zstd: Update to upstream 1.4.0

One step towards fixing #17374 as most experimental APIs we use are now
part of the stable 1.4.0.

19 files changed, 1719 insertions, 1181 deletions

diff --git a/thirdparty/zstd/common/compiler.h b/thirdparty/zstd/common/compiler.h
index 7f561282ca..0836e3ed27 100644
--- a/thirdparty/zstd/common/compiler.h
+++ b/thirdparty/zstd/common/compiler.h
@@ -40,7 +40,7 @@
 
 /**
  * FORCE_INLINE_TEMPLATE is used to define C "templates", which take constant
- * parameters. They must be inlined for the compiler to elimininate the constant
+ * parameters. They must be inlined for the compiler to eliminate the constant
  * branches.
  */
 #define FORCE_INLINE_TEMPLATE static INLINE_KEYWORD FORCE_INLINE_ATTR
diff --git a/thirdparty/zstd/common/fse.h b/thirdparty/zstd/common/fse.h
index f72c519b25..811c670bdd 100644
--- a/thirdparty/zstd/common/fse.h
+++ b/thirdparty/zstd/common/fse.h
@@ -358,7 +358,7 @@ size_t FSE_decompress_wksp(void* dst, size_t dstCapacity, const void* cSrc, size
 typedef enum {
    FSE_repeat_none,  /**< Cannot use the previous table */
    FSE_repeat_check, /**< Can use the previous table but it must be checked */
-   FSE_repeat_valid  /**< Can use the previous table and it is asumed to be valid */
+   FSE_repeat_valid  /**< Can use the previous table and it is assumed to be valid */
  } FSE_repeat;
 
 /* *****************************************
diff --git a/thirdparty/zstd/common/threading.c b/thirdparty/zstd/common/threading.c
index 8be8c8da94..f3d4fa8418 100644
--- a/thirdparty/zstd/common/threading.c
+++ b/thirdparty/zstd/common/threading.c
@@ -14,8 +14,8 @@
  * This file will hold wrapper for systems, which do not support pthreads
  */
 
-/* create fake symbol to avoid empty trnaslation unit warning */
-int g_ZSTD_threading_useles_symbol;
+/* create fake symbol to avoid empty translation unit warning */
+int g_ZSTD_threading_useless_symbol;
 
 #if defined(ZSTD_MULTITHREAD) && defined(_WIN32)
 
diff --git a/thirdparty/zstd/common/xxhash.c b/thirdparty/zstd/common/xxhash.c
index 532b816192..30599aaae4 100644
--- a/thirdparty/zstd/common/xxhash.c
+++ b/thirdparty/zstd/common/xxhash.c
@@ -66,10 +66,10 @@
 /* #define XXH_ACCEPT_NULL_INPUT_POINTER 1 */
 
 /*!XXH_FORCE_NATIVE_FORMAT :
- * By default, xxHash library provides endian-independant Hash values, based on little-endian convention.
+ * By default, xxHash library provides endian-independent Hash values, based on little-endian convention.
  * Results are therefore identical for little-endian and big-endian CPU.
  * This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
- * Should endian-independance be of no importance for your application, you may set the #define below to 1,
+ * Should endian-independence be of no importance for your application, you may set the #define below to 1,
  * to improve speed for Big-endian CPU.
  * This option has no impact on Little_Endian CPU.
  */
diff --git a/thirdparty/zstd/common/zstd_internal.h b/thirdparty/zstd/common/zstd_internal.h
index edeb74b9c3..31f756ab58 100644
--- a/thirdparty/zstd/common/zstd_internal.h
+++ b/thirdparty/zstd/common/zstd_internal.h
@@ -53,8 +53,50 @@ extern "C" {
 #undef MAX
 #define MIN(a,b) ((a)<(b) ? (a) : (b))
 #define MAX(a,b) ((a)>(b) ? (a) : (b))
-#define CHECK_F(f) { size_t const errcod = f; if (ERR_isError(errcod)) return errcod; }  /* check and Forward error code */
-#define CHECK_E(f, e) { size_t const errcod = f; if (ERR_isError(errcod)) return ERROR(e); }  /* check and send Error code */
+
+/**
+ * Return the specified error if the condition evaluates to true.
+ *
+ * In debug modes, prints additional information. In order to do that
+ * (particularly, printing the conditional that failed), this can't just wrap
+ * RETURN_ERROR().
+ */
+#define RETURN_ERROR_IF(cond, err, ...) \
+  if (cond) { \
+    RAWLOG(3, "%s:%d: ERROR!: check %s failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(cond), ZSTD_QUOTE(ERROR(err))); \
+    RAWLOG(3, ": " __VA_ARGS__); \
+    RAWLOG(3, "\n"); \
+    return ERROR(err); \
+  }
+
+/**
+ * Unconditionally return the specified error.
+ *
+ * In debug modes, prints additional information.
+ */
+#define RETURN_ERROR(err, ...) \
+  do { \
+    RAWLOG(3, "%s:%d: ERROR!: unconditional check failed, returning %s", __FILE__, __LINE__, ZSTD_QUOTE(ERROR(err))); \
+    RAWLOG(3, ": " __VA_ARGS__); \
+    RAWLOG(3, "\n"); \
+    return ERROR(err); \
+  } while(0);
+
+/**
+ * If the provided expression evaluates to an error code, returns that error code.
+ *
+ * In debug modes, prints additional information.
+ */
+#define FORWARD_IF_ERROR(err, ...) \
+  do { \
+    size_t const err_code = (err); \
+    if (ERR_isError(err_code)) { \
+      RAWLOG(3, "%s:%d: ERROR!: forwarding error in %s: %s", __FILE__, __LINE__, ZSTD_QUOTE(err), ERR_getErrorName(err_code)); \
+      RAWLOG(3, ": " __VA_ARGS__); \
+      RAWLOG(3, "\n"); \
+      return err_code; \
+    } \
+  } while(0);
 
 
 /*-*************************************
@@ -200,6 +242,17 @@ typedef struct {
     U32   longLengthPos;
 } seqStore_t;
 
+/**
+ * Contains the compressed frame size and an upper-bound for the decompressed frame size.
+ * Note: before using `compressedSize`, check for errors using ZSTD_isError().
+ *       similarly, before using `decompressedBound`, check for errors using:
+ *          `decompressedBound != ZSTD_CONTENTSIZE_ERROR`
+ */
+typedef struct {
+    size_t compressedSize;
+    unsigned long long decompressedBound;
+} ZSTD_frameSizeInfo;   /* decompress & legacy */
+
 const seqStore_t* ZSTD_getSeqStore(const ZSTD_CCtx* ctx);   /* compress & dictBuilder */
 void ZSTD_seqToCodes(const seqStore_t* seqStorePtr);   /* compress, dictBuilder, decodeCorpus (shouldn't get its definition from here) */
 
diff --git a/thirdparty/zstd/compress/fse_compress.c b/thirdparty/zstd/compress/fse_compress.c
index 60f357bbd2..68b47e1093 100644
--- a/thirdparty/zstd/compress/fse_compress.c
+++ b/thirdparty/zstd/compress/fse_compress.c
@@ -129,9 +129,9 @@ size_t FSE_buildCTable_wksp(FSE_CTable* ct,
     {   U32 position = 0;
         U32 symbol;
         for (symbol=0; symbol<=maxSymbolValue; symbol++) {
-            int nbOccurences;
+            int nbOccurrences;
             int const freq = normalizedCounter[symbol];
-            for (nbOccurences=0; nbOccurences<freq; nbOccurences++) {
+            for (nbOccurrences=0; nbOccurrences<freq; nbOccurrences++) {
                 tableSymbol[position] = (FSE_FUNCTION_TYPE)symbol;
                 position = (position + step) & tableMask;
                 while (position > highThreshold)
diff --git a/thirdparty/zstd/compress/zstd_compress.c b/thirdparty/zstd/compress/zstd_compress.c
index c2c9d3bc55..2e163c8bf3 100644
--- a/thirdparty/zstd/compress/zstd_compress.c
+++ b/thirdparty/zstd/compress/zstd_compress.c
@@ -103,12 +103,31 @@ ZSTD_CCtx* ZSTD_initStaticCCtx(void *workspace, size_t workspaceSize)
     return cctx;
 }
 
+/**
+ * Clears and frees all of the dictionaries in the CCtx.
+ */
+static void ZSTD_clearAllDicts(ZSTD_CCtx* cctx)
+{
+    ZSTD_free(cctx->localDict.dictBuffer, cctx->customMem);
+    ZSTD_freeCDict(cctx->localDict.cdict);
+    memset(&cctx->localDict, 0, sizeof(cctx->localDict));
+    memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));
+    cctx->cdict = NULL;
+}
+
+static size_t ZSTD_sizeof_localDict(ZSTD_localDict dict)
+{
+    size_t const bufferSize = dict.dictBuffer != NULL ? dict.dictSize : 0;
+    size_t const cdictSize = ZSTD_sizeof_CDict(dict.cdict);
+    return bufferSize + cdictSize;
+}
+
 static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx)
 {
     assert(cctx != NULL);
     assert(cctx->staticSize == 0);
     ZSTD_free(cctx->workSpace, cctx->customMem); cctx->workSpace = NULL;
-    ZSTD_freeCDict(cctx->cdictLocal); cctx->cdictLocal = NULL;
+    ZSTD_clearAllDicts(cctx);
 #ifdef ZSTD_MULTITHREAD
     ZSTDMT_freeCCtx(cctx->mtctx); cctx->mtctx = NULL;
 #endif
@@ -117,7 +136,8 @@ static void ZSTD_freeCCtxContent(ZSTD_CCtx* cctx)
 size_t ZSTD_freeCCtx(ZSTD_CCtx* cctx)
 {
     if (cctx==NULL) return 0;   /* support free on NULL */
-    if (cctx->staticSize) return ERROR(memory_allocation);   /* not compatible with static CCtx */
+    RETURN_ERROR_IF(cctx->staticSize, memory_allocation,
+                    "not compatible with static CCtx");
     ZSTD_freeCCtxContent(cctx);
     ZSTD_free(cctx, cctx->customMem);
     return 0;
@@ -139,7 +159,7 @@ size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx)
 {
     if (cctx==NULL) return 0;   /* support sizeof on NULL */
     return sizeof(*cctx) + cctx->workSpaceSize
-           + ZSTD_sizeof_CDict(cctx->cdictLocal)
+           + ZSTD_sizeof_localDict(cctx->localDict)
            + ZSTD_sizeof_mtctx(cctx);
 }
 
@@ -195,7 +215,7 @@ size_t ZSTD_CCtxParams_reset(ZSTD_CCtx_params* params)
 }
 
 size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel) {
-    if (!cctxParams) { return ERROR(GENERIC); }
+    RETURN_ERROR_IF(!cctxParams, GENERIC);
     memset(cctxParams, 0, sizeof(*cctxParams));
     cctxParams->compressionLevel = compressionLevel;
     cctxParams->fParams.contentSizeFlag = 1;
@@ -204,8 +224,8 @@ size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compressionLevel)
 
 size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params)
 {
-    if (!cctxParams) { return ERROR(GENERIC); }
-    CHECK_F( ZSTD_checkCParams(params.cParams) );
+    RETURN_ERROR_IF(!cctxParams, GENERIC);
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) );
     memset(cctxParams, 0, sizeof(*cctxParams));
     cctxParams->cParams = params.cParams;
     cctxParams->fParams = params.fParams;
@@ -359,6 +379,12 @@ ZSTD_bounds ZSTD_cParam_getBounds(ZSTD_cParameter param)
         bounds.upperBound = ZSTD_dictForceCopy;       /* note : how to ensure at compile time that this is the highest value enum ? */
         return bounds;
 
+    case ZSTD_c_literalCompressionMode:
+        ZSTD_STATIC_ASSERT(ZSTD_lcm_auto < ZSTD_lcm_huffman && ZSTD_lcm_huffman < ZSTD_lcm_uncompressed);
+        bounds.lowerBound = ZSTD_lcm_auto;
+        bounds.upperBound = ZSTD_lcm_uncompressed;
+        return bounds;
+
     default:
         {   ZSTD_bounds const boundError = { ERROR(parameter_unsupported), 0, 0 };
             return boundError;
@@ -378,10 +404,22 @@ static int ZSTD_cParam_withinBounds(ZSTD_cParameter cParam, int value)
     return 1;
 }
 
-#define BOUNDCHECK(cParam, val) {                  \
-    if (!ZSTD_cParam_withinBounds(cParam,val)) {   \
-        return ERROR(parameter_outOfBound);        \
-}   }
+/* ZSTD_cParam_clampBounds:
+ * Clamps the value into the bounded range.
+ */
+static size_t ZSTD_cParam_clampBounds(ZSTD_cParameter cParam, int* value)
+{
+    ZSTD_bounds const bounds = ZSTD_cParam_getBounds(cParam);
+    if (ZSTD_isError(bounds.error)) return bounds.error;
+    if (*value < bounds.lowerBound) *value = bounds.lowerBound;
+    if (*value > bounds.upperBound) *value = bounds.upperBound;
+    return 0;
+}
+
+#define BOUNDCHECK(cParam, val) { \
+    RETURN_ERROR_IF(!ZSTD_cParam_withinBounds(cParam,val), \
+                    parameter_outOfBound); \
+}
 
 
 static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
@@ -413,6 +451,7 @@ static int ZSTD_isUpdateAuthorized(ZSTD_cParameter param)
     case ZSTD_c_ldmBucketSizeLog:
     case ZSTD_c_ldmHashRateLog:
     case ZSTD_c_forceAttachDict:
+    case ZSTD_c_literalCompressionMode:
     default:
         return 0;
     }
@@ -425,18 +464,17 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
         if (ZSTD_isUpdateAuthorized(param)) {
             cctx->cParamsChanged = 1;
         } else {
-            return ERROR(stage_wrong);
+            RETURN_ERROR(stage_wrong);
     }   }
 
     switch(param)
     {
-    case ZSTD_c_format :
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
+    case ZSTD_c_nbWorkers:
+        RETURN_ERROR_IF((value!=0) && cctx->staticSize, parameter_unsupported,
+                        "MT not compatible with static alloc");
+        break;
 
     case ZSTD_c_compressionLevel:
-        if (cctx->cdict) return ERROR(stage_wrong);
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
     case ZSTD_c_windowLog:
     case ZSTD_c_hashLog:
     case ZSTD_c_chainLog:
@@ -444,49 +482,32 @@ size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int value)
     case ZSTD_c_minMatch:
     case ZSTD_c_targetLength:
     case ZSTD_c_strategy:
-        if (cctx->cdict) return ERROR(stage_wrong);
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
+    case ZSTD_c_ldmHashRateLog:
+    case ZSTD_c_format:
     case ZSTD_c_contentSizeFlag:
     case ZSTD_c_checksumFlag:
     case ZSTD_c_dictIDFlag:
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
-    case ZSTD_c_forceMaxWindow :  /* Force back-references to remain < windowSize,
-                                   * even when referencing into Dictionary content.
-                                   * default : 0 when using a CDict, 1 when using a Prefix */
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
+    case ZSTD_c_forceMaxWindow:
     case ZSTD_c_forceAttachDict:
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
-    case ZSTD_c_nbWorkers:
-        if ((value!=0) && cctx->staticSize) {
-            return ERROR(parameter_unsupported);  /* MT not compatible with static alloc */
-        }
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
+    case ZSTD_c_literalCompressionMode:
     case ZSTD_c_jobSize:
     case ZSTD_c_overlapLog:
     case ZSTD_c_rsyncable:
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
-
     case ZSTD_c_enableLongDistanceMatching:
     case ZSTD_c_ldmHashLog:
     case ZSTD_c_ldmMinMatch:
     case ZSTD_c_ldmBucketSizeLog:
-    case ZSTD_c_ldmHashRateLog:
-        if (cctx->cdict) return ERROR(stage_wrong);
-        return ZSTD_CCtxParam_setParameter(&cctx->requestedParams, param, value);
+        break;
 
-    default: return ERROR(parameter_unsupported);
+    default: RETURN_ERROR(parameter_unsupported);
     }
+    return ZSTD_CCtxParams_setParameter(&cctx->requestedParams, param, value);
 }
 
-size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
-                                   ZSTD_cParameter param, int value)
+size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* CCtxParams,
+                                    ZSTD_cParameter param, int value)
 {
-    DEBUGLOG(4, "ZSTD_CCtxParam_setParameter (%i, %i)", (int)param, value);
+    DEBUGLOG(4, "ZSTD_CCtxParams_setParameter (%i, %i)", (int)param, value);
     switch(param)
     {
     case ZSTD_c_format :
@@ -495,11 +516,9 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
         return (size_t)CCtxParams->format;
 
     case ZSTD_c_compressionLevel : {
-        int cLevel = value;
-        if (cLevel > ZSTD_maxCLevel()) cLevel = ZSTD_maxCLevel();
-        if (cLevel < ZSTD_minCLevel()) cLevel = ZSTD_minCLevel();
-        if (cLevel) {  /* 0 : does not change current level */
-            CCtxParams->compressionLevel = cLevel;
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value));
+        if (value) {  /* 0 : does not change current level */
+            CCtxParams->compressionLevel = value;
         }
         if (CCtxParams->compressionLevel >= 0) return CCtxParams->compressionLevel;
         return 0;  /* return type (size_t) cannot represent negative values */
@@ -573,33 +592,55 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
         return CCtxParams->attachDictPref;
     }
 
+    case ZSTD_c_literalCompressionMode : {
+        const ZSTD_literalCompressionMode_e lcm = (ZSTD_literalCompressionMode_e)value;
+        BOUNDCHECK(ZSTD_c_literalCompressionMode, lcm);
+        CCtxParams->literalCompressionMode = lcm;
+        return CCtxParams->literalCompressionMode;
+    }
+
     case ZSTD_c_nbWorkers :
 #ifndef ZSTD_MULTITHREAD
-        if (value!=0) return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
         return 0;
 #else
-        return ZSTDMT_CCtxParam_setNbWorkers(CCtxParams, value);
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value));
+        CCtxParams->nbWorkers = value;
+        return CCtxParams->nbWorkers;
 #endif
 
     case ZSTD_c_jobSize :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
 #else
-        return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_jobSize, value);
+        /* Adjust to the minimum non-default value. */
+        if (value != 0 && value < ZSTDMT_JOBSIZE_MIN)
+            value = ZSTDMT_JOBSIZE_MIN;
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(param, &value));
+        assert(value >= 0);
+        CCtxParams->jobSize = value;
+        return CCtxParams->jobSize;
 #endif
 
     case ZSTD_c_overlapLog :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
 #else
-        return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_overlapLog, value);
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value));
+        CCtxParams->overlapLog = value;
+        return CCtxParams->overlapLog;
 #endif
 
     case ZSTD_c_rsyncable :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR_IF(value!=0, parameter_unsupported, "not compiled with multithreading");
+        return 0;
 #else
-        return ZSTDMT_CCtxParam_setMTCtxParameter(CCtxParams, ZSTDMT_p_rsyncable, value);
+        FORWARD_IF_ERROR(ZSTD_cParam_clampBounds(ZSTD_c_overlapLog, &value));
+        CCtxParams->rsyncable = value;
+        return CCtxParams->rsyncable;
 #endif
 
     case ZSTD_c_enableLongDistanceMatching :
@@ -625,21 +666,21 @@ size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* CCtxParams,
         return CCtxParams->ldmParams.bucketSizeLog;
 
     case ZSTD_c_ldmHashRateLog :
-        if (value > ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN)
-            return ERROR(parameter_outOfBound);
+        RETURN_ERROR_IF(value > ZSTD_WINDOWLOG_MAX - ZSTD_HASHLOG_MIN,
+                        parameter_outOfBound);
         CCtxParams->ldmParams.hashRateLog = value;
         return CCtxParams->ldmParams.hashRateLog;
 
-    default: return ERROR(parameter_unsupported);
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
     }
 }
 
 size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param, int* value)
 {
-    return ZSTD_CCtxParam_getParameter(&cctx->requestedParams, param, value);
+    return ZSTD_CCtxParams_getParameter(&cctx->requestedParams, param, value);
 }
 
-size_t ZSTD_CCtxParam_getParameter(
+size_t ZSTD_CCtxParams_getParameter(
         ZSTD_CCtx_params* CCtxParams, ZSTD_cParameter param, int* value)
 {
     switch(param)
@@ -686,6 +727,9 @@ size_t ZSTD_CCtxParam_getParameter(
     case ZSTD_c_forceAttachDict :
         *value = CCtxParams->attachDictPref;
         break;
+    case ZSTD_c_literalCompressionMode :
+        *value = CCtxParams->literalCompressionMode;
+        break;
     case ZSTD_c_nbWorkers :
 #ifndef ZSTD_MULTITHREAD
         assert(CCtxParams->nbWorkers == 0);
@@ -694,7 +738,7 @@ size_t ZSTD_CCtxParam_getParameter(
         break;
     case ZSTD_c_jobSize :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
 #else
         assert(CCtxParams->jobSize <= INT_MAX);
         *value = (int)CCtxParams->jobSize;
@@ -702,14 +746,14 @@ size_t ZSTD_CCtxParam_getParameter(
 #endif
     case ZSTD_c_overlapLog :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
 #else
         *value = CCtxParams->overlapLog;
         break;
 #endif
     case ZSTD_c_rsyncable :
 #ifndef ZSTD_MULTITHREAD
-        return ERROR(parameter_unsupported);
+        RETURN_ERROR(parameter_unsupported, "not compiled with multithreading");
 #else
         *value = CCtxParams->rsyncable;
         break;
@@ -729,7 +773,7 @@ size_t ZSTD_CCtxParam_getParameter(
     case ZSTD_c_ldmHashRateLog :
         *value = CCtxParams->ldmParams.hashRateLog;
         break;
-    default: return ERROR(parameter_unsupported);
+    default: RETURN_ERROR(parameter_unsupported, "unknown parameter");
     }
     return 0;
 }
@@ -745,8 +789,8 @@ size_t ZSTD_CCtx_setParametersUsingCCtxParams(
         ZSTD_CCtx* cctx, const ZSTD_CCtx_params* params)
 {
     DEBUGLOG(4, "ZSTD_CCtx_setParametersUsingCCtxParams");
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-    if (cctx->cdict) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    RETURN_ERROR_IF(cctx->cdict, stage_wrong);
 
     cctx->requestedParams = *params;
     return 0;
@@ -755,33 +799,71 @@ size_t ZSTD_CCtx_setParametersUsingCCtxParams(
 ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize)
 {
     DEBUGLOG(4, "ZSTD_CCtx_setPledgedSrcSize to %u bytes", (U32)pledgedSrcSize);
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
     cctx->pledgedSrcSizePlusOne = pledgedSrcSize+1;
     return 0;
 }
 
+/**
+ * Initializes the local dict using the requested parameters.
+ * NOTE: This does not use the pledged src size, because it may be used for more
+ * than one compression.
+ */
+static size_t ZSTD_initLocalDict(ZSTD_CCtx* cctx)
+{
+    ZSTD_localDict* const dl = &cctx->localDict;
+    ZSTD_compressionParameters const cParams = ZSTD_getCParamsFromCCtxParams(
+            &cctx->requestedParams, 0, dl->dictSize);
+    if (dl->dict == NULL) {
+        /* No local dictionary. */
+        assert(dl->dictBuffer == NULL);
+        assert(dl->cdict == NULL);
+        assert(dl->dictSize == 0);
+        return 0;
+    }
+    if (dl->cdict != NULL) {
+        assert(cctx->cdict == dl->cdict);
+        /* Local dictionary already initialized. */
+        return 0;
+    }
+    assert(dl->dictSize > 0);
+    assert(cctx->cdict == NULL);
+    assert(cctx->prefixDict.dict == NULL);
+
+    dl->cdict = ZSTD_createCDict_advanced(
+            dl->dict,
+            dl->dictSize,
+            ZSTD_dlm_byRef,
+            dl->dictContentType,
+            cParams,
+            cctx->customMem);
+    RETURN_ERROR_IF(!dl->cdict, memory_allocation);
+    cctx->cdict = dl->cdict;
+    return 0;
+}
+
 size_t ZSTD_CCtx_loadDictionary_advanced(
         ZSTD_CCtx* cctx, const void* dict, size_t dictSize,
         ZSTD_dictLoadMethod_e dictLoadMethod, ZSTD_dictContentType_e dictContentType)
 {
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-    if (cctx->staticSize) return ERROR(memory_allocation);  /* no malloc for static CCtx */
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    RETURN_ERROR_IF(cctx->staticSize, memory_allocation,
+                    "no malloc for static CCtx");
     DEBUGLOG(4, "ZSTD_CCtx_loadDictionary_advanced (size: %u)", (U32)dictSize);
-    ZSTD_freeCDict(cctx->cdictLocal);  /* in case one already exists */
-    if (dict==NULL || dictSize==0) {   /* no dictionary mode */
-        cctx->cdictLocal = NULL;
-        cctx->cdict = NULL;
+    ZSTD_clearAllDicts(cctx);  /* in case one already exists */
+    if (dict == NULL || dictSize == 0)  /* no dictionary mode */
+        return 0;
+    if (dictLoadMethod == ZSTD_dlm_byRef) {
+        cctx->localDict.dict = dict;
     } else {
-        ZSTD_compressionParameters const cParams =
-                ZSTD_getCParamsFromCCtxParams(&cctx->requestedParams, cctx->pledgedSrcSizePlusOne-1, dictSize);
-        cctx->cdictLocal = ZSTD_createCDict_advanced(
-                                dict, dictSize,
-                                dictLoadMethod, dictContentType,
-                                cParams, cctx->customMem);
-        cctx->cdict = cctx->cdictLocal;
-        if (cctx->cdictLocal == NULL)
-            return ERROR(memory_allocation);
+        void* dictBuffer = ZSTD_malloc(dictSize, cctx->customMem);
+        RETURN_ERROR_IF(!dictBuffer, memory_allocation);
+        memcpy(dictBuffer, dict, dictSize);
+        cctx->localDict.dictBuffer = dictBuffer;
+        cctx->localDict.dict = dictBuffer;
     }
+    cctx->localDict.dictSize = dictSize;
+    cctx->localDict.dictContentType = dictContentType;
     return 0;
 }
 
@@ -801,9 +883,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, s
 
 size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict)
 {
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    /* Free the existing local cdict (if any) to save memory. */
+    ZSTD_clearAllDicts(cctx);
     cctx->cdict = cdict;
-    memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));  /* exclusive */
     return 0;
 }
 
@@ -815,8 +898,8 @@ size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx, const void* prefix, size_t prefixSiz
 size_t ZSTD_CCtx_refPrefix_advanced(
         ZSTD_CCtx* cctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
 {
-    if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-    cctx->cdict = NULL;   /* prefix discards any prior cdict */
+    RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+    ZSTD_clearAllDicts(cctx);
     cctx->prefixDict.dict = prefix;
     cctx->prefixDict.dictSize = prefixSize;
     cctx->prefixDict.dictContentType = dictContentType;
@@ -834,8 +917,8 @@ size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset)
     }
     if ( (reset == ZSTD_reset_parameters)
       || (reset == ZSTD_reset_session_and_parameters) ) {
-        if (cctx->streamStage != zcss_init) return ERROR(stage_wrong);
-        cctx->cdict = NULL;
+        RETURN_ERROR_IF(cctx->streamStage != zcss_init, stage_wrong);
+        ZSTD_clearAllDicts(cctx);
         return ZSTD_CCtxParams_reset(&cctx->requestedParams);
     }
     return 0;
@@ -888,10 +971,11 @@ static U32 ZSTD_cycleLog(U32 hashLog, ZSTD_strategy strat)
 }
 
 /** ZSTD_adjustCParams_internal() :
-    optimize `cPar` for a given input (`srcSize` and `dictSize`).
-    mostly downsizing to reduce memory consumption and initialization latency.
-    Both `srcSize` and `dictSize` are optional (use 0 if unknown).
-    Note : cPar is assumed validated. Use ZSTD_checkCParams() to ensure this condition. */
+ *  optimize `cPar` for a specified input (`srcSize` and `dictSize`).
+ *  mostly downsize to reduce memory consumption and initialization latency.
+ * `srcSize` can be ZSTD_CONTENTSIZE_UNKNOWN when not known.
+ *  note : for the time being, `srcSize==0` means "unknown" too, for compatibility with older convention.
+ *  condition : cPar is presumed validated (can be checked using ZSTD_checkCParams()). */
 static ZSTD_compressionParameters
 ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
                             unsigned long long srcSize,
@@ -901,7 +985,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
     static const U64 maxWindowResize = 1ULL << (ZSTD_WINDOWLOG_MAX-1);
     assert(ZSTD_checkCParams(cPar)==0);
 
-    if (dictSize && (srcSize+1<2) /* srcSize unknown */ )
+    if (dictSize && (srcSize+1<2) /* ZSTD_CONTENTSIZE_UNKNOWN and 0 mean "unknown" */ )
         srcSize = minSrcSize;  /* presumed small when there is a dictionary */
     else if (srcSize == 0)
         srcSize = ZSTD_CONTENTSIZE_UNKNOWN;  /* 0 == unknown : presumed large */
@@ -922,7 +1006,7 @@ ZSTD_adjustCParams_internal(ZSTD_compressionParameters cPar,
     }
 
     if (cPar.windowLog < ZSTD_WINDOWLOG_ABSOLUTEMIN)
-        cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN;  /* required for frame header */
+        cPar.windowLog = ZSTD_WINDOWLOG_ABSOLUTEMIN;  /* minimum wlog required for valid frame header */
 
     return cPar;
 }
@@ -932,7 +1016,7 @@ ZSTD_adjustCParams(ZSTD_compressionParameters cPar,
                    unsigned long long srcSize,
                    size_t dictSize)
 {
-    cPar = ZSTD_clampCParams(cPar);
+    cPar = ZSTD_clampCParams(cPar);   /* resulting cPar is necessarily valid (all parameters within range) */
     return ZSTD_adjustCParams_internal(cPar, srcSize, dictSize);
 }
 
@@ -973,8 +1057,7 @@ ZSTD_sizeof_matchState(const ZSTD_compressionParameters* const cParams,
 
 size_t ZSTD_estimateCCtxSize_usingCCtxParams(const ZSTD_CCtx_params* params)
 {
-    /* Estimate CCtx size is supported for single-threaded compression only. */
-    if (params->nbWorkers > 0) { return ERROR(GENERIC); }
+    RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only.");
     {   ZSTD_compressionParameters const cParams =
                 ZSTD_getCParamsFromCCtxParams(params, 0, 0);
         size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
@@ -1022,10 +1105,12 @@ size_t ZSTD_estimateCCtxSize(int compressionLevel)
 
 size_t ZSTD_estimateCStreamSize_usingCCtxParams(const ZSTD_CCtx_params* params)
 {
-    if (params->nbWorkers > 0) { return ERROR(GENERIC); }
-    {   size_t const CCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params);
-        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << params->cParams.windowLog);
-        size_t const inBuffSize = ((size_t)1 << params->cParams.windowLog) + blockSize;
+    RETURN_ERROR_IF(params->nbWorkers > 0, GENERIC, "Estimate CCtx size is supported for single-threaded compression only.");
+    {   ZSTD_compressionParameters const cParams =
+                ZSTD_getCParamsFromCCtxParams(params, 0, 0);
+        size_t const CCtxSize = ZSTD_estimateCCtxSize_usingCCtxParams(params);
+        size_t const blockSize = MIN(ZSTD_BLOCKSIZE_MAX, (size_t)1 << cParams.windowLog);
+        size_t const inBuffSize = ((size_t)1 << cParams.windowLog) + blockSize;
         size_t const outBuffSize = ZSTD_compressBound(blockSize) + 1;
         size_t const streamingSize = inBuffSize + outBuffSize;
 
@@ -1367,13 +1452,13 @@ static size_t ZSTD_resetCCtx_internal(ZSTD_CCtx* zc,
                 DEBUGLOG(4, "Need to resize workSpaceSize from %zuKB to %zuKB",
                             zc->workSpaceSize >> 10,
                             neededSpace >> 10);
-                /* static cctx : no resize, error out */
-                if (zc->staticSize) return ERROR(memory_allocation);
+
+                RETURN_ERROR_IF(zc->staticSize, memory_allocation, "static cctx : no resize");
 
                 zc->workSpaceSize = 0;
                 ZSTD_free(zc->workSpace, zc->customMem);
                 zc->workSpace = ZSTD_malloc(neededSpace, zc->customMem);
-                if (zc->workSpace == NULL) return ERROR(memory_allocation);
+                RETURN_ERROR_IF(zc->workSpace == NULL, memory_allocation);
                 zc->workSpaceSize = neededSpace;
                 zc->workSpaceOversizedDuration = 0;
 
