#ifndef _I386_BITOPS_H
#define _I386_BITOPS_H

/*
 * Copyright 1992, Linus Torvalds.
 */

#include <linux/config.h>

/*
 * These have to be done with inline assembly: that way the bit-setting
 * is guaranteed to be atomic. All bit operations return 0 if the bit
 * was cleared before the operation and != 0 if it was not.
 *
 * bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
 */

#ifdef CONFIG_SMP
#define LOCK_PREFIX "lock ; "
#else
#define LOCK_PREFIX ""
#endif

#define ADDR (*(volatile long *) addr)

static __inline__ void set_bit(int nr, volatile void * addr)
{
	__asm__ __volatile__( LOCK_PREFIX
		"btsl %1,%0"
		:"=m" (ADDR)
		:"Ir" (nr));
}

/* WARNING: non atomic and it can be reordered! */
static __inline__ void __set_bit(int nr, volatile void * addr)
{
	__asm__(
		"btsl %1,%0"
		:"=m" (ADDR)
		:"Ir" (nr));
}

/*
 * clear_bit() doesn't provide any barrier for the compiler.
 */
#define smp_mb__before_clear_bit()	barrier()
#define smp_mb__after_clear_bit()	barrier()
static __inline__ void clear_bit(int nr, volatile void * addr)
{
	__asm__ __volatile__( LOCK_PREFIX
		"btrl %1,%0"
		:"=m" (ADDR)
		:"Ir" (nr));
}

static __inline__ void change_bit(int nr, volatile void * addr)
{
	__asm__ __volatile__( LOCK_PREFIX
		"btcl %1,%0"
		:"=m" (ADDR)
		:"Ir" (nr));
}

/*
 * It will also imply a memory barrier, thus it must clobber memory
 * to make sure to reload anything that was cached into registers
 * outside _this_ critical section.
 */
static __inline__ int test_and_set_bit(int nr, volatile void * addr)
{
	int oldbit;

	__asm__ __volatile__( LOCK_PREFIX
		"btsl %2,%1\n\tsbbl %0,%0"
		:"=r" (oldbit),"=m" (ADDR)
		:"Ir" (nr) : "memory");
	return oldbit;
}

/* WARNING: non atomic and it can be reordered! */
static __inline__ int __test_and_set_bit(int nr, volatile void * addr)
{
	int oldbit;

	__asm__(
		"btsl %2,%1\n\tsbbl %0,%0"
		:"=r" (oldbit),"=m" (ADDR)
		:"Ir" (nr));
	return oldbit;
}

static __inline__ int test_and_clear_bit(int nr, volatile void * addr)
{
	int oldbit;

	__asm__ __volatile__( LOCK_PREFIX
		"btrl %2,%1\n\tsbbl %0,%0"
		:"=r" (oldbit),"=m" (ADDR)
		:"Ir" (nr) : "memory");
	return oldbit;
}

/* WARNING: non atomic and it can be reordered! */
static __inline__ int __test_and_clear_bit(int nr, volatile void * addr)
{
	int oldbit;

	__asm__(
		"btrl %2,%1\n\tsbbl %0,%0"
		:"=r" (oldbit),"=m" (ADDR)
		:"Ir" (nr));
	return oldbit;
}

static __inline__ int test_and_change_bit(int nr, volatile void * addr)
{
	int oldbit;

	__asm__ __volatile__( LOCK_PREFIX
		"btcl %2,%1\n\tsbbl %0,%0"
		:"=r" (oldbit),"=m" (ADDR)
		:"Ir" (nr) : "memory");
	return oldbit;
}

/*
 * This routine doesn't need to be atomic.
 */
static __inline__ int constant_test_bit(int nr, const volatile void * addr)
{
	return ((1UL << (nr & 31)) & (((const volatile unsigned int *) addr)[nr >> 5])) != 0;
}

static __inline__ int variable_test_bit(int nr, volatile void * addr)
{
	int oldbit;

