Merge inbound to mozilla-central. a=merge
authorCosmin Sabou <csabou@mozilla.com>
Thu, 10 May 2018 00:57:27 +0300
changeset 417591 96b37ba12225d580f2b201d26915f88c5cb0d8a6
parent 417585 087157c4e7c3fecfdc0ca1ed64e6289550e53450 (current diff)
parent 417590 b7c092ba3274e11434c42a31dc7303823f65309a (diff)
child 417621 6505db7f437de65a5b158baa8ff890239721d2b8
child 417685 3b3ca6f189ae2981942a77aadb1059ea15e10852
push id33973
push usercsabou@mozilla.com
push dateWed, 09 May 2018 21:57:50 +0000
treeherdermozilla-central@96b37ba12225 [default view] [failures only]
perfherder[talos] [build metrics] [platform microbench] (compared to previous push)
reviewersmerge
milestone62.0a1
first release with
nightly linux32
96b37ba12225 / 62.0a1 / 20180509220105 / files
nightly linux64
96b37ba12225 / 62.0a1 / 20180509220105 / files
nightly mac
96b37ba12225 / 62.0a1 / 20180509220105 / files
nightly win32
96b37ba12225 / 62.0a1 / 20180509220105 / files
nightly win64
96b37ba12225 / 62.0a1 / 20180509220105 / files
last release without
nightly linux32
nightly linux64
nightly mac
nightly win32
nightly win64
releases
nightly linux32
nightly linux64
nightly mac
nightly win32
nightly win64
Merge inbound to mozilla-central. a=merge
--- a/dom/clients/manager/ClientSourceOpChild.cpp
+++ b/dom/clients/manager/ClientSourceOpChild.cpp
@@ -48,22 +48,27 @@ ClientSourceOpChild::DoSourceOp(Method a
   // The ClientSource methods are required to always return a promise.  If
   // they encounter an error they should just immediately resolve or reject
   // the promise as appropriate.
   MOZ_DIAGNOSTIC_ASSERT(promise);
 
   // Capture 'this' is safe here because we disconnect the promise
   // ActorDestroy() which ensures nethier lambda is called if the
   // actor is destroyed before the source operation completes.
+  //
+  // Also capture the promise to ensure it lives until we get a reaction
+  // or the actor starts shutting down and we disconnect our Thenable.
+  // If the ClientSource is doing something async it may throw away the
+  // promise on its side if the global is closed.
   promise->Then(target, __func__,
-    [this] (const mozilla::dom::ClientOpResult& aResult) {
+    [this, promise] (const mozilla::dom::ClientOpResult& aResult) {
       mPromiseRequestHolder.Complete();
       Unused << PClientSourceOpChild::Send__delete__(this, aResult);
     },
-    [this] (nsresult aRv) {
+    [this, promise] (nsresult aRv) {
       mPromiseRequestHolder.Complete();
       Unused << PClientSourceOpChild::Send__delete__(this, aRv);
     })->Track(mPromiseRequestHolder);
 }
 
 void
 ClientSourceOpChild::ActorDestroy(ActorDestroyReason aReason)
 {
--- a/mfbt/lz4.c
+++ b/mfbt/lz4.c
@@ -64,36 +64,40 @@
  *            This method is safe if your compiler supports it, and *generally* as fast or faster than `memcpy`.
  * Method 2 : direct access. This method is portable but violate C standard.
  *            It can generate buggy code on targets which assembly generation depends on alignment.
  *            But in some circumstances, it's the only known way to get the most performance (ie GCC + ARMv6)
  * See https://fastcompression.blogspot.fr/2015/08/accessing-unaligned-memory.html for details.
  * Prefer these methods in priority order (0 > 1 > 2)
  */
 #ifndef LZ4_FORCE_MEMORY_ACCESS   /* can be defined externally */
-#  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__) )
+#  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 LZ4_FORCE_MEMORY_ACCESS 2
-#  elif defined(__INTEL_COMPILER) || defined(__GNUC__)
+#  elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) || defined(__GNUC__)
 #    define LZ4_FORCE_MEMORY_ACCESS 1
 #  endif
 #endif
 
 /*
  * LZ4_FORCE_SW_BITCOUNT
  * Define this parameter if your target system or compiler does not support hardware bit count
  */
-#if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for Windows CE does not support Hardware bit count */
+#if defined(_MSC_VER) && defined(_WIN32_WCE)   /* Visual Studio for WinCE doesn't support Hardware bit count */
 #  define LZ4_FORCE_SW_BITCOUNT
 #endif
 
 
 
 /*-************************************
 *  Dependency
 **************************************/
+#define LZ4_STATIC_LINKING_ONLY
+#define LZ4_DISABLE_DEPRECATE_WARNINGS /* due to LZ4_decompress_safe_withPrefix64k */
 #include "lz4.h"
 /* see also "memory routines" below */
 
 
 /*-************************************
 *  Compiler Options
 **************************************/
 #ifdef _MSC_VER    /* Visual Studio */
@@ -141,28 +145,33 @@
 #endif
 
 #if (defined(__GNUC__) && (__GNUC__ >= 3)) || (defined(__INTEL_COMPILER) && (__INTEL_COMPILER >= 800)) || defined(__clang__)
 #  define expect(expr,value)    (__builtin_expect ((expr),(value)) )
 #else
 #  define expect(expr,value)    (expr)
 #endif
 
+#ifndef likely
 #define likely(expr)     expect((expr) != 0, 1)
+#endif
+#ifndef unlikely
 #define unlikely(expr)   expect((expr) != 0, 0)
+#endif
 
 
 /*-************************************
 *  Memory routines
 **************************************/
 #include <stdlib.h>   /* malloc, calloc, free */
-#define ALLOCATOR(n,s) calloc(n,s)
-#define FREEMEM        free
+#define ALLOC(s)          malloc(s)
+#define ALLOC_AND_ZERO(s) calloc(1,s)
+#define FREEMEM(p)        free(p)
 #include <string.h>   /* memset, memcpy */
-#define MEM_INIT       memset
+#define MEM_INIT(p,v,s)   memset((p),(v),(s))
 
 
 /*-************************************
 *  Basic Types
 **************************************/
 #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
 # include <stdint.h>
   typedef  uint8_t BYTE;
@@ -265,30 +274,25 @@ static void LZ4_writeLE16(void* memPtr, 
         LZ4_write16(memPtr, value);
     } else {
         BYTE* p = (BYTE*)memPtr;
         p[0] = (BYTE) value;
         p[1] = (BYTE)(value>>8);
     }
 }
 
-static void LZ4_copy8(void* dst, const void* src)
-{
-    memcpy(dst,src,8);
-}
-
 /* customized variant of memcpy, which can overwrite up to 8 bytes beyond dstEnd */
 LZ4_FORCE_O2_INLINE_GCC_PPC64LE
 void LZ4_wildCopy(void* dstPtr, const void* srcPtr, void* dstEnd)
 {
     BYTE* d = (BYTE*)dstPtr;
     const BYTE* s = (const BYTE*)srcPtr;
     BYTE* const e = (BYTE*)dstEnd;
 
-    do { LZ4_copy8(d,s); d+=8; s+=8; } while (d<e);
+    do { memcpy(d,s,8); d+=8; s+=8; } while (d<e);
 }
 
 
 /*-************************************
 *  Common Constants
 **************************************/
 #define MINMATCH 4
 
@@ -316,17 +320,17 @@ static const int LZ4_minLength = (MFLIMI
 #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 only *after* variable declarations */
+#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__);             \
@@ -445,20 +449,43 @@ unsigned LZ4_count(const BYTE* pIn, cons
 **************************************/
 static const int LZ4_64Klimit = ((64 KB) + (MFLIMIT-1));
 static const U32 LZ4_skipTrigger = 6;  /* Increase this value ==> compression run slower on incompressible data */
 
 
 /*-************************************
 *  Local Structures and types
 **************************************/
-typedef enum { notLimited = 0, limitedOutput = 1 } limitedOutput_directive;
-typedef enum { byPtr, byU32, byU16 } tableType_t;
+typedef enum { notLimited = 0, limitedOutput = 1, fillOutput = 2 } limitedOutput_directive;
+typedef enum { clearedTable = 0, byPtr, byU32, byU16 } tableType_t;
 
-typedef enum { noDict = 0, withPrefix64k, usingExtDict } dict_directive;
+/**
+ * This enum distinguishes several different modes of accessing previous
+ * content in the stream.
+ *
+ * - noDict        : There is no preceding content.
+ * - withPrefix64k : Table entries up to ctx->dictSize before the current blob
+ *                   blob being compressed are valid and refer to the preceding
+ *                   content (of length ctx->dictSize), which is available
+ *                   contiguously preceding in memory the content currently
+ *                   being compressed.
+ * - usingExtDict  : Like withPrefix64k, but the preceding content is somewhere
+ *                   else in memory, starting at ctx->dictionary with length
+ *                   ctx->dictSize.
+ * - usingDictCtx  : Like usingExtDict, but everything concerning the preceding
+ *                   content is in a separate context, pointed to by
+ *                   ctx->dictCtx. ctx->dictionary, ctx->dictSize, and table
+ *                   entries in the current context that refer to positions
+ *                   preceding the beginning of the current compression are
+ *                   ignored. Instead, ctx->dictCtx->dictionary and ctx->dictCtx
+ *                   ->dictSize describe the location and size of the preceding
+ *                   content, and matches are found by looking in the ctx
+ *                   ->dictCtx->hashTable.
+ */
+typedef enum { noDict = 0, withPrefix64k, usingExtDict, usingDictCtx } dict_directive;
 typedef enum { noDictIssue = 0, dictSmall } dictIssue_directive;
 
 typedef enum { endOnOutputSize = 0, endOnInputSize = 1 } endCondition_directive;
 typedef enum { full = 0, partial = 1 } earlyEnd_directive;
 
 
 /*-************************************
 *  Local Utils
@@ -492,186 +519,373 @@ static U32 LZ4_hash5(U64 sequence, table
 }
 
 LZ4_FORCE_INLINE U32 LZ4_hashPosition(const void* const p, tableType_t const tableType)
 {
     if ((sizeof(reg_t)==8) && (tableType != byU16)) return LZ4_hash5(LZ4_read_ARCH(p), tableType);
     return LZ4_hash4(LZ4_read32(p), tableType);
 }
 
-static void LZ4_putPositionOnHash(const BYTE* p, U32 h, void* tableBase, tableType_t const tableType, const BYTE* srcBase)
+static void LZ4_putIndexOnHash(U32 idx, U32 h, void* tableBase, tableType_t const tableType)
 {
     switch (tableType)
     {
+    default: /* fallthrough */
+    case clearedTable: /* fallthrough */
+    case byPtr: { /* illegal! */ assert(0); return; }
+    case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = idx; return; }
+    case byU16: { U16* hashTable = (U16*) tableBase; assert(idx < 65536); hashTable[h] = (U16)idx; return; }
+    }
+}
+
+static void LZ4_putPositionOnHash(const BYTE* p, U32 h,
+                                  void* tableBase, tableType_t const tableType,
+                            const BYTE* srcBase)
+{
+    switch (tableType)
+    {
+    case clearedTable: { /* illegal! */ assert(0); return; }
     case byPtr: { const BYTE** hashTable = (const BYTE**)tableBase; hashTable[h] = p; return; }
     case byU32: { U32* hashTable = (U32*) tableBase; hashTable[h] = (U32)(p-srcBase); return; }
     case byU16: { U16* hashTable = (U16*) tableBase; hashTable[h] = (U16)(p-srcBase); return; }
     }
 }
 
 LZ4_FORCE_INLINE void LZ4_putPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
 {
     U32 const h = LZ4_hashPosition(p, tableType);
     LZ4_putPositionOnHash(p, h, tableBase, tableType, srcBase);
 }
 
-static const BYTE* LZ4_getPositionOnHash(U32 h, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+/* LZ4_getIndexOnHash() :
+ * Index of match position registered in hash table.
+ * hash position must be calculated by using base+index, or dictBase+index.
+ * 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)
 {
-    if (tableType == byPtr) { const BYTE** hashTable = (const BYTE**) tableBase; return hashTable[h]; }
-    if (tableType == byU32) { const U32* const hashTable = (U32*) tableBase; return hashTable[h] + srcBase; }
-    { const U16* const hashTable = (U16*) tableBase; return hashTable[h] + srcBase; }   /* default, to ensure a return */
+    LZ4_STATIC_ASSERT(LZ4_MEMORY_USAGE > 2);
+    if (tableType == byU32) {
+        const U32* const hashTable = (const U32*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-2)));
+        return hashTable[h];
+    }
+    if (tableType == byU16) {
+        const U16* const hashTable = (const U16*) tableBase;
+        assert(h < (1U << (LZ4_MEMORY_USAGE-1)));
+        return hashTable[h];
+    }
+    assert(0); return 0;  /* forbidden case */
 }
 
-LZ4_FORCE_INLINE const BYTE* LZ4_getPosition(const BYTE* p, void* tableBase, tableType_t tableType, const BYTE* srcBase)
+static const BYTE* LZ4_getPositionOnHash(U32 h, const void* tableBase, tableType_t tableType, const BYTE* srcBase)
+{
+    if (tableType == byPtr) { const BYTE* const* hashTable = (const BYTE* const*) tableBase; return hashTable[h]; }
+    if (tableType == byU32) { const U32* const hashTable = (const U32*) tableBase; return hashTable[h] + srcBase; }
+    { 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)
 {
     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) {
+    /* If the table hasn't been used, it's guaranteed to be zeroed out, and is
+     * therefore safe to use no matter what mode we're in. Otherwise, we figure
+     * out if it's safe to leave as is or whether it needs to be reset.
+     */
+    if (cctx->tableType != clearedTable) {
+        if (cctx->tableType != tableType
+          || (tableType == byU16 && cctx->currentOffset + inputSize >= 0xFFFFU)
+          || (tableType == byU32 && cctx->currentOffset > 1 GB)
+          || tableType == byPtr
+          || inputSize >= 4 KB)
+        {
+            DEBUGLOG(4, "LZ4_prepareTable: Resetting table in %p", cctx);
+            MEM_INIT(cctx->hashTable, 0, LZ4_HASHTABLESIZE);
+            cctx->currentOffset = 0;
+            cctx->tableType = clearedTable;
+        } else {
+            DEBUGLOG(4, "LZ4_prepareTable: Re-use hash table (no reset)");
+        }
+    }
+
+    /* Adding a gap, so all previous entries are > MAX_DISTANCE back, is faster
+     * than compressing without a gap. However, compressing with
+     * currentOffset == 0 is faster still, so we preserve that case.
+     */
+    if (cctx->currentOffset != 0 && tableType == byU32) {
+        DEBUGLOG(5, "LZ4_prepareTable: adding 64KB to currentOffset");
+        cctx->currentOffset += 64 KB;
+    }
+
+    /* Finally, clear history */
+    cctx->dictCtx = NULL;
+    cctx->dictionary = NULL;
+    cctx->dictSize = 0;
+}
 