@@ -1644,7 +1729,7 @@ static size_t ZSTD_copyCCtx_internal(ZSTD_CCtx* dstCCtx,
                             ZSTD_buffered_policy_e zbuff)
 {
     DEBUGLOG(5, "ZSTD_copyCCtx_internal");
-    if (srcCCtx->stage!=ZSTDcs_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(srcCCtx->stage!=ZSTDcs_init, stage_wrong);
 
     memcpy(&dstCCtx->customMem, &srcCCtx->customMem, sizeof(ZSTD_customMem));
     {   ZSTD_CCtx_params params = dstCCtx->requestedParams;
@@ -1777,7 +1862,8 @@ static void ZSTD_reduceIndex (ZSTD_CCtx* zc, const U32 reducerValue)
 static size_t ZSTD_noCompressBlock (void* dst, size_t dstCapacity, const void* src, size_t srcSize, U32 lastBlock)
 {
     U32 const cBlockHeader24 = lastBlock + (((U32)bt_raw)<<1) + (U32)(srcSize << 3);
-    if (srcSize + ZSTD_blockHeaderSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(srcSize + ZSTD_blockHeaderSize > dstCapacity,
+                    dstSize_tooSmall);
     MEM_writeLE24(dst, cBlockHeader24);
     memcpy((BYTE*)dst + ZSTD_blockHeaderSize, src, srcSize);
     return ZSTD_blockHeaderSize + srcSize;
@@ -1788,7 +1874,7 @@ static size_t ZSTD_noCompressLiterals (void* dst, size_t dstCapacity, const void
     BYTE* const ostart = (BYTE* const)dst;
     U32   const flSize = 1 + (srcSize>31) + (srcSize>4095);
 
-    if (srcSize + flSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(srcSize + flSize > dstCapacity, dstSize_tooSmall);
 
     switch(flSize)
     {
@@ -1878,7 +1964,7 @@ static size_t ZSTD_compressLiterals (ZSTD_hufCTables_t const* prevHuf,
         if (srcSize <= minLitSize) return ZSTD_noCompressLiterals(dst, dstCapacity, src, srcSize);
     }
 
-    if (dstCapacity < lhSize+1) return ERROR(dstSize_tooSmall);   /* not enough space for compression */
+    RETURN_ERROR_IF(dstCapacity < lhSize+1, dstSize_tooSmall, "not enough space for compression");
     {   HUF_repeat repeat = prevHuf->repeatMode;
         int const preferRepeat = strategy < ZSTD_lazy ? srcSize <= 1024 : 0;
         if (repeat == HUF_repeat_valid && lhSize == 3) singleStream = 1;
@@ -1960,7 +2046,7 @@ void ZSTD_seqToCodes(const seqStore_t* seqStorePtr)
  * If x == 0: Return 0
  * Else: Return floor(-log2(x / 256) * 256)
  */
-static unsigned const kInverseProbabiltyLog256[256] = {
+static unsigned const kInverseProbabilityLog256[256] = {
     0,    2048, 1792, 1642, 1536, 1453, 1386, 1329, 1280, 1236, 1197, 1162,
     1130, 1100, 1073, 1047, 1024, 1001, 980,  960,  941,  923,  906,  889,
     874,  859,  844,  830,  817,  804,  791,  779,  768,  756,  745,  734,
@@ -1999,7 +2085,7 @@ static size_t ZSTD_entropyCost(unsigned const* count, unsigned const max, size_t
         if (count[s] != 0 && norm == 0)
             norm = 1;
         assert(count[s] < total);
-        cost += count[s] * kInverseProbabiltyLog256[norm];
+        cost += count[s] * kInverseProbabilityLog256[norm];
     }
     return cost >> 8;
 }
@@ -2022,7 +2108,7 @@ static size_t ZSTD_crossEntropyCost(short const* norm, unsigned accuracyLog,
         unsigned const norm256 = normAcc << shift;
         assert(norm256 > 0);
         assert(norm256 < 256);
-        cost += count[s] * kInverseProbabiltyLog256[norm256];
+        cost += count[s] * kInverseProbabilityLog256[norm256];
     }
     return cost >> 8;
 }
@@ -2050,21 +2136,17 @@ static size_t ZSTD_fseBitCost(
     unsigned s;
     FSE_CState_t cstate;
     FSE_initCState(&cstate, ctable);
-    if (ZSTD_getFSEMaxSymbolValue(ctable) < max) {
-        DEBUGLOG(5, "Repeat FSE_CTable has maxSymbolValue %u < %u",
+    RETURN_ERROR_IF(ZSTD_getFSEMaxSymbolValue(ctable) < max, GENERIC,
+                    "Repeat FSE_CTable has maxSymbolValue %u < %u",
                     ZSTD_getFSEMaxSymbolValue(ctable), max);
-        return ERROR(GENERIC);
-    }
     for (s = 0; s <= max; ++s) {
         unsigned const tableLog = cstate.stateLog;
         unsigned const badCost = (tableLog + 1) << kAccuracyLog;
         unsigned const bitCost = FSE_bitCost(cstate.symbolTT, tableLog, s, kAccuracyLog);
         if (count[s] == 0)
             continue;
-        if (bitCost >= badCost) {
-            DEBUGLOG(5, "Repeat FSE_CTable has Prob[%u] == 0", s);
-            return ERROR(GENERIC);
-        }
+        RETURN_ERROR_IF(bitCost >= badCost, GENERIC,
+                        "Repeat FSE_CTable has Prob[%u] == 0", s);
         cost += count[s] * bitCost;
     }
     return cost >> kAccuracyLog;
@@ -2080,7 +2162,7 @@ static size_t ZSTD_NCountCost(unsigned const* count, unsigned const max,
     BYTE wksp[FSE_NCOUNTBOUND];
     S16 norm[MaxSeq + 1];
     const U32 tableLog = FSE_optimalTableLog(FSELog, nbSeq, max);
-    CHECK_F(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
+    FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq, max));
     return FSE_writeNCount(wksp, sizeof(wksp), norm, max, tableLog);
 }
 
@@ -2186,15 +2268,15 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity,
 
     switch (type) {
     case set_rle:
-        CHECK_F(FSE_buildCTable_rle(nextCTable, (BYTE)max));
-        if (dstCapacity==0) return ERROR(dstSize_tooSmall);
+        FORWARD_IF_ERROR(FSE_buildCTable_rle(nextCTable, (BYTE)max));
+        RETURN_ERROR_IF(dstCapacity==0, dstSize_tooSmall);
         *op = codeTable[0];
         return 1;
     case set_repeat:
         memcpy(nextCTable, prevCTable, prevCTableSize);
         return 0;
     case set_basic:
-        CHECK_F(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize));  /* note : could be pre-calculated */
+        FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, defaultNorm, defaultMax, defaultNormLog, workspace, workspaceSize));  /* note : could be pre-calculated */
         return 0;
     case set_compressed: {
         S16 norm[MaxSeq + 1];
@@ -2205,14 +2287,14 @@ ZSTD_buildCTable(void* dst, size_t dstCapacity,
             nbSeq_1--;
         }
         assert(nbSeq_1 > 1);
-        CHECK_F(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
+        FORWARD_IF_ERROR(FSE_normalizeCount(norm, tableLog, count, nbSeq_1, max));
         {   size_t const NCountSize = FSE_writeNCount(op, oend - op, norm, max, tableLog);   /* overflow protected */
-            if (FSE_isError(NCountSize)) return NCountSize;
-            CHECK_F(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
+            FORWARD_IF_ERROR(NCountSize);
+            FORWARD_IF_ERROR(FSE_buildCTable_wksp(nextCTable, norm, max, tableLog, workspace, workspaceSize));
             return NCountSize;
         }
     }
-    default: return assert(0), ERROR(GENERIC);
+    default: assert(0); RETURN_ERROR(GENERIC);
     }
 }
 
@@ -2229,7 +2311,9 @@ ZSTD_encodeSequences_body(
     FSE_CState_t  stateOffsetBits;
     FSE_CState_t  stateLitLength;
 
-    CHECK_E(BIT_initCStream(&blockStream, dst, dstCapacity), dstSize_tooSmall); /* not enough space remaining */
+    RETURN_ERROR_IF(
+        ERR_isError(BIT_initCStream(&blockStream, dst, dstCapacity)),
+        dstSize_tooSmall, "not enough space remaining");
     DEBUGLOG(6, "available space for bitstream : %i  (dstCapacity=%u)",
                 (int)(blockStream.endPtr - blockStream.startPtr),
                 (unsigned)dstCapacity);
@@ -2303,7 +2387,7 @@ ZSTD_encodeSequences_body(
     FSE_flushCState(&blockStream, &stateLitLength);
 
     {   size_t const streamSize = BIT_closeCStream(&blockStream);
-        if (streamSize==0) return ERROR(dstSize_tooSmall);   /* not enough space */
+        RETURN_ERROR_IF(streamSize==0, dstSize_tooSmall, "not enough space");
         return streamSize;
     }
 }
@@ -2368,6 +2452,21 @@ static size_t ZSTD_encodeSequences(
                                         sequences, nbSeq, longOffsets);
 }
 
+static int ZSTD_disableLiteralsCompression(const ZSTD_CCtx_params* cctxParams)
+{
+    switch (cctxParams->literalCompressionMode) {
+    case ZSTD_lcm_huffman:
+        return 0;
+    case ZSTD_lcm_uncompressed:
+        return 1;
+    default:
+        assert(0 /* impossible: pre-validated */);
+        /* fall-through */
+    case ZSTD_lcm_auto:
+        return (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0);
+    }
+}
+
 /* ZSTD_compressSequences_internal():
  * actually compresses both literals and sequences */
 MEM_STATIC size_t
@@ -2403,22 +2502,22 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
     /* Compress literals */
     {   const BYTE* const literals = seqStorePtr->litStart;
         size_t const litSize = seqStorePtr->lit - literals;
-        int const disableLiteralCompression = (cctxParams->cParams.strategy == ZSTD_fast) && (cctxParams->cParams.targetLength > 0);
         size_t const cSize = ZSTD_compressLiterals(
                                     &prevEntropy->huf, &nextEntropy->huf,
-                                    cctxParams->cParams.strategy, disableLiteralCompression,
+                                    cctxParams->cParams.strategy,
+                                    ZSTD_disableLiteralsCompression(cctxParams),
                                     op, dstCapacity,
                                     literals, litSize,
                                     workspace, wkspSize,
                                     bmi2);
-        if (ZSTD_isError(cSize))
-          return cSize;
+        FORWARD_IF_ERROR(cSize);
         assert(cSize <= dstCapacity);
         op += cSize;
     }
 
     /* Sequences Header */
-    if ((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF((oend-op) < 3 /*max nbSeq Size*/ + 1 /*seqHead*/,
+                    dstSize_tooSmall);
     if (nbSeq < 0x7F)
         *op++ = (BYTE)nbSeq;
     else if (nbSeq < LONGNBSEQ)
@@ -2452,7 +2551,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                                     count, max, llCodeTable, nbSeq, LL_defaultNorm, LL_defaultNormLog, MaxLL,
                                                     prevEntropy->fse.litlengthCTable, sizeof(prevEntropy->fse.litlengthCTable),
                                                     workspace, wkspSize);
-            if (ZSTD_isError(countSize)) return countSize;
+            FORWARD_IF_ERROR(countSize);
             if (LLtype == set_compressed)
                 lastNCount = op;
             op += countSize;
@@ -2474,7 +2573,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                                     count, max, ofCodeTable, nbSeq, OF_defaultNorm, OF_defaultNormLog, DefaultMaxOff,
                                                     prevEntropy->fse.offcodeCTable, sizeof(prevEntropy->fse.offcodeCTable),
                                                     workspace, wkspSize);
-            if (ZSTD_isError(countSize)) return countSize;
+            FORWARD_IF_ERROR(countSize);
             if (Offtype == set_compressed)
                 lastNCount = op;
             op += countSize;
@@ -2494,7 +2593,7 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                                     count, max, mlCodeTable, nbSeq, ML_defaultNorm, ML_defaultNormLog, MaxML,
                                                     prevEntropy->fse.matchlengthCTable, sizeof(prevEntropy->fse.matchlengthCTable),
                                                     workspace, wkspSize);
-            if (ZSTD_isError(countSize)) return countSize;
+            FORWARD_IF_ERROR(countSize);
             if (MLtype == set_compressed)
                 lastNCount = op;
             op += countSize;
@@ -2509,10 +2608,10 @@ ZSTD_compressSequences_internal(seqStore_t* seqStorePtr,
                                         CTable_LitLength, llCodeTable,
                                         sequences, nbSeq,
                                         longOffsets, bmi2);
-        if (ZSTD_isError(bitstreamSize)) return bitstreamSize;
+        FORWARD_IF_ERROR(bitstreamSize);
         op += bitstreamSize;
         /* zstd versions <= 1.3.4 mistakenly report corruption when
-         * FSE_readNCount() recieves a buffer < 4 bytes.
+         * FSE_readNCount() receives a buffer < 4 bytes.
          * Fixed by https://github.com/facebook/zstd/pull/1146.
          * This can happen when the last set_compressed table present is 2
          * bytes and the bitstream is only one byte.
@@ -2552,7 +2651,7 @@ ZSTD_compressSequences(seqStore_t* seqStorePtr,
      */
     if ((cSize == ERROR(dstSize_tooSmall)) & (srcSize <= dstCapacity))
         return 0;  /* block not compressed */
-    if (ZSTD_isError(cSize)) return cSize;
+    FORWARD_IF_ERROR(cSize);
 
     /* Check compressibility */
     {   size_t const maxCSize = srcSize - ZSTD_minGain(srcSize, cctxParams->cParams.strategy);
@@ -2641,7 +2740,10 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
         goto out;  /* don't even attempt compression below a certain srcSize */
     }
     ZSTD_resetSeqStore(&(zc->seqStore));
-    ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy;   /* required for optimal parser to read stats from dictionary */
+    /* required for optimal parser to read stats from dictionary */
+    ms->opt.symbolCosts = &zc->blockState.prevCBlock->entropy;
+    /* tell the optimal parser how we expect to compress literals */
+    ms->opt.literalCompressionMode = zc->appliedParams.literalCompressionMode;
 
     /* a gap between an attached dict and the current window is not safe,
      * they must remain adjacent,
@@ -2679,7 +2781,7 @@ static size_t ZSTD_compressBlock_internal(ZSTD_CCtx* zc,
             ldmSeqStore.seq = zc->ldmSequences;
             ldmSeqStore.capacity = zc->maxNbLdmSequences;
             /* Updates ldmSeqStore.size */
-            CHECK_F(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore,
+            FORWARD_IF_ERROR(ZSTD_ldm_generateSequences(&zc->ldmState, &ldmSeqStore,
                                                &zc->appliedParams.ldmParams,
                                                src, srcSize));
             /* Updates ldmSeqStore.pos */
@@ -2752,8 +2854,9 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
         ZSTD_matchState_t* const ms = &cctx->blockState.matchState;
         U32 const lastBlock = lastFrameChunk & (blockSize >= remaining);
 
-        if (dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE)
-            return ERROR(dstSize_tooSmall);   /* not enough space to store compressed block */
+        RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize + MIN_CBLOCK_SIZE,
+                        dstSize_tooSmall,
+                        "not enough space to store compressed block");
         if (remaining < blockSize) blockSize = remaining;
 
         if (ZSTD_window_needOverflowCorrection(ms->window, ip + blockSize)) {
@@ -2774,11 +2877,11 @@ static size_t ZSTD_compress_frameChunk (ZSTD_CCtx* cctx,
         {   size_t cSize = ZSTD_compressBlock_internal(cctx,
                                 op+ZSTD_blockHeaderSize, dstCapacity-ZSTD_blockHeaderSize,
                                 ip, blockSize);
-            if (ZSTD_isError(cSize)) return cSize;
+            FORWARD_IF_ERROR(cSize);
 
             if (cSize == 0) {  /* block is not compressible */
                 cSize = ZSTD_noCompressBlock(op, dstCapacity, ip, blockSize, lastBlock);
-                if (ZSTD_isError(cSize)) return cSize;
+                FORWARD_IF_ERROR(cSize);
             } else {
                 U32 const cBlockHeader24 = lastBlock + (((U32)bt_compressed)<<1) + (U32)(cSize << 3);
                 MEM_writeLE24(op, cBlockHeader24);
@@ -2811,11 +2914,11 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
     BYTE  const windowLogByte = (BYTE)((params.cParams.windowLog - ZSTD_WINDOWLOG_ABSOLUTEMIN) << 3);
     U32   const fcsCode = params.fParams.contentSizeFlag ?
                      (pledgedSrcSize>=256) + (pledgedSrcSize>=65536+256) + (pledgedSrcSize>=0xFFFFFFFFU) : 0;  /* 0-3 */
-    BYTE  const frameHeaderDecriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) );
+    BYTE  const frameHeaderDescriptionByte = (BYTE)(dictIDSizeCode + (checksumFlag<<2) + (singleSegment<<5) + (fcsCode<<6) );
     size_t pos=0;
 
     assert(!(params.fParams.contentSizeFlag && pledgedSrcSize == ZSTD_CONTENTSIZE_UNKNOWN));
-    if (dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(dstCapacity < ZSTD_FRAMEHEADERSIZE_MAX, dstSize_tooSmall);
     DEBUGLOG(4, "ZSTD_writeFrameHeader : dictIDFlag : %u ; dictID : %u ; dictIDSizeCode : %u",
                 !params.fParams.noDictIDFlag, (unsigned)dictID, (unsigned)dictIDSizeCode);
 
@@ -2823,7 +2926,7 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
         MEM_writeLE32(dst, ZSTD_MAGICNUMBER);
         pos = 4;
     }
-    op[pos++] = frameHeaderDecriptionByte;
+    op[pos++] = frameHeaderDescriptionByte;
     if (!singleSegment) op[pos++] = windowLogByte;
     switch(dictIDSizeCode)
     {
@@ -2847,11 +2950,11 @@ static size_t ZSTD_writeFrameHeader(void* dst, size_t dstCapacity,
 /* ZSTD_writeLastEmptyBlock() :
  * output an empty Block with end-of-frame mark to complete a frame
  * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
- *           or an error code if `dstCapcity` is too small (<ZSTD_blockHeaderSize)
+ *           or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
  */
 size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity)
 {
-    if (dstCapacity < ZSTD_blockHeaderSize) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(dstCapacity < ZSTD_blockHeaderSize, dstSize_tooSmall);
     {   U32 const cBlockHeader24 = 1 /*lastBlock*/ + (((U32)bt_raw)<<1);  /* 0 size */
         MEM_writeLE24(dst, cBlockHeader24);
         return ZSTD_blockHeaderSize;
@@ -2860,10 +2963,9 @@ size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity)
 
 size_t ZSTD_referenceExternalSequences(ZSTD_CCtx* cctx, rawSeq* seq, size_t nbSeq)
 {
-    if (cctx->stage != ZSTDcs_init)
-        return ERROR(stage_wrong);
-    if (cctx->appliedParams.ldmParams.enableLdm)
-        return ERROR(parameter_unsupported);
+    RETURN_ERROR_IF(cctx->stage != ZSTDcs_init, stage_wrong);
+    RETURN_ERROR_IF(cctx->appliedParams.ldmParams.enableLdm,
+                    parameter_unsupported);
     cctx->externSeqStore.seq = seq;
     cctx->externSeqStore.size = nbSeq;
     cctx->externSeqStore.capacity = nbSeq;
@@ -2882,12 +2984,13 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
 
     DEBUGLOG(5, "ZSTD_compressContinue_internal, stage: %u, srcSize: %u",
                 cctx->stage, (unsigned)srcSize);
-    if (cctx->stage==ZSTDcs_created) return ERROR(stage_wrong);   /* missing init (ZSTD_compressBegin) */
+    RETURN_ERROR_IF(cctx->stage==ZSTDcs_created, stage_wrong,
+                    "missing init (ZSTD_compressBegin)");
 
     if (frame && (cctx->stage==ZSTDcs_init)) {
         fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams,
                                        cctx->pledgedSrcSizePlusOne-1, cctx->dictID);
-        if (ZSTD_isError(fhSize)) return fhSize;
+        FORWARD_IF_ERROR(fhSize);
         dstCapacity -= fhSize;
         dst = (char*)dst + fhSize;
         cctx->stage = ZSTDcs_ongoing;
@@ -2922,17 +3025,18 @@ static size_t ZSTD_compressContinue_internal (ZSTD_CCtx* cctx,
     {   size_t const cSize = frame ?
                              ZSTD_compress_frameChunk (cctx, dst, dstCapacity, src, srcSize, lastFrameChunk) :
                              ZSTD_compressBlock_internal (cctx, dst, dstCapacity, src, srcSize);
-        if (ZSTD_isError(cSize)) return cSize;
+        FORWARD_IF_ERROR(cSize);
         cctx->consumedSrcSize += srcSize;
         cctx->producedCSize += (cSize + fhSize);
         assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0));
         if (cctx->pledgedSrcSizePlusOne != 0) {  /* control src size */
             ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1);
-            if (cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne) {
-                DEBUGLOG(4, "error : pledgedSrcSize = %u, while realSrcSize >= %u",
-                    (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize);
-                return ERROR(srcSize_wrong);
-            }
+            RETURN_ERROR_IF(
+                cctx->consumedSrcSize+1 > cctx->pledgedSrcSizePlusOne,
+                srcSize_wrong,
+                "error : pledgedSrcSize = %u, while realSrcSize >= %u",
+                (unsigned)cctx->pledgedSrcSizePlusOne-1,
+                (unsigned)cctx->consumedSrcSize);
         }
         return cSize + fhSize;
     }
@@ -2957,7 +3061,7 @@ size_t ZSTD_getBlockSize(const ZSTD_CCtx* cctx)
 size_t ZSTD_compressBlock(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
     size_t const blockSizeMax = ZSTD_getBlockSize(cctx);
-    if (srcSize > blockSizeMax) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize > blockSizeMax, srcSize_wrong);
 
     return ZSTD_compressContinue_internal(cctx, dst, dstCapacity, src, srcSize, 0 /* frame mode */, 0 /* last chunk */);
 }
@@ -3020,9 +3124,9 @@ static size_t ZSTD_loadDictionaryContent(ZSTD_matchState_t* ms,
    NOTE: This behavior is not standard and could be improved in the future. */
 static size_t ZSTD_checkDictNCount(short* normalizedCounter, unsigned dictMaxSymbolValue, unsigned maxSymbolValue) {
     U32 s;
-    if (dictMaxSymbolValue < maxSymbolValue) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictMaxSymbolValue < maxSymbolValue, dictionary_corrupted);
     for (s = 0; s <= maxSymbolValue; ++s) {
-        if (normalizedCounter[s] == 0) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(normalizedCounter[s] == 0, dictionary_corrupted);
     }
     return 0;
 }
@@ -3060,53 +3164,56 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
 
     {   unsigned maxSymbolValue = 255;
         size_t const hufHeaderSize = HUF_readCTable((HUF_CElt*)bs->entropy.huf.CTable, &maxSymbolValue, dictPtr, dictEnd-dictPtr);
-        if (HUF_isError(hufHeaderSize)) return ERROR(dictionary_corrupted);
-        if (maxSymbolValue < 255) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(HUF_isError(hufHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(maxSymbolValue < 255, dictionary_corrupted);
         dictPtr += hufHeaderSize;
     }
 
     {   unsigned offcodeLog;
         size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted);
-        if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted);
         /* Defer checking offcodeMaxValue because we need to know the size of the dictionary content */
         /* fill all offset symbols to avoid garbage at end of table */
-        CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.offcodeCTable,
-                                    offcodeNCount, MaxOff, offcodeLog,
-                                    workspace, HUF_WORKSPACE_SIZE),
-                 dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.offcodeCTable,
+                offcodeNCount, MaxOff, offcodeLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted);
         dictPtr += offcodeHeaderSize;
     }
 
     {   short matchlengthNCount[MaxML+1];
         unsigned matchlengthMaxValue = MaxML, matchlengthLog;
         size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted);
         /* Every match length code must have non-zero probability */
-        CHECK_F( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
-        CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.matchlengthCTable,
-                                    matchlengthNCount, matchlengthMaxValue, matchlengthLog,
-                                    workspace, HUF_WORKSPACE_SIZE),
-                 dictionary_corrupted);
+        FORWARD_IF_ERROR( ZSTD_checkDictNCount(matchlengthNCount, matchlengthMaxValue, MaxML));
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.matchlengthCTable,
+                matchlengthNCount, matchlengthMaxValue, matchlengthLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted);
         dictPtr += matchlengthHeaderSize;
     }
 
     {   short litlengthNCount[MaxLL+1];
         unsigned litlengthMaxValue = MaxLL, litlengthLog;
         size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted);
         /* Every literal length code must have non-zero probability */
-        CHECK_F( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
-        CHECK_E( FSE_buildCTable_wksp(bs->entropy.fse.litlengthCTable,
-                                    litlengthNCount, litlengthMaxValue, litlengthLog,
-                                    workspace, HUF_WORKSPACE_SIZE),
-                 dictionary_corrupted);
+        FORWARD_IF_ERROR( ZSTD_checkDictNCount(litlengthNCount, litlengthMaxValue, MaxLL));
+        RETURN_ERROR_IF(FSE_isError(FSE_buildCTable_wksp(
+                bs->entropy.fse.litlengthCTable,
+                litlengthNCount, litlengthMaxValue, litlengthLog,
+                workspace, HUF_WORKSPACE_SIZE)),
+            dictionary_corrupted);
         dictPtr += litlengthHeaderSize;
     }
 
-    if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted);
     bs->rep[0] = MEM_readLE32(dictPtr+0);
     bs->rep[1] = MEM_readLE32(dictPtr+4);
     bs->rep[2] = MEM_readLE32(dictPtr+8);
@@ -3119,19 +3226,19 @@ static size_t ZSTD_loadZstdDictionary(ZSTD_compressedBlockState_t* bs,
             offcodeMax = ZSTD_highbit32(maxOffset); /* Calculate minimum offset code required to represent maxOffset */
         }
         /* All offset values <= dictContentSize + 128 KB must be representable */
-        CHECK_F (ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)));
+        FORWARD_IF_ERROR(ZSTD_checkDictNCount(offcodeNCount, offcodeMaxValue, MIN(offcodeMax, MaxOff)));
         /* All repCodes must be <= dictContentSize and != 0*/
         {   U32 u;
             for (u=0; u<3; u++) {
-                if (bs->rep[u] == 0) return ERROR(dictionary_corrupted);
-                if (bs->rep[u] > dictContentSize) return ERROR(dictionary_corrupted);
+                RETURN_ERROR_IF(bs->rep[u] == 0, dictionary_corrupted);
+                RETURN_ERROR_IF(bs->rep[u] > dictContentSize, dictionary_corrupted);
         }   }
 
         bs->entropy.huf.repeatMode = HUF_repeat_valid;
         bs->entropy.fse.offcode_repeatMode = FSE_repeat_valid;
         bs->entropy.fse.matchlength_repeatMode = FSE_repeat_valid;
         bs->entropy.fse.litlength_repeatMode = FSE_repeat_valid;
-        CHECK_F(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm));
+        FORWARD_IF_ERROR(ZSTD_loadDictionaryContent(ms, params, dictPtr, dictContentSize, dtlm));
         return dictID;
     }
 }
@@ -3161,8 +3268,7 @@ ZSTD_compress_insertDictionary(ZSTD_compressedBlockState_t* bs,
             DEBUGLOG(4, "raw content dictionary detected");
             return ZSTD_loadDictionaryContent(ms, params, dict, dictSize, dtlm);
         }
-        if (dictContentType == ZSTD_dct_fullDict)
-            return ERROR(dictionary_wrong);
+        RETURN_ERROR_IF(dictContentType == ZSTD_dct_fullDict, dictionary_wrong);
         assert(0);   /* impossible */
     }
 
@@ -3189,13 +3295,13 @@ static size_t ZSTD_compressBegin_internal(ZSTD_CCtx* cctx,
         return ZSTD_resetCCtx_usingCDict(cctx, cdict, params, pledgedSrcSize, zbuff);
     }
 
-    CHECK_F( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
+    FORWARD_IF_ERROR( ZSTD_resetCCtx_internal(cctx, params, pledgedSrcSize,
                                      ZSTDcrp_continue, zbuff) );
     {
         size_t const dictID = ZSTD_compress_insertDictionary(
                 cctx->blockState.prevCBlock, &cctx->blockState.matchState,
                 &params, dict, dictSize, dictContentType, dtlm, cctx->entropyWorkspace);
-        if (ZSTD_isError(dictID)) return dictID;
+        FORWARD_IF_ERROR(dictID);
         assert(dictID <= (size_t)(U32)-1);
         cctx->dictID = (U32)dictID;
     }
@@ -3212,7 +3318,7 @@ size_t ZSTD_compressBegin_advanced_internal(ZSTD_CCtx* cctx,
 {
     DEBUGLOG(4, "ZSTD_compressBegin_advanced_internal: wlog=%u", params.cParams.windowLog);
     /* compression parameters verification and optimization */
-    CHECK_F( ZSTD_checkCParams(params.cParams) );
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) );
     return ZSTD_compressBegin_internal(cctx,
                                        dict, dictSize, dictContentType, dtlm,
                                        cdict,
@@ -3260,12 +3366,12 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
     size_t fhSize = 0;
 
     DEBUGLOG(4, "ZSTD_writeEpilogue");
-    if (cctx->stage == ZSTDcs_created) return ERROR(stage_wrong);  /* init missing */
+    RETURN_ERROR_IF(cctx->stage == ZSTDcs_created, stage_wrong, "init missing");
 
     /* special case : empty frame */
     if (cctx->stage == ZSTDcs_init) {
         fhSize = ZSTD_writeFrameHeader(dst, dstCapacity, cctx->appliedParams, 0, 0);
-        if (ZSTD_isError(fhSize)) return fhSize;
+        FORWARD_IF_ERROR(fhSize);
         dstCapacity -= fhSize;
         op += fhSize;
         cctx->stage = ZSTDcs_ongoing;
@@ -3274,7 +3380,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
     if (cctx->stage != ZSTDcs_ending) {
         /* write one last empty block, make it the "last" block */
         U32 const cBlockHeader24 = 1 /* last block */ + (((U32)bt_raw)<<1) + 0;
-        if (dstCapacity<4) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall);
         MEM_writeLE32(op, cBlockHeader24);
         op += ZSTD_blockHeaderSize;
         dstCapacity -= ZSTD_blockHeaderSize;
@@ -3282,7 +3388,7 @@ static size_t ZSTD_writeEpilogue(ZSTD_CCtx* cctx, void* dst, size_t dstCapacity)
 
     if (cctx->appliedParams.fParams.checksumFlag) {
         U32 const checksum = (U32) XXH64_digest(&cctx->xxhState);
-        if (dstCapacity<4) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(dstCapacity<4, dstSize_tooSmall);
         DEBUGLOG(4, "ZSTD_writeEpilogue: write checksum : %08X", (unsigned)checksum);
         MEM_writeLE32(op, checksum);
         op += 4;
@@ -3300,18 +3406,20 @@ size_t ZSTD_compressEnd (ZSTD_CCtx* cctx,
     size_t const cSize = ZSTD_compressContinue_internal(cctx,
                                 dst, dstCapacity, src, srcSize,
                                 1 /* frame mode */, 1 /* last chunk */);
-    if (ZSTD_isError(cSize)) return cSize;
+    FORWARD_IF_ERROR(cSize);
     endResult = ZSTD_writeEpilogue(cctx, (char*)dst + cSize, dstCapacity-cSize);
-    if (ZSTD_isError(endResult)) return endResult;
+    FORWARD_IF_ERROR(endResult);
     assert(!(cctx->appliedParams.fParams.contentSizeFlag && cctx->pledgedSrcSizePlusOne == 0));
     if (cctx->pledgedSrcSizePlusOne != 0) {  /* control src size */
         ZSTD_STATIC_ASSERT(ZSTD_CONTENTSIZE_UNKNOWN == (unsigned long long)-1);
         DEBUGLOG(4, "end of frame : controlling src size");
-        if (cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1) {
-            DEBUGLOG(4, "error : pledgedSrcSize = %u, while realSrcSize = %u",
-                (unsigned)cctx->pledgedSrcSizePlusOne-1, (unsigned)cctx->consumedSrcSize);
-            return ERROR(srcSize_wrong);
-    }   }
+        RETURN_ERROR_IF(
+            cctx->pledgedSrcSizePlusOne != cctx->consumedSrcSize+1,
+            srcSize_wrong,
+             "error : pledgedSrcSize = %u, while realSrcSize = %u",
+            (unsigned)cctx->pledgedSrcSizePlusOne-1,
+            (unsigned)cctx->consumedSrcSize);
+    }
     return cSize + endResult;
 }
 
