zstdlib 0.2.0-x86-mingw32 → 0.3.0-x86-mingw32

data/ext/zstdlib/{zstd-1.4.0 → zstd-1.4.2}/lib/compress/zstd_ldm.c

@@ -447,7 +447,7 @@ size_t ZSTD_ldm_generateSequences(
         if (ZSTD_window_needOverflowCorrection(ldmState->window, chunkEnd)) {
             U32 const ldmHSize = 1U << params->hashLog;
             U32 const correction = ZSTD_window_correctOverflow(
-                &ldmState->window, /* cycleLog */ 0, maxDist, src);
+                &ldmState->window, /* cycleLog */ 0, maxDist, chunkStart);
             ZSTD_ldm_reduceTable(ldmState->hashTable, ldmHSize, correction);
         }
         /* 2. We enforce the maximum offset allowed.

data/ext/zstdlib/{zstd-1.4.0 → zstd-1.4.2}/lib/compress/zstd_opt.c

@@ -255,13 +255,13 @@ static U32 ZSTD_litLengthPrice(U32 const litLength, const optState_t* const optP
  * to provide a cost which is directly comparable to a match ending at same position */
 static int ZSTD_litLengthContribution(U32 const litLength, const optState_t* const optPtr, int optLevel)
 {
-    if (optPtr->priceType >= zop_predef) return WEIGHT(litLength, optLevel);
+    if (optPtr->priceType >= zop_predef) return (int)WEIGHT(litLength, optLevel);
 
     /* dynamic statistics */
     {   U32 const llCode = ZSTD_LLcode(litLength);
-        int const contribution = (LL_bits[llCode] * BITCOST_MULTIPLIER)
-                               + WEIGHT(optPtr->litLengthFreq[0], optLevel)   /* note: log2litLengthSum cancel out */
-                               - WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
+        int const contribution = (int)(LL_bits[llCode] * BITCOST_MULTIPLIER)
+                               + (int)WEIGHT(optPtr->litLengthFreq[0], optLevel)   /* note: log2litLengthSum cancel out */
+                               - (int)WEIGHT(optPtr->litLengthFreq[llCode], optLevel);
 #if 1
         return contribution;
 #else
@@ -278,7 +278,7 @@ static int ZSTD_literalsContribution(const BYTE* const literals, U32 const litLe
                                      const optState_t* const optPtr,
                                      int optLevel)
 {
-    int const contribution = ZSTD_rawLiteralsCost(literals, litLength, optPtr, optLevel)
+    int const contribution = (int)ZSTD_rawLiteralsCost(literals, litLength, optPtr, optLevel)
                            + ZSTD_litLengthContribution(litLength, optPtr, optLevel);
     return contribution;
 }
@@ -372,13 +372,15 @@ MEM_STATIC U32 ZSTD_readMINMATCH(const void* memPtr, U32 length)
 
 /* Update hashTable3 up to ip (excluded)
    Assumption : always within prefix (i.e. not within extDict) */
-static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, const BYTE* const ip)
+static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms,
+                                              U32* nextToUpdate3,
+                                              const BYTE* const ip)
 {
     U32* const hashTable3 = ms->hashTable3;
     U32 const hashLog3 = ms->hashLog3;
     const BYTE* const base = ms->window.base;
-    U32 idx = ms->nextToUpdate3;
-    U32 const target = ms->nextToUpdate3 = (U32)(ip - base);
+    U32 idx = *nextToUpdate3;
+    U32 const target = (U32)(ip - base);
     size_t const hash3 = ZSTD_hash3Ptr(ip, hashLog3);
     assert(hashLog3 > 0);
 
@@ -387,6 +389,7 @@ static U32 ZSTD_insertAndFindFirstIndexHash3 (ZSTD_matchState_t* ms, const BYTE*
         idx++;
     }
 
+    *nextToUpdate3 = target;
     return hashTable3[hash3];
 }
 
@@ -503,9 +506,11 @@ static U32 ZSTD_insertBt1(
     }   }
 
     *smallerPtr = *largerPtr = 0;
-    if (bestLength > 384) return MIN(192, (U32)(bestLength - 384));   /* speed optimization */
-    assert(matchEndIdx > current + 8);
-    return matchEndIdx - (current + 8);
+    {   U32 positions = 0;
+        if (bestLength > 384) positions = MIN(192, (U32)(bestLength - 384));   /* speed optimization */
+        assert(matchEndIdx > current + 8);
+        return MAX(positions, matchEndIdx - (current + 8));
+    }
 }
 
