#ifndef _PERF_LINUX_BITOPS_H_
#define _PERF_LINUX_BITOPS_H_

#include <linux/kernel.h>

#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 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))

static inline void set_bit(int nr, unsigned long *addr)
{
	addr[nr / BITS_PER_LONG] |= 1UL << (nr % BITS_PER_LONG);
}

static inline void clear_bit(int nr, unsigned long *addr)
{
	addr[nr / BITS_PER_LONG] &= ~(1UL << (nr % BITS_PER_LONG));
}

/**
 * hweightN - returns the hamming weight of a N-bit word
 * @x: the word to weigh
 *
 * The Hamming Weight of a number is the total number of bits set in it.
 */

static inline unsigned int hweight32(unsigned int w)
{
	unsigned int res = w - ((w >> 1) & 0x55555555);
	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
	res = (res + (res >> 4)) & 0x0F0F0F0F;
	res = res + (res >> 8);
	return (res + (res >> 16)) & 0x000000FF;
}

static inline unsigned long hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
	res = res + (res >> 8);
	res = res + (res >> 16);
	return (res + (res >> 32)) & 0x00000000000000FFul;
#endif
}

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)

/**
 * __ffs - find first bit in word.
 * @word: The word to search
 *
 * Undefined if no bit exists, so code should check against 0 first.
 */
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;
}

#define ffz(x) __ffs(~(x))

/*
 * Find the first set bit in a memory region.
 */
static inline unsigned long
find_first_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 >> (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);
}

/*
 * This implementation of find_{first,next}_zero_bit was stolen from
 * Linus' asm-alpha/bitops.h.
 */
static inline unsigned long
find_next_zero_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 >> (BITS_PER_LONG - 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 << size;
	if (tmp == ~0UL)	/* Are any bits zero? */
		return result + size;	/* Nope. */
found_middle:
	return result + ffz(tmp);
}
#endif