#ifndef __ASM_CMPXCHG_H
#define __ASM_CMPXCHG_H

#include <linux/bitops.h> /* for LOCK_PREFIX */

/*
 * Note: if you use set64_bit(), __cmpxchg64(), or their variants, you
 *       you need to test for the feature in boot_cpu_data.
 */

#define xchg(ptr,v) ((__typeof__(*(ptr)))__xchg((unsigned long)(v),(ptr),sizeof(*(ptr))))

struct __xchg_dummy { unsigned long a[100]; };
#define __xg(x) ((struct __xchg_dummy *)(x))

/*
 * The semantics of XCHGCMP8B are a bit strange, this is why
 * there is a loop and the loading of %%eax and %%edx has to
 * be inside. This inlines well in most cases, the cached
 * cost is around ~38 cycles. (in the future we might want
 * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that
 * might have an implicit FPU-save as a cost, so it's not
 * clear which path to go.)
 *
 * cmpxchg8b must be used with the lock prefix here to allow
 * the instruction to be executed atomically, see page 3-102
 * of the instruction set reference 24319102.pdf. We need
 * the reader side to see the coherent 64bit value.
 */
static inline void __set_64bit (unsigned long long * ptr,
		unsigned int low, unsigned int high)
{
	__asm__ __volatile__ (
		"\n1:\t"
		"movl (%0), %%eax\n\t"
		"movl 4(%0), %%edx\n\t"
		LOCK_PREFIX "cmpxchg8b (%0)\n\t"
		"jnz 1b"
		: /* no outputs */
		:	"D"(ptr),
			"b"(low),
			"c"(high)
		:	"ax","dx","memory");
}

static inline void __set_64bit_constant (unsigned long long *ptr,
						 unsigned long long value)
{
	__set_64bit(ptr,(unsigned int)(value), (unsigned int)((value)>>32ULL));
}
#define ll_low(x)	*(((unsigned int*)&(x))+0)
#define ll_high(x)	*(((unsigned int*)&(x))+1)

static inline void __set_64bit_var (unsigned long long *ptr,
			 unsigned long long value)
{
	__set_64bit(ptr,ll_low(value), ll_high(value));
}

#define set_64bit(ptr,value) \
(__builtin_constant_p(value) ? \
 __set_64bit_constant(ptr, value) : \
 __set_64bit_var(ptr, value) )

#define _set_64bit(ptr,value) \
(__builtin_constant_p(value) ? \
 __set_64bit(ptr, (unsigned int)(value), (unsigned int)((value)>>32ULL) ) : \
 __set_64bit(ptr, ll_low(value), ll_high(value)) )

/*
 * Note: no "lock" prefix even on SMP: xchg always implies lock anyway
 * Note 2: xchg has side effect, so that attribute volatile is necessary,
 *	  but generally the primitive is invalid, *ptr is output argument. --ANK
 */
static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int size)
{
	switch (size) {
		case 1:
			__asm__ __volatile__("xchgb %b0,%1"
				:"=q" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
		case 2:
			__asm__ __volatile__("xchgw %w0,%1"
				:"=r" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
		case 4:
			__asm__ __volatile__("xchgl %0,%1"
				:"=r" (x)
				:"m" (*__xg(ptr)), "0" (x)
				:"memory");
			break;
	}
	return x;
}

/*
 * Atomic compare and exchange.  Compare OLD with MEM, if identical,
 * store NEW in MEM.  Return the initial value in MEM.  Success is
 * indicated by comparing RETURN with OLD.
 */

#ifdef CONFIG_X86_CMPXCHG
#define __HAVE_ARCH_CMPXCHG 1
#define cmpxchg(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
#define sync_cmpxchg(ptr,o,n)\
	((__typeof__(*(ptr)))__sync_cmpxchg((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
#define cmpxchg_local(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg_local((ptr),(unsigned long)(o),\
					(unsigned long)(n),sizeof(*(ptr))))
#endif

static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
				      unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__(LOCK_PREFIX "cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

