Update zstd to 1.4.3

18 files changed, 813 insertions, 663 deletions

diff --git a/thirdparty/zstd/common/bitstream.h b/thirdparty/zstd/common/bitstream.h
index d955bd677b..7bdb060460 100644
--- a/thirdparty/zstd/common/bitstream.h
+++ b/thirdparty/zstd/common/bitstream.h
@@ -57,6 +57,8 @@ extern "C" {
 =========================================*/
 #if defined(__BMI__) && defined(__GNUC__)
 #  include <immintrin.h>   /* support for bextr (experimental) */
+#elif defined(__ICCARM__)
+#  include <intrinsics.h>
 #endif
 
 #define STREAM_ACCUMULATOR_MIN_32  25
@@ -163,6 +165,8 @@ MEM_STATIC unsigned BIT_highbit32 (U32 val)
         return (unsigned) r;
 #   elif defined(__GNUC__) && (__GNUC__ >= 3)   /* Use GCC Intrinsic */
         return 31 - __builtin_clz (val);
+#   elif defined(__ICCARM__)    /* IAR Intrinsic */
+        return 31 - __CLZ(val);
 #   else   /* Software version */
         static const unsigned DeBruijnClz[32] = { 0,  9,  1, 10, 13, 21,  2, 29,
                                                  11, 14, 16, 18, 22, 25,  3, 30,
diff --git a/thirdparty/zstd/common/compiler.h b/thirdparty/zstd/common/compiler.h
index 87bf51ae8c..6686b837d6 100644
--- a/thirdparty/zstd/common/compiler.h
+++ b/thirdparty/zstd/common/compiler.h
@@ -23,7 +23,7 @@
 #  define INLINE_KEYWORD
 #endif
 
-#if defined(__GNUC__)
+#if defined(__GNUC__) || defined(__ICCARM__)
 #  define FORCE_INLINE_ATTR __attribute__((always_inline))
 #elif defined(_MSC_VER)
 #  define FORCE_INLINE_ATTR __forceinline
@@ -65,7 +65,7 @@
 #ifdef _MSC_VER
 #  define FORCE_NOINLINE static __declspec(noinline)
 #else
-#  ifdef __GNUC__
+#  if defined(__GNUC__) || defined(__ICCARM__)
 #    define FORCE_NOINLINE static __attribute__((__noinline__))
 #  else
 #    define FORCE_NOINLINE static
@@ -76,7 +76,7 @@
 #ifndef __has_attribute
   #define __has_attribute(x) 0  /* Compatibility with non-clang compilers. */
 #endif
-#if defined(__GNUC__)
+#if defined(__GNUC__) || defined(__ICCARM__)
 #  define TARGET_ATTRIBUTE(target) __attribute__((__target__(target)))
 #else
 #  define TARGET_ATTRIBUTE(target)
diff --git a/thirdparty/zstd/common/mem.h b/thirdparty/zstd/common/mem.h
index 5da248756f..c10d7f61e1 100644
--- a/thirdparty/zstd/common/mem.h
+++ b/thirdparty/zstd/common/mem.h
@@ -102,7 +102,7 @@ MEM_STATIC void MEM_check(void) { MEM_STATIC_ASSERT((sizeof(size_t)==4) || (size
 #ifndef MEM_FORCE_MEMORY_ACCESS   /* can be defined externally, on command line for example */
 #  if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
 #    define MEM_FORCE_MEMORY_ACCESS 2
-#  elif defined(__INTEL_COMPILER) || defined(__GNUC__)
+#  elif defined(__INTEL_COMPILER) || defined(__GNUC__) || defined(__ICCARM__)
 #    define MEM_FORCE_MEMORY_ACCESS 1
 #  endif
 #endif
diff --git a/thirdparty/zstd/common/xxhash.c b/thirdparty/zstd/common/xxhash.c
index 30599aaae4..99d2459621 100644
--- a/thirdparty/zstd/common/xxhash.c
+++ b/thirdparty/zstd/common/xxhash.c
@@ -53,7 +53,8 @@
 #  if defined(__GNUC__) && ( defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) || defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__) )
 #    define XXH_FORCE_MEMORY_ACCESS 2
 #  elif (defined(__INTEL_COMPILER) && !defined(WIN32)) || \
-  (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) ))
+  (defined(__GNUC__) && ( defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) || defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || defined(__ARM_ARCH_7S__) )) || \
+  defined(__ICCARM__)
 #    define XXH_FORCE_MEMORY_ACCESS 1
 #  endif
 #endif
@@ -120,7 +121,7 @@ static void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcp
 #  define INLINE_KEYWORD
 #endif
 
-#if defined(__GNUC__)
+#if defined(__GNUC__) || defined(__ICCARM__)
 #  define FORCE_INLINE_ATTR __attribute__((always_inline))
 #elif defined(_MSC_VER)
 #  define FORCE_INLINE_ATTR __forceinline
@@ -206,7 +207,12 @@ static U64 XXH_read64(const void* memPtr)
 #  define XXH_rotl32(x,r) _rotl(x,r)
 #  define XXH_rotl64(x,r) _rotl64(x,r)
 #else
+#if defined(__ICCARM__)
+#  include <intrinsics.h>
+#  define XXH_rotl32(x,r) __ROR(x,(32 - r))
+#else
 #  define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
+#endif
 #  define XXH_rotl64(x,r) ((x << r) | (x >> (64 - r)))
 #endif
 
diff --git a/thirdparty/zstd/common/zstd_internal.h b/thirdparty/zstd/common/zstd_internal.h
index 81b16eac2e..585fd6b19e 100644
--- a/thirdparty/zstd/common/zstd_internal.h
+++ b/thirdparty/zstd/common/zstd_internal.h
@@ -56,9 +56,9 @@ extern "C" {
 /**
  * Return the specified error if the condition evaluates to true.
  *
- * In debug modes, prints additional information. In order to do that
- * (particularly, printing the conditional that failed), this can't just wrap
- * RETURN_ERROR().
+ * In debug modes, prints additional information.
+ * In order to do that (particularly, printing the conditional that failed),
+ * this can't just wrap RETURN_ERROR().
  */
 #define RETURN_ERROR_IF(cond, err, ...) \
   if (cond) { \
@@ -324,6 +324,8 @@ MEM_STATIC U32 ZSTD_highbit32(U32 val)   /* compress, dictBuilder, decodeCorpus
         return (unsigned)r;
 #   elif defined(__GNUC__) && (__GNUC__ >= 3)   /* GCC Intrinsic */
         return 31 - __builtin_clz(val);
+#   elif defined(__ICCARM__)    /* IAR Intrinsic */
+        return 31 - __CLZ(val);
 #   else   /* Software version */
         static const U32 DeBruijnClz[32] = { 0, 9, 1, 10, 13, 21, 2, 29, 11, 14, 16, 18, 22, 25, 3, 30, 8, 12, 20, 28, 15, 17, 24, 7, 19, 27, 23, 6, 26, 5, 4, 31 };
         U32 v = val;
diff --git a/thirdparty/zstd/compress/zstd_compress.c b/thirdparty/zstd/compress/zstd_compress.c
index 1476512580..cd73db13be 100644
--- a/thirdparty/zstd/compress/zstd_compress.c
+++ b/thirdparty/zstd/compress/zstd_compress.c
@@ -21,6 +21,8 @@
 #define HUF_STATIC_LINKING_ONLY
 #include "huf.h"
 #include "zstd_compress_internal.h"
+#include "zstd_compress_sequences.h"
+#include "zstd_compress_literals.h"
 #include "zstd_fast.h"
 #include "zstd_double_fast.h"
 #include "zstd_lazy.h"
@@ -397,18 +399,6 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
     }
 }
 
-/* ZSTD_cParam_withinBounds:
- * @return 1 if value is within cParam bounds,
- * 0 otherwise */
-static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
-{
-    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
-    if (ZSTD_isError(bounds.error)) return 0;
-    if (value < bounds.lowerBound) return 0;
-    if (value > bounds.upperBound) return 0;
-    return 1;
-}
-
 /* ZSTD_cParam_clampBounds:
  * Clamps the value into the bounded range.
  */
@@ -1903,155 +1893,6 @@ static size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* s
     return ZSTD_blockHeaderSize + srcSize;
 }
 
-static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
-{
-    BYTE* const ostart = (BYTE* const)dst;
-    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
-
-    RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
-
-    switch(flSize)
-    {
-        case 1: /* 2 - 1 - 5 */
-            ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
-            break;
-        case 2: /* 2 - 2 - 12 */
-            MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
-            break;
-        case 3: /* 2 - 2 - 20 */
-            MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
-            break;
-        default:   /* not necessary : flSize is {1,2,3} */
-            assert(0);
-    }
-
-    memcpy(ostart + flSize, src, srcSize);
-    return srcSize + flSize;
-}
-
-static size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
-{
-    BYTE* const ostart = (BYTE* const)dst;
-    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
-
-    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
-
-    switch(flSize)
-    {
-        case 1: /* 2 - 1 - 5 */
-            ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
-            break;
-        case 2: /* 2 - 2 - 12 */
-            MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
-            break;
-        case 3: /* 2 - 2 - 20 */
-            MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
-            break;
-        default:   /* not necessary : flSize is {1,2,3} */
-            assert(0);
-    }
-
-    ostart[flSize] = *(const BYTE*)src;
-    return flSize+1;
-}
-
-
-/* ZSTD_minGain() :
- * minimum compression required
- * to generate a compress block or a compressed literals section.
- * note : use same formula for both situations */
-static size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
-{
-    U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
-    ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
-    assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
-    return (srcSize >> minlog) + 2;
-}
-
-static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
-                                     ZSTD_hufCTables_t* nextHuf,
-                                     ZSTD_strategy strategy, int disableLiteralCompression,
-                                     void* dst, size_t dstCapacity,
-                               const void* src, size_t srcSize,
-                                     void* workspace, size_t wkspSize,
-                               const int bmi2)
-{
-    size_t const minGain = ZSTD_minGain(srcSize, strategy);
-    size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
-    BYTE*  const ostart = (BYTE*)dst;
-    U32 singleStream = srcSize < 256;
-    symbolEncodingType_e hType = set_compressed;
-    size_t cLitSize;
-
-    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
-                disableLiteralCompression);
-
-    /* Prepare nextEntropy assuming reusing the existing table */
-    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-
-    if (disableLiteralCompression)
-        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-
-    /* small ? don't even attempt compression (speed opt) */
-#   define COMPRESS_LITERALS_SIZE_MIN 63
-    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
-        if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-    }
-
-    RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
-    {   HUF_repeat repeat = prevHuf->repeatMode;
-        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
-        if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
-        cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
-                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
-                                : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
-                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
-        if (repeat != HUF_repeat_none) {
-            /* reused the existing table */
-            hType = set_repeat;
-        }
-    }
-
-    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
-        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
-    }
-    if (cLitSize==1) {
-        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
-        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
-    }
-
-    if (hType == set_compressed) {
-        /* using a newly constructed table */
-        nextHuf->repeatMode = HUF_repeat_check;
-    }
-
-    /* Build header */
-    switch(lhSize)
-    {
-    case 3: /* 2 - 2 - 10 - 10 */
-        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
-            MEM_writeLE24(ostart, lhc);
-            break;
-        }
-    case 4: /* 2 - 2 - 14 - 14 */
-        {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
-            MEM_writeLE32(ostart, lhc);
-            break;
-        }
-    case 5: /* 2 - 2 - 18 - 18 */
-        {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
-            MEM_writeLE32(ostart, lhc);
-            ostart[4] = (BYTE)(cLitSize >> 10);
-            break;
-        }
-    default:  /* not possible : lhSize is {3,4,5} */
-        assert(0);
-    }
-    return lhSize+cLitSize;
-}
-
-
 void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
 {
     const seqDef* const sequences = seqStorePtr->sequencesStart;
@@ -2074,418 +1915,6 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
         mlCodeTable[seqStorePtr->longLengthPos] = MaxML;
 }
 