@@ -3339,7 +3447,7 @@ size_t ZSTD_compress_advanced (ZSTD_CCtx* cctx,
                                ZSTD_parameters params)
 {
     DEBUGLOG(4, "ZSTD_compress_advanced");
-    CHECK_F(ZSTD_checkCParams(params.cParams));
+    FORWARD_IF_ERROR(ZSTD_checkCParams(params.cParams));
     return ZSTD_compress_internal(cctx,
                                   dst, dstCapacity,
                                   src, srcSize,
@@ -3356,7 +3464,7 @@ size_t ZSTD_compress_advanced_internal(
         ZSTD_CCtx_params params)
 {
     DEBUGLOG(4, "ZSTD_compress_advanced_internal (srcSize:%u)", (unsigned)srcSize);
-    CHECK_F( ZSTD_compressBegin_internal(cctx,
+    FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx,
                          dict, dictSize, ZSTD_dct_auto, ZSTD_dtlm_fast, NULL,
                          params, srcSize, ZSTDb_not_buffered) );
     return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
@@ -3440,7 +3548,7 @@ static size_t ZSTD_initCDict_internal(
         void* const internalBuffer = ZSTD_malloc(dictSize, cdict->customMem);
         cdict->dictBuffer = internalBuffer;
         cdict->dictContent = internalBuffer;
-        if (!internalBuffer) return ERROR(memory_allocation);
+        RETURN_ERROR_IF(!internalBuffer, memory_allocation);
         memcpy(internalBuffer, dictBuffer, dictSize);
     }
     cdict->dictContentSize = dictSize;
@@ -3466,7 +3574,7 @@ static size_t ZSTD_initCDict_internal(
                     &cdict->cBlockState, &cdict->matchState, &params,
                     cdict->dictContent, cdict->dictContentSize,
                     dictContentType, ZSTD_dtlm_full, cdict->workspace);
-            if (ZSTD_isError(dictID)) return dictID;
+            FORWARD_IF_ERROR(dictID);
             assert(dictID <= (size_t)(U32)-1);
             cdict->dictID = (U32)dictID;
         }
@@ -3596,7 +3704,7 @@ size_t ZSTD_compressBegin_usingCDict_advanced(
     ZSTD_frameParameters const fParams, unsigned long long const pledgedSrcSize)
 {
     DEBUGLOG(4, "ZSTD_compressBegin_usingCDict_advanced");
-    if (cdict==NULL) return ERROR(dictionary_wrong);
+    RETURN_ERROR_IF(cdict==NULL, dictionary_wrong);
     {   ZSTD_CCtx_params params = cctx->requestedParams;
         params.cParams = ZSTD_getCParamsFromCDict(cdict);
         /* Increase window log to fit the entire dictionary and source if the
@@ -3632,7 +3740,7 @@ size_t ZSTD_compress_usingCDict_advanced(ZSTD_CCtx* cctx,
                                 const void* src, size_t srcSize,
                                 const ZSTD_CDict* cdict, ZSTD_frameParameters fParams)
 {
-    CHECK_F (ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize));   /* will check if cdict != NULL */
+    FORWARD_IF_ERROR(ZSTD_compressBegin_usingCDict_advanced(cctx, cdict, fParams, srcSize));   /* will check if cdict != NULL */
     return ZSTD_compressEnd(cctx, dst, dstCapacity, src, srcSize);
 }
 
@@ -3700,7 +3808,7 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* cctx,
     assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
     assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
 
-    CHECK_F( ZSTD_compressBegin_internal(cctx,
+    FORWARD_IF_ERROR( ZSTD_compressBegin_internal(cctx,
                                          dict, dictSize, dictContentType, ZSTD_dtlm_fast,
                                          cdict,
                                          params, pledgedSrcSize,
@@ -3718,13 +3826,17 @@ static size_t ZSTD_resetCStream_internal(ZSTD_CStream* cctx,
 
 /* ZSTD_resetCStream():
  * pledgedSrcSize == 0 means "unknown" */
-size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pledgedSrcSize)
+size_t ZSTD_resetCStream(ZSTD_CStream* zcs, unsigned long long pss)
 {
-    ZSTD_CCtx_params params = zcs->requestedParams;
+    /* temporary : 0 interpreted as "unknown" during transition period.
+     * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN.
+     * 0 will be interpreted as "empty" in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
     DEBUGLOG(4, "ZSTD_resetCStream: pledgedSrcSize = %u", (unsigned)pledgedSrcSize);
-    if (pledgedSrcSize==0) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN;
-    params.fParams.contentSizeFlag = 1;
-    return ZSTD_resetCStream_internal(zcs, NULL, 0, ZSTD_dct_auto, zcs->cdict, params, pledgedSrcSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    return 0;
 }
 
 /*! ZSTD_initCStream_internal() :
@@ -3736,32 +3848,18 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
                     ZSTD_CCtx_params params, unsigned long long pledgedSrcSize)
 {
     DEBUGLOG(4, "ZSTD_initCStream_internal");
-    params.cParams = ZSTD_getCParamsFromCCtxParams(&params, pledgedSrcSize, dictSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
     assert(!ZSTD_isError(ZSTD_checkCParams(params.cParams)));
+    zcs->requestedParams = params;
     assert(!((dict) && (cdict)));  /* either dict or cdict, not both */
-
-    if (dict && dictSize >= 8) {
-        DEBUGLOG(4, "loading dictionary of size %u", (unsigned)dictSize);
-        if (zcs->staticSize) {   /* static CCtx : never uses malloc */
-            /* incompatible with internal cdict creation */
-            return ERROR(memory_allocation);
-        }
-        ZSTD_freeCDict(zcs->cdictLocal);
-        zcs->cdictLocal = ZSTD_createCDict_advanced(dict, dictSize,
-                                            ZSTD_dlm_byCopy, ZSTD_dct_auto,
-                                            params.cParams, zcs->customMem);
-        zcs->cdict = zcs->cdictLocal;
-        if (zcs->cdictLocal == NULL) return ERROR(memory_allocation);
+    if (dict) {
+        FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) );
     } else {
-        if (cdict) {
-            params.cParams = ZSTD_getCParamsFromCDict(cdict);  /* cParams are enforced from cdict; it includes windowLog */
-        }
-        ZSTD_freeCDict(zcs->cdictLocal);
-        zcs->cdictLocal = NULL;
-        zcs->cdict = cdict;
+        /* Dictionary is cleared if !cdict */
+        FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) );
     }
-
-    return ZSTD_resetCStream_internal(zcs, NULL, 0, ZSTD_dct_auto, zcs->cdict, params, pledgedSrcSize);
+    return 0;
 }
 
 /* ZSTD_initCStream_usingCDict_advanced() :
@@ -3772,22 +3870,20 @@ size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs,
                                             unsigned long long pledgedSrcSize)
 {
     DEBUGLOG(4, "ZSTD_initCStream_usingCDict_advanced");
-    if (!cdict) return ERROR(dictionary_wrong); /* cannot handle NULL cdict (does not know what to do) */
-    {   ZSTD_CCtx_params params = zcs->requestedParams;
-        params.cParams = ZSTD_getCParamsFromCDict(cdict);
-        params.fParams = fParams;
-        return ZSTD_initCStream_internal(zcs,
-                                NULL, 0, cdict,
-                                params, pledgedSrcSize);
-    }
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    zcs->requestedParams.fParams = fParams;
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) );
+    return 0;
 }
 
 /* note : cdict must outlive compression session */
 size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
 {
-    ZSTD_frameParameters const fParams = { 0 /* contentSizeFlag */, 0 /* checksum */, 0 /* hideDictID */ };
     DEBUGLOG(4, "ZSTD_initCStream_usingCDict");
-    return ZSTD_initCStream_usingCDict_advanced(zcs, cdict, fParams, ZSTD_CONTENTSIZE_UNKNOWN);  /* note : will check that cdict != NULL */
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, cdict) );
+    return 0;
 }
 
 
@@ -3797,33 +3893,53 @@ size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict)
  * dict is loaded with default parameters ZSTD_dm_auto and ZSTD_dlm_byCopy. */
 size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs,
                                  const void* dict, size_t dictSize,
-                                 ZSTD_parameters params, unsigned long long pledgedSrcSize)
+                                 ZSTD_parameters params, unsigned long long pss)
 {
-    DEBUGLOG(4, "ZSTD_initCStream_advanced: pledgedSrcSize=%u, flag=%u",
-                (unsigned)pledgedSrcSize, params.fParams.contentSizeFlag);
-    CHECK_F( ZSTD_checkCParams(params.cParams) );
-    if ((pledgedSrcSize==0) && (params.fParams.contentSizeFlag==0)) pledgedSrcSize = ZSTD_CONTENTSIZE_UNKNOWN;  /* for compatibility with older programs relying on this behavior. Users should now specify ZSTD_CONTENTSIZE_UNKNOWN. This line will be removed in the future. */
+    /* for compatibility with older programs relying on this behavior.
+     * Users should now specify ZSTD_CONTENTSIZE_UNKNOWN.
+     * This line will be removed in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0 && params.fParams.contentSizeFlag==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_initCStream_advanced");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    FORWARD_IF_ERROR( ZSTD_checkCParams(params.cParams) );
     zcs->requestedParams = ZSTD_assignParamsToCCtxParams(zcs->requestedParams, params);
-    return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL /*cdict*/, zcs->requestedParams, pledgedSrcSize);
+    FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) );
+    return 0;
 }
 
 size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel)
 {
-    ZSTD_CCtxParams_init(&zcs->requestedParams, compressionLevel);
-    return ZSTD_initCStream_internal(zcs, dict, dictSize, NULL, zcs->requestedParams, ZSTD_CONTENTSIZE_UNKNOWN);
+    DEBUGLOG(4, "ZSTD_initCStream_usingDict");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_loadDictionary(zcs, dict, dictSize) );
+    return 0;
 }
 
 size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pss)
 {
-    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;  /* temporary : 0 interpreted as "unknown" during transition period. Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN. `0` will be interpreted as "empty" in the future */
-    ZSTD_CCtxParams_init(&zcs->requestedParams, compressionLevel);
-    return ZSTD_initCStream_internal(zcs, NULL, 0, NULL, zcs->requestedParams, pledgedSrcSize);
+    /* temporary : 0 interpreted as "unknown" during transition period.
+     * Users willing to specify "unknown" **must** use ZSTD_CONTENTSIZE_UNKNOWN.
+     * 0 will be interpreted as "empty" in the future.
+     */
+    U64 const pledgedSrcSize = (pss==0) ? ZSTD_CONTENTSIZE_UNKNOWN : pss;
+    DEBUGLOG(4, "ZSTD_initCStream_srcSize");
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize) );
+    return 0;
 }
 
 size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel)
 {
     DEBUGLOG(4, "ZSTD_initCStream");
-    return ZSTD_initCStream_srcSize(zcs, compressionLevel, ZSTD_CONTENTSIZE_UNKNOWN);
+    FORWARD_IF_ERROR( ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_refCDict(zcs, NULL) );
+    FORWARD_IF_ERROR( ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel) );
+    return 0;
 }
 
 /*======   Compression   ======*/
@@ -3847,10 +3963,10 @@ static size_t ZSTD_limitCopy(void* dst, size_t dstCapacity,
  *  internal function for all *compressStream*() variants
  *  non-static, because can be called from zstdmt_compress.c
  * @return : hint size for next input */
-size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
-                                   ZSTD_outBuffer* output,
-                                   ZSTD_inBuffer* input,
-                                   ZSTD_EndDirective const flushMode)
+static size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
+                                          ZSTD_outBuffer* output,
+                                          ZSTD_inBuffer* input,
+                                          ZSTD_EndDirective const flushMode)
 {
     const char* const istart = (const char*)input->src;
     const char* const iend = istart + input->size;
@@ -3873,8 +3989,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
         switch(zcs->streamStage)
         {
         case zcss_init:
-            /* call ZSTD_initCStream() first ! */
-            return ERROR(init_missing);
+            RETURN_ERROR(init_missing, "call ZSTD_initCStream() first!");
 
         case zcss_load:
             if ( (flushMode == ZSTD_e_end)
@@ -3884,7 +3999,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
                 size_t const cSize = ZSTD_compressEnd(zcs,
                                                 op, oend-op, ip, iend-ip);
                 DEBUGLOG(4, "ZSTD_compressEnd : cSize=%u", (unsigned)cSize);
-                if (ZSTD_isError(cSize)) return cSize;
+                FORWARD_IF_ERROR(cSize);
                 ip = iend;
                 op += cSize;
                 zcs->frameEnded = 1;
@@ -3925,7 +4040,7 @@ size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
                                     zcs->inBuff + zcs->inToCompress, iSize) :
                         ZSTD_compressContinue(zcs, cDst, oSize,
                                     zcs->inBuff + zcs->inToCompress, iSize);
-                if (ZSTD_isError(cSize)) return cSize;
+                FORWARD_IF_ERROR(cSize);
                 zcs->frameEnded = lastBlock;
                 /* prepare next block */
                 zcs->inBuffTarget = zcs->inBuffPos + zcs->blockSize;
@@ -4001,7 +4116,7 @@ static size_t ZSTD_nextInputSizeHint_MTorST(const ZSTD_CCtx* cctx)
 
 size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
 {
-    CHECK_F( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) );
+    FORWARD_IF_ERROR( ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue) );
     return ZSTD_nextInputSizeHint_MTorST(zcs);
 }
 
@@ -4013,14 +4128,15 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
 {
     DEBUGLOG(5, "ZSTD_compressStream2, endOp=%u ", (unsigned)endOp);
     /* check conditions */
-    if (output->pos > output->size) return ERROR(GENERIC);
-    if (input->pos  > input->size)  return ERROR(GENERIC);
+    RETURN_ERROR_IF(output->pos > output->size, GENERIC);
+    RETURN_ERROR_IF(input->pos  > input->size, GENERIC);
     assert(cctx!=NULL);
 
     /* transparent initialization stage */
     if (cctx->streamStage == zcss_init) {
         ZSTD_CCtx_params params = cctx->requestedParams;
         ZSTD_prefixDict const prefixDict = cctx->prefixDict;
+        FORWARD_IF_ERROR( ZSTD_initLocalDict(cctx) ); /* Init the local dict if present. */
         memset(&cctx->prefixDict, 0, sizeof(cctx->prefixDict));   /* single usage */
         assert(prefixDict.dict==NULL || cctx->cdict==NULL);    /* only one can be set */
         DEBUGLOG(4, "ZSTD_compressStream2 : transparent init stage");
@@ -4039,11 +4155,11 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
                 DEBUGLOG(4, "ZSTD_compressStream2: creating new mtctx for nbWorkers=%u",
                             params.nbWorkers);
                 cctx->mtctx = ZSTDMT_createCCtx_advanced(params.nbWorkers, cctx->customMem);
-                if (cctx->mtctx == NULL) return ERROR(memory_allocation);
+                RETURN_ERROR_IF(cctx->mtctx == NULL, memory_allocation);
             }
             /* mt compression */
             DEBUGLOG(4, "call ZSTDMT_initCStream_internal as nbWorkers=%u", params.nbWorkers);
-            CHECK_F( ZSTDMT_initCStream_internal(
+            FORWARD_IF_ERROR( ZSTDMT_initCStream_internal(
                         cctx->mtctx,
                         prefixDict.dict, prefixDict.dictSize, ZSTD_dct_rawContent,
                         cctx->cdict, params, cctx->pledgedSrcSizePlusOne-1) );
@@ -4051,7 +4167,7 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
             cctx->appliedParams.nbWorkers = params.nbWorkers;
         } else
 #endif
-        {   CHECK_F( ZSTD_resetCStream_internal(cctx,
+        {   FORWARD_IF_ERROR( ZSTD_resetCStream_internal(cctx,
                             prefixDict.dict, prefixDict.dictSize, prefixDict.dictContentType,
                             cctx->cdict,
                             params, cctx->pledgedSrcSizePlusOne-1) );
@@ -4063,20 +4179,30 @@ size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
     /* compression stage */
 #ifdef ZSTD_MULTITHREAD
     if (cctx->appliedParams.nbWorkers > 0) {
+        int const forceMaxProgress = (endOp == ZSTD_e_flush || endOp == ZSTD_e_end);
+        size_t flushMin;
+        assert(forceMaxProgress || endOp == ZSTD_e_continue /* Protection for a new flush type */);
         if (cctx->cParamsChanged) {
             ZSTDMT_updateCParams_whileCompressing(cctx->mtctx, &cctx->requestedParams);
             cctx->cParamsChanged = 0;
         }
-        {   size_t const flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp);
+        do {
+            flushMin = ZSTDMT_compressStream_generic(cctx->mtctx, output, input, endOp);
             if ( ZSTD_isError(flushMin)
               || (endOp == ZSTD_e_end && flushMin == 0) ) { /* compression completed */
                 ZSTD_CCtx_reset(cctx, ZSTD_reset_session_only);
             }
-            DEBUGLOG(5, "completed ZSTD_compressStream2 delegating to ZSTDMT_compressStream_generic");
-            return flushMin;
-    }   }
+            FORWARD_IF_ERROR(flushMin);
+        } while (forceMaxProgress && flushMin != 0 && output->pos < output->size);
+        DEBUGLOG(5, "completed ZSTD_compressStream2 delegating to ZSTDMT_compressStream_generic");
+        /* Either we don't require maximum forward progress, we've finished the
+         * flush, or we are out of output space.
+         */
+        assert(!forceMaxProgress || flushMin == 0 || output->pos == output->size);
+        return flushMin;
+    }
 #endif
-    CHECK_F( ZSTD_compressStream_generic(cctx, output, input, endOp) );
+    FORWARD_IF_ERROR( ZSTD_compressStream_generic(cctx, output, input, endOp) );
     DEBUGLOG(5, "completed ZSTD_compressStream2");
     return cctx->outBuffContentSize - cctx->outBuffFlushedSize; /* remaining to flush */
 }
@@ -4107,10 +4233,10 @@ size_t ZSTD_compress2(ZSTD_CCtx* cctx,
                                         dst, dstCapacity, &oPos,
                                         src, srcSize, &iPos,
                                         ZSTD_e_end);
-        if (ZSTD_isError(result)) return result;
+        FORWARD_IF_ERROR(result);
         if (result != 0) {  /* compression not completed, due to lack of output space */
             assert(oPos == dstCapacity);
-            return ERROR(dstSize_tooSmall);
+            RETURN_ERROR(dstSize_tooSmall);
         }
         assert(iPos == srcSize);   /* all input is expected consumed */
         return oPos;
@@ -4132,7 +4258,7 @@ size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output)
 {
     ZSTD_inBuffer input = { NULL, 0, 0 };
     size_t const remainingToFlush = ZSTD_compressStream2(zcs, output, &input, ZSTD_e_end);
-    CHECK_F( remainingToFlush );
+    FORWARD_IF_ERROR( remainingToFlush );
     if (zcs->appliedParams.nbWorkers > 0) return remainingToFlush;   /* minimal estimation */
     /* single thread mode : attempt to calculate remaining to flush more precisely */
     {   size_t const lastBlockSize = zcs->frameEnded ? 0 : ZSTD_BLOCKHEADERSIZE;
@@ -4151,7 +4277,7 @@ int ZSTD_maxCLevel(void) { return ZSTD_MAX_CLEVEL; }
 int ZSTD_minCLevel(void) { return (int)-ZSTD_TARGETLENGTH_MAX; }
 
 static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEVEL+1] = {
-{   /* "default" - guarantees a monotonically increasing memory budget */
+{   /* "default" - for any srcSize > 256 KB */
     /* W,  C,  H,  S,  L, TL, strat */
     { 19, 12, 13,  1,  6,  1, ZSTD_fast    },  /* base for negative levels */
     { 19, 13, 14,  1,  7,  0, ZSTD_fast    },  /* level  1 */
@@ -4258,13 +4384,13 @@ static const ZSTD_compressionParameters ZSTD_defaultCParameters[4][ZSTD_MAX_CLEV
 };
 
 /*! ZSTD_getCParams() :
-*  @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize.
-*   Size values are optional, provide 0 if not known or unused */
+ * @return ZSTD_compressionParameters structure for a selected compression level, srcSize and dictSize.
+ *  Size values are optional, provide 0 if not known or unused */
 ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize)
 {
     size_t const addedSize = srcSizeHint ? 0 : 500;
-    U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : (U64)-1;
-    U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB);   /* intentional underflow for srcSizeHint == 0 */
+    U64 const rSize = srcSizeHint+dictSize ? srcSizeHint+dictSize+addedSize : ZSTD_CONTENTSIZE_UNKNOWN;  /* intentional overflow for srcSizeHint == ZSTD_CONTENTSIZE_UNKNOWN */
+    U32 const tableID = (rSize <= 256 KB) + (rSize <= 128 KB) + (rSize <= 16 KB);
     int row = compressionLevel;
     DEBUGLOG(5, "ZSTD_getCParams (cLevel=%i)", compressionLevel);
     if (compressionLevel == 0) row = ZSTD_CLEVEL_DEFAULT;   /* 0 == default */
@@ -4272,13 +4398,14 @@ ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long l
     if (compressionLevel > ZSTD_MAX_CLEVEL) row = ZSTD_MAX_CLEVEL;
     {   ZSTD_compressionParameters cp = ZSTD_defaultCParameters[tableID][row];
         if (compressionLevel < 0) cp.targetLength = (unsigned)(-compressionLevel);   /* acceleration factor */
-        return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize);
+        return ZSTD_adjustCParams_internal(cp, srcSizeHint, dictSize);               /* refine parameters based on srcSize & dictSize */
     }
 }
 
 /*! ZSTD_getParams() :
-*   same as ZSTD_getCParams(), but @return a `ZSTD_parameters` object (instead of `ZSTD_compressionParameters`).
-*   All fields of `ZSTD_frameParameters` are set to default (0) */
+ *  same idea as ZSTD_getCParams()
+ * @return a `ZSTD_parameters` structure (instead of `ZSTD_compressionParameters`).
+ *  Fields of `ZSTD_frameParameters` are set to default values */
 ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long srcSizeHint, size_t dictSize) {
     ZSTD_parameters params;
     ZSTD_compressionParameters const cParams = ZSTD_getCParams(compressionLevel, srcSizeHint, dictSize);
diff --git a/thirdparty/zstd/compress/zstd_compress_internal.h b/thirdparty/zstd/compress/zstd_compress_internal.h
index 29bca59859..cc3cbb9da9 100644
--- a/thirdparty/zstd/compress/zstd_compress_internal.h
+++ b/thirdparty/zstd/compress/zstd_compress_internal.h
@@ -36,9 +36,9 @@ extern "C" {
 #define ZSTD_DUBT_UNSORTED_MARK 1   /* For btlazy2 strategy, index 1 now means "unsorted".
                                        It could be confused for a real successor at index "1", if sorted as larger than its predecessor.
                                        It's not a big deal though : candidate will just be sorted again.
-                                       Additionnally, candidate position 1 will be lost.
+                                       Additionally, candidate position 1 will be lost.
                                        But candidate 1 cannot hide a large tree of candidates, so it's a minimal loss.
-                                       The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be misdhandled after table re-use with a different strategy
+                                       The benefit is that ZSTD_DUBT_UNSORTED_MARK cannot be mishandled after table re-use with a different strategy
                                        Constant required by ZSTD_compressBlock_btlazy2() and ZSTD_reduceTable_internal() */
 
 
@@ -55,6 +55,14 @@ typedef struct ZSTD_prefixDict_s {
 } ZSTD_prefixDict;
 
 typedef struct {
+    void* dictBuffer;
+    void const* dict;
+    size_t dictSize;
+    ZSTD_dictContentType_e dictContentType;
+    ZSTD_CDict* cdict;
+} ZSTD_localDict;
+
+typedef struct {
     U32 CTable[HUF_CTABLE_SIZE_U32(255)];
     HUF_repeat repeatMode;
 } ZSTD_hufCTables_t;
@@ -107,6 +115,7 @@ typedef struct {
     U32  offCodeSumBasePrice;    /* to compare to log2(offreq)  */
     ZSTD_OptPrice_e priceType;   /* prices can be determined dynamically, or follow a pre-defined cost structure */
     const ZSTD_entropyCTables_t* symbolCosts;  /* pre-calculated dictionary statistics */
+    ZSTD_literalCompressionMode_e literalCompressionMode;
 } optState_t;
 
 typedef struct {
@@ -188,6 +197,7 @@ struct ZSTD_CCtx_params_s {
                                 * 1<<wLog, even for dictionary */
 
     ZSTD_dictAttachPref_e attachDictPref;
+    ZSTD_literalCompressionMode_e literalCompressionMode;
 
     /* Multithreading: used to pass parameters to mtctx */
     int nbWorkers;
@@ -243,7 +253,7 @@ struct ZSTD_CCtx_s {
     U32    frameEnded;
 
     /* Dictionary */
-    ZSTD_CDict* cdictLocal;
+    ZSTD_localDict localDict;
     const ZSTD_CDict* cdict;
     ZSTD_prefixDict prefixDict;   /* single-usage dictionary */
 
@@ -806,13 +816,6 @@ size_t ZSTD_initCStream_internal(ZSTD_CStream* zcs,
 
 void ZSTD_resetSeqStore(seqStore_t* ssPtr);
 
-/*! ZSTD_compressStream_generic() :
- *  Private use only. To be called from zstdmt_compress.c in single-thread mode. */
-size_t ZSTD_compressStream_generic(ZSTD_CStream* zcs,
-                                   ZSTD_outBuffer* output,
-                                   ZSTD_inBuffer* input,
-                                   ZSTD_EndDirective const flushMode);
-
 /*! ZSTD_getCParamsFromCDict() :
  *  as the name implies */
 ZSTD_compressionParameters ZSTD_getCParamsFromCDict(const ZSTD_CDict* cdict);
@@ -839,7 +842,7 @@ size_t ZSTD_compress_advanced_internal(ZSTD_CCtx* cctx,
 /* ZSTD_writeLastEmptyBlock() :
  * output an empty Block with end-of-frame mark to complete a frame
  * @return : size of data written into `dst` (== ZSTD_blockHeaderSize (defined in zstd_internal.h))
- *           or an error code if `dstCapcity` is too small (<ZSTD_blockHeaderSize)
+ *           or an error code if `dstCapacity` is too small (<ZSTD_blockHeaderSize)
  */
 size_t ZSTD_writeLastEmptyBlock(void* dst, size_t dstCapacity);
 
diff --git a/thirdparty/zstd/compress/zstd_fast.c b/thirdparty/zstd/compress/zstd_fast.c
index 40ba0f73e6..ed997b441c 100644
--- a/thirdparty/zstd/compress/zstd_fast.c
+++ b/thirdparty/zstd/compress/zstd_fast.c
@@ -45,7 +45,155 @@ FORCE_INLINE_TEMPLATE
 size_t ZSTD_compressBlock_fast_generic(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize,
-        U32 const mls, ZSTD_dictMode_e const dictMode)
+        U32 const mls)
+{
+    const ZSTD_compressionParameters* const cParams = &ms->cParams;
+    U32* const hashTable = ms->hashTable;
+    U32 const hlog = cParams->hashLog;
+    /* support stepSize of 0 */
+    size_t const stepSize = cParams->targetLength + !(cParams->targetLength) + 1;
+    const BYTE* const base = ms->window.base;
+    const BYTE* const istart = (const BYTE*)src;
+    /* We check ip0 (ip + 0) and ip1 (ip + 1) each loop */
+    const BYTE* ip0 = istart;
+    const BYTE* ip1;
+    const BYTE* anchor = istart;
+    const U32   prefixStartIndex = ms->window.dictLimit;
+    const BYTE* const prefixStart = base + prefixStartIndex;
+    const BYTE* const iend = istart + srcSize;
+    const BYTE* const ilimit = iend - HASH_READ_SIZE;
+    U32 offset_1=rep[0], offset_2=rep[1];
+    U32 offsetSaved = 0;
+
+    /* init */
+    ip0 += (ip0 == prefixStart);
+    ip1 = ip0 + 1;
+    {
+        U32 const maxRep = (U32)(ip0 - prefixStart);
+        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
+        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
+    }
+
+    /* Main Search Loop */
+    while (ip1 < ilimit) {   /* < instead of <=, because check at ip0+2 */
+        size_t mLength;
+        BYTE const* ip2 = ip0 + 2;
+        size_t const h0 = ZSTD_hashPtr(ip0, hlog, mls);
+        U32 const val0 = MEM_read32(ip0);
+        size_t const h1 = ZSTD_hashPtr(ip1, hlog, mls);
+        U32 const val1 = MEM_read32(ip1);
+        U32 const current0 = (U32)(ip0-base);
+        U32 const current1 = (U32)(ip1-base);
+        U32 const matchIndex0 = hashTable[h0];
+        U32 const matchIndex1 = hashTable[h1];
+        BYTE const* repMatch = ip2-offset_1;
+        const BYTE* match0 = base + matchIndex0;
+        const BYTE* match1 = base + matchIndex1;
+        U32 offcode;
+        hashTable[h0] = current0;   /* update hash table */
+        hashTable[h1] = current1;   /* update hash table */
+
+        assert(ip0 + 1 == ip1);
+
+        if ((offset_1 > 0) & (MEM_read32(repMatch) == MEM_read32(ip2))) {
+            mLength = ip2[-1] == repMatch[-1] ? 1 : 0;
+            ip0 = ip2 - mLength;
+            match0 = repMatch - mLength;
+            offcode = 0;
+            goto _match;
+        }
+        if ((matchIndex0 > prefixStartIndex) && MEM_read32(match0) == val0) {
+            /* found a regular match */
+            goto _offset;
+        }
+        if ((matchIndex1 > prefixStartIndex) && MEM_read32(match1) == val1) {
+            /* found a regular match after one literal */
+            ip0 = ip1;
+            match0 = match1;
+            goto _offset;
+        }
+        {
+            size_t const step = ((ip0-anchor) >> (kSearchStrength - 1)) + stepSize;
+            assert(step >= 2);
+            ip0 += step;
+            ip1 += step;
+            continue;
+        }
+_offset: /* Requires: ip0, match0 */
+        /* Compute the offset code */
+        offset_2 = offset_1;
+        offset_1 = (U32)(ip0-match0);
+        offcode = offset_1 + ZSTD_REP_MOVE;
+        mLength = 0;
+        /* Count the backwards match length */
+        while (((ip0>anchor) & (match0>prefixStart))
+             && (ip0[-1] == match0[-1])) { ip0--; match0--; mLength++; } /* catch up */
+
+_match: /* Requires: ip0, match0, offcode */
+        /* Count the forward length */
+        mLength += ZSTD_count(ip0+mLength+4, match0+mLength+4, iend) + 4;
+        ZSTD_storeSeq(seqStore, ip0-anchor, anchor, offcode, mLength-MINMATCH);
+        /* match found */
+        ip0 += mLength;
+        anchor = ip0;
+        ip1 = ip0 + 1;
+
+        if (ip0 <= ilimit) {
+            /* Fill Table */
+            assert(base+current0+2 > istart);  /* check base overflow */
+            hashTable[ZSTD_hashPtr(base+current0+2, hlog, mls)] = current0+2;  /* here because current+2 could be > iend-8 */
+            hashTable[ZSTD_hashPtr(ip0-2, hlog, mls)] = (U32)(ip0-2-base);
+
+            while ( (ip0 <= ilimit)
+                 && ( (offset_2>0)
+                    & (MEM_read32(ip0) == MEM_read32(ip0 - offset_2)) )) {
+                /* store sequence */
+                size_t const rLength = ZSTD_count(ip0+4, ip0+4-offset_2, iend) + 4;
+                U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff;  /* swap offset_2 <=> offset_1 */
+                hashTable[ZSTD_hashPtr(ip0, hlog, mls)] = (U32)(ip0-base);
+                ip0 += rLength;
+                ip1 = ip0 + 1;
+                ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
+                anchor = ip0;
+                continue;   /* faster when present (confirmed on gcc-8) ... (?) */
+            }
+        }
+    }
+
+    /* save reps for next block */
+    rep[0] = offset_1 ? offset_1 : offsetSaved;
+    rep[1] = offset_2 ? offset_2 : offsetSaved;
+
+    /* Return the last literals size */
+    return iend - anchor;
+}
+
+
+size_t ZSTD_compressBlock_fast(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize)
+{
+    ZSTD_compressionParameters const* cParams = &ms->cParams;
+    U32 const mls = cParams->minMatch;
+    assert(ms->dictMatchState == NULL);
+    switch(mls)
+    {
+    default: /* includes case 3 */
+    case 4 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4);
+    case 5 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5);
+    case 6 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6);
+    case 7 :
+        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7);
+    }
+}
+
+FORCE_INLINE_TEMPLATE
+size_t ZSTD_compressBlock_fast_dictMatchState_generic(
+        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
+        void const* src, size_t srcSize, U32 const mls)
 {
     const ZSTD_compressionParameters* const cParams = &ms->cParams;
     U32* const hashTable = ms->hashTable;
@@ -64,46 +212,26 @@ size_t ZSTD_compressBlock_fast_generic(
     U32 offsetSaved = 0;
 
     const ZSTD_matchState_t* const dms = ms->dictMatchState;
-    const ZSTD_compressionParameters* const dictCParams =
-                                     dictMode == ZSTD_dictMatchState ?
-                                     &dms->cParams : NULL;
-    const U32* const dictHashTable = dictMode == ZSTD_dictMatchState ?
-                                     dms->hashTable : NULL;
-    const U32 dictStartIndex       = dictMode == ZSTD_dictMatchState ?
-                                     dms->window.dictLimit : 0;
-    const BYTE* const dictBase     = dictMode == ZSTD_dictMatchState ?
-                                     dms->window.base : NULL;
-    const BYTE* const dictStart    = dictMode == ZSTD_dictMatchState ?
-                                     dictBase + dictStartIndex : NULL;
-    const BYTE* const dictEnd      = dictMode == ZSTD_dictMatchState ?
-                                     dms->window.nextSrc : NULL;
-    const U32 dictIndexDelta       = dictMode == ZSTD_dictMatchState ?
-                                     prefixStartIndex - (U32)(dictEnd - dictBase) :
-                                     0;
+    const ZSTD_compressionParameters* const dictCParams = &dms->cParams ;
+    const U32* const dictHashTable = dms->hashTable;
+    const U32 dictStartIndex       = dms->window.dictLimit;
+    const BYTE* const dictBase     = dms->window.base;
+    const BYTE* const dictStart    = dictBase + dictStartIndex;
+    const BYTE* const dictEnd      = dms->window.nextSrc;
+    const U32 dictIndexDelta       = prefixStartIndex - (U32)(dictEnd - dictBase);
     const U32 dictAndPrefixLength  = (U32)(ip - prefixStart + dictEnd - dictStart);
-    const U32 dictHLog             = dictMode == ZSTD_dictMatchState ?
-                                     dictCParams->hashLog : hlog;
-
-    assert(dictMode == ZSTD_noDict || dictMode == ZSTD_dictMatchState);
+    const U32 dictHLog             = dictCParams->hashLog;
 