 FORCE_INLINE_TEMPLATE
@@ -520,8 +525,13 @@ void ZSTD_updateTree_internal(
     DEBUGLOG(6, "ZSTD_updateTree_internal, from %u to %u  (dictMode:%u)",
                 idx, target, dictMode);
 
-    while(idx < target)
-        idx += ZSTD_insertBt1(ms, base+idx, iend, mls, dictMode == ZSTD_extDict);
+    while(idx < target) {
+        U32 const forward = ZSTD_insertBt1(ms, base+idx, iend, mls, dictMode == ZSTD_extDict);
+        assert(idx < (U32)(idx + forward));
+        idx += forward;
+    }
+    assert((size_t)(ip - base) <= (size_t)(U32)(-1));
+    assert((size_t)(iend - base) <= (size_t)(U32)(-1));
     ms->nextToUpdate = target;
 }
 
@@ -531,16 +541,18 @@ void ZSTD_updateTree(ZSTD_matchState_t* ms, const BYTE* ip, const BYTE* iend) {
 
 FORCE_INLINE_TEMPLATE
 U32 ZSTD_insertBtAndGetAllMatches (
+                    ZSTD_match_t* matches,   /* store result (found matches) in this table (presumed large enough) */
                     ZSTD_matchState_t* ms,
+                    U32* nextToUpdate3,
                     const BYTE* const ip, const BYTE* const iLimit, const ZSTD_dictMode_e dictMode,
-                    U32 rep[ZSTD_REP_NUM],
+                    const U32 rep[ZSTD_REP_NUM],
                     U32 const ll0,   /* tells if associated literal length is 0 or not. This value must be 0 or 1 */
-                    ZSTD_match_t* matches,
                     const U32 lengthToBeat,
                     U32 const mls /* template */)
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
     U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
+    U32 const maxDistance = 1U << cParams->windowLog;
     const BYTE* const base = ms->window.base;
     U32 const current = (U32)(ip-base);
     U32 const hashLog = cParams->hashLog;
@@ -556,8 +568,9 @@ U32 ZSTD_insertBtAndGetAllMatches (
     U32 const dictLimit = ms->window.dictLimit;
     const BYTE* const dictEnd = dictBase + dictLimit;
     const BYTE* const prefixStart = base + dictLimit;
-    U32 const btLow = btMask >= current ? 0 : current - btMask;
-    U32 const windowLow = ms->window.lowLimit;
+    U32 const btLow = (btMask >= current) ? 0 : current - btMask;
+    U32 const windowValid = ms->window.lowLimit;
+    U32 const windowLow = ((current - windowValid) > maxDistance) ? current - maxDistance : windowValid;
     U32 const matchLow = windowLow ? windowLow : 1;
     U32* smallerPtr = bt + 2*(current&btMask);
     U32* largerPtr  = bt + 2*(current&btMask) + 1;
@@ -627,7 +640,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
 
     /* HC3 match finder */
     if ((mls == 3) /*static*/ && (bestLength < mls)) {
-        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, ip);
+        U32 const matchIndex3 = ZSTD_insertAndFindFirstIndexHash3(ms, nextToUpdate3, ip);
         if ((matchIndex3 >= matchLow)
           & (current - matchIndex3 < (1<<18)) /*heuristic : longer distance likely too expensive*/ ) {
             size_t mlen;
@@ -653,9 +666,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
                      (ip+mlen == iLimit) ) {  /* best possible length */
                     ms->nextToUpdate = current+1;  /* skip insertion */
                     return 1;
-                }
-            }
-        }
+        }   }   }
         /* no dictMatchState lookup: dicts don't have a populated HC3 table */
     }
 
