Merge branch 'locking-arch-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull arch atomic cleanups from Ingo Molnar:
 "This is a series kept separate from the main locking tree, which
  cleans up and improves various details in the atomics type handling:

   - Remove the unused atomic_or_long() method

   - Consolidate and compress atomic ops implementations between
     architectures, to reduce linecount and to make it easier to add new
     ops.

   - Rewrite generic atomic support to only require cmpxchg() from an
     architecture - generate all other methods from that"

* 'locking-arch-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (23 commits)
  locking,arch: Use ACCESS_ONCE() instead of cast to volatile in atomic_read()
  locking, mips: Fix atomics
  locking, sparc64: Fix atomics
  locking,arch: Rewrite generic atomic support
  locking,arch,xtensa: Fold atomic_ops
  locking,arch,sparc: Fold atomic_ops
  locking,arch,sh: Fold atomic_ops
  locking,arch,powerpc: Fold atomic_ops
  locking,arch,parisc: Fold atomic_ops
  locking,arch,mn10300: Fold atomic_ops
  locking,arch,mips: Fold atomic_ops
  locking,arch,metag: Fold atomic_ops
  locking,arch,m68k: Fold atomic_ops
  locking,arch,m32r: Fold atomic_ops
  locking,arch,ia64: Fold atomic_ops
  locking,arch,hexagon: Fold atomic_ops
  locking,arch,cris: Fold atomic_ops
  locking,arch,avr32: Fold atomic_ops
  locking,arch,arm64: Fold atomic_ops
  locking,arch,arm: Fold atomic_ops
  ...

30 files changed, 1462 insertions, 2172 deletions

diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index ed60a1ee1ed3..8f8eafbedd7c 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -17,8 +17,8 @@
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }
 
-#define atomic_read(v)		(*(volatile int *)&(v)->counter)
-#define atomic64_read(v)	(*(volatile long *)&(v)->counter)
+#define atomic_read(v)		ACCESS_ONCE((v)->counter)
+#define atomic64_read(v)	ACCESS_ONCE((v)->counter)
 
 #define atomic_set(v,i)		((v)->counter = (i))
 #define atomic64_set(v,i)	((v)->counter = (i))
@@ -29,145 +29,92 @@
  * branch back to restart the operation.
  */
 
-static __inline__ void atomic_add(int i, atomic_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	addl %0,%2,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
-}
-
-static __inline__ void atomic64_add(long i, atomic64_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	addq %0,%2,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
-}
-
-static __inline__ void atomic_sub(int i, atomic_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	subl %0,%2,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
+#define ATOMIC_OP(op)							\
+static __inline__ void atomic_##op(int i, atomic_t * v)			\
+{									\
+	unsigned long temp;						\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %0,%1\n"						\
+	"	" #op "l %0,%2,%0\n"					\
+	"	stl_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter)				\
+	:"Ir" (i), "m" (v->counter));					\
+}									\
+
+#define ATOMIC_OP_RETURN(op)						\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	long temp, result;						\
+	smp_mb();							\
+	__asm__ __volatile__(						\
+	"1:	ldl_l %0,%1\n"						\
+	"	" #op "l %0,%3,%2\n"					\
+	"	" #op "l %0,%3,%0\n"					\
+	"	stl_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_mb();							\
+	return result;							\
 }
 
-static __inline__ void atomic64_sub(long i, atomic64_t * v)
-{
-	unsigned long temp;
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	subq %0,%2,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter)
-	:"Ir" (i), "m" (v->counter));
-}
-
-
-/*
- * Same as above, but return the result value
- */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	addl %0,%3,%2\n"
-	"	addl %0,%3,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
+#define ATOMIC64_OP(op)							\
+static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
+{									\
+	unsigned long temp;						\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %0,%1\n"						\
+	"	" #op "q %0,%2,%0\n"					\
+	"	stq_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter)				\
+	:"Ir" (i), "m" (v->counter));					\
+}									\
+
+#define ATOMIC64_OP_RETURN(op)						\
+static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	\
+{									\
+	long temp, result;						\
+	smp_mb();							\
+	__asm__ __volatile__(						\
+	"1:	ldq_l %0,%1\n"						\
+	"	" #op "q %0,%3,%2\n"					\
+	"	" #op "q %0,%3,%0\n"					\
+	"	stq_c %0,%1\n"						\
+	"	beq %0,2f\n"						\
+	".subsection 2\n"						\
+	"2:	br 1b\n"						\
+	".previous"							\
+	:"=&r" (temp), "=m" (v->counter), "=&r" (result)		\
+	:"Ir" (i), "m" (v->counter) : "memory");			\
+	smp_mb();							\
+	return result;							\
 }
 
