sharpetronics/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-12-04 00:04:23 -05:00
Code Issues Projects Releases Wiki Activity

Merge pull request #1162 from facebook/corruptionFix

Browse Source 
Fixed a corruption bug
This commit is contained in:
Yann Collet 2018-06-05 06:50:29 -07:00 committed by GitHub
commit bdb673666f
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 145 additions and 124 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
lib/compress/zstd_compress.c
View File

@ -581,6 +581,7 @@ size_t ZSTD_CCtxParam_getParameter(
size_t ZSTD_CCtx_setParametersUsingCCtxParams(
ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params)
{
DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams");
if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
if (cctx->cdict) return ERROR(stage_wrong);
@ -1226,6 +1227,8 @@ static size_t ZSTD_resetCCtx_usingCDict(ZSTD_CCtx* cctx,
&& ZSTD_equivalentCParams(cctx->appliedParams.cParams,
cdict->cParams);
DEBUGLOG(4, "ZSTD_resetCCtx_usingCDict (pledgedSrcSize=%u)", (U32)pledgedSrcSize);
{ unsigned const windowLog = params.cParams.windowLog;
assert(windowLog != 0);

5
lib/compress/zstd_compress_internal.h
View File

@ -435,6 +435,11 @@ ZSTD_count_2segments(const BYTE* ip, const BYTE* match,
const BYTE* const vEnd = MIN( ip + (mEnd - match), iEnd);
size_t const matchLength = ZSTD_count(ip, match, vEnd);
if (match + matchLength != mEnd) return matchLength;
DEBUGLOG(7, "ZSTD_count_2segments: found a 2-parts match (current length==%zu)", matchLength);
DEBUGLOG(7, "distance from match beginning to end dictionary = %zi", mEnd - match);
DEBUGLOG(7, "distance from current pos to end buffer = %zi", iEnd - ip);
DEBUGLOG(7, "next byte : ip==%02X, istart==%02X", ip[matchLength], *iStart);
DEBUGLOG(7, "final match length = %zu", matchLength + ZSTD_count(ip+matchLength, iStart, iEnd));
return matchLength + ZSTD_count(ip+matchLength, iStart, iEnd);
}

100
lib/compress/zstd_double_fast.c
View File

@ -74,18 +74,18 @@ size_t ZSTD_compressBlock_doubleFast_generic(
dms->hashTable : NULL;
const U32* const dictHashSmall = dictMode == ZSTD_dictMatchState ?
dms->chainTable : NULL;
const U32 dictLowestIndex = dictMode == ZSTD_dictMatchState ?
const U32 dictStartIndex = dictMode == ZSTD_dictMatchState ?
dms->window.dictLimit : 0;
const BYTE* const dictBase = dictMode == ZSTD_dictMatchState ?
dms->window.base : NULL;
const BYTE* const dictLowest = dictMode == ZSTD_dictMatchState ?
dictBase + dictLowestIndex : NULL;
const BYTE* const dictStart = dictMode == ZSTD_dictMatchState ?
dictBase + dictStartIndex : NULL;
const BYTE* const dictEnd = dictMode == ZSTD_dictMatchState ?
dms->window.nextSrc : NULL;
const U32 dictIndexDelta = dictMode == ZSTD_dictMatchState ?
