Reduce streaming decompression memory by 128KB

The split literals buffer patch increased streaming decompression memory
by 64KB (shrunk lit buffer from 128KB to 64KB, and added 128KB). This
patch removes the added 128KB buffer, because it isn't necessary.

The buffer was there because the literals compression code didn't know
the true `blockSizeMax` of the frame, and always put split literals so
they ended 128KB - 32 from the beginning of the block. Instead, we can
pass down the true `blockSizeMax` and ensure that the split literals
end up at `blockSizeMax - 32` from the beginning of the block. We
already reserve a full `blockSizeMax` bytes in streaming mode, so we
won't be overwriting the extDict window.

tests/fullbench.c

@@ -141,15 +141,14 @@ static size_t local_ZSTD_decompress(const void* src, size_t srcSize,
 static ZSTD_DCtx* g_zdc = NULL;
 
 #ifndef ZSTD_DLL_IMPORT
-typedef enum {
-    not_streaming = 0,
-    is_streaming = 1
-} streaming_operation;
-extern size_t ZSTD_decodeLiteralsBlock(ZSTD_DCtx* ctx, const void* src, size_t srcSize, void* dst, size_t dstCapacity, const streaming_operation streaming);
+
+extern size_t ZSTD_decodeLiteralsBlock_wrapper(ZSTD_DCtx* dctx,
+                          const void* src, size_t srcSize,
+                          void* dst, size_t dstCapacity);
 static size_t local_ZSTD_decodeLiteralsBlock(const void* src, size_t srcSize, void* dst, size_t dstSize, void* buff2)
 {
     (void)src; (void)srcSize; (void)dst; (void)dstSize;
-    return ZSTD_decodeLiteralsBlock(g_zdc, buff2, g_cSize, dst, dstSize, not_streaming);
+    return ZSTD_decodeLiteralsBlock_wrapper(g_zdc, buff2, g_cSize, dst, dstSize);
 }
 
 static size_t local_ZSTD_decodeSeqHeaders(const void* src, size_t srcSize, void* dst, size_t dstSize, void* buff2)
@@ -606,7 +605,7 @@ static int benchMem(unsigned benchNb,
             ip += ZSTD_blockHeaderSize;    /* skip block header */
             ZSTD_decompressBegin(g_zdc);
             CONTROL(iend > ip);
-            ip += ZSTD_decodeLiteralsBlock(g_zdc, ip, (size_t)(iend-ip), dstBuff, dstBuffSize, not_streaming);   /* skip literal segment */
+            ip += ZSTD_decodeLiteralsBlock_wrapper(g_zdc, ip, (size_t)(iend-ip), dstBuff, dstBuffSize);   /* skip literal segment */
             g_cSize = (size_t)(iend-ip);
             memcpy(dstBuff2, ip, g_cSize);   /* copy rest of block (it starts by SeqHeader) */
             srcSize = srcSize > 128 KB ? 128 KB : srcSize;   /* speed relative to block */