lz4 - sync to latest current lz4 upstream source

6 files changed, 515 insertions, 234 deletions

diff --git a/src/static_libs/lz4/lz4.c b/src/static_libs/lz4/lz4.c
index e614c4577f..82ab490811 100644
--- a/src/static_libs/lz4/lz4.c
+++ b/src/static_libs/lz4/lz4.c
@@ -106,6 +106,7 @@
 #define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
 #endif
 
+#define LZ4_STATIC_LINKING_ONLY  /* LZ4_DISTANCE_MAX */
 #include "lz4.h"
 /* see also "memory routines" below */
 
@@ -183,6 +184,60 @@
 
 
 /*-************************************
+*  Common Constants
+**************************************/
+#define MINMATCH 4
+
+#define WILDCOPYLENGTH 8
+#define LASTLITERALS   5   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MFLIMIT       12   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
+#define MATCH_SAFEGUARD_DISTANCE  ((2*WILDCOPYLENGTH) - MINMATCH)   /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
+#define FASTLOOP_SAFE_DISTANCE 64
+static const int LZ4_minLength = (MFLIMIT+1);
+
+#define KB *(1 <<10)
+#define MB *(1 <<20)
+#define GB *(1U<<30)
+
+#define LZ4_DISTANCE_ABSOLUTE_MAX 65535
+#if (LZ4_DISTANCE_MAX > LZ4_DISTANCE_ABSOLUTE_MAX)   /* max supported by LZ4 format */
+#  error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
+#endif
+
+#define ML_BITS  4
+#define ML_MASK  ((1U<<ML_BITS)-1)
+#define RUN_BITS (8-ML_BITS)
+#define RUN_MASK ((1U<<RUN_BITS)-1)
+
+
+/*-************************************
+*  Error detection
+**************************************/
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
+#  include <assert.h>
+#else
+#  ifndef assert
+#    define assert(condition) ((void)0)
+#  endif
+#endif
+
+#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use after variable declarations */
+
+#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
+#  include <stdio.h>
+   static int g_debuglog_enable = 1;
+#  define DEBUGLOG(l, ...) {                          \
+        if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \
+            fprintf(stderr, __FILE__ ": ");           \
+            fprintf(stderr, __VA_ARGS__);             \
+            fprintf(stderr, " \n");                   \
+    }   }
+#else
+#  define DEBUGLOG(l, ...) {}    /* disabled */
+#endif
+
+
+/*-************************************
 *  Types
 **************************************/
 #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
@@ -194,6 +249,10 @@
   typedef uint64_t U64;
   typedef uintptr_t uptrval;
 #else
+# include <limits.h>
+# if UINT_MAX != 4294967295UL
+#   error "LZ4 code (when not C++ or C99) assumes that sizeof(int) == 4"
+# endif
   typedef unsigned char       BYTE;
   typedef unsigned short      U16;
   typedef unsigned int        U32;
@@ -315,7 +374,12 @@ static const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};
 
 
 #ifndef LZ4_FAST_DEC_LOOP
-#  if defined(__i386__) || defined(__x86_64__)
+#  if defined __i386__ || defined _M_IX86 || defined __x86_64__ || defined _M_X64
+#    define LZ4_FAST_DEC_LOOP 1
+#  elif defined(__aarch64__) && !defined(__clang__)
+     /* On aarch64, we disable this optimization for clang because on certain
+      * mobile chipsets, performance is reduced with clang. For information
+      * refer to https://github.com/lz4/lz4/pull/707 */
 #    define LZ4_FAST_DEC_LOOP 1
 #  else
 #    define LZ4_FAST_DEC_LOOP 0
@@ -358,29 +422,35 @@ LZ4_wildCopy32(void* dstPtr, const void* srcPtr, void* dstEnd)
     do { memcpy(d,s,16); memcpy(d+16,s+16,16); d+=32; s+=32; } while (d<e);
 }
 
+/* LZ4_memcpy_using_offset()  presumes :
+ * - dstEnd >= dstPtr + MINMATCH
+ * - there is at least 8 bytes available to write after dstEnd */
 LZ4_FORCE_O2_INLINE_GCC_PPC64LE void
 LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const size_t offset)
 {
     BYTE v[8];
+
+    assert(dstEnd >= dstPtr + MINMATCH);
+    LZ4_write32(dstPtr, 0);   /* silence an msan warning when offset==0 */
+
     switch(offset) {
     case 1:
         memset(v, *srcPtr, 8);
-        goto copy_loop;
+        break;
     case 2:
         memcpy(v, srcPtr, 2);
         memcpy(&v[2], srcPtr, 2);
         memcpy(&v[4], &v[0], 4);
-        goto copy_loop;
+        break;
     case 4:
         memcpy(v, srcPtr, 4);
         memcpy(&v[4], srcPtr, 4);
-        goto copy_loop;
+        break;
     default:
         LZ4_memcpy_using_offset_base(dstPtr, srcPtr, dstEnd, offset);
         return;
     }
 
- copy_loop:
     memcpy(dstPtr, v, 8);
     dstPtr += 8;
     while (dstPtr < dstEnd) {
@@ -392,63 +462,6 @@ LZ4_memcpy_using_offset(BYTE* dstPtr, const BYTE* srcPtr, BYTE* dstEnd, const si
 
 
 /*-************************************
-*  Common Constants
-**************************************/
-#define MINMATCH 4
-
-#define WILDCOPYLENGTH 8
-#define LASTLITERALS   5   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
-#define MFLIMIT       12   /* see ../doc/lz4_Block_format.md#parsing-restrictions */
-#define MATCH_SAFEGUARD_DISTANCE  ((2*WILDCOPYLENGTH) - MINMATCH)   /* ensure it's possible to write 2 x wildcopyLength without overflowing output buffer */
-#define FASTLOOP_SAFE_DISTANCE 64
-static const int LZ4_minLength = (MFLIMIT+1);
-
-#define KB *(1 <<10)
-#define MB *(1 <<20)
-#define GB *(1U<<30)
-
-#ifndef LZ4_DISTANCE_MAX   /* can be user - defined at compile time */
-#  define LZ4_DISTANCE_MAX 65535
-#endif
-
-#if (LZ4_DISTANCE_MAX > 65535)   /* max supported by LZ4 format */
-#  error "LZ4_DISTANCE_MAX is too big : must be <= 65535"
-#endif
-
-#define ML_BITS  4
-#define ML_MASK  ((1U<<ML_BITS)-1)
-#define RUN_BITS (8-ML_BITS)
-#define RUN_MASK ((1U<<RUN_BITS)-1)
-
-
-/*-************************************
-*  Error detection
-**************************************/
-#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=1)
-#  include <assert.h>
-#else
-#  ifndef assert
-#    define assert(condition) ((void)0)
-#  endif
-#endif
-
-#define LZ4_STATIC_ASSERT(c)   { enum { LZ4_static_assert = 1/(int)(!!(c)) }; }   /* use after variable declarations */
-
-#if defined(LZ4_DEBUG) && (LZ4_DEBUG>=2)
-#  include <stdio.h>
-static int g_debuglog_enable = 1;
-#  define DEBUGLOG(l, ...) {                                  \
-                if ((g_debuglog_enable) && (l<=LZ4_DEBUG)) {  \
-                    fprintf(stderr, __FILE__ ": ");           \
-                    fprintf(stderr, __VA_ARGS__);             \
-                    fprintf(stderr, " \n");                   \
-            }   }
-#else
-#  define DEBUGLOG(l, ...)      {}    /* disabled */
-#endif
-
-
-/*-************************************
 *  Common functions
 **************************************/
 static unsigned LZ4_NbCommonBytes (reg_t val)
@@ -460,7 +473,7 @@ static unsigned LZ4_NbCommonBytes (reg_t val)
             _BitScanForward64( &r, (U64)val );
             return (int)(r>>3);
 #       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-            return (__builtin_ctzll((U64)val) >> 3);
+            return (unsigned)__builtin_ctzll((U64)val) >> 3;
 #       else
             static const int DeBruijnBytePos[64] = { 0, 0, 0, 0, 0, 1, 1, 2,
                                                      0, 3, 1, 3, 1, 4, 2, 7,
@@ -478,7 +491,7 @@ static unsigned LZ4_NbCommonBytes (reg_t val)
             _BitScanForward( &r, (U32)val );
             return (int)(r>>3);
 #       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-            return (__builtin_ctz((U32)val) >> 3);
+            return (unsigned)__builtin_ctz((U32)val) >> 3;
 #       else
             static const int DeBruijnBytePos[32] = { 0, 0, 3, 0, 3, 1, 3, 0,
                                                      3, 2, 2, 1, 3, 2, 0, 1,
@@ -494,7 +507,7 @@ static unsigned LZ4_NbCommonBytes (reg_t val)
             _BitScanReverse64( &r, val );
             return (unsigned)(r>>3);
 #       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-            return (__builtin_clzll((U64)val) >> 3);
+            return (unsigned)__builtin_clzll((U64)val) >> 3;
 #       else
             static const U32 by32 = sizeof(val)*4;  /* 32 on 64 bits (goal), 16 on 32 bits.
                 Just to avoid some static analyzer complaining about shift by 32 on 32-bits target.
@@ -511,7 +524,7 @@ static unsigned LZ4_NbCommonBytes (reg_t val)
             _BitScanReverse( &r, (unsigned long)val );
             return (unsigned)(r>>3);
 #       elif (defined(__clang__) || (defined(__GNUC__) && (__GNUC__>=3))) && !defined(LZ4_FORCE_SW_BITCOUNT)
-            return (__builtin_clz((U32)val) >> 3);
+            return (unsigned)__builtin_clz((U32)val) >> 3;
 #       else
             unsigned r;
             if (!(val>>16)) { r=2; val>>=8; } else { r=0; val>>=24; }
@@ -606,9 +619,11 @@ int LZ4_sizeofState() { return LZ4_STREAMSIZE; }
 extern "C" {
 #endif
 
