zstd-ruby 1.3.8.0 → 1.4.5.0

data/ext/zstdruby/libzstd/compress/zstd_fast.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -15,7 +15,7 @@
 extern "C" {
 #endif
 
-#include "mem.h"      /* U32 */
+#include "../common/mem.h"      /* U32 */
 #include "zstd_compress_internal.h"
 
 void ZSTD_fillHashTable(ZSTD_matchState_t* ms,

data/ext/zstdruby/libzstd/compress/zstd_lazy.c

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -83,7 +83,10 @@ ZSTD_insertDUBT1(ZSTD_matchState_t* ms,
     U32* largerPtr  = smallerPtr + 1;
     U32 matchIndex = *smallerPtr;   /* this candidate is unsorted : next sorted candidate is reached through *smallerPtr, while *largerPtr contains previous unsorted candidate (which is already saved and can be overwritten) */
     U32 dummy32;   /* to be nullified at the end */
-    U32 const windowLow = ms->window.lowLimit;
+    U32 const windowValid = ms->window.lowLimit;
+    U32 const maxDistance = 1U << cParams->windowLog;
+    U32 const windowLow = (current - windowValid > maxDistance) ? current - maxDistance : windowValid;
+
 
     DEBUGLOG(8, "ZSTD_insertDUBT1(%u) (dictLimit=%u, lowLimit=%u)",
                 current, dictLimit, windowLow);
@@ -239,7 +242,7 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms,
 
     const BYTE* const base = ms->window.base;
     U32    const current = (U32)(ip-base);
-    U32    const windowLow = ms->window.lowLimit;
+    U32    const windowLow = ZSTD_getLowestMatchIndex(ms, current, cParams->windowLog);
 
     U32*   const bt = ms->chainTable;
     U32    const btLog  = cParams->chainLog - 1;
@@ -490,8 +493,12 @@ size_t ZSTD_HcFindBestMatch_generic (
     const U32 dictLimit = ms->window.dictLimit;
     const BYTE* const prefixStart = base + dictLimit;
     const BYTE* const dictEnd = dictBase + dictLimit;
-    const U32 lowLimit = ms->window.lowLimit;
     const U32 current = (U32)(ip-base);
+    const U32 maxDistance = 1U << cParams->windowLog;
+    const U32 lowestValid = ms->window.lowLimit;
+    const U32 withinMaxDistance = (current - lowestValid > maxDistance) ? current - maxDistance : lowestValid;
+    const U32 isDictionary = (ms->loadedDictEnd != 0);
+    const U32 lowLimit = isDictionary ? lowestValid : withinMaxDistance;
     const U32 minChain = current > chainSize ? current - chainSize : 0;
     U32 nbAttempts = 1U << cParams->searchLog;
     size_t ml=4-1;
@@ -612,12 +619,14 @@ FORCE_INLINE_TEMPLATE size_t ZSTD_HcFindBestMatch_extDict_selectMLS (
 /* *******************************
 *  Common parser - lazy strategy
 *********************************/
-FORCE_INLINE_TEMPLATE
-size_t ZSTD_compressBlock_lazy_generic(
+typedef enum { search_hashChain, search_binaryTree } searchMethod_e;
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_compressBlock_lazy_generic(
                         ZSTD_matchState_t* ms, seqStore_t* seqStore,
                         U32 rep[ZSTD_REP_NUM],
                         const void* src, size_t srcSize,
-                        const U32 searchMethod, const U32 depth,
+                        const searchMethod_e searchMethod, const U32 depth,
                         ZSTD_dictMode_e const dictMode)
 {
     const BYTE* const istart = (const BYTE*)src;
@@ -633,8 +642,10 @@ size_t ZSTD_compressBlock_lazy_generic(
                         ZSTD_matchState_t* ms,
                         const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr);
     searchMax_f const searchMax = dictMode == ZSTD_dictMatchState ?
-        (searchMethod ? ZSTD_BtFindBestMatch_dictMatchState_selectMLS : ZSTD_HcFindBestMatch_dictMatchState_selectMLS) :
-        (searchMethod ? ZSTD_BtFindBestMatch_selectMLS : ZSTD_HcFindBestMatch_selectMLS);
+        (searchMethod==search_binaryTree ? ZSTD_BtFindBestMatch_dictMatchState_selectMLS
+                                         : ZSTD_HcFindBestMatch_dictMatchState_selectMLS) :
+        (searchMethod==search_binaryTree ? ZSTD_BtFindBestMatch_selectMLS
+                                         : ZSTD_HcFindBestMatch_selectMLS);
     U32 offset_1 = rep[0], offset_2 = rep[1], savedOffset=0;
 