prefixLowestIndex - (U32)(dictEnd - dictBase) :
0;
const U32 dictAndPrefixLength = (U32)(ip - prefixLowest + dictEnd - dictLowest);
const U32 dictAndPrefixLength = (U32)(ip - prefixLowest + dictEnd - dictStart);
assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
@ -126,7 +126,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
&& ((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, istart) + 4;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixLowest) + 4;
ip++;
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
goto _match_stored;
@ -155,10 +155,10 @@ size_t ZSTD_compressBlock_doubleFast_generic(
const BYTE* dictMatchL = dictBase + dictMatchIndexL;
assert(dictMatchL < dictEnd);
if (dictMatchL > dictLowest && MEM_read64(dictMatchL) == MEM_read64(ip)) {
if (dictMatchL > dictStart && MEM_read64(dictMatchL) == MEM_read64(ip)) {
mLength = ZSTD_count_2segments(ip+8, dictMatchL+8, iend, dictEnd, prefixLowest) + 8;
offset = (U32)(current - dictMatchIndexL - dictIndexDelta);
while (((ip>anchor) & (dictMatchL>dictLowest)) && (ip[-1] == dictMatchL[-1])) { ip--; dictMatchL--; mLength++; } /* catch up */
while (((ip>anchor) & (dictMatchL>dictStart)) && (ip[-1] == dictMatchL[-1])) { ip--; dictMatchL--; mLength++; } /* catch up */
goto _match_found;
}
}
@ -174,7 +174,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
match = dictBase + dictMatchIndexS;
matchIndexS = dictMatchIndexS + dictIndexDelta;
if (match > dictLowest && MEM_read32(match) == MEM_read32(ip)) {
if (match > dictStart && MEM_read32(match) == MEM_read32(ip)) {
goto _search_next_long;
}
}
@ -183,7 +183,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
continue;
_search_next_long:
{
size_t const hl3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
U32 const matchIndexL3 = hashLong[hl3];
@ -204,21 +204,21 @@ _search_next_long:
U32 const dictMatchIndexL3 = dictHashLong[hl3];
const BYTE* dictMatchL3 = dictBase + dictMatchIndexL3;
assert(dictMatchL3 < dictEnd);
if (dictMatchL3 > dictLowest && MEM_read64(dictMatchL3) == MEM_read64(ip+1)) {
if (dictMatchL3 > dictStart && MEM_read64(dictMatchL3) == MEM_read64(ip+1)) {
mLength = ZSTD_count_2segments(ip+1+8, dictMatchL3+8, iend, dictEnd, prefixLowest) + 8;
ip++;
offset = (U32)(current + 1 - dictMatchIndexL3 - dictIndexDelta);
while (((ip>anchor) & (dictMatchL3>dictLowest)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */
while (((ip>anchor) & (dictMatchL3>dictStart)) && (ip[-1] == dictMatchL3[-1])) { ip--; dictMatchL3--; mLength++; } /* catch up */
goto _match_found;
}
}
}
/* if no long +1 match, explore the short match we found */
if (dictMode == ZSTD_dictMatchState && matchIndexS < prefixLowestIndex) {
mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, istart) + 4;
mLength = ZSTD_count_2segments(ip+4, match+4, iend, dictEnd, prefixLowest) + 4;
offset = (U32)(current - matchIndexS);
while (((ip>anchor) & (match>dictLowest)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
while (((ip>anchor) & (match>dictStart)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
} else {
mLength = ZSTD_count(ip+4, match+4, iend) + 4;
offset = (U32)(ip - match);
@ -257,7 +257,7 @@ _match_stored:
if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < prefixLowestIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, istart) + 4;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixLowest) + 4;
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2;
@ -343,18 +343,18 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
U32 const hBitsL = cParams->hashLog;
U32* const hashSmall = ms->chainTable;
U32 const hBitsS = cParams->chainLog;
const BYTE* const base = ms->window.base;
const BYTE* const dictBase = ms->window.dictBase;
const BYTE* const istart = (const BYTE*)src;
const BYTE* ip = istart;
const BYTE* anchor = istart;
const U32 lowestIndex = ms->window.lowLimit;
const BYTE* const dictStart = dictBase + lowestIndex;
