arch/arm/include/asm/atomic.h - kernel/msm-4.9 - Gitiles

 /*
  *  arch/arm/include/asm/atomic.h
  *
  *  Copyright (C) 1996 Russell King.
  *  Copyright (C) 2002 Deep Blue Solutions Ltd.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
 #ifndef __ASM_ARM_ATOMIC_H
 #define __ASM_ARM_ATOMIC_H

 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/system.h>

 #define ATOMIC_INIT(i)	{ (i) }

 #ifdef __KERNEL__

 /*
  * On ARM, ordinary assignment (str instruction) doesn't clear the local
  * strex/ldrex monitor on some implementations. The reason we can use it for
  * atomic_set() is the clrex or dummy strex done on every exception return.
  */
 #define atomic_read(v)	((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))

 #if __LINUX_ARM_ARCH__ >= 6

 /*
  * ARMv6 UP and SMP safe atomic ops.  We use load exclusive and
  * store exclusive to ensure that these are atomic.  We may loop
  * to ensure that the update happens.
  */
 static inline void atomic_add(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;

 	__asm__ __volatile__("@ atomic_add\n"
 "1:	ldrex	%0, [%2]\n"
 "	add	%0, %0, %3\n"
 "	strex	%1, %0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }

 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;

 	smp_mb();

 	__asm__ __volatile__("@ atomic_add_return\n"
 "1:	ldrex	%0, [%2]\n"
 "	add	%0, %0, %3\n"
 "	strex	%1, %0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");

 	smp_mb();

 	return result;
 }

 static inline void atomic_sub(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;

 	__asm__ __volatile__("@ atomic_sub\n"
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, %3\n"
 "	strex	%1, %0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 }

 static inline int atomic_sub_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;

 	smp_mb();

 	__asm__ __volatile__("@ atomic_sub_return\n"
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, %3\n"
 "	strex	%1, %0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");

 	smp_mb();

 	return result;
 }

 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
 	unsigned long oldval, res;

 	smp_mb();

 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
 		"ldrex	%1, [%2]\n"
 		"mov	%0, #0\n"
 		"teq	%1, %3\n"
 		"strexeq %0, %4, [%2]\n"
 		    : "=&r" (res), "=&r" (oldval)
 		    : "r" (&ptr->counter), "Ir" (old), "r" (new)
 		    : "cc");
 	} while (res);

 	smp_mb();

 	return oldval;
 }

 static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 {
 	unsigned long tmp, tmp2;

 	__asm__ __volatile__("@ atomic_clear_mask\n"
 "1:	ldrex	%0, [%2]\n"
 "	bic	%0, %0, %3\n"
 "	strex	%1, %0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (tmp), "=&r" (tmp2)
 	: "r" (addr), "Ir" (mask)
 	: "cc");
 }

 #else /* ARM_ARCH_6 */

 #ifdef CONFIG_SMP
 #error SMP not supported on pre-ARMv6 CPUs
 #endif

 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long flags;
 	int val;

 	raw_local_irq_save(flags);
 	val = v->counter;
 	v->counter = val += i;
 	raw_local_irq_restore(flags);

 	return val;
 }
 #define atomic_add(i, v)	(void) atomic_add_return(i, v)

 static inline int atomic_sub_return(int i, atomic_t *v)
 {
 	unsigned long flags;
 	int val;

 	raw_local_irq_save(flags);
 	val = v->counter;
 	v->counter = val -= i;
 	raw_local_irq_restore(flags);

 	return val;
 }
 #define atomic_sub(i, v)	(void) atomic_sub_return(i, v)

 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	int ret;
 	unsigned long flags;

 	raw_local_irq_save(flags);
 	ret = v->counter;
 	if (likely(ret == old))
 		v->counter = new;
 	raw_local_irq_restore(flags);

 	return ret;
 }

 static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 {
 	unsigned long flags;

 	raw_local_irq_save(flags);
 	*addr &= ~mask;
 	raw_local_irq_restore(flags);
 }

 #endif /* __LINUX_ARM_ARCH__ */

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

 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)