     const ZSTD_matchState_t* const dms = ms->dictMatchState;
@@ -649,13 +660,16 @@ size_t ZSTD_compressBlock_lazy_generic(
     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 - dictLowest));
+
+    DEBUGLOG(5, "ZSTD_compressBlock_lazy_generic (dictMode=%u)", (U32)dictMode);
 
     /* init */
     ip += (dictAndPrefixLength == 0);
-    ms->nextToUpdate3 = ms->nextToUpdate;
     if (dictMode == ZSTD_noDict) {
-        U32 const maxRep = (U32)(ip - prefixLowest);
+        U32 const current = (U32)(ip - base);
+        U32 const windowLow = ZSTD_getLowestPrefixIndex(ms, current, ms->cParams.windowLog);
+        U32 const maxRep = current - windowLow;
         if (offset_2 > maxRep) savedOffset = offset_2, offset_2 = 0;
         if (offset_1 > maxRep) savedOffset = offset_1, offset_1 = 0;
     }
@@ -667,6 +681,12 @@ size_t ZSTD_compressBlock_lazy_generic(
     }
 
     /* Match Loop */
+#if defined(__GNUC__) && defined(__x86_64__)
+    /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the
+     * code alignment is perturbed. To fix the instability align the loop on 32-bytes.
+     */
+    __asm__(".p2align 5");
+#endif
     while (ip < ilimit) {
         size_t matchLength=0;
         size_t offset=0;
@@ -800,7 +820,7 @@ size_t ZSTD_compressBlock_lazy_generic(
         /* store sequence */
 _storeSequence:
         {   size_t const litLength = start - anchor;
-            ZSTD_storeSeq(seqStore, litLength, anchor, (U32)offset, matchLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offset, matchLength-MINMATCH);
             anchor = ip = start + matchLength;
         }
 
@@ -818,7 +838,7 @@ _storeSequence:
                     const BYTE* const repEnd2 = repIndex < prefixLowestIndex ? dictEnd : iend;
                     matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd2, prefixLowest) + 4;
                     offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset;   /* swap offset_2 <=> offset_1 */
-                    ZSTD_storeSeq(seqStore, 0, anchor, 0, matchLength-MINMATCH);
+                    ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH);
                     ip += matchLength;
                     anchor = ip;
                     continue;
@@ -833,7 +853,7 @@ _storeSequence:
                 /* store sequence */
                 matchLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
                 offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset; /* swap repcodes */
-                ZSTD_storeSeq(seqStore, 0, anchor, 0, matchLength-MINMATCH);
+                ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH);
                 ip += matchLength;
                 anchor = ip;
                 continue;   /* faster when present ... (?) */
@@ -844,7 +864,7 @@ _storeSequence:
     rep[1] = offset_2 ? offset_2 : savedOffset;
 
     /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }
 
 
@@ -852,56 +872,56 @@ size_t ZSTD_compressBlock_btlazy2(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 1, 2, ZSTD_noDict);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_noDict);
 }
 
 size_t ZSTD_compressBlock_lazy2(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 0, 2, ZSTD_noDict);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_noDict);
 }
 
 size_t ZSTD_compressBlock_lazy(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 0, 1, ZSTD_noDict);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_noDict);
 }
 
 size_t ZSTD_compressBlock_greedy(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 0, 0, ZSTD_noDict);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_noDict);
 }
 
 size_t ZSTD_compressBlock_btlazy2_dictMatchState(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 1, 2, ZSTD_dictMatchState);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2, ZSTD_dictMatchState);
 }
 
 size_t ZSTD_compressBlock_lazy2_dictMatchState(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 0, 2, ZSTD_dictMatchState);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2, ZSTD_dictMatchState);
 }
 
 size_t ZSTD_compressBlock_lazy_dictMatchState(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 0, 1, ZSTD_dictMatchState);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1, ZSTD_dictMatchState);
 }
 
 size_t ZSTD_compressBlock_greedy_dictMatchState(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, 0, 0, ZSTD_dictMatchState);
+    return ZSTD_compressBlock_lazy_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0, ZSTD_dictMatchState);
 }
 