-
-/**
- * -log2(x / 256) lookup table for x in [0, 256).
- * If x == 0: Return 0
- * Else: Return floor(-log2(x / 256) * 256)
- */
-static unsigned const kInverseProbabilityLog256[256] = {
-    0,    2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
-    1130, 1100, 1073, 1047, 1024, 1001, 980,  960,  941,  923,  906,  889,
-    874,  859,  844,  830,  817,  804,  791,  779,  768,  756,  745,  734,
-    724,  714,  704,  694,  685,  676,  667,  658,  650,  642,  633,  626,
-    618,  610,  603,  595,  588,  581,  574,  567,  561,  554,  548,  542,
-    535,  529,  523,  517,  512,  506,  500,  495,  489,  484,  478,  473,
-    468,  463,  458,  453,  448,  443,  438,  434,  429,  424,  420,  415,
-    411,  407,  402,  398,  394,  390,  386,  382,  377,  373,  370,  366,
-    362,  358,  354,  350,  347,  343,  339,  336,  332,  329,  325,  322,
-    318,  315,  311,  308,  305,  302,  298,  295,  292,  289,  286,  282,
-    279,  276,  273,  270,  267,  264,  261,  258,  256,  253,  250,  247,
-    244,  241,  239,  236,  233,  230,  228,  225,  222,  220,  217,  215,
-    212,  209,  207,  204,  202,  199,  197,  194,  192,  190,  187,  185,
-    182,  180,  178,  175,  173,  171,  168,  166,  164,  162,  159,  157,
-    155,  153,  151,  149,  146,  144,  142,  140,  138,  136,  134,  132,
-    130,  128,  126,  123,  121,  119,  117,  115,  114,  112,  110,  108,
-    106,  104,  102,  100,  98,   96,   94,   93,   91,   89,   87,   85,
-    83,   82,   80,   78,   76,   74,   73,   71,   69,   67,   66,   64,
-    62,   61,   59,   57,   55,   54,   52,   50,   49,   47,   46,   44,
-    42,   41,   39,   37,   36,   34,   33,   31,   30,   28,   26,   25,
-    23,   22,   20,   19,   17,   16,   14,   13,   11,   10,   8,    7,
-    5,    4,    2,    1,
-};
-
-
-/**
- * Returns the cost in bits of encoding the distribution described by count
- * using the entropy bound.
- */
-static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
-{
-    unsigned cost = 0;
-    unsigned s;
-    for (s = 0; s <= max; ++s) {
-        unsigned norm = (unsigned)((256 * count[s]) / total);
-        if (count[s] != 0 && norm == 0)
-            norm = 1;
-        assert(count[s] < total);
-        cost += count[s] * kInverseProbabilityLog256[norm];
-    }
-    return cost >> 8;
-}
-
-
-/**
- * Returns the cost in bits of encoding the distribution in count using the
- * table described by norm. The max symbol support by norm is assumed >= max.
- * norm must be valid for every symbol with non-zero probability in count.
- */
-static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
-                                    unsigned const* count, unsigned const max)
-{
-    unsigned const shift = 8 - accuracyLog;
-    size_t cost = 0;
-    unsigned s;
-    assert(accuracyLog <= 8);
-    for (s = 0; s <= max; ++s) {
-        unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
-        unsigned const norm256 = normAcc << shift;
-        assert(norm256 > 0);
-        assert(norm256 < 256);
-        cost += count[s] * kInverseProbabilityLog256[norm256];
-    }
-    return cost >> 8;
-}
-
-
-static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
-  void const* ptr = ctable;
-  U16 const* u16ptr = (U16 const*)ptr;
-  U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
-  return maxSymbolValue;
-}
-
-
-/**
- * Returns the cost in bits of encoding the distribution in count using ctable.
- * Returns an error if ctable cannot represent all the symbols in count.
- */
-static size_t ZSTD_fseBitCost(
-    FSE_CTable const* ctable,
-    unsigned const* count,
-    unsigned const max)
-{
-    unsigned const kAccuracyLog = 8;
-    size_t cost = 0;
-    unsigned s;
-    FSE_CState_t cstate;
-    FSE_initCState(&cstate, ctable);
-    RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
-                    "Repeat FSE_CTable has maxSymbolValue %u < %u",
-                    ZSTD_getFSEMaxSymbolValue(ctable), max);
-    for (s = 0; s <= max; ++s) {
-        unsigned const tableLog = cstate.stateLog;
-        unsigned const badCost = (tableLog + 1) << kAccuracyLog;
-        unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
-        if (count[s] == 0)
-            continue;
-        RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
-                        "Repeat FSE_CTable has Prob[%u] == 0", s);
-        cost += count[s] * bitCost;
-    }
-    return cost >> kAccuracyLog;
-}
-
-/**
- * Returns the cost in bytes of encoding the normalized count header.
- * Returns an error if any of the helper functions return an error.
- */
-static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
-                              size_t const nbSeq, unsigned const FSELog)
-{
-    BYTE wksp[FSE_NCOUNTBOUND];
-    S16 norm[MaxSeq + 1];
-    const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
-    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
-    return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
-}
-
-
-typedef enum {
-    ZSTD_defaultDisallowed = 0,
-    ZSTD_defaultAllowed = 1
-} ZSTD_defaultPolicy_e;
-
-MEM_STATIC symbolEncodingType_e
-ZSTD_selectEncodingType(
-        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
-        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
-        FSE_CTable const* prevCTable,
-        short const* defaultNorm, U32 defaultNormLog,
-        ZSTD_defaultPolicy_e const isDefaultAllowed,
-        ZSTD_strategy const strategy)
-{
-    ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
-    if (mostFrequent == nbSeq) {
-        *repeatMode = FSE_repeat_none;
-        if (isDefaultAllowed && nbSeq <= 2) {
-            /* Prefer set_basic over set_rle when there are 2 or less symbols,
-             * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
-             * If basic encoding isn't possible, always choose RLE.
-             */
-            DEBUGLOG(5, "Selected set_basic");
-            return set_basic;
-        }
-        DEBUGLOG(5, "Selected set_rle");
-        return set_rle;
-    }
-    if (strategy < ZSTD_lazy) {
-        if (isDefaultAllowed) {
-            size_t const staticFse_nbSeq_max = 1000;
-            size_t const mult = 10 - strategy;
-            size_t const baseLog = 3;
-            size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog;  /* 28-36 for offset, 56-72 for lengths */
-            assert(defaultNormLog >= 5 && defaultNormLog <= 6);  /* xx_DEFAULTNORMLOG */
-            assert(mult <= 9 && mult >= 7);
-            if ( (*repeatMode == FSE_repeat_valid)
-              && (nbSeq < staticFse_nbSeq_max) ) {
-                DEBUGLOG(5, "Selected set_repeat");
-                return set_repeat;
-            }
-            if ( (nbSeq < dynamicFse_nbSeq_min)
-              || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
-                DEBUGLOG(5, "Selected set_basic");
-                /* The format allows default tables to be repeated, but it isn't useful.
-                 * When using simple heuristics to select encoding type, we don't want
-                 * to confuse these tables with dictionaries. When running more careful
-                 * analysis, we don't need to waste time checking both repeating tables
-                 * and default tables.
-                 */
-                *repeatMode = FSE_repeat_none;
-                return set_basic;
-            }
-        }
-    } else {
-        size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
-        size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
-        size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
-        size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
-
-        if (isDefaultAllowed) {
-            assert(!ZSTD_isError(basicCost));
-            assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
-        }
-        assert(!ZSTD_isError(NCountCost));
-        assert(compressedCost < ERROR(maxCode));
-        DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
-                    (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
-        if (basicCost <= repeatCost && basicCost <= compressedCost) {
-            DEBUGLOG(5, "Selected set_basic");
-            assert(isDefaultAllowed);
-            *repeatMode = FSE_repeat_none;
-            return set_basic;
-        }
-        if (repeatCost <= compressedCost) {
-            DEBUGLOG(5, "Selected set_repeat");
-            assert(!ZSTD_isError(repeatCost));
-            return set_repeat;
-        }
-        assert(compressedCost < basicCost && compressedCost < repeatCost);
-    }
-    DEBUGLOG(5, "Selected set_compressed");
-    *repeatMode = FSE_repeat_check;
-    return set_compressed;
-}
-
-MEM_STATIC size_t
-ZSTD_buildCTable(void* dst, size_t dstCapacity,
-                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
-                unsigned* count, U32 max,
-                const BYTE* codeTable, size_t nbSeq,
-                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
-                const FSE_CTable* prevCTable, size_t prevCTableSize,
-                void* workspace, size_t workspaceSize)
-{
-    BYTE* op = (BYTE*)dst;
-    const BYTE* const oend = op + dstCapacity;
-    DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
-
-    switch (type) {
-    case set_rle:
-        FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
-        RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
-        *op = codeTable[0];
-        return 1;
-    case set_repeat:
-        memcpy(nextCTable, prevCTable, prevCTableSize);
-        return 0;
-    case set_basic:
-        FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize));  /* note : could be pre-calculated */
-        return 0;
-    case set_compressed: {
-        S16 norm[MaxSeq + 1];
-        size_t nbSeq_1 = nbSeq;
-        const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
-        if (count[codeTable[nbSeq-1]] > 1) {
-            count[codeTable[nbSeq-1]]--;
-            nbSeq_1--;
-        }
-        assert(nbSeq_1 > 1);
-        FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
-        {   size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog);   /* overflow protected */
-            FORWARD_IF_ERROR(NCountSize);
-            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
-            return NCountSize;
-        }
-    }
-    default: assert(0); RETURN_ERROR(GENERIC);
-    }
-}
-
-FORCE_INLINE_TEMPLATE size_t
-ZSTD_encodeSequences_body(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
-{
-    BIT_CStream_t blockStream;
-    FSE_CState_t  stateMatchLength;
-    FSE_CState_t  stateOffsetBits;
-    FSE_CState_t  stateLitLength;
-
-    RETURN_ERROR_IF(
-        ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
-        dstSize_tooSmall, "not enough space remaining");
-    DEBUGLOG(6, "available space for bitstream : %i  (dstCapacity=%u)",
-                (int)(blockStream.endPtr - blockStream.startPtr),
-                (unsigned)dstCapacity);
-
-    /* first symbols */
-    FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
-    FSE_initCState2(&stateOffsetBits,  CTable_OffsetBits,  ofCodeTable[nbSeq-1]);
-    FSE_initCState2(&stateLitLength,   CTable_LitLength,   llCodeTable[nbSeq-1]);
-    BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
-    if (MEM_32bits()) BIT_flushBits(&blockStream);
-    BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
-    if (MEM_32bits()) BIT_flushBits(&blockStream);
-    if (longOffsets) {
-        U32 const ofBits = ofCodeTable[nbSeq-1];
-        int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
-        if (extraBits) {
-            BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
-            BIT_flushBits(&blockStream);
-        }
-        BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
-                    ofBits - extraBits);
-    } else {
-        BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
-    }
-    BIT_flushBits(&blockStream);
-
-    {   size_t n;
-        for (n=nbSeq-2 ; n<nbSeq ; n--) {      /* intentional underflow */
-            BYTE const llCode = llCodeTable[n];
-            BYTE const ofCode = ofCodeTable[n];
-            BYTE const mlCode = mlCodeTable[n];
-            U32  const llBits = LL_bits[llCode];
-            U32  const ofBits = ofCode;
-            U32  const mlBits = ML_bits[mlCode];
-            DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
-                        (unsigned)sequences[n].litLength,
-                        (unsigned)sequences[n].matchLength + MINMATCH,
-                        (unsigned)sequences[n].offset);
-                                                                            /* 32b*/  /* 64b*/
-                                                                            /* (7)*/  /* (7)*/
-            FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode);       /* 15 */  /* 15 */
-            FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode);      /* 24 */  /* 24 */
-            if (MEM_32bits()) BIT_flushBits(&blockStream);                  /* (7)*/
-            FSE_encodeSymbol(&blockStream, &stateLitLength, llCode);        /* 16 */  /* 33 */
-            if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
-                BIT_flushBits(&blockStream);                                /* (7)*/
-            BIT_addBits(&blockStream, sequences[n].litLength, llBits);
-            if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
-            BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
-            if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
-            if (longOffsets) {
-                int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
-                if (extraBits) {
-                    BIT_addBits(&blockStream, sequences[n].offset, extraBits);
-                    BIT_flushBits(&blockStream);                            /* (7)*/
-                }
-                BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
-                            ofBits - extraBits);                            /* 31 */
-            } else {
-                BIT_addBits(&blockStream, sequences[n].offset, ofBits);     /* 31 */
-            }
-            BIT_flushBits(&blockStream);                                    /* (7)*/
-            DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
-    }   }
-
-    DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
-    FSE_flushCState(&blockStream, &stateMatchLength);
-    DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
-    FSE_flushCState(&blockStream, &stateOffsetBits);
-    DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
-    FSE_flushCState(&blockStream, &stateLitLength);
-
-    {   size_t const streamSize = BIT_closeCStream(&blockStream);
-        RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
-        return streamSize;
-    }
-}
-
-static size_t
-ZSTD_encodeSequences_default(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
-{
-    return ZSTD_encodeSequences_body(dst, dstCapacity,
-                                    CTable_MatchLength, mlCodeTable,
-                                    CTable_OffsetBits, ofCodeTable,
-                                    CTable_LitLength, llCodeTable,
-                                    sequences, nbSeq, longOffsets);
-}
-
-
-#if DYNAMIC_BMI2
-
-static TARGET_ATTRIBUTE("bmi2") size_t
-ZSTD_encodeSequences_bmi2(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets)
-{
-    return ZSTD_encodeSequences_body(dst, dstCapacity,
-                                    CTable_MatchLength, mlCodeTable,
-                                    CTable_OffsetBits, ofCodeTable,
-                                    CTable_LitLength, llCodeTable,
-                                    sequences, nbSeq, longOffsets);
-}
-
-#endif
-
-static size_t ZSTD_encodeSequences(
-            void* dst, size_t dstCapacity,
-            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
-            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
-            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
-            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
-{
-    DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
-#if DYNAMIC_BMI2
-    if (bmi2) {
-        return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
-                                         CTable_MatchLength, mlCodeTable,
-                                         CTable_OffsetBits, ofCodeTable,
-                                         CTable_LitLength, llCodeTable,
-                                         sequences, nbSeq, longOffsets);
-    }
-#endif
-    (void)bmi2;
-    return ZSTD_encodeSequences_default(dst, dstCapacity,
-                                        CTable_MatchLength, mlCodeTable,
-                                        CTable_OffsetBits, ofCodeTable,
-                                        CTable_LitLength, llCodeTable,
-                                        sequences, nbSeq, longOffsets);
-}
-
 static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams)
 {
     switch (cctxParams->literalCompressionMode) {
@@ -2526,16 +1955,16 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
     BYTE* const ostart = (BYTE*)dst;
     BYTE* const oend = ostart + dstCapacity;
     BYTE* op = ostart;
-    size_t const nbSeq = seqStorePtr->sequences - seqStorePtr->sequencesStart;
+    size_t const nbSeq = (size_t)(seqStorePtr->sequences - seqStorePtr->sequencesStart);
     BYTE* seqHead;
     BYTE* lastNCount = NULL;
 