const U32 dictLimit = ms->window.dictLimit;
const BYTE* const lowPrefixPtr = base + dictLimit;
const BYTE* const dictEnd = dictBase + dictLimit;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - 8;
const U32 prefixStartIndex = ms->window.dictLimit;
const BYTE* const base = ms->window.base;
const BYTE* const prefixStart = base + prefixStartIndex;
const U32 dictStartIndex = ms->window.lowLimit;
const BYTE* const dictBase = ms->window.dictBase;
const BYTE* const dictStart = dictBase + dictStartIndex;
const BYTE* const dictEnd = dictBase + prefixStartIndex;
U32 offset_1=rep[0], offset_2=rep[1];
DEBUGLOG(5, "ZSTD_compressBlock_doubleFast_extDict_generic (srcSize=%zu)", srcSize);
@ -363,57 +363,58 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
while (ip < ilimit) { /* < instead of <=, because (ip+1) */
const size_t hSmall = ZSTD_hashPtr(ip, hBitsS, mls);
const U32 matchIndex = hashSmall[hSmall];
const BYTE* matchBase = matchIndex < dictLimit ? dictBase : base;
const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base;
const BYTE* match = matchBase + matchIndex;
const size_t hLong = ZSTD_hashPtr(ip, hBitsL, 8);
const U32 matchLongIndex = hashLong[hLong];
const BYTE* matchLongBase = matchLongIndex < dictLimit ? dictBase : base;
const BYTE* const matchLongBase = matchLongIndex < prefixStartIndex ? dictBase : base;
const BYTE* matchLong = matchLongBase + matchLongIndex;
const U32 current = (U32)(ip-base);
const U32 repIndex = current + 1 - offset_1; /* offset_1 expected <= current +1 */
const BYTE* repBase = repIndex < dictLimit ? dictBase : base;
const BYTE* repMatch = repBase + repIndex;
const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base;
const BYTE* const repMatch = repBase + repIndex;
size_t mLength;
hashSmall[hSmall] = hashLong[hLong] = current; /* update hash table */
if ( (((U32)((dictLimit-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex))
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, lowPrefixPtr) + 4;
if ((((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex doesn't overlap dict + prefix */
& (repIndex > dictStartIndex))
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
ip++;
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
} else {
if ((matchLongIndex > lowestIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) {
const BYTE* matchEnd = matchLongIndex < dictLimit ? dictEnd : iend;
const BYTE* lowMatchPtr = matchLongIndex < dictLimit ? dictStart : lowPrefixPtr;
if ((matchLongIndex > dictStartIndex) && (MEM_read64(matchLong) == MEM_read64(ip))) {
const BYTE* const matchEnd = matchLongIndex < prefixStartIndex ? dictEnd : iend;
const BYTE* const lowMatchPtr = matchLongIndex < prefixStartIndex ? dictStart : prefixStart;
U32 offset;
mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, lowPrefixPtr) + 8;
mLength = ZSTD_count_2segments(ip+8, matchLong+8, iend, matchEnd, prefixStart) + 8;
offset = current - matchLongIndex;
while (((ip>anchor) & (matchLong>lowMatchPtr)) && (ip[-1] == matchLong[-1])) { ip--; matchLong--; mLength++; } /* catch up */
offset_2 = offset_1;
offset_1 = offset;
ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
} else if ((matchIndex > lowestIndex) && (MEM_read32(match) == MEM_read32(ip))) {
} else if ((matchIndex > dictStartIndex) && (MEM_read32(match) == MEM_read32(ip))) {
size_t const h3 = ZSTD_hashPtr(ip+1, hBitsL, 8);
U32 const matchIndex3 = hashLong[h3];
const BYTE* const match3Base = matchIndex3 < dictLimit ? dictBase : base;
const BYTE* const match3Base = matchIndex3 < prefixStartIndex ? dictBase : base;
const BYTE* match3 = match3Base + matchIndex3;
U32 offset;
hashLong[h3] = current + 1;
if ( (matchIndex3 > lowestIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) {
const BYTE* matchEnd = matchIndex3 < dictLimit ? dictEnd : iend;
const BYTE* lowMatchPtr = matchIndex3 < dictLimit ? dictStart : lowPrefixPtr;
mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, lowPrefixPtr) + 8;
if ( (matchIndex3 > dictStartIndex) && (MEM_read64(match3) == MEM_read64(ip+1)) ) {
const BYTE* const matchEnd = matchIndex3 < prefixStartIndex ? dictEnd : iend;
const BYTE* const lowMatchPtr = matchIndex3 < prefixStartIndex ? dictStart : prefixStart;
mLength = ZSTD_count_2segments(ip+9, match3+8, iend, matchEnd, prefixStart) + 8;
ip++;
offset = current+1 - matchIndex3;
while (((ip>anchor) & (match3>lowMatchPtr)) && (ip[-1] == match3[-1])) { ip--; match3--; mLength++; } /* catch up */
} else {
const BYTE* matchEnd = matchIndex < dictLimit ? dictEnd : iend;
const BYTE* lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, lowPrefixPtr) + 4;
const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
offset = current - matchIndex;
while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
}
@ -440,12 +441,13 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2;
const BYTE* repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
if ( (((U32)((dictLimit-1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, lowPrefixPtr) + 4;
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) /* intentional overflow : ensure repIndex2 doesn't overlap dict + prefix */
& (repIndex2 > dictStartIndex))
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
U32 const tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
hashSmall[ZSTD_hashPtr(ip, hBitsS, mls)] = current2;
hashLong[ZSTD_hashPtr(ip, hBitsL, 8)] = current2;

95
lib/compress/zstd_fast.c
View File

@ -53,8 +53,8 @@ size_t ZSTD_compressBlock_fast_generic(
const BYTE* const istart = (const BYTE*)src;
const BYTE* ip = istart;
const BYTE* anchor = istart;
const U32 prefixLowestIndex = ms->window.dictLimit;
const BYTE* const prefixLowest = base + prefixLowestIndex;
const U32 prefixStartIndex = ms->window.dictLimit;
const BYTE* const prefixStart = base + prefixStartIndex;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - HASH_READ_SIZE;
U32 offset_1=rep[0], offset_2=rep[1];
@ -63,30 +63,30 @@ size_t ZSTD_compressBlock_fast_generic(
const ZSTD_matchState_t* const dms = ms->dictMatchState;
const U32* const dictHashTable = dictMode == ZSTD_dictMatchState ?
dms->hashTable : NULL;
const U32 dictLowestIndex = dictMode == ZSTD_dictMatchState ?
const U32 dictStartIndex = dictMode == ZSTD_dictMatchState ?
dms->window.dictLimit : 0;
const BYTE* const dictBase = dictMode == ZSTD_dictMatchState ?
dms->window.base : NULL;
const BYTE* const dictLowest = dictMode == ZSTD_dictMatchState ?
dictBase + dictLowestIndex : NULL;
const BYTE* const dictStart = dictMode == ZSTD_dictMatchState ?
dictBase + dictStartIndex : NULL;
const BYTE* const dictEnd = dictMode == ZSTD_dictMatchState ?
dms->window.nextSrc : NULL;
const U32 dictIndexDelta = dictMode == ZSTD_dictMatchState ?
prefixLowestIndex - (U32)(dictEnd - dictBase) :
prefixStartIndex - (U32)(dictEnd - dictBase) :
0;
const U32 dictAndPrefixLength = (U32)(ip - prefixLowest + dictEnd - dictLowest);
const U32 dictAndPrefixLength = (U32)(ip - prefixStart + dictEnd - dictStart);
assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
/* otherwise, we would get index underflow when translating a dict index
* into a local index */
assert(dictMode != ZSTD_dictMatchState
|| prefixLowestIndex >= (U32)(dictEnd - dictBase));
|| prefixStartIndex >= (U32)(dictEnd - dictBase));
/* init */
ip += (dictAndPrefixLength == 0);
if (dictMode == ZSTD_noDict) {
U32 const maxRep = (U32)(ip - prefixLowest);
U32 const maxRep = (U32)(ip - prefixStart);
if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
}
@ -106,16 +106,16 @@ size_t ZSTD_compressBlock_fast_generic(
const BYTE* match = base + matchIndex;
const U32 repIndex = current + 1 - offset_1;
const BYTE* repMatch = (dictMode == ZSTD_dictMatchState
&& repIndex < prefixLowestIndex) ?
&& repIndex < prefixStartIndex) ?