     /* otherwise, we would get index underflow when translating a dict index
      * into a local index */
-    assert(dictMode != ZSTD_dictMatchState
-        || prefixStartIndex >= (U32)(dictEnd - dictBase));
+    assert(prefixStartIndex >= (U32)(dictEnd - dictBase));
 
     /* init */
     ip += (dictAndPrefixLength == 0);
-    if (dictMode == ZSTD_noDict) {
-        U32 const maxRep = (U32)(ip - prefixStart);
-        if (offset_2 > maxRep) offsetSaved = offset_2, offset_2 = 0;
-        if (offset_1 > maxRep) offsetSaved = offset_1, offset_1 = 0;
-    }
-    if (dictMode == ZSTD_dictMatchState) {
-        /* dictMatchState repCode checks don't currently handle repCode == 0
-         * disabling. */
-        assert(offset_1 <= dictAndPrefixLength);
-        assert(offset_2 <= dictAndPrefixLength);
-    }
+    /* dictMatchState repCode checks don't currently handle repCode == 0
+     * disabling. */
+    assert(offset_1 <= dictAndPrefixLength);
+    assert(offset_2 <= dictAndPrefixLength);
 
     /* Main Search Loop */
     while (ip < ilimit) {   /* < instead of <=, because repcode check at (ip+1) */
@@ -113,50 +241,37 @@ size_t ZSTD_compressBlock_fast_generic(
         U32 const matchIndex = hashTable[h];
         const BYTE* match = base + matchIndex;
         const U32 repIndex = current + 1 - offset_1;
-        const BYTE* repMatch = (dictMode == ZSTD_dictMatchState
-                            && repIndex < prefixStartIndex) ?
+        const BYTE* repMatch = (repIndex < prefixStartIndex) ?
                                dictBase + (repIndex - dictIndexDelta) :
                                base + repIndex;
         hashTable[h] = current;   /* update hash table */
 
-        if ( (dictMode == ZSTD_dictMatchState)
-          && ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
+        if ( ((U32)((prefixStartIndex-1) - repIndex) >= 3) /* intentional underflow : ensure repIndex isn't overlapping dict + prefix */
           && (MEM_read32(repMatch) == MEM_read32(ip+1)) ) {
             const BYTE* const repMatchEnd = repIndex < prefixStartIndex ? dictEnd : iend;
             mLength = ZSTD_count_2segments(ip+1+4, repMatch+4, iend, repMatchEnd, prefixStart) + 4;
             ip++;
             ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
-        } else if ( dictMode == ZSTD_noDict
-                 && ((offset_1 > 0) & (MEM_read32(ip+1-offset_1) == MEM_read32(ip+1)))) {
-            mLength = ZSTD_count(ip+1+4, ip+1+4-offset_1, iend) + 4;
-            ip++;
-            ZSTD_storeSeq(seqStore, ip-anchor, anchor, 0, mLength-MINMATCH);
         } else if ( (matchIndex <= prefixStartIndex) ) {
-            if (dictMode == ZSTD_dictMatchState) {
-                size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
-                U32 const dictMatchIndex = dictHashTable[dictHash];
-                const BYTE* dictMatch = dictBase + dictMatchIndex;
-                if (dictMatchIndex <= dictStartIndex ||
-                    MEM_read32(dictMatch) != MEM_read32(ip)) {
-                    assert(stepSize >= 1);
-                    ip += ((ip-anchor) >> kSearchStrength) + stepSize;
-                    continue;
-                } else {
-                    /* found a dict match */
-                    U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
-                    mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
-                    while (((ip>anchor) & (dictMatch>dictStart))
-                         && (ip[-1] == dictMatch[-1])) {
-                        ip--; dictMatch--; mLength++;
-                    } /* catch up */
-                    offset_2 = offset_1;
-                    offset_1 = offset;
-                    ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
-                }
-            } else {
+            size_t const dictHash = ZSTD_hashPtr(ip, dictHLog, mls);
+            U32 const dictMatchIndex = dictHashTable[dictHash];
+            const BYTE* dictMatch = dictBase + dictMatchIndex;
+            if (dictMatchIndex <= dictStartIndex ||
+                MEM_read32(dictMatch) != MEM_read32(ip)) {
                 assert(stepSize >= 1);
                 ip += ((ip-anchor) >> kSearchStrength) + stepSize;
                 continue;
+            } else {
+                /* found a dict match */
+                U32 const offset = (U32)(current-dictMatchIndex-dictIndexDelta);
+                mLength = ZSTD_count_2segments(ip+4, dictMatch+4, iend, dictEnd, prefixStart) + 4;
+                while (((ip>anchor) & (dictMatch>dictStart))
+                     && (ip[-1] == dictMatch[-1])) {
+                    ip--; dictMatch--; mLength++;
+                } /* catch up */
+                offset_2 = offset_1;
+                offset_1 = offset;
+                ZSTD_storeSeq(seqStore, ip-anchor, anchor, offset + ZSTD_REP_MOVE, mLength-MINMATCH);
             }
         } else if (MEM_read32(match) != MEM_read32(ip)) {
             /* it's not a match, and we're not going to check the dictionary */
@@ -185,41 +300,27 @@ size_t ZSTD_compressBlock_fast_generic(
             hashTable[ZSTD_hashPtr(ip-2, hlog, mls)] = (U32)(ip-2-base);
 
             /* check immediate repcode */
-            if (dictMode == ZSTD_dictMatchState) {
-                while (ip <= ilimit) {
-                    U32 const current2 = (U32)(ip-base);
-                    U32 const repIndex2 = current2 - offset_2;
-                    const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
-                            dictBase - dictIndexDelta + repIndex2 :
-                            base + repIndex2;
-                    if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
-                       && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
-                        const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
-                        size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
-                        U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
-                        ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
-                        hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
-                        ip += repLength2;
-                        anchor = ip;
-                        continue;
-                    }
-                    break;
+            while (ip <= ilimit) {
+                U32 const current2 = (U32)(ip-base);
+                U32 const repIndex2 = current2 - offset_2;
+                const BYTE* repMatch2 = repIndex2 < prefixStartIndex ?
+                        dictBase - dictIndexDelta + repIndex2 :
+                        base + repIndex2;
+                if ( ((U32)((prefixStartIndex-1) - (U32)repIndex2) >= 3 /* intentional overflow */)
+                   && (MEM_read32(repMatch2) == MEM_read32(ip)) ) {
+                    const BYTE* const repEnd2 = repIndex2 < prefixStartIndex ? dictEnd : iend;
+                    size_t const repLength2 = ZSTD_count_2segments(ip+4, repMatch2+4, iend, repEnd2, prefixStart) + 4;
+                    U32 tmpOffset = offset_2; offset_2 = offset_1; offset_1 = tmpOffset;   /* swap offset_2 <=> offset_1 */
+                    ZSTD_storeSeq(seqStore, 0, anchor, 0, repLength2-MINMATCH);
+                    hashTable[ZSTD_hashPtr(ip, hlog, mls)] = current2;
+                    ip += repLength2;
+                    anchor = ip;
+                    continue;
                 }
+                break;
             }
-
-            if (dictMode == ZSTD_noDict) {
-                while ( (ip <= ilimit)
-                     && ( (offset_2>0)
-                        & (MEM_read32(ip) == MEM_read32(ip - offset_2)) )) {
-                    /* store sequence */
-                    size_t const rLength = ZSTD_count(ip+4, ip+4-offset_2, iend) + 4;
-                    U32 const tmpOff = offset_2; offset_2 = offset_1; offset_1 = tmpOff;  /* swap offset_2 <=> offset_1 */
-                    hashTable[ZSTD_hashPtr(ip, hlog, mls)] = (U32)(ip-base);
-                    ZSTD_storeSeq(seqStore, 0, anchor, 0, rLength-MINMATCH);
-                    ip += rLength;
-                    anchor = ip;
-                    continue;   /* faster when present ... (?) */
-    }   }   }   }
+        }
+    }
 
     /* save reps for next block */
     rep[0] = offset_1 ? offset_1 : offsetSaved;
@@ -229,28 +330,6 @@ size_t ZSTD_compressBlock_fast_generic(
     return iend - anchor;
 }
 
-
-size_t ZSTD_compressBlock_fast(
-        ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
-        void const* src, size_t srcSize)
-{
-    ZSTD_compressionParameters const* cParams = &ms->cParams;
-    U32 const mls = cParams->minMatch;
-    assert(ms->dictMatchState == NULL);
-    switch(mls)
-    {
-    default: /* includes case 3 */
-    case 4 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_noDict);
-    case 5 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_noDict);
-    case 6 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_noDict);
-    case 7 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_noDict);
-    }
-}
-
 size_t ZSTD_compressBlock_fast_dictMatchState(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
         void const* src, size_t srcSize)
@@ -262,13 +341,13 @@ size_t ZSTD_compressBlock_fast_dictMatchState(
     {
     default: /* includes case 3 */
     case 4 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 4, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 4);
     case 5 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 5, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 5);
     case 6 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 6, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 6);
     case 7 :
-        return ZSTD_compressBlock_fast_generic(ms, seqStore, rep, src, srcSize, 7, ZSTD_dictMatchState);
+        return ZSTD_compressBlock_fast_dictMatchState_generic(ms, seqStore, rep, src, srcSize, 7);
     }
 }
 
diff --git a/thirdparty/zstd/compress/zstd_lazy.h b/thirdparty/zstd/compress/zstd_lazy.h
index ef85a6df9c..bb1763069f 100644
--- a/thirdparty/zstd/compress/zstd_lazy.h
+++ b/thirdparty/zstd/compress/zstd_lazy.h
@@ -19,7 +19,7 @@ extern "C" {
 
 U32 ZSTD_insertAndFindFirstIndex(ZSTD_matchState_t* ms, const BYTE* ip);
 
-void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). pre-emptively increase value of ZSTD_DUBT_UNSORTED_MARK */
+void ZSTD_preserveUnsortedMark (U32* const table, U32 const size, U32 const reducerValue);  /*! used in ZSTD_reduceIndex(). preemptively increase value of ZSTD_DUBT_UNSORTED_MARK */
 
 size_t ZSTD_compressBlock_btlazy2(
         ZSTD_matchState_t* ms, seqStore_t* seqStore, U32 rep[ZSTD_REP_NUM],
diff --git a/thirdparty/zstd/compress/zstd_ldm.c b/thirdparty/zstd/compress/zstd_ldm.c
index 58eb2ffe4d..784d20f3ab 100644
--- a/thirdparty/zstd/compress/zstd_ldm.c
+++ b/thirdparty/zstd/compress/zstd_ldm.c
@@ -429,7 +429,7 @@ size_t ZSTD_ldm_generateSequences(
      */
     assert(ldmState->window.nextSrc >= (BYTE const*)src + srcSize);
     /* The input could be very large (in zstdmt), so it must be broken up into
-     * chunks to enforce the maximmum distance and handle overflow correction.
+     * chunks to enforce the maximum distance and handle overflow correction.
      */
     assert(sequences->pos <= sequences->size);
     assert(sequences->size <= sequences->capacity);
diff --git a/thirdparty/zstd/compress/zstd_opt.c b/thirdparty/zstd/compress/zstd_opt.c
index 44de6e97fd..efb69d3267 100644
--- a/thirdparty/zstd/compress/zstd_opt.c
+++ b/thirdparty/zstd/compress/zstd_opt.c
@@ -64,9 +64,15 @@ MEM_STATIC double ZSTD_fCost(U32 price)
 }
 #endif
 
+static int ZSTD_compressedLiterals(optState_t const* const optPtr)
+{
+    return optPtr->literalCompressionMode != ZSTD_lcm_uncompressed;
+}
+
 static void ZSTD_setBasePrices(optState_t* optPtr, int optLevel)
 {
-    optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
+    if (ZSTD_compressedLiterals(optPtr))
+        optPtr->litSumBasePrice = WEIGHT(optPtr->litSum, optLevel);
     optPtr->litLengthSumBasePrice = WEIGHT(optPtr->litLengthSum, optLevel);
     optPtr->matchLengthSumBasePrice = WEIGHT(optPtr->matchLengthSum, optLevel);
     optPtr->offCodeSumBasePrice = WEIGHT(optPtr->offCodeSum, optLevel);
@@ -99,6 +105,7 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
             const BYTE* const src, size_t const srcSize,
                   int const optLevel)
 {
+    int const compressedLiterals = ZSTD_compressedLiterals(optPtr);
     DEBUGLOG(5, "ZSTD_rescaleFreqs (srcSize=%u)", (unsigned)srcSize);
     optPtr->priceType = zop_dynamic;
 
@@ -113,9 +120,10 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
             /* huffman table presumed generated by dictionary */
             optPtr->priceType = zop_dynamic;
 
-            assert(optPtr->litFreq != NULL);
-            optPtr->litSum = 0;
-            {   unsigned lit;
+            if (compressedLiterals) {
+                unsigned lit;
+                assert(optPtr->litFreq != NULL);
+                optPtr->litSum = 0;
                 for (lit=0; lit<=MaxLit; lit++) {
                     U32 const scaleLog = 11;   /* scale to 2K */
                     U32 const bitCost = HUF_getNbBits(optPtr->symbolCosts->huf.CTable, lit);
@@ -163,10 +171,11 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
         } else {  /* not a dictionary */
 
             assert(optPtr->litFreq != NULL);
-            {   unsigned lit = MaxLit;
+            if (compressedLiterals) {
+                unsigned lit = MaxLit;
                 HIST_count_simple(optPtr->litFreq, &lit, src, srcSize);   /* use raw first block to init statistics */
+                optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
             }
-            optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
 
             {   unsigned ll;
                 for (ll=0; ll<=MaxLL; ll++)
@@ -190,7 +199,8 @@ ZSTD_rescaleFreqs(optState_t* const optPtr,
 
     } else {   /* new block : re-use previous statistics, scaled down */
 
-        optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
+        if (compressedLiterals)
+            optPtr->litSum = ZSTD_downscaleStat(optPtr->litFreq, MaxLit, 1);
         optPtr->litLengthSum = ZSTD_downscaleStat(optPtr->litLengthFreq, MaxLL, 0);
         optPtr->matchLengthSum = ZSTD_downscaleStat(optPtr->matchLengthFreq, MaxML, 0);
         optPtr->offCodeSum = ZSTD_downscaleStat(optPtr->offCodeFreq, MaxOff, 0);
@@ -207,6 +217,10 @@ static U32 ZSTD_rawLiteralsCost(const BYTE* const literals, U32 const litLength,
                                 int optLevel)
 {
     if (litLength == 0) return 0;
+
+    if (!ZSTD_compressedLiterals(optPtr))
+        return (litLength << 3) * BITCOST_MULTIPLIER;  /* Uncompressed - 8 bytes per literal. */
+
     if (optPtr->priceType == zop_predef)
         return (litLength*6) * BITCOST_MULTIPLIER;  /* 6 bit per literal - no statistic used */
 
@@ -310,7 +324,8 @@ static void ZSTD_updateStats(optState_t* const optPtr,
                              U32 offsetCode, U32 matchLength)
 {
     /* literals */
-    {   U32 u;
+    if (ZSTD_compressedLiterals(optPtr)) {
+        U32 u;
         for (u=0; u < litLength; u++)
             optPtr->litFreq[literals[u]] += ZSTD_LITFREQ_ADD;
         optPtr->litSum += litLength*ZSTD_LITFREQ_ADD;
@@ -870,7 +885,7 @@ ZSTD_compressBlock_opt_generic(ZSTD_matchState_t* ms,
             /* large match -> immediate encoding */
             {   U32 const maxML = matches[nbMatches-1].len;
                 U32 const maxOffset = matches[nbMatches-1].off;
-                DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new serie",
+                DEBUGLOG(6, "found %u matches of maxLength=%u and maxOffCode=%u at cPos=%u => start new series",
                             nbMatches, maxML, maxOffset, (U32)(ip-prefixStart));
 
                 if (maxML > sufficient_len) {
@@ -1108,7 +1123,8 @@ static U32 ZSTD_upscaleStat(unsigned* table, U32 lastEltIndex, int bonus)
 /* used in 2-pass strategy */
 MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
 {
-    optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
+    if (ZSTD_compressedLiterals(optPtr))
+        optPtr->litSum = ZSTD_upscaleStat(optPtr->litFreq, MaxLit, 0);
     optPtr->litLengthSum = ZSTD_upscaleStat(optPtr->litLengthFreq, MaxLL, 0);
     optPtr->matchLengthSum = ZSTD_upscaleStat(optPtr->matchLengthFreq, MaxML, 0);
     optPtr->offCodeSum = ZSTD_upscaleStat(optPtr->offCodeFreq, MaxOff, 0);
@@ -1117,7 +1133,7 @@ MEM_STATIC void ZSTD_upscaleStats(optState_t* optPtr)
 /* ZSTD_initStats_ultra():
  * make a first compression pass, just to seed stats with more accurate starting values.
  * only works on first block, with no dictionary and no ldm.
- * this function cannot error, hence its constract must be respected.
+ * this function cannot error, hence its contract must be respected.
  */
 static void
 ZSTD_initStats_ultra(ZSTD_matchState_t* ms,
diff --git a/thirdparty/zstd/compress/zstdmt_compress.c b/thirdparty/zstd/compress/zstdmt_compress.c
index 2cbd6ffade..38fbb90768 100644
--- a/thirdparty/zstd/compress/zstdmt_compress.c
+++ b/thirdparty/zstd/compress/zstdmt_compress.c
@@ -22,6 +22,7 @@
 /* ======   Dependencies   ====== */
 #include <string.h>      /* memcpy, memset */
 #include <limits.h>      /* INT_MAX, UINT_MAX */
+#include "mem.h"         /* MEM_STATIC */
 #include "pool.h"        /* threadpool */
 #include "threading.h"   /* mutex */
 #include "zstd_compress_internal.h"  /* MIN, ERROR, ZSTD_*, ZSTD_highbit32 */
@@ -456,7 +457,7 @@ typedef struct {
      * Must be acquired after the main mutex when acquiring both.
      */
     ZSTD_pthread_mutex_t ldmWindowMutex;
-    ZSTD_pthread_cond_t ldmWindowCond;  /* Signaled when ldmWindow is udpated */
+    ZSTD_pthread_cond_t ldmWindowCond;  /* Signaled when ldmWindow is updated */
     ZSTD_window_t ldmWindow;  /* A thread-safe copy of ldmState.window */
 } serialState_t;
 
@@ -647,7 +648,7 @@ static void ZSTDMT_compressionJob(void* jobDescription)
     buffer_t dstBuff = job->dstBuff;
     size_t lastCBlockSize = 0;
 
-    /* ressources */
+    /* resources */
     if (cctx==NULL) JOB_ERROR(ERROR(memory_allocation));
     if (dstBuff.start == NULL) {   /* streaming job : doesn't provide a dstBuffer */
         dstBuff = ZSTDMT_getBuffer(job->bufPool);
@@ -672,7 +673,7 @@ static void ZSTDMT_compressionJob(void* jobDescription)
         if (ZSTD_isError(initError)) JOB_ERROR(initError);
     } else {  /* srcStart points at reloaded section */
         U64 const pledgedSrcSize = job->firstJob ? job->fullFrameSize : job->src.size;
-        {   size_t const forceWindowError = ZSTD_CCtxParam_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
+        {   size_t const forceWindowError = ZSTD_CCtxParams_setParameter(&jobParams, ZSTD_c_forceMaxWindow, !job->firstJob);
             if (ZSTD_isError(forceWindowError)) JOB_ERROR(forceWindowError);
         }
         {   size_t const initError = ZSTD_compressBegin_advanced_internal(cctx,
@@ -864,14 +865,10 @@ static size_t ZSTDMT_expandJobsTable (ZSTDMT_CCtx* mtctx, U32 nbWorkers) {
  * Internal use only */
 size_t ZSTDMT_CCtxParam_setNbWorkers(ZSTD_CCtx_params* params, unsigned nbWorkers)
 {
-    if (nbWorkers > ZSTDMT_NBWORKERS_MAX) nbWorkers = ZSTDMT_NBWORKERS_MAX;
-    params->nbWorkers = nbWorkers;
-    params->overlapLog = ZSTDMT_OVERLAPLOG_DEFAULT;
-    params->jobSize = 0;
-    return nbWorkers;
+    return ZSTD_CCtxParams_setParameter(params, ZSTD_c_nbWorkers, (int)nbWorkers);
 }
 
-ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
+MEM_STATIC ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced_internal(unsigned nbWorkers, ZSTD_customMem cMem)
 {
     ZSTDMT_CCtx* mtctx;
     U32 nbJobs = nbWorkers + 2;
@@ -906,6 +903,17 @@ ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
     return mtctx;
 }
 
+ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers, ZSTD_customMem cMem)
+{
+#ifdef ZSTD_MULTITHREAD
+    return ZSTDMT_createCCtx_advanced_internal(nbWorkers, cMem);
+#else
+    (void)nbWorkers;
+    (void)cMem;
+    return NULL;
+#endif
+}
+
 ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers)
 {
     return ZSTDMT_createCCtx_advanced(nbWorkers, ZSTD_defaultCMem);
@@ -986,26 +994,13 @@ ZSTDMT_CCtxParam_setMTCtxParameter(ZSTD_CCtx_params* params,
     {
     case ZSTDMT_p_jobSize :
         DEBUGLOG(4, "ZSTDMT_CCtxParam_setMTCtxParameter : set jobSize to %i", value);
-        if ( value != 0  /* default */
-          && value < ZSTDMT_JOBSIZE_MIN)
-            value = ZSTDMT_JOBSIZE_MIN;
-        assert(value >= 0);
-        if (value > ZSTDMT_JOBSIZE_MAX) value = ZSTDMT_JOBSIZE_MAX;
-        params->jobSize = value;
-        return value;
-
+        return ZSTD_CCtxParams_setParameter(params, ZSTD_c_jobSize, value);
     case ZSTDMT_p_overlapLog :
         DEBUGLOG(4, "ZSTDMT_p_overlapLog : %i", value);
-        if (value < ZSTD_OVERLAPLOG_MIN) value = ZSTD_OVERLAPLOG_MIN;
-        if (value > ZSTD_OVERLAPLOG_MAX) value = ZSTD_OVERLAPLOG_MAX;
-        params->overlapLog = value;
-        return value;
-
+        return ZSTD_CCtxParams_setParameter(params, ZSTD_c_overlapLog, value);
     case ZSTDMT_p_rsyncable :
-        value = (value != 0);
-        params->rsyncable = value;
-        return value;
-
+        DEBUGLOG(4, "ZSTD_p_rsyncable : %i", value);
+        return ZSTD_CCtxParams_setParameter(params, ZSTD_c_rsyncable, value);
     default :
         return ERROR(parameter_unsupported);
     }
@@ -1021,32 +1016,29 @@ size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter,
 {
     switch (parameter) {
     case ZSTDMT_p_jobSize:
-        assert(mtctx->params.jobSize <= INT_MAX);
-        *value = (int)(mtctx->params.jobSize);
-        break;
+        return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_jobSize, value);
     case ZSTDMT_p_overlapLog:
-        *value = mtctx->params.overlapLog;
-        break;
+        return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_overlapLog, value);
     case ZSTDMT_p_rsyncable:
-        *value = mtctx->params.rsyncable;
-        break;
+        return ZSTD_CCtxParams_getParameter(&mtctx->params, ZSTD_c_rsyncable, value);
     default:
         return ERROR(parameter_unsupported);
     }
-    return 0;
 }
 
 /* Sets parameters relevant to the compression job,
  * initializing others to default values. */
 static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
 {
-    ZSTD_CCtx_params jobParams;
-    memset(&jobParams, 0, sizeof(jobParams));
-
-    jobParams.cParams = params.cParams;
-    jobParams.fParams = params.fParams;
-    jobParams.compressionLevel = params.compressionLevel;
-
+    ZSTD_CCtx_params jobParams = params;
+    /* Clear parameters related to multithreading */
+    jobParams.forceWindow = 0;
+    jobParams.nbWorkers = 0;
+    jobParams.jobSize = 0;
+    jobParams.overlapLog = 0;
+    jobParams.rsyncable = 0;
+    memset(&jobParams.ldmParams, 0, sizeof(ldmParams_t));
+    memset(&jobParams.customMem, 0, sizeof(ZSTD_customMem));
     return jobParams;
 }
 
@@ -1056,7 +1048,7 @@ static ZSTD_CCtx_params ZSTDMT_initJobCCtxParams(ZSTD_CCtx_params const params)
 static size_t ZSTDMT_resize(ZSTDMT_CCtx* mtctx, unsigned nbWorkers)
 {
     if (POOL_resize(mtctx->factory, nbWorkers)) return ERROR(memory_allocation);
-    CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
+    FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbWorkers) );
     mtctx->bufPool = ZSTDMT_expandBufferPool(mtctx->bufPool, nbWorkers);
     if (mtctx->bufPool == NULL) return ERROR(memory_allocation);
     mtctx->cctxPool = ZSTDMT_expandCCtxPool(mtctx->cctxPool, nbWorkers);
@@ -1263,7 +1255,7 @@ static size_t ZSTDMT_compress_advanced_internal(
     if (ZSTDMT_serialState_reset(&mtctx->serial, mtctx->seqPool, params, avgJobSize))
         return ERROR(memory_allocation);
 
-    CHECK_F( ZSTDMT_expandJobsTable(mtctx, nbJobs) );  /* only expands if necessary */
+    FORWARD_IF_ERROR( ZSTDMT_expandJobsTable(mtctx, nbJobs) );  /* only expands if necessary */
 
     {   unsigned u;
         for (u=0; u<nbJobs; u++) {
@@ -1396,7 +1388,7 @@ size_t ZSTDMT_initCStream_internal(
 
     /* init */
     if (params.nbWorkers != mtctx->params.nbWorkers)
-        CHECK_F( ZSTDMT_resize(mtctx, params.nbWorkers) );
+        FORWARD_IF_ERROR( ZSTDMT_resize(mtctx, params.nbWorkers) );
 
     if (params.jobSize != 0 && params.jobSize < ZSTDMT_JOBSIZE_MIN) params.jobSize = ZSTDMT_JOBSIZE_MIN;
     if (params.jobSize > (size_t)ZSTDMT_JOBSIZE_MAX) params.jobSize = ZSTDMT_JOBSIZE_MAX;
@@ -1547,7 +1539,7 @@ size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel) {
 /* ZSTDMT_writeLastEmptyBlock()
  * Write a single empty block with an end-of-frame to finish a frame.
  * Job must be created from streaming variant.
- * This function is always successfull if expected conditions are fulfilled.
+ * This function is always successful if expected conditions are fulfilled.
  */
 static void ZSTDMT_writeLastEmptyBlock(ZSTDMT_jobDescription* job)
 {
@@ -1987,7 +1979,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
     assert(input->pos  <= input->size);
 
     if (mtctx->singleBlockingThread) {  /* delegate to single-thread (synchronous) */
-        return ZSTD_compressStream_generic(mtctx->cctxPool->cctx[0], output, input, endOp);
+        return ZSTD_compressStream2(mtctx->cctxPool->cctx[0], output, input, endOp);
     }
 
     if ((mtctx->frameEnded) && (endOp==ZSTD_e_continue)) {
@@ -2051,7 +2043,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
       || ((endOp == ZSTD_e_end) && (!mtctx->frameEnded)) ) {   /* must finish the frame with a zero-size block */
         size_t const jobSize = mtctx->inBuff.filled;
         assert(mtctx->inBuff.filled <= mtctx->targetSectionSize);
-        CHECK_F( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) );
+        FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, jobSize, endOp) );
     }
 
     /* check for potential compressed data ready to be flushed */
@@ -2065,7 +2057,7 @@ size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
 
 size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input)
 {
-    CHECK_F( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) );
+    FORWARD_IF_ERROR( ZSTDMT_compressStream_generic(mtctx, output, input, ZSTD_e_continue) );
 
     /* recommended next input size : fill current input buffer */
     return mtctx->targetSectionSize - mtctx->inBuff.filled;   /* note : could be zero when input buffer is fully filled and no more availability to create new job */
@@ -2082,7 +2074,7 @@ static size_t ZSTDMT_flushStream_internal(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* ou
       || ((endFrame==ZSTD_e_end) && !mtctx->frameEnded)) {  /* need a last 0-size block to end frame */
            DEBUGLOG(5, "ZSTDMT_flushStream_internal : create a new job (%u bytes, end:%u)",
                         (U32)srcSize, (U32)endFrame);
-        CHECK_F( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) );
+        FORWARD_IF_ERROR( ZSTDMT_createCompressionJob(mtctx, srcSize, endFrame) );
     }
 
     /* check if there is any data available to flush */
diff --git a/thirdparty/zstd/compress/zstdmt_compress.h b/thirdparty/zstd/compress/zstdmt_compress.h
index ee771681fa..12e6bcb3a3 100644
--- a/thirdparty/zstd/compress/zstdmt_compress.h
+++ b/thirdparty/zstd/compress/zstdmt_compress.h
@@ -17,10 +17,25 @@
 
 
 /* Note : This is an internal API.
- *        Some methods are still exposed (ZSTDLIB_API),
+ *        These APIs used to be exposed with ZSTDLIB_API,
  *        because it used to be the only way to invoke MT compression.
- *        Now, it's recommended to use ZSTD_compress_generic() instead.
- *        These methods will stop being exposed in a future version */
+ *        Now, it's recommended to use ZSTD_compress2 and ZSTD_compressStream2()
+ *        instead.
+ *
+ *        If you depend on these APIs and can't switch, then define
+ *        ZSTD_LEGACY_MULTITHREADED_API when making the dynamic library.
+ *        However, we may completely remove these functions in a future
+ *        release, so please switch soon.
+ *
+ *        This API requires ZSTD_MULTITHREAD to be defined during compilation,
+ *        otherwise ZSTDMT_createCCtx*() will fail.
+ */
+
+#ifdef ZSTD_LEGACY_MULTITHREADED_API
+#  define ZSTDMT_API ZSTDLIB_API
+#else
+#  define ZSTDMT_API
+#endif
 
 /* ===   Dependencies   === */
 #include <stddef.h>                /* size_t */
@@ -40,17 +55,19 @@
 
 /* ===   Memory management   === */
 typedef struct ZSTDMT_CCtx_s ZSTDMT_CCtx;
-ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
-ZSTDLIB_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
+/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
+ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx(unsigned nbWorkers);
+/* Requires ZSTD_MULTITHREAD to be defined during compilation, otherwise it will return NULL. */
+ZSTDMT_API ZSTDMT_CCtx* ZSTDMT_createCCtx_advanced(unsigned nbWorkers,
                                                     ZSTD_customMem cMem);
-ZSTDLIB_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_freeCCtx(ZSTDMT_CCtx* mtctx);
 
-ZSTDLIB_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_sizeof_CCtx(ZSTDMT_CCtx* mtctx);
 
 
 /* ===   Simple one-pass compression function   === */
 
-ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
                                        void* dst, size_t dstCapacity,
                                  const void* src, size_t srcSize,
                                        int compressionLevel);
@@ -59,31 +76,31 @@ ZSTDLIB_API size_t ZSTDMT_compressCCtx(ZSTDMT_CCtx* mtctx,
 
 /* ===   Streaming functions   === */
 
-ZSTDLIB_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
-ZSTDLIB_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);  /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */
+ZSTDMT_API size_t ZSTDMT_initCStream(ZSTDMT_CCtx* mtctx, int compressionLevel);
+ZSTDMT_API size_t ZSTDMT_resetCStream(ZSTDMT_CCtx* mtctx, unsigned long long pledgedSrcSize);  /**< if srcSize is not known at reset time, use ZSTD_CONTENTSIZE_UNKNOWN. Note: for compatibility with older programs, 0 means the same as ZSTD_CONTENTSIZE_UNKNOWN, but it will change in the future to mean "empty" */
 
-ZSTDLIB_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
-ZSTDLIB_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+ZSTDMT_API size_t ZSTDMT_nextInputSizeHint(const ZSTDMT_CCtx* mtctx);
+ZSTDMT_API size_t ZSTDMT_compressStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
 
