Merge branch 'dev' into fullbench

lib/common/huf.h

@@ -111,6 +111,18 @@ HUF_PUBLIC_API size_t HUF_compress2 (void* dst, size_t dstCapacity, const void*
 #define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
 HUF_PUBLIC_API size_t HUF_compress4X_wksp (void* dst, size_t dstCapacity, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);
 
+/**
+ *  The minimum workspace size for the `workSpace` used in
+ *  HUF_readDTableX2_wksp() and HUF_readDTableX4_wksp().
+ *
+ *  The space used depends on HUF_TABLELOG_MAX, ranging from ~1500 bytes when
+ *  HUF_TABLE_LOG_MAX=12 to ~1850 bytes when HUF_TABLE_LOG_MAX=15.
+ *  Buffer overflow errors may potentially occur if code modifications result in
+ *  a required workspace size greater than that specified in the following
+ *  macro.
+ */
+#define HUF_DECOMPRESS_WORKSPACE_SIZE (2 << 10)
+#define HUF_DECOMPRESS_WORKSPACE_SIZE_U32 (HUF_DECOMPRESS_WORKSPACE_SIZE / sizeof(U32))
 
 
 /* ******************************************************************
@@ -170,8 +182,11 @@ size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cS
 
 size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< decodes RLE and uncompressed */
 size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize); /**< considers RLE and uncompressed as errors */
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize); /**< considers RLE and uncompressed as errors */
 size_t HUF_decompress4X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< single-symbol decoder */
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< single-symbol decoder */
 size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< double-symbols decoder */
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< double-symbols decoder */
 
 
 /* ****************************************
@@ -243,7 +258,9 @@ HUF_decompress() does the following:
 U32 HUF_selectDecoder (size_t dstSize, size_t cSrcSize);
 
 size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX2_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
 size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize);
+size_t HUF_readDTableX4_wksp (HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize);
 
 size_t HUF_decompress4X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
 size_t HUF_decompress4X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);
@@ -266,8 +283,11 @@ size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cS
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */
 
 size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);
+size_t HUF_decompress1X_DCtx_wksp (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);
 size_t HUF_decompress1X2_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< single-symbol decoder */
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< single-symbol decoder */
 size_t HUF_decompress1X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /**< double-symbols decoder */
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize, void* workSpace, size_t wkspSize);   /**< double-symbols decoder */
 
 size_t HUF_decompress1X_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);   /**< automatic selection of sing or double symbol decoder, based on DTable */
 size_t HUF_decompress1X2_usingDTable(void* dst, size_t maxDstSize, const void* cSrc, size_t cSrcSize, const HUF_DTable* DTable);

lib/decompress/huf_decompress.c

@@ -67,6 +67,12 @@
 #define HUF_STATIC_ASSERT(c) { enum { HUF_static_assert = 1/(int)(!!(c)) }; }   /* use only *after* variable declarations */
 
 
+/* **************************************************************
+*  Byte alignment for workSpace management
+****************************************************************/
+#define HUF_ALIGN(x, a) HUF_ALIGN_MASK((x), (a) - 1)
+#define HUF_ALIGN_MASK(x, mask) (((x) + (mask)) & ~(mask))
+
 /*-***************************/
 /*  generic DTableDesc       */
 /*-***************************/
@@ -87,16 +93,28 @@ static DTableDesc HUF_getDTableDesc(const HUF_DTable* table)
 
 typedef struct { BYTE byte; BYTE nbBits; } HUF_DEltX2;   /* single-symbol decoding */
 
-size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX2_wksp(HUF_DTable* DTable, const void* src, size_t srcSize, void* workSpace, size_t wkspSize)
 {
-    BYTE huffWeight[HUF_SYMBOLVALUE_MAX + 1];
-    U32 rankVal[HUF_TABLELOG_ABSOLUTEMAX + 1];   /* large enough for values from 0 to 16 */
     U32 tableLog = 0;
     U32 nbSymbols = 0;
     size_t iSize;
     void* const dtPtr = DTable + 1;
     HUF_DEltX2* const dt = (HUF_DEltX2*)dtPtr;
 