dictBase + (repIndex - dictIndexDelta) :
base + repIndex;
hashTable[h] = current; /* update hash table */
if (dictMode == ZSTD_dictMatchState
&& ((U32)((prefixLowestIndex-1) - repIndex) >= 3 /* intentional underflow */)
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < prefixLowestIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, istart) + 4;
if ( (dictMode == ZSTD_dictMatchState)
&& ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
ip++;
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
} else if ( dictMode == ZSTD_noDict
@ -123,12 +123,12 @@ size_t ZSTD_compressBlock_fast_generic(
mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
ip++;
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
} else if ( (matchIndex <= prefixLowestIndex)
} else if ( (matchIndex <= prefixStartIndex)
|| (MEM_read32(match) != MEM_read32(ip)) ) {
if (dictMode == ZSTD_dictMatchState) {
U32 const dictMatchIndex = dictHashTable[h];
const BYTE* dictMatch = dictBase + dictMatchIndex;
if (dictMatchIndex <= dictLowestIndex ||
if (dictMatchIndex <= dictStartIndex ||
MEM_read32(dictMatch) != MEM_read32(ip)) {
assert(stepSize >= 1);
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
@ -136,8 +136,8 @@ size_t ZSTD_compressBlock_fast_generic(
} else {
/* found a dict match */
U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, istart) + 4;
while (((ip>anchor) & (dictMatch>dictLowest))
mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
while (((ip>anchor) & (dictMatch>dictStart))
&& (ip[-1] == dictMatch[-1])) {
ip--; dictMatch--; mLength++;
} /* catch up */
@ -154,7 +154,7 @@ size_t ZSTD_compressBlock_fast_generic(
/* found a regular match */
U32 const offset = (U32)(ip-match);
mLength = ZSTD_count(ip+4, match+4, iend) + 4;
while (((ip>anchor) & (match>prefixLowest))
while (((ip>anchor) & (match>prefixStart))
&& (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset_2 = offset_1;
offset_1 = offset;
@ -175,13 +175,13 @@ size_t ZSTD_compressBlock_fast_generic(
while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2;
const BYTE* repMatch2 = repIndex2 < prefixLowestIndex ?
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
dictBase - dictIndexDelta + repIndex2 :
base + repIndex2;
if ( ((U32)((prefixLowestIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < prefixLowestIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, istart) + 4;
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
@ -272,11 +272,11 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
const BYTE* const istart = (const BYTE*)src;
const BYTE* ip = istart;
const BYTE* anchor = istart;
const U32 lowestIndex = ms->window.lowLimit;
const BYTE* const dictStart = dictBase + lowestIndex;
const U32 dictLimit = ms->window.dictLimit;
const BYTE* const lowPrefixPtr = base + dictLimit;
const BYTE* const dictEnd = dictBase + dictLimit;
const U32 dictStartIndex = ms->window.lowLimit;
const BYTE* const dictStart = dictBase + dictStartIndex;
const U32 prefixStartIndex = ms->window.dictLimit;
const BYTE* const prefixStart = base + prefixStartIndex;
const BYTE* const dictEnd = dictBase + prefixStartIndex;
const BYTE* const iend = istart + srcSize;
const BYTE* const ilimit = iend - 8;
U32 offset_1=rep[0], offset_2=rep[1];
@ -284,33 +284,34 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
/* Search Loop */
while (ip < ilimit) { /* < instead of <=, because (ip+1) */
const size_t h = ZSTD_hashPtr(ip, hlog, mls);
const U32 matchIndex = hashTable[h];
const BYTE* matchBase = matchIndex < dictLimit ? dictBase : base;
const BYTE* match = matchBase + matchIndex;
const U32 current = (U32)(ip-base);
const U32 repIndex = current + 1 - offset_1; /* offset_1 expected <= current +1 */
const BYTE* repBase = repIndex < dictLimit ? dictBase : base;
const BYTE* repMatch = repBase + repIndex;
const U32 matchIndex = hashTable[h];
const BYTE* const matchBase = matchIndex < prefixStartIndex ? dictBase : base;
const BYTE* match = matchBase + matchIndex;