-static __inline__ long atomic64_add_return(long i, atomic64_t * v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	addq %0,%3,%2\n"
-	"	addq %0,%3,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
-}
+#define ATOMIC_OPS(opg)							\
+	ATOMIC_OP(opg)							\
+	ATOMIC_OP_RETURN(opg)						\
+	ATOMIC64_OP(opg)						\
+	ATOMIC64_OP_RETURN(opg)
 
-static __inline__ long atomic_sub_return(int i, atomic_t * v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldl_l %0,%1\n"
-	"	subl %0,%3,%2\n"
-	"	subl %0,%3,%0\n"
-	"	stl_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
-}
+ATOMIC_OPS(add)
+ATOMIC_OPS(sub)
 
-static __inline__ long atomic64_sub_return(long i, atomic64_t * v)
-{
-	long temp, result;
-	smp_mb();
-	__asm__ __volatile__(
-	"1:	ldq_l %0,%1\n"
-	"	subq %0,%3,%2\n"
-	"	subq %0,%3,%0\n"
-	"	stq_c %0,%1\n"
-	"	beq %0,2f\n"
-	".subsection 2\n"
-	"2:	br 1b\n"
-	".previous"
-	:"=&r" (temp), "=m" (v->counter), "=&r" (result)
-	:"Ir" (i), "m" (v->counter) : "memory");
-	smp_mb();
-	return result;
-}
+#undef ATOMIC_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 #define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), old, new))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 83f03ca6caf6..173f303a868f 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -25,79 +25,36 @@
 
 #define atomic_set(v, i) (((v)->counter) = (i))
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	add     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-}
-
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	sub     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-}
-
-/* add and also return the new value */
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	add     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-
-	return temp;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	sub     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(&v->counter), "ir"(i)
-	: "cc");
-
-	return temp;
-}
-
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned int temp;
-
-	__asm__ __volatile__(
-	"1:	llock   %0, [%1]	\n"
-	"	bic     %0, %0, %2	\n"
-	"	scond   %0, [%1]	\n"
-	"	bnz     1b		\n"
-	: "=&r"(temp)
-	: "r"(addr), "ir"(mask)
-	: "cc");
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned int temp;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %0, [%1]	\n"				\
+	"	" #asm_op " %0, %0, %2	\n"				\
+	"	scond   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(temp)	/* Early clobber, to prevent reg reuse */	\
+	: "r"(&v->counter), "ir"(i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned int temp;						\
+									\
+	__asm__ __volatile__(						\
+	"1:	llock   %0, [%1]	\n"				\
+	"	" #asm_op " %0, %0, %2	\n"				\
+	"	scond   %0, [%1]	\n"				\
+	"	bnz     1b		\n"				\
+	: "=&r"(temp)							\
+	: "r"(&v->counter), "ir"(i)					\
+	: "cc");							\
+									\
+	return temp;							\
 }
 
 #else	/* !CONFIG_ARC_HAS_LLSC */
@@ -126,6 +83,7 @@ static inline void atomic_set(atomic_t *v, int i)
 	v->counter = i;
 	atomic_ops_unlock(flags);
 }
+
 #endif
 
 /*
@@ -133,62 +91,46 @@ static inline void atomic_set(atomic_t *v, int i)
  * Locking would change to irq-disabling only (UP) and spinlocks (SMP)
  */
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	atomic_ops_lock(flags);
-	v->counter += i;
-	atomic_ops_unlock(flags);
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	atomic_ops_lock(flags);						\
+	v->counter c_op i;						\
+	atomic_ops_unlock(flags);					\
 }
 