@@ -760,10 +771,13 @@ U32 ZSTD_insertBtAndGetAllMatches (
 
 
 FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
+                        ZSTD_match_t* matches,   /* store result (match found, increasing size) in this table */
                         ZSTD_matchState_t* ms,
+                        U32* nextToUpdate3,
                         const BYTE* ip, const BYTE* const iHighLimit, const ZSTD_dictMode_e dictMode,
-                        U32 rep[ZSTD_REP_NUM], U32 const ll0,
-                        ZSTD_match_t* matches, U32 const lengthToBeat)
+                        const U32 rep[ZSTD_REP_NUM],
+                        U32 const ll0,
+                        U32 const lengthToBeat)
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
     U32 const matchLengthSearch = cParams->minMatch;
@@ -772,12 +786,12 @@ FORCE_INLINE_TEMPLATE U32 ZSTD_BtGetAllMatches (
     ZSTD_updateTree_internal(ms, ip, iHighLimit, matchLengthSearch, dictMode);
     switch(matchLengthSearch)
     {
-    case 3 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 3);
+    case 3 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 3);
     default :
-    case 4 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 4);
-    case 5 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 5);
+    case 4 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 4);
+    case 5 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 5);
     case 7 :
-    case 6 : return ZSTD_insertBtAndGetAllMatches(ms, ip, iHighLimit, dictMode, rep, ll0, matches, lengthToBeat, 6);
+    case 6 : return ZSTD_insertBtAndGetAllMatches(matches, ms, nextToUpdate3, ip, iHighLimit, dictMode, rep, ll0, lengthToBeat, 6);
     }
 }
 
@@ -853,6 +867,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
 
     U32 const sufficient_len = MIN(cParams->targetLength, ZSTD_OPT_NUM -1);
     U32 const minMatch = (cParams->minMatch == 3) ? 3 : 4;
+    U32 nextToUpdate3 = ms->nextToUpdate;
 
     ZSTD_optimal_t* const opt = optStatePtr->priceTable;
     ZSTD_match_t* const matches = optStatePtr->matchTable;
@@ -862,7 +877,6 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
     DEBUGLOG(5, "ZSTD_compressBlock_opt_generic: current=%u, prefix=%u, nextToUpdate=%u",
                 (U32)(ip - base), ms->window.dictLimit, ms->nextToUpdate);
     assert(optLevel <= 2);
-    ms->nextToUpdate3 = ms->nextToUpdate;
     ZSTD_rescaleFreqs(optStatePtr, (const BYTE*)src, srcSize, optLevel);
     ip += (ip==prefixStart);
 
@@ -873,7 +887,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
         /* find first match */
         {   U32 const litlen = (U32)(ip - anchor);
             U32 const ll0 = !litlen;
-            U32 const nbMatches = ZSTD_BtGetAllMatches(ms, ip, iend, dictMode, rep, ll0, matches, minMatch);
+            U32 const nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, ip, iend, dictMode, rep, ll0, minMatch);
             if (!nbMatches) { ip++; continue; }
 
             /* initialize opt[0] */
@@ -970,7 +984,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
                 U32 const litlen = (opt[cur].mlen == 0) ? opt[cur].litlen : 0;
                 U32 const previousPrice = opt[cur].price;
                 U32 const basePrice = previousPrice + ZSTD_litLengthPrice(0, optStatePtr, optLevel);
-                U32 const nbMatches = ZSTD_BtGetAllMatches(ms, inr, iend, dictMode, opt[cur].rep, ll0, matches, minMatch);
+                U32 const nbMatches = ZSTD_BtGetAllMatches(matches, ms, &nextToUpdate3, inr, iend, dictMode, opt[cur].rep, ll0, minMatch);
                 U32 matchNb;
                 if (!nbMatches) {
                     DEBUGLOG(7, "rPos:%u : no match found", cur);
@@ -1094,7 +1108,7 @@ _shortestPath:   /* cur, last_pos, best_mlen, best_off have to be set */
     }   /* while (ip < ilimit) */
 
     /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }
 
 
@@ -1158,7 +1172,6 @@ ZSTD_initStats_ultra(ZSTD_matchState_t* ms,
     ms->window.dictLimit += (U32)srcSize;
     ms->window.lowLimit = ms->window.dictLimit;
     ms->nextToUpdate = ms->window.dictLimit;
-    ms->nextToUpdate3 = ms->window.dictLimit;
 