 /** LZ4_compress_generic() :
     inlined, to ensure branches are decided at compilation time */
 LZ4_FORCE_INLINE int LZ4_compress_generic(
                  LZ4_stream_t_internal* const cctx,
                  const char* const source,
                  char* const dest,
                  const int inputSize,
+                 int *inputConsumed, /* only written when outputLimited == fillOutput */
                  const int maxOutputSize,
                  const limitedOutput_directive outputLimited,
                  const tableType_t tableType,
-                 const dict_directive dict,
+                 const dict_directive dictDirective,
                  const dictIssue_directive dictIssue,
                  const U32 acceleration)
 {
     const BYTE* ip = (const BYTE*) source;
-    const BYTE* base;
+
+    U32 const startIndex = cctx->currentOffset;
+    const BYTE* base = (const BYTE*) source - startIndex;
     const BYTE* lowLimit;
-    const BYTE* const lowRefLimit = ip - cctx->dictSize;
-    const BYTE* const dictionary = cctx->dictionary;
-    const BYTE* const dictEnd = dictionary + cctx->dictSize;
-    const ptrdiff_t dictDelta = dictEnd - (const BYTE*)source;
+
+    const LZ4_stream_t_internal* dictCtx = (const LZ4_stream_t_internal*) cctx->dictCtx;
+    const BYTE* const dictionary =
+        dictDirective == usingDictCtx ? dictCtx->dictionary : cctx->dictionary;
+    const U32 dictSize =
+        dictDirective == usingDictCtx ? dictCtx->dictSize : cctx->dictSize;
+    const U32 dictDelta = (dictDirective == usingDictCtx) ? startIndex - dictCtx->currentOffset : 0;   /* make indexes in dictCtx comparable with index in current context */
+
+    int const maybe_extMem = (dictDirective == usingExtDict) || (dictDirective == usingDictCtx);
+    U32 const prefixIdxLimit = startIndex - dictSize;   /* used when dictDirective == dictSmall */
+    const BYTE* const dictEnd = dictionary + dictSize;
     const BYTE* anchor = (const BYTE*) source;
     const BYTE* const iend = ip + inputSize;
-    const BYTE* const mflimit = iend - MFLIMIT;
+    const BYTE* const mflimitPlusOne = iend - MFLIMIT + 1;
     const BYTE* const matchlimit = iend - LASTLITERALS;
 
+    /* the dictCtx currentOffset is indexed on the start of the dictionary,
+     * while a dictionary in the current context precedes the currentOffset */
+    const BYTE* dictBase = dictDirective == usingDictCtx ?
+        dictionary + dictSize - dictCtx->currentOffset :
+        dictionary + dictSize - startIndex;
+
     BYTE* op = (BYTE*) dest;
     BYTE* const olimit = op + maxOutputSize;
 
+    U32 offset = 0;
     U32 forwardH;
 
+    DEBUGLOG(5, "LZ4_compress_generic: srcSize=%i, tableType=%u", inputSize, tableType);
     /* Init conditions */
+    if (outputLimited == 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) */
-    switch(dict)
-    {
-    case noDict:
-    default:
-        base = (const BYTE*)source;
-        lowLimit = (const BYTE*)source;
-        break;
-    case withPrefix64k:
-        base = (const BYTE*)source - cctx->currentOffset;
-        lowLimit = (const BYTE*)source - cctx->dictSize;
-        break;
-    case usingExtDict:
-        base = (const BYTE*)source - cctx->currentOffset;
-        lowLimit = (const BYTE*)source;
-        break;
+    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);
+
+    lowLimit = (const BYTE*)source - (dictDirective == withPrefix64k ? dictSize : 0);
+
+    /* Update context state */
+    if (dictDirective == usingDictCtx) {
+        /* Subsequent linked blocks can't use the dictionary. */
+        /* Instead, they use the block we just compressed. */
+        cctx->dictCtx = NULL;
+        cctx->dictSize = (U32)inputSize;
+    } else {
+        cctx->dictSize += (U32)inputSize;
     }
-    if ((tableType == byU16) && (inputSize>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
-    if (inputSize<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
+    cctx->currentOffset += (U32)inputSize;
+    cctx->tableType = tableType;
+
+    if (inputSize<LZ4_minLength) goto _last_literals;        /* Input too small, no compression (all literals) */
 
     /* First Byte */
     LZ4_putPosition(ip, cctx->hashTable, tableType, base);
     ip++; forwardH = LZ4_hashPosition(ip, tableType);
 
     /* Main Loop */
     for ( ; ; ) {
-        ptrdiff_t refDelta = 0;
         const BYTE* match;
         BYTE* token;
 
         /* Find a match */
-        {   const BYTE* forwardIp = ip;
+        if (tableType == byPtr) {
+            const BYTE* forwardIp = ip;
             unsigned step = 1;
             unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
             do {
                 U32 const h = forwardH;
                 ip = forwardIp;
                 forwardIp += step;
                 step = (searchMatchNb++ >> LZ4_skipTrigger);
 
-                if (unlikely(forwardIp > mflimit)) goto _last_literals;
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
 
                 match = LZ4_getPositionOnHash(h, cctx->hashTable, tableType, base);
-                if (dict==usingExtDict) {
-                    if (match < (const BYTE*)source) {
-                        refDelta = dictDelta;
-                        lowLimit = dictionary;
-                    } else {
-                        refDelta = 0;
-                        lowLimit = (const BYTE*)source;
-                }   }
                 forwardH = LZ4_hashPosition(forwardIp, tableType);
                 LZ4_putPositionOnHash(ip, h, cctx->hashTable, tableType, base);
 
-            } while ( ((dictIssue==dictSmall) ? (match < lowRefLimit) : 0)
-                || ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
-                || (LZ4_read32(match+refDelta) != LZ4_read32(ip)) );
+            } while ( (match+MAX_DISTANCE < ip)
+                   || (LZ4_read32(match) != LZ4_read32(ip)) );
+
+        } else {   /* byU32, byU16 */
+
+            const BYTE* forwardIp = ip;
+            unsigned step = 1;
+            unsigned searchMatchNb = acceleration << LZ4_skipTrigger;
+            do {
+                U32 const h = forwardH;
+                U32 const current = (U32)(forwardIp - base);
+                U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+                assert(matchIndex <= current);
+                assert(forwardIp - base < (ptrdiff_t)(2 GB - 1));
+                ip = forwardIp;
+                forwardIp += step;
+                step = (searchMatchNb++ >> LZ4_skipTrigger);
+
+                if (unlikely(forwardIp > mflimitPlusOne)) goto _last_literals;
+                assert(ip < mflimitPlusOne);
+
+                if (dictDirective == usingDictCtx) {
+                    if (matchIndex < startIndex) {
+                        /* there was no match, try the dictionary */
+                        assert(tableType == byU32);
+                        matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                        match = dictBase + matchIndex;
+                        matchIndex += dictDelta;   /* make dictCtx index comparable with current context */
+                        lowLimit = dictionary;
+                    } else {
+                        match = base + matchIndex;
+                        lowLimit = (const BYTE*)source;
+                    }
+                } else if (dictDirective==usingExtDict) {
+                    if (matchIndex < startIndex) {
+                        DEBUGLOG(7, "extDict candidate: matchIndex=%5u  <  startIndex=%5u", matchIndex, startIndex);
+                        assert(startIndex - matchIndex >= MINMATCH);
+                        match = dictBase + matchIndex;
+                        lowLimit = dictionary;
+                    } else {
+                        match = base + matchIndex;
+                        lowLimit = (const BYTE*)source;
+                    }
+                } else {   /* single continuous memory segment */
+                    match = base + matchIndex;
+                }
+                forwardH = LZ4_hashPosition(forwardIp, tableType);
+                LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+
+                if ((dictIssue == dictSmall) && (matchIndex < prefixIdxLimit)) continue;    /* match outside of valid area */
+                assert(matchIndex < current);
+                if ((tableType != byU16) && (matchIndex+MAX_DISTANCE < current)) continue;  /* too far */
+                if (tableType == byU16) assert((current - matchIndex) <= MAX_DISTANCE);     /* too_far presumed impossible with byU16 */
+
+                if (LZ4_read32(match) == LZ4_read32(ip)) {
+                    if (maybe_extMem) offset = current - matchIndex;
+                    break;   /* match found */
+                }
+
+            } while(1);
         }
 
         /* Catch up */
-        while (((ip>anchor) & (match+refDelta > lowLimit)) && (unlikely(ip[-1]==match[refDelta-1]))) { ip--; match--; }
+        while (((ip>anchor) & (match > lowLimit)) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
 
         /* Encode Literals */
         {   unsigned const litLength = (unsigned)(ip - anchor);
             token = op++;
-            if ((outputLimited) &&  /* Check output buffer overflow */
+            if ((outputLimited == limitedOutput) &&  /* Check output buffer overflow */
                 (unlikely(op + litLength + (2 + 1 + LASTLITERALS) + (litLength/255) > olimit)))
                 return 0;
+            if ((outputLimited == 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--;
+                goto _last_literals;
+            }
             if (litLength >= RUN_MASK) {
                 int len = (int)litLength-RUN_MASK;
                 *token = (RUN_MASK<<ML_BITS);
                 for(; len >= 255 ; len-=255) *op++ = 255;
                 *op++ = (BYTE)len;
             }
             else *token = (BYTE)(litLength<<ML_BITS);
 
             /* Copy Literals */
             LZ4_wildCopy(op, anchor, op+litLength);
             op+=litLength;
+            DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                        (int)(anchor-(const BYTE*)source), litLength, (int)(ip-(const BYTE*)source));
         }
 
 _next_match:
+        /* at this stage, the following variables must be correctly set :
+         * - ip : at start of LZ operation
+         * - match : at start of previous pattern occurence; can be within current prefix, or within extDict
+         * - offset : if maybe_ext_memSegment==1 (constant)
+         * - lowLimit : must be == dictionary to mean "match is within extDict"; must be == source otherwise
+         * - token and *token : position to write 4-bits for match length; higher 4-bits for literal length supposed already written
+         */
+
+        if ((outputLimited == fillOutput) &&
+            (op + 2 /* offset */ + 1 /* token */ + MFLIMIT - MINMATCH /* min last literals so last match is <= end - MFLIMIT */ > olimit)) {
+            /* the match was too close to the end, rewind and go to last literals */
+            op = token;
+            goto _last_literals;
+        }
+
         /* Encode Offset */
-        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
+        if (maybe_extMem) {   /* static test */
+            DEBUGLOG(6, "             with offset=%u  (ext if > %i)", offset, (int)(ip - (const BYTE*)source));
+            assert(offset <= MAX_DISTANCE && offset > 0);
+            LZ4_writeLE16(op, (U16)offset); op+=2;
+        } else  {
+            DEBUGLOG(6, "             with offset=%u  (same segment)", (U32)(ip - match));
+            assert(ip-match <= MAX_DISTANCE);
+            LZ4_writeLE16(op, (U16)(ip - match)); op+=2;
+        }
 
         /* Encode MatchLength */
         {   unsigned matchCode;
 
-            if ((dict==usingExtDict) && (lowLimit==dictionary)) {
-                const BYTE* limit;
-                match += refDelta;
-                limit = ip + (dictEnd-match);
+            if ( (dictDirective==usingExtDict || dictDirective==usingDictCtx)
+              && (lowLimit==dictionary) /* match within extDict */ ) {
+                const BYTE* limit = ip + (dictEnd-match);
+                assert(dictEnd > match);
                 if (limit > matchlimit) limit = matchlimit;
                 matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, limit);
                 ip += MINMATCH + matchCode;
                 if (ip==limit) {
-                    unsigned const more = LZ4_count(ip, (const BYTE*)source, matchlimit);
+                    unsigned const more = LZ4_count(limit, (const BYTE*)source, matchlimit);
                     matchCode += more;
                     ip += more;
                 }
+                DEBUGLOG(6, "             with matchLength=%u starting in extDict", matchCode+MINMATCH);
             } else {
                 matchCode = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
                 ip += MINMATCH + matchCode;
+                DEBUGLOG(6, "             with matchLength=%u", matchCode+MINMATCH);
             }
 
-            if ( outputLimited &&    /* Check output buffer overflow */
-                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) )
-                return 0;
+            if ((outputLimited) &&    /* Check output buffer overflow */
+                (unlikely(op + (1 + LASTLITERALS) + (matchCode>>8) > olimit)) ) {
+                if (outputLimited == limitedOutput)
+                  return 0;
+                if (outputLimited == 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;
+                    ip -= matchCode - newMatchCode;
+                    matchCode = newMatchCode;
+                }
+            }
             if (matchCode >= ML_MASK) {
                 *token += ML_MASK;
                 matchCode -= ML_MASK;
                 LZ4_write32(op, 0xFFFFFFFF);
                 while (matchCode >= 4*255) {
                     op+=4;
                     LZ4_write32(op, 0xFFFFFFFF);
                     matchCode -= 4*255;
@@ -680,94 +894,190 @@ LZ4_FORCE_INLINE int LZ4_compress_generi
                 *op++ = (BYTE)(matchCode % 255);
             } else
                 *token += (BYTE)(matchCode);
         }
 
         anchor = ip;
 
