#ifndef _PERF_LINUX_BITOPS_H_
#define _PERF_LINUX_BITOPS_H_

#include "kerncompat.h"
#include <endian.h>
#include "common/internal.h"

#ifndef DIV_ROUND_UP
#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
#endif

#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 BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)

#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));
}

static inline bool test_and_set_bit(unsigned long nr, unsigned long *addr)
{
	unsigned long mask = BIT_MASK(nr);
	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
	unsigned long old = *p;

	*p = old | mask;
	return (old & mask) != 0;
}

/**
 * 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))

#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
#define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))

/*
 * This is a common helper function for find_next_bit, find_next_zero_bit, and
 * find_next_and_bit. The differences are:
 *  - The "invert" argument, which is XORed with each fetched word before
 *    searching it for one bits.
 *  - The optional "addr2", which is anded with "addr1" if present.
 */
static inline unsigned long _find_next_bit(const unsigned long *addr1,
		const unsigned long *addr2, unsigned long nbits,
		unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (start >= nbits)
		return nbits;

	tmp = addr1[start / BITS_PER_LONG];
	if (addr2)
		tmp &= addr2[start / BITS_PER_LONG];
	tmp ^= invert;

	/* Handle 1st word. */
	tmp &= BITMAP_FIRST_WORD_MASK(start);
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr1[start / BITS_PER_LONG];
		if (addr2)
			tmp &= addr2[start / BITS_PER_LONG];
		tmp ^= invert;
	}

	return min(start + __ffs(tmp), nbits);
}

/*
 * 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)
{
	return _find_next_bit(addr, NULL, size, offset, 0UL);
}

static inline unsigned long find_next_zero_bit(const unsigned long *addr,
					       unsigned long size,
					       unsigned long offset)
{
	return _find_next_bit(addr, NULL, size, offset, ~0UL);
}

#define find_first_bit(addr, size) find_next_bit((addr), (size), 0)
#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0)

#if __BYTE_ORDER == __BIG_ENDIAN

static inline unsigned long ext2_swab(const unsigned long y)
{
#if BITS_PER_LONG == 64
	return (unsigned long) bswap_64((u64) y);
#elif BITS_PER_LONG == 32
	return (unsigned long) bswap_32((u32) y);
#else
#error BITS_PER_LONG not defined
#endif
}

static inline unsigned long _find_next_bit_le(const unsigned long *addr1,
		const unsigned long *addr2, unsigned long nbits,
		unsigned long start, unsigned long invert)
{
	unsigned long tmp;

	if (start >= nbits)
		return nbits;

	tmp = addr1[start / BITS_PER_LONG];
	if (addr2)
		tmp &= addr2[start / BITS_PER_LONG];
	tmp ^= invert;

	/* Handle 1st word. */
	tmp &= ext2_swab(BITMAP_FIRST_WORD_MASK(start));
	start = round_down(start, BITS_PER_LONG);

	while (!tmp) {
		start += BITS_PER_LONG;
		if (start >= nbits)
			return nbits;

		tmp = addr1[start / BITS_PER_LONG];
		if (addr2)
			tmp &= addr2[start / BITS_PER_LONG];
		tmp ^= invert;
	}

	return min(start + __ffs(ext2_swab(tmp)), nbits);
}

static inline unsigned long find_next_zero_bit_le(const void *addr, unsigned long size,
		unsigned long offset)
{
	return _find_next_bit_le(addr, NULL, size, offset, ~0UL);
}


static inline unsigned long find_next_bit_le(const void *addr, unsigned long size,
		unsigned long offset)
{
	return _find_next_bit_le(addr, NULL, size, offset, 0UL);
}

#else

static inline unsigned long find_next_zero_bit_le(const void *addr,
                unsigned long size, unsigned long offset)
{
        return find_next_zero_bit(addr, size, offset);
}

static inline unsigned long find_next_bit_le(const void *addr,
                unsigned long size, unsigned long offset)
{
        return find_next_bit(addr, size, offset);
}

static inline unsigned long find_first_zero_bit_le(const void *addr,
                unsigned long size)
{
        return find_first_zero_bit(addr, size);
}

#endif

#endif