-ZSTDLIB_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);   /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);     /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_flushStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);   /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
+ZSTDMT_API size_t ZSTDMT_endStream(ZSTDMT_CCtx* mtctx, ZSTD_outBuffer* output);     /**< @return : 0 == all flushed; >0 : still some data to be flushed; or an error code (ZSTD_isError()) */
 
 
 /* ===   Advanced functions and parameters  === */
 
-ZSTDLIB_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
-                                           void* dst, size_t dstCapacity,
-                                     const void* src, size_t srcSize,
-                                     const ZSTD_CDict* cdict,
-                                           ZSTD_parameters params,
-                                           int overlapLog);
+ZSTDMT_API size_t ZSTDMT_compress_advanced(ZSTDMT_CCtx* mtctx,
+                                          void* dst, size_t dstCapacity,
+                                    const void* src, size_t srcSize,
+                                    const ZSTD_CDict* cdict,
+                                          ZSTD_parameters params,
+                                          int overlapLog);
 
-ZSTDLIB_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_initCStream_advanced(ZSTDMT_CCtx* mtctx,
                                         const void* dict, size_t dictSize,   /* dict can be released after init, a local copy is preserved within zcs */
                                         ZSTD_parameters params,
                                         unsigned long long pledgedSrcSize);  /* pledgedSrcSize is optional and can be zero == unknown */
 
-ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
                                         const ZSTD_CDict* cdict,
                                         ZSTD_frameParameters fparams,
                                         unsigned long long pledgedSrcSize);  /* note : zero means empty */
@@ -92,7 +109,7 @@ ZSTDLIB_API size_t ZSTDMT_initCStream_usingCDict(ZSTDMT_CCtx* mtctx,
  * List of parameters that can be set using ZSTDMT_setMTCtxParameter() */
 typedef enum {
     ZSTDMT_p_jobSize,     /* Each job is compressed in parallel. By default, this value is dynamically determined depending on compression parameters. Can be set explicitly here. */
-    ZSTDMT_p_overlapLog,  /* Each job may reload a part of previous job to enhance compressionr ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
+    ZSTDMT_p_overlapLog,  /* Each job may reload a part of previous job to enhance compression ratio; 0 == no overlap, 6(default) == use 1/8th of window, >=9 == use full window. This is a "sticky" parameter : its value will be re-used on next compression job */
     ZSTDMT_p_rsyncable    /* Enables rsyncable mode. */
 } ZSTDMT_parameter;
 
@@ -101,12 +118,12 @@ typedef enum {
  * The function must be called typically after ZSTD_createCCtx() but __before ZSTDMT_init*() !__
  * Parameters not explicitly reset by ZSTDMT_init*() remain the same in consecutive compression sessions.
  * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
+ZSTDMT_API size_t ZSTDMT_setMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int value);
 
 /* ZSTDMT_getMTCtxParameter() :
  * Query the ZSTDMT_CCtx for a parameter value.
  * @return : 0, or an error code (which can be tested using ZSTD_isError()) */
-ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
+ZSTDMT_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter parameter, int* value);
 
 
 /*! ZSTDMT_compressStream_generic() :
@@ -116,7 +133,7 @@ ZSTDLIB_API size_t ZSTDMT_getMTCtxParameter(ZSTDMT_CCtx* mtctx, ZSTDMT_parameter
  *           0 if fully flushed
  *           or an error code
  *  note : needs to be init using any ZSTD_initCStream*() variant */
-ZSTDLIB_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
+ZSTDMT_API size_t ZSTDMT_compressStream_generic(ZSTDMT_CCtx* mtctx,
                                                 ZSTD_outBuffer* output,
                                                 ZSTD_inBuffer* input,
                                                 ZSTD_EndDirective endOp);
diff --git a/thirdparty/zstd/decompress/zstd_ddict.c b/thirdparty/zstd/decompress/zstd_ddict.c
index 2ad0440684..0af3d23bfe 100644
--- a/thirdparty/zstd/decompress/zstd_ddict.c
+++ b/thirdparty/zstd/decompress/zstd_ddict.c
@@ -105,9 +105,9 @@ ZSTD_loadEntropy_intoDDict(ZSTD_DDict* ddict,
     ddict->dictID = MEM_readLE32((const char*)ddict->dictContent + ZSTD_FRAMEIDSIZE);
 
     /* load entropy tables */
-    CHECK_E( ZSTD_loadDEntropy(&ddict->entropy,
-                                ddict->dictContent, ddict->dictSize),
-             dictionary_corrupted );
+    RETURN_ERROR_IF(ZSTD_isError(ZSTD_loadDEntropy(
+            &ddict->entropy, ddict->dictContent, ddict->dictSize)),
+        dictionary_corrupted);
     ddict->entropyPresent = 1;
     return 0;
 }
@@ -133,7 +133,7 @@ static size_t ZSTD_initDDict_internal(ZSTD_DDict* ddict,
     ddict->entropy.hufTable[0] = (HUF_DTable)((HufLog)*0x1000001);  /* cover both little and big endian */
 
     /* parse dictionary content */
-    CHECK_F( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );
+    FORWARD_IF_ERROR( ZSTD_loadEntropy_intoDDict(ddict, dictContentType) );
 
     return 0;
 }
diff --git a/thirdparty/zstd/decompress/zstd_decompress.c b/thirdparty/zstd/decompress/zstd_decompress.c
index feef1ef67a..675596f5aa 100644
--- a/thirdparty/zstd/decompress/zstd_decompress.c
+++ b/thirdparty/zstd/decompress/zstd_decompress.c
@@ -106,6 +106,7 @@ static void ZSTD_initDCtx_internal(ZSTD_DCtx* dctx)
     dctx->ddictLocal  = NULL;
     dctx->dictEnd     = NULL;
     dctx->ddictIsCold = 0;
+    dctx->dictUses = ZSTD_dont_use;
     dctx->inBuff      = NULL;
     dctx->inBuffSize  = 0;
     dctx->outBuffSize = 0;
@@ -147,13 +148,20 @@ ZSTD_DCtx* ZSTD_createDCtx(void)
     return ZSTD_createDCtx_advanced(ZSTD_defaultCMem);
 }
 
+static void ZSTD_clearDict(ZSTD_DCtx* dctx)
+{
+    ZSTD_freeDDict(dctx->ddictLocal);
+    dctx->ddictLocal = NULL;
+    dctx->ddict = NULL;
+    dctx->dictUses = ZSTD_dont_use;
+}
+
 size_t ZSTD_freeDCtx(ZSTD_DCtx* dctx)
 {
     if (dctx==NULL) return 0;   /* support free on NULL */
-    if (dctx->staticSize) return ERROR(memory_allocation);   /* not compatible with static DCtx */
+    RETURN_ERROR_IF(dctx->staticSize, memory_allocation, "not compatible with static DCtx");
     {   ZSTD_customMem const cMem = dctx->customMem;
-        ZSTD_freeDDict(dctx->ddictLocal);
-        dctx->ddictLocal = NULL;
+        ZSTD_clearDict(dctx);
         ZSTD_free(dctx->inBuff, cMem);
         dctx->inBuff = NULL;
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
@@ -203,7 +211,7 @@ unsigned ZSTD_isFrame(const void* buffer, size_t size)
 static size_t ZSTD_frameHeaderSize_internal(const void* src, size_t srcSize, ZSTD_format_e format)
 {
     size_t const minInputSize = ZSTD_startingInputLength(format);
-    if (srcSize < minInputSize) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < minInputSize, srcSize_wrong);
 
     {   BYTE const fhd = ((const BYTE*)src)[minInputSize-1];
         U32 const dictID= fhd & 3;
@@ -238,7 +246,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
 
     memset(zfhPtr, 0, sizeof(*zfhPtr));   /* not strictly necessary, but static analyzer do not understand that zfhPtr is only going to be read only if return value is zero, since they are 2 different signals */
     if (srcSize < minInputSize) return minInputSize;
-    if (src==NULL) return ERROR(GENERIC);   /* invalid parameter */
+    RETURN_ERROR_IF(src==NULL, GENERIC, "invalid parameter");
 
     if ( (format != ZSTD_f_zstd1_magicless)
       && (MEM_readLE32(src) != ZSTD_MAGICNUMBER) ) {
@@ -251,7 +259,7 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
             zfhPtr->frameType = ZSTD_skippableFrame;
             return 0;
         }
-        return ERROR(prefix_unknown);
+        RETURN_ERROR(prefix_unknown);
     }
 
     /* ensure there is enough `srcSize` to fully read/decode frame header */
@@ -269,14 +277,13 @@ size_t ZSTD_getFrameHeader_advanced(ZSTD_frameHeader* zfhPtr, const void* src, s
         U64 windowSize = 0;
         U32 dictID = 0;
         U64 frameContentSize = ZSTD_CONTENTSIZE_UNKNOWN;
-        if ((fhdByte & 0x08) != 0)
-            return ERROR(frameParameter_unsupported); /* reserved bits, must be zero */
+        RETURN_ERROR_IF((fhdByte & 0x08) != 0, frameParameter_unsupported,
+                        "reserved bits, must be zero");
 
         if (!singleSegment) {
             BYTE const wlByte = ip[pos++];
             U32 const windowLog = (wlByte >> 3) + ZSTD_WINDOWLOG_ABSOLUTEMIN;
-            if (windowLog > ZSTD_WINDOWLOG_MAX)
-                return ERROR(frameParameter_windowTooLarge);
+            RETURN_ERROR_IF(windowLog > ZSTD_WINDOWLOG_MAX, frameParameter_windowTooLarge);
             windowSize = (1ULL << windowLog);
             windowSize += (windowSize >> 3) * (wlByte&7);
         }
@@ -348,12 +355,11 @@ static size_t readSkippableFrameSize(void const* src, size_t srcSize)
     size_t const skippableHeaderSize = ZSTD_SKIPPABLEHEADERSIZE;
     U32 sizeU32;
 
-    if (srcSize < ZSTD_SKIPPABLEHEADERSIZE)
-        return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < ZSTD_SKIPPABLEHEADERSIZE, srcSize_wrong);
 
     sizeU32 = MEM_readLE32((BYTE const*)src + ZSTD_FRAMEIDSIZE);
-    if ((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32)
-        return ERROR(frameParameter_unsupported);
+    RETURN_ERROR_IF((U32)(sizeU32 + ZSTD_SKIPPABLEHEADERSIZE) < sizeU32,
+                    frameParameter_unsupported);
 
     return skippableHeaderSize + sizeU32;
 }
@@ -428,67 +434,124 @@ static size_t ZSTD_decodeFrameHeader(ZSTD_DCtx* dctx, const void* src, size_t he
 {
     size_t const result = ZSTD_getFrameHeader_advanced(&(dctx->fParams), src, headerSize, dctx->format);
     if (ZSTD_isError(result)) return result;    /* invalid header */
-    if (result>0) return ERROR(srcSize_wrong);  /* headerSize too small */
-    if (dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID))
-        return ERROR(dictionary_wrong);
+    RETURN_ERROR_IF(result>0, srcSize_wrong, "headerSize too small");
+#ifndef FUZZING_BUILD_MODE_UNSAFE_FOR_PRODUCTION
+    /* Skip the dictID check in fuzzing mode, because it makes the search
+     * harder.
+     */
+    RETURN_ERROR_IF(dctx->fParams.dictID && (dctx->dictID != dctx->fParams.dictID),
+                    dictionary_wrong);
+#endif
     if (dctx->fParams.checksumFlag) XXH64_reset(&dctx->xxhState, 0);
     return 0;
 }
 
+static ZSTD_frameSizeInfo ZSTD_errorFrameSizeInfo(size_t ret)
+{
+    ZSTD_frameSizeInfo frameSizeInfo;
+    frameSizeInfo.compressedSize = ret;
+    frameSizeInfo.decompressedBound = ZSTD_CONTENTSIZE_ERROR;
+    return frameSizeInfo;
+}
 
-/** ZSTD_findFrameCompressedSize() :
- *  compatible with legacy mode
- *  `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame
- *  `srcSize` must be at least as large as the frame contained
- *  @return : the compressed size of the frame starting at `src` */
-size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
+static ZSTD_frameSizeInfo ZSTD_findFrameSizeInfo(const void* src, size_t srcSize)
 {
+    ZSTD_frameSizeInfo frameSizeInfo;
+    memset(&frameSizeInfo, 0, sizeof(ZSTD_frameSizeInfo));
+
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT >= 1)
     if (ZSTD_isLegacy(src, srcSize))
-        return ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
+        return ZSTD_findFrameSizeInfoLegacy(src, srcSize);
 #endif
-    if ( (srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
-      && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START ) {
-        return readSkippableFrameSize(src, srcSize);
+
+    if ((srcSize >= ZSTD_SKIPPABLEHEADERSIZE)
+        && (MEM_readLE32(src) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {
+        frameSizeInfo.compressedSize = readSkippableFrameSize(src, srcSize);
+        return frameSizeInfo;
     } else {
         const BYTE* ip = (const BYTE*)src;
         const BYTE* const ipstart = ip;
         size_t remainingSize = srcSize;
+        size_t nbBlocks = 0;
         ZSTD_frameHeader zfh;
 
         /* Extract Frame Header */
         {   size_t const ret = ZSTD_getFrameHeader(&zfh, src, srcSize);
-            if (ZSTD_isError(ret)) return ret;
-            if (ret > 0) return ERROR(srcSize_wrong);
+            if (ZSTD_isError(ret))
+                return ZSTD_errorFrameSizeInfo(ret);
+            if (ret > 0)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
         }
 
         ip += zfh.headerSize;
         remainingSize -= zfh.headerSize;
 
-        /* Loop on each block */
+        /* Iterate over each block */
         while (1) {
             blockProperties_t blockProperties;
             size_t const cBlockSize = ZSTD_getcBlockSize(ip, remainingSize, &blockProperties);
-            if (ZSTD_isError(cBlockSize)) return cBlockSize;
+            if (ZSTD_isError(cBlockSize))
+                return ZSTD_errorFrameSizeInfo(cBlockSize);
 
             if (ZSTD_blockHeaderSize + cBlockSize > remainingSize)
-                return ERROR(srcSize_wrong);
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
 
             ip += ZSTD_blockHeaderSize + cBlockSize;
             remainingSize -= ZSTD_blockHeaderSize + cBlockSize;
+            nbBlocks++;
 
             if (blockProperties.lastBlock) break;
         }
 
-        if (zfh.checksumFlag) {   /* Final frame content checksum */
-            if (remainingSize < 4) return ERROR(srcSize_wrong);
+        /* Final frame content checksum */
+        if (zfh.checksumFlag) {
+            if (remainingSize < 4)
+                return ZSTD_errorFrameSizeInfo(ERROR(srcSize_wrong));
             ip += 4;
         }
 
-        return ip - ipstart;
+        frameSizeInfo.compressedSize = ip - ipstart;
+        frameSizeInfo.decompressedBound = (zfh.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN)
+                                        ? zfh.frameContentSize
+                                        : nbBlocks * zfh.blockSizeMax;
+        return frameSizeInfo;
     }
 }
 
+/** ZSTD_findFrameCompressedSize() :
+ *  compatible with legacy mode
+ *  `src` must point to the start of a ZSTD frame, ZSTD legacy frame, or skippable frame
+ *  `srcSize` must be at least as large as the frame contained
+ *  @return : the compressed size of the frame starting at `src` */
+size_t ZSTD_findFrameCompressedSize(const void *src, size_t srcSize)
+{
+    ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
+    return frameSizeInfo.compressedSize;
+}
+
+
+/** ZSTD_decompressBound() :
+ *  compatible with legacy mode
+ *  `src` must point to the start of a ZSTD frame or a skippeable frame
+ *  `srcSize` must be at least as large as the frame contained
+ *  @return : the maximum decompressed size of the compressed source
+ */
+unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize)
+{
+    unsigned long long bound = 0;
+    /* Iterate over each frame */
+    while (srcSize > 0) {
+        ZSTD_frameSizeInfo const frameSizeInfo = ZSTD_findFrameSizeInfo(src, srcSize);
+        size_t const compressedSize = frameSizeInfo.compressedSize;
+        unsigned long long const decompressedBound = frameSizeInfo.decompressedBound;
+        if (ZSTD_isError(compressedSize) || decompressedBound == ZSTD_CONTENTSIZE_ERROR)
+            return ZSTD_CONTENTSIZE_ERROR;
+        src = (const BYTE*)src + compressedSize;
+        srcSize -= compressedSize;
+        bound += decompressedBound;
+    }
+    return bound;
+}
 
 
 /*-*************************************************************
@@ -522,9 +585,9 @@ static size_t ZSTD_copyRawBlock(void* dst, size_t dstCapacity,
     DEBUGLOG(5, "ZSTD_copyRawBlock");
     if (dst == NULL) {
         if (srcSize == 0) return 0;
-        return ERROR(dstBuffer_null);
+        RETURN_ERROR(dstBuffer_null);
     }
-    if (srcSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(srcSize > dstCapacity, dstSize_tooSmall);
     memcpy(dst, src, srcSize);
     return srcSize;
 }
@@ -535,9 +598,9 @@ static size_t ZSTD_setRleBlock(void* dst, size_t dstCapacity,
 {
     if (dst == NULL) {
         if (regenSize == 0) return 0;
-        return ERROR(dstBuffer_null);
+        RETURN_ERROR(dstBuffer_null);
     }
-    if (regenSize > dstCapacity) return ERROR(dstSize_tooSmall);
+    RETURN_ERROR_IF(regenSize > dstCapacity, dstSize_tooSmall);
     memset(dst, b, regenSize);
     return regenSize;
 }
@@ -560,15 +623,16 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
     DEBUGLOG(4, "ZSTD_decompressFrame (srcSize:%i)", (int)*srcSizePtr);
 
     /* check */
-    if (remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize)
-        return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(
+        remainingSrcSize < ZSTD_FRAMEHEADERSIZE_MIN+ZSTD_blockHeaderSize,
+        srcSize_wrong);
 
     /* Frame Header */
     {   size_t const frameHeaderSize = ZSTD_frameHeaderSize(ip, ZSTD_FRAMEHEADERSIZE_PREFIX);
         if (ZSTD_isError(frameHeaderSize)) return frameHeaderSize;
-        if (remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize)
-            return ERROR(srcSize_wrong);
-        CHECK_F( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) );
+        RETURN_ERROR_IF(remainingSrcSize < frameHeaderSize+ZSTD_blockHeaderSize,
+                        srcSize_wrong);
+        FORWARD_IF_ERROR( ZSTD_decodeFrameHeader(dctx, ip, frameHeaderSize) );
         ip += frameHeaderSize; remainingSrcSize -= frameHeaderSize;
     }
 
@@ -581,7 +645,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
 
         ip += ZSTD_blockHeaderSize;
         remainingSrcSize -= ZSTD_blockHeaderSize;
-        if (cBlockSize > remainingSrcSize) return ERROR(srcSize_wrong);
+        RETURN_ERROR_IF(cBlockSize > remainingSrcSize, srcSize_wrong);
 
         switch(blockProperties.blockType)
         {
@@ -596,7 +660,7 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
             break;
         case bt_reserved :
         default:
-            return ERROR(corruption_detected);
+            RETURN_ERROR(corruption_detected);
         }
 
         if (ZSTD_isError(decodedSize)) return decodedSize;
@@ -609,15 +673,15 @@ static size_t ZSTD_decompressFrame(ZSTD_DCtx* dctx,
     }
 
     if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
-        if ((U64)(op-ostart) != dctx->fParams.frameContentSize) {
-            return ERROR(corruption_detected);
-    }   }
+        RETURN_ERROR_IF((U64)(op-ostart) != dctx->fParams.frameContentSize,
+                        corruption_detected);
+    }
     if (dctx->fParams.checksumFlag) { /* Frame content checksum verification */
         U32 const checkCalc = (U32)XXH64_digest(&dctx->xxhState);
         U32 checkRead;
-        if (remainingSrcSize<4) return ERROR(checksum_wrong);
+        RETURN_ERROR_IF(remainingSrcSize<4, checksum_wrong);
         checkRead = MEM_readLE32(ip);
-        if (checkRead != checkCalc) return ERROR(checksum_wrong);
+        RETURN_ERROR_IF(checkRead != checkCalc, checksum_wrong);
         ip += 4;
         remainingSrcSize -= 4;
     }
@@ -652,8 +716,8 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
             size_t decodedSize;
             size_t const frameSize = ZSTD_findFrameCompressedSizeLegacy(src, srcSize);
             if (ZSTD_isError(frameSize)) return frameSize;
-            /* legacy support is not compatible with static dctx */
-            if (dctx->staticSize) return ERROR(memory_allocation);
+            RETURN_ERROR_IF(dctx->staticSize, memory_allocation,
+                "legacy support is not compatible with static dctx");
 
             decodedSize = ZSTD_decompressLegacy(dst, dstCapacity, src, frameSize, dict, dictSize);
             if (ZSTD_isError(decodedSize)) return decodedSize;
@@ -676,7 +740,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
                 size_t const skippableSize = readSkippableFrameSize(src, srcSize);
                 if (ZSTD_isError(skippableSize))
                     return skippableSize;
-                if (srcSize < skippableSize) return ERROR(srcSize_wrong);
+                RETURN_ERROR_IF(srcSize < skippableSize, srcSize_wrong);
 
                 src = (const BYTE *)src + skippableSize;
                 srcSize -= skippableSize;
@@ -685,29 +749,29 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
 
         if (ddict) {
             /* we were called from ZSTD_decompress_usingDDict */
-            CHECK_F(ZSTD_decompressBegin_usingDDict(dctx, ddict));
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(dctx, ddict));
         } else {
             /* this will initialize correctly with no dict if dict == NULL, so
              * use this in all cases but ddict */
-            CHECK_F(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDict(dctx, dict, dictSize));
         }
         ZSTD_checkContinuity(dctx, dst);
 
         {   const size_t res = ZSTD_decompressFrame(dctx, dst, dstCapacity,
                                                     &src, &srcSize);
-            if ( (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
-              && (moreThan1Frame==1) ) {
-                /* at least one frame successfully completed,
-                 * but following bytes are garbage :
-                 * it's more likely to be a srcSize error,
-                 * specifying more bytes than compressed size of frame(s).
-                 * This error message replaces ERROR(prefix_unknown),
-                 * which would be confusing, as the first header is actually correct.
-                 * Note that one could be unlucky, it might be a corruption error instead,
-                 * happening right at the place where we expect zstd magic bytes.
-                 * But this is _much_ less likely than a srcSize field error. */
-                return ERROR(srcSize_wrong);
-            }
+            RETURN_ERROR_IF(
+                (ZSTD_getErrorCode(res) == ZSTD_error_prefix_unknown)
+             && (moreThan1Frame==1),
+                srcSize_wrong,
+                "at least one frame successfully completed, but following "
+                "bytes are garbage: it's more likely to be a srcSize error, "
+                "specifying more bytes than compressed size of frame(s). This "
+                "error message replaces ERROR(prefix_unknown), which would be "
+                "confusing, as the first header is actually correct. Note that "
+                "one could be unlucky, it might be a corruption error instead, "
+                "happening right at the place where we expect zstd magic "
+                "bytes. But this is _much_ less likely than a srcSize field "
+                "error.");
             if (ZSTD_isError(res)) return res;
             assert(res <= dstCapacity);
             dst = (BYTE*)dst + res;
@@ -716,7 +780,7 @@ static size_t ZSTD_decompressMultiFrame(ZSTD_DCtx* dctx,
         moreThan1Frame = 1;
     }  /* while (srcSize >= ZSTD_frameHeaderSize_prefix) */
 
-    if (srcSize) return ERROR(srcSize_wrong); /* input not entirely consumed */
+    RETURN_ERROR_IF(srcSize, srcSize_wrong, "input not entirely consumed");
 
     return (BYTE*)dst - (BYTE*)dststart;
 }
@@ -730,9 +794,26 @@ size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
 }
 
 
+static ZSTD_DDict const* ZSTD_getDDict(ZSTD_DCtx* dctx)
+{
+    switch (dctx->dictUses) {
+    default:
+        assert(0 /* Impossible */);
+        /* fall-through */
+    case ZSTD_dont_use:
+        ZSTD_clearDict(dctx);
+        return NULL;
+    case ZSTD_use_indefinitely:
+        return dctx->ddict;
+    case ZSTD_use_once:
+        dctx->dictUses = ZSTD_dont_use;
+        return dctx->ddict;
+    }
+}
+
 size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, const void* src, size_t srcSize)
 {
-    return ZSTD_decompress_usingDict(dctx, dst, dstCapacity, src, srcSize, NULL, 0);
+    return ZSTD_decompress_usingDDict(dctx, dst, dstCapacity, src, srcSize, ZSTD_getDDict(dctx));
 }
 
 
@@ -741,7 +822,7 @@ size_t ZSTD_decompress(void* dst, size_t dstCapacity, const void* src, size_t sr
 #if defined(ZSTD_HEAPMODE) && (ZSTD_HEAPMODE>=1)
     size_t regenSize;
     ZSTD_DCtx* const dctx = ZSTD_createDCtx();
-    if (dctx==NULL) return ERROR(memory_allocation);
+    RETURN_ERROR_IF(dctx==NULL, memory_allocation);
     regenSize = ZSTD_decompressDCtx(dctx, dst, dstCapacity, src, srcSize);
     ZSTD_freeDCtx(dctx);
     return regenSize;
@@ -791,8 +872,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
 {
     DEBUGLOG(5, "ZSTD_decompressContinue (srcSize:%u)", (unsigned)srcSize);
     /* Sanity check */
-    if (srcSize != dctx->expected)
-        return ERROR(srcSize_wrong);  /* not allowed */
+    RETURN_ERROR_IF(srcSize != dctx->expected, srcSize_wrong, "not allowed");
     if (dstCapacity) ZSTD_checkContinuity(dctx, dst);
 
     switch (dctx->stage)
@@ -817,7 +897,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
     case ZSTDds_decodeFrameHeader:
         assert(src != NULL);
         memcpy(dctx->headerBuffer + (dctx->headerSize - srcSize), src, srcSize);
-        CHECK_F(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
+        FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(dctx, dctx->headerBuffer, dctx->headerSize));
         dctx->expected = ZSTD_blockHeaderSize;
         dctx->stage = ZSTDds_decodeBlockHeader;
         return 0;
@@ -867,7 +947,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
                 break;
             case bt_reserved :   /* should never happen */
             default:
-                return ERROR(corruption_detected);
+                RETURN_ERROR(corruption_detected);
             }
             if (ZSTD_isError(rSize)) return rSize;
             DEBUGLOG(5, "ZSTD_decompressContinue: decoded size from block : %u", (unsigned)rSize);
@@ -876,10 +956,10 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
 
             if (dctx->stage == ZSTDds_decompressLastBlock) {   /* end of frame */
                 DEBUGLOG(4, "ZSTD_decompressContinue: decoded size from frame : %u", (unsigned)dctx->decodedSize);
-                if (dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN) {
-                    if (dctx->decodedSize != dctx->fParams.frameContentSize) {
-                        return ERROR(corruption_detected);
-                }   }
+                RETURN_ERROR_IF(
+                    dctx->fParams.frameContentSize != ZSTD_CONTENTSIZE_UNKNOWN
+                 && dctx->decodedSize != dctx->fParams.frameContentSize,
+                    corruption_detected);
                 if (dctx->fParams.checksumFlag) {  /* another round for frame checksum */
                     dctx->expected = 4;
                     dctx->stage = ZSTDds_checkChecksum;
@@ -900,7 +980,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
         {   U32 const h32 = (U32)XXH64_digest(&dctx->xxhState);
             U32 const check32 = MEM_readLE32(src);
             DEBUGLOG(4, "ZSTD_decompressContinue: checksum : calculated %08X :: %08X read", (unsigned)h32, (unsigned)check32);
-            if (check32 != h32) return ERROR(checksum_wrong);
+            RETURN_ERROR_IF(check32 != h32, checksum_wrong);
             dctx->expected = 0;
             dctx->stage = ZSTDds_getFrameHeaderSize;
             return 0;
@@ -921,7 +1001,7 @@ size_t ZSTD_decompressContinue(ZSTD_DCtx* dctx, void* dst, size_t dstCapacity, c
 
     default:
         assert(0);   /* impossible */
-        return ERROR(GENERIC);   /* some compiler require default to do something */
+        RETURN_ERROR(GENERIC);   /* some compiler require default to do something */
     }
 }
 
@@ -945,7 +1025,7 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
     const BYTE* dictPtr = (const BYTE*)dict;
     const BYTE* const dictEnd = dictPtr + dictSize;
 
-    if (dictSize <= 8) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictSize <= 8, dictionary_corrupted);
     assert(MEM_readLE32(dict) == ZSTD_MAGIC_DICTIONARY);   /* dict must be valid */
     dictPtr += 8;   /* skip header = magic + dictID */
 
@@ -964,16 +1044,16 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
                                                 dictPtr, dictEnd - dictPtr,
                                                 workspace, workspaceSize);
 #endif
-        if (HUF_isError(hSize)) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(HUF_isError(hSize), dictionary_corrupted);
         dictPtr += hSize;
     }
 
     {   short offcodeNCount[MaxOff+1];
         unsigned offcodeMaxValue = MaxOff, offcodeLog;
         size_t const offcodeHeaderSize = FSE_readNCount(offcodeNCount, &offcodeMaxValue, &offcodeLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(offcodeHeaderSize)) return ERROR(dictionary_corrupted);
-        if (offcodeMaxValue > MaxOff) return ERROR(dictionary_corrupted);
-        if (offcodeLog > OffFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(offcodeHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(offcodeMaxValue > MaxOff, dictionary_corrupted);
+        RETURN_ERROR_IF(offcodeLog > OffFSELog, dictionary_corrupted);
         ZSTD_buildFSETable( entropy->OFTable,
                             offcodeNCount, offcodeMaxValue,
                             OF_base, OF_bits,
@@ -984,9 +1064,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
     {   short matchlengthNCount[MaxML+1];
         unsigned matchlengthMaxValue = MaxML, matchlengthLog;
         size_t const matchlengthHeaderSize = FSE_readNCount(matchlengthNCount, &matchlengthMaxValue, &matchlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(matchlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (matchlengthMaxValue > MaxML) return ERROR(dictionary_corrupted);
-        if (matchlengthLog > MLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(matchlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(matchlengthMaxValue > MaxML, dictionary_corrupted);
+        RETURN_ERROR_IF(matchlengthLog > MLFSELog, dictionary_corrupted);
         ZSTD_buildFSETable( entropy->MLTable,
                             matchlengthNCount, matchlengthMaxValue,
                             ML_base, ML_bits,
@@ -997,9 +1077,9 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
     {   short litlengthNCount[MaxLL+1];
         unsigned litlengthMaxValue = MaxLL, litlengthLog;
         size_t const litlengthHeaderSize = FSE_readNCount(litlengthNCount, &litlengthMaxValue, &litlengthLog, dictPtr, dictEnd-dictPtr);
-        if (FSE_isError(litlengthHeaderSize)) return ERROR(dictionary_corrupted);
-        if (litlengthMaxValue > MaxLL) return ERROR(dictionary_corrupted);
-        if (litlengthLog > LLFSELog) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(FSE_isError(litlengthHeaderSize), dictionary_corrupted);
+        RETURN_ERROR_IF(litlengthMaxValue > MaxLL, dictionary_corrupted);
+        RETURN_ERROR_IF(litlengthLog > LLFSELog, dictionary_corrupted);
         ZSTD_buildFSETable( entropy->LLTable,
                             litlengthNCount, litlengthMaxValue,
                             LL_base, LL_bits,
@@ -1007,12 +1087,13 @@ ZSTD_loadDEntropy(ZSTD_entropyDTables_t* entropy,
         dictPtr += litlengthHeaderSize;
     }
 
-    if (dictPtr+12 > dictEnd) return ERROR(dictionary_corrupted);
+    RETURN_ERROR_IF(dictPtr+12 > dictEnd, dictionary_corrupted);
     {   int i;
         size_t const dictContentSize = (size_t)(dictEnd - (dictPtr+12));
         for (i=0; i<3; i++) {
             U32 const rep = MEM_readLE32(dictPtr); dictPtr += 4;
-            if (rep==0 || rep >= dictContentSize) return ERROR(dictionary_corrupted);
+            RETURN_ERROR_IF(rep==0 || rep >= dictContentSize,
+                            dictionary_corrupted);
             entropy->rep[i] = rep;
     }   }
 
@@ -1030,7 +1111,7 @@ static size_t ZSTD_decompress_insertDictionary(ZSTD_DCtx* dctx, const void* dict
 