-int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize);
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize);
 
-int LZ4_decompress_safe_forceExtDict(const char* in, char* out, int inSize, int outSize, const void* dict, size_t dictSize);
+int LZ4_decompress_safe_forceExtDict(const char* source, char* dest,
+                                     int compressedSize, int maxOutputSize,
+                                     const void* dictStart, size_t dictSize);
 
 #if defined (__cplusplus)
 }
@@ -617,7 +632,7 @@ int LZ4_decompress_safe_forceExtDict(const char* in, char* out, int inSize, int
 /*-******************************
 *  Compression functions
 ********************************/
-static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
+LZ4_FORCE_INLINE U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
 {
     if (tableType == byU16)
         return ((sequence * 2654435761U) >> ((MINMATCH*8)-(LZ4_HASHLOG+1)));
@@ -625,7 +640,7 @@ static U32 LZ4_hash4(U32 sequence, tableType_t const tableType)
         return ((sequence * 2654435761U) >> ((MINMATCH*8)-LZ4_HASHLOG));
 }
 
-static U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
+LZ4_FORCE_INLINE U32 LZ4_hash5(U64 sequence, tableType_t const tableType)
 {
     const U32 hashLog = (tableType == byU16) ? LZ4_HASHLOG+1 : LZ4_HASHLOG;
     if (LZ4_isLittleEndian()) {
@@ -643,7 +658,19 @@ LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tab
     return LZ4_hash4(LZ4_read32(p), tableType);
 }
 
-static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
+LZ4_FORCE_INLINE void LZ4_clearHash(U32 h, void* tableBase, tableType_t const tableType)
+{
+    switch (tableType)
+    {
+    default: /* fallthrough */
+    case clearedTable: { /* illegal! */ assert(0); return; }
+    case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = NULL; return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = 0; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = 0; return; }
+    }
+}
+
+LZ4_FORCE_INLINE void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
 {
     switch (tableType)
     {
@@ -655,7 +682,7 @@ static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t cons
     }
 }
 
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h,
+LZ4_FORCE_INLINE void LZ4_putPositionOnHash(const BYTE* p, U32 h,
                                   void* tableBase, tableType_t const tableType,
                             const BYTE* srcBase)
 {
@@ -680,7 +707,7 @@ LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_
  * Assumption 1 : only valid if tableType == byU32 or byU16.
  * Assumption 2 : h is presumed valid (within limits of hash table)
  */
-static U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
+LZ4_FORCE_INLINE U32 LZ4_getIndexOnHash(U32 h, const void* tableBase, tableType_t tableType)
 {
     LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
     if (tableType == byU32) {
@@ -703,18 +730,19 @@ static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType
     { const U16* const hashTable = (const U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
 }
 
-LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p,
-                                             const void* tableBase, tableType_t tableType,
-                                             const BYTE* srcBase)
+LZ4_FORCE_INLINE const BYTE*
+LZ4_getPosition(const BYTE* p,
+                const void* tableBase, tableType_t tableType,
+                const BYTE* srcBase)
 {
     U32 const h = LZ4_hashPosition(p, tableType);
     return LZ4_getPositionOnHash(h, tableBase, tableType, srcBase);
 }
 
-LZ4_FORCE_INLINE void LZ4_prepareTable(
-        LZ4_stream_t_internal* const cctx,
-        const int inputSize,
-        const tableType_t tableType) {
+LZ4_FORCE_INLINE void
+LZ4_prepareTable(LZ4_stream_t_internal* const cctx,
+           const int inputSize,
+           const tableType_t tableType) {
     /* If compression failed during the previous step, then the context
      * is marked as dirty, therefore, it has to be fully reset.
      */
@@ -729,9 +757,10 @@ LZ4_FORCE_INLINE void LZ4_prepareTable(
      * out if it's safe to leave as is or whether it needs to be reset.
      */
     if (cctx->tableType != clearedTable) {
+        assert(inputSize >= 0);
         if (cctx->tableType != tableType
-          || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU)
-          || (tableType == byU32 && cctx->currentOffset > 1 GB)
+          || ((tableType == byU16) && cctx->currentOffset + (unsigned)inputSize >= 0xFFFFU)
+          || ((tableType == byU32) && cctx->currentOffset > 1 GB)
           || tableType == byPtr
           || inputSize >= 4 KB)
         {
@@ -811,9 +840,9 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
     DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType);
     /* If init conditions are not met, we don't have to mark stream
      * as having dirty context, since no action was taken yet */
-    if (outputDirective == fillOutput && maxOutputSize < 1) return 0;   /* Impossible to store anything */
-    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) return 0;           /* Unsupported inputSize, too large (or negative) */
-    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;  /* Size too large (not within 64K limit) */
+    if (outputDirective == fillOutput && maxOutputSize < 1) { return 0; } /* Impossible to store anything */
+    if ((U32)inputSize > (U32)LZ4_MAX_INPUT_SIZE) { return 0; }           /* Unsupported inputSize, too large (or negative) */
+    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) { return 0; }  /* Size too large (not within 64K limit) */
     if (tableType==byPtr) assert(dictDirective==noDict);      /* only supported use case with byPtr */
     assert(acceleration >= 1);
 
@@ -841,6 +870,7 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
     for ( ; ; ) {
         const BYTE* match;
         BYTE* token;
+        const BYTE* filledIp;
 
         /* Find a match */
         if (tableType == byPtr) {
@@ -909,10 +939,14 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
                 forwardH = LZ4_hashPosition(forwardIp, tableType);
                 LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
 
-                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue;    /* match outside of valid area */
+                DEBUGLOG(7, "candidate at pos=%u  (offset=%u \n", matchIndex, current - matchIndex);
+                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) { continue; }    /* match outside of valid area */
                 assert(matchIndex < current);
-                if ((tableType != byU16) && (matchIndex+LZ4_DISTANCE_MAX < current)) continue;  /* too far */
-                if (tableType == byU16) assert((current - matchIndex) <= LZ4_DISTANCE_MAX);     /* too_far presumed impossible with byU16 */
+                if ( ((tableType != byU16) || (LZ4_DISTANCE_MAX < LZ4_DISTANCE_ABSOLUTE_MAX))
+                  && (matchIndex+LZ4_DISTANCE_MAX < current)) {
+                    continue;
+                } /* too far */
+                assert((current - matchIndex) <= LZ4_DISTANCE_MAX);  /* match now expected within distance */
 
                 if (LZ4_read32(match) == LZ4_read32(ip)) {
                     if (maybe_extMem) offset = current - matchIndex;
@@ -923,15 +957,16 @@ LZ4_FORCE_INLINE int LZ4_compress_generic(
         }
 
         /* Catch up */
+        filledIp = ip;
         while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
 
         /* Encode Literals */
         {   unsigned const litLength = (unsigned)(ip - anchor);
             token = op++;
             if ((outputDirective == limitedOutput) &&  /* Check output buffer overflow */
-                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) )
+                (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)) ) {
                 return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
-
+            }
             if ((outputDirective == fillOutput) &&
                 (unlikely(op + (litLength+240)/255 /* litlen */ + litLength /* literals */ + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit))) {
                 op--;
@@ -1002,12 +1037,26 @@ _next_match:
             }
 
             if ((outputDirective) &&    /* Check output buffer overflow */
-                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) {
+                (unlikely(op + (1 + LASTLITERALS) + (matchCode+240)/255 > olimit)) ) {
                 if (outputDirective == fillOutput) {
                     /* Match description too long : reduce it */
-                    U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 2 - 1 - LASTLITERALS) * 255;
+                    U32 newMatchCode = 15 /* in token */ - 1 /* to avoid needing a zero byte */ + ((U32)(olimit - op) - 1 - LASTLITERALS) * 255;
                     ip -= matchCode - newMatchCode;
+                    assert(newMatchCode < matchCode);
                     matchCode = newMatchCode;
+                    if (unlikely(ip <= filledIp)) {
+                        /* We have already filled up to filledIp so if ip ends up less than filledIp
+                         * we have positions in the hash table beyond the current position. This is
+                         * a problem if we reuse the hash table. So we have to remove these positions
+                         * from the hash table.
+                         */
+                        const BYTE* ptr;
+                        DEBUGLOG(5, "Clearing %u positions", (U32)(filledIp - ip));
+                        for (ptr = ip; ptr <= filledIp; ++ptr) {
+                            U32 const h = LZ4_hashPosition(ptr, tableType);
+                            LZ4_clearHash(h, cctx->hashTable, tableType);
+                        }
+                    }
                 } else {
                     assert(outputDirective == limitedOutput);
                     return 0;   /* cannot compress within `dst` budget. Stored indexes in hash table are nonetheless fine */
@@ -1027,6 +1076,8 @@ _next_match:
             } else
                 *token += (BYTE)(matchCode);
         }
+        /* Ensure we have enough space for the last literals. */
+        assert(!(outputDirective == fillOutput && op + 1 + LASTLITERALS > olimit));
 
         anchor = ip;
 