+    U32* rankVal;
+    BYTE* huffWeight;
+    size_t spaceUsed32 = 0;
+
+    rankVal = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_ABSOLUTEMAX + 1;
+    huffWeight = (BYTE *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+    if ((spaceUsed32 << 2) > wkspSize)
+        return ERROR(tableLog_tooLarge);
+    workSpace = (U32 *)workSpace + spaceUsed32;
+    wkspSize -= (spaceUsed32 << 2);
+
     HUF_STATIC_ASSERT(sizeof(DTableDesc) == sizeof(HUF_DTable));
     /* memset(huffWeight, 0, sizeof(huffWeight)); */   /* is not necessary, even though some analyzer complain ... */
 
@@ -135,6 +153,13 @@ size_t HUF_readDTableX2 (HUF_DTable* DTable, const void* src, size_t srcSize)
     return iSize;
 }
 
+size_t HUF_readDTableX2(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_readDTableX2_wksp(DTable, src, srcSize,
+                                 workSpace, sizeof(workSpace));
+}
+
 
 static BYTE HUF_decodeSymbolX2(BIT_DStream_t* Dstream, const HUF_DEltX2* dt, const U32 dtLog)
 {
@@ -212,11 +237,13 @@ size_t HUF_decompress1X2_usingDTable(
     return HUF_decompress1X2_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
 }
 
-size_t HUF_decompress1X2_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X2_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t const hSize = HUF_readDTableX2 (DCtx, cSrc, cSrcSize);
+    size_t const hSize = HUF_readDTableX2_wksp(DCtx, cSrc, cSrcSize, workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -224,6 +251,15 @@ size_t HUF_decompress1X2_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, cons
     return HUF_decompress1X2_usingDTable_internal (dst, dstSize, ip, cSrcSize, DCtx);
 }
 
+
+size_t HUF_decompress1X2_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X2_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
@@ -335,11 +371,14 @@ size_t HUF_decompress4X2_usingDTable(
 }
 
 
-size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X2_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t const hSize = HUF_readDTableX2 (dctx, cSrc, cSrcSize);
+    size_t const hSize = HUF_readDTableX2_wksp (dctx, cSrc, cSrcSize,
+                                                workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -347,6 +386,13 @@ size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, cons
     return HUF_decompress4X2_usingDTable_internal (dst, dstSize, ip, cSrcSize, dctx);
 }
 
+
+size_t HUF_decompress4X2_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
 size_t HUF_decompress4X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX2(DTable, HUF_TABLELOG_MAX);
@@ -403,7 +449,8 @@ static void HUF_fillDTableX4Level2(HUF_DEltX4* DTable, U32 sizeLog, const U32 co
     }   }
 }
 
-typedef U32 rankVal_t[HUF_TABLELOG_MAX][HUF_TABLELOG_MAX + 1];
+typedef U32 rankValCol_t[HUF_TABLELOG_MAX + 1];
+typedef rankValCol_t rankVal_t[HUF_TABLELOG_MAX];
 
 static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
                            const sortedSymbol_t* sortedList, const U32 sortedListSize,
@@ -447,20 +494,43 @@ static void HUF_fillDTableX4(HUF_DEltX4* DTable, const U32 targetLog,
     }
 }
 