 #define atomic_inc(v)		atomic_add(1, v)
 #define atomic_dec(v)		atomic_sub(1, v)

 #define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
 #define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
 #define atomic_inc_return(v)    (atomic_add_return(1, v))
 #define atomic_dec_return(v)    (atomic_sub_return(1, v))
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)

 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)

 #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()

 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	u64 __aligned(8) counter;
 } atomic64_t;

 #define ATOMIC64_INIT(i) { (i) }

 static inline u64 atomic64_read(atomic64_t *v)
 {
 	u64 result;

 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrexd	%0, %H0, [%1]"
 	: "=&r" (result)
 	: "r" (&v->counter)
 	);

 	return result;
 }

 static inline void atomic64_set(atomic64_t *v, u64 i)
 {
 	u64 tmp;

 	__asm__ __volatile__("@ atomic64_set\n"
 "1:	ldrexd	%0, %H0, [%1]\n"
 "	strexd	%0, %2, %H2, [%1]\n"
 "	teq	%0, #0\n"
 "	bne	1b"
 	: "=&r" (tmp)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }

 static inline void atomic64_add(u64 i, atomic64_t *v)
 {
 	u64 result;
 	unsigned long tmp;

 	__asm__ __volatile__("@ atomic64_add\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	adds	%0, %0, %3\n"
 "	adc	%H0, %H0, %H3\n"
 "	strexd	%1, %0, %H0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }

 static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 {
 	u64 result;
 	unsigned long tmp;

 	smp_mb();

 	__asm__ __volatile__("@ atomic64_add_return\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	adds	%0, %0, %3\n"
 "	adc	%H0, %H0, %H3\n"
 "	strexd	%1, %0, %H0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "r" (i)
 	: "cc");

 	smp_mb();

 	return result;
 }

 static inline void atomic64_sub(u64 i, atomic64_t *v)
 {
 	u64 result;
 	unsigned long tmp;

 	__asm__ __volatile__("@ atomic64_sub\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	subs	%0, %0, %3\n"
 "	sbc	%H0, %H0, %H3\n"
 "	strexd	%1, %0, %H0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "r" (i)
 	: "cc");
 }

 static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
 {
 	u64 result;
 	unsigned long tmp;

 	smp_mb();

 	__asm__ __volatile__("@ atomic64_sub_return\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	subs	%0, %0, %3\n"
 "	sbc	%H0, %H0, %H3\n"
 "	strexd	%1, %0, %H0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter), "r" (i)
 	: "cc");

 	smp_mb();

 	return result;
 }

 static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
 {
 	u64 oldval;
 	unsigned long res;

 	smp_mb();

 	do {
 		__asm__ __volatile__("@ atomic64_cmpxchg\n"
 		"ldrexd		%1, %H1, [%2]\n"
 		"mov		%0, #0\n"
 		"teq		%1, %3\n"
 		"teqeq		%H1, %H3\n"
 		"strexdeq	%0, %4, %H4, [%2]"
 		: "=&r" (res), "=&r" (oldval)
 		: "r" (&ptr->counter), "r" (old), "r" (new)
 		: "cc");
 	} while (res);

 	smp_mb();

 	return oldval;
 }

 static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
 {
 	u64 result;
 	unsigned long tmp;

 	smp_mb();

 	__asm__ __volatile__("@ atomic64_xchg\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	strexd	%1, %3, %H3, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&ptr->counter), "r" (new)
 	: "cc");

 	smp_mb();

 	return result;
 }

 static inline u64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	u64 result;
 	unsigned long tmp;

 	smp_mb();

 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	subs	%0, %0, #1\n"
 "	sbc	%H0, %H0, #0\n"
 "	teq	%H0, #0\n"
 "	bmi	2f\n"
 "	strexd	%1, %0, %H0, [%2]\n"
 "	teq	%1, #0\n"
 "	bne	1b\n"
 "2:"
 	: "=&r" (result), "=&r" (tmp)
 	: "r" (&v->counter)
 	: "cc");

 	smp_mb();

 	return result;
 }

 static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 {
 	u64 val;
 	unsigned long tmp;
 	int ret = 1;

 	smp_mb();