/*
 * Always use locked operations when touching memory shared with a
 * hypervisor, since the system may be SMP even if the guest kernel
 * isn't.
 */
static inline unsigned long __sync_cmpxchg(volatile void *ptr,
					    unsigned long old,
					    unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__("lock; cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__("lock; cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__("lock; cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

static inline unsigned long __cmpxchg_local(volatile void *ptr,
			unsigned long old, unsigned long new, int size)
{
	unsigned long prev;
	switch (size) {
	case 1:
		__asm__ __volatile__("cmpxchgb %b1,%2"
				     : "=a"(prev)
				     : "q"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 2:
		__asm__ __volatile__("cmpxchgw %w1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	case 4:
		__asm__ __volatile__("cmpxchgl %1,%2"
				     : "=a"(prev)
				     : "r"(new), "m"(*__xg(ptr)), "0"(old)
				     : "memory");
		return prev;
	}
	return old;
}

#ifndef CONFIG_X86_CMPXCHG
/*
 * Building a kernel capable running on 80386. It may be necessary to
 * simulate the cmpxchg on the 80386 CPU. For that purpose we define
 * a function for each of the sizes we support.
 */

extern unsigned long cmpxchg_386_u8(volatile void *, u8, u8);
extern unsigned long cmpxchg_386_u16(volatile void *, u16, u16);
extern unsigned long cmpxchg_386_u32(volatile void *, u32, u32);

static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old,
				      unsigned long new, int size)
{
	switch (size) {
	case 1:
		return cmpxchg_386_u8(ptr, old, new);
	case 2:
		return cmpxchg_386_u16(ptr, old, new);
	case 4:
		return cmpxchg_386_u32(ptr, old, new);
	}
	return old;
}

#define cmpxchg(ptr,o,n)						\
({									\
	__typeof__(*(ptr)) __ret;					\
	if (likely(boot_cpu_data.x86 > 3))				\
		__ret = __cmpxchg((ptr), (unsigned long)(o),		\
					(unsigned long)(n), sizeof(*(ptr))); \
	else								\
		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
					(unsigned long)(n), sizeof(*(ptr))); \
	__ret;								\
})
#define cmpxchg_local(ptr,o,n)						\
({									\
	__typeof__(*(ptr)) __ret;					\
	if (likely(boot_cpu_data.x86 > 3))				\
		__ret = __cmpxchg_local((ptr), (unsigned long)(o),	\
					(unsigned long)(n), sizeof(*(ptr))); \
	else								\
		__ret = cmpxchg_386((ptr), (unsigned long)(o),		\
					(unsigned long)(n), sizeof(*(ptr))); \
	__ret;								\
})
#endif

static inline unsigned long long __cmpxchg64(volatile void *ptr, unsigned long long old,
				      unsigned long long new)
{
	unsigned long long prev;
	__asm__ __volatile__(LOCK_PREFIX "cmpxchg8b %3"
			     : "=A"(prev)
			     : "b"((unsigned long)new),
			       "c"((unsigned long)(new >> 32)),
			       "m"(*__xg(ptr)),
			       "0"(old)
			     : "memory");
	return prev;
}

static inline unsigned long long __cmpxchg64_local(volatile void *ptr,
			unsigned long long old, unsigned long long new)
{
	unsigned long long prev;
	__asm__ __volatile__("cmpxchg8b %3"
			     : "=A"(prev)
			     : "b"((unsigned long)new),
			       "c"((unsigned long)(new >> 32)),
			       "m"(*__xg(ptr)),
			       "0"(old)
			     : "memory");
	return prev;
}

#define cmpxchg64(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg64((ptr),(unsigned long long)(o),\
					(unsigned long long)(n)))
#define cmpxchg64_local(ptr,o,n)\
	((__typeof__(*(ptr)))__cmpxchg64_local((ptr),(unsigned long long)(o),\
					(unsigned long long)(n)))
#endif