@@ -1076,7 +1127,7 @@ _next_match:
             LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
             assert(matchIndex < current);
             if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
-              && ((tableType==byU16) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
+              && (((tableType==byU16) && (LZ4_DISTANCE_MAX == LZ4_DISTANCE_ABSOLUTE_MAX)) ? 1 : (matchIndex+LZ4_DISTANCE_MAX >= current))
               && (LZ4_read32(match) == LZ4_read32(ip)) ) {
                 token=op++;
                 *token=0;
@@ -1143,7 +1194,7 @@ int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int
             return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
         }
     } else {
-        if (inputSize < LZ4_64Klimit) {;
+        if (inputSize < LZ4_64Klimit) {
             return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16, noDict, noDictIssue, acceleration);
         } else {
             const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > LZ4_DISTANCE_MAX)) ? byPtr : byU32;
@@ -1306,12 +1357,12 @@ static size_t LZ4_stream_t_alignment(void)
 LZ4_stream_t* LZ4_initStream (void* buffer, size_t size)
 {
     DEBUGLOG(5, "LZ4_initStream");
-    if (buffer == NULL) return NULL;
-    if (size < sizeof(LZ4_stream_t)) return NULL;
+    if (buffer == NULL) { return NULL; }
+    if (size < sizeof(LZ4_stream_t)) { return NULL; }
 #ifndef _MSC_VER  /* for some reason, Visual fails the aligment test on 32-bit x86 :
                      it reports an aligment of 8-bytes,
                      while actually aligning LZ4_stream_t on 4 bytes. */
-    if (((size_t)buffer) & (LZ4_stream_t_alignment() - 1)) return NULL;  /* alignment check */
+    if (((size_t)buffer) & (LZ4_stream_t_alignment() - 1)) { return NULL; } /* alignment check */
 #endif
     MEM_INIT(buffer, 0, sizeof(LZ4_stream_t));
     return (LZ4_stream_t*)buffer;
@@ -1361,18 +1412,18 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
      * there are only valid offsets in the window, which allows an optimization
      * in LZ4_compress_fast_continue() where it uses noDictIssue even when the
      * dictionary isn't a full 64k. */
-
-    if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
-    base = dictEnd - 64 KB - dict->currentOffset;
-    dict->dictionary = p;
-    dict->dictSize = (U32)(dictEnd - p);
     dict->currentOffset += 64 KB;
-    dict->tableType = tableType;
 
     if (dictSize < (int)HASH_UNIT) {
         return 0;
     }
 
+    if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
+    base = dictEnd - dict->currentOffset;
+    dict->dictionary = p;
+    dict->dictSize = (U32)(dictEnd - p);
+    dict->tableType = tableType;
+
     while (p <= dictEnd-HASH_UNIT) {
         LZ4_putPosition(p, dict->hashTable, tableType, base);
         p+=3;
@@ -1381,26 +1432,37 @@ int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
     return (int)dict->dictSize;
 }
 
-void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) {
+void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream) {
+    const LZ4_stream_t_internal* dictCtx = dictionaryStream == NULL ? NULL :
+        &(dictionaryStream->internal_donotuse);
+
+    DEBUGLOG(4, "LZ4_attach_dictionary (%p, %p, size %u)",
+             workingStream, dictionaryStream,
+             dictCtx != NULL ? dictCtx->dictSize : 0);
+
     /* Calling LZ4_resetStream_fast() here makes sure that changes will not be
      * erased by subsequent calls to LZ4_resetStream_fast() in case stream was
      * marked as having dirty context, e.g. requiring full reset.
      */
-    LZ4_resetStream_fast(working_stream);
+    LZ4_resetStream_fast(workingStream);
 
-    if (dictionary_stream != NULL) {
+    if (dictCtx != NULL) {
         /* If the current offset is zero, we will never look in the
          * external dictionary context, since there is no value a table
          * entry can take that indicate a miss. In that case, we need
          * to bump the offset to something non-zero.
          */
-        if (working_stream->internal_donotuse.currentOffset == 0) {
-            working_stream->internal_donotuse.currentOffset = 64 KB;
+        if (workingStream->internal_donotuse.currentOffset == 0) {
+            workingStream->internal_donotuse.currentOffset = 64 KB;
+        }
+
+        /* Don't actually attach an empty dictionary.
+         */
+        if (dictCtx->dictSize == 0) {
+            dictCtx = NULL;
         }
-        working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse);
-    } else {
-        working_stream->internal_donotuse.dictCtx = NULL;
     }
+    workingStream->internal_donotuse.dictCtx = dictCtx;
 }
 
 
@@ -1435,7 +1497,7 @@ int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream,
 
     DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize);
 
-    if (streamPtr->dirty) return 0;   /* Uninitialized structure detected */
+    if (streamPtr->dirty) { return 0; } /* Uninitialized structure detected */
     LZ4_renormDictT(streamPtr, inputSize);   /* avoid index overflow */
     if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
@@ -1532,8 +1594,8 @@ int LZ4_saveDict (LZ4_stream_t* LZ4_dict, char* safeBuffer, int dictSize)
     LZ4_stream_t_internal* const dict = &LZ4_dict->internal_donotuse;
     const BYTE* const previousDictEnd = dict->dictionary + dict->dictSize;
 
-    if ((U32)dictSize > 64 KB) dictSize = 64 KB;   /* useless to define a dictionary > 64 KB */
-    if ((U32)dictSize > dict->dictSize) dictSize = (int)dict->dictSize;
+    if ((U32)dictSize > 64 KB) { dictSize = 64 KB; } /* useless to define a dictionary > 64 KB */
+    if ((U32)dictSize > dict->dictSize) { dictSize = (int)dict->dictSize; }
 
     memmove(safeBuffer, previousDictEnd - dictSize, dictSize);
 
@@ -1567,8 +1629,8 @@ typedef enum { loop_error = -2, initial_error = -1, ok = 0 } variable_length_err
 LZ4_FORCE_INLINE unsigned
 read_variable_length(const BYTE**ip, const BYTE* lencheck, int loop_check, int initial_check, variable_length_error* error)
 {
-  unsigned length = 0;
-  unsigned s;
+  U32 length = 0;
+  U32 s;
   if (initial_check && unlikely((*ip) >= lencheck)) {    /* overflow detection */
     *error = initial_error;
     return length;
@@ -1607,7 +1669,7 @@ LZ4_decompress_generic(
                  const size_t dictSize         /* note : = 0 if noDict */
                  )
 {
-    if (src == NULL) return -1;
+    if (src == NULL) { return -1; }
 
     {   const BYTE* ip = (const BYTE*) src;
         const BYTE* const iend = ip + srcSize;
@@ -1636,9 +1698,13 @@ LZ4_decompress_generic(
 
         /* Special cases */
         assert(lowPrefix <= op);
-        if ((endOnInput) && (unlikely(outputSize==0))) return ((srcSize==1) && (*ip==0)) ? 0 : -1;  /* Empty output buffer */
-        if ((!endOnInput) && (unlikely(outputSize==0))) return (*ip==0 ? 1 : -1);
-        if ((endOnInput) && unlikely(srcSize==0)) return -1;
+        if ((endOnInput) && (unlikely(outputSize==0))) {
+            /* Empty output buffer */
+            if (partialDecoding) return 0;
+            return ((srcSize==1) && (*ip==0)) ? 0 : -1;
+        }
+        if ((!endOnInput) && (unlikely(outputSize==0))) { return (*ip==0 ? 1 : -1); }
+        if ((endOnInput) && unlikely(srcSize==0)) { return -1; }
 
         /* Currently the fast loop shows a regression on qualcomm arm chips. */
 #if LZ4_FAST_DEC_LOOP
@@ -1651,7 +1717,7 @@ LZ4_decompress_generic(
         while (1) {
             /* Main fastloop assertion: We can always wildcopy FASTLOOP_SAFE_DISTANCE */
             assert(oend - op >= FASTLOOP_SAFE_DISTANCE);
-            if (endOnInput) assert(ip < iend);
+            if (endOnInput) { assert(ip < iend); }
             token = *ip++;
             length = token >> ML_BITS;  /* literal length */
 