 	__asm__ __volatile__("@ atomic64_add_unless\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
 "	teq	%0, %4\n"
 "	teqeq	%H0, %H4\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
 "	adds	%0, %0, %5\n"
 "	adc	%H0, %H0, %H5\n"
 "	strexd	%2, %0, %H0, [%3]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
 "2:"
 	: "=&r" (val), "=&r" (ret), "=&r" (tmp)
 	: "r" (&v->counter), "r" (u), "r" (a)
 	: "cc");

 	if (ret)
 		smp_mb();

 	return ret;
 }

 #define atomic64_add_negative(a, v)	(atomic64_add_return((a), (v)) < 0)
 #define atomic64_inc(v)			atomic64_add(1LL, (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1LL, (v))
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)

 #else /* !CONFIG_GENERIC_ATOMIC64 */
 #include <asm-generic/atomic64.h>
 #endif
 #include <asm-generic/atomic-long.h>
 #endif
 #endif
	/*
	* arch/arm/include/asm/atomic.h
	*
	* Copyright (C) 1996 Russell King.
	* Copyright (C) 2002 Deep Blue Solutions Ltd.
	*
	* This program is free software; you can redistribute it and/or modify
	* it under the terms of the GNU General Public License version 2 as
	* published by the Free Software Foundation.
	*/
	#ifndef __ASM_ARM_ATOMIC_H
	#define __ASM_ARM_ATOMIC_H

	#include <linux/compiler.h>
	#include <linux/types.h>
	#include <asm/system.h>

	#define ATOMIC_INIT(i) { (i) }

	#ifdef __KERNEL__

	/*
	* On ARM, ordinary assignment (str instruction) doesn't clear the local
	* strex/ldrex monitor on some implementations. The reason we can use it for
	* atomic_set() is the clrex or dummy strex done on every exception return.
	*/
	#define atomic_read(v) ((v)->counter)
	#define atomic_set(v,i) (((v)->counter) = (i))

	#if __LINUX_ARM_ARCH__ >= 6

	/*
	* ARMv6 UP and SMP safe atomic ops. We use load exclusive and
	* store exclusive to ensure that these are atomic. We may loop
	* to ensure that the update happens.
	*/
	static inline void atomic_add(int i, atomic_t *v)
	{
	unsigned long tmp;
	int result;

	__asm__ __volatile__("@ atomic_add\n"
	"1: ldrex %0, [%2]\n"
	" add %0, %0, %3\n"
	" strex %1, %0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "Ir" (i)
	: "cc");
	}

	static inline int atomic_add_return(int i, atomic_t *v)
	{
	unsigned long tmp;
	int result;

	smp_mb();

	__asm__ __volatile__("@ atomic_add_return\n"
	"1: ldrex %0, [%2]\n"
	" add %0, %0, %3\n"
	" strex %1, %0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "Ir" (i)
	: "cc");

	smp_mb();

	return result;
	}

	static inline void atomic_sub(int i, atomic_t *v)
	{
	unsigned long tmp;
	int result;

	__asm__ __volatile__("@ atomic_sub\n"
	"1: ldrex %0, [%2]\n"
	" sub %0, %0, %3\n"
	" strex %1, %0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "Ir" (i)
	: "cc");
	}

	static inline int atomic_sub_return(int i, atomic_t *v)
	{
	unsigned long tmp;
	int result;

	smp_mb();

	__asm__ __volatile__("@ atomic_sub_return\n"
	"1: ldrex %0, [%2]\n"
	" sub %0, %0, %3\n"
	" strex %1, %0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "Ir" (i)
	: "cc");

	smp_mb();

	return result;
	}

	static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
	{
	unsigned long oldval, res;

	smp_mb();

	do {
	__asm__ __volatile__("@ atomic_cmpxchg\n"
	"ldrex %1, [%2]\n"
	"mov %0, #0\n"
	"teq %1, %3\n"
	"strexeq %0, %4, [%2]\n"
	: "=&r" (res), "=&r" (oldval)
	: "r" (&ptr->counter), "Ir" (old), "r" (new)
	: "cc");
	} while (res);

	smp_mb();

	return oldval;
	}

	static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
	{
	unsigned long tmp, tmp2;