     /* re-inforce weight of collected statistics */
     ZSTD_upscaleStats(&ms->opt);

data/ext/zstdlib/{zstd-1.4.0 → zstd-1.4.2}/lib/compress/zstdmt_compress.c

@@ -1129,9 +1129,14 @@ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx)
             size_t const produced = ZSTD_isError(cResult) ? 0 : cResult;
             size_t const flushed = ZSTD_isError(cResult) ? 0 : jobPtr->dstFlushed;
             assert(flushed <= produced);
+            assert(jobPtr->consumed <= jobPtr->src.size);
             toFlush = produced - flushed;
-            if (toFlush==0 && (jobPtr->consumed >= jobPtr->src.size)) {
-                /* doneJobID is not-fully-flushed, but toFlush==0 : doneJobID should be compressing some more data */
+            /* if toFlush==0, nothing is available to flush.
+             * However, jobID is expected to still be active:
+             * if jobID was already completed and fully flushed,
+             * ZSTDMT_flushProduced() should have already moved onto next job.
+             * Therefore, some input has not yet been consumed. */
+            if (toFlush==0) {
                 assert(jobPtr->consumed < jobPtr->src.size);
             }
         }
@@ -1148,12 +1153,16 @@ size_t ZSTDMT_toFlushNow(ZSTDMT_CCtx* mtctx)
 
 static unsigned ZSTDMT_computeTargetJobLog(ZSTD_CCtx_params const params)
 {
-    if (params.ldmParams.enableLdm)
+    unsigned jobLog;
+    if (params.ldmParams.enableLdm) {
         /* In Long Range Mode, the windowLog is typically oversized.
          * In which case, it's preferable to determine the jobSize
          * based on chainLog instead. */
-        return MAX(21, params.cParams.chainLog + 4);
-    return MAX(20, params.cParams.windowLog + 2);
+        jobLog = MAX(21, params.cParams.chainLog + 4);
+    } else {
+        jobLog = MAX(20, params.cParams.windowLog + 2);
+    }
+    return MIN(jobLog, (unsigned)ZSTDMT_JOBLOG_MAX);
 }
 
 static int ZSTDMT_overlapLog_default(ZSTD_strategy strat)
@@ -1197,7 +1206,7 @@ static size_t ZSTDMT_computeOverlapSize(ZSTD_CCtx_params const params)
         ovLog = MIN(params.cParams.windowLog, ZSTDMT_computeTargetJobLog(params) - 2)
                 - overlapRLog;
     }
-    assert(0 <= ovLog && ovLog <= 30);
+    assert(0 <= ovLog && ovLog <= ZSTD_WINDOWLOG_MAX);
     DEBUGLOG(4, "overlapLog : %i", params.overlapLog);
     DEBUGLOG(4, "overlap size : %i", 1 << ovLog);
     return (ovLog==0) ? 0 : (size_t)1 << ovLog;
@@ -1391,7 +1400,7 @@ size_t ZSTDMT_initCStream_internal(
         FORWARD_IF_ERROR( ZSTDMT_resize(mtctx, params.nbWorkers) );
 
     if (params.jobSize != 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN;
-    if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = ZSTDMT_JOBSIZE_MAX;
+    if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = (size_t)ZSTDMT_JOBSIZE_MAX;
 
     mtctx->singleBlockingThread = (pledgedSrcSize <= ZSTDMT_JOBSIZE_MIN);  /* do not trigger multi-threading when srcSize is too small */
     if (mtctx->singleBlockingThread) {
@@ -1432,6 +1441,8 @@ size_t ZSTDMT_initCStream_internal(
     if (mtctx->targetSectionSize == 0) {
         mtctx->targetSectionSize = 1ULL << ZSTDMT_computeTargetJobLog(params);
     }
+    assert(mtctx->targetSectionSize <= (size_t)ZSTDMT_JOBSIZE_MAX);
+
     if (params.rsyncable) {
         /* Aim for the targetsectionSize as the average job size. */
         U32 const jobSizeMB = (U32)(mtctx->targetSectionSize >> 20);

data/ext/zstdlib/{zstd-1.4.0 → zstd-1.4.2}/lib/compress/zstdmt_compress.h

@@ -50,6 +50,7 @@
 #ifndef ZSTDMT_JOBSIZE_MIN
 #  define ZSTDMT_JOBSIZE_MIN (1 MB)
 #endif
+#define ZSTDMT_JOBLOG_MAX   (MEM_32bits() ? 29 : 30)
 #define ZSTDMT_JOBSIZE_MAX  (MEM_32bits() ? (512 MB) : (1024 MB))
 