-size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize)
+size_t HUF_readDTableX4_wksp(HUF_DTable* DTable, const void* src,
+                             size_t srcSize, void* workSpace,
+                             size_t wkspSize)
 {
-    BYTE weightList[HUF_SYMBOLVALUE_MAX + 1];
-    sortedSymbol_t sortedSymbol[HUF_SYMBOLVALUE_MAX + 1];
-    U32 rankStats[HUF_TABLELOG_MAX + 1] = { 0 };
-    U32 rankStart0[HUF_TABLELOG_MAX + 2] = { 0 };
-    U32* const rankStart = rankStart0+1;
-    rankVal_t rankVal;
     U32 tableLog, maxW, sizeOfSort, nbSymbols;
     DTableDesc dtd = HUF_getDTableDesc(DTable);
     U32 const maxTableLog = dtd.maxTableLog;
     size_t iSize;
     void* dtPtr = DTable+1;   /* force compiler to avoid strict-aliasing */
     HUF_DEltX4* const dt = (HUF_DEltX4*)dtPtr;
+    U32 *rankStart;
+
+    rankValCol_t* rankVal;
+    U32* rankStats;
+    U32* rankStart0;
+    sortedSymbol_t* sortedSymbol;
+    BYTE* weightList;
+    size_t spaceUsed32 = 0;
+
+    rankVal = (rankValCol_t *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += (sizeof(rankValCol_t) * HUF_TABLELOG_MAX) >> 2;
+    rankStats = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_MAX + 1;
+    rankStart0 = (U32 *)workSpace + spaceUsed32;
+    spaceUsed32 += HUF_TABLELOG_MAX + 2;
+    sortedSymbol = (sortedSymbol_t *)workSpace + (spaceUsed32 * sizeof(U32)) / sizeof(sortedSymbol_t);
+    spaceUsed32 += HUF_ALIGN(sizeof(sortedSymbol_t) * (HUF_SYMBOLVALUE_MAX + 1), sizeof(U32)) >> 2;
+    weightList = (BYTE *)((U32 *)workSpace + spaceUsed32);
+    spaceUsed32 += HUF_ALIGN(HUF_SYMBOLVALUE_MAX + 1, sizeof(U32)) >> 2;
+
+    if ((spaceUsed32 << 2) > wkspSize)
+        return ERROR(tableLog_tooLarge);
+    workSpace = (U32 *)workSpace + spaceUsed32;
+    wkspSize -= (spaceUsed32 << 2);
+
+    rankStart = rankStart0 + 1;
+    memset(rankStats, 0, sizeof(U32) * (2 * HUF_TABLELOG_MAX + 2 + 1));
 
     HUF_STATIC_ASSERT(sizeof(HUF_DEltX4) == sizeof(HUF_DTable));   /* if compiler fails here, assertion is wrong */
     if (maxTableLog > HUF_TABLELOG_MAX) return ERROR(tableLog_tooLarge);
@@ -527,6 +597,12 @@ size_t HUF_readDTableX4 (HUF_DTable* DTable, const void* src, size_t srcSize)
     return iSize;
 }
 
+size_t HUF_readDTableX4(HUF_DTable* DTable, const void* src, size_t srcSize)
+{
+  U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+  return HUF_readDTableX4_wksp(DTable, src, srcSize,
+                               workSpace, sizeof(workSpace));
+}
 
 static U32 HUF_decodeSymbolX4(void* op, BIT_DStream_t* DStream, const HUF_DEltX4* dt, const U32 dtLog)
 {
@@ -627,11 +703,14 @@ size_t HUF_decompress1X4_usingDTable(
     return HUF_decompress1X4_usingDTable_internal(dst, dstSize, cSrc, cSrcSize, DTable);
 }
 
-size_t HUF_decompress1X4_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X4_DCtx_wksp(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t const hSize = HUF_readDTableX4 (DCtx, cSrc, cSrcSize);
+    size_t const hSize = HUF_readDTableX4_wksp(DCtx, cSrc, cSrcSize,
+                                               workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -639,6 +718,15 @@ size_t HUF_decompress1X4_DCtx (HUF_DTable* DCtx, void* dst, size_t dstSize, cons
     return HUF_decompress1X4_usingDTable_internal (dst, dstSize, ip, cSrcSize, DCtx);
 }
 
+
+size_t HUF_decompress1X4_DCtx(HUF_DTable* DCtx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X4_DCtx_wksp(DCtx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
@@ -749,11 +837,14 @@ size_t HUF_decompress4X4_usingDTable(
 }
 
 
-size_t HUF_decompress4X4_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X4_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                   const void* cSrc, size_t cSrcSize,
+                                   void* workSpace, size_t wkspSize)
 {
     const BYTE* ip = (const BYTE*) cSrc;
 
-    size_t hSize = HUF_readDTableX4 (dctx, cSrc, cSrcSize);
+    size_t hSize = HUF_readDTableX4_wksp(dctx, cSrc, cSrcSize,
+                                         workSpace, wkspSize);
     if (HUF_isError(hSize)) return hSize;
     if (hSize >= cSrcSize) return ERROR(srcSize_wrong);
     ip += hSize; cSrcSize -= hSize;
@@ -761,6 +852,15 @@ size_t HUF_decompress4X4_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, cons
     return HUF_decompress4X4_usingDTable_internal(dst, dstSize, ip, cSrcSize, dctx);
 }
 
