#ifndef ASM_X86_CMPXCHG_H
#define ASM_X86_CMPXCHG_H

#include <linux/compiler.h>
#include <asm/alternative.h> /* Provides LOCK_PREFIX */

/*
 * Non-existant functions to indicate usage errors at link time
 * (or compile-time if the compiler implements __compiletime_error().
 */
extern void __xchg_wrong_size(void)
	__compiletime_error("Bad argument size for xchg");
extern void __cmpxchg_wrong_size(void)
	__compiletime_error("Bad argument size for cmpxchg");
extern void __xadd_wrong_size(void)
	__compiletime_error("Bad argument size for xadd");
extern void __add_wrong_size(void)
	__compiletime_error("Bad argument size for add");

/*
 * Constants for operation sizes. On 32-bit, the 64-bit size it set to
 * -1 because sizeof will never return -1, thereby making those switch
 * case statements guaranteeed dead code which the compiler will
 * eliminate, and allowing the "missing symbol in the default case" to
 * indicate a usage error.
 */
#define __X86_CASE_B	1
#define __X86_CASE_W	2
#define __X86_CASE_L	4
#ifdef CONFIG_64BIT
#define __X86_CASE_Q	8
#else
#define	__X86_CASE_Q	-1		/* sizeof will never return -1 */
#endif

/*
 * Note: no "lock" prefix even on SMP: xchg always implies lock anyway.
 * Since this is generally used to protect other memory information, we
 * use "asm volatile" and "memory" clobbers to prevent gcc from moving
 * information around.
 */
#define __xchg(x, ptr, size)						\
({									\
	__typeof(*(ptr)) __x = (x);					\
	switch (size) {							\
	case __X86_CASE_B:						\
	{								\
		volatile u8 *__ptr = (volatile u8 *)(ptr);		\
		asm volatile("xchgb %0,%1"				\
			     : "=q" (__x), "+m" (*__ptr)		\
			     : "0" (__x)				\
			     : "memory");				\
		break;							\
	}								\
	case __X86_CASE_W:						\
	{								\
		volatile u16 *__ptr = (volatile u16 *)(ptr);		\
		asm volatile("xchgw %0,%1"				\
			     : "=r" (__x), "+m" (*__ptr)		\
			     : "0" (__x)				\
			     : "memory");				\
		break;							\
	}								\
	case __X86_CASE_L:						\
	{								\
		volatile u32 *__ptr = (volatile u32 *)(ptr);		\
		asm volatile("xchgl %0,%1"				\
			     : "=r" (__x), "+m" (*__ptr)		\
			     : "0" (__x)				\
			     : "memory");				\
		break;							\
	}								\
	case __X86_CASE_Q:						\
	{								\
		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
		asm volatile("xchgq %0,%1"				\
			     : "=r" (__x), "+m" (*__ptr)		\
			     : "0" (__x)				\
			     : "memory");				\
		break;							\
	}								\
	default:							\
		__xchg_wrong_size();					\
	}								\
	__x;								\
})

#define xchg(ptr, v)							\
	__xchg((v), (ptr), sizeof(*ptr))

/*
 * 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.
 */
#define __raw_cmpxchg(ptr, old, new, size, lock)			\
({									\
	__typeof__(*(ptr)) __ret;					\
	__typeof__(*(ptr)) __old = (old);				\
	__typeof__(*(ptr)) __new = (new);				\
	switch (size) {							\
	case __X86_CASE_B:						\
	{								\
		volatile u8 *__ptr = (volatile u8 *)(ptr);		\
		asm volatile(lock "cmpxchgb %2,%1"			\
			     : "=a" (__ret), "+m" (*__ptr)		\
			     : "q" (__new), "0" (__old)			\
			     : "memory");				\
		break;							\
	}								\
	case __X86_CASE_W:						\
	{								\
		volatile u16 *__ptr = (volatile u16 *)(ptr);		\
		asm volatile(lock "cmpxchgw %2,%1"			\
			     : "=a" (__ret), "+m" (*__ptr)		\
			     : "r" (__new), "0" (__old)			\
			     : "memory");				\
		break;							\
	}								\
	case __X86_CASE_L:						\
	{								\
		volatile u32 *__ptr = (volatile u32 *)(ptr);		\
		asm volatile(lock "cmpxchgl %2,%1"			\
			     : "=a" (__ret), "+m" (*__ptr)		\
			     : "r" (__new), "0" (__old)			\
			     : "memory");				\
		break;							\
	}								\
	case __X86_CASE_Q:						\
	{								\
		volatile u64 *__ptr = (volatile u64 *)(ptr);		\
		asm volatile(lock "cmpxchgq %2,%1"			\
			     : "=a" (__ret), "+m" (*__ptr)		\
			     : "r" (__new), "0" (__old)			\
			     : "memory");				\
		break;							\
	}								\
	default:							\
		__cmpxchg_wrong_size();					\
	}								\
	__ret;								\
})

