#ifndef __ARCH_S390_ATOMIC__
#define __ARCH_S390_ATOMIC__

/*
 *  include/asm-s390/atomic.h
 *
 *  S390 version
 *    Copyright (C) 1999-2005 IBM Deutschland Entwicklung GmbH, IBM Corporation
 *    Author(s): Martin Schwidefsky (schwidefsky@de.ibm.com),
 *               Denis Joseph Barrow,
 *		 Arnd Bergmann (arndb@de.ibm.com)
 *
 *  Derived from "include/asm-i386/bitops.h"
 *    Copyright (C) 1992, Linus Torvalds
 *
 */

/*
 * Atomic operations that C can't guarantee us.  Useful for
 * resource counting etc..
 * S390 uses 'Compare And Swap' for atomicity in SMP enviroment
 */

typedef struct {
	volatile int counter;
} __attribute__ ((aligned (4))) atomic_t;
#define ATOMIC_INIT(i)  { (i) }

#ifdef __KERNEL__

#define __CS_LOOP(ptr, op_val, op_string) ({				\
	typeof(ptr->counter) old_val, new_val;				\
        __asm__ __volatile__("   l     %0,0(%3)\n"			\
                             "0: lr    %1,%0\n"				\
                             op_string "  %1,%4\n"			\
                             "   cs    %0,%1,0(%3)\n"			\
                             "   jl    0b"				\
                             : "=&d" (old_val), "=&d" (new_val),	\
			       "=m" (((atomic_t *)(ptr))->counter)	\
			     : "a" (ptr), "d" (op_val),			\
			       "m" (((atomic_t *)(ptr))->counter)	\
			     : "cc", "memory" );			\
	new_val;							\
})
#define atomic_read(v)          ((v)->counter)
#define atomic_set(v,i)         (((v)->counter) = (i))

static __inline__ int atomic_add_return(int i, atomic_t * v)
{
	return __CS_LOOP(v, i, "ar");
}
#define atomic_add(_i, _v)		atomic_add_return(_i, _v)
#define atomic_add_negative(_i, _v)	(atomic_add_return(_i, _v) < 0)
#define atomic_inc(_v)			atomic_add_return(1, _v)
#define atomic_inc_return(_v)		atomic_add_return(1, _v)
#define atomic_inc_and_test(_v)		(atomic_add_return(1, _v) == 0)

static __inline__ int atomic_sub_return(int i, atomic_t * v)
{
	return __CS_LOOP(v, i, "sr");
}
#define atomic_sub(_i, _v)		atomic_sub_return(_i, _v)
#define atomic_sub_and_test(_i, _v)	(atomic_sub_return(_i, _v) == 0)
#define atomic_dec(_v)			atomic_sub_return(1, _v)
#define atomic_dec_return(_v)		atomic_sub_return(1, _v)
#define atomic_dec_and_test(_v)		(atomic_sub_return(1, _v) == 0)

static __inline__ void atomic_clear_mask(unsigned long mask, atomic_t * v)
{
	       __CS_LOOP(v, ~mask, "nr");
}

static __inline__ void atomic_set_mask(unsigned long mask, atomic_t * v)
{
	       __CS_LOOP(v, mask, "or");
}

#define atomic_xchg(v, new) (xchg(&((v)->counter), new))

static __inline__ int atomic_cmpxchg(atomic_t *v, int old, int new)
{
	__asm__ __volatile__("  cs   %0,%3,0(%2)\n"
			     : "+d" (old), "=m" (v->counter)
			     : "a" (v), "d" (new), "m" (v->counter)
			     : "cc", "memory" );
	return old;
}

static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
{
	int c, old;

	c = atomic_read(v);
	while (c != u && (old = atomic_cmpxchg(v, c, c + a)) != c)
		c = old;
	return c != u;
}

#define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)

#undef __CS_LOOP

#ifdef __s390x__
typedef struct {
	volatile long long counter;
} __attribute__ ((aligned (8))) atomic64_t;
#define ATOMIC64_INIT(i)  { (i) }

#define __CSG_LOOP(ptr, op_val, op_string) ({				\
	typeof(ptr->counter) old_val, new_val;				\
        __asm__ __volatile__("   lg    %0,0(%3)\n"			\
                             "0: lgr   %1,%0\n"				\
                             op_string "  %1,%4\n"			\
                             "   csg   %0,%1,0(%3)\n"			\
                             "   jl    0b"				\
                             : "=&d" (old_val), "=&d" (new_val),	\
			       "=m" (((atomic_t *)(ptr))->counter)	\
			     : "a" (ptr), "d" (op_val),			\
			       "m" (((atomic_t *)(ptr))->counter)	\
			     : "cc", "memory" );			\
	new_val;							\
})
#define atomic64_read(v)          ((v)->counter)
#define atomic64_set(v,i)         (((v)->counter) = (i))

static __inline__ long long atomic64_add_return(long long i, atomic64_t * v)
{
	return __CSG_LOOP(v, i, "agr");
}
#define atomic64_add(_i, _v)		atomic64_add_return(_i, _v)
#define atomic64_add_negative(_i, _v)	(atomic64_add_return(_i, _v) < 0)
#define atomic64_inc(_v)		atomic64_add_return(1, _v)
#define atomic64_inc_return(_v)		atomic64_add_return(1, _v)
#define atomic64_inc_and_test(_v)	(atomic64_add_return(1, _v) == 0)

static __inline__ long long atomic64_sub_return(long long i, atomic64_t * v)
{
	return __CSG_LOOP(v, i, "sgr");
}
#define atomic64_sub(_i, _v)		atomic64_sub_return(_i, _v)
#define atomic64_sub_and_test(_i, _v)	(atomic64_sub_return(_i, _v) == 0)
#define atomic64_dec(_v)		atomic64_sub_return(1, _v)
#define atomic64_dec_return(_v)		atomic64_sub_return(1, _v)
#define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)

static __inline__ void atomic64_clear_mask(unsigned long mask, atomic64_t * v)
{
	       __CSG_LOOP(v, ~mask, "ngr");
}

static __inline__ void atomic64_set_mask(unsigned long mask, atomic64_t * v)
{
	       __CSG_LOOP(v, mask, "ogr");
}

static __inline__ long long atomic64_cmpxchg(atomic64_t *v,
					     long long old, long long new)
{
	__asm__ __volatile__("  csg  %0,%3,0(%2)\n"
			     : "+d" (old), "=m" (v->counter)
			     : "a" (v), "d" (new), "m" (v->counter)
			     : "cc", "memory" );
	return old;
}

static __inline__ int atomic64_add_unless(atomic64_t *v,
					  long long a, long long u)
{
	long long c, old;

	c = atomic64_read(v);
	while (c != u && (old = atomic64_cmpxchg(v, c, c + a)) != c)
		c = old;
	return c != u;
}

#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1, 0)

#undef __CSG_LOOP
#endif

#define smp_mb__before_atomic_dec()	smp_mb()
#define smp_mb__after_atomic_dec()	smp_mb()
#define smp_mb__before_atomic_inc()	smp_mb()
#define smp_mb__after_atomic_inc()	smp_mb()

#include <asm-generic/atomic.h>
#endif /* __KERNEL__ */
#endif /* __ARCH_S390_ATOMIC__  */