+    DEBUGLOG(5, "ZSTD_compressSequences_internal (nbSeq=%zu)", nbSeq);
     ZSTD_STATIC_ASSERT(HUF_WORKSPACE_SIZE >= (1<<MAX(MLFSELog,LLFSELog)));
-    DEBUGLOG(5, "ZSTD_compressSequences_internal");
 
     /* Compress literals */
     {   const BYTE* const literals = seqStorePtr->litStart;
-        size_t const litSize = seqStorePtr->lit - literals;
+        size_t const litSize = (size_t)(seqStorePtr->lit - literals);
         size_t const cSize = ZSTD_compressLiterals(
                                     &prevEntropy->huf, &nextEntropy->huf,
                                     cctxParams->cParams.strategy,
@@ -2562,7 +1991,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
     if (nbSeq==0) {
         /* Copy the old tables over as if we repeated them */
         memcpy(&nextEntropy->fse, &prevEntropy->fse, sizeof(prevEntropy->fse));
-        return op - ostart;
+        return (size_t)(op - ostart);
     }
 
     /* seqHead : flags for FSE encoding type */
@@ -2583,7 +2012,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                         ZSTD_defaultAllowed, strategy);
         assert(set_basic < set_compressed && set_rle < set_compressed);
         assert(!(LLtype < set_compressed && nextEntropy->fse.litlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
-        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
+        {   size_t const countSize = ZSTD_buildCTable(op, (size_t)(oend - op), CTable_LitLength, LLFSELog, (symbolEncodingType_e)LLtype,
                                                     count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
                                                     prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable),
                                                     workspace, wkspSize);
@@ -2606,7 +2035,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                         OF_defaultNorm, OF_defaultNormLog,
                                         defaultPolicy, strategy);
         assert(!(Offtype < set_compressed && nextEntropy->fse.offcode_repeatMode != FSE_repeat_none)); /* We don't copy tables */
-        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
+        {   size_t const countSize = ZSTD_buildCTable(op, (size_t)(oend - op), CTable_OffsetBits, OffFSELog, (symbolEncodingType_e)Offtype,
                                                     count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
                                                     prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable),
                                                     workspace, wkspSize);
@@ -2627,7 +2056,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                         ML_defaultNorm, ML_defaultNormLog,
                                         ZSTD_defaultAllowed, strategy);
         assert(!(MLtype < set_compressed && nextEntropy->fse.matchlength_repeatMode != FSE_repeat_none)); /* We don't copy tables */
-        {   size_t const countSize = ZSTD_buildCTable(op, oend - op, CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
+        {   size_t const countSize = ZSTD_buildCTable(op, (size_t)(oend - op), CTable_MatchLength, MLFSELog, (symbolEncodingType_e)MLtype,
                                                     count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
                                                     prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable),
                                                     workspace, wkspSize);
@@ -2641,7 +2070,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
     *seqHead = (BYTE)((LLtype<<6) + (Offtype<<4) + (MLtype<<2));
 
