#ifndef _PERF_LINUX_BITOPS_H_
#define _PERF_LINUX_BITOPS_H_

#include <linux/kernel.h>
#include <linux/compiler.h>
#include <asm/hweight.h>

#ifndef __WORDSIZE
#define __WORDSIZE (__SIZEOF_LONG__ * 8)
#endif

#define BITS_PER_LONG __WORDSIZE

#define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
#define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
#define BITS_PER_BYTE		8
#define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
#define BITS_TO_U64(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
#define BITS_TO_U32(nr)		DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
#define BITS_TO_BYTES(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE)

#define for_each_set_bit(bit, addr, size) \
	for ((bit) = find_first_bit((addr), (size));		\
	     (bit) < (size);					\
	     (bit) = find_next_bit((addr), (size), (bit) + 1))

/* same as for_each_set_bit() but use bit as value to start with */
#define for_each_set_bit_from(bit, addr, size) \
	for ((bit) = find_next_bit((addr), (size), (bit));	\
	     (bit) < (size);					\
	     (bit) = find_next_bit((addr), (size), (bit) + 1))

#include <asm-generic/bitops/atomic.h>

static inline unsigned long hweight_long(unsigned long w)
{
	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
}

#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)

#include <asm-generic/bitops/__ffs.h>

typedef const unsigned long __attribute__((__may_alias__)) long_alias_t;

/*
 * Find the first set bit in a memory region.
 */
static inline unsigned long
find_first_bit(const unsigned long *addr, unsigned long size)
{
	long_alias_t *p = (long_alias_t *) 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 >> (BITS_PER_LONG - size));
	if (tmp == 0UL)		/* Are any bits set? */
		return result + size;	/* Nope. */
found:
	return result + __ffs(tmp);
}

/*
 * Find the next set bit in a memory region.
 */
static inline unsigned long
find_next_bit(const unsigned long *addr, unsigned long size, unsigned long offset)
{
	const unsigned long *p = addr + BITOP_WORD(offset);
	unsigned long result = offset & ~(BITS_PER_LONG-1);
	unsigned long tmp;

	if (offset >= size)
		return size;
	size -= result;
	offset %= BITS_PER_LONG;
	if (offset) {
		tmp = *(p++);
		tmp &= (~0UL << offset);
		if (size < BITS_PER_LONG)
			goto found_first;
		if (tmp)
			goto found_middle;
		size -= BITS_PER_LONG;
		result += BITS_PER_LONG;
	}
	while (size & ~(BITS_PER_LONG-1)) {
		if ((tmp = *(p++)))
			goto found_middle;
		result += BITS_PER_LONG;
		size -= BITS_PER_LONG;
	}
	if (!size)
		return result;
	tmp = *p;

found_first:
	tmp &= (~0UL >> (BITS_PER_LONG - size));
	if (tmp == 0UL)		/* Are any bits set? */
		return result + size;	/* Nope. */
found_middle:
	return result + __ffs(tmp);
}

#endif