@@ -1661,18 +1727,18 @@ LZ4_decompress_generic(
             if (length == RUN_MASK) {
                 variable_length_error error = ok;
                 length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error);
-                if (error == initial_error) goto _output_error;
-                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
-                if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error;   /* overflow detection */
+                if (error == initial_error) { goto _output_error; }
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+                if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
 
                 /* copy literals */
                 cpy = op+length;
                 LZ4_STATIC_ASSERT(MFLIMIT >= WILDCOPYLENGTH);
                 if (endOnInput) {  /* LZ4_decompress_safe() */
-                    if ((cpy>oend-32) || (ip+length>iend-32)) goto safe_literal_copy;
+                    if ((cpy>oend-32) || (ip+length>iend-32)) { goto safe_literal_copy; }
                     LZ4_wildCopy32(op, ip, cpy);
                 } else {   /* LZ4_decompress_fast() */
-                    if (cpy>oend-8) goto safe_literal_copy;
+                    if (cpy>oend-8) { goto safe_literal_copy; }
                     LZ4_wildCopy8(op, ip, cpy); /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
                                                  * it doesn't know input length, and only relies on end-of-block properties */
                 }
@@ -1682,14 +1748,14 @@ LZ4_decompress_generic(
                 if (endOnInput) {  /* LZ4_decompress_safe() */
                     DEBUGLOG(7, "copy %u bytes in a 16-bytes stripe", (unsigned)length);
                     /* We don't need to check oend, since we check it once for each loop below */
-                    if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) goto safe_literal_copy;
+                    if (ip > iend-(16 + 1/*max lit + offset + nextToken*/)) { goto safe_literal_copy; }
                     /* Literals can only be 14, but hope compilers optimize if we copy by a register size */
                     memcpy(op, ip, 16);
                 } else {  /* LZ4_decompress_fast() */
                     /* LZ4_decompress_fast() cannot copy more than 8 bytes at a time :
                      * it doesn't know input length, and relies on end-of-block properties */
                     memcpy(op, ip, 8);
-                    if (length > 8) memcpy(op+8, ip+8, 8);
+                    if (length > 8) { memcpy(op+8, ip+8, 8); }
                 }
                 ip += length; op = cpy;
             }
@@ -1697,17 +1763,17 @@ LZ4_decompress_generic(
             /* get offset */
             offset = LZ4_readLE16(ip); ip+=2;
             match = op - offset;
+            assert(match <= op);
 
             /* get matchlength */
             length = token & ML_MASK;
 
-            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
-
             if (length == ML_MASK) {
               variable_length_error error = ok;
+              if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
               length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error);
-              if (error != ok) goto _output_error;
-                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
+              if (error != ok) { goto _output_error; }
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) { goto _output_error; } /* overflow detection */
                 length += MINMATCH;
                 if (op + length >= oend - FASTLOOP_SAFE_DISTANCE) {
                     goto safe_match_copy;
@@ -1719,8 +1785,12 @@ LZ4_decompress_generic(
                 }
 
                 /* Fastpath check: Avoids a branch in LZ4_wildCopy32 if true */
-                if (!(dict == usingExtDict) || (match >= lowPrefix)) {
+                if ((dict == withPrefix64k) || (match >= lowPrefix)) {
                     if (offset >= 8) {
+                        assert(match >= lowPrefix);
+                        assert(match <= op);
+                        assert(op + 18 <= oend);
+
                         memcpy(op, match, 8);
                         memcpy(op+8, match+8, 8);
                         memcpy(op+16, match+16, 2);
@@ -1728,12 +1798,15 @@ LZ4_decompress_generic(
                         continue;
             }   }   }
 
+            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) { goto _output_error; } /* Error : offset outside buffers */
             /* match starting within external dictionary */
             if ((dict==usingExtDict) && (match < lowPrefix)) {
                 if (unlikely(op+length > oend-LASTLITERALS)) {
-                    if (partialDecoding) length = MIN(length, (size_t)(oend-op));
-                    else goto _output_error;   /* doesn't respect parsing restriction */
-                }
+                    if (partialDecoding) {
+                        length = MIN(length, (size_t)(oend-op));  /* reach end of buffer */
+                    } else {
+                        goto _output_error;  /* end-of-block condition violated */
+                }   }
 
                 if (length <= (size_t)(lowPrefix-match)) {
                     /* match fits entirely within external dictionary : just copy */
@@ -1748,7 +1821,7 @@ LZ4_decompress_generic(
                     if (restSize > (size_t)(op - lowPrefix)) {  /* overlap copy */
                         BYTE* const endOfMatch = op + restSize;
                         const BYTE* copyFrom = lowPrefix;
-                        while (op < endOfMatch) *op++ = *copyFrom++;
+                        while (op < endOfMatch) { *op++ = *copyFrom++; }
                     } else {
                         memcpy(op, lowPrefix, restSize);
                         op += restSize;
@@ -1821,11 +1894,11 @@ LZ4_decompress_generic(
 
             /* decode literal length */
             if (length == RUN_MASK) {
-              variable_length_error error = ok;
-              length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error);
-              if (error == initial_error) goto _output_error;
-                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) goto _output_error;   /* overflow detection */
-                if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) goto _output_error;   /* overflow detection */
+                variable_length_error error = ok;
+                length += read_variable_length(&ip, iend-RUN_MASK, endOnInput, endOnInput, &error);
+                if (error == initial_error) { goto _output_error; }
+                if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)(op))) { goto _output_error; } /* overflow detection */
+                if ((safeDecode) && unlikely((uptrval)(ip)+length<(uptrval)(ip))) { goto _output_error; } /* overflow detection */
             }
 
             /* copy literals */
@@ -1837,21 +1910,50 @@ LZ4_decompress_generic(
             if ( ((endOnInput) && ((cpy>oend-MFLIMIT) || (ip+length>iend-(2+1+LASTLITERALS))) )
               || ((!endOnInput) && (cpy>oend-WILDCOPYLENGTH)) )
             {
+                /* We've either hit the input parsing restriction or the output parsing restriction.
+                 * If we've hit the input parsing condition then this must be the last sequence.
+                 * If we've hit the output parsing condition then we are either using partialDecoding
+                 * or we've hit the output parsing condition.
+                 */
                 if (partialDecoding) {
-                    if (cpy > oend) { cpy = oend; assert(op<=oend); length = (size_t)(oend-op); }  /* Partial decoding : stop in the middle of literal segment */
-                    if ((endOnInput) && (ip+length > iend)) goto _output_error;   /* Error : read attempt beyond end of input buffer */
+                    /* Since we are partial decoding we may be in this block because of the output parsing
+                     * restriction, which is not valid since the output buffer is allowed to be undersized.
+                     */
+                    assert(endOnInput);
+                    /* If we're in this block because of the input parsing condition, then we must be on the
+                     * last sequence (or invalid), so we must check that we exactly consume the input.
+                     */
+                    if ((ip+length>iend-(2+1+LASTLITERALS)) && (ip+length != iend)) { goto _output_error; }
+                    assert(ip+length <= iend);
+                    /* We are finishing in the middle of a literals segment.
+                     * Break after the copy.
+                     */
+                    if (cpy > oend) {
+                        cpy = oend;
+                        assert(op<=oend);
+                        length = (size_t)(oend-op);
+                    }
+                    assert(ip+length <= iend);
                 } else {
-                    if ((!endOnInput) && (cpy != oend)) goto _output_error;       /* Error : block decoding must stop exactly there */
-                    if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) goto _output_error;   /* Error : input must be consumed */
+                    /* We must be on the last sequence because of the parsing limitations so check
+                     * that we exactly regenerate the original size (must be exact when !endOnInput).
+                     */
+                    if ((!endOnInput) && (cpy != oend)) { goto _output_error; }
+                     /* We must be on the last sequence (or invalid) because of the parsing limitations
+                      * so check that we exactly consume the input and don't overrun the output buffer.
+                      */
+                    if ((endOnInput) && ((ip+length != iend) || (cpy > oend))) { goto _output_error; }
                 }
-                memcpy(op, ip, length);
+                memmove(op, ip, length);  /* supports overlapping memory regions, which only matters for in-place decompression scenarios */
                 ip += length;
                 op += length;
-                if (!partialDecoding || (cpy == oend)) {
-                    /* Necessarily EOF, due to parsing restrictions */
+                /* Necessarily EOF when !partialDecoding. When partialDecoding
+                 * it is EOF if we've either filled the output buffer or hit
+                 * the input parsing restriction.
+                 */
+                if (!partialDecoding || (cpy == oend) || (ip == iend)) {
                     break;
                 }
-
             } else {
                 LZ4_wildCopy8(op, ip, cpy);   /* may overwrite up to WILDCOPYLENGTH beyond cpy */
                 ip += length; op = cpy;
@@ -1865,13 +1967,6 @@ LZ4_decompress_generic(
             length = token & ML_MASK;
 