     {   size_t const bitstreamSize = ZSTD_encodeSequences(
-                                        op, oend - op,
+                                        op, (size_t)(oend - op),
                                         CTable_MatchLength, mlCodeTable,
                                         CTable_OffsetBits, ofCodeTable,
                                         CTable_LitLength, llCodeTable,
@@ -2668,7 +2097,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
     }
 
     DEBUGLOG(5, "compressed block size : %u", (unsigned)(op - ostart));
-    return op - ostart;
+    return (size_t)(op - ostart);
 }
 
 MEM_STATIC size_t
@@ -2841,7 +2270,8 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
 {
     size_t cSize;
     DEBUGLOG(5, "ZSTD_compressBlock_internal (dstCapacity=%u, dictLimit=%u, nextToUpdate=%u)",
-                (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit, (unsigned)zc->blockState.matchState.nextToUpdate);
+                (unsigned)dstCapacity, (unsigned)zc->blockState.matchState.window.dictLimit,
+                (unsigned)zc->blockState.matchState.nextToUpdate);
 
     {   const size_t bss = ZSTD_buildSeqStore(zc, src, srcSize);
         FORWARD_IF_ERROR(bss);
@@ -3109,8 +2539,9 @@ size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx)
 
 size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
-    size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
-    RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong);
+    DEBUGLOG(5, "ZSTD_compressBlock: srcSize = %u", (unsigned)srcSize);
+    { size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
+      RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong); }
 
     return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */);
 }
@@ -3135,7 +2566,7 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
     if (srcSize <= HASH_READ_SIZE) return 0;
 
     while (iend - ip > HASH_READ_SIZE) {
-        size_t const remaining = iend - ip;
+        size_t const remaining = (size_t)(iend - ip);
         size_t const chunk = MIN(remaining, ZSTD_CHUNKSIZE_MAX);
         const BYTE* const ichunk = ip + chunk;
 
diff --git a/thirdparty/zstd/compress/zstd_compress_internal.h b/thirdparty/zstd/compress/zstd_compress_internal.h
index 5495899be3..6d623cc6be 100644
--- a/thirdparty/zstd/compress/zstd_compress_internal.h
+++ b/thirdparty/zstd/compress/zstd_compress_internal.h
@@ -134,9 +134,15 @@ typedef struct {
 typedef struct ZSTD_matchState_t ZSTD_matchState_t;
 struct ZSTD_matchState_t {
     ZSTD_window_t window;   /* State for window round buffer management */
-    U32 loadedDictEnd;      /* index of end of dictionary, within context's referential. When dict referential is copied into active context (i.e. not attached), effectively same value as dictSize, since referential starts from zero */
+    U32 loadedDictEnd;      /* index of end of dictionary, within context's referential.
+                             * When loadedDictEnd != 0, a dictionary is in use, and still valid.
+                             * This relies on a mechanism to set loadedDictEnd=0 when dictionary is no longer within distance.
+                             * Such mechanism is provided within ZSTD_window_enforceMaxDist() and ZSTD_checkDictValidity().
+                             * When dict referential is copied into active context (i.e. not attached),
+                             * loadedDictEnd == dictSize, since referential starts from zero.
+                             */
     U32 nextToUpdate;       /* index from which to continue table update */
-    U32 hashLog3;           /* dispatch table : larger == faster, more memory */
+    U32 hashLog3;           /* dispatch table for matches of len==3 : larger == faster, more memory */
     U32* hashTable;
     U32* hashTable3;
     U32* chainTable;
@@ -307,6 +313,30 @@ MEM_STATIC U32 ZSTD_MLcode(U32 mlBase)
     return (mlBase > 127) ? ZSTD_highbit32(mlBase) + ML_deltaCode : ML_Code[mlBase];
 }
 
+/* ZSTD_cParam_withinBounds:
+ * @return 1 if value is within cParam bounds,
+ * 0 otherwise */
+MEM_STATIC int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
+{
+    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
+    if (ZSTD_isError(bounds.error)) return 0;
+    if (value < bounds.lowerBound) return 0;
+    if (value > bounds.upperBound) return 0;
+    return 1;
+}
+
+/* ZSTD_minGain() :
+ * minimum compression required
+ * to generate a compress block or a compressed literals section.
+ * note : use same formula for both situations */
+MEM_STATIC size_t ZSTD_minGain(size_t srcSize, ZSTD_strategy strat)
+{
+    U32 const minlog = (strat>=ZSTD_btultra) ? (U32)(strat) - 1 : 6;
+    ZSTD_STATIC_ASSERT(ZSTD_btultra == 8);
+    assert(ZSTD_cParam_withinBounds(ZSTD_c_strategy, strat));
+    return (srcSize >> minlog) + 2;
+}
+
 /*! ZSTD_storeSeq() :
  *  Store a sequence (literal length, literals, offset code and match length code) into seqStore_t.
  *  `offsetCode` : distance to match + 3 (values 1-3 are repCodes).
@@ -326,7 +356,7 @@ MEM_STATIC void ZSTD_storeSeq(seqStore_t* seqStorePtr, size_t litLength, const v
     /* copy Literals */
     assert(seqStorePtr->maxNbLit <= 128 KB);
     assert(seqStorePtr->lit + litLength <= seqStorePtr->litStart + seqStorePtr->maxNbLit);
-    ZSTD_wildcopy(seqStorePtr->lit, literals, litLength, ZSTD_no_overlap);
+    ZSTD_wildcopy(seqStorePtr->lit, literals, (ptrdiff_t)litLength, ZSTD_no_overlap);
     seqStorePtr->lit += litLength;
 
     /* literal Length */
@@ -739,24 +769,37 @@ ZSTD_window_enforceMaxDist(ZSTD_window_t* window,
 
 /* Similar to ZSTD_window_enforceMaxDist(),
  * but only invalidates dictionary
- * when input progresses beyond window size. */
+ * when input progresses beyond window size.
+ * assumption : loadedDictEndPtr and dictMatchStatePtr are valid (non NULL)
+ *              loadedDictEnd uses same referential as window->base
+ *              maxDist is the window size */
 MEM_STATIC void
-ZSTD_checkDictValidity(ZSTD_window_t* window,
+ZSTD_checkDictValidity(const ZSTD_window_t* window,
                        const void* blockEnd,
                              U32   maxDist,
                              U32*  loadedDictEndPtr,
                        const ZSTD_matchState_t** dictMatchStatePtr)
 {
-    U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
-    U32 const loadedDictEnd = (loadedDictEndPtr != NULL) ? *loadedDictEndPtr : 0;
-    DEBUGLOG(5, "ZSTD_checkDictValidity: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
-                (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
-
-    if (loadedDictEnd && (blockEndIdx > maxDist + loadedDictEnd)) {
-        /* On reaching window size, dictionaries are invalidated */
-        if (loadedDictEndPtr) *loadedDictEndPtr = 0;
-        if (dictMatchStatePtr) *dictMatchStatePtr = NULL;
-    }
+    assert(loadedDictEndPtr != NULL);
+    assert(dictMatchStatePtr != NULL);
+    {   U32 const blockEndIdx = (U32)((BYTE const*)blockEnd - window->base);
+        U32 const loadedDictEnd = *loadedDictEndPtr;
+        DEBUGLOG(5, "ZSTD_checkDictValidity: blockEndIdx=%u, maxDist=%u, loadedDictEnd=%u",
+                    (unsigned)blockEndIdx, (unsigned)maxDist, (unsigned)loadedDictEnd);
+        assert(blockEndIdx >= loadedDictEnd);
+
+        if (blockEndIdx > loadedDictEnd + maxDist) {
+            /* On reaching window size, dictionaries are invalidated.
+             * For simplification, if window size is reached anywhere within next block,
+             * the dictionary is invalidated for the full block.
+             */
+            DEBUGLOG(6, "invalidating dictionary for current block (distance > windowSize)");
+            *loadedDictEndPtr = 0;
+            *dictMatchStatePtr = NULL;
+        } else {
+            if (*loadedDictEndPtr != 0) {
+                DEBUGLOG(6, "dictionary considered valid for current block");
+    }   }   }
 }
 
 /**
@@ -798,6 +841,17 @@ MEM_STATIC U32 ZSTD_window_update(ZSTD_window_t* window,
     return contiguous;
 }
 
+MEM_STATIC U32 ZSTD_getLowestMatchIndex(const ZSTD_matchState_t* ms, U32 current, unsigned windowLog)
+{
+    U32    const maxDistance = 1U << windowLog;
+    U32    const lowestValid = ms->window.lowLimit;
+    U32    const withinWindow = (current - lowestValid > maxDistance) ? current - maxDistance : lowestValid;
+    U32    const isDictionary = (ms->loadedDictEnd != 0);
+    U32    const matchLowest = isDictionary ? lowestValid : withinWindow;
+    return matchLowest;
+}
+
+
 