         /* Test end of chunk */
-        if (ip > mflimit) break;
+        if (ip >= mflimitPlusOne) break;
 
         /* Fill table */
         LZ4_putPosition(ip-2, cctx->hashTable, tableType, base);
 
         /* Test next position */
-        match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
-        if (dict==usingExtDict) {
-            if (match < (const BYTE*)source) {
-                refDelta = dictDelta;
-                lowLimit = dictionary;
-            } else {
-                refDelta = 0;
-                lowLimit = (const BYTE*)source;
-        }   }
-        LZ4_putPosition(ip, cctx->hashTable, tableType, base);
-        if ( ((dictIssue==dictSmall) ? (match>=lowRefLimit) : 1)
-            && (match+MAX_DISTANCE>=ip)
-            && (LZ4_read32(match+refDelta)==LZ4_read32(ip)) )
-        { token=op++; *token=0; goto _next_match; }
+        if (tableType == byPtr) {
+
+            match = LZ4_getPosition(ip, cctx->hashTable, tableType, base);
+            LZ4_putPosition(ip, cctx->hashTable, tableType, base);
+            if ( (match+MAX_DISTANCE >= ip)
+              && (LZ4_read32(match) == LZ4_read32(ip)) )
+            { token=op++; *token=0; goto _next_match; }
+
+        } else {   /* byU32, byU16 */
+
+            U32 const h = LZ4_hashPosition(ip, tableType);
+            U32 const current = (U32)(ip-base);
+            U32 matchIndex = LZ4_getIndexOnHash(h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if (dictDirective == usingDictCtx) {
+                if (matchIndex < startIndex) {
+                    /* there was no match, try the dictionary */
+                    matchIndex = LZ4_getIndexOnHash(h, dictCtx->hashTable, byU32);
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                    matchIndex += dictDelta;
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;  /* required for match length counter */
+                }
+            } else if (dictDirective==usingExtDict) {
+                if (matchIndex < startIndex) {
+                    match = dictBase + matchIndex;
+                    lowLimit = dictionary;   /* required for match length counter */
+                } else {
+                    match = base + matchIndex;
+                    lowLimit = (const BYTE*)source;   /* required for match length counter */
+                }
+            } else {   /* single memory segment */
+                match = base + matchIndex;
+            }
+            LZ4_putIndexOnHash(current, h, cctx->hashTable, tableType);
+            assert(matchIndex < current);
+            if ( ((dictIssue==dictSmall) ? (matchIndex >= prefixIdxLimit) : 1)
+              && ((tableType==byU16) ? 1 : (matchIndex+MAX_DISTANCE >= current))
+              && (LZ4_read32(match) == LZ4_read32(ip)) ) {
+                token=op++;
+                *token=0;
+                if (maybe_extMem) offset = current - matchIndex;
+                DEBUGLOG(6, "seq.start:%i, literals=%u, match.start:%i",
+                            (int)(anchor-(const BYTE*)source), 0, (int)(ip-(const BYTE*)source));
+                goto _next_match;
+            }
+        }
 
         /* Prepare next loop */
         forwardH = LZ4_hashPosition(++ip, tableType);
+
     }
 
 _last_literals:
     /* Encode Last Literals */
-    {   size_t const lastRun = (size_t)(iend - anchor);
+    {   size_t lastRun = (size_t)(iend - anchor);
         if ( (outputLimited) &&  /* Check output buffer overflow */
-            ((op - (BYTE*)dest) + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > (U32)maxOutputSize) )
-            return 0;
+            (op + lastRun + 1 + ((lastRun+255-RUN_MASK)/255) > olimit)) {
+            if (outputLimited == fillOutput) {
+                /* adapt lastRun to fill 'dst' */
+                lastRun  = (olimit-op) - 1;
+                lastRun -= (lastRun+240)/255;
+            }
+            if (outputLimited == limitedOutput)
+                return 0;
+        }
         if (lastRun >= RUN_MASK) {
             size_t accumulator = lastRun - RUN_MASK;
             *op++ = RUN_MASK << ML_BITS;
             for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
             *op++ = (BYTE) accumulator;
         } else {
             *op++ = (BYTE)(lastRun<<ML_BITS);
         }
         memcpy(op, anchor, lastRun);
+        ip = anchor + lastRun;
         op += lastRun;
     }
 
-    /* End */
-    return (int) (((char*)op)-dest);
+    if (outputLimited == fillOutput) {
+        *inputConsumed = (int) (((const char*)ip)-source);
+    }
+    DEBUGLOG(5, "LZ4_compress_generic: compressed %i bytes into %i bytes", inputSize, (int)(((char*)op) - dest));
+    return (int)(((char*)op) - dest);
 }
 
 
 int LZ4_compress_fast_extState(void* state, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
     LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
+    if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
     LZ4_resetStream((LZ4_stream_t*)state);
+    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
+        if (inputSize < LZ4_64Klimit) {
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, byU16, noDict, noDictIssue, acceleration);
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)source > MAX_DISTANCE)) ? byPtr : byU32;
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+        }
+    } else {
+        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 > MAX_DISTANCE)) ? byPtr : byU32;
+            return LZ4_compress_generic(ctx, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+        }
+    }
+}
+
+/**
+ * LZ4_compress_fast_extState_fastReset() :
+ * A variant of LZ4_compress_fast_extState().
+ *
+ * Using this variant avoids an expensive initialization step. It is only safe
+ * to call if the state buffer is known to be correctly initialized already
+ * (see comment in lz4.h on LZ4_resetStream_fast() for a definition of
+ * "correctly initialized").
+ */
+int LZ4_compress_fast_extState_fastReset(void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration)
+{
+    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)state)->internal_donotuse;
     if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
-    if (maxOutputSize >= LZ4_compressBound(inputSize)) {
-        if (inputSize < LZ4_64Klimit)
-            return LZ4_compress_generic(ctx, source, dest, inputSize,             0,    notLimited,                        byU16, noDict, noDictIssue, acceleration);
-        else
-            return LZ4_compress_generic(ctx, source, dest, inputSize,             0,    notLimited, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+    if (dstCapacity >= LZ4_compressBound(srcSize)) {
+        if (srcSize < LZ4_64Klimit) {
+            const tableType_t tableType = byU16;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            if (ctx->currentOffset) {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, dictSmall, acceleration);
+            } else {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+            }
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, 0, notLimited, tableType, noDict, noDictIssue, acceleration);
+        }
     } else {
-        if (inputSize < LZ4_64Klimit)
-            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput,                        byU16, noDict, noDictIssue, acceleration);
-        else
-            return LZ4_compress_generic(ctx, source, dest, inputSize, maxOutputSize, limitedOutput, (sizeof(void*)==8) ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+        if (srcSize < LZ4_64Klimit) {
+            const tableType_t tableType = byU16;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            if (ctx->currentOffset) {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, dictSmall, acceleration);
+            } else {
+                return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+            }
+        } else {
+            const tableType_t tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
+            LZ4_prepareTable(ctx, srcSize, tableType);
+            return LZ4_compress_generic(ctx, src, dst, srcSize, NULL, dstCapacity, limitedOutput, tableType, noDict, noDictIssue, acceleration);
+        }
     }
 }
 
 
 int LZ4_compress_fast(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
+    int result;
 #if (LZ4_HEAPMODE)
-    void* ctxPtr = ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    LZ4_stream_t* ctxPtr = ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    if (ctxPtr == NULL) return 0;
 #else
     LZ4_stream_t ctx;
-    void* const ctxPtr = &ctx;
+    LZ4_stream_t* const ctxPtr = &ctx;
 #endif
-
-    int const result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
+    result = LZ4_compress_fast_extState(ctxPtr, source, dest, inputSize, maxOutputSize, acceleration);
 
 #if (LZ4_HEAPMODE)
     FREEMEM(ctxPtr);
 #endif
     return result;
 }
 
 
@@ -780,201 +1090,46 @@ int LZ4_compress_default(const char* sou
 /* hidden debug function */
 /* strangely enough, gcc generates faster code when this function is uncommented, even if unused */
 int LZ4_compress_fast_force(const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
     LZ4_stream_t ctx;
     LZ4_resetStream(&ctx);
 
     if (inputSize < LZ4_64Klimit)
-        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
+        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, byU16,                        noDict, noDictIssue, acceleration);
     else
-        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration);
+        return LZ4_compress_generic(&ctx.internal_donotuse, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, sizeof(void*)==8 ? byU32 : byPtr, noDict, noDictIssue, acceleration);
 }
 
 
-/*-******************************
-*  *_destSize() variant
-********************************/
-
-static int LZ4_compress_destSize_generic(
-                       LZ4_stream_t_internal* const ctx,
-                 const char* const src,
-                       char* const dst,
-                       int*  const srcSizePtr,
-                 const int targetDstSize,
-                 const tableType_t tableType)
-{
-    const BYTE* ip = (const BYTE*) src;
-    const BYTE* base = (const BYTE*) src;
-    const BYTE* lowLimit = (const BYTE*) src;
-    const BYTE* anchor = ip;
-    const BYTE* const iend = ip + *srcSizePtr;
-    const BYTE* const mflimit = iend - MFLIMIT;
-    const BYTE* const matchlimit = iend - LASTLITERALS;
-
-    BYTE* op = (BYTE*) dst;
-    BYTE* const oend = op + targetDstSize;
-    BYTE* const oMaxLit = op + targetDstSize - 2 /* offset */ - 8 /* because 8+MINMATCH==MFLIMIT */ - 1 /* token */;
-    BYTE* const oMaxMatch = op + targetDstSize - (LASTLITERALS + 1 /* token */);
-    BYTE* const oMaxSeq = oMaxLit - 1 /* token */;
-
-    U32 forwardH;
-
-
-    /* Init conditions */
-    if (targetDstSize < 1) return 0;                                     /* Impossible to store anything */
-    if ((U32)*srcSizePtr > (U32)LZ4_MAX_INPUT_SIZE) return 0;            /* Unsupported input size, too large (or negative) */
-    if ((tableType == byU16) && (*srcSizePtr>=LZ4_64Klimit)) return 0;   /* Size too large (not within 64K limit) */
-    if (*srcSizePtr<LZ4_minLength) goto _last_literals;                  /* Input too small, no compression (all literals) */
-
-    /* First Byte */
-    *srcSizePtr = 0;
-    LZ4_putPosition(ip, ctx->hashTable, tableType, base);
-    ip++; forwardH = LZ4_hashPosition(ip, tableType);
-
-    /* Main Loop */
-    for ( ; ; ) {
-        const BYTE* match;
-        BYTE* token;
-
-        /* Find a match */
-        {   const BYTE* forwardIp = ip;
-            unsigned step = 1;
-            unsigned searchMatchNb = 1 << LZ4_skipTrigger;
-
-            do {
-                U32 h = forwardH;
-                ip = forwardIp;
-                forwardIp += step;
-                step = (searchMatchNb++ >> LZ4_skipTrigger);
-
-                if (unlikely(forwardIp > mflimit)) goto _last_literals;
-
-                match = LZ4_getPositionOnHash(h, ctx->hashTable, tableType, base);
-                forwardH = LZ4_hashPosition(forwardIp, tableType);
-                LZ4_putPositionOnHash(ip, h, ctx->hashTable, tableType, base);
-
-            } while ( ((tableType==byU16) ? 0 : (match + MAX_DISTANCE < ip))
-                || (LZ4_read32(match) != LZ4_read32(ip)) );
-        }
-
-        /* Catch up */
-        while ((ip>anchor) && (match > lowLimit) && (unlikely(ip[-1]==match[-1]))) { ip--; match--; }
-
-        /* Encode Literal length */
-        {   unsigned litLength = (unsigned)(ip - anchor);
-            token = op++;
-            if (op + ((litLength+240)/255) + litLength > oMaxLit) {
-                /* Not enough space for a last match */
-                op--;
-                goto _last_literals;
-            }
-            if (litLength>=RUN_MASK) {
-                unsigned len = litLength - RUN_MASK;
-                *token=(RUN_MASK<<ML_BITS);
-                for(; len >= 255 ; len-=255) *op++ = 255;
-                *op++ = (BYTE)len;
-            }
-            else *token = (BYTE)(litLength<<ML_BITS);
-
-            /* Copy Literals */
-            LZ4_wildCopy(op, anchor, op+litLength);
-            op += litLength;
-        }
-
-_next_match:
-        /* Encode Offset */
-        LZ4_writeLE16(op, (U16)(ip-match)); op+=2;
-
-        /* Encode MatchLength */
-        {   size_t matchLength = LZ4_count(ip+MINMATCH, match+MINMATCH, matchlimit);
-
-            if (op + ((matchLength+240)/255) > oMaxMatch) {
-                /* Match description too long : reduce it */
-                matchLength = (15-1) + (oMaxMatch-op) * 255;
-            }
-            ip += MINMATCH + matchLength;
-
-            if (matchLength>=ML_MASK) {
-                *token += ML_MASK;
-                matchLength -= ML_MASK;
-                while (matchLength >= 255) { matchLength-=255; *op++ = 255; }
-                *op++ = (BYTE)matchLength;
-            }
-            else *token += (BYTE)(matchLength);
-        }
-
-        anchor = ip;
-
-        /* Test end of block */
-        if (ip > mflimit) break;
-        if (op > oMaxSeq) break;
-
-        /* Fill table */
-        LZ4_putPosition(ip-2, ctx->hashTable, tableType, base);
-
-        /* Test next position */
-        match = LZ4_getPosition(ip, ctx->hashTable, tableType, base);
-        LZ4_putPosition(ip, ctx->hashTable, tableType, base);
-        if ( (match+MAX_DISTANCE>=ip)
-            && (LZ4_read32(match)==LZ4_read32(ip)) )
-        { token=op++; *token=0; goto _next_match; }
-
-        /* Prepare next loop */
-        forwardH = LZ4_hashPosition(++ip, tableType);
-    }
-
-_last_literals:
-    /* Encode Last Literals */
-    {   size_t lastRunSize = (size_t)(iend - anchor);
-        if (op + 1 /* token */ + ((lastRunSize+240)/255) /* litLength */ + lastRunSize /* literals */ > oend) {
-            /* adapt lastRunSize to fill 'dst' */
-            lastRunSize  = (oend-op) - 1;
-            lastRunSize -= (lastRunSize+240)/255;
-        }
-        ip = anchor + lastRunSize;
-
-        if (lastRunSize >= RUN_MASK) {
-            size_t accumulator = lastRunSize - RUN_MASK;
-            *op++ = RUN_MASK << ML_BITS;
-            for(; accumulator >= 255 ; accumulator-=255) *op++ = 255;
-            *op++ = (BYTE) accumulator;
-        } else {
-            *op++ = (BYTE)(lastRunSize<<ML_BITS);
-        }
-        memcpy(op, anchor, lastRunSize);
-        op += lastRunSize;
-    }
-
-    /* End */
-    *srcSizePtr = (int) (((const char*)ip)-src);
-    return (int) (((char*)op)-dst);
-}
-
-
+/* Note!: This function leaves the stream in an unclean/broken state!
+ * It is not safe to subsequently use the same state with a _fastReset() or
+ * _continue() call without resetting it. */
 static int LZ4_compress_destSize_extState (LZ4_stream_t* state, const char* src, char* dst, int* srcSizePtr, int targetDstSize)
 {
     LZ4_resetStream(state);
 