 
@@ -910,7 +930,7 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
                         ZSTD_matchState_t* ms, seqStore_t* seqStore,
                         U32 rep[ZSTD_REP_NUM],
                         const void* src, size_t srcSize,
-                        const U32 searchMethod, const U32 depth)
+                        const searchMethod_e searchMethod, const U32 depth)
 {
     const BYTE* const istart = (const BYTE*)src;
     const BYTE* ip = istart;
@@ -919,24 +939,31 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
     const BYTE* const ilimit = iend - 8;
     const BYTE* const base = ms->window.base;
     const U32 dictLimit = ms->window.dictLimit;
-    const U32 lowestIndex = ms->window.lowLimit;
     const BYTE* const prefixStart = base + dictLimit;
     const BYTE* const dictBase = ms->window.dictBase;
     const BYTE* const dictEnd  = dictBase + dictLimit;
-    const BYTE* const dictStart  = dictBase + lowestIndex;
+    const BYTE* const dictStart  = dictBase + ms->window.lowLimit;
+    const U32 windowLog = ms->cParams.windowLog;
 
     typedef size_t (*searchMax_f)(
                         ZSTD_matchState_t* ms,
                         const BYTE* ip, const BYTE* iLimit, size_t* offsetPtr);
-    searchMax_f searchMax = searchMethod ? ZSTD_BtFindBestMatch_extDict_selectMLS : ZSTD_HcFindBestMatch_extDict_selectMLS;
+    searchMax_f searchMax = searchMethod==search_binaryTree ? ZSTD_BtFindBestMatch_extDict_selectMLS : ZSTD_HcFindBestMatch_extDict_selectMLS;
 
     U32 offset_1 = rep[0], offset_2 = rep[1];
 
+    DEBUGLOG(5, "ZSTD_compressBlock_lazy_extDict_generic");
+
     /* init */
-    ms->nextToUpdate3 = ms->nextToUpdate;
     ip += (ip == prefixStart);
 
     /* Match Loop */
+#if defined(__GNUC__) && defined(__x86_64__)
+    /* I've measured random a 5% speed loss on levels 5 & 6 (greedy) when the
+     * code alignment is perturbed. To fix the instability align the loop on 32-bytes.
+     */
+    __asm__(".p2align 5");
+#endif
     while (ip < ilimit) {
         size_t matchLength=0;
         size_t offset=0;
@@ -944,10 +971,11 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
         U32 current = (U32)(ip-base);
 
         /* check repCode */
-        {   const U32 repIndex = (U32)(current+1 - offset_1);
+        {   const U32 windowLow = ZSTD_getLowestMatchIndex(ms, current+1, windowLog);
+            const U32 repIndex = (U32)(current+1 - offset_1);
             const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
             const BYTE* const repMatch = repBase + repIndex;
-            if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex))   /* intentional overflow */
+            if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))   /* intentional overflow */
             if (MEM_read32(ip+1) == MEM_read32(repMatch)) {
                 /* repcode detected we should take it */
                 const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
@@ -974,10 +1002,11 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
             current++;
             /* check repCode */
             if (offset) {
+                const U32 windowLow = ZSTD_getLowestMatchIndex(ms, current, windowLog);
                 const U32 repIndex = (U32)(current - offset_1);
                 const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
                 const BYTE* const repMatch = repBase + repIndex;
-                if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex))  /* intentional overflow */
+                if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))  /* intentional overflow */
                 if (MEM_read32(ip) == MEM_read32(repMatch)) {
                     /* repcode detected */
                     const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
@@ -1004,10 +1033,11 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
                 current++;
                 /* check repCode */
                 if (offset) {
+                    const U32 windowLow = ZSTD_getLowestMatchIndex(ms, current, windowLog);
                     const U32 repIndex = (U32)(current - offset_1);
                     const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
                     const BYTE* const repMatch = repBase + repIndex;
-                    if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex))  /* intentional overflow */
+                    if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))  /* intentional overflow */
                     if (MEM_read32(ip) == MEM_read32(repMatch)) {
                         /* repcode detected */
                         const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
@@ -1042,22 +1072,24 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
         /* store sequence */
 _storeSequence:
         {   size_t const litLength = start - anchor;
-            ZSTD_storeSeq(seqStore, litLength, anchor, (U32)offset, matchLength-MINMATCH);
+            ZSTD_storeSeq(seqStore, litLength, anchor, iend, (U32)offset, matchLength-MINMATCH);
             anchor = ip = start + matchLength;
         }
 