 /* debug functions */
 #if (DEBUGLEVEL>=2)
diff --git a/thirdparty/zstd/compress/zstd_compress_literals.c b/thirdparty/zstd/compress/zstd_compress_literals.c
new file mode 100644
index 0000000000..eb3e5a44bc
--- /dev/null
+++ b/thirdparty/zstd/compress/zstd_compress_literals.c
@@ -0,0 +1,149 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_literals.h"
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    BYTE* const ostart = (BYTE* const)dst;
+    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+    RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
+
+    switch(flSize)
+    {
+        case 1: /* 2 - 1 - 5 */
+            ostart[0] = (BYTE)((U32)set_basic + (srcSize<<3));
+            break;
+        case 2: /* 2 - 2 - 12 */
+            MEM_writeLE16(ostart, (U16)((U32)set_basic + (1<<2) + (srcSize<<4)));
+            break;
+        case 3: /* 2 - 2 - 20 */
+            MEM_writeLE32(ostart, (U32)((U32)set_basic + (3<<2) + (srcSize<<4)));
+            break;
+        default:   /* not necessary : flSize is {1,2,3} */
+            assert(0);
+    }
+
+    memcpy(ostart + flSize, src, srcSize);
+    return srcSize + flSize;
+}
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize)
+{
+    BYTE* const ostart = (BYTE* const)dst;
+    U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
+
+    (void)dstCapacity;  /* dstCapacity already guaranteed to be >=4, hence large enough */
+
+    switch(flSize)
+    {
+        case 1: /* 2 - 1 - 5 */
+            ostart[0] = (BYTE)((U32)set_rle + (srcSize<<3));
+            break;
+        case 2: /* 2 - 2 - 12 */
+            MEM_writeLE16(ostart, (U16)((U32)set_rle + (1<<2) + (srcSize<<4)));
+            break;
+        case 3: /* 2 - 2 - 20 */
+            MEM_writeLE32(ostart, (U32)((U32)set_rle + (3<<2) + (srcSize<<4)));
+            break;
+        default:   /* not necessary : flSize is {1,2,3} */
+            assert(0);
+    }
+
+    ostart[flSize] = *(const BYTE*)src;
+    return flSize+1;
+}
+
+size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                              void* workspace, size_t wkspSize,
+                        const int bmi2)
+{
+    size_t const minGain = ZSTD_minGain(srcSize, strategy);
+    size_t const lhSize = 3 + (srcSize >= 1 KB) + (srcSize >= 16 KB);
+    BYTE*  const ostart = (BYTE*)dst;
+    U32 singleStream = srcSize < 256;
+    symbolEncodingType_e hType = set_compressed;
+    size_t cLitSize;
+
+    DEBUGLOG(5,"ZSTD_compressLiterals (disableLiteralCompression=%i)",
+                disableLiteralCompression);
+
+    /* Prepare nextEntropy assuming reusing the existing table */
+    memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+
+    if (disableLiteralCompression)
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+
+    /* small ? don't even attempt compression (speed opt) */
+#   define COMPRESS_LITERALS_SIZE_MIN 63
+    {   size_t const minLitSize = (prevHuf->repeatMode == HUF_repeat_valid) ? 6 : COMPRESS_LITERALS_SIZE_MIN;
+        if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+    }
+
+    RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
+    {   HUF_repeat repeat = prevHuf->repeatMode;
+        int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
+        if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
+        cLitSize = singleStream ? HUF_compress1X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
+                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2)
+                                : HUF_compress4X_repeat(ostart+lhSize, dstCapacity-lhSize, src, srcSize, 255, 11,
+                                      workspace, wkspSize, (HUF_CElt*)nextHuf->CTable, &repeat, preferRepeat, bmi2);
+        if (repeat != HUF_repeat_none) {
+            /* reused the existing table */
+            hType = set_repeat;
+        }
+    }
+
+    if ((cLitSize==0) | (cLitSize >= srcSize - minGain) | ERR_isError(cLitSize)) {
+        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
+    }
+    if (cLitSize==1) {
+        memcpy(nextHuf, prevHuf, sizeof(*prevHuf));
+        return ZSTD_compressRleLiteralsBlock(dst, dstCapacity, src, srcSize);
+    }
+
+    if (hType == set_compressed) {
+        /* using a newly constructed table */
+        nextHuf->repeatMode = HUF_repeat_check;
+    }
+
+    /* Build header */
+    switch(lhSize)
+    {
+    case 3: /* 2 - 2 - 10 - 10 */
+        {   U32 const lhc = hType + ((!singleStream) << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<14);
+            MEM_writeLE24(ostart, lhc);
+            break;
+        }
+    case 4: /* 2 - 2 - 14 - 14 */
+        {   U32 const lhc = hType + (2 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<18);
+            MEM_writeLE32(ostart, lhc);
+            break;
+        }
+    case 5: /* 2 - 2 - 18 - 18 */
+        {   U32 const lhc = hType + (3 << 2) + ((U32)srcSize<<4) + ((U32)cLitSize<<22);
+            MEM_writeLE32(ostart, lhc);
+            ostart[4] = (BYTE)(cLitSize >> 10);
+            break;
+        }
+    default:  /* not possible : lhSize is {3,4,5} */
+        assert(0);
+    }
+    return lhSize+cLitSize;
+}
diff --git a/thirdparty/zstd/compress/zstd_compress_literals.h b/thirdparty/zstd/compress/zstd_compress_literals.h
new file mode 100644
index 0000000000..7adbecc0be
--- /dev/null
+++ b/thirdparty/zstd/compress/zstd_compress_literals.h
@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_LITERALS_H
+#define ZSTD_COMPRESS_LITERALS_H
+
+#include "zstd_compress_internal.h" /* ZSTD_hufCTables_t, ZSTD_minGain() */
+
+
+size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressRleLiteralsBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize);
+
+size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
+                              ZSTD_hufCTables_t* nextHuf,
+                              ZSTD_strategy strategy, int disableLiteralCompression,
+                              void* dst, size_t dstCapacity,
+                        const void* src, size_t srcSize,
+                              void* workspace, size_t wkspSize,
+                        const int bmi2);
+
+#endif /* ZSTD_COMPRESS_LITERALS_H */
diff --git a/thirdparty/zstd/compress/zstd_compress_sequences.c b/thirdparty/zstd/compress/zstd_compress_sequences.c
new file mode 100644
index 0000000000..3c3deae08c
--- /dev/null
+++ b/thirdparty/zstd/compress/zstd_compress_sequences.c
@@ -0,0 +1,415 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+ /*-*************************************
+ *  Dependencies
+ ***************************************/
+#include "zstd_compress_sequences.h"
+
+/**
+ * -log2(x / 256) lookup table for x in [0, 256).
+ * If x == 0: Return 0
+ * Else: Return floor(-log2(x / 256) * 256)
+ */
+static unsigned const kInverseProbabilityLog256[256] = {
+    0,    2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
+    1130, 1100, 1073, 1047, 1024, 1001, 980,  960,  941,  923,  906,  889,
+    874,  859,  844,  830,  817,  804,  791,  779,  768,  756,  745,  734,
+    724,  714,  704,  694,  685,  676,  667,  658,  650,  642,  633,  626,
+    618,  610,  603,  595,  588,  581,  574,  567,  561,  554,  548,  542,
+    535,  529,  523,  517,  512,  506,  500,  495,  489,  484,  478,  473,
+    468,  463,  458,  453,  448,  443,  438,  434,  429,  424,  420,  415,
+    411,  407,  402,  398,  394,  390,  386,  382,  377,  373,  370,  366,
+    362,  358,  354,  350,  347,  343,  339,  336,  332,  329,  325,  322,
+    318,  315,  311,  308,  305,  302,  298,  295,  292,  289,  286,  282,
+    279,  276,  273,  270,  267,  264,  261,  258,  256,  253,  250,  247,
+    244,  241,  239,  236,  233,  230,  228,  225,  222,  220,  217,  215,
+    212,  209,  207,  204,  202,  199,  197,  194,  192,  190,  187,  185,
+    182,  180,  178,  175,  173,  171,  168,  166,  164,  162,  159,  157,
+    155,  153,  151,  149,  146,  144,  142,  140,  138,  136,  134,  132,
+    130,  128,  126,  123,  121,  119,  117,  115,  114,  112,  110,  108,
+    106,  104,  102,  100,  98,   96,   94,   93,   91,   89,   87,   85,
+    83,   82,   80,   78,   76,   74,   73,   71,   69,   67,   66,   64,
+    62,   61,   59,   57,   55,   54,   52,   50,   49,   47,   46,   44,
+    42,   41,   39,   37,   36,   34,   33,   31,   30,   28,   26,   25,
+    23,   22,   20,   19,   17,   16,   14,   13,   11,   10,   8,    7,
+    5,    4,    2,    1,
+};
+
+static unsigned ZSTD_getFSEMaxSymbolValue(FSE_CTable const* ctable) {
+  void const* ptr = ctable;
+  U16 const* u16ptr = (U16 const*)ptr;
+  U32 const maxSymbolValue = MEM_read16(u16ptr + 1);
+  return maxSymbolValue;
+}
+
+/**
+ * Returns the cost in bytes of encoding the normalized count header.
+ * Returns an error if any of the helper functions return an error.
+ */
+static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
+                              size_t const nbSeq, unsigned const FSELog)
+{
+    BYTE wksp[FSE_NCOUNTBOUND];
+    S16 norm[MaxSeq + 1];
+    const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
+    return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution described by count
+ * using the entropy bound.
+ */
+static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t const total)
+{
+    unsigned cost = 0;
+    unsigned s;
+    for (s = 0; s <= max; ++s) {
+        unsigned norm = (unsigned)((256 * count[s]) / total);
+        if (count[s] != 0 && norm == 0)
+            norm = 1;
+        assert(count[s] < total);
+        cost += count[s] * kInverseProbabilityLog256[norm];
+    }
+    return cost >> 8;
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution in count using ctable.
+ * Returns an error if ctable cannot represent all the symbols in count.
+ */
+static size_t ZSTD_fseBitCost(
+    FSE_CTable const* ctable,
+    unsigned const* count,
+    unsigned const max)
+{
+    unsigned const kAccuracyLog = 8;
+    size_t cost = 0;
+    unsigned s;
+    FSE_CState_t cstate;
+    FSE_initCState(&cstate, ctable);
+    RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
+                    "Repeat FSE_CTable has maxSymbolValue %u < %u",
+                    ZSTD_getFSEMaxSymbolValue(ctable), max);
+    for (s = 0; s <= max; ++s) {
+        unsigned const tableLog = cstate.stateLog;
+        unsigned const badCost = (tableLog + 1) << kAccuracyLog;
+        unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
+        if (count[s] == 0)
+            continue;
+        RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
+                        "Repeat FSE_CTable has Prob[%u] == 0", s);
+        cost += count[s] * bitCost;
+    }
+    return cost >> kAccuracyLog;
+}
+
+/**
+ * Returns the cost in bits of encoding the distribution in count using the
+ * table described by norm. The max symbol support by norm is assumed >= max.
+ * norm must be valid for every symbol with non-zero probability in count.
+ */
+static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
+                                    unsigned const* count, unsigned const max)
+{
+    unsigned const shift = 8 - accuracyLog;
+    size_t cost = 0;
+    unsigned s;
+    assert(accuracyLog <= 8);
+    for (s = 0; s <= max; ++s) {
+        unsigned const normAcc = norm[s] != -1 ? norm[s] : 1;
+        unsigned const norm256 = normAcc << shift;
+        assert(norm256 > 0);
+        assert(norm256 < 256);
+        cost += count[s] * kInverseProbabilityLog256[norm256];
+    }
+    return cost >> 8;
+}
+
+symbolEncodingType_e
+ZSTD_selectEncodingType(
+        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
+        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
+        FSE_CTable const* prevCTable,
+        short const* defaultNorm, U32 defaultNormLog,
+        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_strategy const strategy)
+{
+    ZSTD_STATIC_ASSERT(ZSTD_defaultDisallowed == 0 && ZSTD_defaultAllowed != 0);
+    if (mostFrequent == nbSeq) {
+        *repeatMode = FSE_repeat_none;
+        if (isDefaultAllowed && nbSeq <= 2) {
+            /* Prefer set_basic over set_rle when there are 2 or less symbols,
+             * since RLE uses 1 byte, but set_basic uses 5-6 bits per symbol.
+             * If basic encoding isn't possible, always choose RLE.
+             */
+            DEBUGLOG(5, "Selected set_basic");
+            return set_basic;
+        }
+        DEBUGLOG(5, "Selected set_rle");
+        return set_rle;
+    }
+    if (strategy < ZSTD_lazy) {
+        if (isDefaultAllowed) {
+            size_t const staticFse_nbSeq_max = 1000;
+            size_t const mult = 10 - strategy;
+            size_t const baseLog = 3;
+            size_t const dynamicFse_nbSeq_min = (((size_t)1 << defaultNormLog) * mult) >> baseLog;  /* 28-36 for offset, 56-72 for lengths */
+            assert(defaultNormLog >= 5 && defaultNormLog <= 6);  /* xx_DEFAULTNORMLOG */
+            assert(mult <= 9 && mult >= 7);
+            if ( (*repeatMode == FSE_repeat_valid)
+              && (nbSeq < staticFse_nbSeq_max) ) {
+                DEBUGLOG(5, "Selected set_repeat");
+                return set_repeat;
+            }
+            if ( (nbSeq < dynamicFse_nbSeq_min)
+              || (mostFrequent < (nbSeq >> (defaultNormLog-1))) ) {
+                DEBUGLOG(5, "Selected set_basic");
+                /* The format allows default tables to be repeated, but it isn't useful.
+                 * When using simple heuristics to select encoding type, we don't want
+                 * to confuse these tables with dictionaries. When running more careful
+                 * analysis, we don't need to waste time checking both repeating tables
+                 * and default tables.
+                 */
+                *repeatMode = FSE_repeat_none;
+                return set_basic;
+            }
+        }
+    } else {