+
+size_t HUF_decompress4X4_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+                              const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                       workSpace, sizeof(workSpace));
+}
+
 size_t HUF_decompress4X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
 {
     HUF_CREATE_STATIC_DTABLEX4(DTable, HUF_TABLELOG_MAX);
@@ -862,19 +962,32 @@ size_t HUF_decompress4X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
     }
 }
 
-size_t HUF_decompress4X_hufOnly (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress4X_hufOnly(HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress4X_hufOnly_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                         workSpace, sizeof(workSpace));
+}
+
+
+size_t HUF_decompress4X_hufOnly_wksp(HUF_DTable* dctx, void* dst,
+                                     size_t dstSize, const void* cSrc,
+                                     size_t cSrcSize, void* workSpace,
+                                     size_t wkspSize)
 {
     /* validation checks */
     if (dstSize == 0) return ERROR(dstSize_tooSmall);
     if ((cSrcSize >= dstSize) || (cSrcSize <= 1)) return ERROR(corruption_detected);   /* invalid */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress4X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
-                        HUF_decompress4X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+        return algoNb ? HUF_decompress4X4_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize):
+                        HUF_decompress4X2_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize, workSpace, wkspSize);
     }
 }
 
-size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize)
+size_t HUF_decompress1X_DCtx_wksp(HUF_DTable* dctx, void* dst, size_t dstSize,
+                                  const void* cSrc, size_t cSrcSize,
+                                  void* workSpace, size_t wkspSize)
 {
     /* validation checks */
     if (dstSize == 0) return ERROR(dstSize_tooSmall);
@@ -883,7 +996,17 @@ size_t HUF_decompress1X_DCtx (HUF_DTable* dctx, void* dst, size_t dstSize, const
     if (cSrcSize == 1) { memset(dst, *(const BYTE*)cSrc, dstSize); return dstSize; }   /* RLE */
 
     {   U32 const algoNb = HUF_selectDecoder(dstSize, cSrcSize);
-        return algoNb ? HUF_decompress1X4_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) :
-                        HUF_decompress1X2_DCtx(dctx, dst, dstSize, cSrc, cSrcSize) ;
+        return algoNb ? HUF_decompress1X4_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize):
+                        HUF_decompress1X2_DCtx_wksp(dctx, dst, dstSize, cSrc,
+                                cSrcSize, workSpace, wkspSize);
     }
 }
+
+size_t HUF_decompress1X_DCtx(HUF_DTable* dctx, void* dst, size_t dstSize,
+                             const void* cSrc, size_t cSrcSize)
+{
+    U32 workSpace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
+    return HUF_decompress1X_DCtx_wksp(dctx, dst, dstSize, cSrc, cSrcSize,
+                                      workSpace, sizeof(workSpace));
+}

lib/decompress/zstd_decompress.c

@@ -93,6 +93,7 @@ typedef struct {
     FSE_DTable OFTable[FSE_DTABLE_SIZE_U32(OffFSELog)];
     FSE_DTable MLTable[FSE_DTABLE_SIZE_U32(MLFSELog)];
     HUF_DTable hufTable[HUF_DTABLE_SIZE(HufLog)];  /* can accommodate HUF_decompress4X */
+    U32 workspace[HUF_DECOMPRESS_WORKSPACE_SIZE_U32];
     U32 rep[ZSTD_REP_NUM];
 } ZSTD_entropyTables_t;
 
@@ -559,8 +560,10 @@ size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* dctx,
                                         HUF_decompress1X_usingDTable(dctx->litBuffer, litSize, istart+lhSize, litCSize, dctx->HUFptr) :
                                         HUF_decompress4X_usingDTable(dctx->litBuffer, litSize, istart+lhSize, litCSize, dctx->HUFptr) ) :
                                     ( singleStream ?
-                                        HUF_decompress1X2_DCtx(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize) :
-                                        HUF_decompress4X_hufOnly (dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize)) ))
+                                        HUF_decompress1X2_DCtx_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize,
+                                                                    dctx->entropy.workspace, sizeof(dctx->entropy.workspace)) :
+                                        HUF_decompress4X_hufOnly_wksp(dctx->entropy.hufTable, dctx->litBuffer, litSize, istart+lhSize, litCSize,
+                                                                      dctx->entropy.workspace, sizeof(dctx->entropy.workspace)))))
                     return ERROR(corruption_detected);
 
                 dctx->litPtr = dctx->litBuffer;
@@ -1854,7 +1857,9 @@ static size_t ZSTD_loadEntropy(ZSTD_entropyTables_t* entropy, const void* const
     dictPtr += 8;   /* skip header = magic + dictID */
 