     /* load entropy tables */
     {   size_t const eSize = ZSTD_loadDEntropy(&dctx->entropy, dict, dictSize);
-        if (ZSTD_isError(eSize)) return ERROR(dictionary_corrupted);
+        RETURN_ERROR_IF(ZSTD_isError(eSize), dictionary_corrupted);
         dict = (const char*)dict + eSize;
         dictSize -= eSize;
     }
@@ -1064,9 +1145,11 @@ size_t ZSTD_decompressBegin(ZSTD_DCtx* dctx)
 
 size_t ZSTD_decompressBegin_usingDict(ZSTD_DCtx* dctx, const void* dict, size_t dictSize)
 {
-    CHECK_F( ZSTD_decompressBegin(dctx) );
+    FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) );
     if (dict && dictSize)
-        CHECK_E(ZSTD_decompress_insertDictionary(dctx, dict, dictSize), dictionary_corrupted);
+        RETURN_ERROR_IF(
+            ZSTD_isError(ZSTD_decompress_insertDictionary(dctx, dict, dictSize)),
+            dictionary_corrupted);
     return 0;
 }
 
@@ -1085,7 +1168,7 @@ size_t ZSTD_decompressBegin_usingDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
         DEBUGLOG(4, "DDict is %s",
                     dctx->ddictIsCold ? "~cold~" : "hot!");
     }
-    CHECK_F( ZSTD_decompressBegin(dctx) );
+    FORWARD_IF_ERROR( ZSTD_decompressBegin(dctx) );
     if (ddict) {   /* NULL ddict is equivalent to no dictionary */
         ZSTD_copyDDictParameters(dctx, ddict);
     }
@@ -1104,7 +1187,7 @@ unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize)
 }
 
 /*! ZSTD_getDictID_fromFrame() :
- *  Provides the dictID required to decompresse frame stored within `src`.
+ *  Provides the dictID required to decompress frame stored within `src`.
  *  If @return == 0, the dictID could not be decoded.
  *  This could for one of the following reasons :
  *  - The frame does not require a dictionary (most common case).
@@ -1176,15 +1259,14 @@ size_t ZSTD_DCtx_loadDictionary_advanced(ZSTD_DCtx* dctx,
                                          ZSTD_dictLoadMethod_e dictLoadMethod,
                                          ZSTD_dictContentType_e dictContentType)
 {
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
-    ZSTD_freeDDict(dctx->ddictLocal);
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+    ZSTD_clearDict(dctx);
     if (dict && dictSize >= 8) {
         dctx->ddictLocal = ZSTD_createDDict_advanced(dict, dictSize, dictLoadMethod, dictContentType, dctx->customMem);
-        if (dctx->ddictLocal == NULL) return ERROR(memory_allocation);
-    } else {
-        dctx->ddictLocal = NULL;
+        RETURN_ERROR_IF(dctx->ddictLocal == NULL, memory_allocation);
+        dctx->ddict = dctx->ddictLocal;
+        dctx->dictUses = ZSTD_use_indefinitely;
     }
-    dctx->ddict = dctx->ddictLocal;
     return 0;
 }
 
@@ -1200,7 +1282,9 @@ size_t ZSTD_DCtx_loadDictionary(ZSTD_DCtx* dctx, const void* dict, size_t dictSi
 
 size_t ZSTD_DCtx_refPrefix_advanced(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize, ZSTD_dictContentType_e dictContentType)
 {
-    return ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType);
+    FORWARD_IF_ERROR(ZSTD_DCtx_loadDictionary_advanced(dctx, prefix, prefixSize, ZSTD_dlm_byRef, dictContentType));
+    dctx->dictUses = ZSTD_use_once;
+    return 0;
 }
 
 size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSize)
@@ -1215,9 +1299,8 @@ size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx, const void* prefix, size_t prefixSiz
 size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize)
 {
     DEBUGLOG(4, "ZSTD_initDStream_usingDict");
-    zds->streamStage = zdss_init;
-    zds->noForwardProgress = 0;
-    CHECK_F( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
+    FORWARD_IF_ERROR( ZSTD_DCtx_reset(zds, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_DCtx_loadDictionary(zds, dict, dictSize) );
     return ZSTD_FRAMEHEADERSIZE_PREFIX;
 }
 
@@ -1225,7 +1308,7 @@ size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t di
 size_t ZSTD_initDStream(ZSTD_DStream* zds)
 {
     DEBUGLOG(4, "ZSTD_initDStream");
-    return ZSTD_initDStream_usingDict(zds, NULL, 0);
+    return ZSTD_initDStream_usingDDict(zds, NULL);
 }
 
 /* ZSTD_initDStream_usingDDict() :
@@ -1233,9 +1316,9 @@ size_t ZSTD_initDStream(ZSTD_DStream* zds)
  * this function cannot fail */
 size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
 {
-    size_t const initResult = ZSTD_initDStream(dctx);
-    dctx->ddict = ddict;
-    return initResult;
+    FORWARD_IF_ERROR( ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only) );
+    FORWARD_IF_ERROR( ZSTD_DCtx_refDDict(dctx, ddict) );
+    return ZSTD_FRAMEHEADERSIZE_PREFIX;
 }
 
 /* ZSTD_resetDStream() :
@@ -1243,19 +1326,19 @@ size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* dctx, const ZSTD_DDict* ddict)
  * this function cannot fail */
 size_t ZSTD_resetDStream(ZSTD_DStream* dctx)
 {
-    DEBUGLOG(4, "ZSTD_resetDStream");
-    dctx->streamStage = zdss_loadHeader;
-    dctx->lhSize = dctx->inPos = dctx->outStart = dctx->outEnd = 0;
-    dctx->legacyVersion = 0;
-    dctx->hostageByte = 0;
+    FORWARD_IF_ERROR(ZSTD_DCtx_reset(dctx, ZSTD_reset_session_only));
     return ZSTD_FRAMEHEADERSIZE_PREFIX;
 }
 
 
 size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict)
 {
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
-    dctx->ddict = ddict;
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+    ZSTD_clearDict(dctx);
+    if (ddict) {
+        dctx->ddict = ddict;
+        dctx->dictUses = ZSTD_use_indefinitely;
+    }
     return 0;
 }
 
@@ -1267,9 +1350,9 @@ size_t ZSTD_DCtx_setMaxWindowSize(ZSTD_DCtx* dctx, size_t maxWindowSize)
     ZSTD_bounds const bounds = ZSTD_dParam_getBounds(ZSTD_d_windowLogMax);
     size_t const min = (size_t)1 << bounds.lowerBound;
     size_t const max = (size_t)1 << bounds.upperBound;
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
-    if (maxWindowSize < min) return ERROR(parameter_outOfBound);
-    if (maxWindowSize > max) return ERROR(parameter_outOfBound);
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+    RETURN_ERROR_IF(maxWindowSize < min, parameter_outOfBound);
+    RETURN_ERROR_IF(maxWindowSize > max, parameter_outOfBound);
     dctx->maxWindowSize = maxWindowSize;
     return 0;
 }
@@ -1311,15 +1394,15 @@ static int ZSTD_dParam_withinBounds(ZSTD_dParameter dParam, int value)
 }
 
 #define CHECK_DBOUNDS(p,v) {                \
-    if (!ZSTD_dParam_withinBounds(p, v))    \
-        return ERROR(parameter_outOfBound); \
+    RETURN_ERROR_IF(!ZSTD_dParam_withinBounds(p, v), parameter_outOfBound); \
 }
 
 size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value)
 {
-    if (dctx->streamStage != zdss_init) return ERROR(stage_wrong);
+    RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
     switch(dParam) {
         case ZSTD_d_windowLogMax:
+            if (value == 0) value = ZSTD_WINDOWLOG_LIMIT_DEFAULT;
             CHECK_DBOUNDS(ZSTD_d_windowLogMax, value);
             dctx->maxWindowSize = ((size_t)1) << value;
             return 0;
@@ -1329,19 +1412,20 @@ size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter dParam, int value
             return 0;
         default:;
     }
-    return ERROR(parameter_unsupported);
+    RETURN_ERROR(parameter_unsupported);
 }
 
 size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset)
 {
     if ( (reset == ZSTD_reset_session_only)
       || (reset == ZSTD_reset_session_and_parameters) ) {
-        (void)ZSTD_initDStream(dctx);
+        dctx->streamStage = zdss_init;
+        dctx->noForwardProgress = 0;
     }
     if ( (reset == ZSTD_reset_parameters)
       || (reset == ZSTD_reset_session_and_parameters) ) {
-        if (dctx->streamStage != zdss_init)
-            return ERROR(stage_wrong);
+        RETURN_ERROR_IF(dctx->streamStage != zdss_init, stage_wrong);
+        ZSTD_clearDict(dctx);
         dctx->format = ZSTD_f_zstd1;
         dctx->maxWindowSize = ZSTD_MAXWINDOWSIZE_DEFAULT;
     }
@@ -1360,7 +1444,8 @@ size_t ZSTD_decodingBufferSize_min(unsigned long long windowSize, unsigned long
     unsigned long long const neededRBSize = windowSize + blockSize + (WILDCOPY_OVERLENGTH * 2);
     unsigned long long const neededSize = MIN(frameContentSize, neededRBSize);
     size_t const minRBSize = (size_t) neededSize;
-    if ((unsigned long long)minRBSize != neededSize) return ERROR(frameParameter_windowTooLarge);
+    RETURN_ERROR_IF((unsigned long long)minRBSize != neededSize,
+                    frameParameter_windowTooLarge);
     return minRBSize;
 }
 
@@ -1378,9 +1463,9 @@ size_t ZSTD_estimateDStreamSize_fromFrame(const void* src, size_t srcSize)
     ZSTD_frameHeader zfh;
     size_t const err = ZSTD_getFrameHeader(&zfh, src, srcSize);
     if (ZSTD_isError(err)) return err;
-    if (err>0) return ERROR(srcSize_wrong);
-    if (zfh.windowSize > windowSizeMax)
-        return ERROR(frameParameter_windowTooLarge);
+    RETURN_ERROR_IF(err>0, srcSize_wrong);
+    RETURN_ERROR_IF(zfh.windowSize > windowSizeMax,
+                    frameParameter_windowTooLarge);
     return ZSTD_estimateDStreamSize((size_t)zfh.windowSize);
 }
 
@@ -1406,16 +1491,16 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
     U32 someMoreWork = 1;
 
     DEBUGLOG(5, "ZSTD_decompressStream");
-    if (input->pos > input->size) {  /* forbidden */
-        DEBUGLOG(5, "in: pos: %u   vs size: %u",
-                    (U32)input->pos, (U32)input->size);
-        return ERROR(srcSize_wrong);
-    }
-    if (output->pos > output->size) {  /* forbidden */
-        DEBUGLOG(5, "out: pos: %u   vs size: %u",
-                    (U32)output->pos, (U32)output->size);
-        return ERROR(dstSize_tooSmall);
-    }
+    RETURN_ERROR_IF(
+        input->pos > input->size,
+        srcSize_wrong,
+        "forbidden. in: pos: %u   vs size: %u",
+        (U32)input->pos, (U32)input->size);
+    RETURN_ERROR_IF(
+        output->pos > output->size,
+        dstSize_tooSmall,
+        "forbidden. out: pos: %u   vs size: %u",
+        (U32)output->pos, (U32)output->size);
     DEBUGLOG(5, "input size : %u", (U32)(input->size - input->pos));
 
     while (someMoreWork) {
@@ -1423,15 +1508,18 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
         {
         case zdss_init :
             DEBUGLOG(5, "stage zdss_init => transparent reset ");
-            ZSTD_resetDStream(zds);   /* transparent reset on starting decoding a new frame */
+            zds->streamStage = zdss_loadHeader;
+            zds->lhSize = zds->inPos = zds->outStart = zds->outEnd = 0;
+            zds->legacyVersion = 0;
+            zds->hostageByte = 0;
             /* fall-through */
 
         case zdss_loadHeader :
             DEBUGLOG(5, "stage zdss_loadHeader (srcSize : %u)", (U32)(iend - ip));
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
             if (zds->legacyVersion) {
-                /* legacy support is incompatible with static dctx */
-                if (zds->staticSize) return ERROR(memory_allocation);
+                RETURN_ERROR_IF(zds->staticSize, memory_allocation,
+                    "legacy support is incompatible with static dctx");
                 {   size_t const hint = ZSTD_decompressLegacyStream(zds->legacyContext, zds->legacyVersion, output, input);
                     if (hint==0) zds->streamStage = zdss_init;
                     return hint;
@@ -1443,12 +1531,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
 #if defined(ZSTD_LEGACY_SUPPORT) && (ZSTD_LEGACY_SUPPORT>=1)
                     U32 const legacyVersion = ZSTD_isLegacy(istart, iend-istart);
                     if (legacyVersion) {
-                        const void* const dict = zds->ddict ? ZSTD_DDict_dictContent(zds->ddict) : NULL;
-                        size_t const dictSize = zds->ddict ? ZSTD_DDict_dictSize(zds->ddict) : 0;
+                        ZSTD_DDict const* const ddict = ZSTD_getDDict(zds);
+                        const void* const dict = ddict ? ZSTD_DDict_dictContent(ddict) : NULL;
+                        size_t const dictSize = ddict ? ZSTD_DDict_dictSize(ddict) : 0;
                         DEBUGLOG(5, "ZSTD_decompressStream: detected legacy version v0.%u", legacyVersion);
-                        /* legacy support is incompatible with static dctx */
-                        if (zds->staticSize) return ERROR(memory_allocation);
-                        CHECK_F(ZSTD_initLegacyStream(&zds->legacyContext,
+                        RETURN_ERROR_IF(zds->staticSize, memory_allocation,
+                            "legacy support is incompatible with static dctx");
+                        FORWARD_IF_ERROR(ZSTD_initLegacyStream(&zds->legacyContext,
                                     zds->previousLegacyVersion, legacyVersion,
                                     dict, dictSize));
                         zds->legacyVersion = zds->previousLegacyVersion = legacyVersion;
@@ -1482,7 +1571,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                 size_t const cSize = ZSTD_findFrameCompressedSize(istart, iend-istart);
                 if (cSize <= (size_t)(iend-istart)) {
                     /* shortcut : using single-pass mode */
-                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, zds->ddict);
+                    size_t const decompressedSize = ZSTD_decompress_usingDDict(zds, op, oend-op, istart, cSize, ZSTD_getDDict(zds));
                     if (ZSTD_isError(decompressedSize)) return decompressedSize;
                     DEBUGLOG(4, "shortcut to single-pass ZSTD_decompress_usingDDict()")
                     ip = istart + cSize;
@@ -1495,13 +1584,13 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
 
             /* Consume header (see ZSTDds_decodeFrameHeader) */
             DEBUGLOG(4, "Consume header");
-            CHECK_F(ZSTD_decompressBegin_usingDDict(zds, zds->ddict));
+            FORWARD_IF_ERROR(ZSTD_decompressBegin_usingDDict(zds, ZSTD_getDDict(zds)));
 
             if ((MEM_readLE32(zds->headerBuffer) & ZSTD_MAGIC_SKIPPABLE_MASK) == ZSTD_MAGIC_SKIPPABLE_START) {  /* skippable frame */
                 zds->expected = MEM_readLE32(zds->headerBuffer + ZSTD_FRAMEIDSIZE);
                 zds->stage = ZSTDds_skipFrame;
             } else {
-                CHECK_F(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
+                FORWARD_IF_ERROR(ZSTD_decodeFrameHeader(zds, zds->headerBuffer, zds->lhSize));
                 zds->expected = ZSTD_blockHeaderSize;
                 zds->stage = ZSTDds_decodeBlockHeader;
             }
@@ -1511,7 +1600,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                         (U32)(zds->fParams.windowSize >>10),
                         (U32)(zds->maxWindowSize >> 10) );
             zds->fParams.windowSize = MAX(zds->fParams.windowSize, 1U << ZSTD_WINDOWLOG_ABSOLUTEMIN);
-            if (zds->fParams.windowSize > zds->maxWindowSize) return ERROR(frameParameter_windowTooLarge);
+            RETURN_ERROR_IF(zds->fParams.windowSize > zds->maxWindowSize,
+                            frameParameter_windowTooLarge);
 
             /* Adapt buffer sizes to frame header instructions */
             {   size_t const neededInBuffSize = MAX(zds->fParams.blockSizeMax, 4 /* frame checksum */);
@@ -1525,14 +1615,15 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                     if (zds->staticSize) {  /* static DCtx */
                         DEBUGLOG(4, "staticSize : %u", (U32)zds->staticSize);
                         assert(zds->staticSize >= sizeof(ZSTD_DCtx));  /* controlled at init */
-                        if (bufferSize > zds->staticSize - sizeof(ZSTD_DCtx))
-                            return ERROR(memory_allocation);
+                        RETURN_ERROR_IF(
+                            bufferSize > zds->staticSize - sizeof(ZSTD_DCtx),
+                            memory_allocation);
                     } else {
                         ZSTD_free(zds->inBuff, zds->customMem);
                         zds->inBuffSize = 0;
                         zds->outBuffSize = 0;
                         zds->inBuff = (char*)ZSTD_malloc(bufferSize, zds->customMem);
-                        if (zds->inBuff == NULL) return ERROR(memory_allocation);
+                        RETURN_ERROR_IF(zds->inBuff == NULL, memory_allocation);
                     }
                     zds->inBuffSize = neededInBuffSize;
                     zds->outBuff = zds->inBuff + zds->inBuffSize;
@@ -1574,7 +1665,9 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
                 if (isSkipFrame) {
                     loadedSize = MIN(toLoad, (size_t)(iend-ip));
                 } else {
-                    if (toLoad > zds->inBuffSize - zds->inPos) return ERROR(corruption_detected);   /* should never happen */
+                    RETURN_ERROR_IF(toLoad > zds->inBuffSize - zds->inPos,
+                                    corruption_detected,
+                                    "should never happen");
                     loadedSize = ZSTD_limitCopy(zds->inBuff + zds->inPos, toLoad, ip, iend-ip);
                 }
                 ip += loadedSize;
@@ -1615,7 +1708,7 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
 
         default:
             assert(0);    /* impossible */
-            return ERROR(GENERIC);   /* some compiler require default to do something */
+            RETURN_ERROR(GENERIC);   /* some compiler require default to do something */
     }   }
 
     /* result */
@@ -1624,8 +1717,8 @@ size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inB
     if ((ip==istart) && (op==ostart)) {  /* no forward progress */
         zds->noForwardProgress ++;
         if (zds->noForwardProgress >= ZSTD_NO_FORWARD_PROGRESS_MAX) {
-            if (op==oend) return ERROR(dstSize_tooSmall);
-            if (ip==iend) return ERROR(srcSize_wrong);
+            RETURN_ERROR_IF(op==oend, dstSize_tooSmall);
+            RETURN_ERROR_IF(ip==iend, srcSize_wrong);
             assert(0);
         }
     } else {
diff --git a/thirdparty/zstd/decompress/zstd_decompress_block.c b/thirdparty/zstd/decompress/zstd_decompress_block.c
index 32baad9fbb..a2a7eedcf2 100644
--- a/thirdparty/zstd/decompress/zstd_decompress_block.c
+++ b/thirdparty/zstd/decompress/zstd_decompress_block.c
@@ -56,14 +56,15 @@ static void ZSTD_copy4(void* dst, const void* src) { memcpy(dst, src, 4); }
 size_t ZSTD_getcBlockSize(const void* src, size_t srcSize,
                           blockProperties_t* bpPtr)
 {
-    if (srcSize < ZSTD_blockHeaderSize) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < ZSTD_blockHeaderSize, srcSize_wrong);
+
     {   U32 const cBlockHeader = MEM_readLE24(src);
         U32 const cSize = cBlockHeader >> 3;
         bpPtr->lastBlock = cBlockHeader & 1;
         bpPtr->blockType = (blockType_e)((cBlockHeader >> 1) & 3);
         bpPtr->origSize = cSize;   /* only useful for RLE */
         if (bpPtr->blockType == bt_rle) return 1;
-        if (bpPtr->blockType == bt_reserved) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(bpPtr->blockType == bt_reserved, corruption_detected);
         return cSize;
     }
 }
@@ -78,7 +79,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
 size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                           const void* src, size_t srcSize)   /* note : srcSize < BLOCKSIZE */
 {
-    if (srcSize < MIN_CBLOCK_SIZE) return ERROR(corruption_detected);
+    RETURN_ERROR_IF(srcSize < MIN_CBLOCK_SIZE, corruption_detected);
 
     {   const BYTE* const istart = (const BYTE*) src;
         symbolEncodingType_e const litEncType = (symbolEncodingType_e)(istart[0] & 3);
@@ -86,11 +87,11 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
         switch(litEncType)
         {
         case set_repeat:
-            if (dctx->litEntropy==0) return ERROR(dictionary_corrupted);
+            RETURN_ERROR_IF(dctx->litEntropy==0, dictionary_corrupted);
             /* fall-through */
 
         case set_compressed:
-            if (srcSize < 5) return ERROR(corruption_detected);   /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3 */
+            RETURN_ERROR_IF(srcSize < 5, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need up to 5 for case 3");
             {   size_t lhSize, litSize, litCSize;
                 U32 singleStream=0;
                 U32 const lhlCode = (istart[0] >> 2) & 3;
@@ -118,8 +119,8 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                     litCSize = (lhc >> 22) + (istart[4] << 10);
                     break;
                 }
-                if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
-                if (litCSize + lhSize > srcSize) return ERROR(corruption_detected);
+                RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
+                RETURN_ERROR_IF(litCSize + lhSize > srcSize, corruption_detected);
 
                 /* prefetch huffman table if cold */
                 if (dctx->ddictIsCold && (litSize > 768 /* heuristic */)) {
@@ -157,7 +158,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                     }
                 }
 
-                if (HUF_isError(hufSuccess)) return ERROR(corruption_detected);
+                RETURN_ERROR_IF(HUF_isError(hufSuccess), corruption_detected);
 
                 dctx->litPtr = dctx->litBuffer;
                 dctx->litSize = litSize;
@@ -187,7 +188,7 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                 }
 
                 if (lhSize+litSize+WILDCOPY_OVERLENGTH > srcSize) {  /* risk reading beyond src buffer with wildcopy */
-                    if (litSize+lhSize > srcSize) return ERROR(corruption_detected);
+                    RETURN_ERROR_IF(litSize+lhSize > srcSize, corruption_detected);
                     memcpy(dctx->litBuffer, istart+lhSize, litSize);
                     dctx->litPtr = dctx->litBuffer;
                     dctx->litSize = litSize;
@@ -216,17 +217,17 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                 case 3:
                     lhSize = 3;
                     litSize = MEM_readLE24(istart) >> 4;
-                    if (srcSize<4) return ERROR(corruption_detected);   /* srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4 */
+                    RETURN_ERROR_IF(srcSize<4, corruption_detected, "srcSize >= MIN_CBLOCK_SIZE == 3; here we need lhSize+1 = 4");
                     break;
                 }
-                if (litSize > ZSTD_BLOCKSIZE_MAX) return ERROR(corruption_detected);
+                RETURN_ERROR_IF(litSize > ZSTD_BLOCKSIZE_MAX, corruption_detected);
                 memset(dctx->litBuffer, istart[lhSize], litSize + WILDCOPY_OVERLENGTH);
                 dctx->litPtr = dctx->litBuffer;
                 dctx->litSize = litSize;
                 return lhSize+1;
             }
         default:
-            return ERROR(corruption_detected);   /* impossible */
+            RETURN_ERROR(corruption_detected, "impossible");
         }
     }
 }
@@ -436,8 +437,8 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
     switch(type)
     {
     case set_rle :
-        if (!srcSize) return ERROR(srcSize_wrong);
-        if ( (*(const BYTE*)src) > max) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(!srcSize, srcSize_wrong);
+        RETURN_ERROR_IF((*(const BYTE*)src) > max, corruption_detected);
         {   U32 const symbol = *(const BYTE*)src;
             U32 const baseline = baseValue[symbol];
             U32 const nbBits = nbAdditionalBits[symbol];
@@ -449,7 +450,7 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
         *DTablePtr = defaultTable;
         return 0;
     case set_repeat:
-        if (!flagRepeatTable) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(!flagRepeatTable, corruption_detected);
         /* prefetch FSE table if used */
         if (ddictIsCold && (nbSeq > 24 /* heuristic */)) {
             const void* const pStart = *DTablePtr;
@@ -461,15 +462,15 @@ static size_t ZSTD_buildSeqTable(ZSTD_seqSymbol* DTableSpace, const ZSTD_seqSymb
         {   unsigned tableLog;
             S16 norm[MaxSeq+1];
             size_t const headerSize = FSE_readNCount(norm, &max, &tableLog, src, srcSize);
-            if (FSE_isError(headerSize)) return ERROR(corruption_detected);
-            if (tableLog > maxLog) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(FSE_isError(headerSize), corruption_detected);
+            RETURN_ERROR_IF(tableLog > maxLog, corruption_detected);
             ZSTD_buildFSETable(DTableSpace, norm, max, baseValue, nbAdditionalBits, tableLog);
             *DTablePtr = DTableSpace;
             return headerSize;
         }
-    default :   /* impossible */
+    default :
         assert(0);
-        return ERROR(GENERIC);
+        RETURN_ERROR(GENERIC, "impossible");
     }
 }
 
@@ -483,28 +484,28 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
     DEBUGLOG(5, "ZSTD_decodeSeqHeaders");
 
     /* check */
-    if (srcSize < MIN_SEQUENCES_SIZE) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize < MIN_SEQUENCES_SIZE, srcSize_wrong);
 
     /* SeqHead */
     nbSeq = *ip++;
     if (!nbSeq) {
         *nbSeqPtr=0;
-        if (srcSize != 1) return ERROR(srcSize_wrong);
+        RETURN_ERROR_IF(srcSize != 1, srcSize_wrong);
         return 1;
     }
     if (nbSeq > 0x7F) {
         if (nbSeq == 0xFF) {
-            if (ip+2 > iend) return ERROR(srcSize_wrong);
+            RETURN_ERROR_IF(ip+2 > iend, srcSize_wrong);
             nbSeq = MEM_readLE16(ip) + LONGNBSEQ, ip+=2;
         } else {
-            if (ip >= iend) return ERROR(srcSize_wrong);
+            RETURN_ERROR_IF(ip >= iend, srcSize_wrong);
             nbSeq = ((nbSeq-0x80)<<8) + *ip++;
         }
     }
     *nbSeqPtr = nbSeq;
 
     /* FSE table descriptors */
-    if (ip+4 > iend) return ERROR(srcSize_wrong); /* minimum possible size */
+    RETURN_ERROR_IF(ip+4 > iend, srcSize_wrong); /* minimum possible size */
     {   symbolEncodingType_e const LLtype = (symbolEncodingType_e)(*ip >> 6);
         symbolEncodingType_e const OFtype = (symbolEncodingType_e)((*ip >> 4) & 3);
         symbolEncodingType_e const MLtype = (symbolEncodingType_e)((*ip >> 2) & 3);
@@ -517,7 +518,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                                                       LL_base, LL_bits,
                                                       LL_defaultDTable, dctx->fseEntropy,
                                                       dctx->ddictIsCold, nbSeq);
-            if (ZSTD_isError(llhSize)) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(ZSTD_isError(llhSize), corruption_detected);
             ip += llhSize;
         }
 
@@ -527,7 +528,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                                                       OF_base, OF_bits,
                                                       OF_defaultDTable, dctx->fseEntropy,
                                                       dctx->ddictIsCold, nbSeq);
-            if (ZSTD_isError(ofhSize)) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(ZSTD_isError(ofhSize), corruption_detected);
             ip += ofhSize;
         }
 
@@ -537,7 +538,7 @@ size_t ZSTD_decodeSeqHeaders(ZSTD_DCtx* dctx, int* nbSeqPtr,
                                                       ML_base, ML_bits,
                                                       ML_defaultDTable, dctx->fseEntropy,
                                                       dctx->ddictIsCold, nbSeq);
-            if (ZSTD_isError(mlhSize)) return ERROR(corruption_detected);
+            RETURN_ERROR_IF(ZSTD_isError(mlhSize), corruption_detected);
             ip += mlhSize;
         }
     }
@@ -590,8 +591,8 @@ size_t ZSTD_execSequenceLast7(BYTE* op,
     const BYTE* match = oLitEnd - sequence.offset;
 
     /* check */
-    if (oMatchEnd>oend) return ERROR(dstSize_tooSmall);   /* last match must fit within dstBuffer */
-    if (iLitEnd > litLimit) return ERROR(corruption_detected);   /* try to read beyond literal buffer */
+    RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must fit within dstBuffer");
+    RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "try to read beyond literal buffer");
 
     /* copy literals */
     while (op < oLitEnd) *op++ = *(*litPtr)++;
@@ -599,7 +600,7 @@ size_t ZSTD_execSequenceLast7(BYTE* op,
     /* copy Match */
     if (sequence.offset > (size_t)(oLitEnd - base)) {
         /* offset beyond prefix */
-        if (sequence.offset > (size_t)(oLitEnd - vBase)) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - vBase),corruption_detected);
         match = dictEnd - (base-match);
         if (match + sequence.matchLength <= dictEnd) {
             memmove(oLitEnd, match, sequence.matchLength);
@@ -631,8 +632,8 @@ size_t ZSTD_execSequence(BYTE* op,
     const BYTE* match = oLitEnd - sequence.offset;
 
     /* check */
-    if (oMatchEnd>oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-    if (iLitEnd > litLimit) return ERROR(corruption_detected);   /* over-read beyond lit buffer */
+    RETURN_ERROR_IF(oMatchEnd>oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend");
+    RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer");
     if (oLitEnd>oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, virtualStart, dictEnd);
 
     /* copy Literals */
@@ -645,8 +646,7 @@ size_t ZSTD_execSequence(BYTE* op,
     /* copy Match */
     if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
         /* offset beyond prefix -> go into extDict */
-        if (sequence.offset > (size_t)(oLitEnd - virtualStart))
-            return ERROR(corruption_detected);
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - virtualStart), corruption_detected);
         match = dictEnd + (match - prefixStart);
         if (match + sequence.matchLength <= dictEnd) {
             memmove(oLitEnd, match, sequence.matchLength);
@@ -712,8 +712,8 @@ size_t ZSTD_execSequenceLong(BYTE* op,
     const BYTE* match = sequence.match;
 
     /* check */
-    if (oMatchEnd > oend) return ERROR(dstSize_tooSmall); /* last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend */
-    if (iLitEnd > litLimit) return ERROR(corruption_detected);   /* over-read beyond lit buffer */
+    RETURN_ERROR_IF(oMatchEnd > oend, dstSize_tooSmall, "last match must start at a minimum distance of WILDCOPY_OVERLENGTH from oend");
+    RETURN_ERROR_IF(iLitEnd > litLimit, corruption_detected, "over-read beyond lit buffer");
     if (oLitEnd > oend_w) return ZSTD_execSequenceLast7(op, oend, sequence, litPtr, litLimit, prefixStart, dictStart, dictEnd);
 
     /* copy Literals */
@@ -726,7 +726,7 @@ size_t ZSTD_execSequenceLong(BYTE* op,
     /* copy Match */
     if (sequence.offset > (size_t)(oLitEnd - prefixStart)) {
         /* offset beyond prefix */
-        if (sequence.offset > (size_t)(oLitEnd - dictStart)) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(sequence.offset > (size_t)(oLitEnd - dictStart), corruption_detected);
         if (match + sequence.matchLength <= dictEnd) {
             memmove(oLitEnd, match, sequence.matchLength);
             return sequenceLength;
@@ -801,7 +801,7 @@ ZSTD_updateFseState(ZSTD_fseState* DStatePtr, BIT_DStream_t* bitD)
 /* We need to add at most (ZSTD_WINDOWLOG_MAX_32 - 1) bits to read the maximum
  * offset bits. But we can only read at most (STREAM_ACCUMULATOR_MIN_32 - 1)
  * bits before reloading. This value is the maximum number of bytes we read
- * after reloading when we are decoding long offets.
+ * after reloading when we are decoding long offsets.
  */
 #define LONG_OFFSETS_MAX_EXTRA_BITS_32                       \
     (ZSTD_WINDOWLOG_MAX_32 > STREAM_ACCUMULATOR_MIN_32       \
@@ -911,7 +911,9 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
         seqState_t seqState;
         dctx->fseEntropy = 1;
         { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) seqState.prevOffset[i] = dctx->entropy.rep[i]; }
-        CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected);
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
+            corruption_detected);
         ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
         ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
         ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
@@ -927,14 +929,14 @@ ZSTD_decompressSequences_body( ZSTD_DCtx* dctx,
 
         /* check if reached exact end */
         DEBUGLOG(5, "ZSTD_decompressSequences_body: after decode loop, remaining nbSeq : %i", nbSeq);
-        if (nbSeq) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(nbSeq, corruption_detected);
         /* save reps for next block */
         { U32 i; for (i=0; i<ZSTD_REP_NUM; i++) dctx->entropy.rep[i] = (U32)(seqState.prevOffset[i]); }
     }
 