const U32 current = (U32)(ip-base);
const U32 repIndex = current + 1 - offset_1;
const BYTE* const repBase = repIndex < prefixStartIndex ? dictBase : base;
const BYTE* const repMatch = repBase + repIndex;
size_t mLength;
hashTable[h] = current; /* update hash table */
assert(offset_1 <= current +1); /* check repIndex */
if ( (((U32)((dictLimit-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > lowestIndex))
if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (repIndex > dictStartIndex))
&& (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
const BYTE* repMatchEnd = repIndex < dictLimit ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, lowPrefixPtr) + 4;
const BYTE* repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
ip++;
ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
} else {
if ( (matchIndex < lowestIndex) ||
if ( (matchIndex < dictStartIndex) ||
(MEM_read32(match) != MEM_read32(ip)) ) {
assert(stepSize >= 1);
ip += ((ip-anchor) >> kSearchStrength) + stepSize;
continue;
}
{ const BYTE* matchEnd = matchIndex < dictLimit ? dictEnd : iend;
const BYTE* lowMatchPtr = matchIndex < dictLimit ? dictStart : lowPrefixPtr;
{ const BYTE* matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
const BYTE* lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
U32 offset;
mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, lowPrefixPtr) + 4;
mLength = ZSTD_count_2segments(ip+4, match+4, iend, matchEnd, prefixStart) + 4;
while (((ip>anchor) & (match>lowMatchPtr)) && (ip[-1] == match[-1])) { ip--; match--; mLength++; } /* catch up */
offset = current - matchIndex;
offset_2 = offset_1;
@ -330,11 +331,11 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
while (ip <= ilimit) {
U32 const current2 = (U32)(ip-base);
U32 const repIndex2 = current2 - offset_2;
const BYTE* repMatch2 = repIndex2 < dictLimit ? dictBase + repIndex2 : base + repIndex2;
if ( (((U32)((dictLimit-1) - repIndex2) >= 3) & (repIndex2 > lowestIndex)) /* intentional overflow */
const BYTE* repMatch2 = repIndex2 < prefixStartIndex ? dictBase + repIndex2 : base + repIndex2;
if ( (((U32)((prefixStartIndex-1) - repIndex2) >= 3) & (repIndex2 > dictStartIndex)) /* intentional overflow */
&& (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
const BYTE* const repEnd2 = repIndex2 < dictLimit ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, lowPrefixPtr) + 4;
const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset; /* swap offset_2 <=> offset_1 */
ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;

50
lib/decompress/zstd_decompress.c
View File

@ -115,8 +115,8 @@ struct ZSTD_DCtx_s
const HUF_DTable* HUFptr;
ZSTD_entropyDTables_t entropy;
const void* previousDstEnd; /* detect continuity */
const void* base; /* start of current segment */
const void* vBase; /* virtual start of previous segment if it was just before current one */
const void* prefixStart; /* start of current segment */
const void* virtualStart; /* virtual start of previous segment if it was just before current one */
const void* dictEnd; /* end of previous segment */
size_t expected;
ZSTD_frameHeader fParams;
@ -1076,7 +1076,7 @@ HINT_INLINE
size_t ZSTD_execSequence(BYTE* op,
BYTE* const oend, seq_t sequence,
const BYTE** litPtr, const BYTE* const litLimit,
const BYTE* const base, const BYTE* const vBase, const BYTE* const dictEnd)
const BYTE* const prefixStart, const BYTE* const virtualStart, const BYTE* const dictEnd)
{
BYTE* const oLitEnd = op + sequence.litLength;
size_t const sequenceLength = sequence.litLength + sequence.matchLength;
@ -1088,7 +1088,7 @@ size_t ZSTD_execSequence(BYTE* op,
/* check */
if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
if (iLitEnd > litLimit) return ERROR(corruption_detected); /* over-read beyond lit buffer */
if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, base, vBase, dictEnd);
if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd);