	__asm__ __volatile__("@ atomic_clear_mask\n"
	"1: ldrex %0, [%2]\n"
	" bic %0, %0, %3\n"
	" strex %1, %0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (tmp), "=&r" (tmp2)
	: "r" (addr), "Ir" (mask)
	: "cc");
	}

	#else /* ARM_ARCH_6 */

	#ifdef CONFIG_SMP
	#error SMP not supported on pre-ARMv6 CPUs
	#endif

	static inline int atomic_add_return(int i, atomic_t *v)
	{
	unsigned long flags;
	int val;

	raw_local_irq_save(flags);
	val = v->counter;
	v->counter = val += i;
	raw_local_irq_restore(flags);

	return val;
	}
	#define atomic_add(i, v) (void) atomic_add_return(i, v)

	static inline int atomic_sub_return(int i, atomic_t *v)
	{
	unsigned long flags;
	int val;

	raw_local_irq_save(flags);
	val = v->counter;
	v->counter = val -= i;
	raw_local_irq_restore(flags);

	return val;
	}
	#define atomic_sub(i, v) (void) atomic_sub_return(i, v)

	static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
	{
	int ret;
	unsigned long flags;

	raw_local_irq_save(flags);
	ret = v->counter;
	if (likely(ret == old))
	v->counter = new;
	raw_local_irq_restore(flags);

	return ret;
	}

	static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
	{
	unsigned long flags;

	raw_local_irq_save(flags);
	*addr &= ~mask;
	raw_local_irq_restore(flags);
	}

	#endif /* __LINUX_ARM_ARCH__ */

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

	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)

	#define atomic_inc(v) atomic_add(1, v)
	#define atomic_dec(v) atomic_sub(1, v)

	#define atomic_inc_and_test(v) (atomic_add_return(1, v) == 0)
	#define atomic_dec_and_test(v) (atomic_sub_return(1, v) == 0)
	#define atomic_inc_return(v) (atomic_add_return(1, v))
	#define atomic_dec_return(v) (atomic_sub_return(1, v))
	#define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)

	#define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)

	#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()

	#ifndef CONFIG_GENERIC_ATOMIC64
	typedef struct {
	u64 __aligned(8) counter;
	} atomic64_t;

	#define ATOMIC64_INIT(i) { (i) }

	static inline u64 atomic64_read(atomic64_t *v)
	{
	u64 result;

	__asm__ __volatile__("@ atomic64_read\n"
	" ldrexd %0, %H0, [%1]"
	: "=&r" (result)
	: "r" (&v->counter)
	);

	return result;
	}

	static inline void atomic64_set(atomic64_t *v, u64 i)
	{
	u64 tmp;

	__asm__ __volatile__("@ atomic64_set\n"
	"1: ldrexd %0, %H0, [%1]\n"
	" strexd %0, %2, %H2, [%1]\n"
	" teq %0, #0\n"
	" bne 1b"
	: "=&r" (tmp)
	: "r" (&v->counter), "r" (i)
	: "cc");
	}

	static inline void atomic64_add(u64 i, atomic64_t *v)
	{
	u64 result;
	unsigned long tmp;

	__asm__ __volatile__("@ atomic64_add\n"
	"1: ldrexd %0, %H0, [%2]\n"
	" adds %0, %0, %3\n"
	" adc %H0, %H0, %H3\n"
	" strexd %1, %0, %H0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "r" (i)
	: "cc");
	}

	static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
	{
	u64 result;
	unsigned long tmp;

	smp_mb();

	__asm__ __volatile__("@ atomic64_add_return\n"
	"1: ldrexd %0, %H0, [%2]\n"
	" adds %0, %0, %3\n"
	" adc %H0, %H0, %H3\n"
	" strexd %1, %0, %H0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "r" (i)
	: "cc");

	smp_mb();

	return result;
	}

	static inline void atomic64_sub(u64 i, atomic64_t *v)
	{
	u64 result;
	unsigned long tmp;