-static inline void atomic_sub(int i, atomic_t *v)
-{
-	unsigned long flags;
-
-	atomic_ops_lock(flags);
-	v->counter -= i;
-	atomic_ops_unlock(flags);
+#define ATOMIC_OP_RETURN(op, c_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	unsigned long temp;						\
+									\
+	atomic_ops_lock(flags);						\
+	temp = v->counter;						\
+	temp c_op i;							\
+	v->counter = temp;						\
+	atomic_ops_unlock(flags);					\
+									\
+	return temp;							\
 }
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	unsigned long temp;
-
-	atomic_ops_lock(flags);
-	temp = v->counter;
-	temp += i;
-	v->counter = temp;
-	atomic_ops_unlock(flags);
-
-	return temp;
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long flags;
-	unsigned long temp;
-
-	atomic_ops_lock(flags);
-	temp = v->counter;
-	temp -= i;
-	v->counter = temp;
-	atomic_ops_unlock(flags);
+#endif /* !CONFIG_ARC_HAS_LLSC */
 
-	return temp;
-}
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned long flags;
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+ATOMIC_OP(and, &=, and)
 
-	atomic_ops_lock(flags);
-	*addr &= ~mask;
-	atomic_ops_unlock(flags);
-}
+#define atomic_clear_mask(mask, v) atomic_and(~(mask), (v))
 
-#endif /* !CONFIG_ARC_HAS_LLSC */
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
 
 /**
  * __atomic_add_unless - add unless the number is a given value
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 3040359094d9..e22c11970b7b 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -27,7 +27,7 @@
  * 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)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 #if __LINUX_ARM_ARCH__ >= 6
@@ -37,84 +37,47 @@
  * 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;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic_add\n"
-"1:	ldrex	%0, [%3]\n"
-"	add	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-}
 
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic_add_return\n"
-"1:	ldrex	%0, [%3]\n"
-"	add	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "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;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic_sub\n"
-"1:	ldrex	%0, [%3]\n"
-"	sub	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-}
-
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic_sub_return\n"
-"1:	ldrex	%0, [%3]\n"
-"	sub	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "Ir" (i)
-	: "cc");
-
-	smp_mb();
-
-	return result;
+#define ATOMIC_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	prefetchw(&v->counter);						\
+	__asm__ __volatile__("@ atomic_" #op "\n"			\
+"1:	ldrex	%0, [%3]\n"						\
+"	" #asm_op "	%0, %0, %4\n"					\
+"	strex	%1, %0, [%3]\n"						\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	smp_mb();							\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic_" #op "_return\n"		\
+"1:	ldrex	%0, [%3]\n"						\
+"	" #asm_op "	%0, %0, %4\n"					\
+"	strex	%1, %0, [%3]\n"						\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "Ir" (i)					\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return result;							\
 }
 
 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
@@ -174,33 +137,29 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #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_OP(op, c_op, asm_op)					\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long flags;						\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	raw_local_irq_restore(flags);					\
+}									\
+
+#define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long flags;						\
+	int val;							\
+									\
+	raw_local_irq_save(flags);					\
+	v->counter c_op i;						\
+	val = v->counter;						\
+	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)
 {
@@ -228,6 +187,17 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #endif /* __LINUX_ARM_ARCH__ */
 
+#define ATOMIC_OPS(op, c_op, asm_op)					\
+	ATOMIC_OP(op, c_op, asm_op)					\
+	ATOMIC_OP_RETURN(op, c_op, asm_op)
+
+ATOMIC_OPS(add, +=, add)
+ATOMIC_OPS(sub, -=, sub)
+
+#undef ATOMIC_OPS
+#undef ATOMIC_OP_RETURN
+#undef ATOMIC_OP
+
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 #define atomic_inc(v)		atomic_add(1, v)
@@ -300,89 +270,60 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 }
 #endif
 