/* copy Literals */
ZSTD_copy8(op, *litPtr);
@ -1098,21 +1098,25 @@ size_t ZSTD_execSequence(BYTE* op,
*litPtr = iLitEnd; /* update for next sequence */
/* copy Match */
if (sequence.offset > (size_t)(oLitEnd - base)) {
if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
/* offset beyond prefix -> go into extDict */
if (sequence.offset > (size_t)(oLitEnd - vBase))
if (sequence.offset > (size_t)(oLitEnd - virtualStart))
return ERROR(corruption_detected);
match = dictEnd + (match - base);
match = dictEnd + (match - prefixStart);
if (match + sequence.matchLength <= dictEnd) {
memmove(oLitEnd, match, sequence.matchLength);
return sequenceLength;
}
/* span extDict & currentPrefixSegment */
DEBUGLOG(2, "ZSTD_execSequence: found a 2-segments match")
{ size_t const length1 = dictEnd - match;
DEBUGLOG(2, "first part (extDict) is %zu bytes long", length1);
memmove(oLitEnd, match, length1);
op = oLitEnd + length1;
sequence.matchLength -= length1;
match = base;
DEBUGLOG(2, "second part (prefix) is %zu bytes long", sequence.matchLength);
match = prefixStart;
DEBUGLOG(2, "first byte of 2nd part : %02X", *prefixStart);
if (op > oend_w || sequence.matchLength < MINMATCH) {
U32 i;
for (i = 0; i < sequence.matchLength; ++i) op[i] = match[i];
@ -1355,10 +1359,10 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
BYTE* op = ostart;
const BYTE* litPtr = dctx->litPtr;
const BYTE* const litEnd = litPtr + dctx->litSize;
const BYTE* const base = (const BYTE*) (dctx->base);
const BYTE* const vBase = (const BYTE*) (dctx->vBase);
const BYTE* const prefixStart = (const BYTE*) (dctx->prefixStart);
const BYTE* const vBase = (const BYTE*) (dctx->virtualStart);
const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
DEBUGLOG(5, "ZSTD_decompressSequences");
DEBUGLOG(5, "ZSTD_decompressSequences_body");
/* Regen sequences */
if (nbSeq) {
@ -1373,14 +1377,14 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && nbSeq ; ) {
nbSeq--;
{ seq_t const sequence = ZSTD_decodeSequence(&seqState, isLongOffset);
size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, base, vBase, dictEnd);
size_t const oneSeqSize = ZSTD_execSequence(op, oend, sequence, &litPtr, litEnd, prefixStart, vBase, dictEnd);
DEBUGLOG(6, "regenerated sequence size : %u", (U32)oneSeqSize);
if (ZSTD_isError(oneSeqSize)) return oneSeqSize;
op += oneSeqSize;
} }
/* check if reached exact end */
DEBUGLOG(5, "ZSTD_decompressSequences: after decode loop, remaining nbSeq : %i", nbSeq);
DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
if (nbSeq) return ERROR(corruption_detected);
/* save reps for next block */
{ U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
@ -1499,8 +1503,8 @@ ZSTD_decompressSequencesLong_body(
BYTE* op = ostart;
const BYTE* litPtr = dctx->litPtr;
const BYTE* const litEnd = litPtr + dctx->litSize;
const BYTE* const prefixStart = (const BYTE*) (dctx->base);
const BYTE* const dictStart = (const BYTE*) (dctx->vBase);
const BYTE* const prefixStart = (const BYTE*) (dctx->prefixStart);
const BYTE* const dictStart = (const BYTE*) (dctx->virtualStart);
const BYTE* const dictEnd = (const BYTE*) (dctx->dictEnd);
/* Regen sequences */
@ -1702,8 +1706,8 @@ static void ZSTD_checkContinuity(ZSTD_DCtx* dctx, const void* dst)
{
if (dst != dctx->previousDstEnd) { /* not contiguous */
dctx->dictEnd = dctx->previousDstEnd;
dctx->vBase = (const char*)dst - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->base));
dctx->base = dst;
dctx->virtualStart = (const char*)dst - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->prefixStart));
dctx->prefixStart = dst;
dctx->previousDstEnd = dst;
}
}
@ -2171,8 +2175,8 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
static size_t ZSTD_refDictContent(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
{
dctx->dictEnd = dctx->previousDstEnd;
dctx->vBase = (const char*)dict - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->base));
dctx->base = dict;
