Delay routine problem

I want to create delay functions in a separate c file. The code should be as perfect as possible without using internal timer. I read somewhere that 'Calling the routine takes about 22us' Though 22uS may be different for my cpu clock, if possible this factor should also be taken into account.

I am using 89S52 with 24Mhz crystal. I tried following code.

void usdelay(unsigned int us){
        while (us--){
                _nop_();        //0.5uS single-cycle instruction delay
                _nop_();        //0.5uS single-cycle instruction delay
        }
}

void msdelay(unsigned int ms){
        unsigned long tm = 1000*ms;
        while (tm--){
                _nop_();        //0.5uS single-cycle instruction delay
                _nop_();        //0.5uS single-cycle instruction delay
        }
}


void secdelay(unsigned int sec){
        unsigned long tm = 1000*sec;
        while (tm--){
                msdelay(1);
        }
}

The problem is that the uS & ms delays are proper (may be - I have not measured them), but it takes very long to finish secdelay with 1 sec timing. Please HELP.