     if (targetDstSize >= LZ4_compressBound(*srcSizePtr)) {  /* compression success is guaranteed */
         return LZ4_compress_fast_extState(state, src, dst, *srcSizePtr, targetDstSize, 1);
     } else {
-        if (*srcSizePtr < LZ4_64Klimit)
-            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, byU16);
-        else
-            return LZ4_compress_destSize_generic(&state->internal_donotuse, src, dst, srcSizePtr, targetDstSize, sizeof(void*)==8 ? byU32 : byPtr);
-    }
+        if (*srcSizePtr < LZ4_64Klimit) {
+            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, byU16, noDict, noDictIssue, 1);
+        } else {
+            tableType_t const tableType = ((sizeof(void*)==4) && ((uptrval)src > MAX_DISTANCE)) ? byPtr : byU32;
+            return LZ4_compress_generic(&state->internal_donotuse, src, dst, *srcSizePtr, srcSizePtr, targetDstSize, fillOutput, tableType, noDict, noDictIssue, 1);
+    }   }
 }
 
 
 int LZ4_compress_destSize(const char* src, char* dst, int* srcSizePtr, int targetDstSize)
 {
 #if (LZ4_HEAPMODE)
-    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOCATOR(1, sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    LZ4_stream_t* ctx = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));   /* malloc-calloc always properly aligned */
+    if (ctx == NULL) return 0;
 #else
     LZ4_stream_t ctxBody;
     LZ4_stream_t* ctx = &ctxBody;
 #endif
 
     int result = LZ4_compress_destSize_extState(ctx, src, dst, srcSizePtr, targetDstSize);
 
 #if (LZ4_HEAPMODE)
@@ -986,151 +1141,210 @@ int LZ4_compress_destSize(const char* sr
 
 
 /*-******************************
 *  Streaming functions
 ********************************/
 
 LZ4_stream_t* LZ4_createStream(void)
 {
-    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOCATOR(8, LZ4_STREAMSIZE_U64);
+    LZ4_stream_t* lz4s = (LZ4_stream_t*)ALLOC(sizeof(LZ4_stream_t));
     LZ4_STATIC_ASSERT(LZ4_STREAMSIZE >= sizeof(LZ4_stream_t_internal));    /* A compilation error here means LZ4_STREAMSIZE is not large enough */
+    DEBUGLOG(4, "LZ4_createStream %p", lz4s);
+    if (lz4s == NULL) return NULL;
     LZ4_resetStream(lz4s);
     return lz4s;
 }
 
 void LZ4_resetStream (LZ4_stream_t* LZ4_stream)
 {
-    DEBUGLOG(4, "LZ4_resetStream");
+    DEBUGLOG(5, "LZ4_resetStream (ctx:%p)", LZ4_stream);
     MEM_INIT(LZ4_stream, 0, sizeof(LZ4_stream_t));
 }
 
+void LZ4_resetStream_fast(LZ4_stream_t* ctx) {
+    LZ4_prepareTable(&(ctx->internal_donotuse), 0, byU32);
+}
+
 int LZ4_freeStream (LZ4_stream_t* LZ4_stream)
 {
     if (!LZ4_stream) return 0;   /* support free on NULL */
+    DEBUGLOG(5, "LZ4_freeStream %p", LZ4_stream);
     FREEMEM(LZ4_stream);
     return (0);
 }
 
 
 #define HASH_UNIT sizeof(reg_t)
 int LZ4_loadDict (LZ4_stream_t* LZ4_dict, const char* dictionary, int dictSize)
 {
     LZ4_stream_t_internal* dict = &LZ4_dict->internal_donotuse;
+    const tableType_t tableType = byU32;
     const BYTE* p = (const BYTE*)dictionary;
     const BYTE* const dictEnd = p + dictSize;
     const BYTE* base;
 
-    if ((dict->initCheck) || (dict->currentOffset > 1 GB))  /* Uninitialized structure, or reuse overflow */
-        LZ4_resetStream(LZ4_dict);
+    DEBUGLOG(4, "LZ4_loadDict (%i bytes from %p into %p)", dictSize, dictionary, LZ4_dict);
+
+    /* It's necessary to reset the context,
+     * and not just continue it with prepareTable()
+     * to avoid any risk of generating overflowing matchIndex
+     * when compressing using this dictionary */
+    LZ4_resetStream(LZ4_dict);
+
+    /* We always increment the offset by 64 KB, since, if the dict is longer,
+     * we truncate it to the last 64k, and if it's shorter, we still want to
+     * advance by a whole window length so we can provide the guarantee that
+     * 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) {
-        dict->dictionary = NULL;
-        dict->dictSize = 0;
         return 0;
     }
 
-    if ((dictEnd - p) > 64 KB) p = dictEnd - 64 KB;
-    dict->currentOffset += 64 KB;
-    base = p - dict->currentOffset;
-    dict->dictionary = p;
-    dict->dictSize = (U32)(dictEnd - p);
-    dict->currentOffset += dict->dictSize;
-
     while (p <= dictEnd-HASH_UNIT) {
-        LZ4_putPosition(p, dict->hashTable, byU32, base);
+        LZ4_putPosition(p, dict->hashTable, tableType, base);
         p+=3;
     }
 
     return dict->dictSize;
 }
 
+void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream) {
+    if (dictionary_stream != 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;
+        }
+        working_stream->internal_donotuse.dictCtx = &(dictionary_stream->internal_donotuse);
+    } else {
+        working_stream->internal_donotuse.dictCtx = NULL;
+    }
+}
 
-static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, const BYTE* src)
+
+static void LZ4_renormDictT(LZ4_stream_t_internal* LZ4_dict, int nextSize)
 {
-    if ((LZ4_dict->currentOffset > 0x80000000) ||
-        ((uptrval)LZ4_dict->currentOffset > (uptrval)src)) {   /* address space overflow */
+    if (LZ4_dict->currentOffset + nextSize > 0x80000000) {   /* potential ptrdiff_t overflow (32-bits mode) */
         /* rescale hash table */
         U32 const delta = LZ4_dict->currentOffset - 64 KB;
         const BYTE* dictEnd = LZ4_dict->dictionary + LZ4_dict->dictSize;
         int i;
+        DEBUGLOG(4, "LZ4_renormDictT");
         for (i=0; i<LZ4_HASH_SIZE_U32; i++) {
             if (LZ4_dict->hashTable[i] < delta) LZ4_dict->hashTable[i]=0;
             else LZ4_dict->hashTable[i] -= delta;
         }
         LZ4_dict->currentOffset = 64 KB;
         if (LZ4_dict->dictSize > 64 KB) LZ4_dict->dictSize = 64 KB;
         LZ4_dict->dictionary = dictEnd - LZ4_dict->dictSize;
     }
 }
 
 
 int LZ4_compress_fast_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize, int maxOutputSize, int acceleration)
 {
+    const tableType_t tableType = byU32;
     LZ4_stream_t_internal* streamPtr = &LZ4_stream->internal_donotuse;
-    const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+    const BYTE* dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+
+    DEBUGLOG(5, "LZ4_compress_fast_continue (inputSize=%i)", inputSize);
 
-    const BYTE* smallest = (const BYTE*) source;
     if (streamPtr->initCheck) return 0;   /* Uninitialized structure detected */
-    if ((streamPtr->dictSize>0) && (smallest>dictEnd)) smallest = dictEnd;
-    LZ4_renormDictT(streamPtr, smallest);
+    LZ4_renormDictT(streamPtr, inputSize);   /* avoid index overflow */
     if (acceleration < 1) acceleration = ACCELERATION_DEFAULT;
 
+    /* invalidate tiny dictionaries */
+    if ( (streamPtr->dictSize-1 < 4)   /* intentional underflow */
+      && (dictEnd != (const BYTE*)source) ) {
+        DEBUGLOG(5, "LZ4_compress_fast_continue: dictSize(%u) at addr:%p is too small", streamPtr->dictSize, streamPtr->dictionary);
+        streamPtr->dictSize = 0;
+        streamPtr->dictionary = (const BYTE*)source;
+        dictEnd = (const BYTE*)source;
+    }
+
     /* Check overlapping input/dictionary space */
     {   const BYTE* sourceEnd = (const BYTE*) source + inputSize;
         if ((sourceEnd > streamPtr->dictionary) && (sourceEnd < dictEnd)) {
             streamPtr->dictSize = (U32)(dictEnd - sourceEnd);
             if (streamPtr->dictSize > 64 KB) streamPtr->dictSize = 64 KB;
             if (streamPtr->dictSize < 4) streamPtr->dictSize = 0;
             streamPtr->dictionary = dictEnd - streamPtr->dictSize;
         }
     }
 
     /* prefix mode : source data follows dictionary */
     if (dictEnd == (const BYTE*)source) {
-        int result;
         if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, dictSmall, acceleration);
+            return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, dictSmall, acceleration);
         else
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, withPrefix64k, noDictIssue, acceleration);
-        streamPtr->dictSize += (U32)inputSize;
-        streamPtr->currentOffset += (U32)inputSize;
-        return result;
+            return LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, withPrefix64k, noDictIssue, acceleration);
     }
 
     /* external dictionary mode */
     {   int result;
-        if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset))
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, dictSmall, acceleration);
-        else
-            result = LZ4_compress_generic(streamPtr, source, dest, inputSize, maxOutputSize, limitedOutput, byU32, usingExtDict, noDictIssue, acceleration);
+        if (streamPtr->dictCtx) {
+            /* We depend here on the fact that dictCtx'es (produced by
+             * LZ4_loadDict) guarantee that their tables contain no references
+             * to offsets between dictCtx->currentOffset - 64 KB and
+             * dictCtx->currentOffset - dictCtx->dictSize. This makes it safe
+             * to use noDictIssue even when the dict isn't a full 64 KB.
+             */
+            if (inputSize > 4 KB) {
+                /* For compressing large blobs, it is faster to pay the setup
+                 * cost to copy the dictionary's tables into the active context,
+                 * so that the compression loop is only looking into one table.
+                 */
+                memcpy(streamPtr, streamPtr->dictCtx, sizeof(LZ4_stream_t));
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
+            } else {
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingDictCtx, noDictIssue, acceleration);
+            }
+        } else {
+            if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, dictSmall, acceleration);
+            } else {
+                result = LZ4_compress_generic(streamPtr, source, dest, inputSize, NULL, maxOutputSize, limitedOutput, tableType, usingExtDict, noDictIssue, acceleration);
+            }
+        }
         streamPtr->dictionary = (const BYTE*)source;
         streamPtr->dictSize = (U32)inputSize;
-        streamPtr->currentOffset += (U32)inputSize;
         return result;
     }
 }
 
 
-/* Hidden debug function, to force external dictionary mode */
-int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int inputSize)
+/* Hidden debug function, to force-test external dictionary mode */
+int LZ4_compress_forceExtDict (LZ4_stream_t* LZ4_dict, const char* source, char* dest, int srcSize)
 {
     LZ4_stream_t_internal* streamPtr = &LZ4_dict->internal_donotuse;
     int result;
-    const BYTE* const dictEnd = streamPtr->dictionary + streamPtr->dictSize;
+
+    LZ4_renormDictT(streamPtr, srcSize);
 
-    const BYTE* smallest = dictEnd;
-    if (smallest > (const BYTE*) source) smallest = (const BYTE*) source;
-    LZ4_renormDictT(streamPtr, smallest);
-
-    result = LZ4_compress_generic(streamPtr, source, dest, inputSize, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+    if ((streamPtr->dictSize < 64 KB) && (streamPtr->dictSize < streamPtr->currentOffset)) {
+        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, dictSmall, 1);
+    } else {
+        result = LZ4_compress_generic(streamPtr, source, dest, srcSize, NULL, 0, notLimited, byU32, usingExtDict, noDictIssue, 1);
+    }
 
     streamPtr->dictionary = (const BYTE*)source;
-    streamPtr->dictSize = (U32)inputSize;
-    streamPtr->currentOffset += (U32)inputSize;
+    streamPtr->dictSize = (U32)srcSize;
 
     return result;
 }
 
 
 /*! LZ4_saveDict() :
  *  If previously compressed data block is not guaranteed to remain available at its memory location,
  *  save it into a safer place (char* safeBuffer).
@@ -1191,51 +1405,82 @@ LZ4_FORCE_INLINE int LZ4_decompress_gene
 
     const BYTE* const dictEnd = (const BYTE*)dictStart + dictSize;
     const unsigned inc32table[8] = {0, 1, 2,  1,  0,  4, 4, 4};
     const int      dec64table[8] = {0, 0, 0, -1, -4,  1, 2, 3};
 
     const int safeDecode = (endOnInput==endOnInputSize);
     const int checkOffset = ((safeDecode) && (dictSize < (int)(64 KB)));
 