dctx->virtualStart = (const char*)dict - ((const char*)(dctx->previousDstEnd) - (const char*)(dctx->prefixStart));
dctx->prefixStart = dict;
dctx->previousDstEnd = (const char*)dict + dictSize;
return 0;
}
@ -2276,8 +2280,8 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
dctx->stage = ZSTDds_getFrameHeaderSize;
dctx->decodedSize = 0;
dctx->previousDstEnd = NULL;
dctx->base = NULL;
dctx->vBase = NULL;
dctx->prefixStart = NULL;
dctx->virtualStart = NULL;
dctx->dictEnd = NULL;
dctx->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001); /* cover both little and big endian */
dctx->litEntropy = dctx->fseEntropy = 0;
@ -2327,8 +2331,8 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dstDCtx, const ZSTD_DDict* ddi
CHECK_F( ZSTD_decompressBegin(dstDCtx) );
if (ddict) { /* support begin on NULL */
dstDCtx->dictID = ddict->dictID;
dstDCtx->base = ddict->dictContent;
dstDCtx->vBase = ddict->dictContent;
dstDCtx->prefixStart = ddict->dictContent;
dstDCtx->virtualStart = ddict->dictContent;
dstDCtx->dictEnd = (const BYTE*)ddict->dictContent + ddict->dictSize;
dstDCtx->previousDstEnd = dstDCtx->dictEnd;
if (ddict->entropyPresent) {

16
tests/zstreamtest.c
View File

@ -1671,10 +1671,13 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
/* compression init */
CHECK_Z( ZSTD_CCtx_loadDictionary(zc, NULL, 0) ); /* cancel previous dict /*/
if ((FUZ_rand(&lseed)&1) /* at beginning, to keep same nb of rand */
&& oldTestLog /* at least one test happened */ && resetAllowed) {
&& oldTestLog /* at least one test happened */
&& resetAllowed) {
/* just set a compression level */
maxTestSize = FUZ_randomLength(&lseed, oldTestLog+2);
if (maxTestSize >= srcBufferSize) maxTestSize = srcBufferSize-1;
{ int const compressionLevel = (FUZ_rand(&lseed) % 5) + 1;
DISPLAYLEVEL(5, "t%u : compression level : %i \n", testNb, compressionLevel);
CHECK_Z (setCCtxParameter(zc, cctxParams, ZSTD_p_compressionLevel, compressionLevel, useOpaqueAPI) );
}
} else {
@ -1698,6 +1701,8 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
{ U64 const pledgedSrcSize = (FUZ_rand(&lseed) & 3) ? ZSTD_CONTENTSIZE_UNKNOWN : maxTestSize;
ZSTD_compressionParameters cParams = ZSTD_getCParams(cLevel, pledgedSrcSize, dictSize);
static const U32 windowLogMax = 24;
if (dictSize)
DISPLAYLEVEL(5, "t%u: with dictionary of size : %zu \n", testNb, dictSize);
/* mess with compression parameters */
cParams.windowLog += (FUZ_rand(&lseed) & 3) - 1;
@ -1707,7 +1712,7 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
cParams.searchLog += (FUZ_rand(&lseed) & 3) - 1;
cParams.searchLength += (FUZ_rand(&lseed) & 3) - 1;
cParams.targetLength = (U32)((cParams.targetLength + 1 ) * (0.5 + ((double)(FUZ_rand(&lseed) & 127) / 128)));
cParams = ZSTD_adjustCParams(cParams, 0, 0);
cParams = ZSTD_adjustCParams(cParams, pledgedSrcSize, dictSize);
if (FUZ_rand(&lseed) & 1) {
DISPLAYLEVEL(5, "t%u: windowLog : %u \n", testNb, cParams.windowLog);
@ -1766,7 +1771,7 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
/* Apply parameters */
if (useOpaqueAPI) {
DISPLAYLEVEL(6," t%u: applying CCtxParams \n", testNb);
DISPLAYLEVEL(5, "t%u: applying CCtxParams \n", testNb);
CHECK_Z (ZSTD_CCtx_setParametersUsingCCtxParams(zc, cctxParams) );
}
@ -1832,7 +1837,7 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
} }
crcOrig = XXH64_digest(&xxhState);
cSize = outBuff.pos;
DISPLAYLEVEL(5, "Frame completed : %u bytes \n", (U32)cSize);
DISPLAYLEVEL(5, "Frame completed : %zu bytes \n", cSize);
}
CHECK(badParameters(zc, savedParams), "CCtx params are wrong");
@ -1842,7 +1847,8 @@ static int fuzzerTests_newAPI(U32 seed, U32 nbTests, unsigned startTest, double
DISPLAYLEVEL(5, "resetting DCtx (dict:%08X) \n", (U32)(size_t)dict);
CHECK_Z( ZSTD_resetDStream(zd) );
} else {
DISPLAYLEVEL(5, "using dict of size %u \n", (U32)dictSize);
if (dictSize)
DISPLAYLEVEL(5, "using dictionary of size %zu \n", dictSize);
CHECK_Z( ZSTD_initDStream_usingDict(zd, dict, dictSize) );
}
{ size_t decompressionResult = 1;