-static inline void atomic64_add(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic64_add\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%Q0, %Q0, %Q4\n"
-"	adc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
-}
-
-static inline long long atomic64_add_return(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic64_add_return\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%Q0, %Q0, %Q4\n"
-"	adc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
-
-	smp_mb();
-
-	return result;
-}
-
-static inline void atomic64_sub(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	prefetchw(&v->counter);
-	__asm__ __volatile__("@ atomic64_sub\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%Q0, %Q0, %Q4\n"
-"	sbc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
+#define ATOMIC64_OP(op, op1, op2)					\
+static inline void atomic64_##op(long long i, atomic64_t *v)		\
+{									\
+	long long result;						\
+	unsigned long tmp;						\
+									\
+	prefetchw(&v->counter);						\
+	__asm__ __volatile__("@ atomic64_" #op "\n"			\
+"1:	ldrexd	%0, %H0, [%3]\n"					\
+"	" #op1 " %Q0, %Q0, %Q4\n"					\
+"	" #op2 " %R0, %R0, %R4\n"					\
+"	strexd	%1, %0, %H0, [%3]\n"					\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+}									\
+
+#define ATOMIC64_OP_RETURN(op, op1, op2)				\
+static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
+{									\
+	long long result;						\
+	unsigned long tmp;						\
+									\
+	smp_mb();							\
+	prefetchw(&v->counter);						\
+									\
+	__asm__ __volatile__("@ atomic64_" #op "_return\n"		\
+"1:	ldrexd	%0, %H0, [%3]\n"					\
+"	" #op1 " %Q0, %Q0, %Q4\n"					\
+"	" #op2 " %R0, %R0, %R4\n"					\
+"	strexd	%1, %0, %H0, [%3]\n"					\
+"	teq	%1, #0\n"						\
+"	bne	1b"							\
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)		\
+	: "r" (&v->counter), "r" (i)					\
+	: "cc");							\
+									\
+	smp_mb();							\
+									\
+	return result;							\
 }
 
-static inline long long atomic64_sub_return(long long i, atomic64_t *v)
-{
-	long long result;
-	unsigned long tmp;
-
-	smp_mb();
-	prefetchw(&v->counter);
-
-	__asm__ __volatile__("@ atomic64_sub_return\n"
-"1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%Q0, %Q0, %Q4\n"
-"	sbc	%R0, %R0, %R4\n"
-"	strexd	%1, %0, %H0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
-	: "r" (&v->counter), "r" (i)
-	: "cc");
+#define ATOMIC64_OPS(op, op1, op2)					\
+	ATOMIC64_OP(op, op1, op2)					\
+	ATOMIC64_OP_RETURN(op, op1, op2)
 
-	smp_mb();
+ATOMIC64_OPS(add, adds, adc)
+ATOMIC64_OPS(sub, subs, sbc)
 
-	return result;
-}
+#undef ATOMIC64_OPS
+#undef ATOMIC64_OP_RETURN
+#undef ATOMIC64_OP
 
 static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
 					long long new)
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 65f1569ac96e..7047051ded40 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -35,7 +35,7 @@
  * 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)	(*(volatile int *)&(v)->counter)
+#define atomic_read(v)	ACCESS_ONCE((v)->counter)
 #define atomic_set(v,i)	(((v)->counter) = (i))
 
 /*
@@ -43,69 +43,51 @@
  * 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:	ldxr	%w0, %2\n"
-"	add	%w0, %w0, %w3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
-}
-
-static inline int atomic_add_return(int i, atomic_t *v)
-{
-	unsigned long tmp;
-	int result;
-
-	asm volatile("// atomic_add_return\n"
-"1:	ldxr	%w0, %2\n"
-"	add	%w0, %w0, %w3\n"
-"	stlxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i)
-	: "memory");
-
-	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:	ldxr	%w0, %2\n"
-"	sub	%w0, %w0, %w3\n"
-"	stxr	%w1, %w0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)
-	: "Ir" (i));
+#define ATOMIC_OP(op, asm_op)						\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "\n"				\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i));							\
+}									\
+
+#define ATOMIC_OP_RETURN(op, asm_op)					\
+static inline int atomic_##op##_return(int i, atomic_t *v)		\
+{									\
+	unsigned long tmp;						\
+	int result;							\
+									\
+	asm volatile("// atomic_" #op "_return\n"			\
+"1:	ldxr	%w0, %2\n"						\
+"	" #asm_op "	%w0, %w0, %w3\n"				\
+"	stlxr	%w1, %w0, %2\n"						\
+"	cbnz	%w1, 1b"						\
+	: "=&r" (result), "=&r" (tmp), "+Q" (v->counter)		\
+	: "Ir" (i)							\
+	: "memory");							\
+									\
+	smp_mb();							\
+	return result;							\
 }
 
-static inline int atomic_sub_return(int i, atomic_t *v)
-{
-	unsigned lon