 

data/ext/zstdlib/{zstd-1.4.0 → zstd-1.4.2}/lib/decompress/zstd_decompress.c

@@ -360,8 +360,11 @@ static size_t readSkippableFrameSize(void const* src, size_t srcSize)
     sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE);
     RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32,
                     frameParameter_unsupported);
-
-    return skippableHeaderSize + sizeU32;
+    {
+        size_t const skippableSize = skippableHeaderSize + sizeU32;
+        RETURN_ERROR_IF(skippableSize > srcSize, srcSize_wrong);
+        return skippableSize;
+    }
 }
 
 /** ZSTD_findDecompressedSize() :
@@ -378,11 +381,10 @@ unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize)
 
         if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
             size_t const skippableSize = readSkippableFrameSize(src, srcSize);
-            if (ZSTD_isError(skippableSize))
-                return skippableSize;
-            if (srcSize < skippableSize) {
+            if (ZSTD_isError(skippableSize)) {
                 return ZSTD_CONTENTSIZE_ERROR;
             }
+            assert(skippableSize <= srcSize);
 
             src = (const BYTE *)src + skippableSize;
             srcSize -= skippableSize;
@@ -467,6 +469,8 @@ static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize
     if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
         && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
         frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize);
+        assert(ZSTD_isError(frameSizeInfo.compressedSize) ||
+               frameSizeInfo.compressedSize <= srcSize);
         return frameSizeInfo;
     } else {
         const BYTE* ip = (const BYTE*)src;
@@ -529,7 +533,6 @@ size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
     return frameSizeInfo.compressedSize;
 }
 
-
 /** ZSTD_decompressBound() :
  *  compatible with legacy mode
  *  `src` must point to the start of a ZSTD frame or a skippeable frame
@@ -546,6 +549,7 @@ unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize)
         unsigned long long const decompressedBound = frameSizeInfo.decompressedBound;
         if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR)
             return ZSTD_CONTENTSIZE_ERROR;
+        assert(srcSize >= compressedSize);
         src = (const BYTE*)src + compressedSize;
         srcSize -= compressedSize;
         bound += decompressedBound;
@@ -738,9 +742,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
                         (unsigned)magicNumber, ZSTD_MAGICNUMBER);
             if ((magicNumber & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
                 size_t const skippableSize = readSkippableFrameSize(src, srcSize);
-                if (ZSTD_isError(skippableSize))
-                    return skippableSize;
-                RETURN_ERROR_IF(srcSize < skippableSize, srcSize_wrong);
+                FORWARD_IF_ERROR(skippableSize);
+                assert(skippableSize <= srcSize);
 
                 src = (const BYTE *)src + skippableSize;
                 srcSize -= skippableSize;
@@ -906,6 +909,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
         {   blockProperties_t bp;
             size_t const cBlockSize = ZSTD_getcBlockSize(src, ZSTD_blockHeaderSize, &bp);
             if (ZSTD_isError(cBlockSize)) return cBlockSize;
+            RETURN_ERROR_IF(cBlockSize > dctx->fParams.blockSizeMax, corruption_detected, "Block Size Exceeds Maximum");
             dctx->expected = cBlockSize;
             dctx->bType = bp.blockType;
             dctx->rleSize = bp.origSize;
@@ -950,6 +954,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
                 RETURN_ERROR(corruption_detected);
             }
             if (ZSTD_isError(rSize)) return rSize;
+            RETURN_ERROR_IF(rSize > dctx->fParams.blockSizeMax, corruption_detected, "Decompressed Block Size Exceeds Maximum");
             DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize);
             dctx->decodedSize += rSize;
             if (dctx->fParams.checksumFlag) XXH64_update(&dctx->xxhState, dst, rSize);

data/ext/zstdlib/{zstd-1.4.0 → zstd-1.4.2}/lib/decompress/zstd_decompress_block.c

@@ -505,7 +505,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
     *nbSeqPtr = nbSeq;
 
     /* FSE table descriptors */
-    RETURN_ERROR_IF(ip+4 > iend, srcSize_wrong); /* minimum possible size */
+    RETURN_ERROR_IF(ip+1 > iend, srcSize_wrong); /* minimum possible size: 1 byte for symbol encoding types */
     {   symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
         symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
         symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
@@ -637,9 +637,10 @@ size_t ZSTD_execSequence(BYTE* op,
     if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd);
 
