#include <stdio.h>
#define BITS_PER_LONG 64
#define ffz(x)  __ffs(~(x))
#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
static __always_inline unsigned long __ffs(unsigned long word)
{
	int num = 0;

#if BITS_PER_LONG == 64
	if ((word & 0xffffffff) == 0) {
		num += 32;
		word >>= 32;
	}
#endif
	if ((word & 0xffff) == 0) {
		num += 16;
		word >>= 16;
	}
	if ((word & 0xff) == 0) {
		num += 8;
		word >>= 8;
	}
	if ((word & 0xf) == 0) {
		num += 4;
		word >>= 4;
	}
	if ((word & 0x3) == 0) {
		num += 2;
		word >>= 2;
	}
	if ((word & 0x1) == 0)
		num += 1;
	return num;
}
static inline void set_bit(int nr, volatile unsigned long *addr)
{
	unsigned long mask = BIT_MASK(nr);
	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
	unsigned long flags;

	*p  |= mask;
}

unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
{
	const unsigned long *p = addr;
	unsigned long result = 0;
	unsigned long tmp;

	while (size & ~(BITS_PER_LONG-1)) {
		if (~(tmp = *(p++)))
			goto found;
		result += BITS_PER_LONG;
		size -= BITS_PER_LONG;
	}
	if (!size)
		return result;

	tmp = (*p) | (~0UL << size);
	if (tmp == ~0UL)	/* Are any bits zero? */
		return result + size;	/* Nope. */
found:
	return result + ffz(tmp);
}

int main()
{
	unsigned long a[1] = {0x0UL};
	unsigned long index; 
	index = find_first_zero_bit(a, 64);
	printf("%lu\n", 64-index-1 );
	set_bit( 0, a );
	index = find_first_zero_bit(a, 64);
	printf("%lu\n", 64-index-1 );
	return 0;
}