     /* last literal segment */
     {   size_t const lastLLSize = litEnd - litPtr;
-        if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall);
         memcpy(op, litPtr, lastLLSize);
         op += lastLLSize;
     }
@@ -1066,7 +1068,9 @@ ZSTD_decompressSequencesLong_body(
         seqState.pos = (size_t)(op-prefixStart);
         seqState.dictEnd = dictEnd;
         assert(iend >= ip);
-        CHECK_E(BIT_initDStream(&seqState.DStream, ip, iend-ip), corruption_detected);
+        RETURN_ERROR_IF(
+            ERR_isError(BIT_initDStream(&seqState.DStream, ip, iend-ip)),
+            corruption_detected);
         ZSTD_initFseState(&seqState.stateLL, &seqState.DStream, dctx->LLTptr);
         ZSTD_initFseState(&seqState.stateOffb, &seqState.DStream, dctx->OFTptr);
         ZSTD_initFseState(&seqState.stateML, &seqState.DStream, dctx->MLTptr);
@@ -1076,7 +1080,7 @@ ZSTD_decompressSequencesLong_body(
             sequences[seqNb] = ZSTD_decodeSequenceLong(&seqState, isLongOffset);
             PREFETCH_L1(sequences[seqNb].match); PREFETCH_L1(sequences[seqNb].match + sequences[seqNb].matchLength - 1); /* note : it's safe to invoke PREFETCH() on any memory address, including invalid ones */
         }
-        if (seqNb<seqAdvance) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(seqNb<seqAdvance, corruption_detected);
 
         /* decode and decompress */
         for ( ; (BIT_reloadDStream(&(seqState.DStream)) <= BIT_DStream_completed) && (seqNb<nbSeq) ; seqNb++) {
@@ -1087,7 +1091,7 @@ ZSTD_decompressSequencesLong_body(
             sequences[seqNb & STORED_SEQS_MASK] = sequence;
             op += oneSeqSize;
         }
-        if (seqNb<nbSeq) return ERROR(corruption_detected);
+        RETURN_ERROR_IF(seqNb<nbSeq, corruption_detected);
 
         /* finish queue */
         seqNb -= seqAdvance;
@@ -1103,7 +1107,7 @@ ZSTD_decompressSequencesLong_body(
 
     /* last literal segment */
     {   size_t const lastLLSize = litEnd - litPtr;
-        if (lastLLSize > (size_t)(oend-op)) return ERROR(dstSize_tooSmall);
+        RETURN_ERROR_IF(lastLLSize > (size_t)(oend-op), dstSize_tooSmall);
         memcpy(op, litPtr, lastLLSize);
         op += lastLLSize;
     }
@@ -1176,7 +1180,7 @@ ZSTD_decompressSequences(ZSTD_DCtx* dctx, void* dst, size_t maxDstSize,
 /* ZSTD_decompressSequencesLong() :
  * decompression function triggered when a minimum share of offsets is considered "long",
  * aka out of cache.
- * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes mearning "farther than memory cache distance".
+ * note : "long" definition seems overloaded here, sometimes meaning "wider than bitstream register", and sometimes meaning "farther than memory cache distance".
  * This function will try to mitigate main memory latency through the use of prefetching */
 static size_t
 ZSTD_decompressSequencesLong(ZSTD_DCtx* dctx,
@@ -1240,7 +1244,7 @@ ZSTD_decompressBlock_internal(ZSTD_DCtx* dctx,
     ZSTD_longOffset_e const isLongOffset = (ZSTD_longOffset_e)(MEM_32bits() && (!frame || (dctx->fParams.windowSize > (1ULL << STREAM_ACCUMULATOR_MIN))));
     DEBUGLOG(5, "ZSTD_decompressBlock_internal (size : %u)", (U32)srcSize);
 
-    if (srcSize >= ZSTD_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);
+    RETURN_ERROR_IF(srcSize >= ZSTD_BLOCKSIZE_MAX, srcSize_wrong);
 
     /* Decode literals section */
     {   size_t const litCSize = ZSTD_decodeLiteralsBlock(dctx, src, srcSize);
diff --git a/thirdparty/zstd/decompress/zstd_decompress_internal.h b/thirdparty/zstd/decompress/zstd_decompress_internal.h
index abd0030519..ccbdfa090f 100644
--- a/thirdparty/zstd/decompress/zstd_decompress_internal.h
+++ b/thirdparty/zstd/decompress/zstd_decompress_internal.h
@@ -89,6 +89,12 @@ typedef enum { ZSTDds_getFrameHeaderSize, ZSTDds_decodeFrameHeader,
 typedef enum { zdss_init=0, zdss_loadHeader,
                zdss_read, zdss_load, zdss_flush } ZSTD_dStreamStage;
 
+typedef enum {
+    ZSTD_use_indefinitely = -1,  /* Use the dictionary indefinitely */
+    ZSTD_dont_use = 0,           /* Do not use the dictionary (if one exists free it) */
+    ZSTD_use_once = 1            /* Use the dictionary once and set to ZSTD_dont_use */
+} ZSTD_dictUses_e;
+
 struct ZSTD_DCtx_s
 {
     const ZSTD_seqSymbol* LLTptr;
@@ -123,6 +129,7 @@ struct ZSTD_DCtx_s
     const ZSTD_DDict* ddict;     /* set by ZSTD_initDStream_usingDDict(), or ZSTD_DCtx_refDDict() */
     U32 dictID;
     int ddictIsCold;             /* if == 1 : dictionary is "new" for working context, and presumed "cold" (not in cpu cache) */
+    ZSTD_dictUses_e dictUses;
 
     /* streaming */
     ZSTD_dStreamStage streamStage;
diff --git a/thirdparty/zstd/zstd.h b/thirdparty/zstd/zstd.h
index b18fc8a44b..53470c18f3 100644
--- a/thirdparty/zstd/zstd.h
+++ b/thirdparty/zstd/zstd.h
@@ -70,8 +70,8 @@ extern "C" {
 
 /*------   Version   ------*/
 #define ZSTD_VERSION_MAJOR    1
-#define ZSTD_VERSION_MINOR    3
-#define ZSTD_VERSION_RELEASE  8
+#define ZSTD_VERSION_MINOR    4
+#define ZSTD_VERSION_RELEASE  0
 
 #define ZSTD_VERSION_NUMBER  (ZSTD_VERSION_MAJOR *100*100 + ZSTD_VERSION_MINOR *100 + ZSTD_VERSION_RELEASE)
 ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< to check runtime library version */
@@ -90,6 +90,21 @@ ZSTDLIB_API const char* ZSTD_versionString(void);   /* requires v1.3.0+ */
 #endif
 
 /***************************************
+*  Constants
+***************************************/
+
+/* All magic numbers are supposed read/written to/from files/memory using little-endian convention */
+#define ZSTD_MAGICNUMBER            0xFD2FB528    /* valid since v0.8.0 */
+#define ZSTD_MAGIC_DICTIONARY       0xEC30A437    /* valid since v0.7.0 */
+#define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50    /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */
+#define ZSTD_MAGIC_SKIPPABLE_MASK   0xFFFFFFF0
+
+#define ZSTD_BLOCKSIZELOG_MAX  17
+#define ZSTD_BLOCKSIZE_MAX     (1<<ZSTD_BLOCKSIZELOG_MAX)
+
+
+
+/***************************************
 *  Simple API
 ***************************************/
 /*! ZSTD_compress() :
@@ -145,12 +160,21 @@ ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t
  * @return : decompressed size of `src` frame content _if known and not empty_, 0 otherwise. */
 ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
 
+/*! ZSTD_findFrameCompressedSize() :
+ * `src` should point to the start of a ZSTD frame or skippable frame.
+ * `srcSize` must be >= first frame size
+ * @return : the compressed size of the first frame starting at `src`,
+ *           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
+ *        or an error code if input is invalid */
+ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
+
 
 /*======  Helper functions  ======*/
 #define ZSTD_COMPRESSBOUND(srcSize)   ((srcSize) + ((srcSize)>>8) + (((srcSize) < (128<<10)) ? (((128<<10) - (srcSize)) >> 11) /* margin, from 64 to 0 */ : 0))  /* this formula ensures that bound(A) + bound(B) <= bound(A+B) as long as A and B >= 128 KB */
 ZSTDLIB_API size_t      ZSTD_compressBound(size_t srcSize); /*!< maximum compressed size in worst case single-pass scenario */
 ZSTDLIB_API unsigned    ZSTD_isError(size_t code);          /*!< tells if a `size_t` function result is an error code */
 ZSTDLIB_API const char* ZSTD_getErrorName(size_t code);     /*!< provides readable string from an error code */
+ZSTDLIB_API int         ZSTD_minCLevel(void);               /*!< minimum negative compression level allowed */
 ZSTDLIB_API int         ZSTD_maxCLevel(void);               /*!< maximum compression level available */
 
 
@@ -195,279 +219,6 @@ ZSTDLIB_API size_t ZSTD_decompressDCtx(ZSTD_DCtx* dctx,
                                  const void* src, size_t srcSize);
 
 
-/**************************
-*  Simple dictionary API
-***************************/
-/*! ZSTD_compress_usingDict() :
- *  Compression at an explicit compression level using a Dictionary.
- *  A dictionary can be any arbitrary data segment (also called a prefix),
- *  or a buffer with specified information (see dictBuilder/zdict.h).
- *  Note : This function loads the dictionary, resulting in significant startup delay.
- *         It's intended for a dictionary used only once.
- *  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */
-ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
-                                           void* dst, size_t dstCapacity,
-                                     const void* src, size_t srcSize,
-                                     const void* dict,size_t dictSize,
-                                           int compressionLevel);
-
-/*! ZSTD_decompress_usingDict() :
- *  Decompression using a known Dictionary.
- *  Dictionary must be identical to the one used during compression.
- *  Note : This function loads the dictionary, resulting in significant startup delay.
- *         It's intended for a dictionary used only once.
- *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
-ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
-                                             void* dst, size_t dstCapacity,
-                                       const void* src, size_t srcSize,
-                                       const void* dict,size_t dictSize);
-
-
-/***********************************
- *  Bulk processing dictionary API
- **********************************/
-typedef struct ZSTD_CDict_s ZSTD_CDict;
-
-/*! ZSTD_createCDict() :
- *  When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once.
- *  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost.
- *  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
- * `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict.
- *  Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content.
- *  Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */
-ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
-                                         int compressionLevel);
-
-/*! ZSTD_freeCDict() :
- *  Function frees memory allocated by ZSTD_createCDict(). */
-ZSTDLIB_API size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
-
-/*! ZSTD_compress_usingCDict() :
- *  Compression using a digested Dictionary.
- *  Recommended when same dictionary is used multiple times.
- *  Note : compression level is _decided at dictionary creation time_,
- *     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */
-ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
-                                            void* dst, size_t dstCapacity,
-                                      const void* src, size_t srcSize,
-                                      const ZSTD_CDict* cdict);
-
-
-typedef struct ZSTD_DDict_s ZSTD_DDict;
-
-/*! ZSTD_createDDict() :
- *  Create a digested dictionary, ready to start decompression operation without startup delay.
- *  dictBuffer can be released after DDict creation, as its content is copied inside DDict. */
-ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
-
-/*! ZSTD_freeDDict() :
- *  Function frees memory allocated with ZSTD_createDDict() */
-ZSTDLIB_API size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
-
-/*! ZSTD_decompress_usingDDict() :
- *  Decompression using a digested Dictionary.
- *  Recommended when same dictionary is used multiple times. */
-ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
-                                              void* dst, size_t dstCapacity,
-                                        const void* src, size_t srcSize,
-                                        const ZSTD_DDict* ddict);
-
-
-/****************************
-*  Streaming
-****************************/
-
-typedef struct ZSTD_inBuffer_s {
-  const void* src;    /**< start of input buffer */
-  size_t size;        /**< size of input buffer */
-  size_t pos;         /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */
-} ZSTD_inBuffer;
-
-typedef struct ZSTD_outBuffer_s {
-  void*  dst;         /**< start of output buffer */
-  size_t size;        /**< size of output buffer */
-  size_t pos;         /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */
-} ZSTD_outBuffer;
-
-
-
-/*-***********************************************************************
-*  Streaming compression - HowTo
-*
-*  A ZSTD_CStream object is required to track streaming operation.
-*  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
-*  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
-*  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
-*
-*  For parallel execution, use one separate ZSTD_CStream per thread.
-*
-*  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
-*
-*  Parameters are sticky : when starting a new compression on the same context,
-*  it will re-use the same sticky parameters as previous compression session.
-*  When in doubt, it's recommended to fully initialize the context before usage.
-*  Use ZSTD_initCStream() to set the parameter to a selected compression level.
-*  Use advanced API (ZSTD_CCtx_setParameter(), etc.) to set more specific parameters.
-*
-*  Use ZSTD_compressStream() as many times as necessary to consume input stream.
-*  The function will automatically update both `pos` fields within `input` and `output`.
-*  Note that the function may not consume the entire input,
-*  for example, because the output buffer is already full,
-*  in which case `input.pos < input.size`.
-*  The caller must check if input has been entirely consumed.
-*  If not, the caller must make some room to receive more compressed data,
-*  and then present again remaining input data.
-* @return : a size hint, preferred nb of bytes to use as input for next function call
-*           or an error code, which can be tested using ZSTD_isError().
-*           Note 1 : it's just a hint, to help latency a little, any value will work fine.
-*           Note 2 : size hint is guaranteed to be <= ZSTD_CStreamInSize()
-*
-*  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
-*  using ZSTD_flushStream(). `output->pos` will be updated.
-*  Note that, if `output->size` is too small, a single invocation of ZSTD_flushStream() might not be enough (return code > 0).
-*  In which case, make some room to receive more compressed data, and call again ZSTD_flushStream().
-*  @return : 0 if internal buffers are entirely flushed,
-*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
-*            or an error code, which can be tested using ZSTD_isError().
-*
-*  ZSTD_endStream() instructs to finish a frame.
-*  It will perform a flush and write frame epilogue.
-*  The epilogue is required for decoders to consider a frame completed.
-*  flush() operation is the same, and follows same rules as ZSTD_flushStream().
-*  @return : 0 if frame fully completed and fully flushed,
-*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
-*            or an error code, which can be tested using ZSTD_isError().
-*
-* *******************************************************************/
-
-typedef ZSTD_CCtx ZSTD_CStream;  /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
-                                 /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */
-/*===== ZSTD_CStream management functions =====*/
-ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
-ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
-
-/*===== Streaming compression functions =====*/
-ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
-ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
-ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
-ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
-
-ZSTDLIB_API size_t ZSTD_CStreamInSize(void);    /**< recommended size for input buffer */
-ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */
-
-
-
-/*-***************************************************************************
-*  Streaming decompression - HowTo
-*
-*  A ZSTD_DStream object is required to track streaming operations.
-*  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
-*  ZSTD_DStream objects can be re-used multiple times.
-*
-*  Use ZSTD_initDStream() to start a new decompression operation.
-* @return : recommended first input size
-*  Alternatively, use advanced API to set specific properties.
-*
-*  Use ZSTD_decompressStream() repetitively to consume your input.
-*  The function will update both `pos` fields.
-*  If `input.pos < input.size`, some input has not been consumed.
-*  It's up to the caller to present again remaining data.
-*  The function tries to flush all data decoded immediately, respecting output buffer size.
-*  If `output.pos < output.size`, decoder has flushed everything it could.
-*  But if `output.pos == output.size`, there might be some data left within internal buffers.,
-*  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
-*  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
-* @return : 0 when a frame is completely decoded and fully flushed,
-*        or an error code, which can be tested using ZSTD_isError(),
-*        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
-*                                the return value is a suggested next input size (just a hint for better latency)
-*                                that will never request more than the remaining frame size.
-* *******************************************************************************/
-
-typedef ZSTD_DCtx ZSTD_DStream;  /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
-                                 /* For compatibility with versions <= v1.2.0, prefer differentiating them. */
-/*===== ZSTD_DStream management functions =====*/
-ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
-ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
-
-/*===== Streaming decompression functions =====*/
-ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds);
-ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
-
-ZSTDLIB_API size_t ZSTD_DStreamInSize(void);    /*!< recommended size for input buffer */
-ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */
-
-#endif  /* ZSTD_H_235446 */
-
-
-
-
-/****************************************************************************************
- *   ADVANCED AND EXPERIMENTAL FUNCTIONS
- ****************************************************************************************
- * The definitions in the following section are considered experimental.
- * They are provided for advanced scenarios.
- * They should never be used with a dynamic library, as prototypes may change in the future.
- * Use them only in association with static linking.
- * ***************************************************************************************/
-
-#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
-#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
-
-
-/****************************************************************************************
- *   Candidate API for promotion to stable status
- ****************************************************************************************
- * The following symbols and constants form the "staging area" :
- * they are considered to join "stable API" by v1.4.0.
- * The proposal is written so that it can be made stable "as is",
- * though it's still possible to suggest improvements.
- * Staging is in fact last chance for changes,
- * the API is locked once reaching "stable" status.
- * ***************************************************************************************/
-
-
-/* ===  Constants   === */
-
-/* all magic numbers are supposed read/written to/from files/memory using little-endian convention */
-#define ZSTD_MAGICNUMBER            0xFD2FB528    /* valid since v0.8.0 */
-#define ZSTD_MAGIC_DICTIONARY       0xEC30A437    /* valid since v0.7.0 */
-#define ZSTD_MAGIC_SKIPPABLE_START  0x184D2A50    /* all 16 values, from 0x184D2A50 to 0x184D2A5F, signal the beginning of a skippable frame */
-#define ZSTD_MAGIC_SKIPPABLE_MASK   0xFFFFFFF0
-
-#define ZSTD_BLOCKSIZELOG_MAX  17
-#define ZSTD_BLOCKSIZE_MAX     (1<<ZSTD_BLOCKSIZELOG_MAX)
-
-
-/* ===   query limits   === */
-
-ZSTDLIB_API int ZSTD_minCLevel(void);  /*!< minimum negative compression level allowed */
-
-
-/* ===   frame size   === */
-
-/*! ZSTD_findFrameCompressedSize() :
- * `src` should point to the start of a ZSTD frame or skippable frame.
- * `srcSize` must be >= first frame size
- * @return : the compressed size of the first frame starting at `src`,
- *           suitable to pass as `srcSize` to `ZSTD_decompress` or similar,
- *        or an error code if input is invalid */
-ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
-
-
-/* ===   Memory management   === */
-
-/*! ZSTD_sizeof_*() :
- *  These functions give the _current_ memory usage of selected object.
- *  Note that object memory usage can evolve (increase or decrease) over time. */
-ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
-ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
-ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
-ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
-ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
-ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
-
-
 /***************************************
 *  Advanced compression API
 ***************************************/
@@ -503,7 +254,10 @@ typedef enum { ZSTD_fast=1,
 
 typedef enum {
 
-    /* compression parameters */
+    /* compression parameters
+     * Note: When compressing with a ZSTD_CDict these parameters are superseded
+     * by the parameters used to construct the ZSTD_CDict. See ZSTD_CCtx_refCDict()
+     * for more info (superseded-by-cdict). */
     ZSTD_c_compressionLevel=100, /* Update all compression parameters according to pre-defined cLevel table
                               * Default level is ZSTD_CLEVEL_DEFAULT==3.
                               * Special: value 0 means default, which is controlled by ZSTD_CLEVEL_DEFAULT.
@@ -625,6 +379,7 @@ typedef enum {
      * ZSTD_c_format
      * ZSTD_c_forceMaxWindow
      * ZSTD_c_forceAttachDict
+     * ZSTD_c_literalCompressionMode
      * Because they are not stable, it's necessary to define ZSTD_STATIC_LINKING_ONLY to access them.
      * note : never ever use experimentalParam? names directly;
      *        also, the enums values themselves are unstable and can still change.
@@ -632,10 +387,10 @@ typedef enum {
      ZSTD_c_experimentalParam1=500,
      ZSTD_c_experimentalParam2=10,
      ZSTD_c_experimentalParam3=1000,
-     ZSTD_c_experimentalParam4=1001
+     ZSTD_c_experimentalParam4=1001,
+     ZSTD_c_experimentalParam5=1002,
 } ZSTD_cParameter;
 
-
 typedef struct {
     size_t error;
     int lowerBound;
@@ -677,63 +432,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_setParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param
  *  Note 3 : Whenever all input data is provided and consumed in a single round,
  *           for example with ZSTD_compress2(),
  *           or invoking immediately ZSTD_compressStream2(,,,ZSTD_e_end),
- *           this value is automatically overriden by srcSize instead.
+ *           this value is automatically overridden by srcSize instead.
  */
 ZSTDLIB_API size_t ZSTD_CCtx_setPledgedSrcSize(ZSTD_CCtx* cctx, unsigned long long pledgedSrcSize);
 
-/*! ZSTD_CCtx_loadDictionary() :
- *  Create an internal CDict from `dict` buffer.
- *  Decompression will have to use same dictionary.
- * @result : 0, or an error code (which can be tested with ZSTD_isError()).
- *  Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary,
- *           meaning "return to no-dictionary mode".
- *  Note 1 : Dictionary is sticky, it will be used for all future compressed frames.
- *           To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters).
- *  Note 2 : Loading a dictionary involves building tables.
- *           It's also a CPU consuming operation, with non-negligible impact on latency.
- *           Tables are dependent on compression parameters, and for this reason,
- *           compression parameters can no longer be changed after loading a dictionary.
- *  Note 3 :`dict` content will be copied internally.
- *           Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead.
- *           In such a case, dictionary buffer must outlive its users.
- *  Note 4 : Use ZSTD_CCtx_loadDictionary_advanced()
- *           to precisely select how dictionary content must be interpreted. */
-ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
-
-/*! ZSTD_CCtx_refCDict() :
- *  Reference a prepared dictionary, to be used for all next compressed frames.
- *  Note that compression parameters are enforced from within CDict,
- *  and supercede any compression parameter previously set within CCtx.
- *  The dictionary will remain valid for future compressed frames using same CCtx.
- * @result : 0, or an error code (which can be tested with ZSTD_isError()).
- *  Special : Referencing a NULL CDict means "return to no-dictionary mode".
- *  Note 1 : Currently, only one dictionary can be managed.
- *           Referencing a new dictionary effectively "discards" any previous one.
- *  Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. */
-ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
-
-/*! ZSTD_CCtx_refPrefix() :
- *  Reference a prefix (single-usage dictionary) for next compressed frame.
- *  A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end).
- *  Decompression will need same prefix to properly regenerate data.
- *  Compressing with a prefix is similar in outcome as performing a diff and compressing it,
- *  but performs much faster, especially during decompression (compression speed is tunable with compression level).
- * @result : 0, or an error code (which can be tested with ZSTD_isError()).
- *  Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary
- *  Note 1 : Prefix buffer is referenced. It **must** outlive compression.
- *           Its content must remain unmodified during compression.
- *  Note 2 : If the intention is to diff some large src data blob with some prior version of itself,
- *           ensure that the window size is large enough to contain the entire source.
- *           See ZSTD_c_windowLog.
- *  Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters.
- *           It's a CPU consuming operation, with non-negligible impact on latency.
- *           If there is a need to use the same prefix multiple times, consider loadDictionary instead.
- *  Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent).
- *           Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. */
-ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx,
-                                 const void* prefix, size_t prefixSize);
-
-
 typedef enum {
     ZSTD_reset_session_only = 1,
     ZSTD_reset_parameters = 2,
@@ -756,8 +458,6 @@ typedef enum {
  */
 ZSTDLIB_API size_t ZSTD_CCtx_reset(ZSTD_CCtx* cctx, ZSTD_ResetDirective reset);
 
-
-
 /*! ZSTD_compress2() :
  *  Behave the same as ZSTD_compressCCtx(), but compression parameters are set using the advanced API.
  *  ZSTD_compress2() always starts a new frame.
@@ -772,48 +472,10 @@ ZSTDLIB_API size_t ZSTD_compress2( ZSTD_CCtx* cctx,
                                    void* dst, size_t dstCapacity,
                              const void* src, size_t srcSize);
 
-typedef enum {
-    ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */
-    ZSTD_e_flush=1,    /* flush any data provided so far,
-                        * it creates (at least) one new block, that can be decoded immediately on reception;
-                        * frame will continue: any future data can still reference previously compressed data, improving compression. */
-    ZSTD_e_end=2       /* flush any remaining data _and_ close current frame.
-                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
-                        * After that point, any additional data starts a new frame.
-                        * note : each frame is independent (does not reference any content from previous frame). */
-} ZSTD_EndDirective;
-
-/*! ZSTD_compressStream2() :
- *  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
- *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
- *  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
- *  - outpot->pos must be <= dstCapacity, input->pos must be <= srcSize
- *  - outpot->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
- *  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
- *  - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available,
- *                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
- *                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
- *  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
- *  - @return provides a minimum amount of data remaining to be flushed from internal buffers
- *            or an error code, which can be tested using ZSTD_isError().
- *            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
- *            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
- *            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
- *  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
- *            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
- *            Before starting a new compression job, or changing compression parameters,
- *            it is required to fully flush internal buffers.
- */
-ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
-                                         ZSTD_outBuffer* output,
-                                         ZSTD_inBuffer* input,
-                                         ZSTD_EndDirective endOp);
-
-
 
-/* ============================== */
-/*   Advanced decompression API   */
-/* ============================== */
+/***************************************
+*  Advanced decompression API
+***************************************/
 
 /* The advanced API pushes parameters one by one into an existing DCtx context.
  * Parameters are sticky, and remain valid for all following frames
@@ -823,14 +485,14 @@ ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
  *        Therefore, no new decompression function is necessary.
  */
 
-
 typedef enum {
 
     ZSTD_d_windowLogMax=100, /* Select a size limit (in power of 2) beyond which
                               * the streaming API will refuse to allocate memory buffer
                               * in order to protect the host from unreasonable memory requirements.
                               * This parameter is only useful in streaming mode, since no internal buffer is allocated in single-pass mode.
-                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT) */
+                              * By default, a decompression context accepts window sizes <= (1 << ZSTD_WINDOWLOG_LIMIT_DEFAULT).
+                              * Special: value 0 means "use default maximum windowLog". */
 
     /* note : additional experimental parameters are also available
      * within the experimental section of the API.
@@ -843,7 +505,6 @@ typedef enum {
 
 } ZSTD_dParameter;
 
-
 /*! ZSTD_dParam_getBounds() :
  *  All parameters must belong to an interval with lower and upper bounds,
  *  otherwise they will either trigger an error or be automatically clamped.
@@ -862,6 +523,389 @@ ZSTDLIB_API ZSTD_bounds ZSTD_dParam_getBounds(ZSTD_dParameter dParam);
  */
 ZSTDLIB_API size_t ZSTD_DCtx_setParameter(ZSTD_DCtx* dctx, ZSTD_dParameter param, int value);
 