 
-    {   size_t const hSize = HUF_readDTableX4(entropy->hufTable, dictPtr, dictEnd-dictPtr);
+    {   size_t const hSize = HUF_readDTableX4_wksp(
+            entropy->hufTable, dictPtr, dictEnd - dictPtr,
+            entropy->workspace, sizeof(entropy->workspace));
         if (HUF_isError(hSize)) return ERROR(dictionary_corrupted);
         dictPtr += hSize;
     }

lib/zstd.h

@@ -68,7 +68,7 @@ ZSTDLIB_API unsigned ZSTD_versionNumber(void);   /**< useful to check dll versio
 #define ZSTD_QUOTE(str) #str
 #define ZSTD_EXPAND_AND_QUOTE(str) ZSTD_QUOTE(str)
 #define ZSTD_VERSION_STRING ZSTD_EXPAND_AND_QUOTE(ZSTD_LIB_VERSION)
-ZSTDLIB_API const char* ZSTD_versionString(void);   /* >= v1.3.0 */
+ZSTDLIB_API const char* ZSTD_versionString(void);   /* v1.3.0 */
 
 
 /***************************************
@@ -92,27 +92,41 @@ ZSTDLIB_API size_t ZSTD_compress( void* dst, size_t dstCapacity,
 ZSTDLIB_API size_t ZSTD_decompress( void* dst, size_t dstCapacity,
                               const void* src, size_t compressedSize);
 
-/*! ZSTD_getDecompressedSize() :
- *  NOTE: This function is planned to be obsolete, in favor of ZSTD_getFrameContentSize().
- *  ZSTD_getFrameContentSize() works the same way,
- *  returning the decompressed size of a single frame,
- *  but distinguishes empty frames from frames with an unknown size, or errors.
- *
- *  'src' is the start of a zstd compressed frame.
- *  @return : content size to be decompressed, as a 64-bits value _if known_, 0 otherwise.
- *   note 1 : decompressed size is an optional field, it may not be present, typically in streaming mode.
- *            When `return==0`, data to decompress could be any size.
+/*! ZSTD_getFrameContentSize() : v1.3.0
+ *  `src` should point to the start of a ZSTD encoded frame.
+ *  `srcSize` must be at least as large as the frame header.
+ *            hint : any size >= `ZSTD_frameHeaderSize_max` is large enough.
+ *  @return : - decompressed size of the frame in `src`, if known
+ *            - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
+ *            - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small)
+ *   note 1 : a 0 return value means the frame is valid but "empty".
+ *   note 2 : decompressed size is an optional field, it may not be present, typically in streaming mode.
+ *            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
  *            In which case, it's necessary to use streaming mode to decompress data.
- *            Optionally, application can use ZSTD_decompress() while relying on implied limits.
- *            (For example, data may be necessarily cut into blocks <= 16 KB).
- *   note 2 : decompressed size is always present when compression is done with ZSTD_compress()
- *   note 3 : decompressed size can be very large (64-bits value),
+ *            Optionally, application can rely on some implicit limit,
+ *            as ZSTD_decompress() only needs an upper bound of decompressed size.
+ *            (For example, data could be necessarily cut into blocks <= 16 KB).
+ *   note 3 : decompressed size is always present when compression is done with ZSTD_compress()
+ *   note 4 : decompressed size can be very large (64-bits value),
  *            potentially larger than what local system can handle as a single memory segment.
  *            In which case, it's necessary to use streaming mode to decompress data.
- *   note 4 : If source is untrusted, decompressed size could be wrong or intentionally modified.
- *            Always ensure result fits within application's authorized limits.
+ *   note 5 : If source is untrusted, decompressed size could be wrong or intentionally modified.
+ *            Always ensure return value fits within application's authorized limits.
  *            Each application can set its own limits.
- *   note 5 : when `return==0`, if precise failure cause is needed, use ZSTD_getFrameHeader() to know more. */
+ *   note 6 : This function replaces ZSTD_getDecompressedSize() */
+#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
+#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
+ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
+
+/*! ZSTD_getDecompressedSize() :
+ *  NOTE: This function is now obsolete, in favor of ZSTD_getFrameContentSize().
+ *  Both functions work the same way,
+ *  but ZSTD_getDecompressedSize() blends
+ *  "empty", "unknown" and "error" results in the same return value (0),
+ *  while ZSTD_getFrameContentSize() distinguishes them.
+ *
+ *  'src' is the start of a zstd compressed frame.
+ *  @return : content size to be decompressed, as a 64-bits value _if known and not empty_, 0 otherwise. */
 ZSTDLIB_API unsigned long long ZSTD_getDecompressedSize(const void* src, size_t srcSize);
 
