/*-
 * Copyright (c) 1998 Doug Rabson
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE AUTHOR OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 * $FreeBSD: src/sys/i386/include/atomic.h,v 1.47.2.2.2.1 2010/02/10 00:26:20 kensmith Exp $
 */
/*
 * Portions copyright (c) 2010, Intel Corporation
 */

#ifndef __ATOMIC_H__
#define	__ATOMIC_H__

/*
 * Various simple operations on memory, each of which is atomic in the
 * presence of interrupts and multiple processors.
 *
 * atomic_set_char(P, V)	(*(u_char *)(P) |= (V))
 * atomic_clear_char(P, V)	(*(u_char *)(P) &= ~(V))
 * atomic_add_char(P, V)	(*(u_char *)(P) += (V))
 * atomic_subtract_char(P, V)	(*(u_char *)(P) -= (V))
 *
 * atomic_set_short(P, V)	(*(u_short *)(P) |= (V))
 * atomic_clear_short(P, V)	(*(u_short *)(P) &= ~(V))
 * atomic_add_short(P, V)	(*(u_short *)(P) += (V))
 * atomic_subtract_short(P, V)	(*(u_short *)(P) -= (V))
 *
 * atomic_set_int(P, V)		(*(u_int *)(P) |= (V))
 * atomic_clear_int(P, V)	(*(u_int *)(P) &= ~(V))
 * atomic_add_int(P, V)		(*(u_int *)(P) += (V))
 * atomic_subtract_int(P, V)	(*(u_int *)(P) -= (V))
 * atomic_readandclear_int(P)	(return (*(u_int *)(P)); *(u_int *)(P) = 0;)
 *
 * atomic_set_long(P, V)	(*(u_long *)(P) |= (V))
 * atomic_clear_long(P, V)	(*(u_long *)(P) &= ~(V))
 * atomic_add_long(P, V)	(*(u_long *)(P) += (V))
 * atomic_subtract_long(P, V)	(*(u_long *)(P) -= (V))
 * atomic_readandclear_long(P)	(return (*(u_long *)(P)); *(u_long *)(P) = 0;)
 */

/*
 * The above functions are expanded inline in the statically-linked
 * kernel.  Lock prefixes are generated if an SMP kernel is being
 * built.
 *
 * Kernel modules call real functions which are built into the kernel.
 * This allows kernel modules to be portable between UP and SMP systems.
 */

/* all operations will be defined only for 'int's */
#define atomic_t u_int

#define	MPLOCKED	"lock ; "

/*
 * The assembly is volatilized to avoid code chunk removal by the compiler.
 * GCC aggressively reorders operations and memory clobbering is necessary
 * in order to avoid that for memory barriers.
 */
#define	ATOMIC_ASM(NAME, TYPE, OP, CONS, V)		\
static __inline void					\
atomic_##NAME##_##TYPE(volatile u_##TYPE *p, u_##TYPE v)\
{							\
	__asm __volatile(MPLOCKED OP			\
	: "=m" (*p)					\
	: CONS (V), "m" (*p));				\
}							\
							\
static __inline void					\
atomic_##NAME##_barr_##TYPE(volatile u_##TYPE *p, u_##TYPE v)\
{							\
	__asm __volatile(MPLOCKED OP			\
	: "=m" (*p)					\
	: CONS (V), "m" (*p)				\
	: "memory");					\
}							\
struct __hack

/*
 * Atomically add the value of v to the integer pointed to by p and return
 * the previous value of *p.
 */
static __inline u_int
atomic_fetchadd_int(volatile u_int *p, u_int v)
{

	__asm __volatile(
	"	" MPLOCKED "		"
	"	xaddl	%0, %1 ;	"
	"# atomic_fetchadd_int"
	: "+r" (v),			/* 0 (result) */
	  "=m" (*p)			/* 1 */
	: "m" (*p));			/* 2 */

	return (v);
}

#define	ATOMIC_STORE_LOAD(TYPE, LOP, SOP)		\
static __inline u_##TYPE				\
atomic_load_acq_##TYPE(volatile u_##TYPE *p)		\
{							\
	u_##TYPE res;					\
							\
	__asm __volatile(MPLOCKED LOP			\
	: "=a" (res),			/* 0 */		\
	  "=m" (*p)			/* 1 */		\
	: "m" (*p)			/* 2 */		\
	: "memory");					\
							\
	return (res);					\
}							\
							\
/*							\
 * The XCHG instruction asserts LOCK automagically.	\
 */							\
static __inline void					\
atomic_store_rel_##TYPE(volatile u_##TYPE *p, u_##TYPE v)\
{							\
	__asm __volatile(SOP				\
	: "=m" (*p),			/* 0 */		\
	  "+r" (v)			/* 1 */		\
	: "m" (*p)			/* 2 */		\
	: "memory");					\
}							\
struct __hack

ATOMIC_ASM(set,	     int,   "orl %1,%0",   "ir",  v);
ATOMIC_ASM(clear,    int,   "andl %1,%0",  "ir", ~v);
ATOMIC_ASM(add,	     int,   "addl %1,%0",  "ir",  v);
ATOMIC_ASM(subtract, int,   "subl %1,%0",  "ir",  v);

ATOMIC_STORE_LOAD(int,	"cmpxchgl %0,%1",  "xchgl %1,%0");

#undef ATOMIC_ASM
#undef ATOMIC_STORE_LOAD

/* Read the current value and store a zero in the destination. */
static __inline u_int
atomic_readandclear_int(volatile u_int *addr)
{
	u_int res;

	res = 0;
	__asm __volatile(
	"	xchgl	%1,%0 ;		"
	"# atomic_readandclear_int"
	: "+r" (res),			/* 0 */
	  "=m" (*addr)			/* 1 */
	: "m" (*addr));

	return (res);
}


#define atomic_read(atom)          atomic_load_acq_int(atom)
#define atomic_inc(atom)           atomic_add_int((atom), 1)
#define atomic_dec(atom)           atomic_subtract_int((atom), 1)
#define atomic_set(atom, val)      atomic_set_int((atom), (val))

#endif /* __ATOMIC_H__ */