+        size_t const basicCost = isDefaultAllowed ? ZSTD_crossEntropyCost(defaultNorm, defaultNormLog, count, max) : ERROR(GENERIC);
+        size_t const repeatCost = *repeatMode != FSE_repeat_none ? ZSTD_fseBitCost(prevCTable, count, max) : ERROR(GENERIC);
+        size_t const NCountCost = ZSTD_NCountCost(count, max, nbSeq, FSELog);
+        size_t const compressedCost = (NCountCost << 3) + ZSTD_entropyCost(count, max, nbSeq);
+
+        if (isDefaultAllowed) {
+            assert(!ZSTD_isError(basicCost));
+            assert(!(*repeatMode == FSE_repeat_valid && ZSTD_isError(repeatCost)));
+        }
+        assert(!ZSTD_isError(NCountCost));
+        assert(compressedCost < ERROR(maxCode));
+        DEBUGLOG(5, "Estimated bit costs: basic=%u\trepeat=%u\tcompressed=%u",
+                    (unsigned)basicCost, (unsigned)repeatCost, (unsigned)compressedCost);
+        if (basicCost <= repeatCost && basicCost <= compressedCost) {
+            DEBUGLOG(5, "Selected set_basic");
+            assert(isDefaultAllowed);
+            *repeatMode = FSE_repeat_none;
+            return set_basic;
+        }
+        if (repeatCost <= compressedCost) {
+            DEBUGLOG(5, "Selected set_repeat");
+            assert(!ZSTD_isError(repeatCost));
+            return set_repeat;
+        }
+        assert(compressedCost < basicCost && compressedCost < repeatCost);
+    }
+    DEBUGLOG(5, "Selected set_compressed");
+    *repeatMode = FSE_repeat_check;
+    return set_compressed;
+}
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                unsigned* count, U32 max,
+                const BYTE* codeTable, size_t nbSeq,
+                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                const FSE_CTable* prevCTable, size_t prevCTableSize,
+                void* workspace, size_t workspaceSize)
+{
+    BYTE* op = (BYTE*)dst;
+    const BYTE* const oend = op + dstCapacity;
+    DEBUGLOG(6, "ZSTD_buildCTable (dstCapacity=%u)", (unsigned)dstCapacity);
+
+    switch (type) {
+    case set_rle:
+        FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
+        RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
+        *op = codeTable[0];
+        return 1;
+    case set_repeat:
+        memcpy(nextCTable, prevCTable, prevCTableSize);
+        return 0;
+    case set_basic:
+        FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize));  /* note : could be pre-calculated */
+        return 0;
+    case set_compressed: {
+        S16 norm[MaxSeq + 1];
+        size_t nbSeq_1 = nbSeq;
+        const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
+        if (count[codeTable[nbSeq-1]] > 1) {
+            count[codeTable[nbSeq-1]]--;
+            nbSeq_1--;
+        }
+        assert(nbSeq_1 > 1);
+        FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
+        {   size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog);   /* overflow protected */
+            FORWARD_IF_ERROR(NCountSize);
+            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
+            return NCountSize;
+        }
+    }
+    default: assert(0); RETURN_ERROR(GENERIC);
+    }
+}
+
+FORCE_INLINE_TEMPLATE size_t
+ZSTD_encodeSequences_body(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    BIT_CStream_t blockStream;
+    FSE_CState_t  stateMatchLength;
+    FSE_CState_t  stateOffsetBits;
+    FSE_CState_t  stateLitLength;
+
+    RETURN_ERROR_IF(
+        ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
+        dstSize_tooSmall, "not enough space remaining");
+    DEBUGLOG(6, "available space for bitstream : %i  (dstCapacity=%u)",
+                (int)(blockStream.endPtr - blockStream.startPtr),
+                (unsigned)dstCapacity);
+
+    /* first symbols */
+    FSE_initCState2(&stateMatchLength, CTable_MatchLength, mlCodeTable[nbSeq-1]);
+    FSE_initCState2(&stateOffsetBits,  CTable_OffsetBits,  ofCodeTable[nbSeq-1]);
+    FSE_initCState2(&stateLitLength,   CTable_LitLength,   llCodeTable[nbSeq-1]);
+    BIT_addBits(&blockStream, sequences[nbSeq-1].litLength, LL_bits[llCodeTable[nbSeq-1]]);
+    if (MEM_32bits()) BIT_flushBits(&blockStream);
+    BIT_addBits(&blockStream, sequences[nbSeq-1].matchLength, ML_bits[mlCodeTable[nbSeq-1]]);
+    if (MEM_32bits()) BIT_flushBits(&blockStream);
+    if (longOffsets) {
+        U32 const ofBits = ofCodeTable[nbSeq-1];
+        int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+        if (extraBits) {
+            BIT_addBits(&blockStream, sequences[nbSeq-1].offset, extraBits);
+            BIT_flushBits(&blockStream);
+        }
+        BIT_addBits(&blockStream, sequences[nbSeq-1].offset >> extraBits,
+                    ofBits - extraBits);
+    } else {
+        BIT_addBits(&blockStream, sequences[nbSeq-1].offset, ofCodeTable[nbSeq-1]);
+    }
+    BIT_flushBits(&blockStream);
+
+    {   size_t n;
+        for (n=nbSeq-2 ; n<nbSeq ; n--) {      /* intentional underflow */
+            BYTE const llCode = llCodeTable[n];
+            BYTE const ofCode = ofCodeTable[n];
+            BYTE const mlCode = mlCodeTable[n];
+            U32  const llBits = LL_bits[llCode];
+            U32  const ofBits = ofCode;
+            U32  const mlBits = ML_bits[mlCode];
+            DEBUGLOG(6, "encoding: litlen:%2u - matchlen:%2u - offCode:%7u",
+                        (unsigned)sequences[n].litLength,
+                        (unsigned)sequences[n].matchLength + MINMATCH,
+                        (unsigned)sequences[n].offset);
+                                                                            /* 32b*/  /* 64b*/
+                                                                            /* (7)*/  /* (7)*/
+            FSE_encodeSymbol(&blockStream, &stateOffsetBits, ofCode);       /* 15 */  /* 15 */
+            FSE_encodeSymbol(&blockStream, &stateMatchLength, mlCode);      /* 24 */  /* 24 */
+            if (MEM_32bits()) BIT_flushBits(&blockStream);                  /* (7)*/
+            FSE_encodeSymbol(&blockStream, &stateLitLength, llCode);        /* 16 */  /* 33 */
+            if (MEM_32bits() || (ofBits+mlBits+llBits >= 64-7-(LLFSELog+MLFSELog+OffFSELog)))
+                BIT_flushBits(&blockStream);                                /* (7)*/
+            BIT_addBits(&blockStream, sequences[n].litLength, llBits);
+            if (MEM_32bits() && ((llBits+mlBits)>24)) BIT_flushBits(&blockStream);
+            BIT_addBits(&blockStream, sequences[n].matchLength, mlBits);
+            if (MEM_32bits() || (ofBits+mlBits+llBits > 56)) BIT_flushBits(&blockStream);
+            if (longOffsets) {
+                int const extraBits = ofBits - MIN(ofBits, STREAM_ACCUMULATOR_MIN-1);
+                if (extraBits) {
+                    BIT_addBits(&blockStream, sequences[n].offset, extraBits);
+                    BIT_flushBits(&blockStream);                            /* (7)*/
+                }
+                BIT_addBits(&blockStream, sequences[n].offset >> extraBits,
+                            ofBits - extraBits);                            /* 31 */
+            } else {
+                BIT_addBits(&blockStream, sequences[n].offset, ofBits);     /* 31 */
+            }
+            BIT_flushBits(&blockStream);                                    /* (7)*/
+            DEBUGLOG(7, "remaining space : %i", (int)(blockStream.endPtr - blockStream.ptr));
+    }   }
+
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing ML state with %u bits", stateMatchLength.stateLog);
+    FSE_flushCState(&blockStream, &stateMatchLength);
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing Off state with %u bits", stateOffsetBits.stateLog);
+    FSE_flushCState(&blockStream, &stateOffsetBits);
+    DEBUGLOG(6, "ZSTD_encodeSequences: flushing LL state with %u bits", stateLitLength.stateLog);
+    FSE_flushCState(&blockStream, &stateLitLength);
+
+    {   size_t const streamSize = BIT_closeCStream(&blockStream);
+        RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
+        return streamSize;
+    }
+}
+
+static size_t
+ZSTD_encodeSequences_default(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    return ZSTD_encodeSequences_body(dst, dstCapacity,
+                                    CTable_MatchLength, mlCodeTable,
+                                    CTable_OffsetBits, ofCodeTable,
+                                    CTable_LitLength, llCodeTable,
+                                    sequences, nbSeq, longOffsets);
+}
+
+
+#if DYNAMIC_BMI2
+
+static TARGET_ATTRIBUTE("bmi2") size_t
+ZSTD_encodeSequences_bmi2(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets)
+{
+    return ZSTD_encodeSequences_body(dst, dstCapacity,
+                                    CTable_MatchLength, mlCodeTable,
+                                    CTable_OffsetBits, ofCodeTable,
+                                    CTable_LitLength, llCodeTable,
+                                    sequences, nbSeq, longOffsets);
+}
+
+#endif
+
+size_t ZSTD_encodeSequences(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2)
+{
+    DEBUGLOG(5, "ZSTD_encodeSequences: dstCapacity = %u", (unsigned)dstCapacity);
+#if DYNAMIC_BMI2
+    if (bmi2) {
+        return ZSTD_encodeSequences_bmi2(dst, dstCapacity,
+                                         CTable_MatchLength, mlCodeTable,
+                                         CTable_OffsetBits, ofCodeTable,
+                                         CTable_LitLength, llCodeTable,
+                                         sequences, nbSeq, longOffsets);
+    }
+#endif
+    (void)bmi2;
+    return ZSTD_encodeSequences_default(dst, dstCapacity,
+                                        CTable_MatchLength, mlCodeTable,
+                                        CTable_OffsetBits, ofCodeTable,
+                                        CTable_LitLength, llCodeTable,
+                                        sequences, nbSeq, longOffsets);
+}
diff --git a/thirdparty/zstd/compress/zstd_compress_sequences.h b/thirdparty/zstd/compress/zstd_compress_sequences.h
new file mode 100644
index 0000000000..f5234d94c8
--- /dev/null
+++ b/thirdparty/zstd/compress/zstd_compress_sequences.h
@@ -0,0 +1,47 @@
+/*
+ * Copyright (c) 2016-present, Yann Collet, Facebook, Inc.
+ * All rights reserved.
+ *
+ * This source code is licensed under both the BSD-style license (found in the
+ * LICENSE file in the root directory of this source tree) and the GPLv2 (found
+ * in the COPYING file in the root directory of this source tree).
+ * You may select, at your option, one of the above-listed licenses.
+ */
+
+#ifndef ZSTD_COMPRESS_SEQUENCES_H
+#define ZSTD_COMPRESS_SEQUENCES_H
+
+#include "fse.h" /* FSE_repeat, FSE_CTable */
+#include "zstd_internal.h" /* symbolEncodingType_e, ZSTD_strategy */
+
+typedef enum {
+    ZSTD_defaultDisallowed = 0,
+    ZSTD_defaultAllowed = 1
+} ZSTD_defaultPolicy_e;
+
+symbolEncodingType_e
+ZSTD_selectEncodingType(
+        FSE_repeat* repeatMode, unsigned const* count, unsigned const max,
+        size_t const mostFrequent, size_t nbSeq, unsigned const FSELog,
+        FSE_CTable const* prevCTable,
+        short const* defaultNorm, U32 defaultNormLog,
+        ZSTD_defaultPolicy_e const isDefaultAllowed,
+        ZSTD_strategy const strategy);
+
+size_t
+ZSTD_buildCTable(void* dst, size_t dstCapacity,
+                FSE_CTable* nextCTable, U32 FSELog, symbolEncodingType_e type,
+                unsigned* count, U32 max,
+                const BYTE* codeTable, size_t nbSeq,
+                const S16* defaultNorm, U32 defaultNormLog, U32 defaultMax,
+                const FSE_CTable* prevCTable, size_t prevCTableSize,
+                void* workspace, size_t workspaceSize);
+
+size_t ZSTD_encodeSequences(
+            void* dst, size_t dstCapacity,
+            FSE_CTable const* CTable_MatchLength, BYTE const* mlCodeTable,
+            FSE_CTable const* CTable_OffsetBits, BYTE const* ofCodeTable,
+            FSE_CTable const* CTable_LitLength, BYTE const* llCodeTable,
+            seqDef const* sequences, size_t nbSeq, int longOffsets, int bmi2);
+
+#endif /* ZSTD_COMPRESS_SEQUENCES_H */
diff --git a/thirdparty/zstd/compress/zstd_double_fast.c b/thirdparty/zstd/compress/zstd_double_fast.c
index 5957255d90..54467cc31b 100644
--- a/thirdparty/zstd/compress/zstd_double_fast.c
+++ b/thirdparty/zstd/compress/zstd_double_fast.c
@@ -65,6 +65,7 @@ size_t ZSTD_compressBlock_doubleFast_generic(
     const U32 endIndex = (U32)((size_t)(istart - base) + srcSize);
     const U32 lowestValid = ms->window.dictLimit;
     const U32 maxDistance = 1U << cParams->windowLog;
+    /* presumes that, if there is a dictionary, it must be using Attach mode */
     const U32 prefixLowestIndex = (endIndex - lowestValid > maxDistance) ? endIndex - maxDistance : lowestValid;
     const BYTE* const prefixLowest = base + prefixLowestIndex;
     const BYTE* const iend = istart + srcSize;
@@ -369,9 +370,7 @@ static size_t ZSTD_compressBlock_doubleFast_extDict_generic(
     const BYTE* const ilimit = iend - 8;
     const BYTE* const base = ms->window.base;
     const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
-    const U32   maxDistance = 1U << cParams->windowLog;
-    const U32   lowestValid = ms->window.lowLimit;
-    const U32   lowLimit = (endIndex - lowestValid > maxDistance) ? endIndex - maxDistance : lowestValid;
+    const U32   lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog);
     const U32   dictStartIndex = lowLimit;
     const U32   dictLimit = ms->window.dictLimit;
     const U32   prefixStartIndex = (dictLimit > lowLimit) ? dictLimit : lowLimit;
diff --git a/thirdparty/zstd/compress/zstd_fast.c b/thirdparty/zstd/compress/zstd_fast.c
index a05b8a47f1..59267ffbbc 100644
--- a/thirdparty/zstd/compress/zstd_fast.c
+++ b/thirdparty/zstd/compress/zstd_fast.c
@@ -71,6 +71,7 @@ size_t ZSTD_compressBlock_fast_generic(
     U32 offsetSaved = 0;
 