+    /* Set up the "end" pointers for the shortcut. */
+    const BYTE* const shortiend = iend - (endOnInput ? 14 : 8) /*maxLL*/ - 2 /*offset*/;
+    const BYTE* const shortoend = oend - (endOnInput ? 14 : 8) /*maxLL*/ - 18 /*maxML*/;
+
+    DEBUGLOG(5, "LZ4_decompress_generic (srcSize:%i)", srcSize);
 
     /* Special cases */
     if ((partialDecoding) && (oexit > oend-MFLIMIT)) oexit = oend-MFLIMIT;                      /* targetOutputSize too high => just decode everything */
     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;
 
     /* Main Loop : decode sequences */
     while (1) {
-        size_t length;
         const BYTE* match;
         size_t offset;
 
         unsigned const token = *ip++;
+        size_t length = token >> ML_BITS; /* literal length */
 
-        /* shortcut for common case :
-         * in most circumstances, we expect to decode small matches (<= 18 bytes) separated by few literals (<= 14 bytes).
-         * this shortcut was tested on x86 and x64, where it improves decoding speed.
-         * it has not yet been benchmarked on ARM, Power, mips, etc. */
-        if (((ip + 14 /*maxLL*/ + 2 /*offset*/ <= iend)
-          & (op + 14 /*maxLL*/ + 18 /*maxML*/ <= oend))
-          & ((token < (15<<ML_BITS)) & ((token & ML_MASK) != 15)) ) {
-            size_t const ll = token >> ML_BITS;
-            size_t const off = LZ4_readLE16(ip+ll);
-            const BYTE* const matchPtr = op + ll - off;  /* pointer underflow risk ? */
-            if ((off >= 18) /* do not deal with overlapping matches */ & (matchPtr >= lowPrefix)) {
-                size_t const ml = (token & ML_MASK) + MINMATCH;
-                memcpy(op, ip, 16); op += ll; ip += ll + 2 /*offset*/;
-                memcpy(op, matchPtr, 18); op += ml;
+        assert(!endOnInput || ip <= iend); /* ip < iend before the increment */
+
+        /* A two-stage shortcut for the most common case:
+         * 1) If the literal length is 0..14, and there is enough space,
+         * enter the shortcut and copy 16 bytes on behalf of the literals
+         * (in the fast mode, only 8 bytes can be safely copied this way).
+         * 2) Further if the match length is 4..18, copy 18 bytes in a similar
+         * manner; but we ensure that there's enough space in the output for
+         * those 18 bytes earlier, upon entering the shortcut (in other words,
+         * there is a combined check for both stages).
+         */
+        if ( (endOnInput ? length != RUN_MASK : length <= 8)
+            /* strictly "less than" on input, to re-enter the loop with at least one byte */
+          && likely((endOnInput ? ip < shortiend : 1) & (op <= shortoend)) ) {
+            /* Copy the literals */
+            memcpy(op, ip, endOnInput ? 16 : 8);
+            op += length; ip += length;
+
+            /* The second stage: prepare for match copying, decode full info.
+             * If it doesn't work out, the info won't be wasted. */
+            length = token & ML_MASK; /* match length */
+            offset = LZ4_readLE16(ip); ip += 2;
+            match = op - offset;
+
+            /* Do not deal with overlapping matches. */
+            if ( (length != ML_MASK)
+              && (offset >= 8)
+              && (dict==withPrefix64k || match >= lowPrefix) ) {
+                /* Copy the match. */
+                memcpy(op + 0, match + 0, 8);
+                memcpy(op + 8, match + 8, 8);
+                memcpy(op +16, match +16, 2);
+                op += length + MINMATCH;
+                /* Both stages worked, load the next token. */
                 continue;
             }
+
+            /* The second stage didn't work out, but the info is ready.
+             * Propel it right to the point of match copying. */
+            goto _copy_match;
         }
 
         /* decode literal length */
-        if ((length=(token>>ML_BITS)) == RUN_MASK) {
+        if (length == RUN_MASK) {
             unsigned s;
+            if (unlikely(endOnInput ? ip >= iend-RUN_MASK : 0)) goto _output_error;   /* overflow detection */
             do {
                 s = *ip++;
                 length += s;
             } while ( likely(endOnInput ? ip<iend-RUN_MASK : 1) & (s==255) );
             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 */
         }
 
@@ -1257,21 +1502,24 @@ LZ4_FORCE_INLINE int LZ4_decompress_gene
             break;     /* Necessarily EOF, due to parsing restrictions */
         }
         LZ4_wildCopy(op, ip, cpy);
         ip += length; op = cpy;
 
         /* get offset */
         offset = LZ4_readLE16(ip); ip+=2;
         match = op - offset;
+
+        /* get matchlength */
+        length = token & ML_MASK;
+
+_copy_match:
         if ((checkOffset) && (unlikely(match + dictSize < lowPrefix))) goto _output_error;   /* Error : offset outside buffers */
         LZ4_write32(op, (U32)offset);   /* costs ~1%; silence an msan warning when offset==0 */
 
-        /* get matchlength */
-        length = token & ML_MASK;
         if (length == ML_MASK) {
             unsigned s;
             do {
                 s = *ip++;
                 if ((endOnInput) && (ip > iend-LASTLITERALS)) goto _output_error;
                 length += s;
             } while (s==255);
             if ((safeDecode) && unlikely((uptrval)(op)+length<(uptrval)op)) goto _output_error;   /* overflow detection */
@@ -1308,30 +1556,30 @@ LZ4_FORCE_INLINE int LZ4_decompress_gene
         if (unlikely(offset<8)) {
             op[0] = match[0];
             op[1] = match[1];
             op[2] = match[2];
             op[3] = match[3];
             match += inc32table[offset];
             memcpy(op+4, match, 4);
             match -= dec64table[offset];
-        } else { LZ4_copy8(op, match); match+=8; }
+        } else { memcpy(op, match, 8); match+=8; }
         op += 8;
 
         if (unlikely(cpy>oend-12)) {
             BYTE* const oCopyLimit = oend-(WILDCOPYLENGTH-1);
             if (cpy > oend-LASTLITERALS) goto _output_error;    /* Error : last LASTLITERALS bytes must be literals (uncompressed) */
             if (op < oCopyLimit) {
                 LZ4_wildCopy(op, match, oCopyLimit);
                 match += oCopyLimit - op;
                 op = oCopyLimit;
             }
             while (op<cpy) *op++ = *match++;
         } else {
-            LZ4_copy8(op, match);
+            memcpy(op, match, 8);
             if (length>16) LZ4_wildCopy(op+8, match+8, cpy);
         }
         op = cpy;   /* correction */
     }
 
     /* end of decoding */
     if (endOnInput)
        return (int) (((char*)op)-dst);     /* Nb of output bytes decoded */
@@ -1339,226 +1587,329 @@ LZ4_FORCE_INLINE int LZ4_decompress_gene
        return (int) (((const char*)ip)-src);   /* Nb of input bytes read */
 
     /* Overflow error detected */
 _output_error:
     return (int) (-(((const char*)ip)-src))-1;
 }
 
 
+/*===== Instantiate the API decoding functions. =====*/
+
 LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_safe(const char* source, char* dest, int compressedSize, int maxDecompressedSize)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, full, 0, noDict, (BYTE*)dest, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+                                  endOnInputSize, full, 0, noDict,
+                                  (BYTE*)dest, NULL, 0);
 }
 
 LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_safe_partial(const char* source, char* dest, int compressedSize, int targetOutputSize, int maxDecompressedSize)
 {
-    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize, endOnInputSize, partial, targetOutputSize, noDict, (BYTE*)dest, NULL, 0);
+    return LZ4_decompress_generic(source, dest, compressedSize, maxDecompressedSize,
+                                  endOnInputSize, partial, targetOutputSize,
+                                  noDict, (BYTE*)dest, NULL, 0);
 }
 
 LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_fast(const char* source, char* dest, int originalSize)
 {
-    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)(dest - 64 KB), NULL, 64 KB);
+    return LZ4_decompress_generic(source, dest, 0, originalSize,
+                                  endOnOutputSize, full, 0, withPrefix64k,
+                                  (BYTE*)dest - 64 KB, NULL, 0);
+}
+
+/*===== Instantiate a few more decoding cases, used more than once. =====*/
+
+LZ4_FORCE_O2_GCC_PPC64LE /* Exported, an obsolete API function. */
+int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  endOnInputSize, full, 0, withPrefix64k,
+                                  (BYTE*)dest - 64 KB, NULL, 0);
+}
+
+/* Another obsolete API function, paired with the previous one. */
+int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
+{
+    /* LZ4_decompress_fast doesn't validate match offsets,
+     * and thus serves well with any prefixed dictionary. */
+    return LZ4_decompress_fast(source, dest, originalSize);
+}
+
+LZ4_FORCE_O2_GCC_PPC64LE
+static int LZ4_decompress_safe_withSmallPrefix(const char* source, char* dest, int compressedSize, int maxOutputSize,
+                                               size_t prefixSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  endOnInputSize, full, 0, noDict,
+                                  (BYTE*)dest-prefixSize, NULL, 0);
 }
 
+LZ4_FORCE_O2_GCC_PPC64LE /* Exported under another name, for tests/fullbench.c */
+#define LZ4_decompress_safe_extDict LZ4_decompress_safe_forceExtDict
+int LZ4_decompress_safe_extDict(const char* source, char* dest, int compressedSize, int maxOutputSize,
+                                const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  endOnInputSize, full, 0, usingExtDict,
+                                  (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+LZ4_FORCE_O2_GCC_PPC64LE
+static int LZ4_decompress_fast_extDict(const char* source, char* dest, int originalSize,
+                                       const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_generic(source, dest, 0, originalSize,
+                                  endOnOutputSize, full, 0, usingExtDict,
+                                  (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+}
+
+/* The "double dictionary" mode, for use with e.g. ring buffers: the first part
+ * of the dictionary is passed as prefix, and the second via dictStart + dictSize.
+ * These routines are used only once, in LZ4_decompress_*_continue().
+ */
+LZ4_FORCE_INLINE
+int LZ4_decompress_safe_doubleDict(const char* source, char* dest, int compressedSize, int maxOutputSize,
+                                   size_t prefixSize, const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
+                                  endOnInputSize, full, 0, usingExtDict,
+                                  (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
+}
+
+LZ4_FORCE_INLINE
+int LZ4_decompress_fast_doubleDict(const char* source, char* dest, int originalSize,
+                                   size_t prefixSize, const void* dictStart, size_t dictSize)
+{
+    return LZ4_decompress_generic(source, dest, 0, originalSize,
+                                  endOnOutputSize, full, 0, usingExtDict,
+                                  (BYTE*)dest-prefixSize, (const BYTE*)dictStart, dictSize);
+}
 
 /*===== streaming decompression functions =====*/
 
 LZ4_streamDecode_t* LZ4_createStreamDecode(void)
 {
-    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOCATOR(1, sizeof(LZ4_streamDecode_t));
+    LZ4_streamDecode_t* lz4s = (LZ4_streamDecode_t*) ALLOC_AND_ZERO(sizeof(LZ4_streamDecode_t));
     return lz4s;
 }
 
 int LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream)
 {
     if (!LZ4_stream) return 0;   /* support free on NULL */
     FREEMEM(LZ4_stream);
     return 0;
 }
 
-/*!
- * LZ4_setStreamDecode() :
- * Use this function to instruct where to find the dictionary.
- * This function is not necessary if previous data is still available where it was decoded.
- * Loading a size of 0 is allowed (same effect as no dictionary).
- * Return : 1 if OK, 0 if error
+/*! LZ4_setStreamDecode() :
+ *  Use this function to instruct where to find the dictionary.
+ *  This function is not necessary if previous data is still available where it was decoded.
+ *  Loading a size of 0 is allowed (same effect as no dictionary).
+ * @return : 1 if OK, 0 if error
  */
 int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize)
 {
     LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
     lz4sd->prefixSize = (size_t) dictSize;
     lz4sd->prefixEnd = (const BYTE*) dictionary + dictSize;
     lz4sd->externalDict = NULL;
     lz4sd->extDictSize  = 0;
     return 1;
 }
 
+/*! LZ4_decoderRingBufferSize() :
+ *  when setting a ring buffer for streaming decompression (optional scenario),
+ *  provides the minimum size of this ring buffer
+ *  to be compatible with any source respecting maxBlockSize condition.
+ *  Note : in a ring buffer scenario,
+ *  blocks are presumed decompressed next to each other.
+ *  When not enough space remains for next block (remainingSize < maxBlockSize),
+ *  decoding resumes from beginning of ring buffer.
+ * @return : minimum ring buffer size,
+ *           or 0 if there is an error (invalid maxBlockSize).
+ */
+int LZ4_decoderRingBufferSize(int maxBlockSize)
+{
+    if (maxBlockSize < 0) return 0;
+    if (maxBlockSize > LZ4_MAX_INPUT_SIZE) return 0;
+    if (maxBlockSize < 16) maxBlockSize = 16;
+    return LZ4_DECODER_RING_BUFFER_SIZE(maxBlockSize);
+}
+
 /*
 *_continue() :
     These decoding functions allow decompression of multiple blocks in "streaming" mode.
     Previously decoded blocks must still be available at the memory position where they were decoded.
     If it's not possible, save the relevant part of decoded data into a safe buffer,
     and indicate where it stands using LZ4_setStreamDecode()
 */
 LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int compressedSize, int maxOutputSize)
 {
     LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
     int result;
 