+/*! ZSTD_DCtx_reset() :
+ *  Return a DCtx to clean state.
+ *  Session and parameters can be reset jointly or separately.
+ *  Parameters can only be reset when no active frame is being decompressed.
+ * @return : 0, or an error code, which can be tested with ZSTD_isError()
+ */
+ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
+
+
+/****************************
+*  Streaming
+****************************/
+
+typedef struct ZSTD_inBuffer_s {
+  const void* src;    /**< start of input buffer */
+  size_t size;        /**< size of input buffer */
+  size_t pos;         /**< position where reading stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_inBuffer;
+
+typedef struct ZSTD_outBuffer_s {
+  void*  dst;         /**< start of output buffer */
+  size_t size;        /**< size of output buffer */
+  size_t pos;         /**< position where writing stopped. Will be updated. Necessarily 0 <= pos <= size */
+} ZSTD_outBuffer;
+
+
+
+/*-***********************************************************************
+*  Streaming compression - HowTo
+*
+*  A ZSTD_CStream object is required to track streaming operation.
+*  Use ZSTD_createCStream() and ZSTD_freeCStream() to create/release resources.
+*  ZSTD_CStream objects can be reused multiple times on consecutive compression operations.
+*  It is recommended to re-use ZSTD_CStream since it will play nicer with system's memory, by re-using already allocated memory.
+*
+*  For parallel execution, use one separate ZSTD_CStream per thread.
+*
+*  note : since v1.3.0, ZSTD_CStream and ZSTD_CCtx are the same thing.
+*
+*  Parameters are sticky : when starting a new compression on the same context,
+*  it will re-use the same sticky parameters as previous compression session.
+*  When in doubt, it's recommended to fully initialize the context before usage.
+*  Use ZSTD_CCtx_reset() to reset the context and ZSTD_CCtx_setParameter(),
+*  ZSTD_CCtx_setPledgedSrcSize(), or ZSTD_CCtx_loadDictionary() and friends to
+*  set more specific parameters, the pledged source size, or load a dictionary.
+*
+*  Use ZSTD_compressStream2() with ZSTD_e_continue as many times as necessary to
+*  consume input stream. The function will automatically update both `pos`
+*  fields within `input` and `output`.
+*  Note that the function may not consume the entire input, for example, because
+*  the output buffer is already full, in which case `input.pos < input.size`.
+*  The caller must check if input has been entirely consumed.
+*  If not, the caller must make some room to receive more compressed data,
+*  and then present again remaining input data.
+*  note: ZSTD_e_continue is guaranteed to make some forward progress when called,
+*        but doesn't guarantee maximal forward progress. This is especially relevant
+*        when compressing with multiple threads. The call won't block if it can
+*        consume some input, but if it can't it will wait for some, but not all,
+*        output to be flushed.
+* @return : provides a minimum amount of data remaining to be flushed from internal buffers
+*           or an error code, which can be tested using ZSTD_isError().
+*
+*  At any moment, it's possible to flush whatever data might remain stuck within internal buffer,
+*  using ZSTD_compressStream2() with ZSTD_e_flush. `output->pos` will be updated.
+*  Note that, if `output->size` is too small, a single invocation with ZSTD_e_flush might not be enough (return code > 0).
+*  In which case, make some room to receive more compressed data, and call again ZSTD_compressStream2() with ZSTD_e_flush.
+*  You must continue calling ZSTD_compressStream2() with ZSTD_e_flush until it returns 0, at which point you can change the
+*  operation.
+*  note: ZSTD_e_flush will flush as much output as possible, meaning when compressing with multiple threads, it will
+*        block until the flush is complete or the output buffer is full.
+*  @return : 0 if internal buffers are entirely flushed,
+*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+*            or an error code, which can be tested using ZSTD_isError().
+*
+*  Calling ZSTD_compressStream2() with ZSTD_e_end instructs to finish a frame.
+*  It will perform a flush and write frame epilogue.
+*  The epilogue is required for decoders to consider a frame completed.
+*  flush operation is the same, and follows same rules as calling ZSTD_compressStream2() with ZSTD_e_flush.
+*  You must continue calling ZSTD_compressStream2() with ZSTD_e_end until it returns 0, at which point you are free to
+*  start a new frame.
+*  note: ZSTD_e_end will flush as much output as possible, meaning when compressing with multiple threads, it will
+*        block until the flush is complete or the output buffer is full.
+*  @return : 0 if frame fully completed and fully flushed,
+*            >0 if some data still present within internal buffer (the value is minimal estimation of remaining size),
+*            or an error code, which can be tested using ZSTD_isError().
+*
+* *******************************************************************/
+
+typedef ZSTD_CCtx ZSTD_CStream;  /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
+                                 /* Continue to distinguish them for compatibility with older versions <= v1.2.0 */
+/*===== ZSTD_CStream management functions =====*/
+ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
+ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
+
+/*===== Streaming compression functions =====*/
+typedef enum {
+    ZSTD_e_continue=0, /* collect more data, encoder decides when to output compressed result, for optimal compression ratio */
+    ZSTD_e_flush=1,    /* flush any data provided so far,
+                        * it creates (at least) one new block, that can be decoded immediately on reception;
+                        * frame will continue: any future data can still reference previously compressed data, improving compression.
+                        * note : multithreaded compression will block to flush as much output as possible. */
+    ZSTD_e_end=2       /* flush any remaining data _and_ close current frame.
+                        * note that frame is only closed after compressed data is fully flushed (return value == 0).
+                        * After that point, any additional data starts a new frame.
+                        * note : each frame is independent (does not reference any content from previous frame).
+                        : note : multithreaded compression will block to flush as much output as possible. */
+} ZSTD_EndDirective;
+
+/*! ZSTD_compressStream2() :
+ *  Behaves about the same as ZSTD_compressStream, with additional control on end directive.
+ *  - Compression parameters are pushed into CCtx before starting compression, using ZSTD_CCtx_set*()
+ *  - Compression parameters cannot be changed once compression is started (save a list of exceptions in multi-threading mode)
+ *  - output->pos must be <= dstCapacity, input->pos must be <= srcSize
+ *  - output->pos and input->pos will be updated. They are guaranteed to remain below their respective limit.
+ *  - When nbWorkers==0 (default), function is blocking : it completes its job before returning to caller.
+ *  - When nbWorkers>=1, function is non-blocking : it just acquires a copy of input, and distributes jobs to internal worker threads, flush whatever is available,
+ *                                                  and then immediately returns, just indicating that there is some data remaining to be flushed.
+ *                                                  The function nonetheless guarantees forward progress : it will return only after it reads or write at least 1+ byte.
+ *  - Exception : if the first call requests a ZSTD_e_end directive and provides enough dstCapacity, the function delegates to ZSTD_compress2() which is always blocking.
+ *  - @return provides a minimum amount of data remaining to be flushed from internal buffers
+ *            or an error code, which can be tested using ZSTD_isError().
+ *            if @return != 0, flush is not fully completed, there is still some data left within internal buffers.
+ *            This is useful for ZSTD_e_flush, since in this case more flushes are necessary to empty all buffers.
+ *            For ZSTD_e_end, @return == 0 when internal buffers are fully flushed and frame is completed.
+ *  - after a ZSTD_e_end directive, if internal buffer is not fully flushed (@return != 0),
+ *            only ZSTD_e_end or ZSTD_e_flush operations are allowed.
+ *            Before starting a new compression job, or changing compression parameters,
+ *            it is required to fully flush internal buffers.
+ */
+ZSTDLIB_API size_t ZSTD_compressStream2( ZSTD_CCtx* cctx,
+                                         ZSTD_outBuffer* output,
+                                         ZSTD_inBuffer* input,
+                                         ZSTD_EndDirective endOp);
+
+ZSTDLIB_API size_t ZSTD_CStreamInSize(void);    /**< recommended size for input buffer */
+ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output buffer. Guarantee to successfully flush at least one complete compressed block in all circumstances. */
+
+/*******************************************************************************
+ * This is a legacy streaming API, and can be replaced by ZSTD_CCtx_reset() and
+ * ZSTD_compressStream2(). It is redundant, but is still fully supported.
+ * Advanced parameters and dictionary compression can only be used through the
+ * new API.
+ ******************************************************************************/
+
+/**
+ * Equivalent to:
+ *
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ */
+ZSTDLIB_API size_t ZSTD_initCStream(ZSTD_CStream* zcs, int compressionLevel);
+/**
+ * Alternative for ZSTD_compressStream2(zcs, output, input, ZSTD_e_continue).
+ * NOTE: The return value is different. ZSTD_compressStream() returns a hint for
+ * the next read size (if non-zero and not an error). ZSTD_compressStream2()
+ * returns the number of bytes left to flush (if non-zero and not an error).
+ */
+ZSTDLIB_API size_t ZSTD_compressStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_flush). */
+ZSTDLIB_API size_t ZSTD_flushStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+/** Equivalent to ZSTD_compressStream2(zcs, output, &emptyInput, ZSTD_e_end). */
+ZSTDLIB_API size_t ZSTD_endStream(ZSTD_CStream* zcs, ZSTD_outBuffer* output);
+
+
+/*-***************************************************************************
+*  Streaming decompression - HowTo
+*
+*  A ZSTD_DStream object is required to track streaming operations.
+*  Use ZSTD_createDStream() and ZSTD_freeDStream() to create/release resources.
+*  ZSTD_DStream objects can be re-used multiple times.
+*
+*  Use ZSTD_initDStream() to start a new decompression operation.
+* @return : recommended first input size
+*  Alternatively, use advanced API to set specific properties.
+*
+*  Use ZSTD_decompressStream() repetitively to consume your input.
+*  The function will update both `pos` fields.
+*  If `input.pos < input.size`, some input has not been consumed.
+*  It's up to the caller to present again remaining data.
+*  The function tries to flush all data decoded immediately, respecting output buffer size.
+*  If `output.pos < output.size`, decoder has flushed everything it could.
+*  But if `output.pos == output.size`, there might be some data left within internal buffers.,
+*  In which case, call ZSTD_decompressStream() again to flush whatever remains in the buffer.
+*  Note : with no additional input provided, amount of data flushed is necessarily <= ZSTD_BLOCKSIZE_MAX.
+* @return : 0 when a frame is completely decoded and fully flushed,
+*        or an error code, which can be tested using ZSTD_isError(),
+*        or any other value > 0, which means there is still some decoding or flushing to do to complete current frame :
+*                                the return value is a suggested next input size (just a hint for better latency)
+*                                that will never request more than the remaining frame size.
+* *******************************************************************************/
+
+typedef ZSTD_DCtx ZSTD_DStream;  /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
+                                 /* For compatibility with versions <= v1.2.0, prefer differentiating them. */
+/*===== ZSTD_DStream management functions =====*/
+ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
+ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
+
+/*===== Streaming decompression functions =====*/
+
+/* This function is redundant with the advanced API and equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds);
+ *     ZSTD_DCtx_refDDict(zds, NULL);
+ */
+ZSTDLIB_API size_t ZSTD_initDStream(ZSTD_DStream* zds);
+
+ZSTDLIB_API size_t ZSTD_decompressStream(ZSTD_DStream* zds, ZSTD_outBuffer* output, ZSTD_inBuffer* input);
+
+ZSTDLIB_API size_t ZSTD_DStreamInSize(void);    /*!< recommended size for input buffer */
+ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output buffer. Guarantee to successfully flush at least one complete block in all circumstances. */
+
+
+/**************************
+*  Simple dictionary API
+***************************/
+/*! ZSTD_compress_usingDict() :
+ *  Compression at an explicit compression level using a Dictionary.
+ *  A dictionary can be any arbitrary data segment (also called a prefix),
+ *  or a buffer with specified information (see dictBuilder/zdict.h).
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *         It's intended for a dictionary used only once.
+ *  Note 2 : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ZSTDLIB_API size_t ZSTD_compress_usingDict(ZSTD_CCtx* ctx,
+                                           void* dst, size_t dstCapacity,
+                                     const void* src, size_t srcSize,
+                                     const void* dict,size_t dictSize,
+                                           int compressionLevel);
+
+/*! ZSTD_decompress_usingDict() :
+ *  Decompression using a known Dictionary.
+ *  Dictionary must be identical to the one used during compression.
+ *  Note : This function loads the dictionary, resulting in significant startup delay.
+ *         It's intended for a dictionary used only once.
+ *  Note : When `dict == NULL || dictSize < 8` no dictionary is used. */
+ZSTDLIB_API size_t ZSTD_decompress_usingDict(ZSTD_DCtx* dctx,
+                                             void* dst, size_t dstCapacity,
+                                       const void* src, size_t srcSize,
+                                       const void* dict,size_t dictSize);
+
+
+/***********************************
+ *  Bulk processing dictionary API
+ **********************************/
+typedef struct ZSTD_CDict_s ZSTD_CDict;
+
+/*! ZSTD_createCDict() :
+ *  When compressing multiple messages / blocks using the same dictionary, it's recommended to load it only once.
+ *  ZSTD_createCDict() will create a digested dictionary, ready to start future compression operations without startup cost.
+ *  ZSTD_CDict can be created once and shared by multiple threads concurrently, since its usage is read-only.
+ * `dictBuffer` can be released after ZSTD_CDict creation, because its content is copied within CDict.
+ *  Consider experimental function `ZSTD_createCDict_byReference()` if you prefer to not duplicate `dictBuffer` content.
+ *  Note : A ZSTD_CDict can be created from an empty dictBuffer, but it is inefficient when used to compress small data. */
+ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict(const void* dictBuffer, size_t dictSize,
+                                         int compressionLevel);
+
+/*! ZSTD_freeCDict() :
+ *  Function frees memory allocated by ZSTD_createCDict(). */
+ZSTDLIB_API size_t      ZSTD_freeCDict(ZSTD_CDict* CDict);
+
+/*! ZSTD_compress_usingCDict() :
+ *  Compression using a digested Dictionary.
+ *  Recommended when same dictionary is used multiple times.
+ *  Note : compression level is _decided at dictionary creation time_,
+ *     and frame parameters are hardcoded (dictID=yes, contentSize=yes, checksum=no) */
+ZSTDLIB_API size_t ZSTD_compress_usingCDict(ZSTD_CCtx* cctx,
+                                            void* dst, size_t dstCapacity,
+                                      const void* src, size_t srcSize,
+                                      const ZSTD_CDict* cdict);
+
+
+typedef struct ZSTD_DDict_s ZSTD_DDict;
+
+/*! ZSTD_createDDict() :
+ *  Create a digested dictionary, ready to start decompression operation without startup delay.
+ *  dictBuffer can be released after DDict creation, as its content is copied inside DDict. */
+ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict(const void* dictBuffer, size_t dictSize);
+
+/*! ZSTD_freeDDict() :
+ *  Function frees memory allocated with ZSTD_createDDict() */
+ZSTDLIB_API size_t      ZSTD_freeDDict(ZSTD_DDict* ddict);
+
+/*! ZSTD_decompress_usingDDict() :
+ *  Decompression using a digested Dictionary.
+ *  Recommended when same dictionary is used multiple times. */
+ZSTDLIB_API size_t ZSTD_decompress_usingDDict(ZSTD_DCtx* dctx,
+                                              void* dst, size_t dstCapacity,
+                                        const void* src, size_t srcSize,
+                                        const ZSTD_DDict* ddict);
+
+
+/********************************
+ *  Dictionary helper functions
+ *******************************/
+
+/*! ZSTD_getDictID_fromDict() :
+ *  Provides the dictID stored within dictionary.
+ *  if @return == 0, the dictionary is not conformant with Zstandard specification.
+ *  It can still be loaded, but as a content-only dictionary. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
+
+/*! ZSTD_getDictID_fromDDict() :
+ *  Provides the dictID of the dictionary loaded into `ddict`.
+ *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
+ *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
+
+/*! ZSTD_getDictID_fromFrame() :
+ *  Provides the dictID required to decompressed the frame stored within `src`.
+ *  If @return == 0, the dictID could not be decoded.
+ *  This could for one of the following reasons :
+ *  - The frame does not require a dictionary to be decoded (most common case).
+ *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
+ *    Note : this use case also happens when using a non-conformant dictionary.
+ *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
+ *  - This is not a Zstandard frame.
+ *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
+ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
+
+
+/*******************************************************************************
+ * Advanced dictionary and prefix API
+ *
+ * This API allows dictionaries to be used with ZSTD_compress2(),
+ * ZSTD_compressStream2(), and ZSTD_decompress(). Dictionaries are sticky, and
+ * only reset with the context is reset with ZSTD_reset_parameters or
+ * ZSTD_reset_session_and_parameters. Prefixes are single-use.
+ ******************************************************************************/
+
+
+/*! ZSTD_CCtx_loadDictionary() :
+ *  Create an internal CDict from `dict` buffer.
+ *  Decompression will have to use same dictionary.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special: Loading a NULL (or 0-size) dictionary invalidates previous dictionary,
+ *           meaning "return to no-dictionary mode".
+ *  Note 1 : Dictionary is sticky, it will be used for all future compressed frames.
+ *           To return to "no-dictionary" situation, load a NULL dictionary (or reset parameters).
+ *  Note 2 : Loading a dictionary involves building tables.
+ *           It's also a CPU consuming operation, with non-negligible impact on latency.
+ *           Tables are dependent on compression parameters, and for this reason,
+ *           compression parameters can no longer be changed after loading a dictionary.
+ *  Note 3 :`dict` content will be copied internally.
+ *           Use experimental ZSTD_CCtx_loadDictionary_byReference() to reference content instead.
+ *           In such a case, dictionary buffer must outlive its users.
+ *  Note 4 : Use ZSTD_CCtx_loadDictionary_advanced()
+ *           to precisely select how dictionary content must be interpreted. */
+ZSTDLIB_API size_t ZSTD_CCtx_loadDictionary(ZSTD_CCtx* cctx, const void* dict, size_t dictSize);
+
+/*! ZSTD_CCtx_refCDict() :
+ *  Reference a prepared dictionary, to be used for all next compressed frames.
+ *  Note that compression parameters are enforced from within CDict,
+ *  and supersede any compression parameter previously set within CCtx.
+ *  The parameters ignored are labled as "superseded-by-cdict" in the ZSTD_cParameter enum docs.
+ *  The ignored parameters will be used again if the CCtx is returned to no-dictionary mode.
+ *  The dictionary will remain valid for future compressed frames using same CCtx.
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special : Referencing a NULL CDict means "return to no-dictionary mode".
+ *  Note 1 : Currently, only one dictionary can be managed.
+ *           Referencing a new dictionary effectively "discards" any previous one.
+ *  Note 2 : CDict is just referenced, its lifetime must outlive its usage within CCtx. */
+ZSTDLIB_API size_t ZSTD_CCtx_refCDict(ZSTD_CCtx* cctx, const ZSTD_CDict* cdict);
+
+/*! ZSTD_CCtx_refPrefix() :
+ *  Reference a prefix (single-usage dictionary) for next compressed frame.
+ *  A prefix is **only used once**. Tables are discarded at end of frame (ZSTD_e_end).
+ *  Decompression will need same prefix to properly regenerate data.
+ *  Compressing with a prefix is similar in outcome as performing a diff and compressing it,
+ *  but performs much faster, especially during decompression (compression speed is tunable with compression level).
+ * @result : 0, or an error code (which can be tested with ZSTD_isError()).
+ *  Special: Adding any prefix (including NULL) invalidates any previous prefix or dictionary
+ *  Note 1 : Prefix buffer is referenced. It **must** outlive compression.
+ *           Its content must remain unmodified during compression.
+ *  Note 2 : If the intention is to diff some large src data blob with some prior version of itself,
+ *           ensure that the window size is large enough to contain the entire source.
+ *           See ZSTD_c_windowLog.
+ *  Note 3 : Referencing a prefix involves building tables, which are dependent on compression parameters.
+ *           It's a CPU consuming operation, with non-negligible impact on latency.
+ *           If there is a need to use the same prefix multiple times, consider loadDictionary instead.
+ *  Note 4 : By default, the prefix is interpreted as raw content (ZSTD_dm_rawContent).
+ *           Use experimental ZSTD_CCtx_refPrefix_advanced() to alter dictionary interpretation. */
+ZSTDLIB_API size_t ZSTD_CCtx_refPrefix(ZSTD_CCtx* cctx,
+                                 const void* prefix, size_t prefixSize);
 
 /*! ZSTD_DCtx_loadDictionary() :
  *  Create an internal DDict from dict buffer,
@@ -910,15 +954,32 @@ ZSTDLIB_API size_t ZSTD_DCtx_refDDict(ZSTD_DCtx* dctx, const ZSTD_DDict* ddict);
 ZSTDLIB_API size_t ZSTD_DCtx_refPrefix(ZSTD_DCtx* dctx,
                                  const void* prefix, size_t prefixSize);
 
-/*! ZSTD_DCtx_reset() :
- *  Return a DCtx to clean state.
- *  Session and parameters can be reset jointly or separately.
- *  Parameters can only be reset when no active frame is being decompressed.
- * @return : 0, or an error code, which can be tested with ZSTD_isError()
- */
-ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
+/* ===   Memory management   === */
+
+/*! ZSTD_sizeof_*() :
+ *  These functions give the _current_ memory usage of selected object.
+ *  Note that object memory usage can evolve (increase or decrease) over time. */
+ZSTDLIB_API size_t ZSTD_sizeof_CCtx(const ZSTD_CCtx* cctx);
+ZSTDLIB_API size_t ZSTD_sizeof_DCtx(const ZSTD_DCtx* dctx);
+ZSTDLIB_API size_t ZSTD_sizeof_CStream(const ZSTD_CStream* zcs);
+ZSTDLIB_API size_t ZSTD_sizeof_DStream(const ZSTD_DStream* zds);
+ZSTDLIB_API size_t ZSTD_sizeof_CDict(const ZSTD_CDict* cdict);
+ZSTDLIB_API size_t ZSTD_sizeof_DDict(const ZSTD_DDict* ddict);
+
+#endif  /* ZSTD_H_235446 */
+
 
+/****************************************************************************************
+ *   ADVANCED AND EXPERIMENTAL FUNCTIONS
+ ****************************************************************************************
+ * The definitions in the following section are considered experimental.
+ * They are provided for advanced scenarios.
+ * They should never be used with a dynamic library, as prototypes may change in the future.
+ * Use them only in association with static linking.
+ * ***************************************************************************************/
 
+#if defined(ZSTD_STATIC_LINKING_ONLY) && !defined(ZSTD_H_ZSTD_STATIC_LINKING_ONLY)
+#define ZSTD_H_ZSTD_STATIC_LINKING_ONLY
 
 /****************************************************************************************
  *   experimental API (static linking only)
@@ -962,7 +1023,7 @@ ZSTDLIB_API size_t ZSTD_DCtx_reset(ZSTD_DCtx* dctx, ZSTD_ResetDirective reset);
 #define ZSTD_WINDOWLOG_LIMIT_DEFAULT 27   /* by default, the streaming decoder will refuse any frame
                                            * requiring larger than (1<<ZSTD_WINDOWLOG_LIMIT_DEFAULT) window size,
                                            * to preserve host's memory from unreasonable requirements.
-                                           * This limit can be overriden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,).
+                                           * This limit can be overridden using ZSTD_DCtx_setParameter(,ZSTD_d_windowLogMax,).
                                            * The limit does not apply for one-pass decoders (such as ZSTD_decompress()), since no additional memory is allocated */
 
 
@@ -1064,15 +1125,24 @@ typedef enum {
     ZSTD_dictForceCopy     = 2, /* Always copy the dictionary. */
 } ZSTD_dictAttachPref_e;
 
+typedef enum {
+  ZSTD_lcm_auto = 0,          /**< Automatically determine the compression mode based on the compression level.
+                               *   Negative compression levels will be uncompressed, and positive compression
+                               *   levels will be compressed. */
+  ZSTD_lcm_huffman = 1,       /**< Always attempt Huffman compression. Uncompressed literals will still be
+                               *   emitted if Huffman compression is not profitable. */
+  ZSTD_lcm_uncompressed = 2,  /**< Always emit uncompressed literals. */
+} ZSTD_literalCompressionMode_e;
+
 
 /***************************************
 *  Frame size functions
 ***************************************/
 
 /*! ZSTD_findDecompressedSize() :
- *  `src` should point the start of a series of ZSTD encoded and/or skippable frames
+ *  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
  *  `srcSize` must be the _exact_ size of this series
- *       (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`)
+ *       (i.e. there should be a frame boundary at `src + srcSize`)
  *  @return : - decompressed size of all data in all successive frames
  *            - if the decompressed size cannot be determined: ZSTD_CONTENTSIZE_UNKNOWN
  *            - if an error occurred: ZSTD_CONTENTSIZE_ERROR
@@ -1092,6 +1162,21 @@ typedef enum {
  *            however it does mean that all frame data must be present and valid. */
 ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t srcSize);
 
+/** ZSTD_decompressBound() :
+ *  `src` should point to the start of a series of ZSTD encoded and/or skippable frames
+ *  `srcSize` must be the _exact_ size of this series
+ *       (i.e. there should be a frame boundary at `src + srcSize`)
+ *  @return : - upper-bound for the decompressed size of all data in all successive frames
+ *            - if an error occured: ZSTD_CONTENTSIZE_ERROR
+ *
+ *  note 1  : an error can occur if `src` contains an invalid or incorrectly formatted frame.
+ *  note 2  : the upper-bound is exact when the decompressed size field is available in every ZSTD encoded frame of `src`.
+ *            in this case, `ZSTD_findDecompressedSize` and `ZSTD_decompressBound` return the same value.
+ *  note 3  : when the decompressed size field isn't available, the upper-bound for that frame is calculated by:
+ *              upper-bound = # blocks * min(128 KB, Window_Size)
+ */
+ZSTDLIB_API unsigned long long ZSTD_decompressBound(const void* src, size_t srcSize);
+
 /*! ZSTD_frameHeaderSize() :
  *  srcSize must be >= ZSTD_FRAMEHEADERSIZE_PREFIX.
  * @return : size of the Frame Header,
@@ -1110,7 +1195,7 @@ ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
  *  It will also consider src size to be arbitrarily "large", which is worst case.
  *  If srcSize is known to always be small, ZSTD_estimateCCtxSize_usingCParams() can provide a tighter estimation.
  *  ZSTD_estimateCCtxSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
- *  ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+ *  ZSTD_estimateCCtxSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
  *  Note : CCtx size estimation is only correct for single-threaded compression. */
 ZSTDLIB_API size_t ZSTD_estimateCCtxSize(int compressionLevel);
 ZSTDLIB_API size_t ZSTD_estimateCCtxSize_usingCParams(ZSTD_compressionParameters cParams);
@@ -1122,7 +1207,7 @@ ZSTDLIB_API size_t ZSTD_estimateDCtxSize(void);
  *  It will also consider src size to be arbitrarily "large", which is worst case.
  *  If srcSize is known to always be small, ZSTD_estimateCStreamSize_usingCParams() can provide a tighter estimation.
  *  ZSTD_estimateCStreamSize_usingCParams() can be used in tandem with ZSTD_getCParams() to create cParams from compressionLevel.
- *  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParam_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
+ *  ZSTD_estimateCStreamSize_usingCCtxParams() can be used in tandem with ZSTD_CCtxParams_setParameter(). Only single-threaded compression is supported. This function will return an error code if ZSTD_c_nbWorkers is >= 1.
  *  Note : CStream size estimation is only correct for single-threaded compression.
  *  ZSTD_DStream memory budget depends on window Size.
  *  This information can be passed manually, using ZSTD_estimateDStreamSize,
@@ -1226,22 +1311,26 @@ ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_advanced(const void* dict, size_t dictS
 ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);
 
 /*! ZSTD_getCParams() :
-*   @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
-*   `estimatedSrcSize` value is optional, select 0 if not known */
+ * @return ZSTD_compressionParameters structure for a selected compression level and estimated srcSize.
+ * `estimatedSrcSize` value is optional, select 0 if not known */
 ZSTDLIB_API ZSTD_compressionParameters ZSTD_getCParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
 
 /*! ZSTD_getParams() :
-*   same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
-*   All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */
+ *  same as ZSTD_getCParams(), but @return a full `ZSTD_parameters` object instead of sub-component `ZSTD_compressionParameters`.
+ *  All fields of `ZSTD_frameParameters` are set to default : contentSize=1, checksum=0, noDictID=0 */
 ZSTDLIB_API ZSTD_parameters ZSTD_getParams(int compressionLevel, unsigned long long estimatedSrcSize, size_t dictSize);
 
 /*! ZSTD_checkCParams() :
-*   Ensure param values remain within authorized range */
+ *  Ensure param values remain within authorized range.
+ * @return 0 on success, or an error code (can be checked with ZSTD_isError()) */
 ZSTDLIB_API size_t ZSTD_checkCParams(ZSTD_compressionParameters params);
 
 /*! ZSTD_adjustCParams() :
  *  optimize params for a given `srcSize` and `dictSize`.
- *  both values are optional, select `0` if unknown. */
+ * `srcSize` can be unknown, in which case use ZSTD_CONTENTSIZE_UNKNOWN.
+ * `dictSize` must be `0` when there is no dictionary.
+ *  cPar can be invalid : all parameters will be clamped within valid range in the @return struct.
+ *  This function never fails (wide contract) */
 ZSTDLIB_API ZSTD_compressionParameters ZSTD_adjustCParams(ZSTD_compressionParameters cPar, unsigned long long srcSize, size_t dictSize);
 
 /*! ZSTD_compress_advanced() :
@@ -1314,6 +1403,12 @@ ZSTDLIB_API size_t ZSTD_CCtx_refPrefix_advanced(ZSTD_CCtx* cctx, const void* pre
  * See the comments on that enum for an explanation of the feature. */
 #define ZSTD_c_forceAttachDict ZSTD_c_experimentalParam4
 
+/* Controls how the literals are compressed (default is auto).
+ * The value must be of type ZSTD_literalCompressionMode_e.
+ * See ZSTD_literalCompressionMode_t enum definition for details.
+ */
+#define ZSTD_c_literalCompressionMode ZSTD_c_experimentalParam5
+
 /*! ZSTD_CCtx_getParameter() :
  *  Get the requested compression parameter value, selected by enum ZSTD_cParameter,
  *  and store it into int* value.
@@ -1325,10 +1420,10 @@ ZSTDLIB_API size_t ZSTD_CCtx_getParameter(ZSTD_CCtx* cctx, ZSTD_cParameter param
 /*! ZSTD_CCtx_params :
  *  Quick howto :
  *  - ZSTD_createCCtxParams() : Create a ZSTD_CCtx_params structure
- *  - ZSTD_CCtxParam_setParameter() : Push parameters one by one into
- *                                    an existing ZSTD_CCtx_params structure.
- *                                    This is similar to
- *                                    ZSTD_CCtx_setParameter().
+ *  - ZSTD_CCtxParams_setParameter() : Push parameters one by one into
+ *                                     an existing ZSTD_CCtx_params structure.
+ *                                     This is similar to
+ *                                     ZSTD_CCtx_setParameter().
  *  - ZSTD_CCtx_setParametersUsingCCtxParams() : Apply parameters to
  *                                    an existing CCtx.
  *                                    These parameters will be applied to
@@ -1359,20 +1454,20 @@ ZSTDLIB_API size_t ZSTD_CCtxParams_init(ZSTD_CCtx_params* cctxParams, int compre
  */
 ZSTDLIB_API size_t ZSTD_CCtxParams_init_advanced(ZSTD_CCtx_params* cctxParams, ZSTD_parameters params);
 
-/*! ZSTD_CCtxParam_setParameter() :
+/*! ZSTD_CCtxParams_setParameter() :
  *  Similar to ZSTD_CCtx_setParameter.
  *  Set one compression parameter, selected by enum ZSTD_cParameter.
  *  Parameters must be applied to a ZSTD_CCtx using ZSTD_CCtx_setParametersUsingCCtxParams().
  * @result : 0, or an error code (which can be tested with ZSTD_isError()).
  */
-ZSTDLIB_API size_t ZSTD_CCtxParam_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);
+ZSTDLIB_API size_t ZSTD_CCtxParams_setParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int value);
 
-/*! ZSTD_CCtxParam_getParameter() :
+/*! ZSTD_CCtxParams_getParameter() :
  * Similar to ZSTD_CCtx_getParameter.
  * Get the requested value of one compression parameter, selected by enum ZSTD_cParameter.
  * @result : 0, or an error code (which can be tested with ZSTD_isError()).
  */
-ZSTDLIB_API size_t ZSTD_CCtxParam_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);
+ZSTDLIB_API size_t ZSTD_CCtxParams_getParameter(ZSTD_CCtx_params* params, ZSTD_cParameter param, int* value);
 
 /*! ZSTD_CCtx_setParametersUsingCCtxParams() :
  *  Apply a set of ZSTD_CCtx_params to the compression context.
@@ -1415,31 +1510,6 @@ ZSTDLIB_API unsigned ZSTD_isFrame(const void* buffer, size_t size);
  *  it must remain read accessible throughout the lifetime of DDict */
 ZSTDLIB_API ZSTD_DDict* ZSTD_createDDict_byReference(const void* dictBuffer, size_t dictSize);
 
-
-/*! ZSTD_getDictID_fromDict() :
- *  Provides the dictID stored within dictionary.
- *  if @return == 0, the dictionary is not conformant with Zstandard specification.
- *  It can still be loaded, but as a content-only dictionary. */
-ZSTDLIB_API unsigned ZSTD_getDictID_fromDict(const void* dict, size_t dictSize);
-
-/*! ZSTD_getDictID_fromDDict() :
- *  Provides the dictID of the dictionary loaded into `ddict`.
- *  If @return == 0, the dictionary is not conformant to Zstandard specification, or empty.
- *  Non-conformant dictionaries can still be loaded, but as content-only dictionaries. */
-ZSTDLIB_API unsigned ZSTD_getDictID_fromDDict(const ZSTD_DDict* ddict);
-
-/*! ZSTD_getDictID_fromFrame() :
- *  Provides the dictID required to decompressed the frame stored within `src`.
- *  If @return == 0, the dictID could not be decoded.
- *  This could for one of the following reasons :
- *  - The frame does not require a dictionary to be decoded (most common case).
- *  - The frame was built with dictID intentionally removed. Whatever dictionary is necessary is a hidden information.
- *    Note : this use case also happens when using a non-conformant dictionary.
- *  - `srcSize` is too small, and as a result, the frame header could not be decoded (only possible if `srcSize < ZSTD_FRAMEHEADERSIZE_MAX`).
- *  - This is not a Zstandard frame.
- *  When identifying the exact failure cause, it's possible to use ZSTD_getFrameHeader(), which will provide a more precise error code. */
-ZSTDLIB_API unsigned ZSTD_getDictID_fromFrame(const void* src, size_t srcSize);
-
 /*! ZSTD_DCtx_loadDictionary_byReference() :
  *  Same as ZSTD_DCtx_loadDictionary(),
  *  but references `dict` content instead of copying it into `dctx`.
@@ -1501,14 +1571,68 @@ ZSTDLIB_API size_t ZSTD_decompressStream_simpleArgs (
 ********************************************************************/
 
 /*=====   Advanced Streaming compression functions  =====*/
-ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);   /**< pledgedSrcSize must be correct. If it is not known at init time, use ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs, "0" also disables frame content size field. It may be enabled in the future. */
-ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel); /**< creates of an internal CDict (incompatible with static CCtx), except if dict == NULL or dictSize < 8, in which case no dict is used. Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.*/
+/**! ZSTD_initCStream_srcSize() :
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, NULL); // clear the dictionary (if any)
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
+ * pledgedSrcSize must be correct. If it is not known at init time, use
+ * ZSTD_CONTENTSIZE_UNKNOWN. Note that, for compatibility with older programs,
+ * "0" also disables frame content size field. It may be enabled in the future.
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_srcSize(ZSTD_CStream* zcs, int compressionLevel, unsigned long long pledgedSrcSize);
+/**! ZSTD_initCStream_usingDict() :
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setParameter(zcs, ZSTD_c_compressionLevel, compressionLevel);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * Creates of an internal CDict (incompatible with static CCtx), except if
+ * dict == NULL or dictSize < 8, in which case no dict is used.
+ * Note: dict is loaded with ZSTD_dm_auto (treated as a full zstd dictionary if
+ * it begins with ZSTD_MAGIC_DICTIONARY, else as raw content) and ZSTD_dlm_byCopy.
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingDict(ZSTD_CStream* zcs, const void* dict, size_t dictSize, int compressionLevel);
+/**! ZSTD_initCStream_advanced() :
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setZstdParams(zcs, params); // Set the zstd params and leave the rest as-is
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_loadDictionary(zcs, dict, dictSize);
+ *
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy.
+ */
 ZSTDLIB_API size_t ZSTD_initCStream_advanced(ZSTD_CStream* zcs, const void* dict, size_t dictSize,
-                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);  /**< pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. dict is loaded with ZSTD_dm_auto and ZSTD_dlm_byCopy. */
-ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);  /**< note : cdict will just be referenced, and must outlive compression session */
-ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);  /**< same as ZSTD_initCStream_usingCDict(), with control over frame parameters. pledgedSrcSize must be correct. If srcSize is not known at init time, use value ZSTD_CONTENTSIZE_UNKNOWN. */
+                                             ZSTD_parameters params, unsigned long long pledgedSrcSize);
+/**! ZSTD_initCStream_usingCDict() :
+ * This function is deprecated, and equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * note : cdict will just be referenced, and must outlive compression session
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict(ZSTD_CStream* zcs, const ZSTD_CDict* cdict);
+/**! ZSTD_initCStream_usingCDict_advanced() :
+ * This function is deprecated, and is approximately equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setZstdFrameParams(zcs, fParams); // Set the zstd frame params and leave the rest as-is
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *     ZSTD_CCtx_refCDict(zcs, cdict);
+ *
+ * same as ZSTD_initCStream_usingCDict(), with control over frame parameters.
+ * pledgedSrcSize must be correct. If srcSize is not known at init time, use
+ * value ZSTD_CONTENTSIZE_UNKNOWN.
+ */
+ZSTDLIB_API size_t ZSTD_initCStream_usingCDict_advanced(ZSTD_CStream* zcs, const ZSTD_CDict* cdict, ZSTD_frameParameters fParams, unsigned long long pledgedSrcSize);
 
 /*! ZSTD_resetCStream() :
+ * This function is deprecated, and is equivalent to:
+ *     ZSTD_CCtx_reset(zcs, ZSTD_reset_session_only);
+ *     ZSTD_CCtx_setPledgedSrcSize(zcs, pledgedSrcSize);
+ *
  *  start a new frame, using same parameters from previous frame.
  *  This is typically useful to skip dictionary loading stage, since it will re-use it in-place.
  *  Note that zcs must be init at least once before using ZSTD_resetCStream().
@@ -1555,9 +1679,32 @@ ZSTDLIB_API size_t ZSTD_toFlushNow(ZSTD_CCtx* cctx);
 
 
 /*=====   Advanced Streaming decompression functions  =====*/
-ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize); /**< note: no dictionary will be used if dict == NULL or dictSize < 8 */
-ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);  /**< note : ddict is referenced, it must outlive decompression session */
-ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);  /**< re-use decompression parameters from previous init; saves dictionary loading */
+/**
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_loadDictionary(zds, dict, dictSize);
+ *
+ * note: no dictionary will be used if dict == NULL or dictSize < 8
+ */
+ZSTDLIB_API size_t ZSTD_initDStream_usingDict(ZSTD_DStream* zds, const void* dict, size_t dictSize);
+/**
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *     ZSTD_DCtx_refDDict(zds, ddict);
+ *
+ * note : ddict is referenced, it must outlive decompression session
+ */
+ZSTDLIB_API size_t ZSTD_initDStream_usingDDict(ZSTD_DStream* zds, const ZSTD_DDict* ddict);
+/**
+ * This function is deprecated, and is equivalent to:
+ *
+ *     ZSTD_DCtx_reset(zds, ZSTD_reset_session_only);
+ *
+ * re-use decompression parameters from previous init; saves dictionary loading
+ */
+ZSTDLIB_API size_t ZSTD_resetDStream(ZSTD_DStream* zds);
 
 
 /*********************************************************************