Use workspace for count and CTable

lib/common/huf.h

@@ -91,7 +91,7 @@ size_t HUF_compress2 (void* dst, size_t dstSize, const void* src, size_t srcSize
 
 /** HUF_compress4X_wksp() :
 *   Same as HUF_compress2(), but uses externally allocated `workSpace`, which must be a table of >= 1024 unsigned */
-size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least 1024 unsigned */
+size_t HUF_compress4X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 
 
 
@@ -133,6 +133,10 @@ typedef U32 HUF_DTable;
 #define HUF_CREATE_STATIC_DTABLEX4(DTable, maxTableLog) \
         HUF_DTable DTable[HUF_DTABLE_SIZE(maxTableLog)] = { ((U32)(maxTableLog) * 0x01000001) }
 
+/* The workspace must have alignment at least 4 and be at least this large */
+#define HUF_WORKSPACE_SIZE (6 << 10)
+#define HUF_WORKSPACE_SIZE_U32 (HUF_WORKSPACE_SIZE / sizeof(U32))
+
 
 /* ****************************************
 *  Advanced decompression functions
@@ -177,7 +181,7 @@ typedef enum {
 *   Same as HUF_compress4X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
 *   If it uses hufTable it does not modify hufTable or repeat.
 *   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. */
-size_t HUF_compress4X_repeat(void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat);  /**< `workSpace` must be a table of at least 1024 unsigned */
+size_t HUF_compress4X_repeat(void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 
 /** HUF_buildCTable_wksp() :
  *  Same as HUF_buildCTable(), but using externally allocated scratch buffer.
@@ -224,13 +228,13 @@ size_t HUF_decompress4X4_usingDTable(void* dst, size_t maxDstSize, const void* c
 /* single stream variants */
 
 size_t HUF_compress1X (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog);
-size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least 1024 unsigned */
+size_t HUF_compress1X_wksp (void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 size_t HUF_compress1X_usingCTable(void* dst, size_t dstSize, const void* src, size_t srcSize, const HUF_CElt* CTable);
 /** HUF_compress1X_repeat() :
 *   Same as HUF_compress1X_wksp(), but considers using hufTable if *repeat != HUF_repeat_none.
 *   If it uses hufTable it does not modify hufTable or repeat.
 *   If it doesn't, it sets *repeat = HUF_repeat_none, and it sets hufTable to the table used. */
-size_t HUF_compress1X_repeat(void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat);  /**< `workSpace` must be a table of at least 1024 unsigned */
+size_t HUF_compress1X_repeat(void* dst, size_t dstSize, const void* src, size_t srcSize, unsigned maxSymbolValue, unsigned tableLog, void* workSpace, size_t wkspSize, HUF_CElt* hufTable, HUF_repeat* repeat);  /**< `workSpace` must be a table of at least HUF_WORKSPACE_SIZE_U32 unsigned */
 
 size_t HUF_decompress1X2 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* single-symbol decoder */
 size_t HUF_decompress1X4 (void* dst, size_t dstSize, const void* cSrc, size_t cSrcSize);   /* double-symbol decoder */

lib/compress/huf_compress.c

@@ -558,11 +558,13 @@ static size_t HUF_compress_internal (
     BYTE* const oend = ostart + dstSize;
     BYTE* op = ostart;
 
-    U32 count[HUF_SYMBOLVALUE_MAX+1];
+    U32* count;
-    HUF_CElt CTable[HUF_SYMBOLVALUE_MAX+1];
+    size_t const countSize = sizeof(U32) * (HUF_SYMBOLVALUE_MAX + 1);
+    HUF_CElt* CTable;
+    size_t const CTableSize = sizeof(HUF_CElt) * (HUF_SYMBOLVALUE_MAX + 1);
 
     /* checks & inits */
-    if (wkspSize < sizeof(huffNodeTable)) return ERROR(GENERIC);
+    if (wkspSize < sizeof(huffNodeTable) + countSize + CTableSize) return ERROR(GENERIC);
     if (!srcSize) return 0;  /* Uncompressed (note : 1 means rle, so first byte must be correct) */
     if (!dstSize) return 0;  /* cannot fit within dst budget */
     if (srcSize > HUF_BLOCKSIZE_MAX) return ERROR(srcSize_wrong);   /* current block size limit */
@@ -570,6 +572,13 @@ static size_t HUF_compress_internal (
     if (!maxSymbolValue) maxSymbolValue = HUF_SYMBOLVALUE_MAX;
     if (!huffLog) huffLog = HUF_TABLELOG_DEFAULT;
 
+    count = (U32*)workSpace;
+    workSpace = (BYTE*)workSpace + countSize;
+    wkspSize -= countSize;
+    CTable = (HUF_CElt*)workSpace;
+    workSpace = (BYTE*)workSpace + CTableSize;
+    wkspSize -= CTableSize;
+
     /* Heuristic : If we don't need to check the validity of the old table use the old table for small inputs */
     if (srcSize <= 1024 && repeat && *repeat == HUF_repeat_valid) {
         return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, oldHufTable);
@@ -595,7 +604,7 @@ static size_t HUF_compress_internal (
     {   CHECK_V_F(maxBits, HUF_buildCTable_wksp (CTable, count, maxSymbolValue, huffLog, workSpace, wkspSize) );
         huffLog = (U32)maxBits;
         /* Zero the unused symbols so we can check it for validity */
-        memset(CTable + maxSymbolValue + 1, 0, sizeof(CTable) - (maxSymbolValue + 1) * sizeof(HUF_CElt));
+        memset(CTable + maxSymbolValue + 1, 0, CTableSize - (maxSymbolValue + 1) * sizeof(HUF_CElt));
     }
 
     /* Write table description header */
@@ -612,7 +621,7 @@ static size_t HUF_compress_internal (
         if (hSize + 12ul >= srcSize) { return 0; }
         op += hSize;
         if (repeat) { *repeat = HUF_repeat_none; }
-        if (oldHufTable) { memcpy(oldHufTable, CTable, sizeof(CTable)); } /* Save the new table */
+        if (oldHufTable) { memcpy(oldHufTable, CTable, CTableSize); } /* Save the new table */
     }
     return HUF_compressCTable_internal(ostart, op, oend, src, srcSize, singleStream, CTable);
 }

lib/compress/zstd_compress.c

@@ -85,7 +85,7 @@ struct ZSTD_CCtx_s {
     FSE_CTable offcodeCTable  [FSE_CTABLE_SIZE_U32(OffFSELog, MaxOff)];
     FSE_CTable matchlengthCTable[FSE_CTABLE_SIZE_U32(MLFSELog, MaxML)];
     FSE_CTable litlengthCTable  [FSE_CTABLE_SIZE_U32(LLFSELog, MaxLL)];
-    unsigned tmpCounters[1024];
+    unsigned tmpCounters[HUF_WORKSPACE_SIZE_U32];
 };
 
 ZSTD_CCtx* ZSTD_createCCtx(void)