     _copy_match:
-            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
-            if (!partialDecoding) {
-                assert(oend > op);
-                assert(oend - op >= 4);
-                LZ4_write32(op, 0);   /* silence an msan warning when offset==0; costs <1%; */
-            }   /* note : when partialDecoding, there is no guarantee that at least 4 bytes remain available in output buffer */
-
             if (length == ML_MASK) {
               variable_length_error error = ok;
               length += read_variable_length(&ip, iend - LASTLITERALS + 1, endOnInput, 0, &error);
@@ -1883,6 +1978,7 @@ LZ4_decompress_generic(
 #if LZ4_FAST_DEC_LOOP
         safe_match_copy:
 #endif
+            if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
             /* match starting within external dictionary */
             if ((dict==usingExtDict) && (match < lowPrefix)) {
                 if (unlikely(op+length > oend-LASTLITERALS)) {
@@ -1910,6 +2006,7 @@ LZ4_decompress_generic(
                 }   }
                 continue;
             }
+            assert(match >= lowPrefix);
 
             /* copy match within block */
             cpy = op + length;
@@ -1921,16 +2018,17 @@ LZ4_decompress_generic(
                 const BYTE* const matchEnd = match + mlen;
                 BYTE* const copyEnd = op + mlen;
                 if (matchEnd > op) {   /* overlap copy */
-                    while (op < copyEnd) *op++ = *match++;
+                    while (op < copyEnd) { *op++ = *match++; }
                 } else {
                     memcpy(op, match, mlen);
                 }
                 op = copyEnd;
-                if (op==oend) break;
+                if (op == oend) { break; }
                 continue;
             }
 
             if (unlikely(offset<8)) {
+                LZ4_write32(op, 0);   /* silence msan warning when offset==0 */
                 op[0] = match[0];
                 op[1] = match[1];
                 op[2] = match[2];
@@ -1946,25 +2044,26 @@ LZ4_decompress_generic(
 
             if (unlikely(cpy > oend-MATCH_SAFEGUARD_DISTANCE)) {
                 BYTE* const oCopyLimit = oend - (WILDCOPYLENGTH-1);
-                if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
+                if (cpy > oend-LASTLITERALS) { goto _output_error; } /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
                 if (op < oCopyLimit) {
                     LZ4_wildCopy8(op, match, oCopyLimit);
                     match += oCopyLimit - op;
                     op = oCopyLimit;
                 }
-                while (op < cpy) *op++ = *match++;
+                while (op < cpy) { *op++ = *match++; }
             } else {
                 memcpy(op, match, 8);
-                if (length > 16) LZ4_wildCopy8(op+8, match+8, cpy);
+                if (length > 16)  { LZ4_wildCopy8(op+8, match+8, cpy); }
             }
             op = cpy;   /* wildcopy correction */
         }
 
         /* end of decoding */
-        if (endOnInput)
+        if (endOnInput) {
            return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */
-        else
+       } else {
            return (int) (((const char*)ip)-src);   /* Nb of input bytes read */
+       }
 
         /* Overflow error detected */
     _output_error:
@@ -2079,7 +2178,7 @@ LZ4_streamDecode_t* LZ4_createStreamDecode(void)
 
 int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
 {
-    if (LZ4_stream == NULL) return 0;   /* support free on NULL */
+    if (LZ4_stream == NULL) { return 0; }  /* support free on NULL */
     FREEMEM(LZ4_stream);
     return 0;
 }
@@ -2214,18 +2313,22 @@ int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressed
     if (dictSize==0)
         return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
     if (dictStart+dictSize == dest) {
-        if (dictSize >= 64 KB - 1)
+        if (dictSize >= 64 KB - 1) {
             return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
-        return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize);
+        }
+        assert(dictSize >= 0);
+        return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, (size_t)dictSize);
     }
-    return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize);
+    assert(dictSize >= 0);
+    return LZ4_decompress_safe_forceExtDict(source, dest, compressedSize, maxOutputSize, dictStart, (size_t)dictSize);
 }
 
 int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
 {
     if (dictSize==0 || dictStart+dictSize == dest)
         return LZ4_decompress_fast(source, dest, originalSize);
-    return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, dictSize);
+    assert(dictSize >= 0);
+    return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, (size_t)dictSize);
 }
 
 
@@ -2237,9 +2340,9 @@ int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, in
 {
     return LZ4_compress_default(source, dest, inputSize, maxOutputSize);
 }
-int LZ4_compress(const char* source, char* dest, int inputSize)
+int LZ4_compress(const char* src, char* dest, int srcSize)
 {
-    return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize));
+    return LZ4_compress_default(src, dest, srcSize, LZ4_compressBound(srcSize));
 }
 int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize)
 {
diff --git a/src/static_libs/lz4/lz4.h b/src/static_libs/lz4/lz4.h
index a9c932ccb1..32108e2329 100644
--- a/src/static_libs/lz4/lz4.h
+++ b/src/static_libs/lz4/lz4.h
@@ -46,7 +46,7 @@ extern "C" {
 /**
   Introduction
 
-  LZ4 is lossless compression algorithm, providing compression speed at 500 MB/s per core,
+  LZ4 is lossless compression algorithm, providing compression speed >500 MB/s per core,
   scalable with multi-cores CPU. It features an extremely fast decoder, with speed in
   multiple GB/s per core, typically reaching RAM speed limits on multi-core systems.
 
@@ -58,16 +58,19 @@ extern "C" {
     - unbounded multiple steps (described as Streaming compression)
 
   lz4.h generates and decodes LZ4-compressed blocks (doc/lz4_Block_format.md).
-  Decompressing a block requires additional metadata, such as its compressed size.
+  Decompressing such a compressed block requires additional metadata.
+  Exact metadata depends on exact decompression function.
+  For the typical case of LZ4_decompress_safe(),
+  metadata includes block's compressed size, and maximum bound of decompressed size.
   Each application is free to encode and pass such metadata in whichever way it wants.
 
   lz4.h only handle blocks, it can not generate Frames.
 
   Blocks are different from Frames (doc/lz4_Frame_format.md).
   Frames bundle both blocks and metadata in a specified manner.
-  This are required for compressed data to be self-contained and portable.
+  Embedding metadata is required for compressed data to be self-contained and portable.
   Frame format is delivered through a companion API, declared in lz4frame.h.
-  Note that the `lz4` CLI can only manage frames.
+  The `lz4` CLI can only manage frames.
 */
 
 /*^***************************************************************
@@ -97,7 +100,7 @@ extern "C" {
 /*------   Version   ------*/
 #define LZ4_VERSION_MAJOR    1    /* for breaking interface changes  */
 #define LZ4_VERSION_MINOR    9    /* for new (non-breaking) interface capabilities */
-#define LZ4_VERSION_RELEASE  1    /* for tweaks, bug-fixes, or development */
+#define LZ4_VERSION_RELEASE  2    /* for tweaks, bug-fixes, or development */
 
 #define LZ4_VERSION_NUMBER (LZ4_VERSION_MAJOR *100*100 + LZ4_VERSION_MINOR *100 + LZ4_VERSION_RELEASE)
 
@@ -129,29 +132,35 @@ LZ4LIB_API const char* LZ4_versionString (void);   /**< library version string;
 *  Simple Functions
 **************************************/
 /*! LZ4_compress_default() :
-    Compresses 'srcSize' bytes from buffer 'src'
-    into already allocated 'dst' buffer of size 'dstCapacity'.
-    Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
-    It also runs faster, so it's a recommended setting.
-    If the function cannot compress 'src' into a more limited 'dst' budget,
-    compression stops *immediately*, and the function result is zero.
-    In which case, 'dst' content is undefined (invalid).
-        srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
-        dstCapacity : size of buffer 'dst' (which must be already allocated)
-       @return  : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
-                  or 0 if compression fails
-    Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
-*/
+ *  Compresses 'srcSize' bytes from buffer 'src'
+ *  into already allocated 'dst' buffer of size 'dstCapacity'.
+ *  Compression is guaranteed to succeed if 'dstCapacity' >= LZ4_compressBound(srcSize).
+ *  It also runs faster, so it's a recommended setting.
+ *  If the function cannot compress 'src' into a more limited 'dst' budget,
+ *  compression stops *immediately*, and the function result is zero.
+ *  In which case, 'dst' content is undefined (invalid).
+ *      srcSize : max supported value is LZ4_MAX_INPUT_SIZE.
+ *      dstCapacity : size of buffer 'dst' (which must be already allocated)
+ *     @return  : the number of bytes written into buffer 'dst' (necessarily <= dstCapacity)
+ *                or 0 if compression fails
+ * Note : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
+ */
 LZ4LIB_API int LZ4_compress_default(const char* src, char* dst, int srcSize, int dstCapacity);
 