     /* init */
+    DEBUGLOG(5, "ZSTD_compressBlock_fast_generic");
     ip0 += (ip0 == prefixStart);
     ip1 = ip0 + 1;
     {
@@ -239,6 +240,7 @@ size_t ZSTD_compressBlock_fast_dictMatchState_generic(
     assert(prefixStartIndex >= (U32)(dictEnd - dictBase));
 
     /* init */
+    DEBUGLOG(5, "ZSTD_compressBlock_fast_dictMatchState_generic");
     ip += (dictAndPrefixLength == 0);
     /* dictMatchState repCode checks don't currently handle repCode == 0
      * disabling. */
@@ -379,9 +381,7 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
     const BYTE* ip = istart;
     const BYTE* anchor = istart;
     const U32   endIndex = (U32)((size_t)(istart - base) + srcSize);
-    const U32   maxDistance = 1U << cParams->windowLog;
-    const U32   validLow = ms->window.lowLimit;
-    const U32   lowLimit = (endIndex - validLow > maxDistance) ? endIndex - maxDistance : validLow;
+    const U32   lowLimit = ZSTD_getLowestMatchIndex(ms, endIndex, cParams->windowLog);
     const U32   dictStartIndex = lowLimit;
     const BYTE* const dictStart = dictBase + dictStartIndex;
     const U32   dictLimit = ms->window.dictLimit;
@@ -392,6 +392,8 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
     const BYTE* const ilimit = iend - 8;
     U32 offset_1=rep[0], offset_2=rep[1];
 
+    DEBUGLOG(5, "ZSTD_compressBlock_fast_extDict_generic");
+
     /* switch to "regular" variant if extDict is invalidated due to maxDistance */
     if (prefixStartIndex == dictStartIndex)
         return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, mls);
@@ -412,8 +414,8 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
 
         if ( (((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow */ & (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;
+            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, (size_t)(ip-anchor), anchor, 0, mLength-MINMATCH);
         } else {
@@ -423,8 +425,8 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
                 ip += ((ip-anchor) >> kSearchStrength) + stepSize;
                 continue;
             }
-            {   const BYTE* matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
-                const BYTE* lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
+            {   const BYTE* const matchEnd = matchIndex < prefixStartIndex ? dictEnd : iend;
+                const BYTE* const lowMatchPtr = matchIndex < prefixStartIndex ? dictStart : prefixStart;
                 U32 offset;
                 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 */
@@ -451,7 +453,7 @@ static size_t ZSTD_compressBlock_fast_extDict_generic(
                    && (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 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
+                    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);
                     hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
                     ip += repLength2;
diff --git a/thirdparty/zstd/compress/zstd_lazy.c b/thirdparty/zstd/compress/zstd_lazy.c
index 94d906c01f..0af41724c7 100644
--- a/thirdparty/zstd/compress/zstd_lazy.c
+++ b/thirdparty/zstd/compress/zstd_lazy.c
@@ -242,9 +242,7 @@ ZSTD_DUBT_findBestMatch(ZSTD_matchState_t* ms,
 
     const BYTE* const base = ms->window.base;
     U32    const current = (U32)(ip-base);
-    U32    const maxDistance = 1U << cParams->windowLog;
-    U32    const windowValid = ms->window.lowLimit;
-    U32    const windowLow = (current - windowValid > maxDistance) ? current - maxDistance : windowValid;
+    U32    const windowLow = ZSTD_getLowestMatchIndex(ms, current, cParams->windowLog);
 
