2

I have an assembly routine that calls, in a generic way, a function known to use the stdcall convention and return a float. This function is being used by a marshalling framework to expose stdcall functions to a scripting language.

Background

Here's the function using GNU inline assembly that compiles on MinGW 4.3, Win32:

inline uint64_t stdcall_invoke_return_float(int args_size_bytes,
                                            const char * args_ptr,
                                            void * func_ptr)
{
    uint64_t result;
    assert(
        0 == args_size_bytes % 4
            || !"argument size must be a multiple of 4 bytes");
#if defined(__GNUC__)
    asm
    (
        /* INPUT PARAMS:  %0 is the address where top of FP stack to be stored
         *                %1 is the number of BYTES to push onto the stack, */
        /*                   and during the copy loop it is the address of */
        /*                   the next word to push */
        /*                %2 is the base address of the array */
        /*                %3 is the address of the function to call */
            "testl %1, %1    # If zero argument bytes given, skip \n\t"
            "je    2f        # right to the function call.        \n\t"
            "addl  %2, %1\n"
        "1:\n\t"
            "subl  $4, %1    # Push arguments onto the stack in   \n\t"
            "pushl (%1)      # reverse order. Keep looping while  \n\t"
            "cmp   %2, %1    # addr to push (%1) > base addr (%2) \n\t"
            "jg    1b        # Callee cleans up b/c __stdcall.    \n"
        "2:\n\t"
            "call  * %3      # Callee will leave result in ST0    \n\t"
            "fsts  %0        # Copy 32-bit float from ST0->result"
        : "=m" (result)
        : "r" (args_size_bytes), "r" (args_ptr), "mr" (func_ptr)
        : "%eax", "%edx", "%ecx" /* eax, ecx, edx are caller-save */, "cc"
    );
#else
#pragma error "Replacement for inline assembler required"
#endif
    return result;
}

This is just a little glue to make it easier to write test cases:

template<typename FuncPtr, typename ArgType>
float float_invoke(FuncPtr f, int nargs, ArgType * args)
{
    uint64_t result = stdcall_invoke_return_float(
        nargs * sizeof(ArgType),
        reinterpret_cast<const char *>(args),
        reinterpret_cast<void *>(f)
    );
    return *reinterpret_cast<float *>(&result);
}

Now I have some test cases that invoke this function:

__stdcall float TestReturn1_0Float()
{ return 1.0f; }

__stdcall float TestFloat(float a)
{ return a; }

__stdcall float TestSum2Floats(float a, float b)
{ return a + b; }

static const float args[2] = { 10.0f, -1.0f };

assert_equals(1.0f, float_invoke(TestReturn1_0Float, 0, args)); // test 1
assert_equals(10.0f, float_invoke(TestFloat, 1, args));         // test 2
assert_equals(-1.0f, float_invoke(TestFloat, 1, args + 1));     // test 3
assert_equals(9.0f, float_invoke(TestSumTwoFloats, 2, args));   // test 4

Problem

Randomly, test 3 is giving me garbage output instead of returning -1.0.

I'm wondering if I'm

  • failing to preserve some state before the call instruction?
  • messing up some state with the fsts instruction?
  • fundamentally misunderstanding how to get a float value from a stdcall function that returns float????

All help greatly appreciated.

4

2 回答 2

1

您允许函数指针的内存引用，GCC 可能会在错误假设内联程序集不会更改堆栈指针的情况下构造相对于堆栈指针的引用。

于 2013-08-11T20:48:42.233 回答
1

缺少一台windows机器，我无法完全测试这个；在 Linux 上，以下为我提供了 float 函数的返回码：

extern float something(int);

#include 
#include 

int main(int argc, char **argv)
{
    int val = atoi(argv[1]);
    float ret;

    asm("pushl %1\n\t"
        "call * %2\n\t"
        "addl $4, %%esp"
       : "=t"(ret)
       : "r"(val), "r"(something)
       : "%eax", "%ecx", "%edx", "memory", "cc");

    printf("something(%d) == %f\n", val, ret);
    return 0;
}

关键是使用"=t"(ret)约束 - 获取浮点堆栈的顶部，请参阅机器约束（来自 gcc 手册）。如果 Windows也stdcall返回float结果ST(0)，那应该可以工作，不需要fld/fst因为编译器可以在必要时为你做这些。

当您从内联汇编中调用函数时，您还需要指定memory和ccclobbers。

于 2013-08-11T09:05:19.810 回答