 /*! LZ4_decompress_safe() :
-    compressedSize : is the exact complete size of the compressed block.
-    dstCapacity : is the size of destination buffer, which must be already allocated.
-   @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
-             If destination buffer is not large enough, decoding will stop and output an error code (negative value).
-             If the source stream is detected malformed, the function will stop decoding and return a negative result.
-    Note : This function is protected against malicious data packets (never writes outside 'dst' buffer, nor read outside 'source' buffer).
-*/
+ *  compressedSize : is the exact complete size of the compressed block.
+ *  dstCapacity : is the size of destination buffer (which must be already allocated), presumed an upper bound of decompressed size.
+ * @return : the number of bytes decompressed into destination buffer (necessarily <= dstCapacity)
+ *           If destination buffer is not large enough, decoding will stop and output an error code (negative value).
+ *           If the source stream is detected malformed, the function will stop decoding and return a negative result.
+ * Note 1 : This function is protected against malicious data packets :
+ *          it will never writes outside 'dst' buffer, nor read outside 'source' buffer,
+ *          even if the compressed block is maliciously modified to order the decoder to do these actions.
+ *          In such case, the decoder stops immediately, and considers the compressed block malformed.
+ * Note 2 : compressedSize and dstCapacity must be provided to the function, the compressed block does not contain them.
+ *          The implementation is free to send / store / derive this information in whichever way is most beneficial.
+ *          If there is a need for a different format which bundles together both compressed data and its metadata, consider looking at lz4frame.h instead.
+ */
 LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
 
 
@@ -388,6 +397,8 @@ LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecod
  */
 LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
 
+#endif /* LZ4_H_2983827168210 */
+
 
 /*^*************************************
  * !!!!!!   STATIC LINKING ONLY   !!!!!!
@@ -413,14 +424,17 @@ LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int sr
  * define LZ4_PUBLISH_STATIC_FUNCTIONS when building the LZ4 library.
  ******************************************************************************/
 
+#ifdef LZ4_STATIC_LINKING_ONLY
+
+#ifndef LZ4_STATIC_3504398509
+#define LZ4_STATIC_3504398509
+
 #ifdef LZ4_PUBLISH_STATIC_FUNCTIONS
 #define LZ4LIB_STATIC_API LZ4LIB_API
 #else
 #define LZ4LIB_STATIC_API
 #endif
 
-#ifdef LZ4_STATIC_LINKING_ONLY
-
 
 /*! LZ4_compress_fast_extState_fastReset() :
  *  A variant of LZ4_compress_fast_extState().
@@ -462,8 +476,75 @@ LZ4LIB_STATIC_API int LZ4_compress_fast_extState_fastReset (void* state, const c
  */
 LZ4LIB_STATIC_API void LZ4_attach_dictionary(LZ4_stream_t* workingStream, const LZ4_stream_t* dictionaryStream);
 
+
+/*! In-place compression and decompression
+ *
+ * It's possible to have input and output sharing the same buffer,
+ * for highly contrained memory environments.
+ * In both cases, it requires input to lay at the end of the buffer,
+ * and decompression to start at beginning of the buffer.
+ * Buffer size must feature some margin, hence be larger than final size.
+ *
+ * |<------------------------buffer--------------------------------->|
+ *                             |<-----------compressed data--------->|
+ * |<-----------decompressed size------------------>|
+ *                                                  |<----margin---->|
+ *
+ * This technique is more useful for decompression,
+ * since decompressed size is typically larger,
+ * and margin is short.
+ *
+ * In-place decompression will work inside any buffer
+ * which size is >= LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize).
+ * This presumes that decompressedSize > compressedSize.
+ * Otherwise, it means compression actually expanded data,
+ * and it would be more efficient to store such data with a flag indicating it's not compressed.
+ * This can happen when data is not compressible (already compressed, or encrypted).
+ *
+ * For in-place compression, margin is larger, as it must be able to cope with both
+ * history preservation, requiring input data to remain unmodified up to LZ4_DISTANCE_MAX,
+ * and data expansion, which can happen when input is not compressible.
+ * As a consequence, buffer size requirements are much higher,
+ * and memory savings offered by in-place compression are more limited.
+ *
+ * There are ways to limit this cost for compression :
+ * - Reduce history size, by modifying LZ4_DISTANCE_MAX.
+ *   Note that it is a compile-time constant, so all compressions will apply this limit.
+ *   Lower values will reduce compression ratio, except when input_size < LZ4_DISTANCE_MAX,
+ *   so it's a reasonable trick when inputs are known to be small.
+ * - Require the compressor to deliver a "maximum compressed size".
+ *   This is the `dstCapacity` parameter in `LZ4_compress*()`.
+ *   When this size is < LZ4_COMPRESSBOUND(inputSize), then compression can fail,
+ *   in which case, the return code will be 0 (zero).
+ *   The caller must be ready for these cases to happen,
+ *   and typically design a backup scheme to send data uncompressed.
+ * The combination of both techniques can significantly reduce
+ * the amount of margin required for in-place compression.
+ *
+ * In-place compression can work in any buffer
+ * which size is >= (maxCompressedSize)
+ * with maxCompressedSize == LZ4_COMPRESSBOUND(srcSize) for guaranteed compression success.
+ * LZ4_COMPRESS_INPLACE_BUFFER_SIZE() depends on both maxCompressedSize and LZ4_DISTANCE_MAX,
+ * so it's possible to reduce memory requirements by playing with them.
+ */
+
+#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize)          (((compressedSize) >> 8) + 32)
+#define LZ4_DECOMPRESS_INPLACE_BUFFER_SIZE(decompressedSize)   ((decompressedSize) + LZ4_DECOMPRESS_INPLACE_MARGIN(decompressedSize))  /**< note: presumes that compressedSize < decompressedSize. note2: margin is overestimated a bit, since it could use compressedSize instead */
+
+#ifndef LZ4_DISTANCE_MAX   /* history window size; can be user-defined at compile time */
+#  define LZ4_DISTANCE_MAX 65535   /* set to maximum value by default */
 #endif
 
+#define LZ4_COMPRESS_INPLACE_MARGIN                           (LZ4_DISTANCE_MAX + 32)   /* LZ4_DISTANCE_MAX can be safely replaced by srcSize when it's smaller */
+#define LZ4_COMPRESS_INPLACE_BUFFER_SIZE(maxCompressedSize)   ((maxCompressedSize) + LZ4_COMPRESS_INPLACE_MARGIN)  /**< maxCompressedSize is generally LZ4_COMPRESSBOUND(inputSize), but can be set to any lower value, with the risk that compression can fail (return code 0(zero)) */
+
+#endif   /* LZ4_STATIC_3504398509 */
+#endif   /* LZ4_STATIC_LINKING_ONLY */
+
+
+
+#ifndef LZ4_H_98237428734687
+#define LZ4_H_98237428734687
 
 /*-************************************************************
  *  PRIVATE DEFINITIONS
@@ -567,6 +648,7 @@ union LZ4_streamDecode_u {
 } ;   /* previously typedef'd to LZ4_streamDecode_t */
 
 
+
 /*-************************************
 *  Obsolete Functions
 **************************************/
@@ -601,8 +683,8 @@ union LZ4_streamDecode_u {
 #endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */
 
 /* Obsolete compression functions */
-LZ4_DEPRECATED("use LZ4_compress_default() instead")       LZ4LIB_API int LZ4_compress               (const char* source, char* dest, int sourceSize);
-LZ4_DEPRECATED("use LZ4_compress_default() instead")       LZ4LIB_API int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize);
+LZ4_DEPRECATED("use LZ4_compress_default() instead")       LZ4LIB_API int LZ4_compress               (const char* src, char* dest, int srcSize);
+LZ4_DEPRECATED("use LZ4_compress_default() instead")       LZ4LIB_API int LZ4_compress_limitedOutput (const char* src, char* dest, int srcSize, int maxOutputSize);
 LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_withState               (void* state, const char* source, char* dest, int inputSize);
 LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") LZ4LIB_API int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
 LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_continue                (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
@@ -674,7 +756,7 @@ LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int or
 LZ4LIB_API void LZ4_resetStream (LZ4_stream_t* streamPtr);
 
 
-#endif /* LZ4_H_2983827168210 */
+#endif /* LZ4_H_98237428734687 */
 
 
 #if defined (__cplusplus)
diff --git a/src/static_libs/lz4/lz4frame.c b/src/static_libs/lz4/lz4frame.c
index 95da80ec32..71ee73d8a8 100644
--- a/src/static_libs/lz4/lz4frame.c
+++ b/src/static_libs/lz4/lz4frame.c
@@ -213,8 +213,8 @@ static void LZ4F_writeLE64 (void* dst, U64 value64)
 
 static const size_t minFHSize = LZ4F_HEADER_SIZE_MIN;   /*  7 */
 static const size_t maxFHSize = LZ4F_HEADER_SIZE_MAX;   /* 19 */
-static const size_t BHSize = 4;  /* block header : size, and compress flag */
-static const size_t BFSize = 4;  /* block footer : checksum (optional) */
+static const size_t BHSize = LZ4F_BLOCK_HEADER_SIZE;  /* block header : size, and compress flag */
+static const size_t BFSize = LZ4F_BLOCK_CHECKSUM_SIZE;  /* block footer : checksum (optional) */
 