-    if (lz4sd->prefixEnd == (BYTE*)dest) {
-        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
-                                        endOnInputSize, full, 0,
-                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+    if (lz4sd->prefixSize == 0) {
+        /* The first call, no dictionary yet. */
+        assert(lz4sd->extDictSize == 0);
+        result = LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = result;
+        lz4sd->prefixEnd = (BYTE*)dest + result;
+    } else if (lz4sd->prefixEnd == (BYTE*)dest) {
+        /* They're rolling the current segment. */
+        if (lz4sd->prefixSize >= 64 KB - 1)
+            result = LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
+        else if (lz4sd->extDictSize == 0)
+            result = LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize,
+                                                         lz4sd->prefixSize);
+        else
+            result = LZ4_decompress_safe_doubleDict(source, dest, compressedSize, maxOutputSize,
+                                                    lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
         lz4sd->prefixSize += result;
         lz4sd->prefixEnd  += result;
     } else {
+        /* The buffer wraps around, or they're switching to another buffer. */
         lz4sd->extDictSize = lz4sd->prefixSize;
         lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
-        result = LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize,
-                                        endOnInputSize, full, 0,
-                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+        result = LZ4_decompress_safe_extDict(source, dest, compressedSize, maxOutputSize,
+                                             lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
         lz4sd->prefixSize = result;
         lz4sd->prefixEnd  = (BYTE*)dest + result;
     }
 
     return result;
 }
 
 LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* source, char* dest, int originalSize)
 {
     LZ4_streamDecode_t_internal* lz4sd = &LZ4_streamDecode->internal_donotuse;
     int result;
 
-    if (lz4sd->prefixEnd == (BYTE*)dest) {
-        result = LZ4_decompress_generic(source, dest, 0, originalSize,
-                                        endOnOutputSize, full, 0,
-                                        usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
+    if (lz4sd->prefixSize == 0) {
+        assert(lz4sd->extDictSize == 0);
+        result = LZ4_decompress_fast(source, dest, originalSize);
+        if (result <= 0) return result;
+        lz4sd->prefixSize = originalSize;
+        lz4sd->prefixEnd = (BYTE*)dest + originalSize;
+    } else if (lz4sd->prefixEnd == (BYTE*)dest) {
+        if (lz4sd->prefixSize >= 64 KB - 1 || lz4sd->extDictSize == 0)
+            result = LZ4_decompress_fast(source, dest, originalSize);
+        else
+            result = LZ4_decompress_fast_doubleDict(source, dest, originalSize,
+                                                    lz4sd->prefixSize, lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
         lz4sd->prefixSize += originalSize;
         lz4sd->prefixEnd  += originalSize;
     } else {
         lz4sd->extDictSize = lz4sd->prefixSize;
         lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
-        result = LZ4_decompress_generic(source, dest, 0, originalSize,
-                                        endOnOutputSize, full, 0,
-                                        usingExtDict, (BYTE*)dest, lz4sd->externalDict, lz4sd->extDictSize);
+        result = LZ4_decompress_fast_extDict(source, dest, originalSize,
+                                             lz4sd->externalDict, lz4sd->extDictSize);
         if (result <= 0) return result;
         lz4sd->prefixSize = originalSize;
         lz4sd->prefixEnd  = (BYTE*)dest + originalSize;
     }
 
     return result;
 }
 
 
 /*
 Advanced decoding functions :
 *_usingDict() :
     These decoding functions work the same as "_continue" ones,
     the dictionary must be explicitly provided within parameters
 */
 
-LZ4_FORCE_O2_GCC_PPC64LE
-LZ4_FORCE_INLINE int LZ4_decompress_usingDict_generic(const char* source, char* dest, int compressedSize, int maxOutputSize, int safe, const char* dictStart, int dictSize)
+int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
 {
     if (dictSize==0)
-        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest, NULL, 0);
+        return LZ4_decompress_safe(source, dest, compressedSize, maxOutputSize);
     if (dictStart+dictSize == dest) {
-        if (dictSize >= (int)(64 KB - 1))
-            return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, withPrefix64k, (BYTE*)dest-64 KB, NULL, 0);
-        return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, noDict, (BYTE*)dest-dictSize, NULL, 0);
+        if (dictSize >= 64 KB - 1)
+            return LZ4_decompress_safe_withPrefix64k(source, dest, compressedSize, maxOutputSize);
+        return LZ4_decompress_safe_withSmallPrefix(source, dest, compressedSize, maxOutputSize, dictSize);
     }
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, safe, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+    return LZ4_decompress_safe_extDict(source, dest, compressedSize, maxOutputSize, dictStart, dictSize);
 }
 
-LZ4_FORCE_O2_GCC_PPC64LE
-int LZ4_decompress_safe_usingDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
-{
-    return LZ4_decompress_usingDict_generic(source, dest, compressedSize, maxOutputSize, 1, dictStart, dictSize);
-}
-
-LZ4_FORCE_O2_GCC_PPC64LE
 int LZ4_decompress_fast_usingDict(const char* source, char* dest, int originalSize, const char* dictStart, int dictSize)
 {
-    return LZ4_decompress_usingDict_generic(source, dest, 0, originalSize, 0, dictStart, dictSize);
-}
-
-/* debug function */
-LZ4_FORCE_O2_GCC_PPC64LE
-int LZ4_decompress_safe_forceExtDict(const char* source, char* dest, int compressedSize, int maxOutputSize, const char* dictStart, int dictSize)
-{
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, usingExtDict, (BYTE*)dest, (const BYTE*)dictStart, dictSize);
+    if (dictSize==0 || dictStart+dictSize == dest)
+        return LZ4_decompress_fast(source, dest, originalSize);
+    return LZ4_decompress_fast_extDict(source, dest, originalSize, dictStart, dictSize);
 }
 
 
 /*=*************************************************
 *  Obsolete Functions
 ***************************************************/
 /* obsolete compression functions */
-int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize) { return LZ4_compress_default(source, dest, inputSize, maxOutputSize); }
-int LZ4_compress(const char* source, char* dest, int inputSize) { return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize)); }
-int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1); }
-int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize) { return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1); }
-int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int maxDstSize) { return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, maxDstSize, 1); }
-int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize) { return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1); }
+int LZ4_compress_limitedOutput(const char* source, char* dest, int inputSize, int maxOutputSize)
+{
+    return LZ4_compress_default(source, dest, inputSize, maxOutputSize);
+}
+int LZ4_compress(const char* source, char* dest, int inputSize)
+{
+    return LZ4_compress_default(source, dest, inputSize, LZ4_compressBound(inputSize));
+}
+int LZ4_compress_limitedOutput_withState (void* state, const char* src, char* dst, int srcSize, int dstSize)
+{
+    return LZ4_compress_fast_extState(state, src, dst, srcSize, dstSize, 1);
+}
+int LZ4_compress_withState (void* state, const char* src, char* dst, int srcSize)
+{
+    return LZ4_compress_fast_extState(state, src, dst, srcSize, LZ4_compressBound(srcSize), 1);
+}
+int LZ4_compress_limitedOutput_continue (LZ4_stream_t* LZ4_stream, const char* src, char* dst, int srcSize, int dstCapacity)
+{
+    return LZ4_compress_fast_continue(LZ4_stream, src, dst, srcSize, dstCapacity, 1);
+}
+int LZ4_compress_continue (LZ4_stream_t* LZ4_stream, const char* source, char* dest, int inputSize)
+{
+    return LZ4_compress_fast_continue(LZ4_stream, source, dest, inputSize, LZ4_compressBound(inputSize), 1);
+}
 
 /*
-These function names are deprecated and should no longer be used.
+These decompression functions are deprecated and should no longer be used.
 They are only provided here for compatibility with older user programs.
 - LZ4_uncompress is totally equivalent to LZ4_decompress_fast
 - LZ4_uncompress_unknownOutputSize is totally equivalent to LZ4_decompress_safe
 */
-int LZ4_uncompress (const char* source, char* dest, int outputSize) { return LZ4_decompress_fast(source, dest, outputSize); }
-int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize) { return LZ4_decompress_safe(source, dest, isize, maxOutputSize); }
-
+int LZ4_uncompress (const char* source, char* dest, int outputSize)
+{
+    return LZ4_decompress_fast(source, dest, outputSize);
+}
+int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize)
+{
+    return LZ4_decompress_safe(source, dest, isize, maxOutputSize);
+}
 
 /* Obsolete Streaming functions */
 
 int LZ4_sizeofStreamState() { return LZ4_STREAMSIZE; }
 
-static void LZ4_init(LZ4_stream_t* lz4ds, BYTE* base)
-{
-    MEM_INIT(lz4ds, 0, sizeof(LZ4_stream_t));
-    lz4ds->internal_donotuse.bufferStart = base;
-}
-
 int LZ4_resetStreamState(void* state, char* inputBuffer)
 {
-    if ((((uptrval)state) & 3) != 0) return 1;   /* Error : pointer is not aligned on 4-bytes boundary */
-    LZ4_init((LZ4_stream_t*)state, (BYTE*)inputBuffer);
+    (void)inputBuffer;
+    LZ4_resetStream((LZ4_stream_t*)state);
     return 0;
 }
 
 void* LZ4_create (char* inputBuffer)
 {
-    LZ4_stream_t* lz4ds = (LZ4_stream_t*)ALLOCATOR(8, sizeof(LZ4_stream_t));
-    LZ4_init (lz4ds, (BYTE*)inputBuffer);
-    return lz4ds;
+    (void)inputBuffer;
+    return LZ4_createStream();
 }
 
-char* LZ4_slideInputBuffer (void* LZ4_Data)
+char* LZ4_slideInputBuffer (void* state)
 {
-    LZ4_stream_t_internal* ctx = &((LZ4_stream_t*)LZ4_Data)->internal_donotuse;
-    int dictSize = LZ4_saveDict((LZ4_stream_t*)LZ4_Data, (char*)ctx->bufferStart, 64 KB);
-    return (char*)(ctx->bufferStart + dictSize);
-}
-
-/* Obsolete streaming decompression functions */
-
-int LZ4_decompress_safe_withPrefix64k(const char* source, char* dest, int compressedSize, int maxOutputSize)
-{
-    return LZ4_decompress_generic(source, dest, compressedSize, maxOutputSize, endOnInputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
-}
-
-int LZ4_decompress_fast_withPrefix64k(const char* source, char* dest, int originalSize)
-{
-    return LZ4_decompress_generic(source, dest, 0, originalSize, endOnOutputSize, full, 0, withPrefix64k, (BYTE*)dest - 64 KB, NULL, 64 KB);
+    /* avoid const char * -> char * conversion warning */
+    return (char *)(uptrval)((LZ4_stream_t*)state)->internal_donotuse.dictionary;
 }
 
 #endif   /* LZ4_COMMONDEFS_ONLY */
--- a/mfbt/lz4.h
+++ b/mfbt/lz4.h
@@ -88,98 +88,97 @@ extern "C" {
 #  define LZ4LIB_API __declspec(dllimport) LZ4LIB_VISIBILITY /* It isn't required but allows to generate better code, saving a function pointer load from the IAT and an indirect jump.*/
 #else
 #  define LZ4LIB_API LZ4LIB_VISIBILITY
 #endif
 
 /*------   Version   ------*/
 #define LZ4_VERSION_MAJOR    1    /* for breaking interface changes  */
 #define LZ4_VERSION_MINOR    8    /* 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)
 
 #define LZ4_LIB_VERSION LZ4_VERSION_MAJOR.LZ4_VERSION_MINOR.LZ4_VERSION_RELEASE
 #define LZ4_QUOTE(str) #str
 #define LZ4_EXPAND_AND_QUOTE(str) LZ4_QUOTE(str)
 #define LZ4_VERSION_STRING LZ4_EXPAND_AND_QUOTE(LZ4_LIB_VERSION)
 
-LZ4LIB_API int LZ4_versionNumber (void);  /**< library version number; to be used when checking dll version */
-LZ4LIB_API const char* LZ4_versionString (void);   /**< library version string; to be used when checking dll version */
+LZ4LIB_API int LZ4_versionNumber (void);  /**< library version number; useful to check dll version */
+LZ4LIB_API const char* LZ4_versionString (void);   /**< library version string; unseful to check dll version */
 
 
 /*-************************************
 *  Tuning parameter
 **************************************/
 /*!
  * LZ4_MEMORY_USAGE :
  * Memory usage formula : N->2^N Bytes (examples : 10 -> 1KB; 12 -> 4KB ; 16 -> 64KB; 20 -> 1MB; etc.)
  * Increasing memory usage improves compression ratio
- * Reduced memory usage can improve speed, due to cache effect
+ * Reduced memory usage may improve speed, thanks to cache effect
  * Default value is 14, for 16KB, which nicely fits into Intel x86 L1 cache
  */
 #ifndef LZ4_MEMORY_USAGE
 # define LZ4_MEMORY_USAGE 14
 #endif
 
 /*-************************************
 *  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 limited 'dst' budget,
+    If the function cannot compress 'src' into a more limited 'dst' budget,
     compression stops *immediately*, and the function result is zero.
-    As a consequence, 'dst' content is not valid.
-    This function never writes outside 'dst' buffer, nor read outside 'source' buffer.
-        srcSize : supported max value is LZ4_MAX_INPUT_VALUE
-        dstCapacity : full or partial size of buffer 'dst' (which must be already allocated)
+    Note : as a consequence, 'dst' content is not valid.
+    Note 2 : This function is protected against buffer overflow scenarios (never writes outside 'dst' buffer, nor read outside 'source' buffer).
+        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 */
 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.
-             This function is protected against buffer overflow exploits, including malicious data packets.
-             It never writes outside output buffer, nor reads outside input buffer.
+             This function is protected against malicious data packets.
 */
 LZ4LIB_API int LZ4_decompress_safe (const char* src, char* dst, int compressedSize, int dstCapacity);
 
 
 /*-************************************
 *  Advanced Functions
 **************************************/
 #define LZ4_MAX_INPUT_SIZE        0x7E000000   /* 2 113 929 216 bytes */
 #define LZ4_COMPRESSBOUND(isize)  ((unsigned)(isize) > (unsigned)LZ4_MAX_INPUT_SIZE ? 0 : (isize) + ((isize)/255) + 16)
 