         /* check immediate repcode */
         while (ip <= ilimit) {
-            const U32 repIndex = (U32)((ip-base) - offset_2);
+            const U32 repCurrent = (U32)(ip-base);
+            const U32 windowLow = ZSTD_getLowestMatchIndex(ms, repCurrent, windowLog);
+            const U32 repIndex = repCurrent - offset_2;
             const BYTE* const repBase = repIndex < dictLimit ? dictBase : base;
             const BYTE* const repMatch = repBase + repIndex;
-            if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > lowestIndex))  /* intentional overflow */
+            if (((U32)((dictLimit-1) - repIndex) >= 3) & (repIndex > windowLow))  /* intentional overflow */
             if (MEM_read32(ip) == MEM_read32(repMatch)) {
                 /* repcode detected we should take it */
                 const BYTE* const repEnd = repIndex < dictLimit ? dictEnd : iend;
                 matchLength = ZSTD_count_2segments(ip+4, repMatch+4, iend, repEnd, prefixStart) + 4;
                 offset = offset_2; offset_2 = offset_1; offset_1 = (U32)offset;   /* swap offset history */
-                ZSTD_storeSeq(seqStore, 0, anchor, 0, matchLength-MINMATCH);
+                ZSTD_storeSeq(seqStore, 0, anchor, iend, 0, matchLength-MINMATCH);
                 ip += matchLength;
                 anchor = ip;
                 continue;   /* faster when present ... (?) */
@@ -1070,7 +1102,7 @@ _storeSequence:
     rep[1] = offset_2;
 
     /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }
 
 
@@ -1078,7 +1110,7 @@ size_t ZSTD_compressBlock_greedy_extDict(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
 {
-    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, 0, 0);
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 0);
 }
 
 size_t ZSTD_compressBlock_lazy_extDict(
@@ -1086,7 +1118,7 @@ size_t ZSTD_compressBlock_lazy_extDict(
         void const* src, size_t srcSize)
 
 {
-    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, 0, 1);
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 1);
 }
 
 size_t ZSTD_compressBlock_lazy2_extDict(
@@ -1094,7 +1126,7 @@ size_t ZSTD_compressBlock_lazy2_extDict(
         void const* src, size_t srcSize)
 
 {
-    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, 0, 2);
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_hashChain, 2);
 }
 
 size_t ZSTD_compressBlock_btlazy2_extDict(
@@ -1102,5 +1134,5 @@ size_t ZSTD_compressBlock_btlazy2_extDict(
         void const* src, size_t srcSize)
 
 {
-    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, 1, 2);
+    return ZSTD_compressBlock_lazy_extDict_generic(ms, seqStore, rep, src, srcSize, search_binaryTree, 2);
 }

data/ext/zstdruby/libzstd/compress/zstd_lazy.h

@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
@@ -19,7 +19,7 @@ extern "C" {
 
 U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip);
 
-void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). pre-emptively increase value of ZSTD_DUBT_UNSORTED_MARK */
+void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */
 
 size_t ZSTD_compressBlock_btlazy2(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],

data/ext/zstdruby/libzstd/compress/zstd_ldm.c

@@ -1,15 +1,16 @@
 /*
- * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * Copyright (c) 2016-2020, Yann Collet, Facebook, Inc.
  * All rights reserved.
  *
  * This source code is licensed under both the BSD-style license (found in the
  * LICENSE file in the root directory of this source tree) and the GPLv2 (found
  * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
  */
 
 #include "zstd_ldm.h"
 
-#include "debug.h"
+#include "../common/debug.h"
 #include "zstd_fast.h"          /* ZSTD_fillHashTable() */
 #include "zstd_double_fast.h"   /* ZSTD_fillDoubleHashTable() */
 