 
 /*-************************************
@@ -327,6 +327,7 @@ static size_t LZ4F_compressBound_internal(size_t srcSize,
 {
     LZ4F_preferences_t prefsNull = LZ4F_INIT_PREFERENCES;
     prefsNull.frameInfo.contentChecksumFlag = LZ4F_contentChecksumEnabled;   /* worst case */
+    prefsNull.frameInfo.blockChecksumFlag = LZ4F_blockChecksumEnabled;   /* worst case */
     {   const LZ4F_preferences_t* const prefsPtr = (preferencesPtr==NULL) ? &prefsNull : preferencesPtr;
         U32 const flush = prefsPtr->autoFlush | (srcSize==0);
         LZ4F_blockSizeID_t const blockID = prefsPtr->frameInfo.blockSizeID;
@@ -1130,8 +1131,10 @@ static size_t LZ4F_decodeHeader(LZ4F_dctx* dctx, const void* src, size_t srcSize
     }
 
     /* control magic number */
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
     if (LZ4F_readLE32(srcPtr) != LZ4F_MAGICNUMBER)
         return err0r(LZ4F_ERROR_frameType_unknown);
+#endif
     dctx->frameInfo.frameType = LZ4F_frame;
 
     /* Flags */
@@ -1170,10 +1173,12 @@ static size_t LZ4F_decodeHeader(LZ4F_dctx* dctx, const void* src, size_t srcSize
 
     /* check header */
     assert(frameHeaderSize > 5);
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
     {   BYTE const HC = LZ4F_headerChecksum(srcPtr+4, frameHeaderSize-5);
         if (HC != srcPtr[frameHeaderSize-1])
             return err0r(LZ4F_ERROR_headerChecksum_invalid);
     }
+#endif
 
     /* save */
     dctx->frameInfo.blockMode = (LZ4F_blockMode_t)blockMode;
@@ -1210,8 +1215,10 @@ size_t LZ4F_headerSize(const void* src, size_t srcSize)
         return 8;
 
     /* control magic number */
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
     if (LZ4F_readLE32(src) != LZ4F_MAGICNUMBER)
         return err0r(LZ4F_ERROR_frameType_unknown);
+#endif
 
     /* Frame Header Size */
     {   BYTE const FLG = ((const BYTE*)src)[4];
@@ -1493,7 +1500,7 @@ size_t LZ4F_decompress(LZ4F_dctx* dctx,
                 /* next block is a compressed block */
                 dctx->tmpInTarget = nextCBlockSize + crcSize;
                 dctx->dStage = dstage_getCBlock;
-                if (dstPtr==dstEnd) {
+                if (dstPtr==dstEnd || srcPtr==srcEnd) {
                     nextSrcSizeHint = BHSize + nextCBlockSize + crcSize;
                     doAnotherStage = 0;
                 }
@@ -1554,8 +1561,13 @@ size_t LZ4F_decompress(LZ4F_dctx* dctx,
                 }
                 {   U32 const readCRC = LZ4F_readLE32(crcSrc);
                     U32 const calcCRC = XXH32_digest(&dctx->blockChecksum);
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
                     if (readCRC != calcCRC)
                         return err0r(LZ4F_ERROR_blockChecksum_invalid);
+#else
+                    (void)readCRC;
+                    (void)calcCRC;
+#endif
             }   }
             dctx->dStage = dstage_getBlockHeader;  /* new block */
             break;
@@ -1594,8 +1606,13 @@ size_t LZ4F_decompress(LZ4F_dctx* dctx,
                 assert(selectedIn != NULL);  /* selectedIn is defined at this stage (either srcPtr, or dctx->tmpIn) */
                 {   U32 const readBlockCrc = LZ4F_readLE32(selectedIn + dctx->tmpInTarget);
                     U32 const calcBlockCrc = XXH32(selectedIn, dctx->tmpInTarget, 0);
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
                     if (readBlockCrc != calcBlockCrc)
                         return err0r(LZ4F_ERROR_blockChecksum_invalid);
+#else
+                    (void)readBlockCrc;
+                    (void)calcBlockCrc;
+#endif
             }   }
 
             if ((size_t)(dstEnd-dstPtr) >= dctx->maxBlockSize) {
@@ -1723,8 +1740,13 @@ size_t LZ4F_decompress(LZ4F_dctx* dctx,
         /* case dstage_checkSuffix: */   /* no direct entry, avoid initialization risks */
             {   U32 const readCRC = LZ4F_readLE32(selectedIn);
                 U32 const resultCRC = XXH32_digest(&(dctx->xxh));
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
                 if (readCRC != resultCRC)
                     return err0r(LZ4F_ERROR_contentChecksum_invalid);
+#else
+                (void)readCRC;
+                (void)resultCRC;
+#endif
                 nextSrcSizeHint = 0;
                 LZ4F_resetDecompressionContext(dctx);
                 doAnotherStage = 0;
diff --git a/src/static_libs/lz4/lz4frame.h b/src/static_libs/lz4/lz4frame.h
index 742c2528e0..391e484011 100644
--- a/src/static_libs/lz4/lz4frame.h
+++ b/src/static_libs/lz4/lz4frame.h
@@ -253,6 +253,15 @@ LZ4FLIB_API LZ4F_errorCode_t LZ4F_freeCompressionContext(LZ4F_cctx* cctx);
 #define LZ4F_HEADER_SIZE_MIN  7   /* LZ4 Frame header size can vary, depending on selected paramaters */
 #define LZ4F_HEADER_SIZE_MAX 19
 
+/* Size in bytes of a block header in little-endian format. Highest bit indicates if block data is uncompressed */
+#define LZ4F_BLOCK_HEADER_SIZE 4
+
+/* Size in bytes of a block checksum footer in little-endian format. */
+#define LZ4F_BLOCK_CHECKSUM_SIZE 4
+
+/* Size in bytes of the content checksum. */
+#define LZ4F_CONTENT_CHECKSUM_SIZE 4
+
 /*! LZ4F_compressBegin() :
  *  will write the frame header into dstBuffer.
  *  dstCapacity must be >= LZ4F_HEADER_SIZE_MAX bytes.
diff --git a/src/static_libs/lz4/lz4hc.c b/src/static_libs/lz4/lz4hc.c
index 936f73969e..afadb3f169 100644
--- a/src/static_libs/lz4/lz4hc.c
+++ b/src/static_libs/lz4/lz4hc.c
@@ -151,6 +151,21 @@ int LZ4HC_countBack(const BYTE* const ip, const BYTE* const match,
     return back;
 }
 
+#if defined(_MSC_VER)
+#  define LZ4HC_rotl32(x,r) _rotl(x,r)
+#else
+#  define LZ4HC_rotl32(x,r) ((x << r) | (x >> (32 - r)))
+#endif
+
+
+static U32 LZ4HC_rotatePattern(size_t const rotate, U32 const pattern)
+{
+    size_t const bitsToRotate = (rotate & (sizeof(pattern) - 1)) << 3;
+    if (bitsToRotate == 0)
+        return pattern;
+    return LZ4HC_rotl32(pattern, (int)bitsToRotate);
+}
+
 /* LZ4HC_countPattern() :
  * pattern32 must be a sample of repetitive pattern of length 1, 2 or 4 (but not 3!) */
 static unsigned
@@ -203,6 +218,16 @@ LZ4HC_reverseCountPattern(const BYTE* ip, const BYTE* const iLow, U32 pattern)
     return (unsigned)(iStart - ip);
 }
 
+/* LZ4HC_protectDictEnd() :
+ * Checks if the match is in the last 3 bytes of the dictionary, so reading the
+ * 4 byte MINMATCH would overflow.
+ * @returns true if the match index is okay.
+ */
+static int LZ4HC_protectDictEnd(U32 const dictLimit, U32 const matchIndex)
+{
+    return ((U32)((dictLimit - 1) - matchIndex) >= 3);
+}
+
 typedef enum { rep_untested, rep_not, rep_confirmed } repeat_state_e;
 typedef enum { favorCompressionRatio=0, favorDecompressionSpeed } HCfavor_e;
 