     /* copy Literals */
-    ZSTD_copy8(op, *litPtr);
     if (sequence.litLength > 8)
-        ZSTD_wildcopy(op+8, (*litPtr)+8, sequence.litLength - 8);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+        ZSTD_wildcopy_16min(op, (*litPtr), sequence.litLength, ZSTD_no_overlap);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+    else
+        ZSTD_copy8(op, *litPtr);
     op = oLitEnd;
     *litPtr = iLitEnd;   /* update for next sequence */
 
@@ -686,13 +687,13 @@ size_t ZSTD_execSequence(BYTE* op,
 
     if (oMatchEnd > oend-(16-MINMATCH)) {
         if (op < oend_w) {
-            ZSTD_wildcopy(op, match, oend_w - op);
+            ZSTD_wildcopy(op, match, oend_w - op, ZSTD_overlap_src_before_dst);
             match += oend_w - op;
             op = oend_w;
         }
         while (op < oMatchEnd) *op++ = *match++;
     } else {
-        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8);   /* works even if matchLength < 8 */
+        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8, ZSTD_overlap_src_before_dst);   /* works even if matchLength < 8 */
     }
     return sequenceLength;
 }
@@ -717,9 +718,11 @@ size_t ZSTD_execSequenceLong(BYTE* op,
     if (oLitEnd > oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, dictStart, dictEnd);
 
     /* copy Literals */
-    ZSTD_copy8(op, *litPtr);  /* note : op <= oLitEnd <= oend_w == oend - 8 */
     if (sequence.litLength > 8)
-        ZSTD_wildcopy(op+8, (*litPtr)+8, sequence.litLength - 8);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+        ZSTD_wildcopy_16min(op, *litPtr, sequence.litLength, ZSTD_no_overlap);   /* note : since oLitEnd <= oend-WILDCOPY_OVERLENGTH, no risk of overwrite beyond oend */
+    else
+        ZSTD_copy8(op, *litPtr);  /* note : op <= oLitEnd <= oend_w == oend - 8 */
+
     op = oLitEnd;
     *litPtr = iLitEnd;   /* update for next sequence */
 
@@ -766,13 +769,13 @@ size_t ZSTD_execSequenceLong(BYTE* op,
 
     if (oMatchEnd > oend-(16-MINMATCH)) {
         if (op < oend_w) {
-            ZSTD_wildcopy(op, match, oend_w - op);
+            ZSTD_wildcopy(op, match, oend_w - op, ZSTD_overlap_src_before_dst);
             match += oend_w - op;
             op = oend_w;
         }
         while (op < oMatchEnd) *op++ = *match++;
     } else {
-        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8);   /* works even if matchLength < 8 */
+        ZSTD_wildcopy(op, match, (ptrdiff_t)sequence.matchLength-8, ZSTD_overlap_src_before_dst);   /* works even if matchLength < 8 */
     }
     return sequenceLength;
 }
@@ -889,6 +892,7 @@ ZSTD_decodeSequence(seqState_t* seqState, const ZSTD_longOffset_e longOffsets)
 }
 
 FORCE_INLINE_TEMPLATE size_t
+DONT_VECTORIZE
 ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
                                void* dst, size_t maxDstSize,
                          const void* seqStart, size_t seqSize, int nbSeq,
@@ -918,6 +922,11 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
         ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
         ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
 
+        ZSTD_STATIC_ASSERT(
+                BIT_DStream_unfinished < BIT_DStream_completed &&
+                BIT_DStream_endOfBuffer < BIT_DStream_completed &&
+                BIT_DStream_completed < BIT_DStream_overflow);
+
         for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && nbSeq ; ) {
             nbSeq--;
             {   seq_t const sequence = ZSTD_decodeSequence(&seqState, isLongOffset);
@@ -930,6 +939,7 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
         /* check if reached exact end */
         DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
         RETURN_ERROR_IF(nbSeq, corruption_detected);
+        RETURN_ERROR_IF(BIT_reloadDStream(&seqState.DStream) < BIT_DStream_completed, 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]); }
     }
@@ -1131,6 +1141,7 @@ ZSTD_decompressSequencesLong_default(ZSTD_DCtx* dctx,
 
 #ifndef ZSTD_FORCE_DECOMPRESS_SEQUENCES_LONG
 static TARGET_ATTRIBUTE("bmi2") size_t
+DONT_VECTORIZE
 ZSTD_decompressSequences_bmi2(ZSTD_DCtx* dctx,
                                  void* dst, size_t maxDstSize,
                            const void* seqStart, size_t seqSize, int nbSeq,