 
@@ -291,7 +305,7 @@ typedef struct ZSTD_outBuffer_s {
 * *******************************************************************/
 
 typedef ZSTD_CCtx ZSTD_CStream;  /**< CCtx and CStream are now effectively same object (>= v1.3.0) */
-                                 /* But continue to distinguish them for compatibility with versions <= v1.2.0 */
+                                 /* Continue to distinguish them for compatibility with versions <= v1.2.0 */
 /*===== ZSTD_CStream management functions =====*/
 ZSTDLIB_API ZSTD_CStream* ZSTD_createCStream(void);
 ZSTDLIB_API size_t ZSTD_freeCStream(ZSTD_CStream* zcs);
@@ -330,7 +344,7 @@ ZSTDLIB_API size_t ZSTD_CStreamOutSize(void);   /**< recommended size for output
 * *******************************************************************************/
 
 typedef ZSTD_DCtx ZSTD_DStream;  /**< DCtx and DStream are now effectively same object (>= v1.3.0) */
-                                 /* But continue to distinguish them for compatibility with versions <= v1.2.0 */
+                                 /* Continue to distinguish them for compatibility with versions <= v1.2.0 */
 /*===== ZSTD_DStream management functions =====*/
 ZSTDLIB_API ZSTD_DStream* ZSTD_createDStream(void);
 ZSTDLIB_API size_t ZSTD_freeDStream(ZSTD_DStream* zds);
@@ -349,8 +363,8 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output
 /****************************************************************************************
  * START OF ADVANCED AND EXPERIMENTAL FUNCTIONS
  * The definitions in this section are considered experimental.
- * They should never be used with a dynamic library, as they may change in the future.
- * They are provided for advanced usages.
+ * They should never be used with a dynamic library, as prototypes may change in the future.
+ * They are provided for advanced scenarios.
  * Use them only in association with static linking.
  * ***************************************************************************************/
 
@@ -381,8 +395,8 @@ ZSTDLIB_API size_t ZSTD_DStreamOutSize(void);   /*!< recommended size for output
 #define ZSTD_FRAMEHEADERSIZE_MAX 18    /* for static allocation */
 #define ZSTD_FRAMEHEADERSIZE_MIN  6
 static const size_t ZSTD_frameHeaderSize_prefix = 5;  /* minimum input size to know frame header size */
-static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
 static const size_t ZSTD_frameHeaderSize_max = ZSTD_FRAMEHEADERSIZE_MAX;
+static const size_t ZSTD_frameHeaderSize_min = ZSTD_FRAMEHEADERSIZE_MIN;
 static const size_t ZSTD_skippableHeaderSize = 8;  /* magic number + skippable frame length */
 
 
@@ -433,26 +447,15 @@ static const ZSTD_customMem ZSTD_defaultCMem = { NULL, NULL, NULL };
 /*! ZSTD_findFrameCompressedSize() :
  *  `src` should point to the start of a ZSTD encoded frame or skippable frame
  *  `srcSize` must be at least as large as the frame
- *  @return : the compressed size of the frame pointed to by `src`,
+ *  @return : the compressed size of the first frame starting at `src`,
  *            suitable to pass to `ZSTD_decompress` or similar,
- *            or an error code if given invalid input. */
+ *            or an error code if input is invalid */
 ZSTDLIB_API size_t ZSTD_findFrameCompressedSize(const void* src, size_t srcSize);
 
