repeat*, int, int, unsigned, HUF_depth_mode);
typedef size_t (*huf_compress_f)(void*, size_t, const void*, size_t, unsigned, unsigned, void*, size_t, HUF_CElt*, HUF_repeat*, int, int, int, HUF_depth_mode);
huf_compress_f huf_compress;
if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
huf_compress = singleStream ? HUF_compress1X_repeat : HUF_compress4X_repeat;
@ -159,9 +173,10 @@ size_t ZSTD_compressLiterals (
(HUF_CElt*)nextHuf->CTable,
&repeat, preferRepeat,
bmi2, suspectUncompressible, depthMode);
DEBUGLOG(5, "%zu literals compressed into %zu bytes (before header)", srcSize, cLitSize);
if (repeat != HUF_repeat_none) {
/* reused the existing table */
DEBUGLOG(5, "Reusing previous huffman table");
DEBUGLOG(5, "reusing statistics from previous huffman block");
hType = set_repeat;
}
}
@ -172,9 +187,15 @@ size_t ZSTD_compressLiterals (
return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
} }
if (cLitSize==1) {
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
}
/* A return value of 1 signals that the alphabet consists of a single symbol.
* However, in some rare circumstances, it could be the compressed size (a single byte).
* For that outcome to have a chance to happen, it's necessary that `srcSize < 8`.
* (it's also necessary to not generate statistics).
* Therefore, in such a case, actively check that all bytes are identical. */
if ((srcSize >= 8) || allBytesIdentical(src, srcSize)) {
ZSTD_memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
} }
if (hType == set_compressed) {
/* using a newly constructed table */

4
lib/compress/zstd_compress_literals.h
View File

@ -16,6 +16,10 @@
size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
/* ZSTD_compressRleLiteralsBlock() :
* Conditions :
* - All bytes in @src are identical
* - dstCapacity >= 4 */
size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
/* ZSTD_compressLiterals():

1
lib/decompress/zstd_decompress.c
View File

@ -1043,6 +1043,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
}
ZSTD_DCtx_trace_end(dctx, (U64)(op-ostart), (U64)(ip-istart), /* streaming */ 0);
/* Allow caller to get size read */
DEBUGLOG(4, "ZSTD_decompressFrame: decompressed frame of size %zi, consuming %zi bytes of input", op-ostart, ip - (const BYTE*)*srcPtr);
*srcPtr = ip;
*srcSizePtr = remainingSrcSize;
return (size_t)(op-ostart);