Excel Add-in: Assignment in for loop causes segmentation fault but line-by-line assignments work. Why?

Viewed 182

I just tested a toy Excel add-in project, cross building the XLL with mingw32 tool chains.

Here is my code:

//testXLL.c
#include "windows.h"
#include "xlcall.h"

#define MEMORYSIZE 65535000
char vMemBlock[MEMORYSIZE];
int vOffsetMemBlock =0;

LPSTR GetTempMemory(int cBytes){
    LPSTR lpMemory;
    if(vOffsetMemBlock + cBytes > MEMORYSIZE)
        return 0;
    else{
        lpMemory = (LPSTR) &vMemBlock + vOffsetMemBlock;
        vOffsetMemBlock += cBytes;
        if(vOffsetMemBlock & 1) vOffsetMemBlock++;
        return lpMemory;
    }
}

LPXLOPER TempStr(LPSTR lpstr){
    LPXLOPER lpx;
    int chars;
    lpx = (LPXLOPER)GetTempMemory(sizeof(XLOPER));
    if(!lpx) return 0;
    chars = lstrlen(lpstr); 
    if(chars>255) chars=255;
    lpx->val.str=(char*)GetTempMemory((sizeof(char)*chars+1));
    if(!lpx->val.str) return 0;
    strncpy(lpx->val.str, lpstr,chars);
    lpx->val.str[0]=(BYTE) chars;
    //lpx->val.str[chars]='\0';
    lpx->xltype = xltypeStr;
    return lpx;
}
   
#ifdef __cplusplus
extern "C" {
#endif

    __declspec(dllexport) double __stdcall myadd2(double a1,double a2){
        return a1+a2;
    }

    static char functionTable[11][255] =
    {" myadd2",                    // procedure
        " BBB",                        // type_text
        " add",                     // function_text
        " add1,add2",                     // argument_text
        " 1",                          // macro_type
        " category",              // category
        " ",                           // shortcut_text
        " some help topic",                           // help_topic
        " Adds toy",    // function_help
        " 1st.",   // argument_help1
        " 2nd"   // argument_help2
    };

    __declspec(dllexport) int __stdcall xlAutoOpen(){
        LPXLOPER pxDLL;
        Excel4(xlGetName,pxDLL,0);

        XLOPER xlRegArgs[11];
        for(int i = 0; i < 11; i++){
            xlRegArgs[i] = *TempStr(functionTable[i]);
        }


        Excel4(xlfRegister, 0, 12,
                pxDLL,
                &xlRegArgs[0], &xlRegArgs[1], &xlRegArgs[2], 
                &xlRegArgs[3], &xlRegArgs[4], &xlRegArgs[5],
                &xlRegArgs[6], &xlRegArgs[7], &xlRegArgs[8],
                &xlRegArgs[9], &xlRegArgs[10]);

        return 1;
    }

    __declspec(dllexport) LPXLOPER __stdcall xlAddInManagerInfo(LPXLOPER xlAction) {
        static XLOPER xlReturn, xlLongName, xlTemp;

        xlTemp.xltype = xltypeInt;
        xlTemp.val.w = xltypeInt;
        Excel4(xlCoerce, &xlReturn, 2, xlAction, &xlTemp);

        if(1 == xlReturn.val.w) {
            xlLongName = *TempStr(" xll-name"); 
        } else {
            xlLongName.xltype = xltypeErr;
            xlLongName.val.err = xlerrValue;
        }

        return &xlLongName;
    }

#ifdef __cplusplus
}
#endif

I built this testXLL.c file in Ubuntu:

>i686-w64-mingw32-gcc -shared -Wl,--kill-at testXLL.c -o win.xll -L. -lxlcall32

This generates the "win.xll" successfully but, when loading this win.xll, Excel crashes.

In Windows 10, I tried to use gdb to debug it, but I can't catch break point in the xll file – it got disabled automatically when loading. But I can see in the gdb output, it is a segmentation fault when Excel crashes.

 XLOPER xlRegArgs[11];
for(int i = 0; i < 11; i++){
    xlRegArgs[i] = *TempStr(functionTable[i]);
}

What's weird is that, if I substitute the above for loop with the following line-by-line assignments in the xlAutoOpen function, the compiled XLL file works fine in Excel:

XLOPER xlRegArgs[11];
xlRegArgs[0] = *TempStr(functionTable[0]);
xlRegArgs[1] = *TempStr(functionTable[1]);
xlRegArgs[2] = *TempStr(functionTable[2]);
xlRegArgs[3] = *TempStr(functionTable[3]);
xlRegArgs[4] = *TempStr(functionTable[4]);
xlRegArgs[5] = *TempStr(functionTable[5]);
xlRegArgs[6] = *TempStr(functionTable[6]);
xlRegArgs[7] = *TempStr(functionTable[7]);
xlRegArgs[8] = *TempStr(functionTable[8]);
xlRegArgs[9] = *TempStr(functionTable[9]);
xlRegArgs[10] = *TempStr(functionTable[10]);

Please enlighten me. What's the difference between these two assignment approaches?

1 Answers

Although I don't (yet) have a full explanation for this behaviour, I'm posting this as a possible 'workaround', which I have used in a very similar case I encountered in one of my projects.

The issue appears to be some form of 'stack corruption' caused by the use of the function-local variable (i) used as the loop index; converting this to a global/static variable will likely fix the issue. The following code snippet is a suggested fix (I have changed the name of the index variable to avoid possible name clashes elsewhere in the code):

///...
    static int regloop; // Used as the loop index, below...

    __declspec(dllexport) int __stdcall xlAutoOpen(){
        LPXLOPER pxDLL;
        Excel4(xlGetName,pxDLL,0);

        XLOPER xlRegArgs[11];
        for(regloop = 0; regloop < 11; regloop++){
            xlRegArgs[regloop] = *TempStr(functionTable[regloop]);
        }

Here's the section of code from my aforementioned project (but note this is C++/MFC) that exhibits the same sort of behaviour – but only in x86 builds (x64 builds work without issue):

static int plin;    // NOTA BENE:-  We use this in the two functions below, as the use of
                    // a local 'plin' loop index is prone to induce stack corruption (?), 
                    // especially in MSVC 2017 (MFC 14) builds for x86.

void BasicApp::OnUpdatePICmd(uint32_t nID, void *pUI)
{
//! for (int plin = 0; plin < Plugin_Number; ++plin) { // Can cause problems - vide supra
    for (plin = 0;  plin < Plugin_Number;  ++plin) {
        BOOL mEbl = FALSE;  int mChk = -1;
        if ((Plugin_UDCfnc[plin] != nullptr) && Plugin_UDCfnc[plin](nID, &mEbl, &mChk)) {
            CommandEnable(pUI, mEbl ? true : false);
            if (mChk >= 0) CmdUISetCheck(pUI, mChk);
            return;
        }
    }
    CommandEnable(pUI, false);
    return;
}

(The Plugin_UDCfnc is a static array member of the BasicApp class.)

I have, in the years since the above code was written, had occasional 'fleeting insights' into why this is happening but, as of now, I can't offer a more robust fix. I shall revisit the issue and update this post if I should stumble upon a resolution. In the meantime, others are welcome to take this as a 'clue' and post their own explanations/solutions.

Related