 /*!
 LZ4_compressBound() :
     Provides the maximum size that LZ4 compression may output in a "worst case" scenario (input data not compressible)
     This function is primarily useful for memory allocation purposes (destination buffer size).
     Macro LZ4_COMPRESSBOUND() is also provided for compilation-time evaluation (stack memory allocation for example).
-    Note that LZ4_compress_default() compress faster when dest buffer size is >= LZ4_compressBound(srcSize)
+    Note that LZ4_compress_default() compresses faster when dstCapacity is >= LZ4_compressBound(srcSize)
         inputSize  : max supported value is LZ4_MAX_INPUT_SIZE
         return : maximum output size in a "worst case" scenario
-              or 0, if input size is too large ( > LZ4_MAX_INPUT_SIZE)
+              or 0, if input size is incorrect (too large or negative)
 */
 LZ4LIB_API int LZ4_compressBound(int inputSize);
 
 /*!
 LZ4_compress_fast() :
-    Same as LZ4_compress_default(), but allows to select an "acceleration" factor.
+    Same as LZ4_compress_default(), but allows selection of "acceleration" factor.
     The larger the acceleration value, the faster the algorithm, but also the lesser the compression.
     It's a trade-off. It can be fine tuned, with each successive value providing roughly +~3% to speed.
     An acceleration value of "1" is the same as regular LZ4_compress_default()
-    Values <= 0 will be replaced by ACCELERATION_DEFAULT (see lz4.c), which is 1.
+    Values <= 0 will be replaced by ACCELERATION_DEFAULT (currently == 1, see lz4.c).
 */
 LZ4LIB_API int LZ4_compress_fast (const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
 
 
 /*!
 LZ4_compress_fast_extState() :
     Same compression function, just using an externally allocated memory space to store compression state.
     Use LZ4_sizeofState() to know how much memory must be allocated,
@@ -200,47 +199,51 @@ LZ4_compress_destSize() :
                       New value is necessarily <= old value.
         return : Nb bytes written into 'dst' (necessarily <= targetDestSize)
                  or 0 if compression fails
 */
 LZ4LIB_API int LZ4_compress_destSize (const char* src, char* dst, int* srcSizePtr, int targetDstSize);
 
 
 /*!
-LZ4_decompress_fast() : (unsafe!!)
-    originalSize : is the original uncompressed size
-    return : the number of bytes read from the source buffer (in other words, the compressed size)
-             If the source stream is detected malformed, the function will stop decoding and return a negative result.
-             Destination buffer must be already allocated. Its size must be >= 'originalSize' bytes.
-    note : This function respects memory boundaries for *properly formed* compressed data.
-           It is a bit faster than LZ4_decompress_safe().
-           However, it does not provide any protection against intentionally modified data stream (malicious input).
-           Use this function in trusted environment only (data to decode comes from a trusted source).
+LZ4_decompress_fast() : **unsafe!**
+This function is a bit faster than LZ4_decompress_safe(),
+but it may misbehave on malformed input because it doesn't perform full validation of compressed data.
+    originalSize : is the uncompressed size to regenerate
+                   Destination buffer must be already allocated, and its size must be >= 'originalSize' bytes.
+    return : number of bytes read from source buffer (== compressed size).
+             If the source stream is detected malformed, the function stops decoding and return a negative result.
+    note : This function is only usable if the originalSize of uncompressed data is known in advance.
+           The caller should also check that all the compressed input has been consumed properly,
+           i.e. that the return value matches the size of the buffer with compressed input.
+           The function never writes past the output buffer.  However, since it doesn't know its 'src' size,
+           it may read past the intended input.  Also, because match offsets are not validated during decoding,
+           reads from 'src' may underflow.  Use this function in trusted environment **only**.
 */
 LZ4LIB_API int LZ4_decompress_fast (const char* src, char* dst, int originalSize);
 
 /*!
 LZ4_decompress_safe_partial() :
     This function decompress a compressed block of size 'srcSize' at position 'src'
     into destination buffer 'dst' of size 'dstCapacity'.
     The function will decompress a minimum of 'targetOutputSize' bytes, and stop after that.
-    However, it's not accurate, and may write more than 'targetOutputSize' (but <= dstCapacity).
+    However, it's not accurate, and may write more than 'targetOutputSize' (but always <= dstCapacity).
    @return : the number of bytes decoded in the destination buffer (necessarily <= dstCapacity)
-       Note : this number can be < 'targetOutputSize' should the compressed block contain less data.
-             Always control how many bytes were decoded.
-             If the source stream is detected malformed, the function will stop decoding and return a negative result.
-             This function never writes outside of output buffer, and never reads outside of input buffer. It is therefore protected against malicious data packets.
+        Note : this number can also be < targetOutputSize, if compressed block contains less data.
+            Therefore, always control how many bytes were decoded.
+            If source stream is detected malformed, function returns a negative result.
+            This function is protected against malicious data packets.
 */
 LZ4LIB_API int LZ4_decompress_safe_partial (const char* src, char* dst, int srcSize, int targetOutputSize, int dstCapacity);
 
 
 /*-*********************************************
 *  Streaming Compression Functions
 ***********************************************/
-typedef union LZ4_stream_u LZ4_stream_t;   /* incomplete type (defined later) */
+typedef union LZ4_stream_u LZ4_stream_t;  /* incomplete type (defined later) */
 
 /*! LZ4_createStream() and LZ4_freeStream() :
  *  LZ4_createStream() will allocate and initialize an `LZ4_stream_t` structure.
  *  LZ4_freeStream() releases its memory.
  */
 LZ4LIB_API LZ4_stream_t* LZ4_createStream(void);
 LZ4LIB_API int           LZ4_freeStream (LZ4_stream_t* streamPtr);
 
@@ -254,134 +257,253 @@ LZ4LIB_API void LZ4_resetStream (LZ4_str
  *  Use this function to load a static dictionary into LZ4_stream_t.
  *  Any previous data will be forgotten, only 'dictionary' will remain in memory.
  *  Loading a size of 0 is allowed, and is the same as reset.
  * @return : dictionary size, in bytes (necessarily <= 64 KB)
  */
 LZ4LIB_API int LZ4_loadDict (LZ4_stream_t* streamPtr, const char* dictionary, int dictSize);
 
 /*! LZ4_compress_fast_continue() :
- *  Compress content into 'src' using data from previously compressed blocks, improving compression ratio.
+ *  Compress 'src' content using data from previously compressed blocks, for better compression ratio.
  *  'dst' buffer must be already allocated.
  *  If dstCapacity >= LZ4_compressBound(srcSize), compression is guaranteed to succeed, and runs faster.
  *
- *  Important : Up to 64KB of previously compressed data is assumed to remain present and unmodified in memory !
- *  Special 1 : If input buffer is a double-buffer, it can have any size, including < 64 KB.
- *  Special 2 : If input buffer is a ring-buffer, it can have any size, including < 64 KB.
+ *  Important : The previous 64KB of compressed data is assumed to remain present and unmodified in memory!
+ *
+ *  Special 1 : When input is a double-buffer, they can have any size, including < 64 KB.
+ *              Make sure that buffers are separated by at least one byte.
+ *              This way, each block only depends on previous block.
+ *  Special 2 : If input buffer is a ring-buffer, it can have any size, including < 64 KB.
  *
  * @return : size of compressed block
- *           or 0 if there is an error (typically, compressed data cannot fit into 'dst')
+ *           or 0 if there is an error (typically, cannot fit into 'dst').
  *  After an error, the stream status is invalid, it can only be reset or freed.
  */
 LZ4LIB_API int LZ4_compress_fast_continue (LZ4_stream_t* streamPtr, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
 
 /*! LZ4_saveDict() :
- *  If previously compressed data block is not guaranteed to remain available at its current memory location,
+ *  If last 64KB data cannot be guaranteed to remain available at its current memory location,
  *  save it into a safer place (char* safeBuffer).
- *  Note : it's not necessary to call LZ4_loadDict() after LZ4_saveDict(), dictionary is immediately usable.
- *  @return : saved dictionary size in bytes (necessarily <= dictSize), or 0 if error.
+ *  This is schematically equivalent to a memcpy() followed by LZ4_loadDict(),
+ *  but is much faster, because LZ4_saveDict() doesn't need to rebuild tables.
+ * @return : saved dictionary size in bytes (necessarily <= maxDictSize), or 0 if error.
  */
-LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int dictSize);
+LZ4LIB_API int LZ4_saveDict (LZ4_stream_t* streamPtr, char* safeBuffer, int maxDictSize);
 
 
 /*-**********************************************
 *  Streaming Decompression Functions
 *  Bufferless synchronous API
 ************************************************/
-typedef union LZ4_streamDecode_u LZ4_streamDecode_t;   /* incomplete type (defined later) */
+typedef union LZ4_streamDecode_u LZ4_streamDecode_t;   /* tracking context */
 
 /*! LZ4_createStreamDecode() and LZ4_freeStreamDecode() :
- *  creation / destruction of streaming decompression tracking structure.
- *  A tracking structure can be re-used multiple times sequentially. */
+ *  creation / destruction of streaming decompression tracking context.
+ *  A tracking context can be re-used multiple times.
+ */
 LZ4LIB_API LZ4_streamDecode_t* LZ4_createStreamDecode(void);
 LZ4LIB_API int                 LZ4_freeStreamDecode (LZ4_streamDecode_t* LZ4_stream);
 
 /*! LZ4_setStreamDecode() :
- *  An LZ4_streamDecode_t structure can be allocated once and re-used multiple times.
+ *  An LZ4_streamDecode_t context can be allocated once and re-used multiple times.
  *  Use this function to start decompression of a new stream of blocks.
- *  A dictionary can optionnally be set. Use NULL or size 0 for a simple reset order.
+ *  A dictionary can optionnally be set. Use NULL or size 0 for a reset order.
+ *  Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
  * @return : 1 if OK, 0 if error
  */
 LZ4LIB_API int LZ4_setStreamDecode (LZ4_streamDecode_t* LZ4_streamDecode, const char* dictionary, int dictSize);
 
+/*! LZ4_decoderRingBufferSize() : v1.8.2
+ *  Note : in a ring buffer scenario (optional),
+ *  blocks are presumed decompressed next to each other
+ *  up to the moment there is not enough remaining space for next block (remainingSize < maxBlockSize),
+ *  at which stage it resumes from beginning of ring buffer.
+ *  When setting such a ring buffer for streaming decompression,
+ *  provides the minimum size of this ring buffer
+ *  to be compatible with any source respecting maxBlockSize condition.
+ * @return : minimum ring buffer size,
+ *           or 0 if there is an error (invalid maxBlockSize).
+ */
+LZ4LIB_API int LZ4_decoderRingBufferSize(int maxBlockSize);
+#define LZ4_DECODER_RING_BUFFER_SIZE(mbs) (65536 + 14 + (mbs))  /* for static allocation; mbs presumed valid */
+
 /*! LZ4_decompress_*_continue() :
  *  These decoding functions allow decompression of consecutive blocks in "streaming" mode.
  *  A block is an unsplittable entity, it must be presented entirely to a decompression function.
- *  Decompression functions only accept one block at a time.
- *  Previously decoded blocks *must* remain available at the memory position where they were decoded (up to 64 KB).
+ *  Decompression functions only accepts one block at a time.
+ *  The last 64KB of previously decoded data *must* remain available and unmodified at the memory position where they were decoded.
+ *  If less than 64KB of data has been decoded, all the data must be present.
  *
- *  Special : if application sets a ring buffer for decompression, it must respect one of the following conditions :
- *  - Exactly same size as encoding buffer, with same update rule (block boundaries at same positions)
- *    In which case, the decoding & encoding ring buffer can have any size, including very small ones ( < 64 KB).
- *  - Larger than encoding buffer, by a minimum of maxBlockSize more bytes.
- *    maxBlockSize is implementation dependent. It's the maximum size of any single block.
+ *  Special : if decompression side sets a ring buffer, it must respect one of the following conditions :
+ *  - Decompression buffer size is _at least_ LZ4_decoderRingBufferSize(maxBlockSize).
+ *    maxBlockSize is the maximum size of any single block. It can have any value > 16 bytes.
+ *    In which case, encoding and decoding buffers do not need to be synchronized.
+ *    Actually, data can be produced by any source compliant with LZ4 format specification, and respecting maxBlockSize.
+ *  - Synchronized mode :
+ *    Decompression buffer size is _exactly_ the same as compression buffer size,
+ *    and follows exactly same update rule (block boundaries at same positions),
+ *    and decoding function is provided with exact decompressed size of each block (exception for last block of the stream),
+ *    _then_ decoding & encoding ring buffer can have any size, including small ones ( < 64 KB).
+ *  - Decompression buffer is larger than encoding buffer, by a minimum of maxBlockSize more bytes.
  *    In which case, encoding and decoding buffers do not need to be synchronized,
  *    and encoding ring buffer can have any size, including small ones ( < 64 KB).
- *  - _At least_ 64 KB + 8 bytes + maxBlockSize.
- *    In which case, encoding and decoding buffers do not need to be synchronized,
- *    and encoding ring buffer can have any size, including larger than decoding buffer.
- *  Whenever these conditions are not possible, save the last 64KB of decoded data into a safe buffer,
- *  and indicate where it is saved using LZ4_setStreamDecode() before decompressing next block.
+ *
+ *  Whenever these conditions are not possible,
+ *  save the last 64KB of decoded data into a safe buffer where it can't be modified during decompression,
+ *  then indicate where this data is saved using LZ4_setStreamDecode(), before decompressing next block.
 */
 LZ4LIB_API int LZ4_decompress_safe_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int srcSize, int dstCapacity);
 LZ4LIB_API int LZ4_decompress_fast_continue (LZ4_streamDecode_t* LZ4_streamDecode, const char* src, char* dst, int originalSize);
 
