求助：udelay()的怪问题？

//在驱动nandflash驱动中或其它驱动中：

static int __init era_nand_init(void)

{

    struct nand_chip *this;

    int retval;

        udelay（1）；//这里将变的很慢(纠正：上面多了个s)

         ndelay(1);  //照样慢(纠正：上面多了个s)

         ...

}

#include <linux/module.h>

#include <linux/param.h>

#include <linux/smp.h>



#include <asm/compiler.h>

#include <asm/war.h>



inline void __delay(unsigned int loops)

{

	__asm__ __volatile__ (

	"	.set	noreorder				\n"

	"	.align	3					\n"

	"1:	bnez	%0, 1b					\n"

	"	subu	%0, 1					\n"

	"	.set	reorder					\n"

	: "=r" (loops)

	: "0" (loops));

}

EXPORT_SYMBOL(__delay);



/*

 * Division by multiplication: you don't have to worry about

 * loss of precision.

 *

 * Use only for very small delays ( < 1 msec).  Should probably use a

 * lookup table, really, as the multiplications take much too long with

 * short delays.  This is a "reasonable" implementation, though (and the

 * first constant multiplications gets optimized away if the delay is

 * a constant)

 */



void __udelay(unsigned long us)

{

	unsigned int lpj = current_cpu_data.udelay_val;



	__delay((us * 0x000010c7 * HZ * lpj) >> 32);

}

EXPORT_SYMBOL(__udelay);



void __ndelay(unsigned long ns)

{

	unsigned int lpj = current_cpu_data.udelay_val;



	__delay((ns * 0x00000005 * HZ * lpj) >> 32);

}

EXPORT_SYMBOL(__ndelay);

init\main.c

main()

{

    ...

    calibrate_delay();

    udelay(1);  //这里调用正常

     ndelay(1);  //正常

    ...

}

在驱动nandflash驱动中或其它驱动中：

static int __init era_nand_init(void)

{

	struct nand_chip *this;

	int retval;

        udelays（1）；//这里将变的很慢

         ndelays(1);  //照样慢

         ...