	__asm__ __volatile__("@ atomic64_sub\n"
	"1: ldrexd %0, %H0, [%2]\n"
	" subs %0, %0, %3\n"
	" sbc %H0, %H0, %H3\n"
	" strexd %1, %0, %H0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "r" (i)
	: "cc");
	}

	static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
	{
	u64 result;
	unsigned long tmp;

	smp_mb();

	__asm__ __volatile__("@ atomic64_sub_return\n"
	"1: ldrexd %0, %H0, [%2]\n"
	" subs %0, %0, %3\n"
	" sbc %H0, %H0, %H3\n"
	" strexd %1, %0, %H0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter), "r" (i)
	: "cc");

	smp_mb();

	return result;
	}

	static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
	{
	u64 oldval;
	unsigned long res;

	smp_mb();

	do {
	__asm__ __volatile__("@ atomic64_cmpxchg\n"
	"ldrexd %1, %H1, [%2]\n"
	"mov %0, #0\n"
	"teq %1, %3\n"
	"teqeq %H1, %H3\n"
	"strexdeq %0, %4, %H4, [%2]"
	: "=&r" (res), "=&r" (oldval)
	: "r" (&ptr->counter), "r" (old), "r" (new)
	: "cc");
	} while (res);

	smp_mb();

	return oldval;
	}

	static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
	{
	u64 result;
	unsigned long tmp;

	smp_mb();

	__asm__ __volatile__("@ atomic64_xchg\n"
	"1: ldrexd %0, %H0, [%2]\n"
	" strexd %1, %3, %H3, [%2]\n"
	" teq %1, #0\n"
	" bne 1b"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&ptr->counter), "r" (new)
	: "cc");

	smp_mb();

	return result;
	}

	static inline u64 atomic64_dec_if_positive(atomic64_t *v)
	{
	u64 result;
	unsigned long tmp;

	smp_mb();

	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
	"1: ldrexd %0, %H0, [%2]\n"
	" subs %0, %0, #1\n"
	" sbc %H0, %H0, #0\n"
	" teq %H0, #0\n"
	" bmi 2f\n"
	" strexd %1, %0, %H0, [%2]\n"
	" teq %1, #0\n"
	" bne 1b\n"
	"2:"
	: "=&r" (result), "=&r" (tmp)
	: "r" (&v->counter)
	: "cc");

	smp_mb();

	return result;
	}

	static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
	{
	u64 val;
	unsigned long tmp;
	int ret = 1;

	smp_mb();

	__asm__ __volatile__("@ atomic64_add_unless\n"
	"1: ldrexd %0, %H0, [%3]\n"
	" teq %0, %4\n"
	" teqeq %H0, %H4\n"
	" moveq %1, #0\n"
	" beq 2f\n"
	" adds %0, %0, %5\n"
	" adc %H0, %H0, %H5\n"
	" strexd %2, %0, %H0, [%3]\n"
	" teq %2, #0\n"
	" bne 1b\n"
	"2:"
	: "=&r" (val), "=&r" (ret), "=&r" (tmp)
	: "r" (&v->counter), "r" (u), "r" (a)
	: "cc");

	if (ret)
	smp_mb();

	return ret;
	}

	#define atomic64_add_negative(a, v) (atomic64_add_return((a), (v)) < 0)
	#define atomic64_inc(v) atomic64_add(1LL, (v))
	#define atomic64_inc_return(v) atomic64_add_return(1LL, (v))
	#define atomic64_inc_and_test(v) (atomic64_inc_return(v) == 0)
	#define atomic64_sub_and_test(a, v) (atomic64_sub_return((a), (v)) == 0)
	#define atomic64_dec(v) atomic64_sub(1LL, (v))
	#define atomic64_dec_return(v) atomic64_sub_return(1LL, (v))
	#define atomic64_dec_and_test(v) (atomic64_dec_return((v)) == 0)
	#define atomic64_inc_not_zero(v) atomic64_add_unless((v), 1LL, 0LL)

	#else /* !CONFIG_GENERIC_ATOMIC64 */
	#include <asm-generic/atomic64.h>
	#endif
	#include <asm-generic/atomic-long.h>
	#endif
	#endif