-/*! ZSTD_getFrameContentSize() :
- *  `src` should point to the start of a ZSTD encoded frame.
- *  `srcSize` must be at least as large as the frame header.
- *       A value >= `ZSTD_frameHeaderSize_max` is guaranteed to be large enough.
- *  @return : - decompressed size of the frame pointed to be `src` if known
- *            - ZSTD_CONTENTSIZE_UNKNOWN if the size cannot be determined
- *            - ZSTD_CONTENTSIZE_ERROR if an error occurred (e.g. invalid magic number, srcSize too small) */
-#define ZSTD_CONTENTSIZE_UNKNOWN (0ULL - 1)
-#define ZSTD_CONTENTSIZE_ERROR   (0ULL - 2)
-ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t srcSize);
-
 /*! ZSTD_findDecompressedSize() :
  *  `src` should point 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 `srcSize` bytes after `src`)
+ *       (i.e. there should be a frame boundary exactly at `srcSize` bytes after `src`)
  *  @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
@@ -460,8 +463,6 @@ ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t
  *   note 1 : decompressed size is an optional field, that may not be present, especially in streaming mode.
  *            When `return==ZSTD_CONTENTSIZE_UNKNOWN`, data to decompress could be any size.
  *            In which case, it's necessary to use streaming mode to decompress data.
- *            Optionally, application can still use ZSTD_decompress() while relying on implied limits.
- *            (For example, data may be necessarily cut into blocks <= 16 KB).
  *   note 2 : decompressed size is always present when compression is done with ZSTD_compress()
  *   note 3 : decompressed size can be very large (64-bits value),
  *            potentially larger than what local system can handle as a single memory segment.
@@ -470,7 +471,7 @@ ZSTDLIB_API unsigned long long ZSTD_getFrameContentSize(const void *src, size_t
  *            Always ensure result fits within application's authorized limits.
  *            Each application can set its own limits.
  *   note 5 : ZSTD_findDecompressedSize handles multiple frames, and so it must traverse the input to
- *            read each contained frame header.  This is efficient as most of the data is skipped,
+ *            read each contained frame header.  This is fast as most of the data is skipped,
  *            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);
 
@@ -478,7 +479,8 @@ ZSTDLIB_API unsigned long long ZSTD_findDecompressedSize(const void* src, size_t
 *   `src` should point to the start of a ZSTD frame
 *   `srcSize` must be >= ZSTD_frameHeaderSize_prefix.
 *   @return : size of the Frame Header */
-size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
+ZSTDLIB_API size_t ZSTD_frameHeaderSize(const void* src, size_t srcSize);
+
 
 /***************************************
 *  Context memory usage
@@ -575,7 +577,7 @@ ZSTDLIB_API size_t ZSTD_setCCtxParameter(ZSTD_CCtx* cctx, ZSTD_CCtxParameter par
 ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_byReference(const void* dictBuffer, size_t dictSize, int compressionLevel);
 
 
-typedef enum { ZSTD_dm_auto=0,        /* dictionary is "full" if it starts with ZSTD_MAGIC_DICTIONARY, rawContent otherwize */
+typedef enum { ZSTD_dm_auto=0,        /* dictionary is "full" if it starts with ZSTD_MAGIC_DICTIONARY, otherwise it is "rawContent" */
                ZSTD_dm_rawContent,    /* ensures dictionary is always loaded as rawContent, even if it starts with ZSTD_MAGIC_DICTIONARY */
                ZSTD_dm_fullDict       /* refuses to load a dictionary if it does not respect Zstandard's specification */
 } ZSTD_dictMode_e;
@@ -583,7 +585,8 @@ typedef enum { ZSTD_dm_auto=0,        /* dictionary is "full" if it starts with
  *  Create a ZSTD_CDict using external alloc and free, and customized compression parameters */
 ZSTDLIB_API ZSTD_CDict* ZSTD_createCDict_advanced(const void* dict, size_t dictSize,
                                                   unsigned byReference, ZSTD_dictMode_e dictMode,
-                                                  ZSTD_compressionParameters cParams, ZSTD_customMem customMem);
+                                                  ZSTD_compressionParameters cParams,
+                                                  ZSTD_customMem customMem);
 
 /*! ZSTD_initStaticCDict_advanced() :
  *  Generate a digested dictionary in provided memory area.