     U32*   const bt = ms->chainTable;
     U32    const btLog  = cParams->chainLog - 1;
@@ -497,8 +495,10 @@ size_t ZSTD_HcFindBestMatch_generic (
     const BYTE* const dictEnd = dictBase + dictLimit;
     const U32 current = (U32)(ip-base);
     const U32 maxDistance = 1U << cParams->windowLog;
-    const U32 lowValid = ms->window.lowLimit;
-    const U32 lowLimit = (current - lowValid > maxDistance) ? current - maxDistance : lowValid;
+    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;
@@ -619,12 +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;
@@ -640,8 +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;
@@ -850,7 +854,7 @@ _storeSequence:
     rep[1] = offset_2 ? offset_2 : savedOffset;
 
     /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }
 
 
@@ -858,56 +862,56 @@ 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);
 }
 
 
@@ -916,7 +920,7 @@ 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;
@@ -934,7 +938,7 @@ size_t ZSTD_compressBlock_lazy_extDict_generic(
     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];
 
@@ -1075,7 +1079,7 @@ _storeSequence:
     rep[1] = offset_2;
 
     /* Return the last literals size */
-    return iend - anchor;
+    return (size_t)(iend - anchor);
 }
 
 
@@ -1083,7 +1087,7 @@ 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(
@@ -1091,7 +1095,7 @@ 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(
@@ -1099,7 +1103,7 @@ 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(
@@ -1107,5 +1111,5 @@ 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);
 }
diff --git a/thirdparty/zstd/compress/zstd_opt.c b/thirdparty/zstd/compress/zstd_opt.c
index e32e542e02..2da363f93e 100644
--- a/thirdparty/zstd/compress/zstd_opt.c
+++ b/thirdparty/zstd/compress/zstd_opt.c
@@ -552,7 +552,6 @@ U32 ZSTD_insertBtAndGetAllMatches (
 {
     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;
@@ -569,8 +568,7 @@ U32 ZSTD_insertBtAndGetAllMatches (
     const BYTE* const dictEnd = dictBase + dictLimit;
     const BYTE* const prefixStart = base + dictLimit;
     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 windowLow = ZSTD_getLowestMatchIndex(ms, current, cParams->windowLog);
     U32 const matchLow = windowLow ? windowLow : 1;
     U32* smallerPtr = bt + 2*(current&btMask);
     U32* largerPtr  = bt + 2*(current&btMask) + 1;
@@ -674,19 +672,21 @@ U32 ZSTD_insertBtAndGetAllMatches (
 
     while (nbCompares-- && (matchIndex >= matchLow)) {
         U32* const nextPtr = bt + 2*(matchIndex & btMask);
-        size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
         const BYTE* match;
+        size_t matchLength = MIN(commonLengthSmaller, commonLengthLarger);   /* guaranteed minimum nb of common bytes */
         assert(current > matchIndex);
 
         if ((dictMode == ZSTD_noDict) || (dictMode == ZSTD_dictMatchState) || (matchIndex+matchLength >= dictLimit)) {
             assert(matchIndex+matchLength >= dictLimit);  /* ensure the condition is correct when !extDict */
             match = base + matchIndex;
+            if (matchIndex >= dictLimit) assert(memcmp(match, ip, matchLength) == 0);  /* ensure early section of match is equal as expected */
             matchLength += ZSTD_count(ip+matchLength, match+matchLength, iLimit);
         } else {
             match = dictBase + matchIndex;
+            assert(memcmp(match, ip, matchLength) == 0);  /* ensure early section of match is equal as expected */
             matchLength += ZSTD_count_2segments(ip+matchLength, match+matchLength, iLimit, dictEnd, prefixStart);
             if (matchIndex+matchLength >= dictLimit)
-                match = base + matchIndex;   /* prepare for match[matchLength] */
+                match = base + matchIndex;   /* prepare for match[matchLength] read */
         }
 
         if (matchLength > bestLength) {
diff --git a/thirdparty/zstd/decompress/zstd_decompress.c b/thirdparty/zstd/decompress/zstd_decompress.c
index e42872ad96..751060b2cd 100644
--- a/thirdparty/zstd/decompress/zstd_decompress.c
+++ b/thirdparty/zstd/decompress/zstd_decompress.c
@@ -574,9 +574,10 @@ void ZSTD_checkContinuity(ZSTD_DCtx* dctx, const void* dst)
 }
 
 /** ZSTD_insertBlock() :
-    insert `src` block into `dctx` history. Useful to track uncompressed blocks. */
+ *  insert `src` block into `dctx` history. Useful to track uncompressed blocks. */
 size_t ZSTD_insertBlock(ZSTD_DCtx* dctx, const void* blockStart, size_t blockSize)
 {
+    DEBUGLOG(5, "ZSTD_insertBlock: %u bytes", (unsigned)blockSize);
     ZSTD_checkContinuity(dctx, blockStart);
     dctx->previousDstEnd = (const char*)blockStart + blockSize;
     return blockSize;
@@ -909,6 +910,7 @@ 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;
@@ -953,6 +955,7 @@ 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);
diff --git a/thirdparty/zstd/decompress/zstd_decompress_block.c b/thirdparty/zstd/decompress/zstd_decompress_block.c
index 24f4859c56..cbcfc08406 100644
--- a/thirdparty/zstd/decompress/zstd_decompress_block.c
+++ b/thirdparty/zstd/decompress/zstd_decompress_block.c
@@ -79,6 +79,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
 size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                           const void* src, size_t srcSize)   /* note : srcSize < BLOCKSIZE */
 {
+    DEBUGLOG(5, "ZSTD_decodeLiteralsBlock");
     RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected);
 
     {   const BYTE* const istart = (const BYTE*) src;
@@ -87,6 +88,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
         switch(litEncType)
         {
         case set_repeat:
+            DEBUGLOG(5, "set_repeat flag : re-using stats from previous compressed literals block");
             RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted);
             /* fall-through */
 
@@ -116,7 +118,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                     /* 2 - 2 - 18 - 18 */
                     lhSize = 5;
                     litSize  = (lhc >> 4) & 0x3FFFF;
-                    litCSize = (lhc >> 22) + (istart[4] << 10);
+                    litCSize = (lhc >> 22) + ((size_t)istart[4] << 10);
                     break;
                 }
                 RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
@@ -391,7 +393,8 @@ ZSTD_buildFSETable(ZSTD_seqSymbol* dt,
                     symbolNext[s] = 1;
                 } else {
                     if (normalizedCounter[s] >= largeLimit) DTableH.fastMode=0;
-                    symbolNext[s] = normalizedCounter[s];
+                    assert(normalizedCounter[s]>=0);
+                    symbolNext[s] = (U16)normalizedCounter[s];
         }   }   }
         memcpy(dt, &DTableH, sizeof(DTableH));
     }
diff --git a/thirdparty/zstd/zstd.h b/thirdparty/zstd/zstd.h
index a1910ee223..f8e95f2283 100644
--- a/thirdparty/zstd/zstd.h
+++ b/thirdparty/zstd/zstd.h
@@ -71,7 +71,7 @@ extern "C" {
 /*------   Version   ------*/
 #define ZSTD_VERSION_MAJOR    1
 #define ZSTD_VERSION_MINOR    4
-#define ZSTD_VERSION_RELEASE  1
+#define ZSTD_VERSION_RELEASE  3
 
 #define ZSTD_VERSION_NUMBER  (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
 ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< to check runtime library version */
@@ -1909,7 +1909,7 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
 /*!
     Block functions produce and decode raw zstd blocks, without frame metadata.
     Frame metadata cost is typically ~18 bytes, which can be non-negligible for very small blocks (< 100 bytes).
-    User will have to take in charge required information to regenerate data, such as compressed and content sizes.
+    But users will have to take in charge needed metadata to regenerate data, such as compressed and content sizes.
 
     A few rules to respect :
     - Compressing and decompressing require a context structure
@@ -1920,12 +1920,14 @@ ZSTDLIB_API ZSTD_nextInputType_e ZSTD_nextInputType(ZSTD_DCtx* dctx);
       + copyCCtx() and copyDCtx() can be used too
     - Block size is limited, it must be <= ZSTD_getBlockSize() <= ZSTD_BLOCKSIZE_MAX == 128 KB
       + If input is larger than a block size, it's necessary to split input data into multiple blocks
-      + For inputs larger than a single block, really consider using regular ZSTD_compress() instead.
-        Frame metadata is not that costly, and quickly becomes negligible as source size grows larger.
-    - When a block is considered not compressible enough, ZSTD_compressBlock() result will be zero.
-      In which case, nothing is produced into `dst` !
-      + User must test for such outcome and deal directly with uncompressed data
-      + ZSTD_decompressBlock() doesn't accept uncompressed data as input !!!
+      + For inputs larger than a single block, consider using regular ZSTD_compress() instead.
+        Frame metadata is not that costly, and quickly becomes negligible as source size grows larger than a block.
+    - When a block is considered not compressible enough, ZSTD_compressBlock() result will be 0 (zero) !
+      ===> In which case, nothing is produced into `dst` !
+      + User __must__ test for such outcome and deal directly with uncompressed data
+      + A block cannot be declared incompressible if ZSTD_compressBlock() return value was != 0.
+        Doing so would mess up with statistics history, leading to potential data corruption.
+      + ZSTD_decompressBlock() _doesn't accept uncompressed data as input_ !!
       + In case of multiple successive blocks, should some of them be uncompressed,
         decoder must be informed of their existence in order to follow proper history.
         Use ZSTD_insertBlock() for such a case.