@@ -49,9 +50,9 @@ size_t ZSTD_ldm_getTableSize(ldmParams_t params)
 {
     size_t const ldmHSize = ((size_t)1) << params.hashLog;
     size_t const ldmBucketSizeLog = MIN(params.bucketSizeLog, params.hashLog);
-    size_t const ldmBucketSize =
-        ((size_t)1) << (params.hashLog - ldmBucketSizeLog);
-    size_t const totalSize = ldmBucketSize + ldmHSize * sizeof(ldmEntry_t);
+    size_t const ldmBucketSize = ((size_t)1) << (params.hashLog - ldmBucketSizeLog);
+    size_t const totalSize = ZSTD_cwksp_alloc_size(ldmBucketSize)
+                           + ZSTD_cwksp_alloc_size(ldmHSize * sizeof(ldmEntry_t));
     return params.enableLdm ? totalSize : 0;
 }
 
@@ -223,6 +224,20 @@ static U64 ZSTD_ldm_fillLdmHashTable(ldmState_t* state,
     return rollingHash;
 }
 
+void ZSTD_ldm_fillHashTable(
+            ldmState_t* state, const BYTE* ip,
+            const BYTE* iend, ldmParams_t const* params)
+{
+    DEBUGLOG(5, "ZSTD_ldm_fillHashTable");
+    if ((size_t)(iend - ip) >= params->minMatchLength) {
+        U64 startingHash = ZSTD_rollingHash_compute(ip, params->minMatchLength);
+        ZSTD_ldm_fillLdmHashTable(
+            state, startingHash, ip, iend - params->minMatchLength, state->window.base,
+            params->hashLog - params->bucketSizeLog,
+            *params);
+    }
+}
+
 
 /** ZSTD_ldm_limitTableUpdate() :
  *
@@ -429,7 +444,7 @@ size_t ZSTD_ldm_generateSequences(
      */
     assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize);
     /* The input could be very large (in zstdmt), so it must be broken up into
-     * chunks to enforce the maximmum distance and handle overflow correction.
+     * chunks to enforce the maximum distance and handle overflow correction.
      */
     assert(sequences->pos <= sequences->size);
     assert(sequences->size <= sequences->capacity);
@@ -447,8 +462,10 @@ 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);
+            /* invalidate dictionaries on overflow correction */
+            ldmState->loadedDictEnd = 0;
         }
         /* 2. We enforce the maximum offset allowed.
          *
@@ -457,8 +474,14 @@ size_t ZSTD_ldm_generateSequences(
          * TODO: * Test the chunk size.
          *       * Try invalidation after the sequence generation and test the
          *         the offset against maxDist directly.
+         *
+         * NOTE: Because of dictionaries + sequence splitting we MUST make sure
+         * that any offset used is valid at the END of the sequence, since it may
+         * be split into two sequences. This condition holds when using
+         * ZSTD_window_enforceMaxDist(), but if we move to checking offsets
+         * against maxDist directly, we'll have to carefully handle that case.
          */
-        ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, NULL, NULL);
+        ZSTD_window_enforceMaxDist(&ldmState->window, chunkEnd, maxDist, &ldmState->loadedDictEnd, NULL);
         /* 3. Generate the sequences for the chunk, and get newLeftoverSize. */
         newLeftoverSize = ZSTD_ldm_generateSequences_internal(
             ldmState, sequences, params, chunkStart, chunkSize);
@@ -566,14 +589,13 @@ size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore,
         if (sequence.offset == 0)
             break;
 
-        assert(sequence.offset <= (1U << cParams->windowLog));
         assert(ip + sequence.litLength + sequence.matchLength <= iend);
 
         /* Fill tables for block compressor */
         ZSTD_ldm_limitTableUpdate(ms, ip);
         ZSTD_ldm_fillFastTables(ms, ip);
         /* Run the block compressor */
-        DEBUGLOG(5, "calling block compressor on segment of size %u", sequence.litLength);
+        DEBUGLOG(5, "pos %u : calling block compressor on segment of size %u", (unsigned)(ip-istart), sequence.litLength);
         {
             size_t const newLitLength =
                 blockCompressor(ms, seqStore, rep, ip, sequence.litLength);
@@ -583,7 +605,7 @@ size_t ZSTD_ldm_blockCompress(rawSeqStore_t* rawSeqStore,
                 rep[i] = rep[i-1];
             rep[0] = sequence.offset;
             /* Store the sequence */
-            ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength,
+            ZSTD_storeSeq(seqStore, newLitLength, ip - newLitLength, iend,
                           sequence.offset + ZSTD_REP_MOVE,
                           sequence.matchLength - MINMATCH);
             ip += sequence.matchLength;