 
 /*! LZ4_decompress_*_usingDict() :
  *  These decoding functions work the same as
  *  a combination of LZ4_setStreamDecode() followed by LZ4_decompress_*_continue()
  *  They are stand-alone, and don't need an LZ4_streamDecode_t structure.
+ *  Dictionary is presumed stable : it must remain accessible and unmodified during next decompression.
  */
 LZ4LIB_API int LZ4_decompress_safe_usingDict (const char* src, char* dst, int srcSize, int dstCapcity, const char* dictStart, int dictSize);
 LZ4LIB_API int LZ4_decompress_fast_usingDict (const char* src, char* dst, int originalSize, const char* dictStart, int dictSize);
 
 
 /*^**********************************************
  * !!!!!!   STATIC LINKING ONLY   !!!!!!
  ***********************************************/
+
+/*-************************************
+ *  Unstable declarations
+ **************************************
+ * Declarations in this section should be considered unstable.
+ * Use at your own peril, etc., etc.
+ * They may be removed in the future.
+ * Their signatures may change.
+ **************************************/
+
+#ifdef LZ4_STATIC_LINKING_ONLY
+
+/*! LZ4_resetStream_fast() :
+ *  Use this, like LZ4_resetStream(), to prepare a context for a new chain of
+ *  calls to a streaming API (e.g., LZ4_compress_fast_continue()).
+ *
+ *  Note:
+ *  Using this in advance of a non- streaming-compression function is redundant,
+ *  and potentially bad for performance, since they all perform their own custom
+ *  reset internally.
+ *
+ *  Differences from LZ4_resetStream():
+ *  When an LZ4_stream_t is known to be in a internally coherent state,
+ *  it can often be prepared for a new compression with almost no work, only
+ *  sometimes falling back to the full, expensive reset that is always required
+ *  when the stream is in an indeterminate state (i.e., the reset performed by
+ *  LZ4_resetStream()).
+ *
+ *  LZ4_streams are guaranteed to be in a valid state when:
+ *  - returned from LZ4_createStream()
+ *  - reset by LZ4_resetStream()
+ *  - memset(stream, 0, sizeof(LZ4_stream_t)), though this is discouraged
+ *  - the stream was in a valid state and was reset by LZ4_resetStream_fast()
+ *  - the stream was in a valid state and was then used in any compression call
+ *    that returned success
+ *  - the stream was in an indeterminate state and was used in a compression
+ *    call that fully reset the state (e.g., LZ4_compress_fast_extState()) and
+ *    that returned success
+ *
+ *  When a stream isn't known to be in a valid state, it is not safe to pass to
+ *  any fastReset or streaming function. It must first be cleansed by the full
+ *  LZ4_resetStream().
+ */
+LZ4LIB_API void LZ4_resetStream_fast (LZ4_stream_t* streamPtr);
+
+/*! LZ4_compress_fast_extState_fastReset() :
+ *  A variant of LZ4_compress_fast_extState().
+ *
+ *  Using this variant avoids an expensive initialization step. It is only safe
+ *  to call if the state buffer is known to be correctly initialized already
+ *  (see above comment on LZ4_resetStream_fast() for a definition of "correctly
+ *  initialized"). From a high level, the difference is that this function
+ *  initializes the provided state with a call to something like
+ *  LZ4_resetStream_fast() while LZ4_compress_fast_extState() starts with a
+ *  call to LZ4_resetStream().
+ */
+LZ4LIB_API int LZ4_compress_fast_extState_fastReset (void* state, const char* src, char* dst, int srcSize, int dstCapacity, int acceleration);
+
+/*! LZ4_attach_dictionary() :
+ *  This is an experimental API that allows for the efficient use of a
+ *  static dictionary many times.
+ *
+ *  Rather than re-loading the dictionary buffer into a working context before
+ *  each compression, or copying a pre-loaded dictionary's LZ4_stream_t into a
+ *  working LZ4_stream_t, this function introduces a no-copy setup mechanism,
+ *  in which the working stream references the dictionary stream in-place.
+ *
+ *  Several assumptions are made about the state of the dictionary stream.
+ *  Currently, only streams which have been prepared by LZ4_loadDict() should
+ *  be expected to work.
+ *
+ *  Alternatively, the provided dictionary stream pointer may be NULL, in which
+ *  case any existing dictionary stream is unset.
+ *
+ *  If a dictionary is provided, it replaces any pre-existing stream history.
+ *  The dictionary contents are the only history that can be referenced and
+ *  logically immediately precede the data compressed in the first subsequent
+ *  compression call.
+ *
+ *  The dictionary will only remain attached to the working stream through the
+ *  first compression call, at the end of which it is cleared. The dictionary
+ *  stream (and source buffer) must remain in-place / accessible / unchanged
+ *  through the completion of the first compression call on the stream.
+ */
+LZ4LIB_API void LZ4_attach_dictionary(LZ4_stream_t *working_stream, const LZ4_stream_t *dictionary_stream);
+
+#endif
+
 /*-************************************
  *  Private definitions
  **************************************
  * Do not use these definitions.
  * They are exposed to allow static allocation of `LZ4_stream_t` and `LZ4_streamDecode_t`.
  * Using these definitions will expose code to API and/or ABI break in future versions of the library.
  **************************************/
 #define LZ4_HASHLOG   (LZ4_MEMORY_USAGE-2)
 #define LZ4_HASHTABLESIZE (1 << LZ4_MEMORY_USAGE)
 #define LZ4_HASH_SIZE_U32 (1 << LZ4_HASHLOG)       /* required as macro for static allocation */
 
 #if defined(__cplusplus) || (defined (__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */)
 #include <stdint.h>
 
-typedef struct {
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
     uint32_t hashTable[LZ4_HASH_SIZE_U32];
     uint32_t currentOffset;
-    uint32_t initCheck;
+    uint16_t initCheck;
+    uint16_t tableType;
     const uint8_t* dictionary;
-    uint8_t* bufferStart;   /* obsolete, used for slideInputBuffer */
+    const LZ4_stream_t_internal* dictCtx;
     uint32_t dictSize;
-} LZ4_stream_t_internal;
+};
 
 typedef struct {
     const uint8_t* externalDict;
     size_t extDictSize;
     const uint8_t* prefixEnd;
     size_t prefixSize;
 } LZ4_streamDecode_t_internal;
 
 #else
 
-typedef struct {
+typedef struct LZ4_stream_t_internal LZ4_stream_t_internal;
+struct LZ4_stream_t_internal {
     unsigned int hashTable[LZ4_HASH_SIZE_U32];
     unsigned int currentOffset;
-    unsigned int initCheck;
+    unsigned short initCheck;
+    unsigned short tableType;
     const unsigned char* dictionary;
-    unsigned char* bufferStart;   /* obsolete, used for slideInputBuffer */
+    const LZ4_stream_t_internal* dictCtx;
     unsigned int dictSize;
-} LZ4_stream_t_internal;
+};
 
 typedef struct {
     const unsigned char* externalDict;
     size_t extDictSize;
     const unsigned char* prefixEnd;
     size_t prefixSize;
 } LZ4_streamDecode_t_internal;
 
@@ -428,52 +550,58 @@ union LZ4_streamDecode_u {
    it is generally possible to disable them,
    typically with -Wno-deprecated-declarations for gcc
    or _CRT_SECURE_NO_WARNINGS in Visual.
    Otherwise, it's also possible to define LZ4_DISABLE_DEPRECATE_WARNINGS */
 #ifdef LZ4_DISABLE_DEPRECATE_WARNINGS
 #  define LZ4_DEPRECATED(message)   /* disable deprecation warnings */
 #else
 #  define LZ4_GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
-#  if defined(__clang__) /* clang doesn't handle mixed C++11 and CNU attributes */
-#    define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
-#  elif defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
+#  if defined (__cplusplus) && (__cplusplus >= 201402) /* C++14 or greater */
 #    define LZ4_DEPRECATED(message) [[deprecated(message)]]
-#  elif (LZ4_GCC_VERSION >= 405)
+#  elif (LZ4_GCC_VERSION >= 405) || defined(__clang__)
 #    define LZ4_DEPRECATED(message) __attribute__((deprecated(message)))
 #  elif (LZ4_GCC_VERSION >= 301)
 #    define LZ4_DEPRECATED(message) __attribute__((deprecated))
 #  elif defined(_MSC_VER)
 #    define LZ4_DEPRECATED(message) __declspec(deprecated(message))
 #  else
 #    pragma message("WARNING: You need to implement LZ4_DEPRECATED for this compiler")
 #    define LZ4_DEPRECATED(message)
 #  endif
 #endif /* LZ4_DISABLE_DEPRECATE_WARNINGS */
 
 /* Obsolete compression functions */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress               (const char* source, char* dest, int sourceSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_default() instead") int LZ4_compress_limitedOutput (const char* source, char* dest, int sourceSize, int maxOutputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_withState               (void* state, const char* source, char* dest, int inputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_extState() instead") int LZ4_compress_limitedOutput_withState (void* state, const char* source, char* dest, int inputSize, int maxOutputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_continue                (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") int LZ4_compress_limitedOutput_continue  (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
+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_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);
+LZ4_DEPRECATED("use LZ4_compress_fast_continue() instead") LZ4LIB_API int LZ4_compress_limitedOutput_continue  (LZ4_stream_t* LZ4_streamPtr, const char* source, char* dest, int inputSize, int maxOutputSize);
 
 /* Obsolete decompression functions */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast() instead") int LZ4_uncompress (const char* source, char* dest, int outputSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe() instead") int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
+LZ4_DEPRECATED("use LZ4_decompress_fast() instead") LZ4LIB_API int LZ4_uncompress (const char* source, char* dest, int outputSize);
+LZ4_DEPRECATED("use LZ4_decompress_safe() instead") LZ4LIB_API int LZ4_uncompress_unknownOutputSize (const char* source, char* dest, int isize, int maxOutputSize);
 
-/* Obsolete streaming functions; use new streaming interface whenever possible */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") void* LZ4_create (char* inputBuffer);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_createStream() instead") int   LZ4_sizeofStreamState(void);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_resetStream() instead")  int   LZ4_resetStreamState(void* state, char* inputBuffer);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_saveDict() instead")     char* LZ4_slideInputBuffer (void* state);
+/* Obsolete streaming functions; degraded functionality; do not use!
+ *
+ * In order to perform streaming compression, these functions depended on data
+ * that is no longer tracked in the state. They have been preserved as well as
+ * possible: using them will still produce a correct output. However, they don't
+ * actually retain any history between compression calls. The compression ratio
+ * achieved will therefore be no better than compressing each chunk
+ * independently.
+ */
+LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API void* LZ4_create (char* inputBuffer);
+LZ4_DEPRECATED("Use LZ4_createStream() instead") LZ4LIB_API int   LZ4_sizeofStreamState(void);
+LZ4_DEPRECATED("Use LZ4_resetStream() instead") LZ4LIB_API  int   LZ4_resetStreamState(void* state, char* inputBuffer);
+LZ4_DEPRECATED("Use LZ4_saveDict() instead") LZ4LIB_API     char* LZ4_slideInputBuffer (void* state);
 
 /* Obsolete streaming decoding functions */
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
-LZ4LIB_API LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
+LZ4_DEPRECATED("use LZ4_decompress_safe_usingDict() instead") LZ4LIB_API int LZ4_decompress_safe_withPrefix64k (const char* src, char* dst, int compressedSize, int maxDstSize);
+LZ4_DEPRECATED("use LZ4_decompress_fast_usingDict() instead") LZ4LIB_API int LZ4_decompress_fast_withPrefix64k (const char* src, char* dst, int originalSize);
 
 #endif /* LZ4_H_2983827168210 */
 
 
 #if defined (__cplusplus)
 }
 #endif
--- a/mobile/android/chrome/content/browser.js
+++ b/mobile/android/chrome/content/browser.js
@@ -2899,17 +2899,20 @@ var NativeWindow = {
         {target: this._target, x: event.clientX, y: event.clientY}, "context-menu-not-shown");
     },
 
     // Returns a title for a context menu. If no title attribute exists, will fall back to looking for a url
     _getTitle: function(node) {
       if (node.hasAttribute && node.hasAttribute("title")) {
         return node.getAttribute("title");
       }
-      return this._getUrl(node);
+      let url = this._getUrl(node);
+      let readerUrl = ReaderMode.getOriginalUrlObjectForDisplay(url);
+
+      return (readerUrl && readerUrl.displaySpec) || url;
     },
 
     // Returns a url associated with a node
     _getUrl: function(node) {
       if ((ChromeUtils.getClassName(node) === "HTMLAnchorElement" && node.href) ||
           (ChromeUtils.getClassName(node) === "HTMLAreaElement" && node.href)) {
         return this._getLinkURL(node);
       } else if (node instanceof Ci.nsIImageLoadingContent && node.currentURI) {
--- a/mobile/android/components/geckoview/GeckoViewExternalAppService.js
+++ b/mobile/android/components/geckoview/GeckoViewExternalAppService.js
@@ -21,22 +21,30 @@ ExternalAppService.prototype = {
   classID: Components.ID("{a89eeec6-6608-42ee-a4f8-04d425992f45}"),
   QueryInterface: ChromeUtils.generateQI([Ci.nsIExternalHelperAppService]),
 
   doContent(mimeType, request, context, forceSave) {
     const channel = request.QueryInterface(Ci.nsIChannel);
     debug `doContent: uri=${channel.URI.displaySpec}
                       contentType=${channel.contentType}`;
 
+    let filename = null;
+    try {
+      filename = channel.contentDispositionFilename;
+    } catch (e) {
+      // This throws NS_ERROR_NOT_AVAILABLE if there is not
+      // Content-disposition header.
+    }
+
     GeckoViewUtils.getDispatcherForWindow(context).sendRequest({
       type: "GeckoView:ExternalResponse",
       uri: channel.URI.displaySpec,
       contentType: channel.contentType,
       contentLength: channel.contentLength,
-      filename: channel.contentDispositionFilename
+      filename: filename
     });
 
     request.cancel(Cr.NS_ERROR_ABORT);
     Components.returnCode = Cr.NS_ERROR_ABORT;
   },
 
   applyDecodingForExtension(ext, encoding) {
     debug `applyDecodingForExtension: extension=${ext}