@@ -228,7 +253,7 @@ LZ4HC_InsertAndGetWiderMatch (
     const U32 dictLimit = hc4->dictLimit;
     const BYTE* const lowPrefixPtr = base + dictLimit;
     const U32 ipIndex = (U32)(ip - base);
-    const U32 lowestMatchIndex = (hc4->lowLimit + 64 KB > ipIndex) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX;
+    const U32 lowestMatchIndex = (hc4->lowLimit + (LZ4_DISTANCE_MAX + 1) > ipIndex) ? hc4->lowLimit : ipIndex - LZ4_DISTANCE_MAX;
     const BYTE* const dictBase = hc4->dictBase;
     int const lookBackLength = (int)(ip-iLowLimit);
     int nbAttempts = maxNbAttempts;
@@ -287,14 +312,21 @@ LZ4HC_InsertAndGetWiderMatch (
         if (chainSwap && matchLength==longest) {    /* better match => select a better chain */
             assert(lookBackLength==0);   /* search forward only */
             if (matchIndex + (U32)longest <= ipIndex) {
+                int const kTrigger = 4;
                 U32 distanceToNextMatch = 1;
+                int const end = longest - MINMATCH + 1;
+                int step = 1;
+                int accel = 1 << kTrigger;
                 int pos;
-                for (pos = 0; pos <= longest - MINMATCH; pos++) {
+                for (pos = 0; pos < end; pos += step) {
                     U32 const candidateDist = DELTANEXTU16(chainTable, matchIndex + (U32)pos);
+                    step = (accel++ >> kTrigger);
                     if (candidateDist > distanceToNextMatch) {
                         distanceToNextMatch = candidateDist;
                         matchChainPos = (U32)pos;
-                }   }
+                        accel = 1 << kTrigger;
+                    }
+                }
                 if (distanceToNextMatch > 1) {
                     if (distanceToNextMatch > matchIndex) break;   /* avoid overflow */
                     matchIndex -= distanceToNextMatch;
@@ -313,34 +345,61 @@ LZ4HC_InsertAndGetWiderMatch (
                     } else {
                         repeat = rep_not;
                 }   }
-                if ( (repeat == rep_confirmed)
-                  && (matchCandidateIdx >= dictLimit) ) {   /* same segment only */
-                    const BYTE* const matchPtr = base + matchCandidateIdx;
+                if ( (repeat == rep_confirmed) && (matchCandidateIdx >= lowestMatchIndex)
+                  && LZ4HC_protectDictEnd(dictLimit, matchCandidateIdx) ) {
+                    const int extDict = matchCandidateIdx < dictLimit;
+                    const BYTE* const matchPtr = (extDict ? dictBase : base) + matchCandidateIdx;
                     if (LZ4_read32(matchPtr) == pattern) {  /* good candidate */
-                        size_t const forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iHighLimit, pattern) + sizeof(pattern);
-                        const BYTE* const lowestMatchPtr = (lowPrefixPtr + LZ4_DISTANCE_MAX >= ip) ? lowPrefixPtr : ip - LZ4_DISTANCE_MAX;
-                        size_t const backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern);
-                        size_t const currentSegmentLength = backLength + forwardPatternLength;
-
-                        if ( (currentSegmentLength >= srcPatternLength)   /* current pattern segment large enough to contain full srcPatternLength */
-                          && (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */
-                            matchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength;  /* best position, full pattern, might be followed by more match */
-                        } else {
-                            matchIndex = matchCandidateIdx - (U32)backLength;   /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */
-                            if (lookBackLength==0) {  /* no back possible */
-                                size_t const maxML = MIN(currentSegmentLength, srcPatternLength);
-                                if ((size_t)longest < maxML) {
-                                    assert(base + matchIndex < ip);
-                                    if (ip - (base+matchIndex) > LZ4_DISTANCE_MAX) break;
-                                    assert(maxML < 2 GB);
-                                    longest = (int)maxML;
-                                    *matchpos = base + matchIndex;   /* virtual pos, relative to ip, to retrieve offset */
-                                    *startpos = ip;
+                        const BYTE* const dictStart = dictBase + hc4->lowLimit;
+                        const BYTE* const iLimit = extDict ? dictBase + dictLimit : iHighLimit;
+                        size_t forwardPatternLength = LZ4HC_countPattern(matchPtr+sizeof(pattern), iLimit, pattern) + sizeof(pattern);
+                        if (extDict && matchPtr + forwardPatternLength == iLimit) {
+                            U32 const rotatedPattern = LZ4HC_rotatePattern(forwardPatternLength, pattern);
+                            forwardPatternLength += LZ4HC_countPattern(lowPrefixPtr, iHighLimit, rotatedPattern);
+                        }
+                        {   const BYTE* const lowestMatchPtr = extDict ? dictStart : lowPrefixPtr;
+                            size_t backLength = LZ4HC_reverseCountPattern(matchPtr, lowestMatchPtr, pattern);
+                            size_t currentSegmentLength;
+                            if (!extDict && matchPtr - backLength == lowPrefixPtr && hc4->lowLimit < dictLimit) {
+                                U32 const rotatedPattern = LZ4HC_rotatePattern((U32)(-(int)backLength), pattern);
+                                backLength += LZ4HC_reverseCountPattern(dictBase + dictLimit, dictStart, rotatedPattern);
+                            }
+                            /* Limit backLength not go further than lowestMatchIndex */
+                            backLength = matchCandidateIdx - MAX(matchCandidateIdx - (U32)backLength, lowestMatchIndex);
+                            assert(matchCandidateIdx - backLength >= lowestMatchIndex);
+                            currentSegmentLength = backLength + forwardPatternLength;
+                            /* Adjust to end of pattern if the source pattern fits, otherwise the beginning of the pattern */
+                            if ( (currentSegmentLength >= srcPatternLength)   /* current pattern segment large enough to contain full srcPatternLength */
+                              && (forwardPatternLength <= srcPatternLength) ) { /* haven't reached this position yet */
+                                U32 const newMatchIndex = matchCandidateIdx + (U32)forwardPatternLength - (U32)srcPatternLength;  /* best position, full pattern, might be followed by more match */
+                                if (LZ4HC_protectDictEnd(dictLimit, newMatchIndex))
+                                    matchIndex = newMatchIndex;
+                                else {
+                                    /* Can only happen if started in the prefix */
+                                    assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict);
+                                    matchIndex = dictLimit;
                                 }
-                                {   U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex);
-                                    if (distToNextPattern > matchIndex) break;  /* avoid overflow */
-                                    matchIndex -= distToNextPattern;
-                        }   }   }
+                            } else {
+                                U32 const newMatchIndex = matchCandidateIdx - (U32)backLength;   /* farthest position in current segment, will find a match of length currentSegmentLength + maybe some back */
+                                if (!LZ4HC_protectDictEnd(dictLimit, newMatchIndex)) {
+                                    assert(newMatchIndex >= dictLimit - 3 && newMatchIndex < dictLimit && !extDict);
+                                    matchIndex = dictLimit;
+                                } else {
+                                    matchIndex = newMatchIndex;
+                                    if (lookBackLength==0) {  /* no back possible */
+                                        size_t const maxML = MIN(currentSegmentLength, srcPatternLength);
+                                        if ((size_t)longest < maxML) {
+                                            assert(base + matchIndex != ip);
+                                            if ((size_t)(ip - base) - matchIndex > LZ4_DISTANCE_MAX) break;
+                                            assert(maxML < 2 GB);
+                                            longest = (int)maxML;
+                                            *matchpos = base + matchIndex;   /* virtual pos, relative to ip, to retrieve offset */
+                                            *startpos = ip;
+                                        }
+                                        {   U32 const distToNextPattern = DELTANEXTU16(chainTable, matchIndex);
+                                            if (distToNextPattern > matchIndex) break;  /* avoid overflow */
+                                            matchIndex -= distToNextPattern;
+                        }   }   }   }   }
                         continue;
                 }   }
         }   }   /* PA optimization */
@@ -969,7 +1028,7 @@ int LZ4_loadDictHC (LZ4_streamHC_t* LZ4_streamHCPtr,
               const char* dictionary, int dictSize)
 {
     LZ4HC_CCtx_internal* const ctxPtr = &LZ4_streamHCPtr->internal_donotuse;
-    DEBUGLOG(4, "LZ4_loadDictHC(%p, %p, %d)", LZ4_streamHCPtr, dictionary, dictSize);
+    DEBUGLOG(4, "LZ4_loadDictHC(ctx:%p, dict:%p, dictSize:%d)", LZ4_streamHCPtr, dictionary, dictSize);
     assert(LZ4_streamHCPtr != NULL);
     if (dictSize > 64 KB) {
         dictionary += (size_t)dictSize - 64 KB;
@@ -1005,6 +1064,9 @@ static void LZ4HC_setExternalDict(LZ4HC_CCtx_internal* ctxPtr, const BYTE* newBl
     ctxPtr->base = newBlock - ctxPtr->dictLimit;
     ctxPtr->end  = newBlock;
     ctxPtr->nextToUpdate = ctxPtr->dictLimit;   /* match referencing will resume from there */
+
+    /* cannot reference an extDict and a dictCtx at the same time */
+    ctxPtr->dictCtx = NULL;
 }
 
 static int LZ4_compressHC_continue_generic (LZ4_streamHC_t* LZ4_streamHCPtr,
diff --git a/src/static_libs/lz4/lz4hc.h b/src/static_libs/lz4/lz4hc.h
index cdc6d895ef..44e35bbf6b 100644
--- a/src/static_libs/lz4/lz4hc.h
+++ b/src/static_libs/lz4/lz4hc.h
@@ -336,6 +336,9 @@ LZ4LIB_API void LZ4_resetStreamHC (LZ4_streamHC_t* streamHCPtr, int compressionL
 #ifndef LZ4_HC_SLO_098092834
 #define LZ4_HC_SLO_098092834
 
+#define LZ4_STATIC_LINKING_ONLY   /* LZ4LIB_STATIC_API */
+#include "lz4.h"
+
 #if defined (__cplusplus)
 extern "C" {
 #endif