#define __cmpxchg(ptr, old, new, size)					\
	__raw_cmpxchg((ptr), (old), (new), (size), LOCK_PREFIX)

#define __sync_cmpxchg(ptr, old, new, size)				\
	__raw_cmpxchg((ptr), (old), (new), (size), "lock; ")

#define __cmpxchg_local(ptr, old, new, size)				\
	__raw_cmpxchg((ptr), (old), (new), (size), "")

#ifdef CONFIG_X86_32
# include "cmpxchg_32.h"
#else
# include "cmpxchg_64.h"
#endif

#ifdef __HAVE_ARCH_CMPXCHG
#define cmpxchg(ptr, old, new)						\
	__cmpxchg((ptr), (old), (new), sizeof(*ptr))

#define sync_cmpxchg(ptr, old, new)					\
	__sync_cmpxchg((ptr), (old), (new), sizeof(*ptr))

#define cmpxchg_local(ptr, old, new)					\
	__cmpxchg_local((ptr), (old), (new), sizeof(*ptr))
#endif

#define __xadd(ptr, inc, lock)						\
	({								\
	        __typeof__ (*(ptr)) __ret = (inc);			\
		switch (sizeof(*(ptr))) {				\
		case __X86_CASE_B:					\
			asm volatile (lock "xaddb %b0, %1\n"		\
				      : "+r" (__ret), "+m" (*(ptr))	\
				      : : "memory", "cc");		\
			break;						\
		case __X86_CASE_W:					\
			asm volatile (lock "xaddw %w0, %1\n"		\
				      : "+r" (__ret), "+m" (*(ptr))	\
				      : : "memory", "cc");		\
			break;						\
		case __X86_CASE_L:					\
			asm volatile (lock "xaddl %0, %1\n"		\
				      : "+r" (__ret), "+m" (*(ptr))	\
				      : : "memory", "cc");		\
			break;						\
		case __X86_CASE_Q:					\
			asm volatile (lock "xaddq %q0, %1\n"		\
				      : "+r" (__ret), "+m" (*(ptr))	\
				      : : "memory", "cc");		\
			break;						\
		default:						\
			__xadd_wrong_size();				\
		}							\
		__ret;							\
	})

/*
 * xadd() adds "inc" to "*ptr" and atomically returns the previous
 * value of "*ptr".
 *
 * xadd() is locked when multiple CPUs are online
 * xadd_sync() is always locked
 * xadd_local() is never locked
 */
#define xadd(ptr, inc)		__xadd((ptr), (inc), LOCK_PREFIX)
#define xadd_sync(ptr, inc)	__xadd((ptr), (inc), "lock; ")
#define xadd_local(ptr, inc)	__xadd((ptr), (inc), "")

#define __add(ptr, inc, lock)						\
	({								\
	        __typeof__ (*(ptr)) __ret = (inc);			\
		switch (sizeof(*(ptr))) {				\
		case __X86_CASE_B:					\
			asm volatile (lock "addb %b1, %0\n"		\
				      : "+m" (*(ptr)) : "ri" (inc)	\
				      : "memory", "cc");		\
			break;						\
		case __X86_CASE_W:					\
			asm volatile (lock "addw %w1, %0\n"		\
				      : "+m" (*(ptr)) : "ri" (inc)	\
				      : "memory", "cc");		\
			break;						\
		case __X86_CASE_L:					\
			asm volatile (lock "addl %1, %0\n"		\
				      : "+m" (*(ptr)) : "ri" (inc)	\
				      : "memory", "cc");		\
			break;						\
		case __X86_CASE_Q:					\
			asm volatile (lock "addq %1, %0\n"		\
				      : "+m" (*(ptr)) : "ri" (inc)	\
				      : "memory", "cc");		\
			break;						\
		default:						\
			__add_wrong_size();				\
		}							\
		__ret;							\
	})

/*
 * add_*() adds "inc" to "*ptr"
 *
 * __add() takes a lock prefix
 * add_smp() is locked when multiple CPUs are online
 * add_sync() is always locked
 */
#define add_smp(ptr, inc)	__add((ptr), (inc), LOCK_PREFIX)
#define add_sync(ptr, inc)	__add((ptr), (inc), "lock; ")

#endif	/* ASM_X86_CMPXCHG_H */