	__asm__ __volatile__(
		"btl %2,%1\n\tsbbl %0,%0"
		:"=r" (oldbit)
		:"m" (ADDR),"Ir" (nr));
	return oldbit;
}

#define test_bit(nr,addr) \
(__builtin_constant_p(nr) ? \
 constant_test_bit((nr),(addr)) : \
 variable_test_bit((nr),(addr)))

/*
 * Find-bit routines..
 */
static __inline__ int find_first_zero_bit(void * addr, unsigned size)
{
	int d0, d1, d2;
	int res;

	if (!size)
		return 0;
	/* This looks at memory. Mark it volatile to tell gcc not to move it around */
	__asm__ __volatile__(
		"movl $-1,%%eax\n\t"
		"xorl %%edx,%%edx\n\t"
		"repe; scasl\n\t"
		"je 1f\n\t"
		"xorl -4(%%edi),%%eax\n\t"
		"subl $4,%%edi\n\t"
		"bsfl %%eax,%%edx\n"
		"1:\tsubl %%ebx,%%edi\n\t"
		"shll $3,%%edi\n\t"
		"addl %%edi,%%edx"
		:"=d" (res), "=&c" (d0), "=&D" (d1), "=&a" (d2)
		:"1" ((size + 31) >> 5), "2" (addr), "b" (addr));
	return res;
}

static __inline__ int find_next_zero_bit (void * addr, int size, int offset)
{
	unsigned long * p = ((unsigned long *) addr) + (offset >> 5);
	int set = 0, bit = offset & 31, res;
	
	if (bit) {
		/*
		 * Look for zero in first byte
		 */
		__asm__("bsfl %1,%0\n\t"
			"jne 1f\n\t"
			"movl $32, %0\n"
			"1:"
			: "=r" (set)
			: "r" (~(*p >> bit)));
		if (set < (32 - bit))
			return set + offset;
		set = 32 - bit;
		p++;
	}
	/*
	 * No zero yet, search remaining full bytes for a zero
	 */
	res = find_first_zero_bit (p, size - 32 * (p - (unsigned long *) addr));
	return (offset + set + res);
}

/*
 * ffz = Find First Zero in word. Undefined if no zero exists,
 * so code should check against ~0UL first..
 */
static __inline__ unsigned long ffz(unsigned long word)
{
	__asm__("bsfl %1,%0"
		:"=r" (word)
		:"r" (~word));
	return word;
}

#ifdef __KERNEL__

/*
 * ffs: find first bit set. This is defined the same way as
 * the libc and compiler builtin ffs routines, therefore
 * differs in spirit from the above ffz (man ffs).
 */

static __inline__ int ffs(int x)
{
	int r;

	__asm__("bsfl %1,%0\n\t"
		"jnz 1f\n\t"
		"movl $-1,%0\n"
		"1:" : "=r" (r) : "g" (x));
	return r+1;
}

/*
 * hweightN: returns the hamming weight (i.e. the number
 * of bits set) of a N-bit word
 */

#define hweight32(x) generic_hweight32(x)
#define hweight16(x) generic_hweight16(x)
#define hweight8(x) generic_hweight8(x)

#endif /* __KERNEL__ */

#ifdef __KERNEL__

#define ext2_set_bit                 __test_and_set_bit
#define ext2_clear_bit               __test_and_clear_bit
#define ext2_test_bit                test_bit
#define ext2_find_first_zero_bit     find_first_zero_bit
#define ext2_find_next_zero_bit      find_next_zero_bit

/* Bitmap functions for the minix filesystem.  */
#define minix_test_and_set_bit(nr,addr) __test_and_set_bit(nr,addr)
#define minix_set_bit(nr,addr) __set_bit(nr,addr)
#define minix_test_and_clear_bit(nr,addr) __test_and_clear_bit(nr,addr)
#define minix_test_bit(nr,addr) test_bit(nr,addr)
#define minix_find_first_zero_bit(addr,size) find_first_zero_bit(addr,size)

#endif /* __KERNEL__ */

#endif /* _I386_BITOPS_H */